diff --git a/.gitignore b/.gitignore
index 4879d82bb2c5ce51f43be6ea9fb183cd6e28097c..df134f3d8f4289b954a8b3f7bfbc138b6be6f80e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -26,3 +26,5 @@ output/
# MacOS
.DS_Store
+#Cluster
+run/
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index c5a86242d11893c2d1a7e876bee96665be2b0f3c..07ff3f6e3f200a4a2cde0d6fc6499b0cd8abb23d 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -3,6 +3,7 @@ image: irmb/virtualfluids-python-deps:latest
stages:
- build
- build_python
+ - container_upload
- test
- benchmark
- analyze
@@ -33,27 +34,25 @@ stages:
paths:
- $BUILD_FOLDER
- before_script:
- - export CC=gcc
- - export CXX=g++
+ script:
- export CCACHE_BASEDIR=$CI_PROJECT_DIR
- export CCACHE_DIR=$CI_PROJECT_DIR/cache
- - ccache -s
-
-
- script:
+ - export CCACHE_COMPILERCHECK=content
+ - ccache --zero-stats
+ - ccache --show-stats
- $CXX --version
- $CC --version
- cmake --version
- mpirun --version
- mkdir -p $CI_PROJECT_DIR/$BUILD_FOLDER
- cd $CI_PROJECT_DIR/$BUILD_FOLDER
- - cmake ..
+ - rm -r -f ./*
+ - cmake .. -LAH
--preset=all_make_ccache
-DBUILD_WARNINGS_AS_ERRORS=ON
-DCMAKE_CUDA_ARCHITECTURES=60
- - cmake . -LAH
- make -j4
+ - ccache --show-stats
variables:
BUILD_FOLDER: "build"
@@ -62,8 +61,11 @@ stages:
gcc_9:
extends: .gnu_build_template
-###############################################################################
+ before_script:
+ - export CC=gcc
+ - export CXX=g++
+###############################################################################
clang_10:
extends: .gnu_build_template
@@ -71,42 +73,6 @@ clang_10:
- export CC=clang
- export CXX=clang++
-
-###############################################################################
-gcc_9_rebuild:
- stage: build
-
- image: irmb/virtualfluids-deps-ubuntu20.04
-
- tags:
- - gpu
- - linux
-
- before_script:
- - export CCACHE_BASEDIR=$CI_PROJECT_DIR
- - export CCACHE_DIR=$CI_PROJECT_DIR/cache
- - ccache -s
-
- script:
- - mkdir -p $CI_PROJECT_DIR/build
- - cd $CI_PROJECT_DIR/build
- - rm -r -f ./*
- - cmake ..
- --preset=all_make_ccache
- -DBUILD_WARNINGS_AS_ERRORS=ON
- -DCMAKE_CUDA_ARCHITECTURES=60
- - make -j4 2>&1 | tee gcc_warnings.txt
- - ccache -s
-
- artifacts:
- paths:
- - build/gcc_warnings.txt
-
- cache:
- key: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
- paths:
- - $CI_PROJECT_DIR/cache
-
###############################################################################
msvc_16:
stage: build
@@ -132,7 +98,7 @@ msvc_16:
- cd $CI_PROJECT_DIR
- md -force $env:BUILD_FOLDER
- cd $env:BUILD_FOLDER
- - cmake .. --preset=all_msvc -DBUILD_WARNINGS_AS_ERRORS=ON
+ - cmake .. --preset=all_msvc -DCMAKE_CUDA_ARCHITECTURES=61 -DBUILD_WARNINGS_AS_ERRORS=ON
- MSBuild.exe VirtualFluids.sln /property:Configuration=$env:BUILD_CONFIGURATION /verbosity:minimal /maxcpucount:4
cache:
@@ -145,30 +111,10 @@ msvc_16:
paths:
- $CI_PROJECT_DIR/$env:BUILD_FOLDER/
-###############################################################################
-build_singularity_image:
- stage: build
-
- tags:
- - priviliged
- - linux
-
- rules:
- - if: $CI_COMMIT_TAG
-
- artifacts:
- paths:
- - Containers/VirtualFluidsOpenMPI.sif
-
- script:
- - singularity build --fakeroot Containers/VirtualFluidsOpenMPI.sif Containers/VirtualFluidsOpenMPI.def
- - ls -sh Containers/VirtualFluidsOpenMPI.sif
-
###############################################################################
## Build Python ##
###############################################################################
-
gcc_9_python:
stage: build_python
@@ -190,7 +136,27 @@ gcc_9_python:
- export CCACHE_DIR=$CI_PROJECT_DIR/cache
script:
- - python3 setup.py bdist_wheel
+ - python3 setup.py bdist_wheel build_ext --build-temp=build
+
+###############################################################################
+## Container Upload ##
+###############################################################################
+build_singularity_image:
+ stage: container_upload
+
+ needs:
+ - gcc_9_python
+
+ tags:
+ - linux
+ - privileged
+
+ rules:
+ - if: $CI_COMMIT_TAG
+
+ script:
+ - singularity build Containers/VirtualFluidsPython.sif Containers/VirtualFluidsPython.def
+ - singularity push --docker-username "${CI_REGISTRY_USER}" --docker-password "${CI_REGISTRY_PASSWORD}" Containers/VirtualFluidsPython.sif oras://"$CI_REGISTRY_IMAGE"/"$CI_PROJECT_NAME":"$CI_COMMIT_TAG"
###############################################################################
## Tests ##
@@ -239,6 +205,47 @@ gcc_9_python_bindings_test:
script:
- python3 -m unittest discover -s Python -v
+###############################################################################
+gcc_9_python_slurm_test:
+ stage: test
+
+ needs: ["gcc_9_python"]
+
+ rules:
+ - if: $PHOENIX_PRIVATE_KEY
+
+ tags:
+ - linux
+ - privileged
+
+ variables:
+ SSH_KEY: "$PHOENIX_PRIVATE_KEY"
+ HOST: "$PHOENIX_HOSTNAME"
+ USER: "$PHOENIX_USER"
+
+ before_script:
+ - 'command -v ssh-agent >/dev/null || ( apt-get update -y && apt-get install openssh-client -y )'
+ - apt-get install -y rsync
+ - mkdir -p ~/.ssh
+ - chmod 700 ~/.ssh
+ - eval $(ssh-agent -s)
+ - echo "$SSH_KEY" | tr -d '\r' | ssh-add -
+ - echo $SSH_KEY >> ansible/private_key
+ - ssh-keyscan -t rsa $HOST >> ~/.ssh/known_hosts
+ - ssh $USER@$HOST "rm -rf output-*"
+ - ssh $USER@$HOST "rm -f *.out"
+ - pip3 install git+git://github.com/SvenMarcus/ssh-slurm-runner
+
+ script:
+ - singularity build PoiseuilleTestContainer.sif Python/SlurmTests/poiseuille/PoiseuilleTestContainer.def
+ - scp PoiseuilleTestContainer.sif $USER@$HOST:PoiseuilleTestContainer.sif
+ - scp Python/SlurmTests/poiseuille/slurm.job $USER@$HOST:slurm.job
+ - python3 -m ssh_slurm_runner slurm.job --host $HOST --user $USER --keyfile ansible/private_key
+ - ssh $USER@$HOST "rm -rf output-*"
+ - ssh $USER@$HOST "rm -f *.out"
+ - ssh $USER@$HOST "rm PoiseuilleTestContainer.sif"
+ - ssh $USER@$HOST "rm slurm.job"
+
###############################################################################
## Benchmark ##
###############################################################################
@@ -297,6 +304,7 @@ gpu_numerical_tests:
- $CI_PROJECT_DIR/cache
artifacts:
+ expire_in: 1 hrs
paths:
- $CI_PROJECT_DIR/numerical_tests_gpu_results.txt
@@ -389,11 +397,10 @@ cppcheck:
- cd $CI_PROJECT_DIR
- cppcheck --version
- cppcheck src --enable=all --xml 2> cppcheck.xml
- - cppcheck-htmlreport --file=cppcheck.xml --report-dir=html_report --source-dir=.
artifacts:
+ expire_in: 1 week
paths:
- - html_report/
- cppcheck.xml
###############################################################################
@@ -421,6 +428,7 @@ lizard:
- lizard -l cpp src/ > lizard.txt --warnings_only --ignore_warnings 400
artifacts:
+ expire_in: 1 week
paths:
- lizard.txt
@@ -456,9 +464,9 @@ gcov_gcc_9:
- gcovr -r $CI_PROJECT_DIR -k build -f "src" --print-summary --html coverage/coverage.html --html-details --xml coverage/coverage.xml
artifacts:
+ expire_in: 1 week
paths:
- coverage/
- - build/
reports:
cobertura: coverage/coverage.xml
@@ -480,6 +488,8 @@ clang-tidy:
needs: []
+ allow_failure: true
+
before_script:
- run-clang-tidy -h
@@ -494,10 +504,35 @@ clang-tidy:
- run-clang-tidy -quiet > clangtidy.txt
artifacts:
+ when: always
+ expire_in: 1 week
paths:
- build/clangtidy.txt
- build/compile_commands.json
+
+###############################################################################
+# doxgen
+doxygen:
+ stage: analyze
+
+ only:
+ - develop@irmb/VirtualFluids_dev
+
+ needs: []
+
+ image: alpine
+
+ script:
+ - apk update && apk add doxygen
+ - doxygen docs/Doxyfile
+
+ artifacts:
+ expire_in: 1 week
+ paths:
+ - docs/build/
+
+
###############################################################################
## Deploy ##
###############################################################################
@@ -550,10 +585,10 @@ vf_wheel_to_jupyterhub:
needs: ["gcc_9_python", "gcc_9_unit_tests", "gcc_9_python_bindings_test"]
variables:
- HOST: "finrod.irmb.bau.tu-bs.de"
- SSH_KEY: "$SSH_PRIVATE_KEY_JUPYTER_HOST_AT_FINROD"
- REMOTE_USER: "jupyter_host"
- jupyter_host: "jupyter_host"
+ HOST: "gitlab-runner01.irmb.bau.tu-bs.de"
+ SSH_KEY: "$SSH_PRIVATE_KEY"
+ REMOTE_USER: "runner"
+ jupyter_host: "runner"
script:
- ansible-playbook -i ansible/hosts.cfg -u $REMOTE_USER ansible/playbook_jupyter_update.yml
@@ -574,7 +609,7 @@ sonar-scanner:
variables:
SONAR_HOST_URL: "http://gitlab-runner01.irmb.bau.tu-bs.de/sonarqube/"
- needs: ["cppcheck","clang-tidy","gcov_gcc_9","gcc_9_rebuild"]
+ needs: ["cppcheck","clang-tidy","gcov_gcc_9"]
before_script:
- cd /tmp
diff --git a/AUTHORS.md b/AUTHORS.md
index aca25898d44f5d2f72ea8f018f54546197c301e1..00a5410811196462d6f808036be7feb5e74a102d 100644
--- a/AUTHORS.md
+++ b/AUTHORS.md
@@ -1,24 +1,25 @@
-AUTHORS
-============
-
+# AUTHORS
VF has been developed essentially over the last fifteen years by various researchers at IRMB including (in alphabetical order):
-
-Dr. Benjamin Ahrenholz
-M. Sc. Hussein Alihussein
-Dr. Sebastian Bindick
-J.Prof. Dr. Martin Geier
-Dr. Sebastian Geller
-Dr. Ehsan Goraki Fard
-Dr. Jan Hegewald
-Dr. Christian Janßen
-M. Sc. Konstantin Kutscher
-M. Sc. Stephan Lenz
-Dr. Jan Linxweiler
-M. Sc. Sören Peters
-Dr. Hesameddin Safari
-Dr. Martin Schönherr
-Dipl.-Ing. Maik Stiebler
-Dr. Sören Textor (aka Freudiger)
-PD Dr. Jonas Tölke
-Dr. Sonja Uphoff
+Dr. Benjamin Ahrenholz
+M. Sc. Hussein Alihussein
+Dr. Sebastian Bindick
+B. Sc. Aileen Brendel
+J.Prof. Dr. Martin Geier
+Dr. Sebastian Geller
+Dr. Ehsan Goraki Fard
+Dr. Jan Hegewald
+Dr. Christian Janßen
+M. Sc. Konstantin Kutscher
+M. Sc. Stephan Lenz
+Dr. Jan Linxweiler
+B. Sc. Lennard Lux
+B. Sc. Sven Marcus
+M. Sc. Sören Peters
+Dr. Hesameddin Safari
+Dr. Martin Schönherr
+Dipl.-Ing. Maik Stiebler
+Dr. Sören Textor (aka Freudiger)
+PD Dr. Jonas Tölke
+Dr. Sonja Uphoff
+B. Sc. Anna Wellmann
\ No newline at end of file
diff --git a/CMake/VirtualFluidsMacros.cmake b/CMake/VirtualFluidsMacros.cmake
index 23d5029d2dff46076c27158e4f15d0375bf8565f..2c2bc1d650e5e2c402f34a1a2547b9fa6f5e063b 100644
--- a/CMake/VirtualFluidsMacros.cmake
+++ b/CMake/VirtualFluidsMacros.cmake
@@ -131,18 +131,18 @@ function(vf_add_library)
#################################################################
### ADD TARGET ###
#################################################################
- IF(${ARG_BUILDTYPE} MATCHES binary)
- ADD_EXECUTABLE(${library_name} ${MY_SRCS} )
+ if(${ARG_BUILDTYPE} MATCHES binary)
+ add_executable(${library_name} ${MY_SRCS} )
groupTarget(${library_name} ${appFolder})
- ELSEIF(${ARG_BUILDTYPE} MATCHES shared)
- ADD_LIBRARY(${library_name} SHARED ${MY_SRCS} )
+ elseif(${ARG_BUILDTYPE} MATCHES shared)
+ add_library(${library_name} SHARED ${MY_SRCS} )
groupTarget(${library_name} ${libraryFolder})
- ELSEIF(${ARG_BUILDTYPE} MATCHES static)
- ADD_LIBRARY(${library_name} STATIC ${MY_SRCS} )
+ elseif(${ARG_BUILDTYPE} MATCHES static)
+ add_library(${library_name} STATIC ${MY_SRCS} )
groupTarget(${library_name} ${libraryFolder})
- ELSE()
- MESSAGE(FATAL_ERROR "build_type=${ARG_BUILDTYPE} doesn't match BINARY, SHARED or STATIC")
- ENDIF()
+ else()
+ message(FATAL_ERROR "build_type=${ARG_BUILDTYPE} doesn't match BINARY, SHARED or STATIC")
+ endif()
# Set the output directory for build artifacts
set_target_properties(${library_name}
@@ -152,6 +152,21 @@ function(vf_add_library)
ARCHIVE_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/lib"
PDB_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/bin")
+ # link time optimization
+ if(BUILD_VF_LTO)
+ if(NOT ${ARG_BUILDTYPE} MATCHES binary)
+ include(CheckIPOSupported)
+ check_ipo_supported(RESULT ipo_supported OUTPUT ipo_error LANGUAGES CXX)
+
+ if( ipo_supported )
+ status_lib("IPO / LTO enabled")
+ set_target_properties(${library_name} PROPERTIES INTERPROCEDURAL_OPTIMIZATION TRUE)
+ else()
+ status_lib("IPO / LTO not supported: <${ipo_error}>")
+ endif()
+ endif()
+ endif()
+
# clang-tidy
if(BUILD_VF_CLANG_TIDY)
find_program(CLANG_TIDY_PROGRAM NAMES clang-tidy)
@@ -286,6 +301,7 @@ function(vf_add_tests)
# link googlemock
linkGMOCK()
+ # add the target to ctest
gtest_add_tests(TARGET ${library_test_name})
endfunction()
diff --git a/CMake/cmake_config_files/CSE01.config.cmake b/CMake/cmake_config_files/CSE01.config.cmake
index baa0f94981c2e9f9ac05b62468311f4bead32ff3..cad3f60ce31edac1069d1edce3fdd43b49a72b6e 100644
--- a/CMake/cmake_config_files/CSE01.config.cmake
+++ b/CMake/cmake_config_files/CSE01.config.cmake
@@ -2,22 +2,22 @@
#################################################################################
# BOOST
#################################################################################
-SET(BOOST_VERSION "1.60.0")
-SET(BOOST_ROOT "d:/boost/boost_1_60_0")
-SET(BOOST_DIR ${BOOST_ROOT})
-SET(BOOST_LIBRARYDIR ${BOOST_ROOT}"/stageMSVC64/lib")
+#SET(BOOST_VERSION "1.60.0")
+#SET(BOOST_ROOT "d:/boost/boost_1_60_0")
+#SET(BOOST_DIR ${BOOST_ROOT})
+#SET(BOOST_LIBRARYDIR ${BOOST_ROOT}"/stageMSVC64/lib")
#################################################################################
#################################################################################
# METIS
#################################################################################
-IF(${USE_METIS})
- SET(METIS_INCLUDEDIR "d:/metis-5.1.0/include")
- SET(METIS_DEBUG_LIBRARY "d:/metis-5.1.0/build/libmetis/Debug/metis.lib")
- SET(METIS_RELEASE_LIBRARY "d:/metis-5.1.0/build/libmetis/Release/metis.lib")
-ENDIF()
+#IF(${USE_METIS})
+# SET(METIS_INCLUDEDIR "d:/metis-5.1.0/include")
+# SET(METIS_DEBUG_LIBRARY "d:/metis-5.1.0/build/libmetis/Debug/metis.lib")
+# SET(METIS_RELEASE_LIBRARY "d:/metis-5.1.0/build/libmetis/Release/metis.lib")
+#ENDIF()
#################################################################################
# VTK
#################################################################################
-set(VTK_DIR "d:/tools/VTK/build/VTK-8.2.0")
+#set(VTK_DIR "d:/tools/VTK/build/VTK-8.2.0")
#################################################################################
\ No newline at end of file
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 9685f4de572b180fa32766f6a15b87f4a8d3a922..d74febdac96544fa6f50b65602392d3c44a5ca10 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -51,6 +51,8 @@ option(BUILD_VF_INCLUDE_WHAT_YOU_USE "Add IWYU to the targets" OFF)
option(BUILD_VF_CPPCHECK "Add cppcheck to the targets" OFF)
option(BUILD_VF_COVERAGE "Add the -coverage compiler flag." OFF)
+option(BUILD_CUDA_LTO "Enables the cuda link optimization." OFF)
+
option(BUILD_SHARED_LIBS "" OFF)
option(BUILD_WARNINGS_AS_ERRORS "" OFF)
@@ -94,14 +96,36 @@ if(BUILD_VF_GPU)
set(CMAKE_CUDA_STANDARD_REQUIRED TRUE)
+ enable_language(CUDA)
+
+
if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
message(WARNING "CMAKE_CUDA_ARCHITECTURES was not defined and is set to 30 (CUDA support until 10.1 only).")
set(CMAKE_CUDA_ARCHITECTURES 30)
endif()
+
+ if(BUILD_CUDA_LTO)
+
+ if(CMAKE_CUDA_ARCHITECTURES LESS 50)
+ message(FATAL_ERROR "CUDA Link time optimization requires CUDA 11.2 and CC 5.0.")
+ else()
+
+ set(CMAKE_CUDA_FLAGS "-dlto -arch=sm_${CMAKE_CUDA_ARCHITECTURES}")
+ set(CMAKE_CUDA_ARCHITECTURES OFF)
+
+ list(APPEND VF_COMPILER_DEFINITION BUILD_CUDA_LTO)
+
+ endif()
+ endif()
+
+ set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --extended-lambda")
+
+ message("CMAKE_CUDA_FLAGS: ${CMAKE_CUDA_FLAGS}")
message("CUDA Architecture: ${CMAKE_CUDA_ARCHITECTURES}")
endif()
+
#################################################################################
# COMMON LIBRARIES
#################################################################################
@@ -119,6 +143,7 @@ find_package(MPI REQUIRED)
add_subdirectory(src/basics)
+add_subdirectory(src/lbm)
#################################################################################
diff --git a/CMakePresets.json b/CMakePresets.json
index 6863446af85b177bb4dc99eed475aa52f4d50269..6527d5c1f4feba60064b1473fa12dbb2331279aa 100644
--- a/CMakePresets.json
+++ b/CMakePresets.json
@@ -1,133 +1,179 @@
{
- "version": 1,
- "cmakeMinimumRequired": {
- "major": 3,
- "minor": 19,
- "patch": 0
- },
- "configurePresets": [
- {
- "name": "default",
- "hidden": true,
- "binaryDir": "${sourceDir}/build/",
- "cacheVariables": {
- "BUILD_VF_UNIT_TESTS": "ON"
- }
- },
- {
- "name": "default_make",
- "inherits": "default",
- "hidden": true,
- "generator": "Unix Makefiles"
- },
- {
- "name": "default_ccache_make",
- "inherits": "default_make",
- "hidden": true,
- "cacheVariables": {
- "CMAKE_CXX_COMPILER_LAUNCHER": "ccache",
- "CMAKE_CUDA_COMPILER_LAUNCHER": "ccache",
- "CMAKE_C_COMPILER_LAUNCHER": "ccache"
- }
- },
- {
- "name": "default_msvc",
- "inherits": "default",
- "hidden": true,
- "generator": "Visual Studio 16 2019",
- "architecture": "x64"
- },
- {
- "name": "default_cpu",
- "hidden": true,
- "description": "CPU build of VirtualFluids",
- "cacheVariables": {
- "BUILD_VF_CPU": "ON"
- }
- },
- {
- "name": "default_gpu",
- "hidden": true,
- "description": "GPU build of VirtualFluids",
- "cacheVariables": {
- "BUILD_VF_GPU": "ON"
- }
- },
- {
- "name": "default_gpu_numerical_tests",
- "inherits": ["default_gpu"],
- "hidden": true,
- "description": "GPU numerical tests of VirtualFluids",
- "cacheVariables": {
- "BUILD_VF_DOUBLE_ACCURACY": "ON",
- "BUILD_NUMERIC_TESTS": "ON"
- }
- },
- {
- "name": "default_all",
- "hidden": true,
- "description": "All build of VirtualFluids",
- "inherits": ["default_cpu", "default_gpu"]
- },
- {
- "name": "cpu_make",
- "inherits": ["default_make", "default_cpu"],
- "displayName": "cpu make configuration"
- },
- {
- "name": "cpu_make_ccache",
- "inherits": ["default_ccache_make", "default_cpu"],
- "displayName": "cpu ccache make configuration"
- },
- {
- "name": "cpu_msvc",
- "inherits": ["default_msvc", "default_cpu"],
- "displayName": "cpu msvc configuration"
- },
- {
- "name": "gpu_make",
- "inherits": ["default_make", "default_gpu"],
- "displayName": "gpu make configuration"
- },
- {
- "name": "gpu_make_ccache",
- "inherits": ["default_ccache_make", "default_gpu"],
- "displayName": "gpu ccache make configuration"
- },
- {
- "name": "gpu_msvc",
- "inherits": ["default_msvc", "default_gpu"],
- "displayName": "gpu msvc configuration"
- },
- {
- "name": "all_make",
- "inherits": ["default_make", "default_all"],
- "displayName": "all make configuration"
- },
- {
- "name": "all_make_ccache",
- "inherits": ["default_ccache_make", "default_all"],
- "displayName": "all ccache make configuration"
- },
- {
- "name": "all_msvc",
- "inherits": ["default_msvc", "default_all"],
- "displayName": "all msvc configuration"
- },
- {
- "name": "gpu_numerical_tests_make",
- "inherits": ["default_make", "default_gpu_numerical_tests"],
- "displayName": "gpu numerical tests make configuration"
- },
- {
- "name": "gpu_numerical_tests_ccache_make",
- "inherits": ["default_ccache_make", "default_gpu_numerical_tests"],
- "displayName": "gpu numerical tests ccache make configuration"
- },
- {
- "name": "gpu_numerical_tests_msvc",
- "inherits": ["default_msvc", "default_gpu_numerical_tests"],
- "displayName": "gpu numerical tests msvc configuration"
- }
- ]
+ "version": 1,
+ "cmakeMinimumRequired": {
+ "major": 3,
+ "minor": 19,
+ "patch": 0
+ },
+ "configurePresets": [
+ {
+ "name": "default",
+ "hidden": true,
+ "binaryDir": "${sourceDir}/build/",
+ "cacheVariables": {
+ "BUILD_VF_UNIT_TESTS": "ON"
+ }
+ },
+ {
+ "name": "default_make",
+ "inherits": "default",
+ "hidden": true,
+ "generator": "Unix Makefiles"
+ },
+ {
+ "name": "default_ccache_make",
+ "inherits": "default_make",
+ "hidden": true,
+ "cacheVariables": {
+ "CMAKE_CXX_COMPILER_LAUNCHER": "ccache",
+ "CMAKE_CUDA_COMPILER_LAUNCHER": "ccache",
+ "CMAKE_C_COMPILER_LAUNCHER": "ccache"
+ }
+ },
+ {
+ "name": "default_msvc",
+ "inherits": "default",
+ "hidden": true,
+ "generator": "Visual Studio 16 2019",
+ "architecture": "x64"
+ },
+ {
+ "name": "default_cpu",
+ "hidden": true,
+ "description": "CPU build of VirtualFluids",
+ "cacheVariables": {
+ "BUILD_VF_CPU": "ON",
+ "BUILD_VF_DOUBLE_ACCURACY": "ON"
+ }
+ },
+ {
+ "name": "default_gpu",
+ "hidden": true,
+ "description": "GPU build of VirtualFluids",
+ "cacheVariables": {
+ "BUILD_VF_GPU": "ON",
+ "BUILD_VF_DOUBLE_ACCURACY": "OFF"
+ }
+ },
+ {
+ "name": "default_gpu_numerical_tests",
+ "inherits": [
+ "default_gpu"
+ ],
+ "hidden": true,
+ "description": "GPU numerical tests of VirtualFluids",
+ "cacheVariables": {
+ "BUILD_VF_DOUBLE_ACCURACY": "ON",
+ "BUILD_NUMERIC_TESTS": "ON"
+ }
+ },
+ {
+ "name": "default_all",
+ "hidden": true,
+ "description": "All build of VirtualFluids",
+ "inherits": [
+ "default_cpu",
+ "default_gpu"
+ ],
+ "cacheVariables": {
+ "BUILD_VF_DOUBLE_ACCURACY": "ON"
+ }
+ },
+ {
+ "name": "cpu_make",
+ "inherits": [
+ "default_make",
+ "default_cpu"
+ ],
+ "displayName": "cpu make configuration"
+ },
+ {
+ "name": "cpu_make_ccache",
+ "inherits": [
+ "default_ccache_make",
+ "default_cpu"
+ ],
+ "displayName": "cpu ccache make configuration"
+ },
+ {
+ "name": "cpu_msvc",
+ "inherits": [
+ "default_msvc",
+ "default_cpu"
+ ],
+ "displayName": "cpu msvc configuration"
+ },
+ {
+ "name": "gpu_make",
+ "inherits": [
+ "default_make",
+ "default_gpu"
+ ],
+ "displayName": "gpu make configuration"
+ },
+ {
+ "name": "gpu_make_ccache",
+ "inherits": [
+ "default_ccache_make",
+ "default_gpu"
+ ],
+ "displayName": "gpu ccache make configuration"
+ },
+ {
+ "name": "gpu_msvc",
+ "inherits": [
+ "default_msvc",
+ "default_gpu"
+ ],
+ "displayName": "gpu msvc configuration"
+ },
+ {
+ "name": "all_make",
+ "inherits": [
+ "default_make",
+ "default_all"
+ ],
+ "displayName": "all make configuration"
+ },
+ {
+ "name": "all_make_ccache",
+ "inherits": [
+ "default_ccache_make",
+ "default_all"
+ ],
+ "displayName": "all ccache make configuration"
+ },
+ {
+ "name": "all_msvc",
+ "inherits": [
+ "default_msvc",
+ "default_all"
+ ],
+ "displayName": "all msvc configuration"
+ },
+ {
+ "name": "gpu_numerical_tests_make",
+ "inherits": [
+ "default_make",
+ "default_gpu_numerical_tests"
+ ],
+ "displayName": "gpu numerical tests make configuration"
+ },
+ {
+ "name": "gpu_numerical_tests_ccache_make",
+ "inherits": [
+ "default_ccache_make",
+ "default_gpu_numerical_tests"
+ ],
+ "displayName": "gpu numerical tests ccache make configuration"
+ },
+ {
+ "name": "gpu_numerical_tests_msvc",
+ "inherits": [
+ "default_msvc",
+ "default_gpu_numerical_tests"
+ ],
+ "displayName": "gpu numerical tests msvc configuration"
+ }
+ ]
}
diff --git a/Containers/VirtualFluidsPython.def b/Containers/VirtualFluidsPython.def
new file mode 100644
index 0000000000000000000000000000000000000000..d54066bc634cf25f4340b1e659eae72515467fa8
--- /dev/null
+++ b/Containers/VirtualFluidsPython.def
@@ -0,0 +1,33 @@
+BootStrap: docker
+From: ubuntu:20.04
+
+%files
+ Python Python
+ dist dist
+
+
+%post
+ export DEBIAN_FRONTEND=noninteractive
+ apt-get update && \
+ apt-get install -y \
+ build-essential \
+ cmake=3.16.3-1ubuntu1 \
+ python3 \
+ python3-dev \
+ python3-pip \
+ mpich \
+ libomp-dev
+
+ pip3 install setuptools wheel $(find dist/*.whl)
+
+%environment
+ export PYTHONPATH=/Python
+
+%runscript
+ python3 /Python/liddrivencavity/simulation.py
+
+%appenv poiseuille
+ export PYTHONPATH=Python
+
+%apprun poisueille
+ python3 /Python/poiseuille/poiseuille_hpc.py
diff --git a/Python/SlurmTests/poiseuille/PoiseuilleTestContainer.def b/Python/SlurmTests/poiseuille/PoiseuilleTestContainer.def
new file mode 100644
index 0000000000000000000000000000000000000000..a3836e7906b9be66ec79f68bf53ccc079db9d9ef
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/PoiseuilleTestContainer.def
@@ -0,0 +1,42 @@
+BootStrap: docker
+From: ubuntu:20.04
+
+%files
+ 3rdParty 3rdParty
+ apps apps
+ CMake CMake
+ Python Python
+ src src
+ CMakeLists.txt CMakeLists.txt
+ cpu.cmake cpu.cmake
+ gpu.cmake gpu.cmake
+ setup.py setup.py
+ pyproject.toml pyproject.toml
+
+
+%post
+ export DEBIAN_FRONTEND=noninteractive
+ apt-get update && \
+ apt-get install -y \
+ build-essential \
+ cmake=3.16.3-1ubuntu1 \
+ python3 \
+ python3-dev \
+ python3-pip \
+ mpich \
+ libomp-dev \
+ libgl1
+
+ pip3 install setuptools wheel numpy scipy pyvista
+
+ export PYTHONPATH=Python
+ python3 /setup.py install
+
+%environment
+ export PYTHONPATH=/Python
+
+%apprun testcase
+ python3 /Python/SlurmTests/poiseuille/simulation_runner.py
+
+%apprun evaluate
+ python3 /Python/SlurmTests/poiseuille/evaluator.py
\ No newline at end of file
diff --git a/Python/SlurmTests/poiseuille/evaluator.py b/Python/SlurmTests/poiseuille/evaluator.py
new file mode 100644
index 0000000000000000000000000000000000000000..74602846b67bb82f7e3c3d3ca3015fbe00a63041
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/evaluator.py
@@ -0,0 +1,20 @@
+import numpy as np
+import scipy.stats as stats
+import errors
+from SlurmTests.poiseuille.result_collector import collect_results
+from SlurmTests.poiseuille.settings import Scaling
+
+analytical_results, numerical_results = collect_results()
+normalized_l2_errors = [errors.normalized_l2_error(analytical, numerical)
+ for analytical, numerical in zip(analytical_results, numerical_results)]
+
+nodes_in_x3_per_run = []
+for simulation_run in range(0, 3):
+ grid_params, _, _, _ = Scaling.configuration_for_scale_level(simulation_run)
+ nodes_in_x3_per_run.append(grid_params.number_of_nodes_per_direction[2])
+
+nodes_as_log = [np.log10(node) for node in nodes_in_x3_per_run]
+l2_norms_as_log = [np.log10(l2) for l2 in normalized_l2_errors]
+res = stats.linregress(nodes_as_log, l2_norms_as_log)
+
+assert res.slope <= -2, f"Expected slope of l2 error to be <= -2, but was {res.slope}"
diff --git a/Python/SlurmTests/poiseuille/result_collector.py b/Python/SlurmTests/poiseuille/result_collector.py
new file mode 100644
index 0000000000000000000000000000000000000000..06efa481c8c010647531426f2af2bec2c2d7eaee
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/result_collector.py
@@ -0,0 +1,73 @@
+from typing import Collection, List
+
+import pyvista as pv
+from poiseuille.analytical import PoiseuilleSettings, poiseuille_at_heights
+from vtk_utilities import vertical_column_from_mesh, get_values_from_indices
+from SlurmTests.poiseuille.settings import Scaling
+
+
+def get_output_file_name(output_folder, runtime_params):
+ timesteps = runtime_params.number_of_timesteps
+ file_name = f"{output_folder}/mq/mq{timesteps}/mq0_{timesteps}.bin.vtu"
+
+ return file_name
+
+
+def get_mesh_for_last_timestep(output_folder, runtime_params):
+ file_name_of_last_timestep = get_output_file_name(output_folder, runtime_params)
+ mesh_of_last_timestep = pv.read(file_name_of_last_timestep)
+ return mesh_of_last_timestep
+
+
+def get_heights_from_indices(mesh, indices):
+ return [mesh.points[index][2] for index in indices]
+
+
+def get_heights(output_folder, runtime_params):
+ mesh_of_last_timestep = get_mesh_for_last_timestep(output_folder, runtime_params)
+ column_indices = vertical_column_from_mesh(mesh_of_last_timestep)
+ heights = get_heights_from_indices(mesh_of_last_timestep, column_indices)
+ return heights
+
+
+def get_numerical_results(runtime_params, output_folder):
+ mesh_of_last_timestep = get_mesh_for_last_timestep(output_folder, runtime_params)
+ velocities_in_x_direction = mesh_of_last_timestep.get_array("Vx")
+ column_indices = vertical_column_from_mesh(mesh_of_last_timestep)
+ numerical_results = get_values_from_indices(velocities_in_x_direction, column_indices)
+
+ return numerical_results
+
+
+def get_analytical_results(grid_params, physical_params, kernel, height_values):
+ channel_height = grid_params.number_of_nodes_per_direction[2]
+ settings = get_analytical_poiseuille_settings(channel_height, physical_params, kernel)
+ max_grid_height = channel_height * grid_params.node_distance
+ adjusted_height_values = [value / max_grid_height * channel_height for value in height_values]
+ analytical_results = poiseuille_at_heights(settings, adjusted_height_values)
+ return analytical_results
+
+
+def get_analytical_poiseuille_settings(height, physical_params, kernel):
+ settings = PoiseuilleSettings()
+ settings.height = height
+ settings.viscosity = physical_params.lattice_viscosity
+ settings.density = 1
+ settings.force = kernel.forcing_in_x1
+
+ return settings
+
+
+def collect_results() -> (List[List[float]], List[List[float]]):
+ analytical_results = []
+ numerical_results = []
+
+ for simulation_run in range(0, 3):
+ output_folder = f"output-{simulation_run}"
+ grid_params, physical_params, runtime_params, kernel = Scaling.configuration_for_scale_level(simulation_run)
+ heights = get_heights(output_folder, runtime_params)
+ analytical_results.append(
+ get_analytical_results(grid_params, physical_params, kernel, heights))
+ numerical_results.append(get_numerical_results(runtime_params, output_folder))
+
+ return analytical_results, numerical_results
diff --git a/Python/SlurmTests/poiseuille/settings.py b/Python/SlurmTests/poiseuille/settings.py
new file mode 100644
index 0000000000000000000000000000000000000000..f75c2b1d7133323880dd5520de0a96cb8fa87860
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/settings.py
@@ -0,0 +1,26 @@
+import os
+from acousticscaling import OneDirectionalAcousticScaling
+from pyfluids.kernel import LBMKernel, KernelType
+from pyfluids.parameters import RuntimeParameters, GridParameters, PhysicalParameters
+
+
+grid_params = GridParameters()
+grid_params.node_distance = 1
+grid_params.number_of_nodes_per_direction = [1, 1, 16]
+grid_params.blocks_per_direction = [1, 1, 4]
+grid_params.periodic_boundary_in_x1 = True
+grid_params.periodic_boundary_in_x2 = True
+
+physical_params = PhysicalParameters()
+physical_params.lattice_viscosity = 1e-4
+
+runtime_params = RuntimeParameters()
+runtime_params.number_of_threads = int(os.environ["PYFLUIDS_NUM_THREADS"])
+runtime_params.number_of_timesteps = 4_000_000
+runtime_params.timestep_log_interval = 1_000_000
+
+kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
+kernel.use_forcing = True
+kernel.forcing_in_x1 = 5e-10
+
+Scaling = OneDirectionalAcousticScaling(grid_params, physical_params, runtime_params, kernel)
diff --git a/Python/SlurmTests/poiseuille/simulation_runner.py b/Python/SlurmTests/poiseuille/simulation_runner.py
new file mode 100644
index 0000000000000000000000000000000000000000..0b75de40b6a8f11ccd76f97f2ed9d709dc5362dd
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/simulation_runner.py
@@ -0,0 +1,19 @@
+import os
+
+from SlurmTests.poiseuille.settings import Scaling
+from poiseuille.simulation import run_simulation
+from pyfluids.writer import Writer, OutputFormat
+
+
+scale_level = int(os.environ["PYFLUIDS_SCALE_LEVEL"])
+grid_params, physical_params, runtime_params, kernel = Scaling.configuration_for_scale_level(scale_level)
+
+writer = Writer()
+writer.output_format = OutputFormat.BINARY
+writer.output_path = "./output-" + str(scale_level)
+
+run_simulation(grid_params=grid_params,
+ physical_params=physical_params,
+ runtime_params=runtime_params,
+ kernel=kernel,
+ writer=writer)
diff --git a/Python/SlurmTests/poiseuille/slurm.job b/Python/SlurmTests/poiseuille/slurm.job
new file mode 100644
index 0000000000000000000000000000000000000000..488fc9a42f261d69a8212cff389721fdfb9cbf6e
--- /dev/null
+++ b/Python/SlurmTests/poiseuille/slurm.job
@@ -0,0 +1,26 @@
+#!/bin/bash
+#SBATCH -J PyFluidsTest
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=20
+
+#SBATCH --mem-per-cpu=3000
+#SBATCH --time=07:00:00
+#SBATCH --partition=standard
+
+source $HOME/.bashrc
+
+echo "PyFluids Poiseuille Test Case"
+echo "Number of tasks: ${SLURM_NTASKS}"
+
+export SINGULARITYENV_PYFLUIDS_SCALE_LEVEL=0
+export SINGULARITYENV_PYFLUIDS_NUM_THREADS=4
+srun singularity run --app testcase PoiseuilleTestContainer.sif
+
+export SINGULARITYENV_PYFLUIDS_SCALE_LEVEL=1
+srun singularity run --app testcase PoiseuilleTestContainer.sif
+
+export SINGULARITYENV_PYFLUIDS_SCALE_LEVEL=2
+srun singularity run --app testcase PoiseuilleTestContainer.sif
+
+srun singularity run --app evaluate PoiseuilleTestContainer.sif
diff --git a/Python/acousticscaling.py b/Python/acousticscaling.py
new file mode 100644
index 0000000000000000000000000000000000000000..50b81db064251fa269f29bf72a561567ddedafbc
--- /dev/null
+++ b/Python/acousticscaling.py
@@ -0,0 +1,85 @@
+from pyfluids.kernel import LBMKernel
+from pyfluids.parameters import GridParameters, PhysicalParameters, RuntimeParameters
+
+
+class OneDirectionalAcousticScaling:
+
+ def __init__(self, grid_parameters: GridParameters,
+ physical_parameters: PhysicalParameters,
+ runtime_parameters: RuntimeParameters,
+ kernel: LBMKernel):
+ self._grid_params = grid_parameters
+ self._physical_params = physical_parameters
+ self._runtime_params = runtime_parameters
+ self._kernel = kernel
+
+ def configuration_for_scale_level(self, level: int = 1) -> (GridParameters,
+ PhysicalParameters,
+ RuntimeParameters,
+ LBMKernel):
+ if level < 0:
+ raise ValueError("level must be >= 0")
+
+ grid_params = self.clone_grid_params_for_level(level)
+ physical_params = self.clone_physical_parameters(level)
+ runtime_params = self.clone_runtime_params_for_level(level)
+ kernel = self.clone_kernel_for_level(level)
+
+ return grid_params, physical_params, runtime_params, kernel
+
+ def clone_grid_params_for_level(self, level) -> GridParameters:
+ grid_params = GridParameters()
+ grid_params.reference_direction_index = self._grid_params.reference_direction_index
+ grid_params.periodic_boundary_in_x1 = self._grid_params.periodic_boundary_in_x1
+ grid_params.periodic_boundary_in_x2 = self._grid_params.periodic_boundary_in_x2
+ grid_params.periodic_boundary_in_x3 = self._grid_params.periodic_boundary_in_x3
+
+ grid_params.number_of_nodes_per_direction = list(self._grid_params.number_of_nodes_per_direction)
+ grid_params.blocks_per_direction = list(self._grid_params.blocks_per_direction)
+ grid_params.node_distance = self._grid_params.node_distance
+
+ if level > 0:
+ grid_params.node_distance /= (level * 2)
+ grid_params.number_of_nodes_per_direction = [grid_params.number_of_nodes_per_direction[0],
+ grid_params.number_of_nodes_per_direction[1],
+ grid_params.number_of_nodes_per_direction[2] * (level * 2)]
+
+ grid_params.blocks_per_direction = [grid_params.blocks_per_direction[0],
+ grid_params.blocks_per_direction[1],
+ grid_params.blocks_per_direction[2] * (level * 2)]
+
+ return grid_params
+
+ def clone_physical_parameters(self, level):
+ physical_params = PhysicalParameters()
+ physical_params.lattice_viscosity = self._physical_params.lattice_viscosity
+
+ if level > 0:
+ physical_params.lattice_viscosity *= (level * 2)
+
+ return physical_params
+
+ def clone_runtime_params_for_level(self, level):
+ runtime_params = RuntimeParameters()
+ runtime_params.number_of_timesteps = self._runtime_params.number_of_timesteps
+ runtime_params.number_of_threads = self._runtime_params.number_of_threads
+ runtime_params.timestep_log_interval = self._runtime_params.timestep_log_interval
+
+ if level > 0:
+ runtime_params.number_of_timesteps *= (level * 2)
+
+ return runtime_params
+
+ def clone_kernel_for_level(self, level):
+ kernel = LBMKernel(self._kernel.type)
+ kernel.use_forcing = self._kernel.use_forcing
+ kernel.forcing_in_x1 = self._kernel.forcing_in_x1
+ kernel.forcing_in_x2 = self._kernel.forcing_in_x2
+ kernel.forcing_in_x3 = self._kernel.forcing_in_x3
+
+ if level > 0:
+ kernel.forcing_in_x1 /= (level * 2)
+ kernel.forcing_in_x2 /= (level * 2)
+ kernel.forcing_in_x3 /= (level * 2)
+
+ return kernel
diff --git a/Python/norms.py b/Python/errors.py
similarity index 96%
rename from Python/norms.py
rename to Python/errors.py
index 78ae344591e4d91f28b9a98cf1e28ef447e2f62a..16e8c48ab9f0b7a46ed1372ef0b4d45738cccb1b 100644
--- a/Python/norms.py
+++ b/Python/errors.py
@@ -42,8 +42,8 @@ def mean_squared_error(real_values, numerical_values):
return sum_of_squared_distances / num_values
-def l2_norm_error(real_values, numerical_values):
+def normalized_l2_error(real_values, numerical_values):
sum_of_squared_distances = get_sum_of_squared_distances(real_values, numerical_values)
sum_of_squared_real_values = sum(real_value ** 2 for real_value in real_values)
- return math.sqrt(sum_of_squared_distances / sum_of_squared_real_values)
\ No newline at end of file
+ return math.sqrt(sum_of_squared_distances / sum_of_squared_real_values)
diff --git a/Python/poiseuille/analytical.py b/Python/poiseuille/analytical.py
index bca1a3ff95c1f28bca68ebb0c14efee48a1a5984..33e67595d94c50a1eb98751b7f10df9a031800e8 100644
--- a/Python/poiseuille/analytical.py
+++ b/Python/poiseuille/analytical.py
@@ -1,39 +1,52 @@
from dataclasses import dataclass
+@dataclass
class PoiseuilleSettings:
-
- def __init__(self):
- self.density = 1
- self.viscosity = 0.005
- self.height = 10
- self.length = 1
- self.pressure_in = 0
- self.pressure_out = 0
- self.force = 0
+ density = 1
+ viscosity = 0.005
+ height = 10
+ length = 1
+ pressure_in = 0
+ pressure_out = 0
+ force = 0
def poiseuille_at_z(settings: PoiseuilleSettings, z: float):
pressure_grad = ((settings.pressure_out - settings.pressure_in) / settings.length)
- return (1 / settings.viscosity
+ return ((1 / settings.viscosity)
* (- pressure_grad + settings.density * settings.force)
- * z / 2 * (settings.height - z))
+ * (z / 2)
+ * (settings.height - z))
def poiseuille_at_heights(settings: PoiseuilleSettings, heights):
return [poiseuille_at_z(settings, z) for z in heights]
-if __name__ == '__main__':
- # h1 = [1, 2, 3, 4, 5, 6, 7, 8, 9]
- # h2 = [0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 6, 6.5, 7, 7.5, 8, 8.5, 9, 9.5]
- settings = PoiseuilleSettings()
- settings.force = 1e-8
- settings.height = 32
+def reynolds_number(settings: PoiseuilleSettings):
+ max_v = poiseuille_at_z(settings, settings.height / 2)
+ return max_v * settings.height / settings.viscosity
- # print(max(poiseuille_at_heights(settings, h1)))
- # print(max(poiseuille_at_heights(settings, h2)))
- v = poiseuille_at_z(settings, 16)
- print(v)
\ No newline at end of file
+if __name__ == '__main__':
+ sim_settings = PoiseuilleSettings()
+
+ sim_settings.force = 2e-7
+ sim_settings.viscosity = 1e-3
+ sim_settings.height = 16
+ print(f"v_max = ", poiseuille_at_z(sim_settings, sim_settings.height / 2))
+ print(f"Re =", reynolds_number(sim_settings))
+
+ sim_settings.viscosity *= 2
+ sim_settings.height *= 2
+ sim_settings.force /= 2
+ print(f"v_max = ", poiseuille_at_z(sim_settings, sim_settings.height / 2))
+ print(f"Re =", reynolds_number(sim_settings))
+
+ sim_settings.viscosity *= 2
+ sim_settings.height *= 2
+ sim_settings.force /= 2
+ print(f"v_max = ", poiseuille_at_z(sim_settings, sim_settings.height / 2))
+ print(f"Re =", reynolds_number(sim_settings))
diff --git a/Python/poiseuille/simulation.py b/Python/poiseuille/simulation.py
index f7f6d468f19820993c61b458b3b0138b8c886139..31ceb1ab9ef90fa4fd606bde4f47c45b8f7d7567 100644
--- a/Python/poiseuille/simulation.py
+++ b/Python/poiseuille/simulation.py
@@ -17,23 +17,30 @@ default_physical_params.lattice_viscosity = 0.005
default_runtime_params = RuntimeParameters()
default_runtime_params.number_of_threads = 4
-default_runtime_params.number_of_timesteps = 100000
-default_runtime_params.timestep_log_interval = 10000
+default_runtime_params.number_of_timesteps = 10000
+default_runtime_params.timestep_log_interval = 1000
+
+default_kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
+default_kernel.use_forcing = True
+default_kernel.forcing_in_x1 = 1e-8
+
+default_writer = Writer()
+default_writer.output_path = "./output"
+default_writer.output_format = OutputFormat.BINARY
+
+
+default_kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
+default_kernel.use_forcing = True
+default_kernel.forcing_in_x1 = 1e-8
def run_simulation(physical_params=default_physical_params,
grid_params=default_grid_params,
- runtime_params=default_runtime_params):
+ runtime_params=default_runtime_params,
+ kernel=default_kernel,
+ writer=default_writer):
simulation = Simulation()
- kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
- kernel.use_forcing = True
- kernel.forcing_in_x1 = 1e-8
-
- writer = Writer()
- writer.output_path = "./output"
- writer.output_format = OutputFormat.BINARY
-
simulation.set_kernel_config(kernel)
simulation.set_physical_parameters(physical_params)
simulation.set_grid_parameters(grid_params)
@@ -42,26 +49,26 @@ def run_simulation(physical_params=default_physical_params,
no_slip_bc = NoSlipBoundaryCondition()
- block_width = 3 * grid_params.node_distance
+ block_thickness = 3 * grid_params.node_distance
simulation.add_object(
GbCuboid3D(
- grid_params.bounding_box.min_x1 - block_width,
- grid_params.bounding_box.min_x2 - block_width,
- grid_params.bounding_box.min_x3 - block_width,
- grid_params.bounding_box.max_x1 + block_width,
- grid_params.bounding_box.max_x2 + block_width,
+ grid_params.bounding_box.min_x1 - block_thickness,
+ grid_params.bounding_box.min_x2 - block_thickness,
+ grid_params.bounding_box.min_x3 - block_thickness,
+ grid_params.bounding_box.max_x1 + block_thickness,
+ grid_params.bounding_box.max_x2 + block_thickness,
grid_params.bounding_box.min_x3),
no_slip_bc,
State.SOLID, "/geo/addWallZMin")
simulation.add_object(
GbCuboid3D(
- grid_params.bounding_box.min_x1 - block_width,
- grid_params.bounding_box.min_x2 - block_width,
+ grid_params.bounding_box.min_x1 - block_thickness,
+ grid_params.bounding_box.min_x2 - block_thickness,
grid_params.bounding_box.max_x3,
- grid_params.bounding_box.max_x1 + block_width,
- grid_params.bounding_box.max_x2 + block_width,
- grid_params.bounding_box.max_x3 + block_width),
+ grid_params.bounding_box.max_x1 + block_thickness,
+ grid_params.bounding_box.max_x2 + block_thickness,
+ grid_params.bounding_box.max_x3 + block_thickness),
no_slip_bc,
State.SOLID, "/geo/addWallZMax")
diff --git a/Python/poiseuille/test_poiseuille_l2.py b/Python/poiseuille/test_poiseuille_l2.py
index 508fda5d6f551d428d314ffbfa657b4b6b2a230a..39c8b6dffe05e3c352e7fd340857e43d8d5a3dc8 100644
--- a/Python/poiseuille/test_poiseuille_l2.py
+++ b/Python/poiseuille/test_poiseuille_l2.py
@@ -1,68 +1,90 @@
+import os
import shutil
import unittest
import matplotlib.pyplot as plt
+import numpy as np
import pyvista as pv
+from pyfluids.kernel import LBMKernel, KernelType
from pyfluids.parameters import GridParameters, PhysicalParameters, RuntimeParameters
+from scipy import stats
-from norms import l2_norm_error
+from errors import normalized_l2_error
from poiseuille.analytical import poiseuille_at_heights, PoiseuilleSettings
from poiseuille.simulation import run_simulation
from vtk_utilities import vertical_column_from_mesh, get_values_from_indices
class TestPoiseuilleFlow(unittest.TestCase):
+ node_distances = [1, 0.5, 0.25]
+ number_of_nodes = [16, 32, 64]
+ number_of_timesteps = [2_500_000, 5_000_000, 10_000_000]
+ forcings = [1e-9, 5e-10, 2.5e-10]
+ viscosities = [1e-3, 2e-3, 4e-3]
+
+ def zipped_settings(self):
+ return zip(self.node_distances,
+ self.number_of_nodes,
+ self.number_of_timesteps,
+ self.forcings,
+ self.viscosities)
def test_poiseuille_flow(self):
- self.skipTest("Skipping test! This test has not been implemented correctly yet")
+ self.skipTest("This test is not implemented correctly yet")
plt.ion()
- channel_height = 10
- number_of_nodes = [8, 16, 32]
- number_of_timesteps = [10_000, 20_000, 40_000]
- viscosities = [5e-3, 1e-2, 2e-2]
- l2_norm_results = []
-
physical_params = PhysicalParameters()
runtime_params = RuntimeParameters()
- runtime_params.number_of_threads = 4
- runtime_params.timestep_log_interval = 1000
-
- for test_number, nodes_in_column in enumerate(number_of_nodes):
- runtime_params.number_of_timesteps = number_of_timesteps[test_number]
- physical_params.lattice_viscosity = viscosities[test_number]
- delta_x = channel_height / nodes_in_column
- grid_params = create_grid_params_with_nodes_in_column(nodes_in_column, delta_x)
- l2_norm_result = get_l2_norm_for_simulation(grid_params, physical_params, runtime_params)
- l2_norm_results.append(l2_norm_result)
-
- plt.plot(number_of_nodes, l2_norm_results)
+ runtime_params.number_of_threads = os.cpu_count()
+ runtime_params.timestep_log_interval = 10000
+
+ kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
+ kernel.use_forcing = True
+
+ normalized_l2_errors = []
+ for delta_x, nodes, timesteps, forcing, viscosity in self.zipped_settings():
+ physical_params.lattice_viscosity = viscosity
+ runtime_params.number_of_timesteps = timesteps
+ kernel.forcing_in_x1 = forcing
+
+ grid_params = create_grid_params_with_nodes_in_column(nodes, delta_x)
+ l2_error = get_l2_error_for_simulation(grid_params, physical_params, runtime_params, kernel)
+ normalized_l2_errors.append(l2_error)
+
+ nodes_as_log = [np.log10(node) for node in self.number_of_nodes]
+ l2_norms_as_log = [np.log10(l2) for l2 in normalized_l2_errors]
+ res = stats.linregress(nodes_as_log, l2_norms_as_log)
+
+ plt.xscale("log")
+ plt.yscale("log")
+ plt.plot(self.number_of_nodes, [np.power(10, res.intercept + res.slope * node) for node in nodes_as_log], 'r-')
+ plt.plot(self.number_of_nodes, normalized_l2_errors, "x:")
plt.show()
- self.assertTrue(l2_norm_results[1] <= l2_norm_results[0])
- self.assertTrue(l2_norm_results[2] <= l2_norm_results[1])
-
-
-def run_simulation_with_settings(grid_params, physical_params, runtime_params, output_folder):
- remove_existing_output_directory(output_folder)
- run_simulation(physical_params, grid_params, runtime_params)
+ print(normalized_l2_errors)
+ self.assertAlmostEqual(res.slope, -2, places=2)
-def get_l2_norm_for_simulation(grid_params, physical_params, runtime_params):
+def get_l2_error_for_simulation(grid_params, physical_params, runtime_params, kernel):
output_folder = "./output"
- run_simulation_with_settings(grid_params, physical_params, runtime_params, output_folder)
+ run_simulation_with_settings(grid_params, physical_params, runtime_params, kernel, output_folder)
heights = get_heights(output_folder, runtime_params)
- numerical_results = get_numerical_results(runtime_params, output_folder, heights)
- analytical_results = get_analytical_results(physical_params, heights, grid_params.number_of_nodes_per_direction[2])
+ numerical_results = get_numerical_results(runtime_params, output_folder)
+ analytical_results = get_analytical_results(grid_params, physical_params, kernel, heights)
plt.plot(heights, numerical_results)
plt.plot(heights, analytical_results)
plt.legend(["numerical", "analytical"])
plt.show()
- return l2_norm_error(analytical_results, numerical_results)
+ return normalized_l2_error(analytical_results, numerical_results)
+
+
+def run_simulation_with_settings(grid_params, physical_params, runtime_params, kernel, output_folder):
+ shutil.rmtree(output_folder, ignore_errors=True)
+ run_simulation(physical_params, grid_params, runtime_params, kernel)
def get_heights(output_folder, runtime_params):
@@ -72,7 +94,7 @@ def get_heights(output_folder, runtime_params):
return heights
-def get_numerical_results(runtime_params, output_folder, heights):
+def get_numerical_results(runtime_params, output_folder):
mesh_of_last_timestep = get_mesh_for_last_timestep(output_folder, runtime_params)
velocities_in_x_direction = mesh_of_last_timestep.get_array("Vx")
column_indices = vertical_column_from_mesh(mesh_of_last_timestep)
@@ -81,16 +103,12 @@ def get_numerical_results(runtime_params, output_folder, heights):
return numerical_results
-def calculate_analytical_results(physical_params, height_values, channel_height):
- settings = get_analytical_poiseuille_settings(channel_height, physical_params)
- max_height = max(height_values)
- height_values = [value / max_height * channel_height for value in height_values]
- analytical_results = poiseuille_at_heights(settings, height_values)
- return analytical_results
-
-
-def get_analytical_results(physical_params, heights, channel_height):
- analytical_results = calculate_analytical_results(physical_params, heights, channel_height)
+def get_analytical_results(grid_params, physical_params, kernel, height_values):
+ channel_height = grid_params.number_of_nodes_per_direction[2]
+ settings = get_analytical_poiseuille_settings(channel_height, physical_params, kernel)
+ max_grid_height = channel_height * grid_params.node_distance
+ adjusted_height_values = [value / max_grid_height * channel_height for value in height_values]
+ analytical_results = poiseuille_at_heights(settings, adjusted_height_values)
return analytical_results
@@ -100,18 +118,12 @@ def get_mesh_for_last_timestep(output_folder, runtime_params):
return mesh_of_last_timestep
-def remove_existing_output_directory(output_dir):
- shutil.rmtree(output_dir, ignore_errors=True)
-
-
-def get_analytical_poiseuille_settings(height, physical_params):
+def get_analytical_poiseuille_settings(height, physical_params, kernel):
settings = PoiseuilleSettings()
settings.height = height
settings.viscosity = physical_params.lattice_viscosity
settings.density = 1
- settings.force = 1e-8
-
- # print(settings)
+ settings.force = kernel.forcing_in_x1
return settings
@@ -130,13 +142,10 @@ def get_heights_from_indices(mesh, indices):
def create_grid_params_with_nodes_in_column(nodes_in_column, delta_x):
grid_params = GridParameters()
grid_params.node_distance = delta_x
- grid_params.number_of_nodes_per_direction = [2, 2, nodes_in_column]
- grid_params.blocks_per_direction = [1, 1, 6]
+ grid_params.number_of_nodes_per_direction = [1, 1, nodes_in_column]
+ grid_params.blocks_per_direction = [1, 1, 8]
grid_params.periodic_boundary_in_x1 = True
grid_params.periodic_boundary_in_x2 = True
grid_params.periodic_boundary_in_x3 = False
- print(f"GridParameters.node_distance = {grid_params.node_distance}")
- print(f"GridParameters.number_of_nodes_per_direction = {grid_params.number_of_nodes_per_direction}")
-
return grid_params
diff --git a/Python/requirements.txt b/Python/requirements.txt
index ded26051abb63145842f304ba865dc8487a8be73..8628634d1b85ebc0b07328d563d479f35641be97 100644
--- a/Python/requirements.txt
+++ b/Python/requirements.txt
@@ -14,8 +14,10 @@ py==1.10.0
pyparsing==2.4.7
pytest==6.2.1
python-dateutil==2.8.1
-pyvista==0.27.4
+pyvista==0.28.1
+scipy==1.6.1
scooby==0.5.6
six==1.15.0
toml==0.10.2
+transforms3d==0.3.1
vtk==9.0.1
diff --git a/Python/tests/test_acousticscaling.py b/Python/tests/test_acousticscaling.py
new file mode 100644
index 0000000000000000000000000000000000000000..2da5314529f9559f9ac316f2d1bb3f1a9d0e1211
--- /dev/null
+++ b/Python/tests/test_acousticscaling.py
@@ -0,0 +1,115 @@
+import unittest
+from typing import List
+
+from pyfluids.kernel import LBMKernel, KernelType
+from pyfluids.parameters import GridParameters, PhysicalParameters, RuntimeParameters
+
+from acousticscaling import OneDirectionalAcousticScaling
+
+
+class OneDirectionalAcousticScalingTest(unittest.TestCase):
+
+ def setUp(self) -> None:
+ self.grid_params = self.make_grid_params()
+ self.physical_params = self.make_physical_params()
+ self.runtime_params = self.make_runtime_params()
+ self.kernel = self.make_kernel()
+
+ self.sut = OneDirectionalAcousticScaling(self.grid_params, self.physical_params, self.runtime_params,
+ self.kernel)
+
+ def test_given_sim_parameters__when_scaling_level_zero__should_return_equal_sim_parameters(self):
+ factor = 1
+ actual_params = self.sut.configuration_for_scale_level(0)
+ actual_grid_params = actual_params[0]
+ actual_physical_params = actual_params[factor]
+ actual_runtime_params = actual_params[2]
+ actual_kernel = actual_params[3]
+
+ self.assert_parameters_scaled_by_factor(actual_grid_params, actual_kernel,
+ actual_physical_params, actual_runtime_params, factor)
+
+ def test_given_sim_parameters__when_scaling_level_one__should_return_sim_parameters_scaled_by_two(self):
+ actual_params = self.sut.configuration_for_scale_level(1)
+ actual_grid_params = actual_params[0]
+ actual_physical_params = actual_params[1]
+ actual_runtime_params = actual_params[2]
+ actual_kernel = actual_params[3]
+
+ self.assert_parameters_scaled_by_factor(actual_grid_params, actual_kernel,
+ actual_physical_params, actual_runtime_params, 2)
+
+ def assert_parameters_scaled_by_factor(self, actual_grid_params, actual_kernel,
+ actual_physical_params, actual_runtime_params, factor):
+ self.assert_grid_params_scaled_by_factor(actual_grid_params, factor=factor)
+ self.assert_physical_params_scaled_by_factor(actual_physical_params, factor=factor)
+ self.assert_runtime_params_scaled_by_factor(actual_runtime_params, factor=factor)
+ self.assert_kernel_forcing_scaled_by_factor(actual_kernel, factor=factor)
+
+ def assert_grid_params_scaled_by_factor(self, actual_grid_params: GridParameters, factor: int):
+ expected_nodes_per_direction = self.scaled_list(self.grid_params.number_of_nodes_per_direction, factor)
+ expected_blocks_per_direction = self.scaled_list(self.grid_params.blocks_per_direction, factor)
+ expected_node_distance = self.grid_params.node_distance / factor
+ self.assertEqual(expected_node_distance, actual_grid_params.node_distance)
+ self.assertEqual(expected_nodes_per_direction, actual_grid_params.number_of_nodes_per_direction)
+ self.assertEqual(expected_blocks_per_direction, actual_grid_params.blocks_per_direction)
+ self.assertEqual(self.grid_params.reference_direction_index, actual_grid_params.reference_direction_index)
+ self.assertEqual(self.grid_params.periodic_boundary_in_x1, actual_grid_params.periodic_boundary_in_x1)
+ self.assertEqual(self.grid_params.periodic_boundary_in_x2, actual_grid_params.periodic_boundary_in_x2)
+ self.assertEqual(self.grid_params.periodic_boundary_in_x3, actual_grid_params.periodic_boundary_in_x3)
+
+ def assert_physical_params_scaled_by_factor(self, actual_params: PhysicalParameters, factor: int):
+ self.assertEqual(self.physical_params.lattice_viscosity * factor, actual_params.lattice_viscosity)
+ self.assertEqual(self.physical_params.bulk_viscosity_factor, actual_params.bulk_viscosity_factor)
+
+ def assert_runtime_params_scaled_by_factor(self, actual_params: RuntimeParameters, factor: int):
+ self.assertEqual(self.runtime_params.number_of_timesteps * factor, actual_params.number_of_timesteps)
+ self.assertEqual(self.runtime_params.number_of_threads, actual_params.number_of_threads)
+ self.assertEqual(self.runtime_params.timestep_log_interval, actual_params.timestep_log_interval)
+
+ def assert_kernel_forcing_scaled_by_factor(self, actual_kernel: LBMKernel, factor: int):
+ self.assertEqual(self.kernel.type, actual_kernel.type)
+ self.assertEqual(self.kernel.use_forcing, actual_kernel.use_forcing)
+ self.assertAlmostEqual(self.kernel.forcing_in_x1 / factor, actual_kernel.forcing_in_x1)
+ self.assertAlmostEqual(self.kernel.forcing_in_x2, actual_kernel.forcing_in_x2)
+ self.assertAlmostEqual(self.kernel.forcing_in_x3, actual_kernel.forcing_in_x3)
+
+ @staticmethod
+ def scaled_list(list_to_scale: List[int], factor: int) -> List[int]:
+ return [list_to_scale[0], list_to_scale[1], list_to_scale[2] * factor]
+
+ @staticmethod
+ def make_kernel():
+ kernel = LBMKernel(KernelType.CompressibleCumulantFourthOrderViscosity)
+ kernel.use_forcing = True
+ kernel.forcing_in_x1 = 5e-10
+ return kernel
+
+ @staticmethod
+ def make_runtime_params():
+ runtime_params = RuntimeParameters()
+ runtime_params.number_of_threads = 4
+ runtime_params.number_of_timesteps = 4_000_000
+ runtime_params.timestep_log_interval = 1_000_000
+ return runtime_params
+
+ @staticmethod
+ def make_physical_params():
+ physical_params = PhysicalParameters()
+ physical_params.lattice_viscosity = 1e-4
+ return physical_params
+
+ @staticmethod
+ def make_grid_params():
+ grid_params = GridParameters()
+ grid_params.node_distance = 1
+ grid_params.number_of_nodes_per_direction = [1, 1, 16]
+ grid_params.blocks_per_direction = [1, 1, 16]
+ grid_params.periodic_boundary_in_x1 = True
+ grid_params.periodic_boundary_in_x2 = True
+
+ return grid_params
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/Python/tests/test_boundaryconditions.py b/Python/tests/test_boundaryconditions.py
new file mode 100644
index 0000000000000000000000000000000000000000..5a7d61f36337398fc5621540951f15b72262b17b
--- /dev/null
+++ b/Python/tests/test_boundaryconditions.py
@@ -0,0 +1,61 @@
+import unittest
+from pyfluids.boundaryconditions import *
+
+
+class BoundaryConditionsTest(unittest.TestCase):
+
+ def test__can_create_no_slip_bc(self):
+ """
+ Should be able to create NoSlipBoundaryCondition
+ """
+ sut = NoSlipBoundaryCondition()
+
+ def test__can_create_velocity_bc(self):
+ """
+ Should be able to create VelocityBoundaryCondition
+ """
+ sut = VelocityBoundaryCondition()
+
+ def test__can_create_velocity_bc_with_directions_function_and_time(self):
+ """
+ Should be able to create VelocityBoundaryCondition with directions, function and start/end time
+ """
+ from pymuparser import Parser
+
+ parser = Parser()
+ parser.expression = "1"
+ sut = VelocityBoundaryCondition(True, True, True, parser, 0, 1)
+
+ def test__can_create_velocity_bc_with_directions__function_per_direction__and__time(self):
+ """
+ Should be able to create VelocityBoundaryCondition with directions, function per direction and start/end time
+ """
+ from pymuparser import Parser
+
+ f1 = Parser()
+ f1.expression = "1"
+
+ f2 = Parser()
+ f2.expression = "1"
+
+ f3 = Parser()
+ f3.expression = "1"
+ sut = VelocityBoundaryCondition(True, True, True, f1, f2, f3, 0, 1)
+
+ def test__can_create_velocity_bc_with_speeds_and_times_per_direction(self):
+ """
+ Should be able to create VelocityBoundaryCondition with speeds and start/end times per direction
+ """
+ vx1, vx2, vx3 = 1, 2, 3
+ start1, end1 = 0, 1
+ start2, end2 = 1, 2
+ start3, end3 = 2, 3
+
+ sut = VelocityBoundaryCondition(vx1, start1, end1, vx2, start2, end2, vx3, start3, end3)
+
+ def test__can_create_non_reflecting_outflow(self):
+ """
+ Should be able to create NonReflectingOutflow
+ """
+
+ sut = NonReflectingOutflow()
diff --git a/Python/test_geometry.py b/Python/tests/test_geometry.py
similarity index 100%
rename from Python/test_geometry.py
rename to Python/tests/test_geometry.py
diff --git a/Python/test_kernel.py b/Python/tests/test_kernel.py
similarity index 85%
rename from Python/test_kernel.py
rename to Python/tests/test_kernel.py
index 5e5487903a279501b0acdba1ab192ac8dd381383..b1016f15308a77c9025787e061355819cbca3874 100644
--- a/Python/test_kernel.py
+++ b/Python/tests/test_kernel.py
@@ -51,3 +51,10 @@ class TestLBMKernel(unittest.TestCase):
self.assertEqual(self.sut.forcing_in_x2, 8)
self.assertEqual(self.sut.forcing_in_x3, 5)
+ def test_lbm_kernel__when_getting_type__should_equal_kernel_type_enum_value(self) -> None:
+ """
+ WHEN getting the kernel type IT should equal the corresponding KernelType enum value
+ """
+
+ actual = self.sut.type
+ self.assertEqual(KernelType.BGK, actual)
diff --git a/Python/vtk_utilities.py b/Python/vtk_utilities.py
index e8c16ce02c85518edacde024a012c4ce261fbc14..14d13a40d85e669a463c0b5b31ca2a21e771af75 100644
--- a/Python/vtk_utilities.py
+++ b/Python/vtk_utilities.py
@@ -1,20 +1,29 @@
import math
+from typing import List
+
import pyvista as pv
def vertical_column_from_mesh(mesh):
last_seen = math.inf
relevant_indices = []
+ first_x = 0
+ first_y = 0
for index, point in enumerate(mesh.points):
- if point[2] == last_seen:
+ if index == 0:
+ first_x = point[0]
+ first_y = point[1]
+
+ if (point[0] != first_x or point[1] != first_y) and point[2] == last_seen:
continue
+
relevant_indices.append(index)
last_seen = point[2]
return relevant_indices
-def get_values_from_indices(array, indices):
+def get_values_from_indices(array, indices) -> List[float]:
return [array[index] for index in indices]
diff --git a/apps/cpu/Applications.cmake b/apps/cpu/Applications.cmake
index d8dff8b8c5f776d1d27e9217d7b050ab4022d8a4..e8902e5ffbb3720365476afef50a4f3fbd0ddf76 100644
--- a/apps/cpu/Applications.cmake
+++ b/apps/cpu/Applications.cmake
@@ -1,8 +1,19 @@
+add_subdirectory(${APPS_ROOT_CPU}/PoiseuilleFlow)
+add_subdirectory(${APPS_ROOT_CPU}/HerschelBulkleySphere)
+add_subdirectory(${APPS_ROOT_CPU}/HerschelBulkleyModel)
+add_subdirectory(${APPS_ROOT_CPU}/rheometer)
+add_subdirectory(${APPS_ROOT_CPU}/CouetteFlow)
+add_subdirectory(${APPS_ROOT_CPU}/Multiphase)
+add_subdirectory(${APPS_ROOT_CPU}/ViskomatXL)
+add_subdirectory(${APPS_ROOT_CPU}/sphere)
+add_subdirectory(${APPS_ROOT_CPU}/FlowAroundCylinder)
+add_subdirectory(${APPS_ROOT_CPU}/LaminarTubeFlow)
+add_subdirectory(${APPS_ROOT_CPU}/MultiphaseDropletTest)
+
#add_subdirectory(tests)
#add_subdirectory(Applications/gridRf)
#add_subdirectory(Applications/greenvortex)
# add_subdirectory(Applications/micropart)
-add_subdirectory(${APPS_ROOT_CPU}/sphere)
#add_subdirectory(Applications/vfscript)
#add_subdirectory(Applications/reefer)
#add_subdirectory(Applications/bananas)
@@ -11,8 +22,6 @@ add_subdirectory(${APPS_ROOT_CPU}/sphere)
#add_subdirectory(Applications/bananas2)
# add_subdirectory(Applications/plate)
# add_subdirectory(Applications/plate2)
-add_subdirectory(${APPS_ROOT_CPU}/FlowAroundCylinder)
-add_subdirectory(${APPS_ROOT_CPU}/LaminarTubeFlow)
# add_subdirectory(Applications/LaminarTubeFlowConv)
#add_subdirectory(Applications/cylinderSt)
#add_subdirectory(Applications/mpichTest)
@@ -54,7 +63,6 @@ add_subdirectory(${APPS_ROOT_CPU}/LaminarTubeFlow)
#add_subdirectory(Applications/levels)
#add_subdirectory(Applications/AcousticPulse)
#add_subdirectory(Applications/screw)
-#add_subdirectory(Applications/PoiseuilleFlow)
#add_subdirectory(Applications/InterfaceTest)
#add_subdirectory(Applications/teperm)
#add_subdirectory(Applications/Thermoplast)
@@ -64,10 +72,5 @@ add_subdirectory(${APPS_ROOT_CPU}/LaminarTubeFlow)
#add_subdirectory(Applications/bChannelVA)
#add_subdirectory(Applications/OrganPipe)
#add_subdirectory(Applications/LidDrivenCavity)
-add_subdirectory(${APPS_ROOT_CPU}/HerschelBulkleySphere)
-add_subdirectory(${APPS_ROOT_CPU}/HerschelBulkleyModel)
-add_subdirectory(${APPS_ROOT_CPU}/rheometer)
-add_subdirectory(${APPS_ROOT_CPU}/CouetteFlow)
-add_subdirectory(${APPS_ROOT_CPU}/Multiphase)
-add_subdirectory(${APPS_ROOT_CPU}/ViskomatXL)
+
diff --git a/apps/cpu/LaminarTubeFlow/ltf.cfg b/apps/cpu/LaminarTubeFlow/ltf.cfg
index 94919cc3463c6a60dfd334e1c0505d60e56446d8..8b8e33e4998835da80d2121925acc7d95c3ccd20 100644
--- a/apps/cpu/LaminarTubeFlow/ltf.cfg
+++ b/apps/cpu/LaminarTubeFlow/ltf.cfg
@@ -1,5 +1,5 @@
pathname = d:/temp/LaminarTubeFlow
-numOfThreads = 4
+numOfThreads = 1
availMem = 10e9
#Grid
@@ -22,5 +22,5 @@ restartStep = 100000
cpStart = 100000
cpStep = 100000
-outTime = 1
-endTime = 100
\ No newline at end of file
+outTime = 1000
+endTime = 1000
\ No newline at end of file
diff --git a/apps/cpu/LaminarTubeFlow/ltf.cpp b/apps/cpu/LaminarTubeFlow/ltf.cpp
index 71340ab656b6fca7d5bcc534e69a2e25ca10fa9c..e523dd2de7416ea5189dbceab200725d89f15424 100644
--- a/apps/cpu/LaminarTubeFlow/ltf.cpp
+++ b/apps/cpu/LaminarTubeFlow/ltf.cpp
@@ -315,7 +315,7 @@ void run(string configname)
auto timeDepBC = make_shared<TimeDependentBCCoProcessor>(TimeDependentBCCoProcessor(grid, timeBCSch));
timeDepBC->addInteractor(inflowInt);
- //omp_set_num_threads(numOfThreads);
+ omp_set_num_threads(numOfThreads);
numOfThreads = 1;
SPtr<UbScheduler> stepGhostLayer(visSch);
SPtr<Calculator> calculator(new BasicCalculator(grid, stepGhostLayer, int(endTime)));
diff --git a/apps/cpu/Multiphase/Multiphase.cfg b/apps/cpu/Multiphase/Multiphase.cfg
index d52694ac838c8ae029ebf85476ab6db68de11223..c294ea68ce96c751030380d52d16eb35d06f9faa 100644
--- a/apps/cpu/Multiphase/Multiphase.cfg
+++ b/apps/cpu/Multiphase/Multiphase.cfg
@@ -1,11 +1,11 @@
-pathname = d:/temp/MultiphaseNew4
+pathname = d:/temp/MultiphaseNew5
#pathGeo = d:/Projects/VirtualFluids-Multiphase/source/Applications/Multiphase/backup
pathGeo = d:/Projects/VirtualFluidsCombined/apps/cpu/Multiphase/backup
#geoFile = JetBreakupR.ASCII.stl
#geoFile = inlet1.stl
geoFile = tubeTransformed.stl
-numOfThreads = 1
+numOfThreads = 4
availMem = 10e9
#Grid
@@ -20,21 +20,21 @@ availMem = 10e9
#boundingBox = -40 40 -1.0 -21.0 -40 40 #(Jet Breakup2) (Original without inlet length)
#boundingBox = -40 40 1.0 11.0 -40 40 #(Jet Breakup2) (Original without inlet length)
#boundingBox = -40e-3 40e-3 1.0e-3 11.0e-3 -403-3 40e-3 #(Jet Breakup2) (Original without inlet length)
-blocknx = 20 20 20
+#blocknx = 20 20 20
-boundingBox = 6.0e-3 16.0e-3 -40e-3 40e-3 -40e-3 40e-3
+boundingBox = 6.0e-3 46.0e-3 -5e-3 5e-3 -5e-3 5e-3
blocknx = 20 20 20
-dx = 0.5e-3
+dx = 1.66666666667e-4
refineLevel = 0
#Simulation
-uLB = 0.0005 #inlet velocity
+uLB = 0.005 #inlet velocity
#uF2 = 0.0001
Re = 10
nuL =1e-2# 1.0e-5 #!1e-2
nuG =1e-2# 1.16e-4 #!1e-2
-densityRatio = 30
+densityRatio = 1000
sigma = 1e-5 #4.66e-3 #surface tension 1e-4 ./. 1e-5
interfaceThickness = 5
radius = 615.0 (Jet Breakup)
@@ -55,5 +55,5 @@ restartStep = 100000
cpStart = 100000
cpStep = 100000
-outTime = 100
+outTime = 1
endTime = 10000
\ No newline at end of file
diff --git a/apps/cpu/Multiphase/Multiphase.cpp b/apps/cpu/Multiphase/Multiphase.cpp
index 10ff2b39618c64ef09edd902471387e7ebc90c70..deb2845f4278661bb970ea68b043e3cb435bffcc 100644
--- a/apps/cpu/Multiphase/Multiphase.cpp
+++ b/apps/cpu/Multiphase/Multiphase.cpp
@@ -111,10 +111,15 @@ void run(string configname)
//////////////////////////////////////////////////////////////////////////
// restart
SPtr<UbScheduler> rSch(new UbScheduler(cpStep, cpStart));
- SPtr<MPIIOMigrationBECoProcessor> rcp = make_shared<MPIIOMigrationBECoProcessor>(grid, rSch, pathname, comm);
+ //SPtr<MPIIORestartCoProcessor> rcp(new MPIIORestartCoProcessor(grid, rSch, pathname, comm));
+ //SPtr<MPIIOMigrationCoProcessor> rcp(new MPIIOMigrationCoProcessor(grid, rSch, pathname, comm));
+ SPtr<MPIIOMigrationBECoProcessor> rcp(new MPIIOMigrationBECoProcessor(grid, rSch, pathname, comm));
+ rcp->setNu(nuLB);
+ rcp->setNuLG(nuL, nuG);
+ rcp->setDensityRatio(densityRatio);
+
rcp->setLBMKernel(kernel);
rcp->setBCProcessor(bcProc);
- rcp->setNu(nuLB);
//////////////////////////////////////////////////////////////////////////
mu::Parser fctF1;
@@ -140,7 +145,7 @@ void run(string configname)
SPtr<D3Q27Interactor> cylInt;
if (newStart) {
- // if (newStart) {
+ // if (newStart) {
// bounding box
/*double g_minX1 = 0.0;
@@ -163,7 +168,7 @@ void run(string configname)
SPtr<GbObject3D> gridCube(new GbCuboid3D(g_minX1, g_minX2, g_minX3, g_maxX1, g_maxX2, g_maxX3));
if (myid == 0)
GbSystem3D::writeGeoObject(gridCube.get(), pathname + "/geo/gridCube",
- WbWriterVtkXmlBinary::getInstance());
+ WbWriterVtkXmlBinary::getInstance());
if (myid == 0) UBLOG(logINFO, "Read geoFile:start");
SPtr<GbTriFaceMesh3D> cylinder = make_shared<GbTriFaceMesh3D>();
@@ -176,10 +181,10 @@ void run(string configname)
new GbCuboid3D(g_minX1*0.5 - dx, g_minX2 - dx, g_minX3*0.5 - dx, g_maxX1*0.5 + dx, g_minX2, g_maxX3*0.5 + dx));
if (myid == 0) GbSystem3D::writeGeoObject(geoInflowF1.get(), pathname + "/geo/geoInflowF1", WbWriterVtkXmlASCII::getInstance());
- GbCylinder3DPtr cylinder1(new GbCylinder3D(g_minX1-dx, 0.0, 0.0, cylinder->getX1Maximum(), 0.0, 0.0, 3e-3));
+ GbCylinder3DPtr cylinder1(new GbCylinder3D(g_minX1-dx, 0.0, 0.0, g_minX1+dx, 0.0, 0.0, 3e-3));
if (myid == 0)
GbSystem3D::writeGeoObject(cylinder1.get(), pathname + "/geo/cylinder1",
- WbWriterVtkXmlASCII::getInstance());
+ WbWriterVtkXmlASCII::getInstance());
//GbCylinder3DPtr cylinder2(
// new GbCylinder3D(0.0, g_minX2 - 2.0 * dx / 2.0, 0.0, 0.0, g_minX2 + 4.0 * dx, 0.0, 8.0+2.0*dx));
@@ -192,7 +197,7 @@ void run(string configname)
GbCuboid3DPtr geoOutflow(new GbCuboid3D(g_minX1, g_maxX2, g_minX3, g_maxX1, g_maxX2 + dx, g_maxX3));
if (myid == 0)
GbSystem3D::writeGeoObject(geoOutflow.get(), pathname + "/geo/geoOutflow",
- WbWriterVtkXmlASCII::getInstance());
+ WbWriterVtkXmlASCII::getInstance());
// double blockLength = blocknx[0] * dx;
@@ -254,32 +259,32 @@ void run(string configname)
SPtr<D3Q27Interactor> outflowInt(new D3Q27Interactor(geoOutflow, grid, denBCAdapter, Interactor3D::SOLID));
- // Create boundary conditions geometry
- GbCuboid3DPtr wallXmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_minX1, g_maxX2 + dx, g_maxX3));
- GbSystem3D::writeGeoObject(wallXmin.get(), pathname + "/geo/wallXmin", WbWriterVtkXmlASCII::getInstance());
- GbCuboid3DPtr wallXmax(new GbCuboid3D(g_maxX1, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_maxX3));
- GbSystem3D::writeGeoObject(wallXmax.get(), pathname + "/geo/wallXmax", WbWriterVtkXmlASCII::getInstance());
- GbCuboid3DPtr wallZmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_minX3));
- GbSystem3D::writeGeoObject(wallZmin.get(), pathname + "/geo/wallZmin", WbWriterVtkXmlASCII::getInstance());
- GbCuboid3DPtr wallZmax(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_maxX3, g_maxX1 + dx, g_maxX2 + dx, g_maxX3 + dx));
- GbSystem3D::writeGeoObject(wallZmax.get(), pathname + "/geo/wallZmax", WbWriterVtkXmlASCII::getInstance());
- GbCuboid3DPtr wallYmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_minX2, g_maxX3));
- GbSystem3D::writeGeoObject(wallYmin.get(), pathname + "/geo/wallYmin", WbWriterVtkXmlASCII::getInstance());
- GbCuboid3DPtr wallYmax(new GbCuboid3D(g_minX1 - dx, g_maxX2, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_maxX3));
- GbSystem3D::writeGeoObject(wallYmax.get(), pathname + "/geo/wallYmax", WbWriterVtkXmlASCII::getInstance());
-
- // Add boundary conditions to grid generator
- SPtr<D3Q27Interactor> wallXminInt(new D3Q27Interactor(wallXmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallXmaxInt(new D3Q27Interactor(wallXmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallZminInt(new D3Q27Interactor(wallZmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallZmaxInt(new D3Q27Interactor(wallZmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallYminInt(new D3Q27Interactor(wallYmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallYmaxInt(new D3Q27Interactor(wallYmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
-
-
- cylInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(cylinder1, grid, velBCAdapterF1, Interactor3D::SOLID));
- cylInt->addBCAdapter(velBCAdapterF2);
- //SPtr<D3Q27Interactor> cyl2Int(new D3Q27Interactor(cylinder2, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ // Create boundary conditions geometry
+ GbCuboid3DPtr wallXmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_minX1, g_maxX2 + dx, g_maxX3));
+ GbSystem3D::writeGeoObject(wallXmin.get(), pathname + "/geo/wallXmin", WbWriterVtkXmlASCII::getInstance());
+ GbCuboid3DPtr wallXmax(new GbCuboid3D(g_maxX1, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_maxX3));
+ GbSystem3D::writeGeoObject(wallXmax.get(), pathname + "/geo/wallXmax", WbWriterVtkXmlASCII::getInstance());
+ GbCuboid3DPtr wallZmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_minX3));
+ GbSystem3D::writeGeoObject(wallZmin.get(), pathname + "/geo/wallZmin", WbWriterVtkXmlASCII::getInstance());
+ GbCuboid3DPtr wallZmax(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_maxX3, g_maxX1 + dx, g_maxX2 + dx, g_maxX3 + dx));
+ GbSystem3D::writeGeoObject(wallZmax.get(), pathname + "/geo/wallZmax", WbWriterVtkXmlASCII::getInstance());
+ GbCuboid3DPtr wallYmin(new GbCuboid3D(g_minX1 - dx, g_minX2 - dx, g_minX3 - dx, g_maxX1 + dx, g_minX2, g_maxX3));
+ GbSystem3D::writeGeoObject(wallYmin.get(), pathname + "/geo/wallYmin", WbWriterVtkXmlASCII::getInstance());
+ GbCuboid3DPtr wallYmax(new GbCuboid3D(g_minX1 - dx, g_maxX2, g_minX3 - dx, g_maxX1 + dx, g_maxX2 + dx, g_maxX3));
+ GbSystem3D::writeGeoObject(wallYmax.get(), pathname + "/geo/wallYmax", WbWriterVtkXmlASCII::getInstance());
+
+ // Add boundary conditions to grid generator
+ SPtr<D3Q27Interactor> wallXminInt(new D3Q27Interactor(wallXmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallXmaxInt(new D3Q27Interactor(wallXmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallZminInt(new D3Q27Interactor(wallZmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallZmaxInt(new D3Q27Interactor(wallZmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallYminInt(new D3Q27Interactor(wallYmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallYmaxInt(new D3Q27Interactor(wallYmax, grid, noSlipBCAdapter, Interactor3D::SOLID));
+
+
+ cylInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(cylinder1, grid, velBCAdapterF1, Interactor3D::SOLID));
+ cylInt->addBCAdapter(velBCAdapterF2);
+ //SPtr<D3Q27Interactor> cyl2Int(new D3Q27Interactor(cylinder2, grid, noSlipBCAdapter, Interactor3D::SOLID));
SPtr<Grid3DVisitor> metisVisitor(
new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased, D3Q27System::BSW));
@@ -288,8 +293,8 @@ void run(string configname)
intHelper.addInteractor(tubes);
//intHelper.addInteractor(outflowInt);
//intHelper.addInteractor(cyl2Int);
-
-
+
+
intHelper.addInteractor(wallXminInt);
intHelper.addInteractor(wallXmaxInt);
intHelper.addInteractor(wallZminInt);
@@ -297,7 +302,7 @@ void run(string configname)
intHelper.addInteractor(wallYminInt);
intHelper.addInteractor(wallYmaxInt);
//intHelper.addInteractor(inflowF1Int);
-
+
intHelper.selectBlocks();
@@ -331,7 +336,7 @@ void run(string configname)
}
MultiphaseSetKernelBlockVisitor kernelVisitor(kernel, nuL, nuG, densityRatio, beta, kappa, theta, availMem,
- needMem);
+ needMem);
grid->accept(kernelVisitor);
@@ -382,16 +387,16 @@ void run(string configname)
if (myid == 0)
UBLOG(logINFO, "Restart - end");
}
-
+
TwoDistributionsSetConnectorsBlockVisitor setConnsVisitor(comm);
grid->accept(setConnsVisitor);
-
+
//ThreeDistributionsSetConnectorsBlockVisitor setConnsVisitor(comm);
//grid->accept(setConnsVisitor);
SPtr<UbScheduler> visSch(new UbScheduler(outTime));
SPtr<WriteMultiphaseQuantitiesCoProcessor> pp(new WriteMultiphaseQuantitiesCoProcessor(
- //SPtr<WriteMacroscopicQuantitiesCoProcessor> pp(new WriteMacroscopicQuantitiesCoProcessor(
+ //SPtr<WriteMacroscopicQuantitiesCoProcessor> pp(new WriteMacroscopicQuantitiesCoProcessor(
grid, visSch, pathname, WbWriterVtkXmlBinary::getInstance(), conv, comm));
pp->process(0);
@@ -414,7 +419,7 @@ void run(string configname)
calculator->addCoProcessor(rcp);
-
+
if (myid == 0)
UBLOG(logINFO, "Simulation-start");
diff --git a/apps/cpu/MultiphaseDropletTest.zip b/apps/cpu/MultiphaseDropletTest.zip
new file mode 100644
index 0000000000000000000000000000000000000000..5eb13a6c0bacfbf392deb00c6b388ba282c038e0
Binary files /dev/null and b/apps/cpu/MultiphaseDropletTest.zip differ
diff --git a/apps/cpu/MultiphaseDropletTest/CMakeLists.txt b/apps/cpu/MultiphaseDropletTest/CMakeLists.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3f01ad73a0b28f7050667dde7b9408ac00b76e42
--- /dev/null
+++ b/apps/cpu/MultiphaseDropletTest/CMakeLists.txt
@@ -0,0 +1,3 @@
+PROJECT(MultiphaseDropletTest)
+
+vf_add_library(BUILDTYPE binary PRIVATE_LINK VirtualFluidsCore basics ${MPI_CXX_LIBRARIES} FILES droplet.cpp )
diff --git a/apps/cpu/MultiphaseDropletTest/DropletTest.cfg b/apps/cpu/MultiphaseDropletTest/DropletTest.cfg
new file mode 100644
index 0000000000000000000000000000000000000000..72c0144890c2fd8ba25fa0dfb7528fdbd1b889d8
--- /dev/null
+++ b/apps/cpu/MultiphaseDropletTest/DropletTest.cfg
@@ -0,0 +1,41 @@
+pathname = d:/temp/MultiphaseDropletTest
+
+numOfThreads = 4
+availMem = 10e9
+
+#Grid
+
+boundingBox = 0 128 0 64 0 64
+blocknx = 8 8 8
+
+dx = 1
+refineLevel = 0
+
+#Simulation
+uLB = 0.005
+Re = 10
+nuL =1e-2# 1.0e-5 #!1e-2
+nuG =1e-2# 1.16e-4 #!1e-2
+densityRatio = 1000
+sigma = 1e-5 #4.66e-3 #surface tension 1e-4 ./. 1e-5
+interfaceThickness = 5
+radius = 16
+contactAngle = 110.0
+#gravity = 0.0
+gravity = -5.04e-6
+phi_L = 0.0
+phi_H = 1.0
+Phase-field Relaxation = 0.6
+Mobility = 0.02 # 0.01 ./. 0.08, fine correction of Phase-field Relaxation parameter, to activate it need to change in kernel tauH to tauH1
+
+
+logToFile = false
+
+newStart = true
+restartStep = 100000
+
+cpStart = 100000
+cpStep = 100000
+
+outTime = 1
+endTime = 10000
\ No newline at end of file
diff --git a/apps/cpu/MultiphaseDropletTest/droplet.cpp b/apps/cpu/MultiphaseDropletTest/droplet.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..092d5a16a36b47c726f0f85463484f0c97fdecd0
--- /dev/null
+++ b/apps/cpu/MultiphaseDropletTest/droplet.cpp
@@ -0,0 +1,306 @@
+#include <iostream>
+#include <string>
+#include <memory>
+
+#include "VirtualFluids.h"
+
+using namespace std;
+
+void run(string configname)
+{
+ try {
+ ConfigurationFile config;
+ config.load(configname);
+
+ string pathname = config.getValue<string>("pathname");
+ int numOfThreads = config.getValue<int>("numOfThreads");
+ vector<int> blocknx = config.getVector<int>("blocknx");
+ vector<double> boundingBox = config.getVector<double>("boundingBox");
+ double uLB = config.getValue<double>("uLB");
+ double nuL = config.getValue<double>("nuL");
+ double nuG = config.getValue<double>("nuG");
+ double densityRatio = config.getValue<double>("densityRatio");
+ double sigma = config.getValue<double>("sigma");
+ int interfaceThickness = config.getValue<int>("interfaceThickness");
+ double radius = config.getValue<double>("radius");
+ double theta = config.getValue<double>("contactAngle");
+ double gr = config.getValue<double>("gravity");
+ double phiL = config.getValue<double>("phi_L");
+ double phiH = config.getValue<double>("phi_H");
+ double tauH = config.getValue<double>("Phase-field Relaxation");
+ double mob = config.getValue<double>("Mobility");
+
+ double endTime = config.getValue<double>("endTime");
+ double outTime = config.getValue<double>("outTime");
+ double availMem = config.getValue<double>("availMem");
+ int refineLevel = config.getValue<int>("refineLevel");
+ double Re = config.getValue<double>("Re");
+ double dx = config.getValue<double>("dx");
+ bool logToFile = config.getValue<bool>("logToFile");
+ //double restartStep = config.getValue<double>("restartStep");
+ //double cpStart = config.getValue<double>("cpStart");
+ //double cpStep = config.getValue<double>("cpStep");
+ bool newStart = config.getValue<bool>("newStart");
+
+ double beta = 12 * sigma / interfaceThickness;
+ double kappa = 1.5 * interfaceThickness * sigma;
+
+ SPtr<Communicator> comm = MPICommunicator::getInstance();
+ int myid = comm->getProcessID();
+
+ if (myid == 0)
+ UBLOG(logINFO, "Droplet Test: Start!");
+
+ if (logToFile) {
+#if defined(__unix__)
+ if (myid == 0) {
+ const char *str = pathname.c_str();
+ mkdir(str, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+ }
+#endif
+
+ if (myid == 0) {
+ stringstream logFilename;
+ logFilename << pathname + "/logfile" + UbSystem::toString(UbSystem::getTimeStamp()) + ".txt";
+ UbLog::output_policy::setStream(logFilename.str());
+ }
+ }
+
+ //Sleep(30000);
+
+ // LBMReal dLB = 0; // = length[1] / dx;
+ LBMReal rhoLB = 0.0;
+ LBMReal nuLB = nuL; //(uLB*dLB) / Re;
+
+ SPtr<LBMUnitConverter> conv(new LBMUnitConverter());
+
+ //const int baseLevel = 0;
+
+ SPtr<LBMKernel> kernel;
+
+ //kernel = SPtr<LBMKernel>(new MultiphaseScratchCumulantLBMKernel());
+ kernel = SPtr<LBMKernel>(new MultiphaseCumulantLBMKernel());
+ //kernel = SPtr<LBMKernel>(new MultiphaseTwoPhaseFieldsCumulantLBMKernel());
+
+ kernel->setWithForcing(true);
+ kernel->setForcingX1(gr);
+ kernel->setForcingX2(0.0);
+ kernel->setForcingX3(0.0);
+
+ kernel->setPhiL(phiL);
+ kernel->setPhiH(phiH);
+ kernel->setPhaseFieldRelaxation(tauH);
+ kernel->setMobility(mob);
+
+ SPtr<BCProcessor> bcProc(new BCProcessor());
+ // BCProcessorPtr bcProc(new ThinWallBCProcessor());
+
+ kernel->setBCProcessor(bcProc);
+
+ SPtr<Grid3D> grid(new Grid3D(comm));
+ grid->setDeltaX(dx);
+ grid->setBlockNX(blocknx[0], blocknx[1], blocknx[2]);
+ grid->setPeriodicX1(true);
+ grid->setPeriodicX2(true);
+ grid->setPeriodicX3(true);
+
+ //////////////////////////////////////////////////////////////////////////
+ // restart
+ //SPtr<UbScheduler> rSch(new UbScheduler(cpStep, cpStart));
+ ////SPtr<MPIIORestartCoProcessor> rcp(new MPIIORestartCoProcessor(grid, rSch, pathname, comm));
+ ////SPtr<MPIIOMigrationCoProcessor> rcp(new MPIIOMigrationCoProcessor(grid, rSch, pathname, comm));
+ //SPtr<MPIIOMigrationBECoProcessor> rcp(new MPIIOMigrationBECoProcessor(grid, rSch, pathname, comm));
+ //rcp->setNu(nuLB);
+ //rcp->setNuLG(nuL, nuG);
+ //rcp->setDensityRatio(densityRatio);
+
+ //rcp->setLBMKernel(kernel);
+ //rcp->setBCProcessor(bcProc);
+ //////////////////////////////////////////////////////////////////////////
+
+ if (newStart) {
+
+ // bounding box
+ double g_minX1 = boundingBox[0];
+ double g_minX2 = boundingBox[2];
+ double g_minX3 = boundingBox[4];
+
+ double g_maxX1 = boundingBox[1];
+ double g_maxX2 = boundingBox[3];
+ double g_maxX3 = boundingBox[5];
+
+ // geometry
+ SPtr<GbObject3D> gridCube(new GbCuboid3D(g_minX1, g_minX2, g_minX3, g_maxX1, g_maxX2, g_maxX3));
+ if (myid == 0)
+ GbSystem3D::writeGeoObject(gridCube.get(), pathname + "/geo/gridCube",
+ WbWriterVtkXmlBinary::getInstance());
+
+ if (myid == 0) {
+ UBLOG(logINFO, "uLb = " << uLB);
+ UBLOG(logINFO, "rho = " << rhoLB);
+ UBLOG(logINFO, "nuLb = " << nuLB);
+ UBLOG(logINFO, "Re = " << Re);
+ UBLOG(logINFO, "dx = " << dx);
+ UBLOG(logINFO, "Preprocess - start");
+ }
+
+ GenBlocksGridVisitor genBlocks(gridCube);
+ grid->accept(genBlocks);
+
+
+ SPtr<WriteBlocksCoProcessor> ppblocks(new WriteBlocksCoProcessor(
+ grid, SPtr<UbScheduler>(new UbScheduler(1)), pathname, WbWriterVtkXmlBinary::getInstance(), comm));
+
+ //SPtr<Grid3DVisitor> metisVisitor(
+ // new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased, D3Q27System::BSW));
+ //InteractorsHelper intHelper(grid, metisVisitor);
+ //intHelper.selectBlocks();
+
+ ppblocks->process(0);
+ ppblocks.reset();
+
+ unsigned long long numberOfBlocks = (unsigned long long)grid->getNumberOfBlocks();
+ int ghostLayer = 3;
+ unsigned long long numberOfNodesPerBlock =
+ (unsigned long long)(blocknx[0]) * (unsigned long long)(blocknx[1]) * (unsigned long long)(blocknx[2]);
+ unsigned long long numberOfNodes = numberOfBlocks * numberOfNodesPerBlock;
+ unsigned long long numberOfNodesPerBlockWithGhostLayer =
+ numberOfBlocks * (blocknx[0] + ghostLayer) * (blocknx[1] + ghostLayer) * (blocknx[2] + ghostLayer);
+ double needMemAll =
+ double(numberOfNodesPerBlockWithGhostLayer * (27 * sizeof(double) + sizeof(int) + sizeof(float) * 4));
+ double needMem = needMemAll / double(comm->getNumberOfProcesses());
+
+ if (myid == 0) {
+ UBLOG(logINFO, "Number of blocks = " << numberOfBlocks);
+ UBLOG(logINFO, "Number of nodes = " << numberOfNodes);
+ int minInitLevel = grid->getCoarsestInitializedLevel();
+ int maxInitLevel = grid->getFinestInitializedLevel();
+ for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ int nobl = grid->getNumberOfBlocks(level);
+ UBLOG(logINFO, "Number of blocks for level " << level << " = " << nobl);
+ UBLOG(logINFO, "Number of nodes for level " << level << " = " << nobl * numberOfNodesPerBlock);
+ }
+ UBLOG(logINFO, "Necessary memory = " << needMemAll << " bytes");
+ UBLOG(logINFO, "Necessary memory per process = " << needMem << " bytes");
+ UBLOG(logINFO, "Available memory per process = " << availMem << " bytes");
+ }
+
+ MultiphaseSetKernelBlockVisitor kernelVisitor(kernel, nuL, nuG, densityRatio, beta, kappa, theta, availMem,
+ needMem);
+
+ grid->accept(kernelVisitor);
+
+ if (refineLevel > 0) {
+ SetUndefinedNodesBlockVisitor undefNodesVisitor;
+ grid->accept(undefNodesVisitor);
+ }
+
+
+ //intHelper.setBC();
+
+ //grid->accept(bcVisitor);
+
+ // initialization of distributions
+ LBMReal x1c = (g_maxX1 - g_minX1-1)/2;
+ LBMReal x2c = (g_maxX2 - g_minX2-1)/2;
+ LBMReal x3c = (g_maxX3 - g_minX3-1)/2;
+ mu::Parser fct1;
+ fct1.SetExpr("0.5-0.5*tanh(2*(sqrt((x1-x1c)^2+(x2-x2c)^2+(x3-x3c)^2)-radius)/interfaceThickness)");
+ fct1.DefineConst("x1c", x1c);
+ fct1.DefineConst("x2c", x2c);
+ fct1.DefineConst("x3c", x3c);
+ fct1.DefineConst("radius", radius);
+ fct1.DefineConst("interfaceThickness", interfaceThickness);
+
+ mu::Parser fct2;
+ fct2.SetExpr("0.5*uLB-uLB*0.5*tanh(2*(sqrt((x1-x1c)^2+(x2-x2c)^2+(x3-x3c)^2)-radius)/interfaceThickness)");
+ fct2.DefineConst("uLB", uLB);
+ fct2.DefineConst("x1c", x1c);
+ fct2.DefineConst("x2c", x2c);
+ fct2.DefineConst("x3c", x3c);
+ fct2.DefineConst("radius", radius);
+ fct2.DefineConst("interfaceThickness", interfaceThickness);
+
+ MultiphaseInitDistributionsBlockVisitor initVisitor(densityRatio, interfaceThickness, radius);
+ initVisitor.setPhi(fct1);
+ initVisitor.setVx1(fct2);
+ grid->accept(initVisitor);
+
+ // boundary conditions grid
+ {
+ SPtr<UbScheduler> geoSch(new UbScheduler(1));
+ SPtr<WriteBoundaryConditionsCoProcessor> ppgeo(new WriteBoundaryConditionsCoProcessor(
+ grid, geoSch, pathname, WbWriterVtkXmlBinary::getInstance(), comm));
+ ppgeo->process(0);
+ ppgeo.reset();
+ }
+
+ if (myid == 0)
+ UBLOG(logINFO, "Preprocess - end");
+ } else {
+ if (myid == 0) {
+ UBLOG(logINFO, "Parameters:");
+ UBLOG(logINFO, "uLb = " << uLB);
+ UBLOG(logINFO, "rho = " << rhoLB);
+ UBLOG(logINFO, "nuLb = " << nuLB);
+ UBLOG(logINFO, "Re = " << Re);
+ UBLOG(logINFO, "dx = " << dx);
+ UBLOG(logINFO, "number of levels = " << refineLevel + 1);
+ UBLOG(logINFO, "numOfThreads = " << numOfThreads);
+ UBLOG(logINFO, "path = " << pathname);
+ }
+
+ //rcp->restart((int)restartStep);
+ //grid->setTimeStep(restartStep);
+
+ if (myid == 0)
+ UBLOG(logINFO, "Restart - end");
+ }
+
+ TwoDistributionsSetConnectorsBlockVisitor setConnsVisitor(comm);
+ grid->accept(setConnsVisitor);
+
+ //ThreeDistributionsSetConnectorsBlockVisitor setConnsVisitor(comm);
+ //grid->accept(setConnsVisitor);
+
+ SPtr<UbScheduler> visSch(new UbScheduler(outTime));
+ SPtr<WriteMultiphaseQuantitiesCoProcessor> pp(new WriteMultiphaseQuantitiesCoProcessor(
+ grid, visSch, pathname, WbWriterVtkXmlBinary::getInstance(), conv, comm));
+ //SPtr<WriteMacroscopicQuantitiesCoProcessor> pp(new WriteMacroscopicQuantitiesCoProcessor(
+ // grid, visSch, pathname, WbWriterVtkXmlBinary::getInstance(), conv, comm));
+
+ SPtr<UbScheduler> nupsSch(new UbScheduler(10, 30, 100));
+ SPtr<NUPSCounterCoProcessor> npr(new NUPSCounterCoProcessor(grid, nupsSch, numOfThreads, comm));
+
+ SPtr<UbScheduler> stepGhostLayer(new UbScheduler(1));
+ SPtr<Calculator> calculator(new BasicCalculator(grid, stepGhostLayer, endTime));
+ calculator->addCoProcessor(npr);
+ calculator->addCoProcessor(pp);
+ //calculator->addCoProcessor(rcp);
+
+
+
+ if (myid == 0)
+ UBLOG(logINFO, "Simulation-start");
+ calculator->calculate();
+ if (myid == 0)
+ UBLOG(logINFO, "Simulation-end");
+ } catch (std::exception &e) {
+ cerr << e.what() << endl << flush;
+ } catch (std::string &s) {
+ cerr << s << endl;
+ } catch (...) {
+ cerr << "unknown exception" << endl;
+ }
+}
+int main(int argc, char *argv[])
+{
+ // Sleep(30000);
+ if (argv != NULL) {
+ if (argv[1] != NULL) {
+ run(string(argv[1]));
+ } else {
+ cout << "Configuration file is missing!" << endl;
+ }
+ }
+}
diff --git a/apps/cpu/PoiseuilleFlow/CMakeLists.txt b/apps/cpu/PoiseuilleFlow/CMakeLists.txt
index 43ea7697a846d3453bcdf8e53f6b5a9622ee9e71..1959719d81013762d37f655b342f755135c9ef85 100644
--- a/apps/cpu/PoiseuilleFlow/CMakeLists.txt
+++ b/apps/cpu/PoiseuilleFlow/CMakeLists.txt
@@ -1,25 +1,6 @@
-CMAKE_MINIMUM_REQUIRED(VERSION 2.8)
-
-########################################################
-## C++ PROJECT ###
-########################################################
PROJECT(pf)
-INCLUDE(${APPS_ROOT}/IncludsList.cmake)
-
-#################################################################
-### LOCAL FILES ###
-#################################################################
-FILE(GLOB SPECIFIC_FILES ${CMAKE_CURRENT_SOURCE_DIR}/*.h
- ${CMAKE_CURRENT_SOURCE_DIR}/*.cpp
- ${CMAKE_CURRENT_SOURCE_DIR}/*.hpp )
-
-SET(ALL_SOURCES ${ALL_SOURCES} ${SPECIFIC_FILES})
-SOURCE_GROUP(src FILES ${SPECIFIC_FILES})
-
-SET(CAB_ADDITIONAL_LINK_LIBRARIES VirtualFluids)
+vf_add_library(BUILDTYPE binary PRIVATE_LINK VirtualFluidsCore muparser basics ${MPI_CXX_LIBRARIES} FILES pf.cpp pf1.cpp )
-#################################################################
-### CREATE PROJECT ###
-#################################################################
-CREATE_CAB_PROJECT(pf BINARY)
+vf_get_library_name (library_name)
+target_include_directories(${library_name} PRIVATE ${APPS_ROOT_CPU})
\ No newline at end of file
diff --git a/apps/cpu/PoiseuilleFlow/pf1.cpp b/apps/cpu/PoiseuilleFlow/pf1.cpp
index e7f4bbf1baa03e235a4263c8c9a1293c1d51d7f3..3880e9583dd07bdad7fcd11272f0a372155ef654 100644
--- a/apps/cpu/PoiseuilleFlow/pf1.cpp
+++ b/apps/cpu/PoiseuilleFlow/pf1.cpp
@@ -137,8 +137,7 @@ void pf1()
grid->accept(initVisitor);
//set connectors
- InterpolationProcessorPtr iProcessor(new IncompressibleOffsetInterpolationProcessor());
- SetConnectorsBlockVisitor setConnsVisitor(comm, true, D3Q27System::ENDDIR, nuLB, iProcessor);
+ OneDistributionSetConnectorsBlockVisitor setConnsVisitor(comm);
grid->accept(setConnsVisitor);
SPtr<UbScheduler> mSch(new UbScheduler(cpStep, cpStart));
diff --git a/apps/cpu/ViskomatXL/viskomat.cfg b/apps/cpu/ViskomatXL/viskomat.cfg
index 71228231e36810fca21ebe752be2488b5c56264d..4227ba9f821cfa9336a69c14b828829c6ff2ccb1 100644
--- a/apps/cpu/ViskomatXL/viskomat.cfg
+++ b/apps/cpu/ViskomatXL/viskomat.cfg
@@ -1,4 +1,4 @@
-outputPath = d:/temp/viskomat
+outputPath = d:/temp/viskomatCylinderRestartTest3_Migration
geoPath = d:/Projects/TRR277/Project/WP1/Rheometer/Aileen
geoFile = fishbone.stl
@@ -7,24 +7,44 @@ availMem = 8e9
logToFile = false
blocknx = 16 16 16
+#blocknx = 1 8 8
#boundingBox = -4 171 -9.5 155.5 -76.5 82.5
-boundingBox = -4 166 -9.5 155.5 -76.5 82.5
+#boundingBox = -4 166 -9.5 155.5 -76.5 82.5
+
+#boundingBox = -4 166 0 165 0 165
+
+#boundingBox = -4 166 -82.5 82.5 -82.5 82.5
+
+boundingBox = 0 140 -82.5 82.5 -82.5 82.5
+
+# around X
+#blocknx = 1 16 16
+#boundingBox = 0 1 0 165 0 165
+
+# around Y
+#blocknx = 16 1 16
+#boundingBox = 0 165 0 1 0 165
+
+#zero test
+#blocknx = 8 8 8
+#boundingBox = 0 8 0 8 0 8
+
deltax = 1
refineLevel = 0
#nuLB = 1.5e-4
-OmegaLB = 1e-5
+OmegaLB = 1e-4
tau0 = 20e-7
resolution = 32
scaleFactor = 1
newStart = true
-restartStep = 100000
+restartStep = 10000
cpStart = 10000
cpStep = 10000
-outTime = 10000
-endTime = 100000
\ No newline at end of file
+outTime = 1000
+endTime = 1000000
\ No newline at end of file
diff --git a/apps/cpu/ViskomatXL/viskomat.cpp b/apps/cpu/ViskomatXL/viskomat.cpp
index 113d9c6da16bff21267bb723d48adb2a3c9d5619..91dfb050901571b5cf37e02cfca5ab8c7a8eb8cb 100644
--- a/apps/cpu/ViskomatXL/viskomat.cpp
+++ b/apps/cpu/ViskomatXL/viskomat.cpp
@@ -81,11 +81,11 @@ void bflow(string configname)
//cpStep = endTime;
//double Re = 1.38230076758;
- double N = 80;
- double Omega = 2 * UbMath::PI / 60.0 * N;
- double mu = 1;
- double R = 0.165 / 2.0;
- double rho = 970;
+ double N = 80; //rpm
+ double Omega = 2 * UbMath::PI / 60.0 * N; //rad/s
+ double mu = 1; //Pa s
+ double R = 0.165 / 2.0; //m
+ double rho = 970; //kg/m^3
double Re = Omega * R * R * rho / mu;
double nuLB = OmegaLB * R * 1e3 * R * 1e3 / Re;
@@ -151,21 +151,36 @@ void bflow(string configname)
SPtr<BCAdapter> slipBCAdapter(new SlipBCAdapter());
slipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new SimpleSlipBCAlgorithm()));
- mu::Parser fctVx;
- //fctVx.SetExpr("omega*(r-x2)");
- fctVx.SetExpr("-Omega*(x2-r)");
- fctVx.DefineConst("Omega", OmegaLB);
- //fctVx.DefineConst("r", R0);
- fctVx.DefineConst("r", 0.5 * (g_maxX2 - g_minX2));
-
+ //// rotation around X-axis
mu::Parser fctVy;
- fctVy.SetExpr("Omega*(x3-r)");
+ fctVy.SetExpr("-Omega*(x3-z0-r)");
fctVy.DefineConst("Omega", OmegaLB);
- //fctVy.DefineConst("r", R0);
- fctVy.DefineConst("r", 0.5 * (g_maxX2 - g_minX2));
+ fctVy.DefineConst("r", 0.5 * (g_maxX3 - g_minX3));
+ fctVy.DefineConst("z0", g_minX3);
mu::Parser fctVz;
- fctVz.SetExpr("0.0");
+ fctVz.SetExpr("Omega*(x2-y0-r)");
+ fctVz.DefineConst("Omega", OmegaLB);
+ fctVz.DefineConst("r", 0.5 * (g_maxX2 - g_minX2));
+ fctVz.DefineConst("y0", g_minX2);
+
+ mu::Parser fctVx;
+ fctVx.SetExpr("0.0");
+
+ // rotation around Y-axis
+ //mu::Parser fctVz;
+ //// fctVx.SetExpr("omega*(r-x2)");
+ //fctVz.SetExpr("Omega*(x1-r)");
+ //fctVz.DefineConst("Omega", OmegaLB);
+ //fctVz.DefineConst("r", 0.5 * (g_maxX1 - g_minX1));
+
+ //mu::Parser fctVx;
+ //fctVx.SetExpr("-Omega*(x3-r)");
+ //fctVx.DefineConst("Omega", OmegaLB);
+ //fctVx.DefineConst("r", 0.5 * (g_maxX1 - g_minX1));
+
+ //mu::Parser fctVy;
+ //fctVy.SetExpr("0.0");
SPtr<BCAdapter> velocityBCAdapter(new VelocityBCAdapter(true, true, true, fctVx, fctVy, fctVz, 0, BCFunction::INFCONST));
velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new VelocityBCAlgorithm()));
@@ -188,8 +203,11 @@ void bflow(string configname)
SPtr<BCProcessor> bcProc;
bcProc = SPtr<BCProcessor>(new BCProcessor());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new BGKLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CumulantLBMKernel());
- SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CompressibleCumulant4thOrderViscosityLBMKernel());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CompressibleCumulant4thOrderViscosityLBMKernel());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new IncompressibleCumulantLBMKernel());
+ SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CumulantK17LBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new RheologyBinghamModelLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new HerschelBulkleyModelLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new BinghamModelLBMKernel());
@@ -211,28 +229,64 @@ void bflow(string configname)
//restart
SPtr<UbScheduler> mSch(new UbScheduler(cpStep, cpStart));
SPtr<MPIIOMigrationCoProcessor> restartCoProcessor(new MPIIOMigrationCoProcessor(grid, mSch, outputPath, comm));
+ //SPtr<MPIIORestartCoProcessor> restartCoProcessor(new MPIIORestartCoProcessor(grid, mSch, outputPath, comm));
restartCoProcessor->setLBMKernel(kernel);
restartCoProcessor->setBCProcessor(bcProc);
//restartCoProcessor->setNu(k);
//////////////////////////////////////////////////////////////////////////
////stator
- //SPtr<GbObject3D> stator(new GbCylinder3D(0.5 * g_maxX1, 0.5 * g_maxX2, g_minX3-2.0*deltax, 0.5 * g_maxX1, 0.5 * g_maxX2, g_maxX3+ 2.0 * deltax, 0.5 * g_maxX1));
- SPtr<GbTriFaceMesh3D> stator = make_shared<GbTriFaceMesh3D>();
- stator->readMeshFromSTLFileBinary(geoPath + "/" + geoFile, false);
+ // rotation around X-axis
+ SPtr<GbObject3D> stator(new GbCylinder3D(g_minX1 - 3.0 * deltax, g_minX2 + 0.5 * (g_maxX2 - g_minX2),
+ g_minX3 + 0.5 * (g_maxX3 - g_minX3), g_maxX1 + 3.0 * deltax,
+ g_minX2 + 0.5 * (g_maxX2 - g_minX2), g_minX3 + 0.5 * (g_maxX3 - g_minX3), 0.5 * (g_maxX3 - g_minX3) * 0.5));
+
+ // rotation around Y-axis
+ //SPtr<GbObject3D> stator(new GbCylinder3D(g_minX1 + 0.5 * (g_maxX1 - g_minX1), g_minX2 - 3.0 * deltax,
+ // g_minX3 + 0.5 * (g_maxX3 - g_minX3), g_minX1 + 0.5 * (g_maxX1 - g_minX1),
+ // g_maxX2 + 3.0 * deltax, g_minX3 + 0.5 * (g_maxX3 - g_minX3),
+ // 0.5 * (g_maxX3 - g_minX3) * 0.5));
+
+ SPtr<D3Q27Interactor> statorInt =
+ SPtr<D3Q27Interactor>(new D3Q27Interactor(stator, grid, noSlipBCAdapter, Interactor3D::SOLID));
+
+ //SPtr<GbTriFaceMesh3D> stator = make_shared<GbTriFaceMesh3D>();
+ //stator->readMeshFromSTLFileBinary(geoPath + "/" + geoFile, false);
+ //stator->translate(4.0, -73.0, -6.0);
GbSystem3D::writeGeoObject(stator.get(), outputPath + "/geo/stator", WbWriterVtkXmlBinary::getInstance());
-
- SPtr<D3Q27Interactor> statorInt = SPtr<D3Q27TriFaceMeshInteractor>(
- new D3Q27TriFaceMeshInteractor(stator, grid, velocityBCAdapter, Interactor3D::SOLID, Interactor3D::EDGES));
+
+ //SPtr<D3Q27Interactor> statorInt = SPtr<D3Q27TriFaceMeshInteractor>(
+ // new D3Q27TriFaceMeshInteractor(stator, grid, noSlipBCAdapter, Interactor3D::SOLID, Interactor3D::EDGES));
////rotor (cylinder)
- SPtr<GbObject3D> rotor(new GbCylinder3D(g_minX1, g_minX2 + 0.5 * (g_maxX2 - g_minX2),
- g_minX3 + 0.5 * (g_maxX3 - g_minX3),
- g_maxX1,
+ // rotation around X-axis
+ SPtr<GbObject3D> rotor(new GbCylinder3D(
+ g_minX1 - 3.0 * deltax, g_minX2 + 0.5 * (g_maxX2 - g_minX2),
+ g_minX3 + 0.5 * (g_maxX3 - g_minX3), g_maxX1 + 3.0 * deltax,
g_minX2 + 0.5 * (g_maxX2 - g_minX2), g_minX3 + 0.5 * (g_maxX3 - g_minX3), 0.5 * (g_maxX3 - g_minX3)));
+ // rotation around Y-axis
+ //SPtr<GbObject3D> rotor(new GbCylinder3D(g_minX1 + 0.5 * (g_maxX1 - g_minX1), g_minX2 - 3.0 * deltax,
+ // g_minX3 + 0.5 * (g_maxX3 - g_minX3), g_minX1 + 0.5 * (g_maxX1 - g_minX1),
+ // g_maxX2 + 3.0 * deltax, g_minX3 + 0.5 * (g_maxX3 - g_minX3),
+ // 0.5 * (g_maxX3 - g_minX3)));
+
GbSystem3D::writeGeoObject(rotor.get(), outputPath + "/geo/rotor", WbWriterVtkXmlBinary::getInstance());
- SPtr<D3Q27Interactor> rotorInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(rotor, grid, noSlipBCAdapter, Interactor3D::INVERSESOLID));
+ SPtr<D3Q27Interactor> rotorInt =
+ SPtr<D3Q27Interactor>(new D3Q27Interactor(rotor, grid, velocityBCAdapter, Interactor3D::INVERSESOLID));
+
+ //walls
+ GbCuboid3DPtr wallXmin(new GbCuboid3D(g_minX1 - deltax, g_minX2 - deltax, g_minX3 - deltax, g_minX1,
+ g_maxX2 + deltax, g_maxX3 + deltax));
+ if (myid == 0) GbSystem3D::writeGeoObject(wallXmin.get(), outputPath + "/geo/wallXmin", WbWriterVtkXmlASCII::getInstance());
+
+ GbCuboid3DPtr wallXmax(new GbCuboid3D(g_maxX1, g_minX2 - deltax, g_minX3 - deltax, g_maxX1 + (double)blocknx[0]*deltax,
+ g_maxX2 + deltax, g_maxX3 + deltax));
+ if (myid == 0) GbSystem3D::writeGeoObject(wallXmax.get(), outputPath + "/geo/wallXmax", WbWriterVtkXmlASCII::getInstance());
+
+ //wall interactors
+ SPtr<D3Q27Interactor> wallXminInt(new D3Q27Interactor(wallXmin, grid, slipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> wallXmaxInt(new D3Q27Interactor(wallXmax, grid, slipBCAdapter, Interactor3D::SOLID));
if (myid == 0)
{
@@ -281,19 +335,6 @@ void bflow(string configname)
}
- //walls
- GbCuboid3DPtr wallXmin(new GbCuboid3D(g_minX1 - deltax, g_minX2 - deltax, g_minX3 - deltax, g_minX1,
- g_maxX2 + deltax, g_maxX3 + deltax));
- if (myid == 0) GbSystem3D::writeGeoObject(wallXmin.get(), outputPath + "/geo/wallXmin", WbWriterVtkXmlASCII::getInstance());
-
- GbCuboid3DPtr wallXmax(new GbCuboid3D(g_maxX1, g_minX2 - deltax, g_minX3 - deltax, g_maxX1 + deltax,
- g_maxX2 + deltax, g_maxX3 + deltax));
- if (myid == 0) GbSystem3D::writeGeoObject(wallXmax.get(), outputPath + "/geo/wallXmax", WbWriterVtkXmlASCII::getInstance());
-
- //wall interactors
- SPtr<D3Q27Interactor> wallXminInt(new D3Q27Interactor(wallXmin, grid, noSlipBCAdapter, Interactor3D::SOLID));
- SPtr<D3Q27Interactor> wallXmaxInt(new D3Q27Interactor(wallXmax, grid, slipBCAdapter, Interactor3D::SOLID));
-
////////////////////////////////////////////
//METIS
SPtr<Grid3DVisitor> metisVisitor(new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased, D3Q27System::BSW, MetisPartitioner::KWAY));
@@ -353,6 +394,9 @@ void bflow(string configname)
InitDistributionsBlockVisitor initVisitor;
grid->accept(initVisitor);
+ SPtr<UbScheduler> geoSch(new UbScheduler(1));
+ WriteBoundaryConditionsCoProcessor ppgeo = WriteBoundaryConditionsCoProcessor(grid, geoSch, outputPath, WbWriterVtkXmlBinary::getInstance(), comm);
+ ppgeo.process(0);
if (myid == 0) UBLOG(logINFO, "Preprozess - end");
}
@@ -360,12 +404,24 @@ void bflow(string configname)
{
restartCoProcessor->restart((int)restartStep);
grid->setTimeStep(restartStep);
- SetBcBlocksBlockVisitor v1(rotorInt);
- grid->accept(v1);
- rotorInt->initInteractor();
- SetBcBlocksBlockVisitor v2(statorInt);
- grid->accept(v2);
+
+ //SetBcBlocksBlockVisitor v1(wallXminInt);
+ //grid->accept(v1);
+ //wallXminInt->initInteractor();
+ //
+ //SetBcBlocksBlockVisitor v2(wallXmaxInt);
+ //grid->accept(v2);
+ //wallXmaxInt->initInteractor();
+
+ SetBcBlocksBlockVisitor v3(statorInt);
+ grid->accept(v3);
statorInt->initInteractor();
+
+ SetBcBlocksBlockVisitor v4(rotorInt);
+ grid->accept(v4);
+ rotorInt->initInteractor();
+
+
}
omp_set_num_threads(numOfThreads);
@@ -381,10 +437,6 @@ void bflow(string configname)
grid->accept(bcVisitor);
- SPtr<UbScheduler> geoSch(new UbScheduler(1));
- WriteBoundaryConditionsCoProcessor ppgeo = WriteBoundaryConditionsCoProcessor(grid, geoSch, outputPath, WbWriterVtkXmlBinary::getInstance(), comm);
- ppgeo.process(0);
-
SPtr<UbScheduler> nupsSch(new UbScheduler(10, 30, 100));
SPtr<CoProcessor> npr(new NUPSCounterCoProcessor(grid, nupsSch, numOfThreads, comm));
@@ -392,13 +444,13 @@ void bflow(string configname)
SPtr<UbScheduler> visSch(new UbScheduler(outTime));
//SPtr<UbScheduler> visSch(new UbScheduler(10,1));
SPtr<WriteMacroscopicQuantitiesCoProcessor> writeMQCoProcessor(new WriteMacroscopicQuantitiesCoProcessor(grid, visSch, outputPath, WbWriterVtkXmlBinary::getInstance(), SPtr<LBMUnitConverter>(new LBMUnitConverter()), comm));
- //writeMQCoProcessor->process(0);
+ //writeMQCoProcessor->process(100);
SPtr<UbScheduler> forceSch(new UbScheduler(100));
- SPtr<CalculateTorqueCoProcessor> fp = make_shared<CalculateTorqueCoProcessor>(grid, forceSch, outputPath + "/torque/TorqueRotor.txt", comm);
+ SPtr<CalculateTorqueCoProcessor> fp = make_shared<CalculateTorqueCoProcessor>(grid, forceSch, outputPath + "/torque/TorqueRotor.csv", comm);
fp->addInteractor(rotorInt);
- //SPtr<CalculateTorqueCoProcessor> fp2 = make_shared<CalculateTorqueCoProcessor>(grid, forceSch, outputPath + "/torque/TorqueStator.txt", comm);
- //fp2->addInteractor(statorInt);
+ SPtr<CalculateTorqueCoProcessor> fp2 = make_shared<CalculateTorqueCoProcessor>(grid, forceSch, outputPath + "/torque/TorqueStator.csv", comm);
+ fp2->addInteractor(statorInt);
//SPtr<WriteThixotropyQuantitiesCoProcessor> writeThixotropicMQCoProcessor(new WriteThixotropyQuantitiesCoProcessor(grid, visSch, outputPath, WbWriterVtkXmlBinary::getInstance(), SPtr<LBMUnitConverter>(new LBMUnitConverter()), comm));
@@ -406,7 +458,7 @@ void bflow(string configname)
SPtr<Calculator> calculator(new BasicCalculator(grid, stepGhostLayer, endTime));
calculator->addCoProcessor(npr);
calculator->addCoProcessor(fp);
- //calculator->addCoProcessor(fp2);
+ calculator->addCoProcessor(fp2);
calculator->addCoProcessor(writeMQCoProcessor);
//calculator->addCoProcessor(writeThixotropicMQCoProcessor);
calculator->addCoProcessor(restartCoProcessor);
diff --git a/apps/cpu/rheometer/rheometer.cfg b/apps/cpu/rheometer/rheometer.cfg
index 344062fb9f086cf163542285e5d9d745df3d0d80..9eec8c6ded9b7a5ab8d1e6177c43354a4514ccc3 100644
--- a/apps/cpu/rheometer/rheometer.cfg
+++ b/apps/cpu/rheometer/rheometer.cfg
@@ -1,12 +1,12 @@
-outputPath = d:/temp/rheometer/rheometerBinghamqQBB/rheometerBingham_tau_20e-7_nu_1.5e-3_new_lim_test
-
+#outputPath = d:/temp/rheometer/rheometerBinghamqQBB/rheometerBingham_tau_20e-7_nu_1.5e-3_new_lim_test
+outputPath = d:/temp/Taylor-CouetteFlowIncompCum
viscosityPath = d:/Projects/VirtualFluidsCombined/apps/cpu/rheometer
-numOfThreads = 4
+numOfThreads = 1
availMem = 8e9
logToFile = false
-blocknx = 8 8 1
+blocknx = 16 16 1 #8 8 1
#boundingBox = 32 32 1
deltax = 1
@@ -15,17 +15,20 @@ deltax = 1
refineLevel = 0
-OmegaLB = 4e-5
+#OmegaLB = 4e-5
+#tau0 = 20e-7
+
+OmegaLB = 1e-4
tau0 = 20e-7
-resolution = 32
+resolution = 165
scaleFactor = 1
newStart = true
restartStep = 100000
-cpStart = 10000
-cpStep = 10000
+cpStart = 10000000
+cpStep = 10000000
-outTime = 10000
-endTime = 100000
\ No newline at end of file
+outTime = 1
+endTime = 10
\ No newline at end of file
diff --git a/apps/cpu/rheometer/rheometer.cpp b/apps/cpu/rheometer/rheometer.cpp
index 3f87dee3451f98fa47a26a1b032414cab5a513c2..f6f98c122c3197f1a080fd335f8edfc9ee1f4e33 100644
--- a/apps/cpu/rheometer/rheometer.cpp
+++ b/apps/cpu/rheometer/rheometer.cpp
@@ -38,7 +38,7 @@ void bflow(string configname)
viscosity.load(viscosityPath + "/viscosity.cfg");
double nuLB = viscosity.getValue<double>("nuLB");
- outputPath = outputPath + "/rheometerBingham_" + config.getValue<string>("resolution") + "_" + config.getValue<string>("OmegaLB");
+ //outputPath = outputPath + "/rheometerBingham_" + config.getValue<string>("resolution") + "_" + config.getValue<string>("OmegaLB");
SPtr<Communicator> comm = MPICommunicator::getInstance();
int myid = comm->getProcessID();
@@ -89,12 +89,20 @@ void bflow(string configname)
//bounding box
+ //double g_minX1 = 0;
+ //double g_minX2 = 0;
+ //double g_minX3 = 0;
+
+ //double g_maxX1 = resolution;// boundingBox[0];
+ //double g_maxX2 = resolution;// boundingBox[1];
+ //double g_maxX3 = 1.0; // boundingBox[2];
+
double g_minX1 = 0;
double g_minX2 = 0;
double g_minX3 = 0;
- double g_maxX1 = resolution;// boundingBox[0];
- double g_maxX2 = resolution;// boundingBox[1];
+ double g_maxX1 = resolution; // boundingBox[0];
+ double g_maxX2 = resolution; // boundingBox[1];
double g_maxX3 = 1.0; // boundingBox[2];
//double g_minX1 = -boundingBox[0]/2.0;
@@ -132,9 +140,9 @@ void bflow(string configname)
//thix->setOmegaMin(omegaMin);
SPtr<BCAdapter> noSlipBCAdapter(new NoSlipBCAdapter());
- //noSlipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new NoSlipBCAlgorithm()));
+ noSlipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new NoSlipBCAlgorithm()));
//noSlipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new RheologyHerschelBulkleyModelNoSlipBCAlgorithm()));
- noSlipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new RheologyBinghamModelNoSlipBCAlgorithm()));
+ //noSlipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new RheologyBinghamModelNoSlipBCAlgorithm()));
//SPtr<BCAdapter> slipBCAdapter(new SlipBCAdapter());
//slipBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new SimpleSlipBCAlgorithm()));
@@ -155,11 +163,26 @@ void bflow(string configname)
mu::Parser fctVz;
fctVz.SetExpr("0.0");
+
+ //// rotation around X-axis
+ //mu::Parser fctVy;
+ //fctVy.SetExpr("-Omega*(x3-r)");
+ //fctVy.DefineConst("Omega", OmegaLB);
+ //fctVy.DefineConst("r", 0.5 * (g_maxX2 - g_minX2));
+
+ //mu::Parser fctVz;
+ //fctVz.SetExpr("Omega*(x2-r)");
+ //fctVz.DefineConst("Omega", OmegaLB);
+ //fctVz.DefineConst("r", 0.5 * (g_maxX2 - g_minX2));
+
+ //mu::Parser fctVx;
+ //fctVx.SetExpr("0.0");
+
SPtr<BCAdapter> velocityBCAdapter(new VelocityBCAdapter(true, true, true, fctVx, fctVy, fctVz, 0, BCFunction::INFCONST));
- //velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new VelocityBCAlgorithm()));
+ velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new VelocityBCAlgorithm()));
//velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new SimpleVelocityBCAlgorithm()));
//velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new VelocityWithDensityBCAlgorithm()));
- velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new RheologyBinghamModelVelocityBCAlgorithm()));
+ //velocityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new RheologyBinghamModelVelocityBCAlgorithm()));
//SPtr<BCAdapter> densityBCAdapter(new DensityBCAdapter());
//densityBCAdapter->setBcAlgorithm(SPtr<BCAlgorithm>(new NonEqDensityBCAlgorithm()));
@@ -176,9 +199,12 @@ void bflow(string configname)
SPtr<BCProcessor> bcProc;
bcProc = SPtr<BCProcessor>(new BCProcessor());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new BGKLBMKernel());
+ SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new IncompressibleCumulantLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CumulantLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CompressibleCumulant4thOrderViscosityLBMKernel());
- SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new RheologyBinghamModelLBMKernel());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new CumulantK17LBMKernel());
+ //SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new RheologyBinghamModelLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new HerschelBulkleyModelLBMKernel());
//SPtr<LBMKernel> kernel = SPtr<LBMKernel>(new BinghamModelLBMKernel());
kernel->setBCProcessor(bcProc);
@@ -205,16 +231,26 @@ void bflow(string configname)
//////////////////////////////////////////////////////////////////////////
////stator
- SPtr<GbObject3D> stator(new GbCylinder3D(0.5 * g_maxX1, 0.5 * g_maxX2, g_minX3-2.0*deltax, 0.5 * g_maxX1, 0.5 * g_maxX2, g_maxX3+ 2.0 * deltax, 0.5 * g_maxX1));
- GbSystem3D::writeGeoObject(stator.get(), outputPath + "/geo/stator", WbWriterVtkXmlBinary::getInstance());
+ SPtr<GbObject3D> rotor(new GbCylinder3D(0.5 * g_maxX1, 0.5 * g_maxX2, g_minX3 - 2.0 * deltax, 0.5 * g_maxX1,
+ 0.5 * g_maxX2, g_maxX3 + 2.0 * deltax, 0.5 * g_maxX1));
+
+ //around x
+ //SPtr<GbObject3D> stator(new GbCylinder3D(g_minX1 - 3.0 * deltax, 0.5 * g_maxX2, 0.5 * g_maxX3, g_maxX1 + 3.0 * deltax, 0.5 * g_maxX2, 0.5 * g_maxX3, 0.5 * g_maxX3));
+
+ GbSystem3D::writeGeoObject(rotor.get(), outputPath + "/geo/stator", WbWriterVtkXmlBinary::getInstance());
- SPtr<D3Q27Interactor> statorInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(stator, grid, velocityBCAdapter, Interactor3D::INVERSESOLID));
+ SPtr<D3Q27Interactor> rotorInt =
+ SPtr<D3Q27Interactor>(new D3Q27Interactor(rotor, grid, velocityBCAdapter, Interactor3D::INVERSESOLID));
////rotor (cylinder)
- SPtr<GbObject3D> rotor(new GbCylinder3D(0.5 * g_maxX1, 0.5 * g_maxX2, g_minX3- 2.0 * deltax, 0.5 * g_maxX1, 0.5 * g_maxX2, g_maxX3+ 2.0 * deltax, 0.25 * g_maxX1));
- GbSystem3D::writeGeoObject(rotor.get(), outputPath + "/geo/rotor", WbWriterVtkXmlBinary::getInstance());
+ SPtr<GbObject3D> stator(new GbCylinder3D(0.5 * g_maxX1, 0.5 * g_maxX2, g_minX3- 2.0 * deltax, 0.5 * g_maxX1, 0.5 * g_maxX2, g_maxX3+ 2.0 * deltax, 0.25 * g_maxX1));
+
+ //around x
+ //SPtr<GbObject3D> rotor(new GbCylinder3D(g_minX1 - 3.0 * deltax, 0.5 * g_maxX2, 0.5 * g_maxX3, g_maxX1 + 3.0 * deltax, 0.5 * g_maxX2, 0.5 * g_maxX3, 0.25 * g_maxX3));
+
+ GbSystem3D::writeGeoObject(stator.get(), outputPath + "/geo/rotor", WbWriterVtkXmlBinary::getInstance());
- SPtr<D3Q27Interactor> rotorInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(rotor, grid, noSlipBCAdapter, Interactor3D::SOLID));
+ SPtr<D3Q27Interactor> statorInt = SPtr<D3Q27Interactor>(new D3Q27Interactor(stator, grid, noSlipBCAdapter, Interactor3D::SOLID));
if (myid == 0)
{
@@ -385,8 +421,8 @@ void bflow(string configname)
calculator->addCoProcessor(fp);
calculator->addCoProcessor(fp2);
calculator->addCoProcessor(writeMQCoProcessor);
- calculator->addCoProcessor(writeThixotropicMQCoProcessor);
- calculator->addCoProcessor(restartCoProcessor);
+ //calculator->addCoProcessor(writeThixotropicMQCoProcessor);
+ //calculator->addCoProcessor(restartCoProcessor);
if (myid == 0) UBLOG(logINFO, "Simulation-start");
calculator->calculate();
diff --git a/apps/cpu/rheometer/viscosity.cfg b/apps/cpu/rheometer/viscosity.cfg
index bf2822c7b1d6dd42fdcbc513a4e6b39264ab4180..065757939d9313c7caaf46ba34f7b989b61914f2 100644
--- a/apps/cpu/rheometer/viscosity.cfg
+++ b/apps/cpu/rheometer/viscosity.cfg
@@ -1 +1 @@
-nuLB = 1.5e-3
\ No newline at end of file
+nuLB = 0.0123058 #1.5e-3
\ No newline at end of file
diff --git a/apps/cpu/sphere/CMakeLists.txt b/apps/cpu/sphere/CMakeLists.txt
index d80737cdd94aa0b912a62acd69dcd30372f6fd82..8346e80d26800582c37090b208e846737e087d5d 100644
--- a/apps/cpu/sphere/CMakeLists.txt
+++ b/apps/cpu/sphere/CMakeLists.txt
@@ -1,6 +1,6 @@
########################################################
## C++ PROJECT ###
########################################################
-PROJECT(sphere)
+PROJECT(sphere LANGUAGES CXX)
vf_add_library(BUILDTYPE binary PRIVATE_LINK VirtualFluidsCore basics ${MPI_CXX_LIBRARIES} FILES sphere.cpp )
\ No newline at end of file
diff --git a/apps/gpu/LBM/DrivenCavity/CMakeLists.txt b/apps/gpu/LBM/DrivenCavity/CMakeLists.txt
index e4f62c0150c29f147dee0b99480d1fe28161511a..8384e1bc6fcfa3fd2514434b620b266e96b3626a 100644
--- a/apps/gpu/LBM/DrivenCavity/CMakeLists.txt
+++ b/apps/gpu/LBM/DrivenCavity/CMakeLists.txt
@@ -5,3 +5,5 @@ PROJECT(DrivenCavity LANGUAGES CUDA CXX)
vf_add_library(BUILDTYPE binary PRIVATE_LINK basics VirtualFluids_GPU GridGenerator MPI::MPI_CXX FILES DrivenCavity.cpp)
set_source_files_properties(DrivenCavity.cpp PROPERTIES LANGUAGE CUDA)
+
+set_target_properties(DrivenCavity PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
diff --git a/apps/gpu/LBM/DrivenCavity/DrivenCavity.cpp b/apps/gpu/LBM/DrivenCavity/DrivenCavity.cpp
index 26c2900ef5681861eb7d55e678ec04ac639852db..fc12e73a18c3e63b93724fc10bb0828391a1a096 100644
--- a/apps/gpu/LBM/DrivenCavity/DrivenCavity.cpp
+++ b/apps/gpu/LBM/DrivenCavity/DrivenCavity.cpp
@@ -96,7 +96,9 @@ const real dt = (real)1.0e-3; //0.5e-3;
const uint nx = 64;
-std::string path("E:/temp/DrivenCavity");
+//std::string path("F:/Work/Computations/out/DrivenCavity/"); //LEGOLAS
+//std::string path("D:/out/DrivenCavity"); //Mollok
+std::string path("/home/sopeters/Computations/out/DrivenCavity64_unified"); // phoenix
std::string simulationName("DrivenCavityChim");
@@ -185,7 +187,7 @@ void multipleLevel(const std::string& configPath)
para->setVelocityRatio(velocity/ velocityLB);
- para->setMainKernel("CumulantK17CompChim");
+ //para->setMainKernel("CumulantK17CompChim");
para->setInitialCondition([&](real coordX, real coordY, real coordZ, real &rho, real &vx, real &vy, real &vz) {
rho = (real)0.0;
diff --git a/docs/Doxyfile b/docs/Doxyfile
new file mode 100644
index 0000000000000000000000000000000000000000..b5057d7697d0616f748d8e6652248966d41b2eb2
--- /dev/null
+++ b/docs/Doxyfile
@@ -0,0 +1,2612 @@
+# Doxyfile 1.9.1
+
+# This file describes the settings to be used by the documentation system
+# doxygen (www.doxygen.org) for a project.
+#
+# All text after a double hash (##) is considered a comment and is placed in
+# front of the TAG it is preceding.
+#
+# All text after a single hash (#) is considered a comment and will be ignored.
+# The format is:
+# TAG = value [value, ...]
+# For lists, items can also be appended using:
+# TAG += value [value, ...]
+# Values that contain spaces should be placed between quotes (\" \").
+
+#---------------------------------------------------------------------------
+# Project related configuration options
+#---------------------------------------------------------------------------
+
+# This tag specifies the encoding used for all characters in the configuration
+# file that follow. The default is UTF-8 which is also the encoding used for all
+# text before the first occurrence of this tag. Doxygen uses libiconv (or the
+# iconv built into libc) for the transcoding. See
+# https://www.gnu.org/software/libiconv/ for the list of possible encodings.
+# The default value is: UTF-8.
+
+DOXYFILE_ENCODING = UTF-8
+
+# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by
+# double-quotes, unless you are using Doxywizard) that should identify the
+# project for which the documentation is generated. This name is used in the
+# title of most generated pages and in a few other places.
+# The default value is: My Project.
+
+PROJECT_NAME = VirtualFluids
+
+# The PROJECT_NUMBER tag can be used to enter a project or revision number. This
+# could be handy for archiving the generated documentation or if some version
+# control system is used.
+
+PROJECT_NUMBER = 1.0
+
+# Using the PROJECT_BRIEF tag one can provide an optional one line description
+# for a project that appears at the top of each page and should give viewer a
+# quick idea about the purpose of the project. Keep the description short.
+
+PROJECT_BRIEF = "Parallel CFD LBM Solver"
+
+# With the PROJECT_LOGO tag one can specify a logo or an icon that is included
+# in the documentation. The maximum height of the logo should not exceed 55
+# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy
+# the logo to the output directory.
+
+PROJECT_LOGO = docs/img/VF_logo.png
+
+# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
+# into which the generated documentation will be written. If a relative path is
+# entered, it will be relative to the location where doxygen was started. If
+# left blank the current directory will be used.
+
+OUTPUT_DIRECTORY = docs/build/
+
+# If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-
+# directories (in 2 levels) under the output directory of each output format and
+# will distribute the generated files over these directories. Enabling this
+# option can be useful when feeding doxygen a huge amount of source files, where
+# putting all generated files in the same directory would otherwise causes
+# performance problems for the file system.
+# The default value is: NO.
+
+CREATE_SUBDIRS = NO
+
+# If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII
+# characters to appear in the names of generated files. If set to NO, non-ASCII
+# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode
+# U+3044.
+# The default value is: NO.
+
+ALLOW_UNICODE_NAMES = NO
+
+# The OUTPUT_LANGUAGE tag is used to specify the language in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all constant output in the proper language.
+# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese,
+# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States),
+# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian,
+# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages),
+# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian,
+# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian,
+# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish,
+# Ukrainian and Vietnamese.
+# The default value is: English.
+
+OUTPUT_LANGUAGE = English
+
+# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all generated output in the proper direction.
+# Possible values are: None, LTR, RTL and Context.
+# The default value is: None.
+
+OUTPUT_TEXT_DIRECTION = None
+
+# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member
+# descriptions after the members that are listed in the file and class
+# documentation (similar to Javadoc). Set to NO to disable this.
+# The default value is: YES.
+
+BRIEF_MEMBER_DESC = YES
+
+# If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief
+# description of a member or function before the detailed description
+#
+# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the
+# brief descriptions will be completely suppressed.
+# The default value is: YES.
+
+REPEAT_BRIEF = YES
+
+# This tag implements a quasi-intelligent brief description abbreviator that is
+# used to form the text in various listings. Each string in this list, if found
+# as the leading text of the brief description, will be stripped from the text
+# and the result, after processing the whole list, is used as the annotated
+# text. Otherwise, the brief description is used as-is. If left blank, the
+# following values are used ($name is automatically replaced with the name of
+# the entity):The $name class, The $name widget, The $name file, is, provides,
+# specifies, contains, represents, a, an and the.
+
+ABBREVIATE_BRIEF = "The $name class" \
+ "The $name widget" \
+ "The $name file" \
+ is \
+ provides \
+ specifies \
+ contains \
+ represents \
+ a \
+ an \
+ the
+
+# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then
+# doxygen will generate a detailed section even if there is only a brief
+# description.
+# The default value is: NO.
+
+ALWAYS_DETAILED_SEC = NO
+
+# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all
+# inherited members of a class in the documentation of that class as if those
+# members were ordinary class members. Constructors, destructors and assignment
+# operators of the base classes will not be shown.
+# The default value is: NO.
+
+INLINE_INHERITED_MEMB = NO
+
+# If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path
+# before files name in the file list and in the header files. If set to NO the
+# shortest path that makes the file name unique will be used
+# The default value is: YES.
+
+FULL_PATH_NAMES = YES
+
+# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path.
+# Stripping is only done if one of the specified strings matches the left-hand
+# part of the path. The tag can be used to show relative paths in the file list.
+# If left blank the directory from which doxygen is run is used as the path to
+# strip.
+#
+# Note that you can specify absolute paths here, but also relative paths, which
+# will be relative from the directory where doxygen is started.
+# This tag requires that the tag FULL_PATH_NAMES is set to YES.
+
+STRIP_FROM_PATH =
+
+# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the
+# path mentioned in the documentation of a class, which tells the reader which
+# header file to include in order to use a class. If left blank only the name of
+# the header file containing the class definition is used. Otherwise one should
+# specify the list of include paths that are normally passed to the compiler
+# using the -I flag.
+
+STRIP_FROM_INC_PATH =
+
+# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but
+# less readable) file names. This can be useful is your file systems doesn't
+# support long names like on DOS, Mac, or CD-ROM.
+# The default value is: NO.
+
+SHORT_NAMES = NO
+
+# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the
+# first line (until the first dot) of a Javadoc-style comment as the brief
+# description. If set to NO, the Javadoc-style will behave just like regular Qt-
+# style comments (thus requiring an explicit @brief command for a brief
+# description.)
+# The default value is: NO.
+
+JAVADOC_AUTOBRIEF = NO
+
+# If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line
+# such as
+# /***************
+# as being the beginning of a Javadoc-style comment "banner". If set to NO, the
+# Javadoc-style will behave just like regular comments and it will not be
+# interpreted by doxygen.
+# The default value is: NO.
+
+JAVADOC_BANNER = NO
+
+# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first
+# line (until the first dot) of a Qt-style comment as the brief description. If
+# set to NO, the Qt-style will behave just like regular Qt-style comments (thus
+# requiring an explicit \brief command for a brief description.)
+# The default value is: NO.
+
+QT_AUTOBRIEF = NO
+
+# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a
+# multi-line C++ special comment block (i.e. a block of //! or /// comments) as
+# a brief description. This used to be the default behavior. The new default is
+# to treat a multi-line C++ comment block as a detailed description. Set this
+# tag to YES if you prefer the old behavior instead.
+#
+# Note that setting this tag to YES also means that rational rose comments are
+# not recognized any more.
+# The default value is: NO.
+
+MULTILINE_CPP_IS_BRIEF = NO
+
+# By default Python docstrings are displayed as preformatted text and doxygen's
+# special commands cannot be used. By setting PYTHON_DOCSTRING to NO the
+# doxygen's special commands can be used and the contents of the docstring
+# documentation blocks is shown as doxygen documentation.
+# The default value is: YES.
+
+PYTHON_DOCSTRING = YES
+
+# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the
+# documentation from any documented member that it re-implements.
+# The default value is: YES.
+
+INHERIT_DOCS = YES
+
+# If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new
+# page for each member. If set to NO, the documentation of a member will be part
+# of the file/class/namespace that contains it.
+# The default value is: NO.
+
+SEPARATE_MEMBER_PAGES = NO
+
+# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen
+# uses this value to replace tabs by spaces in code fragments.
+# Minimum value: 1, maximum value: 16, default value: 4.
+
+TAB_SIZE = 4
+
+# This tag can be used to specify a number of aliases that act as commands in
+# the documentation. An alias has the form:
+# name=value
+# For example adding
+# "sideeffect=@par Side Effects:\n"
+# will allow you to put the command \sideeffect (or @sideeffect) in the
+# documentation, which will result in a user-defined paragraph with heading
+# "Side Effects:". You can put \n's in the value part of an alias to insert
+# newlines (in the resulting output). You can put ^^ in the value part of an
+# alias to insert a newline as if a physical newline was in the original file.
+# When you need a literal { or } or , in the value part of an alias you have to
+# escape them by means of a backslash (\), this can lead to conflicts with the
+# commands \{ and \} for these it is advised to use the version @{ and @} or use
+# a double escape (\\{ and \\})
+
+ALIASES =
+
+# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources
+# only. Doxygen will then generate output that is more tailored for C. For
+# instance, some of the names that are used will be different. The list of all
+# members will be omitted, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_FOR_C = YES
+
+# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or
+# Python sources only. Doxygen will then generate output that is more tailored
+# for that language. For instance, namespaces will be presented as packages,
+# qualified scopes will look different, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_JAVA = NO
+
+# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran
+# sources. Doxygen will then generate output that is tailored for Fortran.
+# The default value is: NO.
+
+OPTIMIZE_FOR_FORTRAN = NO
+
+# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL
+# sources. Doxygen will then generate output that is tailored for VHDL.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_VHDL = NO
+
+# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice
+# sources only. Doxygen will then generate output that is more tailored for that
+# language. For instance, namespaces will be presented as modules, types will be
+# separated into more groups, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_SLICE = NO
+
+# Doxygen selects the parser to use depending on the extension of the files it
+# parses. With this tag you can assign which parser to use for a given
+# extension. Doxygen has a built-in mapping, but you can override or extend it
+# using this tag. The format is ext=language, where ext is a file extension, and
+# language is one of the parsers supported by doxygen: IDL, Java, JavaScript,
+# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice, VHDL,
+# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:
+# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser
+# tries to guess whether the code is fixed or free formatted code, this is the
+# default for Fortran type files). For instance to make doxygen treat .inc files
+# as Fortran files (default is PHP), and .f files as C (default is Fortran),
+# use: inc=Fortran f=C.
+#
+# Note: For files without extension you can use no_extension as a placeholder.
+#
+# Note that for custom extensions you also need to set FILE_PATTERNS otherwise
+# the files are not read by doxygen. When specifying no_extension you should add
+# * to the FILE_PATTERNS.
+#
+# Note see also the list of default file extension mappings.
+
+EXTENSION_MAPPING =
+
+# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments
+# according to the Markdown format, which allows for more readable
+# documentation. See https://daringfireball.net/projects/markdown/ for details.
+# The output of markdown processing is further processed by doxygen, so you can
+# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in
+# case of backward compatibilities issues.
+# The default value is: YES.
+
+MARKDOWN_SUPPORT = YES
+
+# When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up
+# to that level are automatically included in the table of contents, even if
+# they do not have an id attribute.
+# Note: This feature currently applies only to Markdown headings.
+# Minimum value: 0, maximum value: 99, default value: 5.
+# This tag requires that the tag MARKDOWN_SUPPORT is set to YES.
+
+TOC_INCLUDE_HEADINGS = 5
+
+# When enabled doxygen tries to link words that correspond to documented
+# classes, or namespaces to their corresponding documentation. Such a link can
+# be prevented in individual cases by putting a % sign in front of the word or
+# globally by setting AUTOLINK_SUPPORT to NO.
+# The default value is: YES.
+
+AUTOLINK_SUPPORT = YES
+
+# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want
+# to include (a tag file for) the STL sources as input, then you should set this
+# tag to YES in order to let doxygen match functions declarations and
+# definitions whose arguments contain STL classes (e.g. func(std::string);
+# versus func(std::string) {}). This also make the inheritance and collaboration
+# diagrams that involve STL classes more complete and accurate.
+# The default value is: NO.
+
+BUILTIN_STL_SUPPORT = NO
+
+# If you use Microsoft's C++/CLI language, you should set this option to YES to
+# enable parsing support.
+# The default value is: NO.
+
+CPP_CLI_SUPPORT = NO
+
+# Set the SIP_SUPPORT tag to YES if your project consists of sip (see:
+# https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen
+# will parse them like normal C++ but will assume all classes use public instead
+# of private inheritance when no explicit protection keyword is present.
+# The default value is: NO.
+
+SIP_SUPPORT = NO
+
+# For Microsoft's IDL there are propget and propput attributes to indicate
+# getter and setter methods for a property. Setting this option to YES will make
+# doxygen to replace the get and set methods by a property in the documentation.
+# This will only work if the methods are indeed getting or setting a simple
+# type. If this is not the case, or you want to show the methods anyway, you
+# should set this option to NO.
+# The default value is: YES.
+
+IDL_PROPERTY_SUPPORT = YES
+
+# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC
+# tag is set to YES then doxygen will reuse the documentation of the first
+# member in the group (if any) for the other members of the group. By default
+# all members of a group must be documented explicitly.
+# The default value is: NO.
+
+DISTRIBUTE_GROUP_DOC = NO
+
+# If one adds a struct or class to a group and this option is enabled, then also
+# any nested class or struct is added to the same group. By default this option
+# is disabled and one has to add nested compounds explicitly via \ingroup.
+# The default value is: NO.
+
+GROUP_NESTED_COMPOUNDS = NO
+
+# Set the SUBGROUPING tag to YES to allow class member groups of the same type
+# (for instance a group of public functions) to be put as a subgroup of that
+# type (e.g. under the Public Functions section). Set it to NO to prevent
+# subgrouping. Alternatively, this can be done per class using the
+# \nosubgrouping command.
+# The default value is: YES.
+
+SUBGROUPING = YES
+
+# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions
+# are shown inside the group in which they are included (e.g. using \ingroup)
+# instead of on a separate page (for HTML and Man pages) or section (for LaTeX
+# and RTF).
+#
+# Note that this feature does not work in combination with
+# SEPARATE_MEMBER_PAGES.
+# The default value is: NO.
+
+INLINE_GROUPED_CLASSES = NO
+
+# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions
+# with only public data fields or simple typedef fields will be shown inline in
+# the documentation of the scope in which they are defined (i.e. file,
+# namespace, or group documentation), provided this scope is documented. If set
+# to NO, structs, classes, and unions are shown on a separate page (for HTML and
+# Man pages) or section (for LaTeX and RTF).
+# The default value is: NO.
+
+INLINE_SIMPLE_STRUCTS = NO
+
+# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or
+# enum is documented as struct, union, or enum with the name of the typedef. So
+# typedef struct TypeS {} TypeT, will appear in the documentation as a struct
+# with name TypeT. When disabled the typedef will appear as a member of a file,
+# namespace, or class. And the struct will be named TypeS. This can typically be
+# useful for C code in case the coding convention dictates that all compound
+# types are typedef'ed and only the typedef is referenced, never the tag name.
+# The default value is: NO.
+
+TYPEDEF_HIDES_STRUCT = NO
+
+# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This
+# cache is used to resolve symbols given their name and scope. Since this can be
+# an expensive process and often the same symbol appears multiple times in the
+# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small
+# doxygen will become slower. If the cache is too large, memory is wasted. The
+# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range
+# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536
+# symbols. At the end of a run doxygen will report the cache usage and suggest
+# the optimal cache size from a speed point of view.
+# Minimum value: 0, maximum value: 9, default value: 0.
+
+LOOKUP_CACHE_SIZE = 0
+
+# The NUM_PROC_THREADS specifies the number threads doxygen is allowed to use
+# during processing. When set to 0 doxygen will based this on the number of
+# cores available in the system. You can set it explicitly to a value larger
+# than 0 to get more control over the balance between CPU load and processing
+# speed. At this moment only the input processing can be done using multiple
+# threads. Since this is still an experimental feature the default is set to 1,
+# which efficively disables parallel processing. Please report any issues you
+# encounter. Generating dot graphs in parallel is controlled by the
+# DOT_NUM_THREADS setting.
+# Minimum value: 0, maximum value: 32, default value: 1.
+
+NUM_PROC_THREADS = 1
+
+#---------------------------------------------------------------------------
+# Build related configuration options
+#---------------------------------------------------------------------------
+
+# If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in
+# documentation are documented, even if no documentation was available. Private
+# class members and static file members will be hidden unless the
+# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES.
+# Note: This will also disable the warnings about undocumented members that are
+# normally produced when WARNINGS is set to YES.
+# The default value is: NO.
+
+EXTRACT_ALL = YES
+
+# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will
+# be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PRIVATE = NO
+
+# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual
+# methods of a class will be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PRIV_VIRTUAL = NO
+
+# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal
+# scope will be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PACKAGE = NO
+
+# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be
+# included in the documentation.
+# The default value is: NO.
+
+EXTRACT_STATIC = NO
+
+# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined
+# locally in source files will be included in the documentation. If set to NO,
+# only classes defined in header files are included. Does not have any effect
+# for Java sources.
+# The default value is: YES.
+
+EXTRACT_LOCAL_CLASSES = YES
+
+# This flag is only useful for Objective-C code. If set to YES, local methods,
+# which are defined in the implementation section but not in the interface are
+# included in the documentation. If set to NO, only methods in the interface are
+# included.
+# The default value is: NO.
+
+EXTRACT_LOCAL_METHODS = NO
+
+# If this flag is set to YES, the members of anonymous namespaces will be
+# extracted and appear in the documentation as a namespace called
+# 'anonymous_namespace{file}', where file will be replaced with the base name of
+# the file that contains the anonymous namespace. By default anonymous namespace
+# are hidden.
+# The default value is: NO.
+
+EXTRACT_ANON_NSPACES = NO
+
+# If this flag is set to YES, the name of an unnamed parameter in a declaration
+# will be determined by the corresponding definition. By default unnamed
+# parameters remain unnamed in the output.
+# The default value is: YES.
+
+RESOLVE_UNNAMED_PARAMS = YES
+
+# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all
+# undocumented members inside documented classes or files. If set to NO these
+# members will be included in the various overviews, but no documentation
+# section is generated. This option has no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_MEMBERS = NO
+
+# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all
+# undocumented classes that are normally visible in the class hierarchy. If set
+# to NO, these classes will be included in the various overviews. This option
+# has no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_CLASSES = NO
+
+# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend
+# declarations. If set to NO, these declarations will be included in the
+# documentation.
+# The default value is: NO.
+
+HIDE_FRIEND_COMPOUNDS = NO
+
+# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any
+# documentation blocks found inside the body of a function. If set to NO, these
+# blocks will be appended to the function's detailed documentation block.
+# The default value is: NO.
+
+HIDE_IN_BODY_DOCS = NO
+
+# The INTERNAL_DOCS tag determines if documentation that is typed after a
+# \internal command is included. If the tag is set to NO then the documentation
+# will be excluded. Set it to YES to include the internal documentation.
+# The default value is: NO.
+
+INTERNAL_DOCS = NO
+
+# With the correct setting of option CASE_SENSE_NAMES doxygen will better be
+# able to match the capabilities of the underlying filesystem. In case the
+# filesystem is case sensitive (i.e. it supports files in the same directory
+# whose names only differ in casing), the option must be set to YES to properly
+# deal with such files in case they appear in the input. For filesystems that
+# are not case sensitive the option should be be set to NO to properly deal with
+# output files written for symbols that only differ in casing, such as for two
+# classes, one named CLASS and the other named Class, and to also support
+# references to files without having to specify the exact matching casing. On
+# Windows (including Cygwin) and MacOS, users should typically set this option
+# to NO, whereas on Linux or other Unix flavors it should typically be set to
+# YES.
+# The default value is: system dependent.
+
+CASE_SENSE_NAMES = NO
+
+# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with
+# their full class and namespace scopes in the documentation. If set to YES, the
+# scope will be hidden.
+# The default value is: NO.
+
+HIDE_SCOPE_NAMES = NO
+
+# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will
+# append additional text to a page's title, such as Class Reference. If set to
+# YES the compound reference will be hidden.
+# The default value is: NO.
+
+HIDE_COMPOUND_REFERENCE= NO
+
+# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of
+# the files that are included by a file in the documentation of that file.
+# The default value is: YES.
+
+SHOW_INCLUDE_FILES = YES
+
+# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each
+# grouped member an include statement to the documentation, telling the reader
+# which file to include in order to use the member.
+# The default value is: NO.
+
+SHOW_GROUPED_MEMB_INC = NO
+
+# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include
+# files with double quotes in the documentation rather than with sharp brackets.
+# The default value is: NO.
+
+FORCE_LOCAL_INCLUDES = NO
+
+# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the
+# documentation for inline members.
+# The default value is: YES.
+
+INLINE_INFO = YES
+
+# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the
+# (detailed) documentation of file and class members alphabetically by member
+# name. If set to NO, the members will appear in declaration order.
+# The default value is: YES.
+
+SORT_MEMBER_DOCS = YES
+
+# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief
+# descriptions of file, namespace and class members alphabetically by member
+# name. If set to NO, the members will appear in declaration order. Note that
+# this will also influence the order of the classes in the class list.
+# The default value is: NO.
+
+SORT_BRIEF_DOCS = NO
+
+# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the
+# (brief and detailed) documentation of class members so that constructors and
+# destructors are listed first. If set to NO the constructors will appear in the
+# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS.
+# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief
+# member documentation.
+# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting
+# detailed member documentation.
+# The default value is: NO.
+
+SORT_MEMBERS_CTORS_1ST = NO
+
+# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy
+# of group names into alphabetical order. If set to NO the group names will
+# appear in their defined order.
+# The default value is: NO.
+
+SORT_GROUP_NAMES = NO
+
+# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by
+# fully-qualified names, including namespaces. If set to NO, the class list will
+# be sorted only by class name, not including the namespace part.
+# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.
+# Note: This option applies only to the class list, not to the alphabetical
+# list.
+# The default value is: NO.
+
+SORT_BY_SCOPE_NAME = NO
+
+# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper
+# type resolution of all parameters of a function it will reject a match between
+# the prototype and the implementation of a member function even if there is
+# only one candidate or it is obvious which candidate to choose by doing a
+# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still
+# accept a match between prototype and implementation in such cases.
+# The default value is: NO.
+
+STRICT_PROTO_MATCHING = NO
+
+# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo
+# list. This list is created by putting \todo commands in the documentation.
+# The default value is: YES.
+
+GENERATE_TODOLIST = YES
+
+# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test
+# list. This list is created by putting \test commands in the documentation.
+# The default value is: YES.
+
+GENERATE_TESTLIST = YES
+
+# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug
+# list. This list is created by putting \bug commands in the documentation.
+# The default value is: YES.
+
+GENERATE_BUGLIST = YES
+
+# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO)
+# the deprecated list. This list is created by putting \deprecated commands in
+# the documentation.
+# The default value is: YES.
+
+GENERATE_DEPRECATEDLIST= YES
+
+# The ENABLED_SECTIONS tag can be used to enable conditional documentation
+# sections, marked by \if <section_label> ... \endif and \cond <section_label>
+# ... \endcond blocks.
+
+ENABLED_SECTIONS =
+
+# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the
+# initial value of a variable or macro / define can have for it to appear in the
+# documentation. If the initializer consists of more lines than specified here
+# it will be hidden. Use a value of 0 to hide initializers completely. The
+# appearance of the value of individual variables and macros / defines can be
+# controlled using \showinitializer or \hideinitializer command in the
+# documentation regardless of this setting.
+# Minimum value: 0, maximum value: 10000, default value: 30.
+
+MAX_INITIALIZER_LINES = 30
+
+# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at
+# the bottom of the documentation of classes and structs. If set to YES, the
+# list will mention the files that were used to generate the documentation.
+# The default value is: YES.
+
+SHOW_USED_FILES = YES
+
+# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This
+# will remove the Files entry from the Quick Index and from the Folder Tree View
+# (if specified).
+# The default value is: YES.
+
+SHOW_FILES = YES
+
+# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces
+# page. This will remove the Namespaces entry from the Quick Index and from the
+# Folder Tree View (if specified).
+# The default value is: YES.
+
+SHOW_NAMESPACES = YES
+
+# The FILE_VERSION_FILTER tag can be used to specify a program or script that
+# doxygen should invoke to get the current version for each file (typically from
+# the version control system). Doxygen will invoke the program by executing (via
+# popen()) the command command input-file, where command is the value of the
+# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided
+# by doxygen. Whatever the program writes to standard output is used as the file
+# version. For an example see the documentation.
+
+FILE_VERSION_FILTER =
+
+# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed
+# by doxygen. The layout file controls the global structure of the generated
+# output files in an output format independent way. To create the layout file
+# that represents doxygen's defaults, run doxygen with the -l option. You can
+# optionally specify a file name after the option, if omitted DoxygenLayout.xml
+# will be used as the name of the layout file.
+#
+# Note that if you run doxygen from a directory containing a file called
+# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE
+# tag is left empty.
+
+LAYOUT_FILE =
+
+# The CITE_BIB_FILES tag can be used to specify one or more bib files containing
+# the reference definitions. This must be a list of .bib files. The .bib
+# extension is automatically appended if omitted. This requires the bibtex tool
+# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info.
+# For LaTeX the style of the bibliography can be controlled using
+# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the
+# search path. See also \cite for info how to create references.
+
+CITE_BIB_FILES =
+
+#---------------------------------------------------------------------------
+# Configuration options related to warning and progress messages
+#---------------------------------------------------------------------------
+
+# The QUIET tag can be used to turn on/off the messages that are generated to
+# standard output by doxygen. If QUIET is set to YES this implies that the
+# messages are off.
+# The default value is: NO.
+
+QUIET = NO
+
+# The WARNINGS tag can be used to turn on/off the warning messages that are
+# generated to standard error (stderr) by doxygen. If WARNINGS is set to YES
+# this implies that the warnings are on.
+#
+# Tip: Turn warnings on while writing the documentation.
+# The default value is: YES.
+
+WARNINGS = YES
+
+# If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate
+# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag
+# will automatically be disabled.
+# The default value is: YES.
+
+WARN_IF_UNDOCUMENTED = YES
+
+# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for
+# potential errors in the documentation, such as not documenting some parameters
+# in a documented function, or documenting parameters that don't exist or using
+# markup commands wrongly.
+# The default value is: YES.
+
+WARN_IF_DOC_ERROR = YES
+
+# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that
+# are documented, but have no documentation for their parameters or return
+# value. If set to NO, doxygen will only warn about wrong or incomplete
+# parameter documentation, but not about the absence of documentation. If
+# EXTRACT_ALL is set to YES then this flag will automatically be disabled.
+# The default value is: NO.
+
+WARN_NO_PARAMDOC = NO
+
+# If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when
+# a warning is encountered. If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS
+# then doxygen will continue running as if WARN_AS_ERROR tag is set to NO, but
+# at the end of the doxygen process doxygen will return with a non-zero status.
+# Possible values are: NO, YES and FAIL_ON_WARNINGS.
+# The default value is: NO.
+
+WARN_AS_ERROR = NO
+
+# The WARN_FORMAT tag determines the format of the warning messages that doxygen
+# can produce. The string should contain the $file, $line, and $text tags, which
+# will be replaced by the file and line number from which the warning originated
+# and the warning text. Optionally the format may contain $version, which will
+# be replaced by the version of the file (if it could be obtained via
+# FILE_VERSION_FILTER)
+# The default value is: $file:$line: $text.
+
+WARN_FORMAT = "$file:$line: $text"
+
+# The WARN_LOGFILE tag can be used to specify a file to which warning and error
+# messages should be written. If left blank the output is written to standard
+# error (stderr).
+
+WARN_LOGFILE =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the input files
+#---------------------------------------------------------------------------
+
+# The INPUT tag is used to specify the files and/or directories that contain
+# documented source files. You may enter file names like myfile.cpp or
+# directories like /usr/src/myproject. Separate the files or directories with
+# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
+# Note: If this tag is empty the current directory is searched.
+
+INPUT = src/
+
+# This tag can be used to specify the character encoding of the source files
+# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
+# libiconv (or the iconv built into libc) for the transcoding. See the libiconv
+# documentation (see:
+# https://www.gnu.org/software/libiconv/) for the list of possible encodings.
+# The default value is: UTF-8.
+
+INPUT_ENCODING = UTF-8
+
+# If the value of the INPUT tag contains directories, you can use the
+# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and
+# *.h) to filter out the source-files in the directories.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# read by doxygen.
+#
+# Note the list of default checked file patterns might differ from the list of
+# default file extension mappings.
+#
+# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,
+# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,
+# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,
+# *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment),
+# *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, *.vhdl,
+# *.ucf, *.qsf and *.ice.
+
+FILE_PATTERNS = *.c \
+ *.cc \
+ *.cxx \
+ *.cpp \
+ *.cuh \
+ *.cu \
+ *.c++ \
+ *.d \
+ *.java \
+ *.ii \
+ *.ixx \
+ *.ipp \
+ *.i++ \
+ *.inl \
+ *.h \
+ *.hh \
+ *.hxx \
+ *.hpp \
+ *.h++ \
+ *.idl \
+ *.odl \
+ *.cs \
+ *.php \
+ *.php3 \
+ *.inc \
+ *.m \
+ *.markdown \
+ *.md \
+ *.mm \
+ *.dox \
+ *.py \
+ *.f90 \
+ *.f \
+ *.for \
+ *.vhd \
+ *.vhdl
+
+# The RECURSIVE tag can be used to specify whether or not subdirectories should
+# be searched for input files as well.
+# The default value is: NO.
+
+RECURSIVE = YES
+
+# The EXCLUDE tag can be used to specify files and/or directories that should be
+# excluded from the INPUT source files. This way you can easily exclude a
+# subdirectory from a directory tree whose root is specified with the INPUT tag.
+#
+# Note that relative paths are relative to the directory from which doxygen is
+# run.
+
+EXCLUDE =
+
+# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or
+# directories that are symbolic links (a Unix file system feature) are excluded
+# from the input.
+# The default value is: NO.
+
+EXCLUDE_SYMLINKS = NO
+
+# If the value of the INPUT tag contains directories, you can use the
+# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude
+# certain files from those directories.
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories for example use the pattern */test/*
+
+EXCLUDE_PATTERNS =
+
+# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
+# (namespaces, classes, functions, etc.) that should be excluded from the
+# output. The symbol name can be a fully qualified name, a word, or if the
+# wildcard * is used, a substring. Examples: ANamespace, AClass,
+# AClass::ANamespace, ANamespace::*Test
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories use the pattern */test/*
+
+EXCLUDE_SYMBOLS =
+
+# The EXAMPLE_PATH tag can be used to specify one or more files or directories
+# that contain example code fragments that are included (see the \include
+# command).
+
+EXAMPLE_PATH =
+
+# If the value of the EXAMPLE_PATH tag contains directories, you can use the
+# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
+# *.h) to filter out the source-files in the directories. If left blank all
+# files are included.
+
+EXAMPLE_PATTERNS = *
+
+# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be
+# searched for input files to be used with the \include or \dontinclude commands
+# irrespective of the value of the RECURSIVE tag.
+# The default value is: NO.
+
+EXAMPLE_RECURSIVE = NO
+
+# The IMAGE_PATH tag can be used to specify one or more files or directories
+# that contain images that are to be included in the documentation (see the
+# \image command).
+
+IMAGE_PATH =
+
+# The INPUT_FILTER tag can be used to specify a program that doxygen should
+# invoke to filter for each input file. Doxygen will invoke the filter program
+# by executing (via popen()) the command:
+#
+# <filter> <input-file>
+#
+# where <filter> is the value of the INPUT_FILTER tag, and <input-file> is the
+# name of an input file. Doxygen will then use the output that the filter
+# program writes to standard output. If FILTER_PATTERNS is specified, this tag
+# will be ignored.
+#
+# Note that the filter must not add or remove lines; it is applied before the
+# code is scanned, but not when the output code is generated. If lines are added
+# or removed, the anchors will not be placed correctly.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# properly processed by doxygen.
+
+INPUT_FILTER =
+
+# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern
+# basis. Doxygen will compare the file name with each pattern and apply the
+# filter if there is a match. The filters are a list of the form: pattern=filter
+# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how
+# filters are used. If the FILTER_PATTERNS tag is empty or if none of the
+# patterns match the file name, INPUT_FILTER is applied.
+#
+# Note that for custom extensions or not directly supported extensions you also
+# need to set EXTENSION_MAPPING for the extension otherwise the files are not
+# properly processed by doxygen.
+
+FILTER_PATTERNS =
+
+# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using
+# INPUT_FILTER) will also be used to filter the input files that are used for
+# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES).
+# The default value is: NO.
+
+FILTER_SOURCE_FILES = NO
+
+# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file
+# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and
+# it is also possible to disable source filtering for a specific pattern using
+# *.ext= (so without naming a filter).
+# This tag requires that the tag FILTER_SOURCE_FILES is set to YES.
+
+FILTER_SOURCE_PATTERNS =
+
+# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that
+# is part of the input, its contents will be placed on the main page
+# (index.html). This can be useful if you have a project on for instance GitHub
+# and want to reuse the introduction page also for the doxygen output.
+
+USE_MDFILE_AS_MAINPAGE = main.md
+
+#---------------------------------------------------------------------------
+# Configuration options related to source browsing
+#---------------------------------------------------------------------------
+
+# If the SOURCE_BROWSER tag is set to YES then a list of source files will be
+# generated. Documented entities will be cross-referenced with these sources.
+#
+# Note: To get rid of all source code in the generated output, make sure that
+# also VERBATIM_HEADERS is set to NO.
+# The default value is: NO.
+
+SOURCE_BROWSER = YES
+
+# Setting the INLINE_SOURCES tag to YES will include the body of functions,
+# classes and enums directly into the documentation.
+# The default value is: NO.
+
+INLINE_SOURCES = NO
+
+# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any
+# special comment blocks from generated source code fragments. Normal C, C++ and
+# Fortran comments will always remain visible.
+# The default value is: YES.
+
+STRIP_CODE_COMMENTS = YES
+
+# If the REFERENCED_BY_RELATION tag is set to YES then for each documented
+# entity all documented functions referencing it will be listed.
+# The default value is: NO.
+
+REFERENCED_BY_RELATION = NO
+
+# If the REFERENCES_RELATION tag is set to YES then for each documented function
+# all documented entities called/used by that function will be listed.
+# The default value is: NO.
+
+REFERENCES_RELATION = NO
+
+# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set
+# to YES then the hyperlinks from functions in REFERENCES_RELATION and
+# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will
+# link to the documentation.
+# The default value is: YES.
+
+REFERENCES_LINK_SOURCE = YES
+
+# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the
+# source code will show a tooltip with additional information such as prototype,
+# brief description and links to the definition and documentation. Since this
+# will make the HTML file larger and loading of large files a bit slower, you
+# can opt to disable this feature.
+# The default value is: YES.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+SOURCE_TOOLTIPS = YES
+
+# If the USE_HTAGS tag is set to YES then the references to source code will
+# point to the HTML generated by the htags(1) tool instead of doxygen built-in
+# source browser. The htags tool is part of GNU's global source tagging system
+# (see https://www.gnu.org/software/global/global.html). You will need version
+# 4.8.6 or higher.
+#
+# To use it do the following:
+# - Install the latest version of global
+# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file
+# - Make sure the INPUT points to the root of the source tree
+# - Run doxygen as normal
+#
+# Doxygen will invoke htags (and that will in turn invoke gtags), so these
+# tools must be available from the command line (i.e. in the search path).
+#
+# The result: instead of the source browser generated by doxygen, the links to
+# source code will now point to the output of htags.
+# The default value is: NO.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+USE_HTAGS = NO
+
+# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a
+# verbatim copy of the header file for each class for which an include is
+# specified. Set to NO to disable this.
+# See also: Section \class.
+# The default value is: YES.
+
+VERBATIM_HEADERS = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to the alphabetical class index
+#---------------------------------------------------------------------------
+
+# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all
+# compounds will be generated. Enable this if the project contains a lot of
+# classes, structs, unions or interfaces.
+# The default value is: YES.
+
+ALPHABETICAL_INDEX = YES
+
+# In case all classes in a project start with a common prefix, all classes will
+# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
+# can be used to specify a prefix (or a list of prefixes) that should be ignored
+# while generating the index headers.
+# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
+
+IGNORE_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the HTML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output
+# The default value is: YES.
+
+GENERATE_HTML = YES
+
+# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_OUTPUT = html
+
+# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each
+# generated HTML page (for example: .htm, .php, .asp).
+# The default value is: .html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FILE_EXTENSION = .html
+
+# The HTML_HEADER tag can be used to specify a user-defined HTML header file for
+# each generated HTML page. If the tag is left blank doxygen will generate a
+# standard header.
+#
+# To get valid HTML the header file that includes any scripts and style sheets
+# that doxygen needs, which is dependent on the configuration options used (e.g.
+# the setting GENERATE_TREEVIEW). It is highly recommended to start with a
+# default header using
+# doxygen -w html new_header.html new_footer.html new_stylesheet.css
+# YourConfigFile
+# and then modify the file new_header.html. See also section "Doxygen usage"
+# for information on how to generate the default header that doxygen normally
+# uses.
+# Note: The header is subject to change so you typically have to regenerate the
+# default header when upgrading to a newer version of doxygen. For a description
+# of the possible markers and block names see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_HEADER =
+
+# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each
+# generated HTML page. If the tag is left blank doxygen will generate a standard
+# footer. See HTML_HEADER for more information on how to generate a default
+# footer and what special commands can be used inside the footer. See also
+# section "Doxygen usage" for information on how to generate the default footer
+# that doxygen normally uses.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FOOTER =
+
+# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style
+# sheet that is used by each HTML page. It can be used to fine-tune the look of
+# the HTML output. If left blank doxygen will generate a default style sheet.
+# See also section "Doxygen usage" for information on how to generate the style
+# sheet that doxygen normally uses.
+# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as
+# it is more robust and this tag (HTML_STYLESHEET) will in the future become
+# obsolete.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_STYLESHEET =
+
+# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined
+# cascading style sheets that are included after the standard style sheets
+# created by doxygen. Using this option one can overrule certain style aspects.
+# This is preferred over using HTML_STYLESHEET since it does not replace the
+# standard style sheet and is therefore more robust against future updates.
+# Doxygen will copy the style sheet files to the output directory.
+# Note: The order of the extra style sheet files is of importance (e.g. the last
+# style sheet in the list overrules the setting of the previous ones in the
+# list). For an example see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_STYLESHEET =
+
+# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the HTML output directory. Note
+# that these files will be copied to the base HTML output directory. Use the
+# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these
+# files. In the HTML_STYLESHEET file, use the file name only. Also note that the
+# files will be copied as-is; there are no commands or markers available.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_FILES =
+
+# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen
+# will adjust the colors in the style sheet and background images according to
+# this color. Hue is specified as an angle on a colorwheel, see
+# https://en.wikipedia.org/wiki/Hue for more information. For instance the value
+# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300
+# purple, and 360 is red again.
+# Minimum value: 0, maximum value: 359, default value: 220.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_HUE = 220
+
+# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors
+# in the HTML output. For a value of 0 the output will use grayscales only. A
+# value of 255 will produce the most vivid colors.
+# Minimum value: 0, maximum value: 255, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_SAT = 100
+
+# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the
+# luminance component of the colors in the HTML output. Values below 100
+# gradually make the output lighter, whereas values above 100 make the output
+# darker. The value divided by 100 is the actual gamma applied, so 80 represents
+# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not
+# change the gamma.
+# Minimum value: 40, maximum value: 240, default value: 80.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_GAMMA = 80
+
+# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML
+# page will contain the date and time when the page was generated. Setting this
+# to YES can help to show when doxygen was last run and thus if the
+# documentation is up to date.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_TIMESTAMP = YES
+
+# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML
+# documentation will contain a main index with vertical navigation menus that
+# are dynamically created via JavaScript. If disabled, the navigation index will
+# consists of multiple levels of tabs that are statically embedded in every HTML
+# page. Disable this option to support browsers that do not have JavaScript,
+# like the Qt help browser.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_DYNAMIC_MENUS = YES
+
+# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
+# documentation will contain sections that can be hidden and shown after the
+# page has loaded.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_DYNAMIC_SECTIONS = NO
+
+# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries
+# shown in the various tree structured indices initially; the user can expand
+# and collapse entries dynamically later on. Doxygen will expand the tree to
+# such a level that at most the specified number of entries are visible (unless
+# a fully collapsed tree already exceeds this amount). So setting the number of
+# entries 1 will produce a full collapsed tree by default. 0 is a special value
+# representing an infinite number of entries and will result in a full expanded
+# tree by default.
+# Minimum value: 0, maximum value: 9999, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_INDEX_NUM_ENTRIES = 100
+
+# If the GENERATE_DOCSET tag is set to YES, additional index files will be
+# generated that can be used as input for Apple's Xcode 3 integrated development
+# environment (see:
+# https://developer.apple.com/xcode/), introduced with OSX 10.5 (Leopard). To
+# create a documentation set, doxygen will generate a Makefile in the HTML
+# output directory. Running make will produce the docset in that directory and
+# running make install will install the docset in
+# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at
+# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy
+# genXcode/_index.html for more information.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_DOCSET = NO
+
+# This tag determines the name of the docset feed. A documentation feed provides
+# an umbrella under which multiple documentation sets from a single provider
+# (such as a company or product suite) can be grouped.
+# The default value is: Doxygen generated docs.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_FEEDNAME = "Doxygen generated docs"
+
+# This tag specifies a string that should uniquely identify the documentation
+# set bundle. This should be a reverse domain-name style string, e.g.
+# com.mycompany.MyDocSet. Doxygen will append .docset to the name.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_BUNDLE_ID = org.doxygen.Project
+
+# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify
+# the documentation publisher. This should be a reverse domain-name style
+# string, e.g. com.mycompany.MyDocSet.documentation.
+# The default value is: org.doxygen.Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_ID = org.doxygen.Publisher
+
+# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher.
+# The default value is: Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_NAME = Publisher
+
+# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
+# additional HTML index files: index.hhp, index.hhc, and index.hhk. The
+# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
+# (see:
+# https://www.microsoft.com/en-us/download/details.aspx?id=21138) on Windows.
+#
+# The HTML Help Workshop contains a compiler that can convert all HTML output
+# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
+# files are now used as the Windows 98 help format, and will replace the old
+# Windows help format (.hlp) on all Windows platforms in the future. Compressed
+# HTML files also contain an index, a table of contents, and you can search for
+# words in the documentation. The HTML workshop also contains a viewer for
+# compressed HTML files.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_HTMLHELP = NO
+
+# The CHM_FILE tag can be used to specify the file name of the resulting .chm
+# file. You can add a path in front of the file if the result should not be
+# written to the html output directory.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_FILE =
+
+# The HHC_LOCATION tag can be used to specify the location (absolute path
+# including file name) of the HTML help compiler (hhc.exe). If non-empty,
+# doxygen will try to run the HTML help compiler on the generated index.hhp.
+# The file has to be specified with full path.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+HHC_LOCATION =
+
+# The GENERATE_CHI flag controls if a separate .chi index file is generated
+# (YES) or that it should be included in the main .chm file (NO).
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+GENERATE_CHI = NO
+
+# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc)
+# and project file content.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_INDEX_ENCODING =
+
+# The BINARY_TOC flag controls whether a binary table of contents is generated
+# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it
+# enables the Previous and Next buttons.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+BINARY_TOC = NO
+
+# The TOC_EXPAND flag can be set to YES to add extra items for group members to
+# the table of contents of the HTML help documentation and to the tree view.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+TOC_EXPAND = NO
+
+# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and
+# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that
+# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help
+# (.qch) of the generated HTML documentation.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_QHP = NO
+
+# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify
+# the file name of the resulting .qch file. The path specified is relative to
+# the HTML output folder.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QCH_FILE =
+
+# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help
+# Project output. For more information please see Qt Help Project / Namespace
+# (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_NAMESPACE = org.doxygen.Project
+
+# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt
+# Help Project output. For more information please see Qt Help Project / Virtual
+# Folders (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-folders).
+# The default value is: doc.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_VIRTUAL_FOLDER = doc
+
+# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom
+# filter to add. For more information please see Qt Help Project / Custom
+# Filters (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_NAME =
+
+# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the
+# custom filter to add. For more information please see Qt Help Project / Custom
+# Filters (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_ATTRS =
+
+# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this
+# project's filter section matches. Qt Help Project / Filter Attributes (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_SECT_FILTER_ATTRS =
+
+# The QHG_LOCATION tag can be used to specify the location (absolute path
+# including file name) of Qt's qhelpgenerator. If non-empty doxygen will try to
+# run qhelpgenerator on the generated .qhp file.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHG_LOCATION =
+
+# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be
+# generated, together with the HTML files, they form an Eclipse help plugin. To
+# install this plugin and make it available under the help contents menu in
+# Eclipse, the contents of the directory containing the HTML and XML files needs
+# to be copied into the plugins directory of eclipse. The name of the directory
+# within the plugins directory should be the same as the ECLIPSE_DOC_ID value.
+# After copying Eclipse needs to be restarted before the help appears.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_ECLIPSEHELP = NO
+
+# A unique identifier for the Eclipse help plugin. When installing the plugin
+# the directory name containing the HTML and XML files should also have this
+# name. Each documentation set should have its own identifier.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES.
+
+ECLIPSE_DOC_ID = org.doxygen.Project
+
+# If you want full control over the layout of the generated HTML pages it might
+# be necessary to disable the index and replace it with your own. The
+# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top
+# of each HTML page. A value of NO enables the index and the value YES disables
+# it. Since the tabs in the index contain the same information as the navigation
+# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+DISABLE_INDEX = NO
+
+# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index
+# structure should be generated to display hierarchical information. If the tag
+# value is set to YES, a side panel will be generated containing a tree-like
+# index structure (just like the one that is generated for HTML Help). For this
+# to work a browser that supports JavaScript, DHTML, CSS and frames is required
+# (i.e. any modern browser). Windows users are probably better off using the
+# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can
+# further fine-tune the look of the index. As an example, the default style
+# sheet generated by doxygen has an example that shows how to put an image at
+# the root of the tree instead of the PROJECT_NAME. Since the tree basically has
+# the same information as the tab index, you could consider setting
+# DISABLE_INDEX to YES when enabling this option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_TREEVIEW = NO
+
+# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
+# doxygen will group on one line in the generated HTML documentation.
+#
+# Note that a value of 0 will completely suppress the enum values from appearing
+# in the overview section.
+# Minimum value: 0, maximum value: 20, default value: 4.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+ENUM_VALUES_PER_LINE = 4
+
+# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used
+# to set the initial width (in pixels) of the frame in which the tree is shown.
+# Minimum value: 0, maximum value: 1500, default value: 250.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+TREEVIEW_WIDTH = 250
+
+# If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to
+# external symbols imported via tag files in a separate window.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+EXT_LINKS_IN_WINDOW = NO
+
+# If the HTML_FORMULA_FORMAT option is set to svg, doxygen will use the pdf2svg
+# tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see
+# https://inkscape.org) to generate formulas as SVG images instead of PNGs for
+# the HTML output. These images will generally look nicer at scaled resolutions.
+# Possible values are: png (the default) and svg (looks nicer but requires the
+# pdf2svg or inkscape tool).
+# The default value is: png.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FORMULA_FORMAT = png
+
+# Use this tag to change the font size of LaTeX formulas included as images in
+# the HTML documentation. When you change the font size after a successful
+# doxygen run you need to manually remove any form_*.png images from the HTML
+# output directory to force them to be regenerated.
+# Minimum value: 8, maximum value: 50, default value: 10.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_FONTSIZE = 10
+
+# Use the FORMULA_TRANSPARENT tag to determine whether or not the images
+# generated for formulas are transparent PNGs. Transparent PNGs are not
+# supported properly for IE 6.0, but are supported on all modern browsers.
+#
+# Note that when changing this option you need to delete any form_*.png files in
+# the HTML output directory before the changes have effect.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_TRANSPARENT = YES
+
+# The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands
+# to create new LaTeX commands to be used in formulas as building blocks. See
+# the section "Including formulas" for details.
+
+FORMULA_MACROFILE =
+
+# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see
+# https://www.mathjax.org) which uses client side JavaScript for the rendering
+# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX
+# installed or if you want to formulas look prettier in the HTML output. When
+# enabled you may also need to install MathJax separately and configure the path
+# to it using the MATHJAX_RELPATH option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+USE_MATHJAX = NO
+
+# When MathJax is enabled you can set the default output format to be used for
+# the MathJax output. See the MathJax site (see:
+# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details.
+# Possible values are: HTML-CSS (which is slower, but has the best
+# compatibility), NativeMML (i.e. MathML) and SVG.
+# The default value is: HTML-CSS.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_FORMAT = HTML-CSS
+
+# When MathJax is enabled you need to specify the location relative to the HTML
+# output directory using the MATHJAX_RELPATH option. The destination directory
+# should contain the MathJax.js script. For instance, if the mathjax directory
+# is located at the same level as the HTML output directory, then
+# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax
+# Content Delivery Network so you can quickly see the result without installing
+# MathJax. However, it is strongly recommended to install a local copy of
+# MathJax from https://www.mathjax.org before deployment.
+# The default value is: https://cdn.jsdelivr.net/npm/mathjax@2.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest
+
+# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax
+# extension names that should be enabled during MathJax rendering. For example
+# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_EXTENSIONS =
+
+# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces
+# of code that will be used on startup of the MathJax code. See the MathJax site
+# (see:
+# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. For an
+# example see the documentation.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_CODEFILE =
+
+# When the SEARCHENGINE tag is enabled doxygen will generate a search box for
+# the HTML output. The underlying search engine uses javascript and DHTML and
+# should work on any modern browser. Note that when using HTML help
+# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET)
+# there is already a search function so this one should typically be disabled.
+# For large projects the javascript based search engine can be slow, then
+# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to
+# search using the keyboard; to jump to the search box use <access key> + S
+# (what the <access key> is depends on the OS and browser, but it is typically
+# <CTRL>, <ALT>/<option>, or both). Inside the search box use the <cursor down
+# key> to jump into the search results window, the results can be navigated
+# using the <cursor keys>. Press <Enter> to select an item or <escape> to cancel
+# the search. The filter options can be selected when the cursor is inside the
+# search box by pressing <Shift>+<cursor down>. Also here use the <cursor keys>
+# to select a filter and <Enter> or <escape> to activate or cancel the filter
+# option.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+SEARCHENGINE = YES
+
+# When the SERVER_BASED_SEARCH tag is enabled the search engine will be
+# implemented using a web server instead of a web client using JavaScript. There
+# are two flavors of web server based searching depending on the EXTERNAL_SEARCH
+# setting. When disabled, doxygen will generate a PHP script for searching and
+# an index file used by the script. When EXTERNAL_SEARCH is enabled the indexing
+# and searching needs to be provided by external tools. See the section
+# "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SERVER_BASED_SEARCH = NO
+
+# When EXTERNAL_SEARCH tag is enabled doxygen will no longer generate the PHP
+# script for searching. Instead the search results are written to an XML file
+# which needs to be processed by an external indexer. Doxygen will invoke an
+# external search engine pointed to by the SEARCHENGINE_URL option to obtain the
+# search results.
+#
+# Doxygen ships with an example indexer (doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see:
+# https://xapian.org/).
+#
+# See the section "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH = NO
+
+# The SEARCHENGINE_URL should point to a search engine hosted by a web server
+# which will return the search results when EXTERNAL_SEARCH is enabled.
+#
+# Doxygen ships with an example indexer (doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see:
+# https://xapian.org/). See the section "External Indexing and Searching" for
+# details.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHENGINE_URL =
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the unindexed
+# search data is written to a file for indexing by an external tool. With the
+# SEARCHDATA_FILE tag the name of this file can be specified.
+# The default file is: searchdata.xml.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHDATA_FILE = searchdata.xml
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the
+# EXTERNAL_SEARCH_ID tag can be used as an identifier for the project. This is
+# useful in combination with EXTRA_SEARCH_MAPPINGS to search through multiple
+# projects and redirect the results back to the right project.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH_ID =
+
+# The EXTRA_SEARCH_MAPPINGS tag can be used to enable searching through doxygen
+# projects other than the one defined by this configuration file, but that are
+# all added to the same external search index. Each project needs to have a
+# unique id set via EXTERNAL_SEARCH_ID. The search mapping then maps the id of
+# to a relative location where the documentation can be found. The format is:
+# EXTRA_SEARCH_MAPPINGS = tagname1=loc1 tagname2=loc2 ...
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTRA_SEARCH_MAPPINGS =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the LaTeX output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_LATEX tag is set to YES, doxygen will generate LaTeX output.
+# The default value is: YES.
+
+GENERATE_LATEX = NO
+
+# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: latex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_OUTPUT = latex
+
+# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
+# invoked.
+#
+# Note that when not enabling USE_PDFLATEX the default is latex when enabling
+# USE_PDFLATEX the default is pdflatex and when in the later case latex is
+# chosen this is overwritten by pdflatex. For specific output languages the
+# default can have been set differently, this depends on the implementation of
+# the output language.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_CMD_NAME = latex
+
+# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to generate
+# index for LaTeX.
+# Note: This tag is used in the Makefile / make.bat.
+# See also: LATEX_MAKEINDEX_CMD for the part in the generated output file
+# (.tex).
+# The default file is: makeindex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+MAKEINDEX_CMD_NAME = makeindex
+
+# The LATEX_MAKEINDEX_CMD tag can be used to specify the command name to
+# generate index for LaTeX. In case there is no backslash (\) as first character
+# it will be automatically added in the LaTeX code.
+# Note: This tag is used in the generated output file (.tex).
+# See also: MAKEINDEX_CMD_NAME for the part in the Makefile / make.bat.
+# The default value is: makeindex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_MAKEINDEX_CMD = makeindex
+
+# If the COMPACT_LATEX tag is set to YES, doxygen generates more compact LaTeX
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+COMPACT_LATEX = NO
+
+# The PAPER_TYPE tag can be used to set the paper type that is used by the
+# printer.
+# Possible values are: a4 (210 x 297 mm), letter (8.5 x 11 inches), legal (8.5 x
+# 14 inches) and executive (7.25 x 10.5 inches).
+# The default value is: a4.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PAPER_TYPE = a4
+
+# The EXTRA_PACKAGES tag can be used to specify one or more LaTeX package names
+# that should be included in the LaTeX output. The package can be specified just
+# by its name or with the correct syntax as to be used with the LaTeX
+# \usepackage command. To get the times font for instance you can specify :
+# EXTRA_PACKAGES=times or EXTRA_PACKAGES={times}
+# To use the option intlimits with the amsmath package you can specify:
+# EXTRA_PACKAGES=[intlimits]{amsmath}
+# If left blank no extra packages will be included.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+EXTRA_PACKAGES =
+
+# The LATEX_HEADER tag can be used to specify a personal LaTeX header for the
+# generated LaTeX document. The header should contain everything until the first
+# chapter. If it is left blank doxygen will generate a standard header. See
+# section "Doxygen usage" for information on how to let doxygen write the
+# default header to a separate file.
+#
+# Note: Only use a user-defined header if you know what you are doing! The
+# following commands have a special meaning inside the header: $title,
+# $datetime, $date, $doxygenversion, $projectname, $projectnumber,
+# $projectbrief, $projectlogo. Doxygen will replace $title with the empty
+# string, for the replacement values of the other commands the user is referred
+# to HTML_HEADER.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HEADER =
+
+# The LATEX_FOOTER tag can be used to specify a personal LaTeX footer for the
+# generated LaTeX document. The footer should contain everything after the last
+# chapter. If it is left blank doxygen will generate a standard footer. See
+# LATEX_HEADER for more information on how to generate a default footer and what
+# special commands can be used inside the footer.
+#
+# Note: Only use a user-defined footer if you know what you are doing!
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_FOOTER =
+
+# The LATEX_EXTRA_STYLESHEET tag can be used to specify additional user-defined
+# LaTeX style sheets that are included after the standard style sheets created
+# by doxygen. Using this option one can overrule certain style aspects. Doxygen
+# will copy the style sheet files to the output directory.
+# Note: The order of the extra style sheet files is of importance (e.g. the last
+# style sheet in the list overrules the setting of the previous ones in the
+# list).
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EXTRA_STYLESHEET =
+
+# The LATEX_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the LATEX_OUTPUT output
+# directory. Note that the files will be copied as-is; there are no commands or
+# markers available.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EXTRA_FILES =
+
+# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated is
+# prepared for conversion to PDF (using ps2pdf or pdflatex). The PDF file will
+# contain links (just like the HTML output) instead of page references. This
+# makes the output suitable for online browsing using a PDF viewer.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PDF_HYPERLINKS = YES
+
+# If the USE_PDFLATEX tag is set to YES, doxygen will use the engine as
+# specified with LATEX_CMD_NAME to generate the PDF file directly from the LaTeX
+# files. Set this option to YES, to get a higher quality PDF documentation.
+#
+# See also section LATEX_CMD_NAME for selecting the engine.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+USE_PDFLATEX = YES
+
+# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \batchmode
+# command to the generated LaTeX files. This will instruct LaTeX to keep running
+# if errors occur, instead of asking the user for help. This option is also used
+# when generating formulas in HTML.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BATCHMODE = NO
+
+# If the LATEX_HIDE_INDICES tag is set to YES then doxygen will not include the
+# index chapters (such as File Index, Compound Index, etc.) in the output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HIDE_INDICES = NO
+
+# If the LATEX_SOURCE_CODE tag is set to YES then doxygen will include source
+# code with syntax highlighting in the LaTeX output.
+#
+# Note that which sources are shown also depends on other settings such as
+# SOURCE_BROWSER.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_SOURCE_CODE = NO
+
+# The LATEX_BIB_STYLE tag can be used to specify the style to use for the
+# bibliography, e.g. plainnat, or ieeetr. See
+# https://en.wikipedia.org/wiki/BibTeX and \cite for more info.
+# The default value is: plain.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BIB_STYLE = plain
+
+# If the LATEX_TIMESTAMP tag is set to YES then the footer of each generated
+# page will contain the date and time when the page was generated. Setting this
+# to NO can help when comparing the output of multiple runs.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_TIMESTAMP = NO
+
+# The LATEX_EMOJI_DIRECTORY tag is used to specify the (relative or absolute)
+# path from which the emoji images will be read. If a relative path is entered,
+# it will be relative to the LATEX_OUTPUT directory. If left blank the
+# LATEX_OUTPUT directory will be used.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EMOJI_DIRECTORY =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the RTF output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_RTF tag is set to YES, doxygen will generate RTF output. The
+# RTF output is optimized for Word 97 and may not look too pretty with other RTF
+# readers/editors.
+# The default value is: NO.
+
+GENERATE_RTF = NO
+
+# The RTF_OUTPUT tag is used to specify where the RTF docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: rtf.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_OUTPUT = rtf
+
+# If the COMPACT_RTF tag is set to YES, doxygen generates more compact RTF
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+COMPACT_RTF = NO
+
+# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated will
+# contain hyperlink fields. The RTF file will contain links (just like the HTML
+# output) instead of page references. This makes the output suitable for online
+# browsing using Word or some other Word compatible readers that support those
+# fields.
+#
+# Note: WordPad (write) and others do not support links.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_HYPERLINKS = NO
+
+# Load stylesheet definitions from file. Syntax is similar to doxygen's
+# configuration file, i.e. a series of assignments. You only have to provide
+# replacements, missing definitions are set to their default value.
+#
+# See also section "Doxygen usage" for information on how to generate the
+# default style sheet that doxygen normally uses.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_STYLESHEET_FILE =
+
+# Set optional variables used in the generation of an RTF document. Syntax is
+# similar to doxygen's configuration file. A template extensions file can be
+# generated using doxygen -e rtf extensionFile.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_EXTENSIONS_FILE =
+
+# If the RTF_SOURCE_CODE tag is set to YES then doxygen will include source code
+# with syntax highlighting in the RTF output.
+#
+# Note that which sources are shown also depends on other settings such as
+# SOURCE_BROWSER.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_SOURCE_CODE = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the man page output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_MAN tag is set to YES, doxygen will generate man pages for
+# classes and files.
+# The default value is: NO.
+
+GENERATE_MAN = NO
+
+# The MAN_OUTPUT tag is used to specify where the man pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it. A directory man3 will be created inside the directory specified by
+# MAN_OUTPUT.
+# The default directory is: man.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_OUTPUT = man
+
+# The MAN_EXTENSION tag determines the extension that is added to the generated
+# man pages. In case the manual section does not start with a number, the number
+# 3 is prepended. The dot (.) at the beginning of the MAN_EXTENSION tag is
+# optional.
+# The default value is: .3.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_EXTENSION = .3
+
+# The MAN_SUBDIR tag determines the name of the directory created within
+# MAN_OUTPUT in which the man pages are placed. If defaults to man followed by
+# MAN_EXTENSION with the initial . removed.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_SUBDIR =
+
+# If the MAN_LINKS tag is set to YES and doxygen generates man output, then it
+# will generate one additional man file for each entity documented in the real
+# man page(s). These additional files only source the real man page, but without
+# them the man command would be unable to find the correct page.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_LINKS = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the XML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_XML tag is set to YES, doxygen will generate an XML file that
+# captures the structure of the code including all documentation.
+# The default value is: NO.
+
+GENERATE_XML = NO
+
+# The XML_OUTPUT tag is used to specify where the XML pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: xml.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_OUTPUT = xml
+
+# If the XML_PROGRAMLISTING tag is set to YES, doxygen will dump the program
+# listings (including syntax highlighting and cross-referencing information) to
+# the XML output. Note that enabling this will significantly increase the size
+# of the XML output.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_PROGRAMLISTING = YES
+
+# If the XML_NS_MEMB_FILE_SCOPE tag is set to YES, doxygen will include
+# namespace members in file scope as well, matching the HTML output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_NS_MEMB_FILE_SCOPE = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the DOCBOOK output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_DOCBOOK tag is set to YES, doxygen will generate Docbook files
+# that can be used to generate PDF.
+# The default value is: NO.
+
+GENERATE_DOCBOOK = NO
+
+# The DOCBOOK_OUTPUT tag is used to specify where the Docbook pages will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be put in
+# front of it.
+# The default directory is: docbook.
+# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
+
+DOCBOOK_OUTPUT = docbook
+
+# If the DOCBOOK_PROGRAMLISTING tag is set to YES, doxygen will include the
+# program listings (including syntax highlighting and cross-referencing
+# information) to the DOCBOOK output. Note that enabling this will significantly
+# increase the size of the DOCBOOK output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
+
+DOCBOOK_PROGRAMLISTING = NO
+
+#---------------------------------------------------------------------------
+# Configuration options for the AutoGen Definitions output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_AUTOGEN_DEF tag is set to YES, doxygen will generate an
+# AutoGen Definitions (see http://autogen.sourceforge.net/) file that captures
+# the structure of the code including all documentation. Note that this feature
+# is still experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_AUTOGEN_DEF = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the Perl module output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_PERLMOD tag is set to YES, doxygen will generate a Perl module
+# file that captures the structure of the code including all documentation.
+#
+# Note that this feature is still experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_PERLMOD = NO
+
+# If the PERLMOD_LATEX tag is set to YES, doxygen will generate the necessary
+# Makefile rules, Perl scripts and LaTeX code to be able to generate PDF and DVI
+# output from the Perl module output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_LATEX = NO
+
+# If the PERLMOD_PRETTY tag is set to YES, the Perl module output will be nicely
+# formatted so it can be parsed by a human reader. This is useful if you want to
+# understand what is going on. On the other hand, if this tag is set to NO, the
+# size of the Perl module output will be much smaller and Perl will parse it
+# just the same.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_PRETTY = YES
+
+# The names of the make variables in the generated doxyrules.make file are
+# prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX. This is useful
+# so different doxyrules.make files included by the same Makefile don't
+# overwrite each other's variables.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_MAKEVAR_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the preprocessor
+#---------------------------------------------------------------------------
+
+# If the ENABLE_PREPROCESSING tag is set to YES, doxygen will evaluate all
+# C-preprocessor directives found in the sources and include files.
+# The default value is: YES.
+
+ENABLE_PREPROCESSING = YES
+
+# If the MACRO_EXPANSION tag is set to YES, doxygen will expand all macro names
+# in the source code. If set to NO, only conditional compilation will be
+# performed. Macro expansion can be done in a controlled way by setting
+# EXPAND_ONLY_PREDEF to YES.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+MACRO_EXPANSION = YES
+
+# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES then
+# the macro expansion is limited to the macros specified with the PREDEFINED and
+# EXPAND_AS_DEFINED tags.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_ONLY_PREDEF = YES
+
+# If the SEARCH_INCLUDES tag is set to YES, the include files in the
+# INCLUDE_PATH will be searched if a #include is found.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SEARCH_INCLUDES = YES
+
+# The INCLUDE_PATH tag can be used to specify one or more directories that
+# contain include files that are not input files but should be processed by the
+# preprocessor.
+# This tag requires that the tag SEARCH_INCLUDES is set to YES.
+
+INCLUDE_PATH =
+
+# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
+# patterns (like *.h and *.hpp) to filter out the header-files in the
+# directories. If left blank, the patterns specified with FILE_PATTERNS will be
+# used.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+INCLUDE_FILE_PATTERNS =
+
+# The PREDEFINED tag can be used to specify one or more macro names that are
+# defined before the preprocessor is started (similar to the -D option of e.g.
+# gcc). The argument of the tag is a list of macros of the form: name or
+# name=definition (no spaces). If the definition and the "=" are omitted, "=1"
+# is assumed. To prevent a macro definition from being undefined via #undef or
+# recursively expanded use the := operator instead of the = operator.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+PREDEFINED = VF_FETOL \
+ VF_MPI \
+ VF_METIS \
+ VF_ZOLTAN
+
+# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this
+# tag can be used to specify a list of macro names that should be expanded. The
+# macro definition that is found in the sources will be used. Use the PREDEFINED
+# tag if you want to use a different macro definition that overrules the
+# definition found in the source code.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_AS_DEFINED =
+
+# If the SKIP_FUNCTION_MACROS tag is set to YES then doxygen's preprocessor will
+# remove all references to function-like macros that are alone on a line, have
+# an all uppercase name, and do not end with a semicolon. Such function macros
+# are typically used for boiler-plate code, and will confuse the parser if not
+# removed.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SKIP_FUNCTION_MACROS = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to external references
+#---------------------------------------------------------------------------
+
+# The TAGFILES tag can be used to specify one or more tag files. For each tag
+# file the location of the external documentation should be added. The format of
+# a tag file without this location is as follows:
+# TAGFILES = file1 file2 ...
+# Adding location for the tag files is done as follows:
+# TAGFILES = file1=loc1 "file2 = loc2" ...
+# where loc1 and loc2 can be relative or absolute paths or URLs. See the
+# section "Linking to external documentation" for more information about the use
+# of tag files.
+# Note: Each tag file must have a unique name (where the name does NOT include
+# the path). If a tag file is not located in the directory in which doxygen is
+# run, you must also specify the path to the tagfile here.
+
+TAGFILES =
+
+# When a file name is specified after GENERATE_TAGFILE, doxygen will create a
+# tag file that is based on the input files it reads. See section "Linking to
+# external documentation" for more information about the usage of tag files.
+
+GENERATE_TAGFILE =
+
+# If the ALLEXTERNALS tag is set to YES, all external class will be listed in
+# the class index. If set to NO, only the inherited external classes will be
+# listed.
+# The default value is: NO.
+
+ALLEXTERNALS = NO
+
+# If the EXTERNAL_GROUPS tag is set to YES, all external groups will be listed
+# in the modules index. If set to NO, only the current project's groups will be
+# listed.
+# The default value is: YES.
+
+EXTERNAL_GROUPS = YES
+
+# If the EXTERNAL_PAGES tag is set to YES, all external pages will be listed in
+# the related pages index. If set to NO, only the current project's pages will
+# be listed.
+# The default value is: YES.
+
+EXTERNAL_PAGES = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to the dot tool
+#---------------------------------------------------------------------------
+
+# If the CLASS_DIAGRAMS tag is set to YES, doxygen will generate a class diagram
+# (in HTML and LaTeX) for classes with base or super classes. Setting the tag to
+# NO turns the diagrams off. Note that this option also works with HAVE_DOT
+# disabled, but it is recommended to install and use dot, since it yields more
+# powerful graphs.
+# The default value is: YES.
+
+CLASS_DIAGRAMS = YES
+
+# You can include diagrams made with dia in doxygen documentation. Doxygen will
+# then run dia to produce the diagram and insert it in the documentation. The
+# DIA_PATH tag allows you to specify the directory where the dia binary resides.
+# If left empty dia is assumed to be found in the default search path.
+
+DIA_PATH =
+
+# If set to YES the inheritance and collaboration graphs will hide inheritance
+# and usage relations if the target is undocumented or is not a class.
+# The default value is: YES.
+
+HIDE_UNDOC_RELATIONS = YES
+
+# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is
+# available from the path. This tool is part of Graphviz (see:
+# http://www.graphviz.org/), a graph visualization toolkit from AT&T and Lucent
+# Bell Labs. The other options in this section have no effect if this option is
+# set to NO
+# The default value is: NO.
+
+HAVE_DOT = NO
+
+# The DOT_NUM_THREADS specifies the number of dot invocations doxygen is allowed
+# to run in parallel. When set to 0 doxygen will base this on the number of
+# processors available in the system. You can set it explicitly to a value
+# larger than 0 to get control over the balance between CPU load and processing
+# speed.
+# Minimum value: 0, maximum value: 32, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_NUM_THREADS = 0
+
+# When you want a differently looking font in the dot files that doxygen
+# generates you can specify the font name using DOT_FONTNAME. You need to make
+# sure dot is able to find the font, which can be done by putting it in a
+# standard location or by setting the DOTFONTPATH environment variable or by
+# setting DOT_FONTPATH to the directory containing the font.
+# The default value is: Helvetica.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTNAME = Helvetica
+
+# The DOT_FONTSIZE tag can be used to set the size (in points) of the font of
+# dot graphs.
+# Minimum value: 4, maximum value: 24, default value: 10.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTSIZE = 10
+
+# By default doxygen will tell dot to use the default font as specified with
+# DOT_FONTNAME. If you specify a different font using DOT_FONTNAME you can set
+# the path where dot can find it using this tag.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTPATH =
+
+# If the CLASS_GRAPH tag is set to YES then doxygen will generate a graph for
+# each documented class showing the direct and indirect inheritance relations.
+# Setting this tag to YES will force the CLASS_DIAGRAMS tag to NO.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CLASS_GRAPH = YES
+
+# If the COLLABORATION_GRAPH tag is set to YES then doxygen will generate a
+# graph for each documented class showing the direct and indirect implementation
+# dependencies (inheritance, containment, and class references variables) of the
+# class with other documented classes.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+COLLABORATION_GRAPH = YES
+
+# If the GROUP_GRAPHS tag is set to YES then doxygen will generate a graph for
+# groups, showing the direct groups dependencies.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GROUP_GRAPHS = YES
+
+# If the UML_LOOK tag is set to YES, doxygen will generate inheritance and
+# collaboration diagrams in a style similar to the OMG's Unified Modeling
+# Language.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+UML_LOOK = NO
+
+# If the UML_LOOK tag is enabled, the fields and methods are shown inside the
+# class node. If there are many fields or methods and many nodes the graph may
+# become too big to be useful. The UML_LIMIT_NUM_FIELDS threshold limits the
+# number of items for each type to make the size more manageable. Set this to 0
+# for no limit. Note that the threshold may be exceeded by 50% before the limit
+# is enforced. So when you set the threshold to 10, up to 15 fields may appear,
+# but if the number exceeds 15, the total amount of fields shown is limited to
+# 10.
+# Minimum value: 0, maximum value: 100, default value: 10.
+# This tag requires that the tag UML_LOOK is set to YES.
+
+UML_LIMIT_NUM_FIELDS = 10
+
+# If the DOT_UML_DETAILS tag is set to NO, doxygen will show attributes and
+# methods without types and arguments in the UML graphs. If the DOT_UML_DETAILS
+# tag is set to YES, doxygen will add type and arguments for attributes and
+# methods in the UML graphs. If the DOT_UML_DETAILS tag is set to NONE, doxygen
+# will not generate fields with class member information in the UML graphs. The
+# class diagrams will look similar to the default class diagrams but using UML
+# notation for the relationships.
+# Possible values are: NO, YES and NONE.
+# The default value is: NO.
+# This tag requires that the tag UML_LOOK is set to YES.
+
+DOT_UML_DETAILS = NO
+
+# The DOT_WRAP_THRESHOLD tag can be used to set the maximum number of characters
+# to display on a single line. If the actual line length exceeds this threshold
+# significantly it will wrapped across multiple lines. Some heuristics are apply
+# to avoid ugly line breaks.
+# Minimum value: 0, maximum value: 1000, default value: 17.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_WRAP_THRESHOLD = 17
+
+# If the TEMPLATE_RELATIONS tag is set to YES then the inheritance and
+# collaboration graphs will show the relations between templates and their
+# instances.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+TEMPLATE_RELATIONS = NO
+
+# If the INCLUDE_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are set to
+# YES then doxygen will generate a graph for each documented file showing the
+# direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDE_GRAPH = YES
+
+# If the INCLUDED_BY_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are
+# set to YES then doxygen will generate a graph for each documented file showing
+# the direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDED_BY_GRAPH = YES
+
+# If the CALL_GRAPH tag is set to YES then doxygen will generate a call
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable call graphs for selected
+# functions only using the \callgraph command. Disabling a call graph can be
+# accomplished by means of the command \hidecallgraph.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALL_GRAPH = NO
+
+# If the CALLER_GRAPH tag is set to YES then doxygen will generate a caller
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable caller graphs for selected
+# functions only using the \callergraph command. Disabling a caller graph can be
+# accomplished by means of the command \hidecallergraph.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALLER_GRAPH = NO
+
+# If the GRAPHICAL_HIERARCHY tag is set to YES then doxygen will graphical
+# hierarchy of all classes instead of a textual one.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GRAPHICAL_HIERARCHY = YES
+
+# If the DIRECTORY_GRAPH tag is set to YES then doxygen will show the
+# dependencies a directory has on other directories in a graphical way. The
+# dependency relations are determined by the #include relations between the
+# files in the directories.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DIRECTORY_GRAPH = YES
+
+# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images
+# generated by dot. For an explanation of the image formats see the section
+# output formats in the documentation of the dot tool (Graphviz (see:
+# http://www.graphviz.org/)).
+# Note: If you choose svg you need to set HTML_FILE_EXTENSION to xhtml in order
+# to make the SVG files visible in IE 9+ (other browsers do not have this
+# requirement).
+# Possible values are: png, jpg, gif, svg, png:gd, png:gd:gd, png:cairo,
+# png:cairo:gd, png:cairo:cairo, png:cairo:gdiplus, png:gdiplus and
+# png:gdiplus:gdiplus.
+# The default value is: png.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_IMAGE_FORMAT = png
+
+# If DOT_IMAGE_FORMAT is set to svg, then this option can be set to YES to
+# enable generation of interactive SVG images that allow zooming and panning.
+#
+# Note that this requires a modern browser other than Internet Explorer. Tested
+# and working are Firefox, Chrome, Safari, and Opera.
+# Note: For IE 9+ you need to set HTML_FILE_EXTENSION to xhtml in order to make
+# the SVG files visible. Older versions of IE do not have SVG support.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INTERACTIVE_SVG = NO
+
+# The DOT_PATH tag can be used to specify the path where the dot tool can be
+# found. If left blank, it is assumed the dot tool can be found in the path.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_PATH =
+
+# The DOTFILE_DIRS tag can be used to specify one or more directories that
+# contain dot files that are included in the documentation (see the \dotfile
+# command).
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOTFILE_DIRS =
+
+# The MSCFILE_DIRS tag can be used to specify one or more directories that
+# contain msc files that are included in the documentation (see the \mscfile
+# command).
+
+MSCFILE_DIRS =
+
+# The DIAFILE_DIRS tag can be used to specify one or more directories that
+# contain dia files that are included in the documentation (see the \diafile
+# command).
+
+DIAFILE_DIRS =
+
+# When using plantuml, the PLANTUML_JAR_PATH tag should be used to specify the
+# path where java can find the plantuml.jar file. If left blank, it is assumed
+# PlantUML is not used or called during a preprocessing step. Doxygen will
+# generate a warning when it encounters a \startuml command in this case and
+# will not generate output for the diagram.
+
+PLANTUML_JAR_PATH =
+
+# When using plantuml, the PLANTUML_CFG_FILE tag can be used to specify a
+# configuration file for plantuml.
+
+PLANTUML_CFG_FILE =
+
+# When using plantuml, the specified paths are searched for files specified by
+# the !include statement in a plantuml block.
+
+PLANTUML_INCLUDE_PATH =
+
+# The DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of nodes
+# that will be shown in the graph. If the number of nodes in a graph becomes
+# larger than this value, doxygen will truncate the graph, which is visualized
+# by representing a node as a red box. Note that doxygen if the number of direct
+# children of the root node in a graph is already larger than
+# DOT_GRAPH_MAX_NODES then the graph will not be shown at all. Also note that
+# the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH.
+# Minimum value: 0, maximum value: 10000, default value: 50.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_GRAPH_MAX_NODES = 50
+
+# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the graphs
+# generated by dot. A depth value of 3 means that only nodes reachable from the
+# root by following a path via at most 3 edges will be shown. Nodes that lay
+# further from the root node will be omitted. Note that setting this option to 1
+# or 2 may greatly reduce the computation time needed for large code bases. Also
+# note that the size of a graph can be further restricted by
+# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction.
+# Minimum value: 0, maximum value: 1000, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+MAX_DOT_GRAPH_DEPTH = 0
+
+# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent
+# background. This is disabled by default, because dot on Windows does not seem
+# to support this out of the box.
+#
+# Warning: Depending on the platform used, enabling this option may lead to
+# badly anti-aliased labels on the edges of a graph (i.e. they become hard to
+# read).
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_TRANSPARENT = NO
+
+# Set the DOT_MULTI_TARGETS tag to YES to allow dot to generate multiple output
+# files in one run (i.e. multiple -o and -T options on the command line). This
+# makes dot run faster, but since only newer versions of dot (>1.8.10) support
+# this, this feature is disabled by default.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_MULTI_TARGETS = NO
+
+# If the GENERATE_LEGEND tag is set to YES doxygen will generate a legend page
+# explaining the meaning of the various boxes and arrows in the dot generated
+# graphs.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GENERATE_LEGEND = YES
+
+# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate
+# files that are used to generate the various graphs.
+#
+# Note: This setting is not only used for dot files but also for msc and
+# plantuml temporary files.
+# The default value is: YES.
+
+DOT_CLEANUP = YES
diff --git a/metadata.xml b/metadata.xml
new file mode 100644
index 0000000000000000000000000000000000000000..7cbae3ae7e1d5d7d48af2f0e5577253a89f953f5
--- /dev/null
+++ b/metadata.xml
@@ -0,0 +1,204 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.3/metadata.xsd">
+ <identifier identifierType="DOI">PLACEHOLDER</identifier>
+ <titles>
+ <title xml:lang="en">VirtualFluids</title>
+ </titles>
+ <language>en</language>
+ <creators>
+ <creator>
+ <creatorName nameType="Personal">Krafczyk, Manfred</creatorName>
+ <givenName>Manfred</givenName>
+ <familyName>Krafczyk</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID">0000-0002-8509-0871</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="de">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </creator>
+ <creator>
+ <creatorName nameType="Organizational">Institut für rechnergestützte Modellierung im Bauingenieurwesen</creatorName>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ </creator>
+ </creators>
+ <publisher xml:lang="de">Institut für rechnergestützte Modellierung im Bauingenieurwesen</publisher>
+ <publicationYear>2021</publicationYear>
+ <resourceType resourceTypeGeneral="Software">Computational Fluid Dynamics Solver</resourceType>
+ <subjects>
+ <subject subjectScheme="DDC" schemeURI="https://www.oclc.org/en/dewey.html">532 Fluid Mechanics, liquid mechanics</subject>
+ </subjects>
+ <contributors>
+ <contributor contributorType="Researcher">
+ <contributorName>Ahrenholz, Benjamin</contributorName>
+ <givenName>Benjamin</givenName>
+ <familyName>Ahrenholz</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Alihussein, Hussein</contributorName>
+ <givenName>Hussein</givenName>
+ <familyName>Alihussein</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3656-7028</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Bindick, Sebastian</contributorName>
+ <givenName>Sebastian</givenName>
+ <familyName>Bindick</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Brendel, Aileen</contributorName>
+ <givenName>Aileen</givenName>
+ <familyName>Brendel</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Geier, Martin</contributorName>
+ <givenName>Martin</givenName>
+ <familyName>Geier</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-8367-9412</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Geller, Sebastian</contributorName>
+ <givenName>Sebastian</givenName>
+ <familyName>Geller</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Goraki Fard, Ehsan</contributorName>
+ <givenName>Ehsan</givenName>
+ <familyName>Goraki Fard</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Hegewald, Jan</contributorName>
+ <givenName>Jan</givenName>
+ <familyName>Hegewald</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Janßen, Christian</contributorName>
+ <givenName>Christian</givenName>
+ <familyName>Janßen</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Kutscher, Konstantin</contributorName>
+ <givenName>Konstantin</givenName>
+ <familyName>Kutscher</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1099-1608</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Lenz, Stephan</contributorName>
+ <givenName>Stephan</givenName>
+ <familyName>Lenz</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Linxweiler, Jan</contributorName>
+ <givenName>Jan</givenName>
+ <familyName>Linxweiler</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-2755-5087</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Lux, Lennard</contributorName>
+ <givenName>Lennard</givenName>
+ <familyName>Lux</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Marcus, Sven</contributorName>
+ <givenName>Sven</givenName>
+ <familyName>Marcus</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3689-2162</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Universitätsbibliothek Braunschweig</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Peters, Sören</contributorName>
+ <givenName>Sören</givenName>
+ <familyName>Peters</familyName>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Safari, Hesameddin</contributorName>
+ <givenName>Hesameddin</givenName>
+ <familyName>Safari</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Schönherr, Martin</contributorName>
+ <givenName>Martin</givenName>
+ <familyName>Schönherr</familyName>
+ <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-4774-1776</nameIdentifier>
+ <affiliation xml:lang="de">TU Braunschweig</affiliation>
+ <affiliation xml:lang="en">Institut für rechnergestützte Modellierung im Bauingenieurwesen</affiliation>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Stiebler, Maik</contributorName>
+ <givenName>Maik</givenName>
+ <familyName>Stiebler</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Textor, Sören</contributorName>
+ <givenName>Sören</givenName>
+ <familyName>Textor</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Tölke, Jonas</contributorName>
+ <givenName>Jonas</givenName>
+ <familyName>Tölke</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Uphoff, Sonja</contributorName>
+ <givenName>Sonja</givenName>
+ <familyName>Uphoff</familyName>
+ </contributor>
+
+ <contributor contributorType="Researcher">
+ <contributorName>Wellmann, Anna</contributorName>
+ <givenName>Anna</givenName>
+ <familyName>Wellmann</familyName>
+ </contributor>
+ </contributors>
+ <dates>
+ <date dateType="Created">2000</date>
+ </dates>
+ <formats>
+ <format>text/x-c</format>
+ <format>text/x-h</format>
+ <format>text/x-script.python</format>
+ </formats>
+ <relatedIdentifiers>
+ <relatedIdentifier relatedIdentifierType="URL" relationType="Requires" resourceTypeGeneral="Software">https://www.open-mpi.org/software/ompi/v4.1/</relatedIdentifier>
+ <relatedIdentifier relatedIdentifierType="URL" relationType="IsCompiledBy" resourceTypeGeneral="Software">https://cmake.org</relatedIdentifier>
+ <relatedIdentifier relatedIdentifierType="URL" relationType="IsCompiledBy" resourceTypeGeneral="Software">https://gcc.gnu.org</relatedIdentifier>
+ <relatedIdentifier relatedIdentifierType="URL" relationType="IsCompiledBy" resourceTypeGeneral="Software">https://clang.llvm.org</relatedIdentifier>
+ <relatedIdentifier relatedIdentifierType="URL" relationType="IsCompiledBy" resourceTypeGeneral="Software">https://visualstudio.microsoft.com/vs/features/cplusplus/</relatedIdentifier>
+ </relatedIdentifiers>
+ <rightsList>
+ <rights xml:lang="en" schemeURI="https://spdx.org/licenses/" rightsIdentifierScheme="SPDX" rightsIdentifier="GPL-3.0-only" rightsURI="https://www.gnu.org/licenses/gpl-3.0-standalone.html">GNU General Public License Version 3</rights>
+ </rightsList>
+ <descriptions>
+ <description descriptionType="Abstract">
+ VirtualFluids (VF) is a research code developed at the Institute for Computational Modeling in Civil Engineering (iRMB). The code is a Computational Fluid Dynamics (CFD) solver based on the Lattice Boltzmann Method (LBM) for turbulent, thermal, multiphase and multicomponent flow problems as well as for multi-field problems such as Fluid-Structure-interaction including distributed pre- and postprocessing capabilities for simulations with more than 100 billion degrees of freedom.
+ </description>
+ </descriptions>
+</resource>
diff --git a/setup.py b/setup.py
index 6f4ff71b014dbafa8800af234cf715f5207fb2a8..ffe6663be9561a209945b91bb396254b703ae892 100644
--- a/setup.py
+++ b/setup.py
@@ -10,11 +10,17 @@ from distutils.version import LooseVersion
vf_cmake_args = [
"-DBUILD_VF_PYTHON_BINDINGS=ON",
+ "-DBUILD_VF_DOUBLE_ACCURACY=ON",
+ "-DCMAKE_CXX_COMPILER_LAUNCHER=ccache",
+ "-DCMAKE_CUDA_COMPILER_LAUNCHER=ccache",
+ "-DCMAKE_C_COMPILER_LAUNCHER=ccache",
"-DBUILD_VF_CPU:BOOL=ON",
+ "-DBUILD_VF_GPU:BOOL=OFF",
"-DUSE_METIS=ON",
"-DUSE_MPI=ON",
"-DBUILD_SHARED_LIBS=OFF",
- "-DBUILD_VF_UNIT_TESTS:BOOL=ON"
+ "-DBUILD_VF_UNIT_TESTS:BOOL=ON",
+ "-DBUILD_WARNINGS_AS_ERRORS=OFF"
]
diff --git a/sonar-project.properties b/sonar-project.properties
index 7f31fa97101d3002aa47096831206cf9768a85b5..a25bb1af8070f0ea5b75f67e624211f38fef38bf 100644
--- a/sonar-project.properties
+++ b/sonar-project.properties
@@ -27,8 +27,6 @@ sonar.cxx.clangtidy.reportPath=build/clangtidy.txt
sonar.cxx.jsonCompilationDatabase=build/compile_commands.json
-sonar.cxx.gcc.reportPath=build/gcc_warnings.txt
-
#sonar.cxx.valgrind.reportPath
sonar.cxx.funccomplexity.threshold=10
diff --git a/src/basics/basics/container/CbVectorPool.h b/src/basics/basics/container/CbVectorPool.h
index e1a061d1ac3016fbe3b116243473ee609b24eb8c..0272056b51d65aacafad78cbae03971a24879a7e 100644
--- a/src/basics/basics/container/CbVectorPool.h
+++ b/src/basics/basics/container/CbVectorPool.h
@@ -118,7 +118,7 @@ public:
return this->allocData(allocator, vec, dataSize, value);
}
- UB_THROW(UbException(UB_EXARGS, "vector-key=" + UbSystem::toString(allocator.key) + " bereits vergeben!"));
+ UB_THROW(UbException(UB_EXARGS, "vector-key=" + UbSystem::toString(allocator.key) + " already taken! (e.g. SetConnectorBlockVisitor was called several times"));
}
/*==================================================================*/
bool resizeVectorData(CbVector<value_type> &vec, const size_type &dataSize, const value_type &value = value_type())
diff --git a/src/basics/geometry3d/GbCylinder3D.cpp b/src/basics/geometry3d/GbCylinder3D.cpp
index f6d1ed6e701fb7e3209a6e67720dc3d41d8f1aeb..2b90ca0fae9a7e22245961b8d713a35d72fa7df8 100644
--- a/src/basics/geometry3d/GbCylinder3D.cpp
+++ b/src/basics/geometry3d/GbCylinder3D.cpp
@@ -1162,12 +1162,10 @@ double GbCylinder3D::getIntersectionRaytraceFactor(const double &x1, const doubl
} else
return -1.0;
} else {
- // if (UbMath::negative(rx1)) d = -1.0 * (x1 - minX1) / rx1;
- // else if(UbMath::positive(rx1)) d = -1.0 * (x1 - maxX1) / rx1;
if (UbMath::negative(rx1))
- d = -1.0 * (x1 - maxX1) / rx1;
- else if (UbMath::positive(rx1))
d = -1.0 * (x1 - minX1) / rx1;
+ else if (UbMath::positive(rx1))
+ d = -1.0 * (x1 - maxX1) / rx1;
}
} else if (this->isParallelToX2Axis()) {
if (UbMath::equal(x2, minX2) && UbMath::negative(rx2))
diff --git a/src/cpu/VirtualFluids.h b/src/cpu/VirtualFluids.h
index 59dee98b1ec59ce85d270fafbe96ca7cd6b85473..363c9c046b37a45d800ea142e79617f71a8499d3 100644
--- a/src/cpu/VirtualFluids.h
+++ b/src/cpu/VirtualFluids.h
@@ -228,7 +228,7 @@
#include <LBM/LBMKernelETD3Q27BGK.h>
#include <LBM/LBMSystem.h>
#include <LBM/LBMUnitConverter.h>
-//#include <LBM/BGKLBMKernel.h>
+#include <LBM/BGKLBMKernel.h>
#include <LBM/ThixotropyLBMKernel.h>
#include <LBM/ThixotropyExpLBMKernel.h>
#include <LBM/CumulantLBMKernel.h>
diff --git a/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.cpp b/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.cpp
index 69543bc6dce034c9c878711013d0297180c3d99f..5c852528a2abe2bf8de06753f9aaa78bf7f8a565 100644
--- a/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.cpp
+++ b/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.cpp
@@ -36,7 +36,12 @@
#include "BCArray3D.h"
#include "BoundaryConditions.h"
#include "EsoTwist3D.h"
+#include "Block3D.h"
+void BCAlgorithm::setBlock(SPtr<Block3D> block)
+{
+ this->block = block;
+}
//////////////////////////////////////////////////////////////////////////
void BCAlgorithm::setNodeIndex(int x1, int x2, int x3)
{
diff --git a/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.h b/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.h
index 6b60da224ecaac9f56412cbd38b65d758816a2b2..67a3620c0a37c623c697bf8ec6a3f70f2ba00247 100644
--- a/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.h
+++ b/src/cpu/VirtualFluidsCore/BoundaryConditions/BCAlgorithm.h
@@ -41,6 +41,7 @@
class DistributionArray3D;
class BCArray3D;
class BoundaryConditions;
+class Block3D;
//! \brief Abstract class of baundary conditions algorithm
//! \details BCAlgorithm provides interface for implementation of diferent boundary conditions
@@ -77,6 +78,7 @@ public:
virtual void addDistributions(SPtr<DistributionArray3D> distributions) = 0;
virtual void addDistributionsH(SPtr<DistributionArray3D> distributionsH) {}
virtual void addDistributionsH2(SPtr<DistributionArray3D> distributionsH2) {}
+ void setBlock(SPtr<Block3D> block);
void setNodeIndex(int x1, int x2, int x3);
void setBcPointer(SPtr<BoundaryConditions> bcPtr);
void setCompressible(bool c);
@@ -107,6 +109,7 @@ protected:
SPtr<DistributionArray3D> distributionsH;
SPtr<DistributionArray3D> distributionsH2;
SPtr<BCArray3D> bcArray;
+ SPtr<Block3D> block;
LBMReal collFactor;
LBMReal collFactorL, collFactorG, collFactorPh;
diff --git a/src/cpu/VirtualFluidsCore/BoundaryConditions/RheologyBinghamModelVelocityBCAlgorithm.h b/src/cpu/VirtualFluidsCore/BoundaryConditions/RheologyBinghamModelVelocityBCAlgorithm.h
index 263119401c1d2c437e8ae3962edd33bfcd3b554c..9673a009f75bccd71924985ec9a27187d9e1e12e 100644
--- a/src/cpu/VirtualFluidsCore/BoundaryConditions/RheologyBinghamModelVelocityBCAlgorithm.h
+++ b/src/cpu/VirtualFluidsCore/BoundaryConditions/RheologyBinghamModelVelocityBCAlgorithm.h
@@ -43,7 +43,7 @@ public:
RheologyBinghamModelVelocityBCAlgorithm()
{
BCAlgorithm::type = BCAlgorithm::RheologyBinghamModelVelocityBCAlgorithm;
- BCAlgorithm::preCollision = false;
+ BCAlgorithm::preCollision = true;
}
~RheologyBinghamModelVelocityBCAlgorithm() {}
SPtr<BCAlgorithm> clone() override
diff --git a/src/cpu/VirtualFluidsCore/BoundaryConditions/VelocityBCAlgorithm.cpp b/src/cpu/VirtualFluidsCore/BoundaryConditions/VelocityBCAlgorithm.cpp
index 4905e76a9f7a3e46848b8d8dbaf81095fe9a5b14..15768aeeb043620aece86194319eafe00ea1df60 100644
--- a/src/cpu/VirtualFluidsCore/BoundaryConditions/VelocityBCAlgorithm.cpp
+++ b/src/cpu/VirtualFluidsCore/BoundaryConditions/VelocityBCAlgorithm.cpp
@@ -34,6 +34,7 @@
#include "VelocityBCAlgorithm.h"
#include "BoundaryConditions.h"
#include "DistributionArray3D.h"
+#include "Block3D.h"
VelocityBCAlgorithm::VelocityBCAlgorithm()
{
@@ -61,6 +62,9 @@ void VelocityBCAlgorithm::applyBC()
calcMacrosFct(f, drho, vx1, vx2, vx3);
calcFeqFct(feq, drho, vx1, vx2, vx3);
+ //DEBUG
+ //int blockID = block->getGlobalID();
+
rho = 1.0 + drho * compressibleFactor;
for (int fdir = D3Q27System::FSTARTDIR; fdir <= D3Q27System::FENDDIR; fdir++) {
diff --git a/src/cpu/VirtualFluidsCore/CMakeLists.txt b/src/cpu/VirtualFluidsCore/CMakeLists.txt
index 09766e266935ed1c7d89223c0713363f4df5edcf..36ac278fb8aee484d38a09a3fd4499965875f712 100644
--- a/src/cpu/VirtualFluidsCore/CMakeLists.txt
+++ b/src/cpu/VirtualFluidsCore/CMakeLists.txt
@@ -25,7 +25,7 @@ if(BUILD_USE_OPENMP)
list(APPEND VF_LIBRARIES OpenMP::OpenMP_CXX)
endif()
-vf_add_library(BUILDTYPE static PUBLIC_LINK basics muparser MPI::MPI_CXX ${VF_LIBRARIES})
+vf_add_library(BUILDTYPE static PUBLIC_LINK basics muparser MPI::MPI_CXX ${VF_LIBRARIES} PRIVATE_LINK lbm)
vf_get_library_name(library_name)
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.cpp
index 37e593d868fa76d5c5cedada99f256c0fa8c74c4..9fd6e8c28aeb1bdb8120c98f0a338aa21b38cc57 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.cpp
@@ -27,13 +27,10 @@ CalculateTorqueCoProcessor::CalculateTorqueCoProcessor( SPtr<Grid3D> grid, SPtr<
if(path.size()>0){ UbSystem::makeDirectory(path); ostr.open(fname.c_str(), std::ios_base::out | std::ios_base::app);}
if(!ostr) throw UbException(UB_EXARGS,"couldn't open file "+fname);
}
- ostr.width(12);
- ostr << "step" << "\t";
- ostr.width(10);
- ostr << "Tx" << "\t";
- ostr.width(18);
- ostr << "Ty" << "\t";
- ostr.width(18);
+
+ ostr << "step;";
+ ostr << "Tx;";
+ ostr << "Ty;";
ostr << "Tz" << std::endl;
ostr.close();
}
@@ -70,12 +67,10 @@ void CalculateTorqueCoProcessor::collectData( double step )
if(!ostr) throw UbException(UB_EXARGS,"couldn't open file "+fname);
}
- ostr.width(12);
- ostr.setf(std::ios::fixed);
- ostr << istep << "\t";
- write(&ostr, forceX1global, (char*)"\t");
- write(&ostr, forceX2global, (char*)"\t");
- write(&ostr, forceX3global, (char*)"\t");
+ ostr << istep << ";";
+ ostr << forceX1global << ";";
+ ostr << forceX2global << ";";
+ ostr << forceX3global;
ostr << std::endl;
ostr.close();
}
@@ -134,6 +129,9 @@ void CalculateTorqueCoProcessor::calculateForces()
int x3 = node[2];
Vector3D worldCoordinates = grid->getNodeCoordinates(block, x1, x2, x3);
+ double rx = worldCoordinates[0] - x1Centre;
+ double ry = worldCoordinates[1] - x2Centre;
+ double rz = worldCoordinates[2] - x3Centre;
//without ghost nodes
if (x1 < minX1 || x1 > maxX1 || x2 < minX2 || x2 > maxX2 ||x3 < minX3 || x3 > maxX3 ) continue;
@@ -141,10 +139,14 @@ void CalculateTorqueCoProcessor::calculateForces()
if(bcArray->isFluid(x1,x2,x3)) //es kann sein, dass der node von einem anderen interactor z.B. als solid gemarkt wurde!!!
{
SPtr<BoundaryConditions> bc = bcArray->getBC(x1,x2,x3);
- UbTupleDouble3 forceVec = getForces(x1,x2,x3,distributions,bc);
- torqueX1 += (worldCoordinates[1] - x2Centre) * val<3>(forceVec) - (worldCoordinates[2] - x3Centre) * val<2>(forceVec);
- torqueX2 += (worldCoordinates[2] - x3Centre) * val<1>(forceVec) - (worldCoordinates[0] - x1Centre) * val<3>(forceVec);
- torqueX3 += (worldCoordinates[0] - x1Centre) * val<2>(forceVec) - (worldCoordinates[1] - x2Centre) * val<1>(forceVec);
+ UbTupleDouble3 forceVec = getForces(x1,x2,x3,distributions,bc);
+ double Fx = val<1>(forceVec);
+ double Fy = val<2>(forceVec);
+ double Fz = val<3>(forceVec);
+
+ torqueX1 += ry * Fz - rz * Fy;
+ torqueX2 += rz * Fx - rx * Fz;
+ torqueX3 += rx * Fy - ry * Fx;
//counter++;
//UBLOG(logINFO, "x1="<<(worldCoordinates[1] - x2Centre)<<",x2=" << (worldCoordinates[2] - x3Centre)<< ",x3=" << (worldCoordinates[0] - x1Centre) <<" forceX3 = " << forceX3);
}
@@ -241,14 +243,6 @@ void CalculateTorqueCoProcessor::addInteractor( SPtr<D3Q27Interactor> interactor
{
interactors.push_back(interactor);
}
-//////////////////////////////////////////////////////////////////////////
-void CalculateTorqueCoProcessor::write(std::ofstream *fileObject, double value, char *separator)
-{
- (*fileObject).width(12);
- (*fileObject).precision(16);
- (*fileObject).setf(std::ios::fixed);
- (*fileObject) << value;
- (*fileObject) << separator;
-}
+
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.h b/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.h
index 2eda4a063a8e4a6649380e05e2684d3f1a8f68ee..43e1e75acaf4ab115ac9c6dc40b449cf98f97e79 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.h
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/CalculateTorqueCoProcessor.h
@@ -36,7 +36,6 @@ protected:
void collectData(double step);
void calculateForces();
UbTupleDouble3 getForces(int x1, int x2, int x3, SPtr<DistributionArray3D> distributions, SPtr<BoundaryConditions> bc);
- void write(std::ofstream *fileObject, double value, char *separator);
private:
std::string path;
SPtr<Communicator> comm;
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOCoProcessor.cpp
index 028cb68ca562771b263b801c48c5f3b3791c723f..a3572c8c40ed63144080c1803d728393eaf30547 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOCoProcessor.cpp
@@ -70,7 +70,7 @@ MPIIOCoProcessor::MPIIOCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const
//---------------------------------------
- MPI_Type_contiguous(7, MPI_CHAR, &arrayPresenceType);
+ MPI_Type_contiguous(8, MPI_CHAR, &arrayPresenceType);
MPI_Type_commit(&arrayPresenceType);
}
@@ -378,10 +378,24 @@ void MPIIOCoProcessor::clearAllFiles(int step)
MPI_File_set_size(file_handler, new_size);
MPI_File_close(&file_handler);
- std::string filename2 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
- int rc2 = MPI_File_open(MPI_COMM_WORLD, filename2.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
- if (rc2 != MPI_SUCCESS)
- throw UbException(UB_EXARGS, "couldn't open file " + filename2);
+ std::string filename21 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
+ int rc21 = MPI_File_open(MPI_COMM_WORLD, filename21.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc21 != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename21);
+ MPI_File_set_size(file_handler, new_size);
+ MPI_File_close(&file_handler);
+
+ std::string filename22 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ int rc22 = MPI_File_open(MPI_COMM_WORLD, filename22.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc22 != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename22);
+ MPI_File_set_size(file_handler, new_size);
+ MPI_File_close(&file_handler);
+
+ std::string filename23 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ int rc23 = MPI_File_open(MPI_COMM_WORLD, filename23.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc23 != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename23);
MPI_File_set_size(file_handler, new_size);
MPI_File_close(&file_handler);
@@ -441,25 +455,20 @@ void MPIIOCoProcessor::clearAllFiles(int step)
MPI_File_set_size(file_handler, new_size);
MPI_File_close(&file_handler);
- std::string filename10 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField.bin";
+ std::string filename10 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField1.bin";
int rc10 = MPI_File_open(MPI_COMM_WORLD, filename10.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc10 != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename10);
MPI_File_set_size(file_handler, new_size);
MPI_File_close(&file_handler);
-
- /*std::string filename10 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpBC1.bin";
- int rc10 = MPI_File_open(MPI_COMM_WORLD, filename10.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info,
- &file_handler); if (rc10 != MPI_SUCCESS) throw UbException(UB_EXARGS, "couldn't open file " + filename10);
+ std::string filename11 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField2.bin";
+ int rc11 = MPI_File_open(MPI_COMM_WORLD, filename11.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc11 != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename11);
MPI_File_set_size(file_handler, new_size);
MPI_File_close(&file_handler);
- std::string filename11 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpBC2.bin";
- int rc11 = MPI_File_open(MPI_COMM_WORLD, filename11.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info,
- &file_handler); if (rc11 != MPI_SUCCESS) throw UbException(UB_EXARGS, "couldn't open file " + filename11);
- MPI_File_set_size(file_handler, new_size);
- MPI_File_close(&file_handler);*/
}
void MPIIOCoProcessor::writeCpTimeStep(int step)
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.cpp
index 39b32b6aac7110eb873a52351d46560f8843820e..f82111472cb8bedf88e9a8e5c556f2eca9f0a9a0 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.cpp
@@ -25,9 +25,8 @@ using namespace MPIIODataStructures;
#define MESSAGE_TAG 80
#define SEND_BLOCK_SIZE 100000
-MPIIOMigrationBECoProcessor::MPIIOMigrationBECoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s,
- const std::string &path, SPtr<Communicator> comm)
- : MPIIOCoProcessor(grid, s, path, comm), nue(-999.999)
+MPIIOMigrationBECoProcessor::MPIIOMigrationBECoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path, SPtr<Communicator> comm)
+ : MPIIOCoProcessor(grid, s, path, comm), nue(-999.999), nuL(-999.999), nuG(-999.999), densityRatio(-999.999)
{
memset(&boundCondParamStr, 0, sizeof(boundCondParamStr));
@@ -107,44 +106,60 @@ void MPIIOMigrationBECoProcessor::writeDataSet(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
dataSetParam dataSetParamStr1, dataSetParamStr2, dataSetParamStr3;
int firstGlobalID;
- std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
+ std::vector<double> doubleValuesArrayF; // double-values (arrays of f's) in all blocks Fdistribution
+ std::vector<double> doubleValuesArrayH1; // double-values (arrays of f's) in all blocks H1distribution
+ // std::vector<double> doubleValuesArrayH2; // double-values (arrays of f's) in all blocks H2distribution
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeDataSet start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+ bool multiPhase = false;
DSArraysPresence arrPresence;
bool firstBlock = true;
int doubleCountInBlock = 0;
int ic = 0;
- SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF, D3Q27EsoTwist3DSplittedVectorPtrH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF, localDistributionsH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF, nonLocalDistributionsH;
- CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF, zeroDistributionsH;
+ SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF = 0, D3Q27EsoTwist3DSplittedVectorPtrH1 = 0, D3Q27EsoTwist3DSplittedVectorPtrH2 = 0;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF = 0, localDistributionsH1 = 0, localDistributionsH2 = 0;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF = 0, nonLocalDistributionsH1 = 0, nonLocalDistributionsH2 = 0;
+ CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF = 0, zeroDistributionsH1 = 0, zeroDistributionsH2 = 0;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getFdistributions());
+ D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getFdistributions());
localDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getLocalDistributions();
nonLocalDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getNonLocalDistributions();
zeroDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getZeroDistributions();
- D3Q27EsoTwist3DSplittedVectorPtrH = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getHdistributions());
- localDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getLocalDistributions();
- nonLocalDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getNonLocalDistributions();
- zeroDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getZeroDistributions();
+ D3Q27EsoTwist3DSplittedVectorPtrH1 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getHdistributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH1 != 0)
+ {
+ multiPhase = true;
+ localDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getLocalDistributions();
+ nonLocalDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getNonLocalDistributions();
+ zeroDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getZeroDistributions();
+ }
+
+ /*D3Q27EsoTwist3DSplittedVectorPtrH2 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getH2distributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ localDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getLocalDistributions();
+ nonLocalDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getNonLocalDistributions();
+ zeroDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getZeroDistributions();
+ }*/
+
if (firstBlock) // && block->getKernel()) // when first (any) valid block...
{
@@ -171,94 +186,92 @@ void MPIIOMigrationBECoProcessor::writeDataSet(int step)
}
// ... than save some parameters that are equal in all blocks
- dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
- dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
- dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
-
- // Fdistributions + Hdistributions
- doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
+ dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
+ dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
+
+ doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3]) * 2;
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray =
- block->getKernel()->getDataSet()->getAverageDensity();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray = block->getKernel()->getDataSet()->getAverageDensity();
if (averageDensityArray)
arrPresence.isAverageDensityArrayPresent = true;
else
arrPresence.isAverageDensityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr =
- block->getKernel()->getDataSet()->getAverageVelocity();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr = block->getKernel()->getDataSet()->getAverageVelocity();
if (AverageVelocityArray3DPtr)
arrPresence.isAverageVelocityArrayPresent = true;
else
arrPresence.isAverageVelocityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr =
- block->getKernel()->getDataSet()->getAverageFluctuations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr = block->getKernel()->getDataSet()->getAverageFluctuations();
if (AverageFluctArray3DPtr)
arrPresence.isAverageFluktuationsArrayPresent = true;
else
arrPresence.isAverageFluktuationsArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr =
- block->getKernel()->getDataSet()->getAverageTriplecorrelations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr = block->getKernel()->getDataSet()->getAverageTriplecorrelations();
if (AverageTripleArray3DPtr)
arrPresence.isAverageTripleArrayPresent = true;
else
arrPresence.isAverageTripleArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr =
- block->getKernel()->getDataSet()->getShearStressValues();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr = block->getKernel()->getDataSet()->getShearStressValues();
if (ShearStressValArray3DPtr)
arrPresence.isShearStressValArrayPresent = true;
else
arrPresence.isShearStressValArrayPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr =
- block->getKernel()->getDataSet()->getRelaxationFactor();
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr = block->getKernel()->getDataSet()->getRelaxationFactor();
if (relaxationFactor3DPtr)
arrPresence.isRelaxationFactorPresent = true;
else
arrPresence.isRelaxationFactorPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr =
- block->getKernel()->getDataSet()->getPhaseField();
- if (phaseField3DPtr)
- arrPresence.isPhaseFieldPresent = true;
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr1 = block->getKernel()->getDataSet()->getPhaseField();
+ if (phaseField3DPtr1)
+ arrPresence.isPhaseField1Present = true;
else
- arrPresence.isPhaseFieldPresent = false;
+ arrPresence.isPhaseField1Present = false;
+
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr2 = block->getKernel()->getDataSet()->getPhaseField2();
+ if (phaseField3DPtr2)
+ arrPresence.isPhaseField2Present = true;
+ else
+ arrPresence.isPhaseField2Present = false;
+
firstBlock = false;
}
- if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsF->getDataVector().begin(),
- localDistributionsF->getDataVector().end());
- if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsF->getDataVector().begin(),
- nonLocalDistributionsF->getDataVector().end());
+ if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), localDistributionsF->getDataVector().begin(), localDistributionsF->getDataVector().end());
+ if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), nonLocalDistributionsF->getDataVector().begin(), nonLocalDistributionsF->getDataVector().end());
if (zeroDistributionsF && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsF->getDataVector().begin(),
- zeroDistributionsF->getDataVector().end());
-
- if (localDistributionsH && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsH->getDataVector().begin(),
- localDistributionsH->getDataVector().end());
- if (nonLocalDistributionsH && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsH->getDataVector().begin(),
- nonLocalDistributionsH->getDataVector().end());
- if (zeroDistributionsH && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsH->getDataVector().begin(),
- zeroDistributionsH->getDataVector().end());
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), zeroDistributionsF->getDataVector().begin(), zeroDistributionsF->getDataVector().end());
+
+ if (multiPhase)
+ {
+ if (localDistributionsH1 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), localDistributionsH1->getDataVector().begin(), localDistributionsH1->getDataVector().end());
+ if (nonLocalDistributionsH1 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), nonLocalDistributionsH1->getDataVector().begin(), nonLocalDistributionsH1->getDataVector().end());
+ if (zeroDistributionsH1 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), zeroDistributionsH1->getDataVector().begin(), zeroDistributionsH1->getDataVector().end());
+ }
+
+ /*if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ if (localDistributionsH2 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), localDistributionsH2->getDataVector().begin(), localDistributionsH2->getDataVector().end());
+ if (nonLocalDistributionsH2 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), nonLocalDistributionsH2->getDataVector().begin(), nonLocalDistributionsH2->getDataVector().end());
+ if (zeroDistributionsH2 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), zeroDistributionsH2->getDataVector().begin(), zeroDistributionsH2->getDataVector().end());
+ }*/
ic++;
}
@@ -267,10 +280,10 @@ void MPIIOMigrationBECoProcessor::writeDataSet(int step)
MPI_Type_contiguous(doubleCountInBlock , MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -287,28 +300,57 @@ void MPIIOMigrationBECoProcessor::writeDataSet(int step)
// write to the file
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
- MPI_Offset write_offset = (MPI_Offset)(3 * sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) *
- (MPI_Offset)(doubleCountInBlock) *
- (MPI_Offset)(sizeof(double));
+ MPI_Offset write_offset = (MPI_Offset)(3 * sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
MPI_File_write_at(file_handler, (MPI_Offset)0, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, write_offset, &doubleValuesArray[0], blocksCount, dataSetDoubleType,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayF[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
+
+ //-------------------------------- H1 ------------------------------------------------
+ if (multiPhase)
+ {
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ write_offset = (MPI_Offset)(firstGlobalID) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH1[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);
+ }
+
+ //-------------------------------- H2 --------------------------------------------------
+ /*if (D3Q27EsoTwist3DSplittedVectorPtr2 != 0)
+ {
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ write_offset = (MPI_Offset)(firstGlobalID) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH2[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);
+ } */
+
+ //--------------------------------
+
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeDataSet time: " << finish - start << " s");
}
@@ -346,9 +388,12 @@ void MPIIOMigrationBECoProcessor::writeDataSet(int step)
write3DArray(step, RelaxationFactor, std::string("/cpRelaxationFactor.bin"));
// writeRelaxationFactor(step);
- if (arrPresence.isPhaseFieldPresent)
- write3DArray(step, PhaseField, std::string("/cpPhaseField.bin"));
-}
+ if (arrPresence.isPhaseField1Present)
+ write3DArray(step, PhaseField1, std::string("/cpPhaseField1.bin"));
+
+ if (arrPresence.isPhaseField2Present)
+ write3DArray(step, PhaseField2, std::string("/cpPhaseField2.bin"));
+ }
void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::string fname)
{
@@ -361,7 +406,8 @@ void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -374,16 +420,18 @@ void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ___Array;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write4DArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- switch (arrayType) {
+ switch (arrayType)
+ {
case AverageDensity:
___Array = block->getKernel()->getDataSet()->getAverageDensity();
break;
@@ -400,8 +448,7 @@ void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::
___Array = block->getKernel()->getDataSet()->getShearStressValues();
break;
default:
- UB_THROW(UbException(UB_EXARGS,
- "MPIIOMigrationBECoProcessor::write4DArray : 4D array type does not exist!"));
+ UB_THROW(UbException(UB_EXARGS, "MPIIOMigrationBECoProcessor::write4DArray : 4D array type does not exist!"));
break;
}
@@ -410,29 +457,26 @@ void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::
firstGlobalID = block->getGlobalID();
dataSetParamStr.nx1 = dataSetParamStr.nx2 = dataSetParamStr.nx3 = 0;
- dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
- dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
- dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
- dataSetParamStr.nx[3] = static_cast<int>(___Array->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
+ dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
+ dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
+ dataSetParamStr.nx[3] = static_cast<int>(___Array->getNX4());
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(),
- ___Array->getDataVector().end());
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
+ doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(), ___Array->getDataVector().end());
ic++;
}
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write4DArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// register new MPI-type depending on the block-specific information
@@ -451,20 +495,18 @@ void MPIIOMigrationBECoProcessor::write4DArray(int step, Arrays arrayType, std::
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
- MPI_Offset write_offset = (MPI_Offset)(sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) *
- (MPI_Offset)(doubleCountInBlock) *
- (MPI_Offset)(sizeof(double));
+ MPI_Offset write_offset = (MPI_Offset)(sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
// each process writes common parameters of a dataSet
MPI_File_write_at(file_handler, 0, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, write_offset, &doubleValuesArray[0], blocksCount, dataSetDoubleType,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write4DArray time: " << finish - start << " s");
}
@@ -481,7 +523,8 @@ void MPIIOMigrationBECoProcessor::write3DArray(int step, Arrays arrayType, std::
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -494,25 +537,30 @@ void MPIIOMigrationBECoProcessor::write3DArray(int step, Arrays arrayType, std::
int ic = 0;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> ___Array;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write3DArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- switch (arrayType) {
+ switch (arrayType)
+ {
case RelaxationFactor:
___Array = block->getKernel()->getDataSet()->getRelaxationFactor();
break;
- case PhaseField:
+ case PhaseField1:
___Array = block->getKernel()->getDataSet()->getPhaseField();
break;
+ case PhaseField2:
+ ___Array = block->getKernel()->getDataSet()->getPhaseField2();
+ break;
default:
UB_THROW(UbException(UB_EXARGS,
- "MPIIOMigrationBECoProcessor::write3DArray : 3D array type does not exist!"));
+ "MPIIOMigrationBECoProcessor::write3DArray : 3D array type does not exist!"));
break;
}
@@ -531,17 +579,16 @@ void MPIIOMigrationBECoProcessor::write3DArray(int step, Arrays arrayType, std::
}
if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(),
- ___Array->getDataVector().end());
+ doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(), ___Array->getDataVector().end());
ic++;
}
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write3DArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// register new MPI-type depending on the block-specific information
@@ -560,37 +607,33 @@ void MPIIOMigrationBECoProcessor::write3DArray(int step, Arrays arrayType, std::
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
- MPI_Offset write_offset = (MPI_Offset)(sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) *
- (MPI_Offset)(doubleCountInBlock) *
- (MPI_Offset)(sizeof(double));
+ MPI_Offset write_offset = (MPI_Offset)(sizeof(dataSetParam)) + (MPI_Offset)(firstGlobalID) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
// each process writes common parameters of a dataSet
MPI_File_write_at(file_handler, 0, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, write_offset, &doubleValuesArray[0], blocksCount, dataSetDoubleType,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::write3DArray time: " << finish - start << " s");
}
}
-//---------------------------------------------------------------------------------
-
void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
{
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeBoundaryConds start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
int blocksCount = 0; // quantity of blocks, that belong to this process
@@ -601,7 +644,8 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -616,24 +660,26 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
int ic = 0;
SPtr<BCArray3D> bcArr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // all the blocks of the current level
{
bcArr = block->getKernel()->getBCProcessor()->getBCArray();
- bcAddArray[ic].globalID =
- block->getGlobalID(); // id of the block needed to find it while regenerating the grid
+ bcAddArray[ic].globalID = block->getGlobalID(); // id of the block needed to find it while regenerating the grid
bcAddArray[ic].boundCond_count = 0; // how many BoundaryConditions in this block
bcAddArray[ic].indexContainer_count = 0; // how many indexContainer-values in this block
bytesCount[ic] = sizeof(BCAddMigration);
bcVector[ic].resize(0);
indexContainerVector[ic].resize(0);
- for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++) {
+ for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++)
+ {
BoundaryCondition *bouCond = new BoundaryCondition();
if (bcArr->bcvector[bc] == NULL)
memset(bouCond, 0, sizeof(BoundaryCondition));
- else {
+ else
+ {
bouCond->noslipBoundaryFlags = bcArr->bcvector[bc]->getNoSlipBoundary();
bouCond->slipBoundaryFlags = bcArr->bcvector[bc]->getSlipBoundary();
bouCond->velocityBoundaryFlags = bcArr->bcvector[bc]->getVelocityBoundary();
@@ -662,7 +708,8 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
bytesCount[ic] += sizeof(BoundaryCondition);
}
- if (bcindexmatrixCountNotInit) {
+ if (bcindexmatrixCountNotInit)
+ {
boundCondParamStr.nx1 = static_cast<int>(bcArr->bcindexmatrix.getNX1());
boundCondParamStr.nx2 = static_cast<int>(bcArr->bcindexmatrix.getNX2());
boundCondParamStr.nx3 = static_cast<int>(bcArr->bcindexmatrix.getNX3());
@@ -670,11 +717,9 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
bcindexmatrixCountNotInit = false;
}
- bcindexmatrixVector.insert(bcindexmatrixVector.end(), bcArr->bcindexmatrix.getDataVector().begin(),
- bcArr->bcindexmatrix.getDataVector().end());
+ bcindexmatrixVector.insert(bcindexmatrixVector.end(), bcArr->bcindexmatrix.getDataVector().begin(), bcArr->bcindexmatrix.getDataVector().end());
- indexContainerVector[ic].insert(indexContainerVector[ic].begin(), bcArr->indexContainer.begin(),
- bcArr->indexContainer.end());
+ indexContainerVector[ic].insert(indexContainerVector[ic].begin(), bcArr->indexContainer.begin(), bcArr->indexContainer.end());
bcAddArray[ic].indexContainer_count = static_cast<int>(bcArr->indexContainer.size());
count_indexContainer += bcAddArray[ic].indexContainer_count;
bytesCount[ic] += bcAddArray[ic].indexContainer_count * sizeof(int);
@@ -688,10 +733,10 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
MPI_Type_contiguous(boundCondParamStr.bcindexmatrixCount, MPI_INT, &bcindexmatrixType);
MPI_Type_commit(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -712,13 +757,10 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
- MPI_Offset write_offset = (MPI_Offset)(sizeof(int)) + (MPI_Offset)(bcAddArray[0].globalID) *
- (MPI_Offset)(boundCondParamStr.bcindexmatrixCount) *
- (MPI_Offset)(sizeof(int));
+ MPI_Offset write_offset = (MPI_Offset)(sizeof(int)) + (MPI_Offset)(bcAddArray[0].globalID) * (MPI_Offset)(boundCondParamStr.bcindexmatrixCount) * (MPI_Offset)(sizeof(int));
MPI_File_write_at(file_handler, 0, &boundCondParamStr.bcindexmatrixCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, write_offset, &bcindexmatrixVector[0], blocksCount, bcindexmatrixType,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, write_offset, &bcindexmatrixVector[0], blocksCount, bcindexmatrixType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
@@ -732,14 +774,17 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
MPI_File_write_at(file_handler, 0, &boundCondParamStr, 4, MPI_INT, MPI_STATUS_IGNORE);
- write_offset =
- (MPI_Offset)(sizeof(boundCondParam)) + (MPI_Offset)(grid->getNumberOfBlocks()) * (MPI_Offset)(sizeof(size_t));
+ write_offset = (MPI_Offset)(sizeof(boundCondParam)) + (MPI_Offset)(grid->getNumberOfBlocks()) * (MPI_Offset)(sizeof(size_t));
size_t next_file_offset = 0;
- if (size > 1) {
- if (rank == 0) {
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
next_file_offset = write_offset + allBytesCount;
MPI_Send(&next_file_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
next_file_offset = write_offset + allBytesCount;
if (rank < size - 1)
@@ -749,21 +794,17 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
MPI_Offset write_offsetIndex;
- for (int nb = 0; nb < blocksCount; nb++) {
- write_offsetIndex =
- (MPI_Offset)(sizeof(boundCondParam)) + (MPI_Offset)(bcAddArray[nb].globalID) * (MPI_Offset)(sizeof(size_t));
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
+ write_offsetIndex = (MPI_Offset)(sizeof(boundCondParam)) + (MPI_Offset)(bcAddArray[nb].globalID) * (MPI_Offset)(sizeof(size_t));
MPI_File_write_at(file_handler, write_offsetIndex, &write_offset, 1, MPI_LONG_LONG_INT, MPI_STATUS_IGNORE);
MPI_File_write_at(file_handler, write_offset, &bcAddArray[nb], 3, MPI_INT, MPI_STATUS_IGNORE);
if (bcVector[nb].size() > 0)
- MPI_File_write_at(file_handler, write_offset + (MPI_Offset)(sizeof(BCAddMigration)), &bcVector[nb][0],
- bcAddArray[nb].boundCond_count, boundCondType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, write_offset + (MPI_Offset)(sizeof(BCAddMigration)), &bcVector[nb][0], bcAddArray[nb].boundCond_count, boundCondType, MPI_STATUS_IGNORE);
if (indexContainerVector[nb].size() > 0)
- MPI_File_write_at(
- file_handler,
- write_offset + (MPI_Offset)(sizeof(BCAddMigration)) +
- (MPI_Offset)(bcAddArray[nb].boundCond_count) * (MPI_Offset)(sizeof(BoundaryCondition)),
+ MPI_File_write_at(file_handler, write_offset + (MPI_Offset)(sizeof(BCAddMigration)) + (MPI_Offset)(bcAddArray[nb].boundCond_count) * (MPI_Offset)(sizeof(BoundaryCondition)),
&indexContainerVector[nb][0], bcAddArray[nb].indexContainer_count, MPI_INT, MPI_STATUS_IGNORE);
write_offset += bytesCount[nb];
@@ -772,7 +813,8 @@ void MPIIOMigrationBECoProcessor::writeBoundaryConds(int step)
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::writeBoundaryConds time: " << finish - start << " s");
}
@@ -792,8 +834,7 @@ void MPIIOMigrationBECoProcessor::restart(int step)
UBLOG(logINFO, "Load check point - start");
readBlocks(step);
- SPtr<Grid3DVisitor> newMetisVisitor(new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased,
- D3Q27System::BSW, MetisPartitioner::KWAY));
+ SPtr<Grid3DVisitor> newMetisVisitor(new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased, D3Q27System::BSW, MetisPartitioner::KWAY));
grid->accept(newMetisVisitor);
readDataSet(step);
@@ -806,8 +847,7 @@ void MPIIOMigrationBECoProcessor::restart(int step)
void MPIIOMigrationBECoProcessor::readBlocks(int step) { MPIIOCoProcessor::readBlocks(step); }
-void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, int doubleCountInBlock,
- std::vector<double> &pV, std::vector<double> *rawDataReceive)
+void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, int doubleCountInBlock, std::vector<double> &pV, std::vector<double> *rawDataReceive)
{
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
@@ -821,7 +861,8 @@ void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, i
int *blocksCounterRec = new int[size];
std::vector<double> *rawDataSend = new std::vector<double>[size];
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
rawDataSend[r].resize(0);
blocksCounterSend[r] = 0;
blocksCounterRec[r] = 0;
@@ -842,8 +883,7 @@ void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, i
{
blocksCounterRec[tempRank]++;
rawDataReceive[tempRank].push_back(double(indexB + ind));
- rawDataReceive[tempRank].insert(rawDataReceive[tempRank].end(),
- pV.begin() + ind * size_t(doubleCountInBlock),
+ rawDataReceive[tempRank].insert(rawDataReceive[tempRank].end(), pV.begin() + ind * size_t(doubleCountInBlock),
pV.begin() + ind * size_t(doubleCountInBlock) + size_t(doubleCountInBlock));
} else // we must send data to other processes
{
@@ -856,17 +896,20 @@ void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, i
MPI_Request *requests = new MPI_Request[size * 2]; // send + receive
int requestCount = 0;
- // MPI_Status status;
- for (int r = 0; r < size; r++) {
- if (r != rank) {
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
MPI_Irecv(&blocksCounterRec[r], 1, MPI_INT, r, tagN, MPI_COMM_WORLD, &requests[requestCount]);
requestCount++;
}
}
- for (int r = 0; r < size; r++) {
- if (r != rank) {
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
MPI_Isend(&blocksCounterSend[r], 1, MPI_INT, r, tagN, MPI_COMM_WORLD, &requests[requestCount]);
requestCount++;
}
@@ -877,7 +920,8 @@ void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, i
MPI_Type_contiguous(doubleCountInBlock + 1, MPI_DOUBLE, &sendBlockDoubleType);
MPI_Type_commit(&sendBlockDoubleType);
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
if (r != rank)
rawDataReceive[r].resize(size_t(blocksCounterRec[r]) * size_t(doubleCountInBlock + 1));
}
@@ -888,35 +932,39 @@ void MPIIOMigrationBECoProcessor::blocksExchange(int tagN, int ind1, int ind2, i
const int maxQuant = 400;
int restQuant;
- for (int r = 0; r < size; r++) {
- if (r != rank) {
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
sendRecCount = int(blocksCounterRec[r] / maxQuant);
if (sendRecCount * maxQuant < blocksCounterRec[r])
sendRecCount++;
requests = (MPI_Request *)realloc(requests, (requestCount + sendRecCount) * sizeof(MPI_Request));
- for (int sc = 0; sc < sendRecCount; sc++) {
+ for (int sc = 0; sc < sendRecCount; sc++)
+ {
restQuant = (sc < sendRecCount - 1) ? maxQuant : blocksCounterRec[r] - sc * maxQuant;
sendRecOffset = size_t(sc) * size_t(maxQuant) * size_t((doubleCountInBlock + 1));
- MPI_Irecv(&rawDataReceive[r][sendRecOffset], restQuant, sendBlockDoubleType, r, tagN, MPI_COMM_WORLD,
- &requests[requestCount]);
+ MPI_Irecv(&rawDataReceive[r][sendRecOffset], restQuant, sendBlockDoubleType, r, tagN, MPI_COMM_WORLD, &requests[requestCount]);
requestCount++;
}
}
}
- for (int r = 0; r < size; r++) {
- if (r != rank) {
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
sendRecCount = int(blocksCounterSend[r] / maxQuant);
if (sendRecCount * maxQuant < blocksCounterSend[r])
sendRecCount++;
requests = (MPI_Request *)realloc(requests, (requestCount + sendRecCount) * sizeof(MPI_Request));
- for (int sc = 0; sc < sendRecCount; sc++) {
+ for (int sc = 0; sc < sendRecCount; sc++)
+ {
restQuant = (sc < sendRecCount - 1) ? maxQuant : blocksCounterSend[r] - sc * maxQuant;
sendRecOffset = size_t(sc) * size_t(maxQuant) * size_t((doubleCountInBlock + 1));
- MPI_Isend(&rawDataSend[r][sendRecOffset], restQuant, sendBlockDoubleType, r, tagN, MPI_COMM_WORLD,
- &requests[requestCount]);
+ MPI_Isend(&rawDataSend[r][sendRecOffset], restQuant, sendBlockDoubleType, r, tagN, MPI_COMM_WORLD, &requests[requestCount]);
requestCount++;
}
}
@@ -942,13 +990,20 @@ void MPIIOMigrationBECoProcessor::readDataSet(int step)
UB_THROW(UbException(UB_EXARGS, "bcProcessor does not exist!"));
if (nue == -999.999)
UB_THROW(UbException(UB_EXARGS, "nue is not initialised!"));
+ if (nuL == -999.999 )
+ UB_THROW(UbException(UB_EXARGS, "nuL is not initialised!"));
+ if (nuG == -999.999)
+ UB_THROW(UbException(UB_EXARGS, "nuG is not initialised!"));
+ if (densityRatio == -999.999)
+ UB_THROW(UbException(UB_EXARGS, "densityRatio is not initialised!"));
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+ bool multiPhase = false;
dataSetParam dataSetParamStr1, dataSetParamStr2, dataSetParamStr3;
int blocksCountAll = grid->getNumberOfBlocks(); // quantity of all blocks in the grid
@@ -968,150 +1023,183 @@ void MPIIOMigrationBECoProcessor::readDataSet(int step)
start = MPI_Wtime();
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
MPI_File_read_at(file_handler, (MPI_Offset)0, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
- size_t doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ size_t doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3]) * 2;
- std::vector<double> doubleValuesArray(myBlocksCount * doubleCountInBlock); // double-values in all blocks
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+ std::vector<double> doubleValuesArrayF(size_t(myBlocksCount * doubleCountInBlock)); // double-values in all blocks Fdistributions
+ std::vector<double> doubleValuesArrayH1; // double-values in all blocks H1distributions
+ //std::vector<double> doubleValuesArrayH2; // double-values in all blocks H2distributions
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- MPI_Offset read_offset =
- (MPI_Offset)(3 * sizeof(dataSetParam)) + (MPI_Offset)(indexB * doubleCountInBlock * sizeof(double));
- MPI_File_read_at(file_handler, read_offset, &doubleValuesArray[0], int(myBlocksCount), dataSetDoubleType,
- MPI_STATUS_IGNORE);
+ //--------------------------------- F ---------------------------------------------------------
+ MPI_Offset read_offset = (MPI_Offset)(3 * sizeof(dataSetParam)) + (MPI_Offset)(indexB * doubleCountInBlock * sizeof(double));
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayF[0], int(myBlocksCount), dataSetDoubleType, MPI_STATUS_IGNORE);
+
+ MPI_File_close(&file_handler);
+
+ //--------------------------------- H1 ---------------------------------------------------------
+ MPI_Offset fsize;
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+ MPI_File_get_size(file_handler, &fsize);
+ if (fsize > 0)
+ {
+ multiPhase = true;
+ doubleValuesArrayH1.resize(myBlocksCount * doubleCountInBlock);
+ read_offset = (MPI_Offset)(indexB * doubleCountInBlock * sizeof(double)) ;
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayH1[0], int(myBlocksCount), dataSetDoubleType, MPI_STATUS_IGNORE);
+ }
MPI_File_close(&file_handler);
+
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet start of exchange of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
- std::vector<double> *rawDataReceive = new std::vector<double>[size];
+ std::vector<double>* rawDataReceiveF = new std::vector<double>[size];
for (int r = 0; r < size; r++)
- rawDataReceive[r].resize(0);
+ rawDataReceiveF[r].resize(0);
+ blocksExchange(MESSAGE_TAG, indexB, indexE, int(doubleCountInBlock), doubleValuesArrayF, rawDataReceiveF);
+
+ std::vector<double>* rawDataReceiveH1 = new std::vector<double>[size];
+ for (int r = 0; r < size; r++)
+ rawDataReceiveH1[r].resize(0);
+ blocksExchange(MESSAGE_TAG, indexB, indexE, int(doubleCountInBlock), doubleValuesArrayH1, rawDataReceiveH1);
- blocksExchange(MESSAGE_TAG, indexB, indexE, int(doubleCountInBlock), doubleValuesArray, rawDataReceive);
+ /* std::vector<double>* rawDataReceiveH2 = new std::vector<double>[size];
+ for (int r = 0; r < size; r++)
+ rawDataReceiveH2[r].resize(0);
+ blocksExchange(MESSAGE_TAG, indexB, indexE, int(doubleCountInBlock), doubleValuesArrayH2, rawDataReceiveH2);*/
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
-
+
//-------------------------------------- restore blocks ---------------------------------
int blockID;
- std::vector<double> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
- std::vector<double> vectorsOfValuesH1, vectorsOfValuesH2, vectorsOfValuesH3;
-
- size_t vectorSize1 =
- dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
- size_t vectorSize2 =
- dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
- size_t vectorSize3 =
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+ std::vector<LBMReal> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
+ std::vector<LBMReal> vectorsOfValuesH11, vectorsOfValuesH12, vectorsOfValuesH13;
+ //std::vector<LBMReal> vectorsOfValuesH21, vectorsOfValuesH22, vectorsOfValuesH23;
+
+ size_t vectorSize1 = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
+ size_t vectorSize2 = dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
+ size_t vectorSize3 = dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
size_t index;
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
index = 0;
- for (int ii = 0; ii < int(rawDataReceive[r].size() / doubleCountInBlock); ii++) {
- blockID = (int)(rawDataReceive[r][index]);
+ for (int ii = 0; ii < int(rawDataReceiveF[r].size() / doubleCountInBlock); ii++)
+ {
+ blockID = (int)(rawDataReceiveF[r][index]);
index += 1;
- vectorsOfValuesF1.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize1);
- index += vectorSize1;
-
- vectorsOfValuesF2.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize2);
- index += vectorSize2;
-
- vectorsOfValuesF3.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize3);
- index += vectorSize3;
-
- vectorsOfValuesH1.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize1);
+ vectorsOfValuesF1.assign(rawDataReceiveF[r].data() + index, rawDataReceiveF[r].data() + index + vectorSize1);
+ if(multiPhase)
+ vectorsOfValuesH11.assign(rawDataReceiveH1[r].data() + index, rawDataReceiveH1[r].data() + index + vectorSize1);
+ //vectorsOfValuesH21.assign(rawDataReceiveH2[r].data() + index, rawDataReceiveH2[r].data() + index + vectorSize1);
index += vectorSize1;
- vectorsOfValuesH2.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize2);
+ vectorsOfValuesF2.assign(rawDataReceiveF[r].data() + index, rawDataReceiveF[r].data() + index + vectorSize2);
+ if (multiPhase)
+ vectorsOfValuesH12.assign(rawDataReceiveH1[r].data() + index, rawDataReceiveH1[r].data() + index + vectorSize1);
+ //vectorsOfValuesH22.assign(rawDataReceiveH2[r].data() + index, rawDataReceiveH2[r].data() + index + vectorSize1);
index += vectorSize2;
- vectorsOfValuesH3.assign(rawDataReceive[r].data() + index, rawDataReceive[r].data() + index + vectorSize3);
+ vectorsOfValuesF3.assign(rawDataReceiveF[r].data() + index, rawDataReceiveF[r].data() + index + vectorSize3);
+ if (multiPhase)
+ vectorsOfValuesH13.assign(rawDataReceiveH1[r].data() + index, rawDataReceiveH1[r].data() + index + vectorSize1);
+ //vectorsOfValuesH23.assign(rawDataReceiveH2[r].data() + index, rawDataReceiveH2[r].data() + index + vectorSize1);
index += vectorSize3;
SPtr<DistributionArray3D> mFdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
vectorsOfValuesF3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX1(dataSetParamStr1.nx1);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX2(dataSetParamStr1.nx2);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX3(dataSetParamStr1.nx3);
- SPtr<DistributionArray3D> mHdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setZeroDistributions( CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
- vectorsOfValuesH3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
-
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX1(dataSetParamStr1.nx1);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX2(dataSetParamStr1.nx2);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX3(dataSetParamStr1.nx3);
+ SPtr<DistributionArray3D> mH1distributions(new D3Q27EsoTwist3DSplittedVector());
+ if (multiPhase)
+ {
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH11, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH12, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH13, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX3(dataSetParamStr1.nx3);
+ }
+
+ /*SPtr<DistributionArray3D> mH2distributions(new D3Q27EsoTwist3DSplittedVector());
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH21, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH22, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH23, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX3(dataSetParamStr1.nx3);*/
+
// find the nesessary block and fill it
SPtr<Block3D> block = grid->getBlock(blockID);
this->lbmKernel->setBlock(block);
SPtr<LBMKernel> kernel = this->lbmKernel->clone();
- LBMReal collFactor = LBMSystem::calcCollisionFactor(this->nue, block->getLevel());
+ LBMReal collFactor = LBMSystem::calcCollisionFactor(this->nue, block->getLevel());
+ LBMReal collFactorL = LBMSystem::calcCollisionFactor(this->nuL, block->getLevel());
+ LBMReal collFactorG = LBMSystem::calcCollisionFactor(this->nuG, block->getLevel());
kernel->setCollisionFactor(collFactor);
kernel->setIndex(block->getX1(), block->getX2(), block->getX3());
kernel->setDeltaT(LBMSystem::getDeltaT(block->getLevel()));
+ kernel->setCollisionFactorMultiphase(collFactorL, collFactorG);
+ kernel->setDensityRatio(this->densityRatio);
SPtr<DataSet3D> dataSetPtr = SPtr<DataSet3D>(new DataSet3D());
dataSetPtr->setFdistributions(mFdistributions);
- dataSetPtr->setHdistributions(mHdistributions);
+ if (multiPhase)
+ dataSetPtr->setHdistributions(mH1distributions);
+// dataSetPtr->setHdistributions(mH2distributions);
kernel->setDataSet(dataSetPtr);
block->setKernel(kernel);
}
}
- if (comm->isRoot()) {
+ //if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readDataSet end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
//-------------------------------------------------------------
@@ -1149,11 +1237,16 @@ void MPIIOMigrationBECoProcessor::readDataSet(int step)
if (arrPresence.isRelaxationFactorPresent)
readArray(step, RelaxationFactor, std::string("/cpRelaxationFactor.bin"));
// readRelaxationFactor(step);
+
+ if (arrPresence.isPhaseField1Present)
+ readArray(step, PhaseField1, std::string("/cpPhaseField1.bin"));
- if (arrPresence.isPhaseFieldPresent)
- readArray(step, PhaseField, std::string("/cpPhaseField.bin"));
+ if (arrPresence.isPhaseField2Present)
+ readArray(step, PhaseField2, std::string("/cpPhaseField2.bin"));
- delete[] rawDataReceive;
+ delete[] rawDataReceiveF;
+// delete[] rawDataReceiveH1;
+// delete[] rawDataReceiveH2;
}
void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::string fname)
@@ -1162,11 +1255,12 @@ void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::strin
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+
double start, finish;
if (comm->isRoot())
start = MPI_Wtime();
@@ -1194,56 +1288,53 @@ void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::strin
MPI_File_read_at(file_handler, (MPI_Offset)0, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
- size_t doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ size_t doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(myBlocksCount * doubleCountInBlock); // double-values in all blocks
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- MPI_Offset read_offset = (MPI_Offset)(sizeof(dataSetParam)) +
- (MPI_Offset)(indexB) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
- MPI_File_read_at(file_handler, read_offset, &doubleValuesArray[0], int(myBlocksCount), dataSetDoubleType,
- MPI_STATUS_IGNORE);
+ MPI_Offset read_offset = (MPI_Offset)(sizeof(dataSetParam)) + (MPI_Offset)(indexB) * (MPI_Offset)(doubleCountInBlock) * (MPI_Offset)(sizeof(double));
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArray[0], int(myBlocksCount), dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray start of exchange of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
std::vector<double> *rawDataReceive = new std::vector<double>[size];
for (int r = 0; r < size; r++)
rawDataReceive[r].resize(0);
- blocksExchange(MESSAGE_TAG + int(arrType), indexB, indexE, int(doubleCountInBlock), doubleValuesArray,
- rawDataReceive);
+ blocksExchange(MESSAGE_TAG + int(arrType), indexB, indexE, int(doubleCountInBlock), doubleValuesArray, rawDataReceive);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray end of exchange of data, rank = " << rank);
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
//----------------------------- restore data ---------------------------------
int blockID;
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
size_t index;
- size_t nextVectorSize =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ size_t nextVectorSize = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
index = 0;
- for (int ii = 0; ii < int(rawDataReceive[r].size() / doubleCountInBlock); ii++) {
- blockID = (int)(rawDataReceive[r][index]);
+ for (int ii = 0; ii < int(rawDataReceive[r].size() / doubleCountInBlock); ii++)
+ {
+ blockID = (int)(rawDataReceive[r][index]);
SPtr<Block3D> block = grid->getBlock(blockID);
index += 1;
@@ -1254,40 +1345,31 @@ void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::strin
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ___4DArray;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> ___3DArray;
- switch (arrType) {
+ switch (arrType)
+ {
case AverageDensity:
- ___4DArray =
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ ___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageDensity(___4DArray);
break;
case AverageVelocity:
- ___4DArray =
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ ___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageVelocity(___4DArray);
break;
case AverageFluktuations:
- ___4DArray =
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ ___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageFluctuations(___4DArray);
break;
case AverageTriple:
- ___4DArray =
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ ___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageTriplecorrelations(___4DArray);
break;
case ShearStressVal:
- ___4DArray =
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ ___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setShearStressValues(___4DArray);
break;
case RelaxationFactor:
@@ -1295,14 +1377,18 @@ void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::strin
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
block->getKernel()->getDataSet()->setRelaxationFactor(___3DArray);
break;
- case PhaseField:
+ case PhaseField1:
___3DArray = CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
block->getKernel()->getDataSet()->setPhaseField(___3DArray);
break;
+ case PhaseField2:
+ ___3DArray = CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
+ block->getKernel()->getDataSet()->setPhaseField2(___3DArray);
+ break;
default:
- UB_THROW(
- UbException(UB_EXARGS, "MPIIOMigrationBECoProcessor::readArray : array type does not exist!"));
+ UB_THROW(UbException(UB_EXARGS, "MPIIOMigrationBECoProcessor::readArray : array type does not exist!"));
break;
}
}
@@ -1310,10 +1396,10 @@ void MPIIOMigrationBECoProcessor::readArray(int step, Arrays arrType, std::strin
delete[] rawDataReceive;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
}
@@ -1323,10 +1409,10 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -1360,25 +1446,24 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
MPI_Type_contiguous(sizeOfBIM, MPI_INT, &bcindexmatrixType);
MPI_Type_commit(&bcindexmatrixType);
- MPI_Offset read_offset =
- (MPI_Offset)(sizeof(int)) + (MPI_Offset)(indexB) * (MPI_Offset)(sizeOfBIM) * (MPI_Offset)(sizeof(int));
- MPI_File_read_at(file_handler, read_offset, &bcindexmatrixVAll[0], int(myBlocksCount), bcindexmatrixType,
- MPI_STATUS_IGNORE);
+ MPI_Offset read_offset = (MPI_Offset)(sizeof(int)) + (MPI_Offset)(indexB) * (MPI_Offset)(sizeOfBIM) * (MPI_Offset)(sizeof(int));
+ MPI_File_read_at(file_handler, read_offset, &bcindexmatrixVAll[0], int(myBlocksCount), bcindexmatrixType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds start of exchange of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
std::vector<int> *rawDataReceive = new std::vector<int>[size];
std::vector<int> *rawDataSend = new std::vector<int>[size];
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
rawDataReceive[r].resize(0);
rawDataSend[r].resize(0);
rawDataReceive[r].push_back(0);
@@ -1396,14 +1481,12 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
{
rawDataReceive[tempRank][0]++;
rawDataReceive[tempRank].push_back(indexB + ind);
- rawDataReceive[tempRank].insert(rawDataReceive[tempRank].end(), bcindexmatrixVAll.begin() + ind * sizeOfBIM,
- bcindexmatrixVAll.begin() + ind * sizeOfBIM + sizeOfBIM);
+ rawDataReceive[tempRank].insert(rawDataReceive[tempRank].end(), bcindexmatrixVAll.begin() + ind * sizeOfBIM, bcindexmatrixVAll.begin() + ind * sizeOfBIM + sizeOfBIM);
} else // we must send data to other processes
{
rawDataSend[tempRank][0]++;
rawDataSend[tempRank].push_back(indexB + ind);
- rawDataSend[tempRank].insert(rawDataSend[tempRank].end(), bcindexmatrixVAll.begin() + ind * sizeOfBIM,
- bcindexmatrixVAll.begin() + ind * sizeOfBIM + sizeOfBIM);
+ rawDataSend[tempRank].insert(rawDataSend[tempRank].end(), bcindexmatrixVAll.begin() + ind * sizeOfBIM, bcindexmatrixVAll.begin() + ind * sizeOfBIM + sizeOfBIM);
}
}
@@ -1414,9 +1497,11 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
int intBlockCount;
int rds;
- for (int r = 0; r < size; r++) {
- if (r != rank) {
- rds = int(rawDataSend[r].size());
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
+ rds = int(rawDataSend[r].size());
intBlockCount = (int)(rds / SEND_BLOCK_SIZE);
if (intBlockCount * SEND_BLOCK_SIZE < rds)
intBlockCount += 1;
@@ -1424,21 +1509,21 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
for (int i = rds; i < intBlockCount * SEND_BLOCK_SIZE; i++)
rawDataSend[r].push_back(0);
- MPI_Isend(&rawDataSend[r][0], intBlockCount, sendBlockIntType, r, MESSAGE_TAG + 7, MPI_COMM_WORLD,
- &requests[requestCount]);
+ MPI_Isend(&rawDataSend[r][0], intBlockCount, sendBlockIntType, r, MESSAGE_TAG + 7, MPI_COMM_WORLD, &requests[requestCount]);
// MPI_Isend(&rawDataSend[r][0], rawDataSend[r].size(), MPI_INT, r, MESSAGE_TAG + 7, MPI_COMM_WORLD,
// &requests[requestCount]);
requestCount++;
}
}
- for (int r = 0; r < size; r++) {
- if (r != rank) {
+ for (int r = 0; r < size; r++)
+ {
+ if (r != rank)
+ {
MPI_Probe(r, MESSAGE_TAG + 7, MPI_COMM_WORLD, &status);
MPI_Get_count(&status, sendBlockIntType, &quant);
rawDataReceive[r].resize(quant * SEND_BLOCK_SIZE);
- MPI_Irecv(&rawDataReceive[r][0], quant, sendBlockIntType, r, MESSAGE_TAG + 7, MPI_COMM_WORLD,
- &requests[requestCount]);
+ MPI_Irecv(&rawDataReceive[r][0], quant, sendBlockIntType, r, MESSAGE_TAG + 7, MPI_COMM_WORLD, &requests[requestCount]);
requestCount++;
}
}
@@ -1447,17 +1532,17 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
//- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds end of exchange of data, rank = " << rank);
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpBC2.bin";
- rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -1475,10 +1560,12 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
std::vector<int> indexContainerV;
std::vector<int> bcindexmatrixV;
- for (int r = 0; r < size; r++) {
+ for (int r = 0; r < size; r++)
+ {
index = 1;
- for (int ii = 0; ii < rawDataReceive[r][0]; ii++) {
+ for (int ii = 0; ii < rawDataReceive[r][0]; ii++)
+ {
blockID = (int)(rawDataReceive[r][index]);
index += 1;
@@ -1498,18 +1585,19 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
bcAddArray.boundCond_count, boundCondType, MPI_STATUS_IGNORE);
if (bcAddArray.indexContainer_count > 0)
- MPI_File_read_at(file_handler,
- read_offset2 + (MPI_Offset)(sizeof(BCAddMigration)) +
+ MPI_File_read_at(file_handler, read_offset2 + (MPI_Offset)(sizeof(BCAddMigration)) +
(MPI_Offset)(bcAddArray.boundCond_count) * (MPI_Offset)(sizeof(BoundaryCondition)),
&indexContainerV[0], bcAddArray.indexContainer_count, MPI_INT, MPI_STATUS_IGNORE);
bcVector.resize(0);
- for (int ibc = 0; ibc < bcAddArray.boundCond_count; ibc++) {
+ for (int ibc = 0; ibc < bcAddArray.boundCond_count; ibc++)
+ {
SPtr<BoundaryConditions> bc;
if (memcmp(&bcArray[ibc], nullBouCond, sizeof(BoundaryCondition)) == 0)
bc = SPtr<BoundaryConditions>();
- else {
+ else
+ {
bc = SPtr<BoundaryConditions>(new BoundaryConditions);
bc->noslipBoundaryFlags = bcArray[ibc].noslipBoundaryFlags;
bc->slipBoundaryFlags = bcArray[ibc].slipBoundaryFlags;
@@ -1537,8 +1625,7 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
bcVector.push_back(bc);
}
- CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2,
- boundCondParamStr.nx3);
+ CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2, boundCondParamStr.nx3);
SPtr<Block3D> block1 = grid->getBlock(blockID);
SPtr<BCProcessor> bcProc = bcProcessor->clone(block1->getKernel());
@@ -1562,12 +1649,12 @@ void MPIIOMigrationBECoProcessor::readBoundaryConds(int step)
delete[] rawDataSend;
delete[] requests;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds end of restore of data, rank = " << rank);
UBLOG(logINFO, "MPIIOMigrationBECoProcessor::readBoundaryConds time: " << finish - start << " s");
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
}
@@ -1577,3 +1664,8 @@ void MPIIOMigrationBECoProcessor::setLBMKernel(SPtr<LBMKernel> kernel) { this->l
void MPIIOMigrationBECoProcessor::setBCProcessor(SPtr<BCProcessor> bcProcessor) { this->bcProcessor = bcProcessor; }
//////////////////////////////////////////////////////////////////////////
void MPIIOMigrationBECoProcessor::setNu(double nu) { this->nue = nu; }
+
+void MPIIOMigrationBECoProcessor::setNuLG(double cfL, double cfG) { this->nuL = cfL; this->nuG = cfG; }
+
+void MPIIOMigrationBECoProcessor::setDensityRatio(double dr) { this->densityRatio = dr; }
+
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.h b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.h
index 4d825fde3956dcbe711f49b18b57cd929ba986d9..9a89ada1ae039d10cd53b06b189e5709398911c8 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.h
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationBECoProcessor.h
@@ -25,7 +25,8 @@ class MPIIOMigrationBECoProcessor : public MPIIOCoProcessor
AverageTriple = 4,
ShearStressVal = 5,
RelaxationFactor = 6,
- PhaseField = 7
+ PhaseField1 = 7,
+ PhaseField2 = 8
};
public:
@@ -71,6 +72,8 @@ public:
//! The function truncates the data files
void clearAllFiles(int step);
void setNu(double nu);
+ void setNuLG(double cfL, double cfG);
+ void setDensityRatio(double dr);
void blocksExchange(int tagN, int ind1, int ind2, int doubleCountInBlock, std::vector<double> &pV,
std::vector<double> *rawDataReceive);
@@ -91,6 +94,10 @@ private:
SPtr<LBMKernel> lbmKernel;
SPtr<BCProcessor> bcProcessor;
double nue;
+ double nuL;
+ double nuG;
+ double densityRatio;
+
};
#endif
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.cpp
index 69cc8795bb7fdb4791420473a242a0f1ff96a06d..fae3b48463a45499ea7c8d5b78d4bcfd01d1bb81 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.cpp
@@ -22,8 +22,7 @@
using namespace MPIIODataStructures;
-MPIIOMigrationCoProcessor::MPIIOMigrationCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path,
- SPtr<Communicator> comm)
+MPIIOMigrationCoProcessor::MPIIOMigrationCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path, SPtr<Communicator> comm)
: MPIIOCoProcessor(grid, s, path, comm)
{
memset(&boundCondParamStr, 0, sizeof(boundCondParamStr));
@@ -31,7 +30,7 @@ MPIIOMigrationCoProcessor::MPIIOMigrationCoProcessor(SPtr<Grid3D> grid, SPtr<UbS
//------------------------- define MPI types ---------------------------------
MPI_Datatype typesDataSet[3] = { MPI_DOUBLE, MPI_INT, MPI_CHAR };
- int blocksDataSet[3] = { 2, 2, 2 };
+ int blocksDataSet[3] = { 5, 2, 2 };
MPI_Aint offsetsDatatSet[3], lbDataSet, extentDataSet;
offsetsDatatSet[0] = 0;
@@ -71,7 +70,8 @@ MPIIOMigrationCoProcessor::~MPIIOMigrationCoProcessor()
//////////////////////////////////////////////////////////////////////////
void MPIIOMigrationCoProcessor::process(double step)
{
- if (scheduler->isDue(step)) {
+ if (scheduler->isDue(step))
+ {
if (comm->isRoot())
UBLOG(logINFO, "MPIIOMigrationCoProcessor save step: " << step);
if (comm->isRoot())
@@ -100,8 +100,7 @@ void MPIIOMigrationCoProcessor::clearAllFiles(int step)
UbSystem::makeDirectory(path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step));
std::string filename10 = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpBC.bin";
- int rc10 =
- MPI_File_open(MPI_COMM_WORLD, filename10.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ int rc10 = MPI_File_open(MPI_COMM_WORLD, filename10.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc10 != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename10);
MPI_File_set_size(file_handler, new_size);
@@ -125,69 +124,93 @@ void MPIIOMigrationCoProcessor::writeDataSet(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
dataSetParam dataSetParamStr1, dataSetParamStr2, dataSetParamStr3;
DataSetMigration *dataSetArray = new DataSetMigration[blocksCount];
- std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
+ std::vector<double> doubleValuesArrayF; // double-values (arrays of f's) in all blocks Fdistribution
+ std::vector<double> doubleValuesArrayH1; // double-values (arrays of f's) in all blocks H1distribution
+ // std::vector<double> doubleValuesArrayH2; // double-values (arrays of f's) in all blocks H2distribution
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeDataSet start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+ bool multiPhase = false;
DSArraysPresence arrPresence;
bool firstBlock = true;
size_t doubleCountInBlock = 0;
int ic = 0;
- SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF, D3Q27EsoTwist3DSplittedVectorPtrH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF, localDistributionsH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF, nonLocalDistributionsH;
- CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF, zeroDistributionsH;
+ SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF = 0, D3Q27EsoTwist3DSplittedVectorPtrH1 = 0, D3Q27EsoTwist3DSplittedVectorPtrH2 = 0;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF = 0, localDistributionsH1 = 0, localDistributionsH2 = 0;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF = 0, nonLocalDistributionsH1 = 0, nonLocalDistributionsH2 = 0;
+ CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF = 0, zeroDistributionsH1 = 0, zeroDistributionsH2 = 0;
+
+ SPtr<LBMKernel> kernel;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetArray[ic].globalID =
- block->getGlobalID(); // id of the block needed to find it while regenerating the grid
- dataSetArray[ic].ghostLayerWidth = block->getKernel()->getGhostLayerWidth();
- dataSetArray[ic].collFactor = block->getKernel()->getCollisionFactor();
- dataSetArray[ic].deltaT = block->getKernel()->getDeltaT();
- dataSetArray[ic].compressible = block->getKernel()->getCompressible();
- dataSetArray[ic].withForcing = block->getKernel()->getWithForcing();
-
- D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getFdistributions());
+ kernel = dynamicPointerCast<LBMKernel>(block->getKernel());
+
+ dataSetArray[ic].globalID = block->getGlobalID(); // id of the block needed to find it while regenerating the grid
+ dataSetArray[ic].ghostLayerWidth = kernel->getGhostLayerWidth();
+ dataSetArray[ic].collFactor = kernel->getCollisionFactor();
+ dataSetArray[ic].deltaT = kernel->getDeltaT();
+ dataSetArray[ic].compressible = kernel->getCompressible();
+ dataSetArray[ic].withForcing = kernel->getWithForcing();
+ dataSetArray[ic].collFactorL = kernel->getCollisionFactorL();
+ dataSetArray[ic].collFactorG = kernel->getCollisionFactorG();
+ dataSetArray[ic].densityRatio = kernel->getDensityRatio();
+
+ D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getFdistributions());
localDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getLocalDistributions();
nonLocalDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getNonLocalDistributions();
zeroDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getZeroDistributions();
- D3Q27EsoTwist3DSplittedVectorPtrH = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getHdistributions());
- localDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getLocalDistributions();
- nonLocalDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getNonLocalDistributions();
- zeroDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getZeroDistributions();
+ D3Q27EsoTwist3DSplittedVectorPtrH1 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getHdistributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH1 != 0)
+ {
+ multiPhase = true;
+ localDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getLocalDistributions();
+ nonLocalDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getNonLocalDistributions();
+ zeroDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getZeroDistributions();
+ }
+
+ /*D3Q27EsoTwist3DSplittedVectorPtrH2 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getH2distributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ localDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getLocalDistributions();
+ nonLocalDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getNonLocalDistributions();
+ zeroDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getZeroDistributions();
+ }*/
if (firstBlock) // && block->getKernel()) // when first (any) valid block...
{
- if (localDistributionsF) {
+ if (localDistributionsF)
+ {
dataSetParamStr1.nx[0] = static_cast<int>(localDistributionsF->getNX1());
dataSetParamStr1.nx[1] = static_cast<int>(localDistributionsF->getNX2());
dataSetParamStr1.nx[2] = static_cast<int>(localDistributionsF->getNX3());
dataSetParamStr1.nx[3] = static_cast<int>(localDistributionsF->getNX4());
}
- if (nonLocalDistributionsF) {
+ if (nonLocalDistributionsF)
+ {
dataSetParamStr2.nx[0] = static_cast<int>(nonLocalDistributionsF->getNX1());
dataSetParamStr2.nx[1] = static_cast<int>(nonLocalDistributionsF->getNX2());
dataSetParamStr2.nx[2] = static_cast<int>(nonLocalDistributionsF->getNX3());
dataSetParamStr2.nx[3] = static_cast<int>(nonLocalDistributionsF->getNX4());
}
- if (zeroDistributionsF) {
+ if (zeroDistributionsF)
+ {
dataSetParamStr3.nx[0] = static_cast<int>(zeroDistributionsF->getNX1());
dataSetParamStr3.nx[1] = static_cast<int>(zeroDistributionsF->getNX2());
dataSetParamStr3.nx[2] = static_cast<int>(zeroDistributionsF->getNX3());
@@ -195,94 +218,91 @@ void MPIIOMigrationCoProcessor::writeDataSet(int step)
}
// ... than save some parameters that are equal in all blocks
- dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
- dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
- dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
-
- // Fdistributions + Hdistributions
- doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
- dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3]) * 2;
-
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray =
- block->getKernel()->getDataSet()->getAverageDensity();
+ dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
+ dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
+ dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
+
+ doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray = block->getKernel()->getDataSet()->getAverageDensity();
if (averageDensityArray)
arrPresence.isAverageDensityArrayPresent = true;
else
arrPresence.isAverageDensityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr =
- block->getKernel()->getDataSet()->getAverageVelocity();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr = block->getKernel()->getDataSet()->getAverageVelocity();
if (AverageVelocityArray3DPtr)
arrPresence.isAverageVelocityArrayPresent = true;
else
arrPresence.isAverageVelocityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr =
- block->getKernel()->getDataSet()->getAverageFluctuations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr = block->getKernel()->getDataSet()->getAverageFluctuations();
if (AverageFluctArray3DPtr)
arrPresence.isAverageFluktuationsArrayPresent = true;
else
arrPresence.isAverageFluktuationsArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr =
- block->getKernel()->getDataSet()->getAverageTriplecorrelations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr = block->getKernel()->getDataSet()->getAverageTriplecorrelations();
if (AverageTripleArray3DPtr)
arrPresence.isAverageTripleArrayPresent = true;
else
arrPresence.isAverageTripleArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr =
- block->getKernel()->getDataSet()->getShearStressValues();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr = block->getKernel()->getDataSet()->getShearStressValues();
if (ShearStressValArray3DPtr)
arrPresence.isShearStressValArrayPresent = true;
else
arrPresence.isShearStressValArrayPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr =
- block->getKernel()->getDataSet()->getRelaxationFactor();
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr = block->getKernel()->getDataSet()->getRelaxationFactor();
if (relaxationFactor3DPtr)
arrPresence.isRelaxationFactorPresent = true;
else
arrPresence.isRelaxationFactorPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr =
- block->getKernel()->getDataSet()->getPhaseField();
- if (phaseField3DPtr)
- arrPresence.isPhaseFieldPresent = true;
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr1 = block->getKernel()->getDataSet()->getPhaseField();
+ if (phaseField3DPtr1)
+ arrPresence.isPhaseField1Present = true;
+ else
+ arrPresence.isPhaseField1Present = false;
+
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr2 = block->getKernel()->getDataSet()->getPhaseField2();
+ if (phaseField3DPtr2)
+ arrPresence.isPhaseField2Present = true;
else
- arrPresence.isPhaseFieldPresent = false;
+ arrPresence.isPhaseField2Present = false;
firstBlock = false;
}
- if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsF->getDataVector().begin(),
- localDistributionsF->getDataVector().end());
- if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsF->getDataVector().begin(),
- nonLocalDistributionsF->getDataVector().end());
+ if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), localDistributionsF->getDataVector().begin(), localDistributionsF->getDataVector().end());
+ if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), nonLocalDistributionsF->getDataVector().begin(), nonLocalDistributionsF->getDataVector().end());
if (zeroDistributionsF && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsF->getDataVector().begin(),
- zeroDistributionsF->getDataVector().end());
-
- if (localDistributionsH && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsH->getDataVector().begin(),
- localDistributionsH->getDataVector().end());
- if (nonLocalDistributionsH && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsH->getDataVector().begin(),
- nonLocalDistributionsH->getDataVector().end());
- if (zeroDistributionsH && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsH->getDataVector().begin(),
- zeroDistributionsH->getDataVector().end());
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), zeroDistributionsF->getDataVector().begin(), zeroDistributionsF->getDataVector().end());
+
+ if (multiPhase)
+ {
+ if (localDistributionsH1 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), localDistributionsH1->getDataVector().begin(), localDistributionsH1->getDataVector().end());
+ if (nonLocalDistributionsH1 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), nonLocalDistributionsH1->getDataVector().begin(), nonLocalDistributionsH1->getDataVector().end());
+ if (zeroDistributionsH1 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), zeroDistributionsH1->getDataVector().begin(), zeroDistributionsH1->getDataVector().end());
+ }
+
+ /*if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ if (localDistributionsH2 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), localDistributionsH2->getDataVector().begin(), localDistributionsH2->getDataVector().end());
+ if (nonLocalDistributionsH2 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), nonLocalDistributionsH2->getDataVector().begin(), nonLocalDistributionsH2->getDataVector().end());
+ if (zeroDistributionsH2 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), zeroDistributionsH2->getDataVector().begin(), zeroDistributionsH2->getDataVector().end());
+ }*/
ic++;
}
@@ -292,10 +312,10 @@ void MPIIOMigrationCoProcessor::writeDataSet(int step)
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -311,32 +331,73 @@ void MPIIOMigrationCoProcessor::writeDataSet(int step)
// write to the file
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
MPI_File_write_at(file_handler, (MPI_Offset)0, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
-
+ MPI_File_write_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
+
MPI_Offset write_offset;
size_t sizeofOneDataSet = sizeof(DataSetMigration) + doubleCountInBlock * sizeof(double);
- for (int nb = 0; nb < blocksCount; nb++) {
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
write_offset = (MPI_Offset)(3 * sizeof(dataSetParam) + dataSetArray[nb].globalID * sizeofOneDataSet);
MPI_File_write_at(file_handler, write_offset, &dataSetArray[nb], 1, dataSetType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(DataSetMigration)),
- &doubleValuesArray[nb * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(DataSetMigration)), &doubleValuesArrayF[nb * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
}
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
+
+ //-------------------------------- H1 ----------------------------------------------------
+ if (multiPhase)
+ {
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ sizeofOneDataSet = doubleCountInBlock * sizeof(double);
+
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
+ write_offset = (MPI_Offset)(dataSetArray[nb].globalID * sizeofOneDataSet);
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH1[nb * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ }
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);
+ }
+
+ //-------------------------------- H2 ----------------------------------------------------
+ /*if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ sizeofOneDataSet = doubleCountInBlock * sizeof(double);
+
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
+ write_offset = (MPI_Offset)(dataSetArray[nb].globalID * sizeofOneDataSet);
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH2[nb * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ }
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);
+ }*/
+ //--------------------------------
+
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeDataSet time: " << finish - start << " s");
}
@@ -375,8 +436,11 @@ void MPIIOMigrationCoProcessor::writeDataSet(int step)
if (arrPresence.isRelaxationFactorPresent)
write3DArray(step, RelaxationFactor, std::string("/cpRelaxationFactor.bin"));
- if (arrPresence.isPhaseFieldPresent)
- write3DArray(step, PhaseField, std::string("/cpPhaseField.bin"));
+ if (arrPresence.isPhaseField1Present)
+ write3DArray(step, PhaseField1, std::string("/cpPhaseField1.bin"));
+
+ if (arrPresence.isPhaseField2Present)
+ write3DArray(step, PhaseField2, std::string("/cpPhaseField2.bin"));
}
@@ -391,7 +455,8 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -400,10 +465,10 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
std::vector<double> doubleValuesArray; // double-values of the AverageDensityArray in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeAverageDensityArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -411,13 +476,14 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ___Array;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].globalID =
- block->getGlobalID(); // id of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].globalID = block->getGlobalID(); // id of the block needed to find it while regenerating the grid
- switch (arrayType) {
+ switch (arrayType)
+ {
case AverageDensity:
___Array = block->getKernel()->getDataSet()->getAverageDensity();
break;
@@ -434,28 +500,24 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
___Array = block->getKernel()->getDataSet()->getShearStressValues();
break;
default:
- UB_THROW(UbException(UB_EXARGS,
- "MPIIOMigrationCoProcessor::write4DArray : 4D array type does not exist!"));
+ UB_THROW(UbException(UB_EXARGS, "MPIIOMigrationCoProcessor::write4DArray : 4D array type does not exist!"));
break;
}
if (firstBlock) // when first (any) valid block...
{
dataSetParamStr.nx1 = dataSetParamStr.nx2 = dataSetParamStr.nx3 = 0;
- dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
- dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
- dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
- dataSetParamStr.nx[3] = static_cast<int>(___Array->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
+ dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
+ dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
+ dataSetParamStr.nx[3] = static_cast<int>(___Array->getNX4());
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if (___Array && (dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(),
- ___Array->getDataVector().end());
+ if (___Array && (dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
+ doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(), ___Array->getDataVector().end());
ic++;
}
@@ -465,10 +527,10 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::write4DArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -489,7 +551,8 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
MPI_Offset write_offset;
size_t sizeofOneDataSet = sizeof(DataSetSmallMigration) + doubleCountInBlock * sizeof(double);
- for (int nb = 0; nb < blocksCount; nb++) {
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
write_offset = (MPI_Offset)(sizeof(dataSetParam) + dataSetSmallArray[nb].globalID * sizeofOneDataSet);
MPI_File_write_at(file_handler, write_offset, &dataSetSmallArray[nb], 1, dataSetSmallType, MPI_STATUS_IGNORE);
MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(DataSetSmallMigration)),
@@ -500,7 +563,8 @@ void MPIIOMigrationCoProcessor::write4DArray(int step, Arrays arrayType, std::st
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::write4DArray time: " << finish - start << " s");
}
@@ -519,7 +583,8 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -528,10 +593,10 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::write3DArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -539,41 +604,42 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
int ic = 0;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> ___Array;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].globalID =
- block->getGlobalID(); // id of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].globalID = block->getGlobalID(); // id of the block needed to find it while regenerating the grid
- switch (arrayType) {
+ switch (arrayType)
+ {
case RelaxationFactor:
___Array = block->getKernel()->getDataSet()->getRelaxationFactor();
break;
- case PhaseField:
+ case PhaseField1:
___Array = block->getKernel()->getDataSet()->getPhaseField();
break;
+ case PhaseField2:
+ ___Array = block->getKernel()->getDataSet()->getPhaseField2();
+ break;
default:
- UB_THROW(UbException(UB_EXARGS,
- "MPIIOMigrationCoProcessor::write3DArray : 3D array type does not exist!"));
+ UB_THROW(UbException(UB_EXARGS, "MPIIOMigrationCoProcessor::write3DArray : 3D array type does not exist!"));
break;
}
if (firstBlock) // when first (any) valid block...
{
dataSetParamStr.nx1 = dataSetParamStr.nx2 = dataSetParamStr.nx3 = 0;
- dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
- dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
- dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
- dataSetParamStr.nx[3] = 1;
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ dataSetParamStr.nx[0] = static_cast<int>(___Array->getNX1());
+ dataSetParamStr.nx[1] = static_cast<int>(___Array->getNX2());
+ dataSetParamStr.nx[2] = static_cast<int>(___Array->getNX3());
+ dataSetParamStr.nx[3] = 1;
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
if (___Array && (dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(),
- ___Array->getDataVector().end());
+ doubleValuesArray.insert(doubleValuesArray.end(), ___Array->getDataVector().begin(), ___Array->getDataVector().end());
ic++;
}
@@ -583,10 +649,10 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::write3DArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -613,7 +679,8 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
size_t sizeofOneDataSet = sizeof(DataSetSmallMigration) + doubleCountInBlock * sizeof(double);
MPI_Offset write_offset;
- for (int nb = 0; nb < blocksCount; nb++) {
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
write_offset = (MPI_Offset)(sizeof(dataSetParam) + dataSetSmallArray[nb].globalID * sizeofOneDataSet);
MPI_File_write_at(file_handler, write_offset, &dataSetSmallArray[nb], 1, dataSetSmallType, MPI_STATUS_IGNORE);
MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(DataSetSmallMigration)),
@@ -624,7 +691,8 @@ void MPIIOMigrationCoProcessor::write3DArray(int step, Arrays arrayType, std::st
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::write3DArray time: " << finish - start << " s");
}
@@ -1352,10 +1420,10 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeBoundaryConds start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
int blocksCount = 0; // quantity of blocks, that belong to this process
@@ -1366,7 +1434,8 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1381,25 +1450,27 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
int ic = 0;
SPtr<BCArray3D> bcArr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // all the blocks of the current level
{
bcArr = block->getKernel()->getBCProcessor()->getBCArray();
- bcAddArray[ic].globalID =
- block->getGlobalID(); // id of the block needed to find it while regenerating the grid
+ bcAddArray[ic].globalID = block->getGlobalID(); // id of the block needed to find it while regenerating the grid
bcAddArray[ic].boundCond_count = 0; // how many BoundaryConditions in this block
bcAddArray[ic].indexContainer_count = 0; // how many indexContainer-values in this block
- bytesCount[ic] = sizeof(BCAddMigration);
+ bytesCount[ic] = sizeof(BCAddMigration);
bcVector[ic].resize(0);
bcindexmatrixVector[ic].resize(0);
indexContainerVector[ic].resize(0);
- for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++) {
+ for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++)
+ {
BoundaryCondition *bouCond = new BoundaryCondition();
- if (bcArr->bcvector[bc] == NULL) {
+ if (bcArr->bcvector[bc] == NULL)
memset(bouCond, 0, sizeof(BoundaryCondition));
- } else {
+ else
+ {
bouCond->noslipBoundaryFlags = bcArr->bcvector[bc]->getNoSlipBoundary();
bouCond->slipBoundaryFlags = bcArr->bcvector[bc]->getSlipBoundary();
bouCond->velocityBoundaryFlags = bcArr->bcvector[bc]->getVelocityBoundary();
@@ -1428,20 +1499,18 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
bytesCount[ic] += sizeof(BoundaryCondition);
}
- if (bcindexmatrixCountNotInit) {
+ if (bcindexmatrixCountNotInit)
+ {
boundCondParamStr.nx1 = static_cast<int>(bcArr->bcindexmatrix.getNX1());
boundCondParamStr.nx2 = static_cast<int>(bcArr->bcindexmatrix.getNX2());
boundCondParamStr.nx3 = static_cast<int>(bcArr->bcindexmatrix.getNX3());
boundCondParamStr.bcindexmatrixCount = static_cast<int>(bcArr->bcindexmatrix.getDataVector().size());
bcindexmatrixCountNotInit = false;
}
- bcindexmatrixVector[ic].insert(bcindexmatrixVector[ic].begin(),
- bcArr->bcindexmatrix.getDataVector().begin(),
- bcArr->bcindexmatrix.getDataVector().end());
+ bcindexmatrixVector[ic].insert(bcindexmatrixVector[ic].begin(), bcArr->bcindexmatrix.getDataVector().begin(), bcArr->bcindexmatrix.getDataVector().end());
bytesCount[ic] += boundCondParamStr.bcindexmatrixCount * sizeof(int);
- indexContainerVector[ic].insert(indexContainerVector[ic].begin(), bcArr->indexContainer.begin(),
- bcArr->indexContainer.end());
+ indexContainerVector[ic].insert(indexContainerVector[ic].begin(), bcArr->indexContainer.begin(), bcArr->indexContainer.end());
bcAddArray[ic].indexContainer_count = static_cast<int>(bcArr->indexContainer.size());
count_indexContainer += bcAddArray[ic].indexContainer_count;
bytesCount[ic] += bcAddArray[ic].indexContainer_count * sizeof(int);
@@ -1455,10 +1524,10 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
MPI_Type_contiguous(boundCondParamStr.bcindexmatrixCount, MPI_INT, &bcindexmatrixType);
MPI_Type_commit(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: "<< Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -1479,11 +1548,15 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
MPI_Offset write_offset = (MPI_Offset)(sizeof(boundCondParam) + grid->getNumberOfBlocks() * sizeof(size_t));
size_t next_file_offset = 0;
- if (size > 1) {
- if (rank == 0) {
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
next_file_offset = write_offset + allBytesCount;
MPI_Send(&next_file_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
next_file_offset = write_offset + allBytesCount;
if (rank < size - 1)
@@ -1495,7 +1568,8 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
MPI_Offset write_offsetIndex;
- for (int nb = 0; nb < blocksCount; nb++) {
+ for (int nb = 0; nb < blocksCount; nb++)
+ {
write_offsetIndex = (MPI_Offset)(sizeof(boundCondParam) + bcAddArray[nb].globalID * sizeof(size_t));
MPI_File_write_at(file_handler, write_offsetIndex, &write_offset, 1, MPI_LONG_LONG_INT, MPI_STATUS_IGNORE);
@@ -1505,17 +1579,12 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
bcAddArray[nb].boundCond_count, boundCondType, MPI_STATUS_IGNORE);
if (bcindexmatrixVector[nb].size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(BCAddMigration) +
- bcAddArray[nb].boundCond_count * sizeof(BoundaryCondition)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(BCAddMigration) + bcAddArray[nb].boundCond_count * sizeof(BoundaryCondition)),
&bcindexmatrixVector[nb][0], 1, bcindexmatrixType, MPI_STATUS_IGNORE);
if (indexContainerVector[nb].size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(BCAddMigration) +
- bcAddArray[nb].boundCond_count * sizeof(BoundaryCondition) +
- boundCondParamStr.bcindexmatrixCount * sizeof(int)),
- &indexContainerVector[nb][0], bcAddArray[nb].indexContainer_count, MPI_INT,
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(BCAddMigration) + bcAddArray[nb].boundCond_count * sizeof(BoundaryCondition) +
+ boundCondParamStr.bcindexmatrixCount * sizeof(int)), &indexContainerVector[nb][0], bcAddArray[nb].indexContainer_count, MPI_INT,
MPI_STATUS_IGNORE);
write_offset += bytesCount[nb];
@@ -1525,7 +1594,8 @@ void MPIIOMigrationCoProcessor::writeBoundaryConds(int step)
MPI_File_close(&file_handler);
MPI_Type_free(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::writeBoundaryConds time: " << finish - start << " s");
}
@@ -1547,8 +1617,7 @@ void MPIIOMigrationCoProcessor::restart(int step)
readBlocks(step);
- SPtr<Grid3DVisitor> metisVisitor(new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased,
- D3Q27System::BSW, MetisPartitioner::KWAY));
+ SPtr<Grid3DVisitor> metisVisitor(new MetisPartitioningGridVisitor(comm, MetisPartitioningGridVisitor::LevelBased, D3Q27System::BSW, MetisPartitioner::KWAY));
grid->accept(metisVisitor);
readDataSet(step);
@@ -1568,15 +1637,16 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
start = MPI_Wtime();
+ bool multiPhase = false;
size_t blocksCount = 0; // quantity of the blocks, that belong to this process
dataSetParam dataSetParamStr1, dataSetParamStr2, dataSetParamStr3;
@@ -1584,7 +1654,8 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1592,22 +1663,21 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
DataSetMigration *dataSetArray = new DataSetMigration[blocksCount];
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
MPI_File_read_at(file_handler, (MPI_Offset)0, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
- size_t doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ size_t doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3] * 2);
- std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+ std::vector<double> doubleValuesArrayF(size_t(blocksCount * doubleCountInBlock)); // double-values in all blocks Fdistributions
+ std::vector<double> doubleValuesArrayH1; // double-values in all blocks H1distributions
+ //std::vector<double> doubleValuesArrayH2; // double-values in all blocks H2distributions
// define MPI_types depending on the block-specific information
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
@@ -1617,95 +1687,145 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
MPI_Offset read_offset;
size_t sizeofOneDataSet = size_t(sizeof(DataSetMigration) + doubleCountInBlock * sizeof(double));
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
read_offset = (MPI_Offset)(3 * sizeof(dataSetParam) + block->getGlobalID() * sizeofOneDataSet);
MPI_File_read_at(file_handler, read_offset, &dataSetArray[ic], 1, dataSetType, MPI_STATUS_IGNORE);
MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(DataSetMigration)),
- &doubleValuesArray[ic * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ &doubleValuesArrayF[ic * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
ic++;
}
}
MPI_File_close(&file_handler);
+
+ //----------------------------------------- H1 ----------------------------------------------------
+ MPI_Offset fsize;
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+ MPI_File_get_size(file_handler, &fsize);
+ if (fsize > 0)
+ {
+ multiPhase = true;
+ doubleValuesArrayH1.resize(blocksCount * doubleCountInBlock);
+
+ sizeofOneDataSet = size_t(doubleCountInBlock * sizeof(double));
+
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
+ for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
+ {
+ read_offset = (MPI_Offset)(block->getGlobalID() * sizeofOneDataSet);
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayH1[ic * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ ic++;
+ }
+ }
+
+ }
+ MPI_File_close(&file_handler);
+
+ //----------------------------------------- H2 ----------------------------------------------------
+ /*filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ sizeofOneDataSet = size_t(doubleCountInBlock * sizeof(double));
+ doubleValuesArrayH2.resize(blocksCount * doubleCountInBlock);
+
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
+ for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
+ {
+ read_offset = (MPI_Offset)(block->getGlobalID() * sizeofOneDataSet);
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayH2[ic * doubleCountInBlock], 1, dataSetDoubleType, MPI_STATUS_IGNORE);
+ ic++;
+ }
+ }
+
+ MPI_File_close(&file_handler);*/
+
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readDataSet time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readDataSet start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
- std::vector<double> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
- std::vector<double> vectorsOfValuesH1, vectorsOfValuesH2, vectorsOfValuesH3;
-
- size_t vectorSize1 =
- dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
- size_t vectorSize2 =
- dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
- size_t vectorSize3 =
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
-
- for (std::size_t n = 0; n < blocksCount; n++) {
- vectorsOfValuesF1.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize1);
+ std::vector<LBMReal> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
+ std::vector<LBMReal> vectorsOfValuesH11, vectorsOfValuesH12, vectorsOfValuesH13;
+ //std::vector<LBMReal> vectorsOfValuesH21, vectorsOfValuesH22, vectorsOfValuesH23;
+
+ size_t vectorSize1 = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
+ size_t vectorSize2 = dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
+ size_t vectorSize3 = dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+
+ for (std::size_t n = 0; n < blocksCount; n++)
+ {
+ vectorsOfValuesF1.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize1);
+ if(multiPhase)
+ vectorsOfValuesH11.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize1);
+ //vectorsOfValuesH21.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize1);
index += vectorSize1;
- vectorsOfValuesF2.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize2);
+ vectorsOfValuesF2.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize2);
+ if (multiPhase)
+ vectorsOfValuesH12.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize2);
+ //vectorsOfValuesH22.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize2);
index += vectorSize2;
- vectorsOfValuesF3.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize3);
- index += vectorSize3;
-
- vectorsOfValuesH1.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize1);
- index += vectorSize1;
-
- vectorsOfValuesH2.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize2);
- index += vectorSize2;
-
- vectorsOfValuesH3.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize3);
+ vectorsOfValuesF3.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize3);
+ if (multiPhase)
+ vectorsOfValuesH13.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize3);
+ //vectorsOfValuesH23.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize3);
index += vectorSize3;
SPtr<DistributionArray3D> mFdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
vectorsOfValuesF3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX1(dataSetParamStr1.nx1);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX2(dataSetParamStr1.nx2);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX3(dataSetParamStr1.nx3);
- SPtr<DistributionArray3D> mHdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
- vectorsOfValuesH3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
-
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX1(dataSetParamStr1.nx1);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX2(dataSetParamStr1.nx2);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX3(dataSetParamStr1.nx3);
+ SPtr<DistributionArray3D> mH1distributions(new D3Q27EsoTwist3DSplittedVector());
+ if (multiPhase)
+ {
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH11, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH12, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH13, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX3(dataSetParamStr1.nx3);
+ }
+
+ /*SPtr<DistributionArray3D> mH2distributions(new D3Q27EsoTwist3DSplittedVector());
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH21, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH22, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH23, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX3(dataSetParamStr1.nx3);*/
// find the nesessary block and fill it
SPtr<Block3D> block = grid->getBlock(dataSetArray[n].globalID);
@@ -1716,17 +1836,22 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
kernel->setDeltaT(dataSetArray[n].deltaT);
kernel->setCompressible(dataSetArray[n].compressible);
kernel->setWithForcing(dataSetArray[n].withForcing);
+ kernel->setCollisionFactorMultiphase(dataSetArray[n].collFactorL, dataSetArray[n].collFactorG);
+ kernel->setDensityRatio(dataSetArray[n].densityRatio);
+
SPtr<DataSet3D> dataSetPtr = SPtr<DataSet3D>(new DataSet3D());
dataSetPtr->setFdistributions(mFdistributions);
- dataSetPtr->setHdistributions(mHdistributions);
+ if (multiPhase)
+ dataSetPtr->setHdistributions(mH1distributions);
+ //dataSetPtr->setH2distributions(mH2distributions);
kernel->setDataSet(dataSetPtr);
block->setKernel(kernel);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readDataSet end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetArray;
@@ -1766,8 +1891,12 @@ void MPIIOMigrationCoProcessor::readDataSet(int step)
readArray(step, RelaxationFactor, std::string("/cpRelaxationFactor.bin"));
// readRelaxationFactor(step);
- if (arrPresence.isPhaseFieldPresent)
- readArray(step, PhaseField, std::string("/cpPhaseField.bin"));
+ if (arrPresence.isPhaseField1Present)
+ readArray(step, PhaseField1, std::string("/cpPhaseField1.bin"));
+
+ if (arrPresence.isPhaseField2Present)
+ readArray(step, PhaseField2, std::string("/cpPhaseField2.bin"));
+
}
void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string fname)
@@ -1776,10 +1905,10 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -1799,7 +1928,8 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1807,8 +1937,7 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
MPI_File_read_at(file_handler, (MPI_Offset)0, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallMigration *dataSetSmallArray = new DataSetSmallMigration[blocksCount];
- size_t doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ size_t doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -1819,7 +1948,8 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
MPI_Offset read_offset;
size_t sizeofOneDataSet = size_t(sizeof(DataSetSmallMigration) + doubleCountInBlock * sizeof(double));
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
read_offset = (MPI_Offset)(sizeof(dataSetParam) + block->getGlobalID() * sizeofOneDataSet);
@@ -1833,19 +1963,19 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readArray readArray: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
//----------------------------- restore data ---------------------------------
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (std::size_t n = 0; n < blocksCount; n++) {
SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].globalID);
@@ -1856,35 +1986,31 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ___4DArray;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> ___3DArray;
- switch (arrType) {
+ switch (arrType)
+ {
case AverageDensity:
___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageDensity(___4DArray);
break;
case AverageVelocity:
___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageVelocity(___4DArray);
break;
case AverageFluktuations:
___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageFluctuations(___4DArray);
break;
case AverageTriple:
___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setAverageTriplecorrelations(___4DArray);
break;
case ShearStressVal:
___4DArray = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(
- vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2],
- dataSetParamStr.nx[3]));
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
block->getKernel()->getDataSet()->setShearStressValues(___4DArray);
break;
case RelaxationFactor:
@@ -1892,21 +2018,26 @@ void MPIIOMigrationCoProcessor::readArray(int step, Arrays arrType, std::string
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
block->getKernel()->getDataSet()->setRelaxationFactor(___3DArray);
break;
- case PhaseField:
+ case PhaseField1:
___3DArray = CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
block->getKernel()->getDataSet()->setPhaseField(___3DArray);
break;
+ case PhaseField2:
+ ___3DArray = CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
+ block->getKernel()->getDataSet()->setPhaseField2(___3DArray);
+ break;
default:
UB_THROW(UbException(UB_EXARGS, "MPIIOMigrationCoProcessor::readArray : array type does not exist!"));
break;
}
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -2548,10 +2679,10 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -2570,7 +2701,8 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -2585,12 +2717,12 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
std::vector<int> bcindexmatrixV;
std::vector<int> indexContainerV;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readBoundaryConds time: " << finish - start << " s");
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readBoundaryConds start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
MPI_File_read_at(file_handler, (MPI_Offset)0, &boundCondParamStr, 1, boundCondParamType, MPI_STATUS_IGNORE);
@@ -2599,7 +2731,8 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
int ic = 0;
MPI_Offset read_offset1, read_offset2;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
read_offset1 = (MPI_Offset)(sizeof(boundCondParam) + block->getGlobalID() * sizeof(size_t));
@@ -2611,31 +2744,30 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
intArray1 = new int[boundCondParamStr.bcindexmatrixCount];
intArray2 = new int[bcAddArray[ic].indexContainer_count];
- if (bcAddArray[ic].boundCond_count > 0) {
+ if (bcAddArray[ic].boundCond_count > 0)
+ {
MPI_File_read_at(file_handler, (MPI_Offset)(read_offset2 + sizeof(BCAddMigration)), &bcArray[0],
bcAddArray[ic].boundCond_count, boundCondType, MPI_STATUS_IGNORE);
}
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset2 + sizeof(BCAddMigration) +
- bcAddArray[ic].boundCond_count * sizeof(BoundaryCondition)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset2 + sizeof(BCAddMigration) + bcAddArray[ic].boundCond_count * sizeof(BoundaryCondition)),
&intArray1[0], 1, bcindexmatrixType, MPI_STATUS_IGNORE);
- if (bcAddArray[ic].indexContainer_count > 0) {
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset2 + sizeof(BCAddMigration) +
- bcAddArray[ic].boundCond_count * sizeof(BoundaryCondition) +
- boundCondParamStr.bcindexmatrixCount * sizeof(int)),
- &intArray2[0], bcAddArray[ic].indexContainer_count, MPI_INT, MPI_STATUS_IGNORE);
+ if (bcAddArray[ic].indexContainer_count > 0)
+ {
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset2 + sizeof(BCAddMigration) + bcAddArray[ic].boundCond_count * sizeof(BoundaryCondition) +
+ boundCondParamStr.bcindexmatrixCount * sizeof(int)), &intArray2[0], bcAddArray[ic].indexContainer_count, MPI_INT, MPI_STATUS_IGNORE);
}
bcindexmatrixV.resize(0);
indexContainerV.resize(0);
bcVector.resize(0);
- for (int ibc = 0; ibc < bcAddArray[ic].boundCond_count; ibc++) {
+ for (int ibc = 0; ibc < bcAddArray[ic].boundCond_count; ibc++)
+ {
SPtr<BoundaryConditions> bc;
if (memcmp(&bcArray[ibc], nullBouCond, sizeof(BoundaryCondition)) == 0)
bc = SPtr<BoundaryConditions>();
- else {
+ else
+ {
bc = SPtr<BoundaryConditions>(new BoundaryConditions);
bc->noslipBoundaryFlags = bcArray[ibc].noslipBoundaryFlags;
bc->slipBoundaryFlags = bcArray[ibc].slipBoundaryFlags;
@@ -2669,8 +2801,7 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
for (int b2 = 0; b2 < bcAddArray[ic].indexContainer_count; b2++)
indexContainerV.push_back(intArray2[b2]);
- CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2,
- boundCondParamStr.nx3);
+ CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2, boundCondParamStr.nx3);
SPtr<Block3D> block1 = grid->getBlock(bcAddArray[ic].globalID);
SPtr<BCProcessor> bcProc = bcProcessor->clone(block1->getKernel());
@@ -2694,10 +2825,10 @@ void MPIIOMigrationCoProcessor::readBoundaryConds(int step)
delete nullBouCond;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIOMigrationCoProcessor::readBoundaryConds end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
}
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.h b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.h
index ad7a93086afa379822fc7909a68fd39748dd607f..ca0de8f3e7ba315bc8a870f89063ea9f38d7b59f 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.h
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIOMigrationCoProcessor.h
@@ -25,7 +25,8 @@ public:
AverageTriple = 4,
ShearStressVal = 5,
RelaxationFactor = 6,
- PhaseField = 7
+ PhaseField1 = 7,
+ PhaseField2 = 8
};
MPIIOMigrationCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path, SPtr<Communicator> comm);
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.cpp
index ed5d3b275c006700d29c43f16928d2ddc08827f0..02e471c4d652a88335c29f481b6c08b15dcc49e8 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.cpp
@@ -25,8 +25,7 @@
using namespace MPIIODataStructures;
-MPIIORestartCoProcessor::MPIIORestartCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path,
- SPtr<Communicator> comm)
+MPIIORestartCoProcessor::MPIIORestartCoProcessor(SPtr<Grid3D> grid, SPtr<UbScheduler> s, const std::string &path, SPtr<Communicator> comm)
: MPIIOCoProcessor(grid, s, path, comm)
{
memset(&boundCondParamStr, 0, sizeof(boundCondParamStr));
@@ -34,7 +33,7 @@ MPIIORestartCoProcessor::MPIIORestartCoProcessor(SPtr<Grid3D> grid, SPtr<UbSched
//------------------------- define MPI types ---------------------------------
MPI_Datatype typesDataSet[3] = { MPI_DOUBLE, MPI_INT, MPI_CHAR };
- int blocksDataSet[3] = { 2, 5, 2 };
+ int blocksDataSet[3] = { 5, 5, 2 };
MPI_Aint offsetsDatatSet[3], lbDataSet, extentDataSet;
offsetsDatatSet[0] = 0;
@@ -80,7 +79,8 @@ MPIIORestartCoProcessor::~MPIIORestartCoProcessor()
//////////////////////////////////////////////////////////////////////////
void MPIIORestartCoProcessor::process(double step)
{
- if (scheduler->isDue(step)) {
+ if (scheduler->isDue(step))
+ {
if (comm->isRoot())
UBLOG(logINFO, "MPIIORestartCoProcessor save step: " << step);
if (comm->isRoot())
@@ -130,56 +130,77 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
dataSetParam dataSetParamStr1, dataSetParamStr2, dataSetParamStr3;
DataSetRestart *dataSetArray = new DataSetRestart[blocksCount];
- std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
+ std::vector<double> doubleValuesArrayF; // double-values (arrays of f's) in all blocks Fdistribution
+ std::vector<double> doubleValuesArrayH1; // double-values (arrays of f's) in all blocks H1distribution
+ // std::vector<double> doubleValuesArrayH2; // double-values (arrays of f's) in all blocks H2distribution
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeDataSet start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+ bool multiPhase = false;
DSArraysPresence arrPresence;
bool firstBlock = true;
int doubleCountInBlock = 0;
int ic = 0;
- SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF, D3Q27EsoTwist3DSplittedVectorPtrH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF, localDistributionsH;
- CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF, nonLocalDistributionsH;
- CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF, zeroDistributionsH;
+ SPtr<D3Q27EsoTwist3DSplittedVector> D3Q27EsoTwist3DSplittedVectorPtrF, D3Q27EsoTwist3DSplittedVectorPtrH1, D3Q27EsoTwist3DSplittedVectorPtrH2;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributionsF, localDistributionsH1, localDistributionsH2;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributionsF, nonLocalDistributionsH1, nonLocalDistributionsH2;
+ CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr zeroDistributionsF, zeroDistributionsH1, zeroDistributionsH2;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ SPtr<LBMKernel> kernel;
+
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
- dataSetArray[ic].x2 = block->getX2();
- dataSetArray[ic].x3 = block->getX3();
- dataSetArray[ic].level = block->getLevel();
- dataSetArray[ic].ghostLayerWidth = block->getKernel()->getGhostLayerWidth();
- dataSetArray[ic].collFactor = block->getKernel()->getCollisionFactor();
- dataSetArray[ic].deltaT = block->getKernel()->getDeltaT();
- dataSetArray[ic].compressible = block->getKernel()->getCompressible();
- dataSetArray[ic].withForcing = block->getKernel()->getWithForcing();
-
- D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getFdistributions());
+ kernel = dynamicPointerCast<LBMKernel>(block->getKernel());
+
+ dataSetArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetArray[ic].x2 = block->getX2();
+ dataSetArray[ic].x3 = block->getX3();
+ dataSetArray[ic].level = block->getLevel();
+ dataSetArray[ic].ghostLayerWidth = kernel->getGhostLayerWidth();
+ dataSetArray[ic].collFactor = kernel->getCollisionFactor();
+ dataSetArray[ic].deltaT = kernel->getDeltaT();
+ dataSetArray[ic].compressible = kernel->getCompressible();
+ dataSetArray[ic].withForcing = kernel->getWithForcing();
+ dataSetArray[ic].collFactorL = kernel->getCollisionFactorL();
+ dataSetArray[ic].collFactorG = kernel->getCollisionFactorG();
+ dataSetArray[ic].densityRatio = kernel->getDensityRatio();
+
+ D3Q27EsoTwist3DSplittedVectorPtrF = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getFdistributions());
localDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getLocalDistributions();
nonLocalDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getNonLocalDistributions();
zeroDistributionsF = D3Q27EsoTwist3DSplittedVectorPtrF->getZeroDistributions();
- D3Q27EsoTwist3DSplittedVectorPtrH = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(
- block->getKernel()->getDataSet()->getHdistributions());
- localDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getLocalDistributions();
- nonLocalDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getNonLocalDistributions();
- zeroDistributionsH = D3Q27EsoTwist3DSplittedVectorPtrH->getZeroDistributions();
+ D3Q27EsoTwist3DSplittedVectorPtrH1 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getHdistributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH1 != 0)
+ {
+ multiPhase = true;
+ localDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getLocalDistributions();
+ nonLocalDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getNonLocalDistributions();
+ zeroDistributionsH1 = D3Q27EsoTwist3DSplittedVectorPtrH1->getZeroDistributions();
+ }
+
+ /*D3Q27EsoTwist3DSplittedVectorPtrH2 = dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(block->getKernel()->getDataSet()->getH2distributions());
+ if (D3Q27EsoTwist3DSplittedVectorPtrH2 != 0)
+ {
+ localDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getLocalDistributions();
+ nonLocalDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getNonLocalDistributions();
+ zeroDistributionsH2 = D3Q27EsoTwist3DSplittedVectorPtrH2->getZeroDistributions();
+ }*/
if (firstBlock) // when first (any) valid block...
{
@@ -204,96 +225,88 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
}
// ... than save some parameters that are equal in all dataSets
- dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
- dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
- dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 =
- static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
-
- // Fdistributions + Hdistributions
- doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ dataSetParamStr1.nx1 = dataSetParamStr2.nx1 = dataSetParamStr3.nx1 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX1());
+ dataSetParamStr1.nx2 = dataSetParamStr2.nx2 = dataSetParamStr3.nx2 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX2());
+ dataSetParamStr1.nx3 = dataSetParamStr2.nx3 = dataSetParamStr3.nx3 = static_cast<int>(block->getKernel()->getDataSet()->getFdistributions()->getNX3());
+
+ doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3]) * 2;
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray =
- block->getKernel()->getDataSet()->getAverageDensity();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray = kernel->getDataSet()->getAverageDensity();
if (averageDensityArray)
arrPresence.isAverageDensityArrayPresent = true;
else
arrPresence.isAverageDensityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr =
- block->getKernel()->getDataSet()->getAverageVelocity();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr = kernel->getDataSet()->getAverageVelocity();
if (AverageVelocityArray3DPtr)
arrPresence.isAverageVelocityArrayPresent = true;
else
arrPresence.isAverageVelocityArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr =
- block->getKernel()->getDataSet()->getAverageFluctuations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr = kernel->getDataSet()->getAverageFluctuations();
if (AverageFluctArray3DPtr)
arrPresence.isAverageFluktuationsArrayPresent = true;
else
arrPresence.isAverageFluktuationsArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr =
- block->getKernel()->getDataSet()->getAverageTriplecorrelations();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr = kernel->getDataSet()->getAverageTriplecorrelations();
if (AverageTripleArray3DPtr)
arrPresence.isAverageTripleArrayPresent = true;
else
arrPresence.isAverageTripleArrayPresent = false;
- SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr =
- block->getKernel()->getDataSet()->getShearStressValues();
+ SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr = kernel->getDataSet()->getShearStressValues();
if (ShearStressValArray3DPtr)
arrPresence.isShearStressValArrayPresent = true;
else
arrPresence.isShearStressValArrayPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr =
- block->getKernel()->getDataSet()->getRelaxationFactor();
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> relaxationFactor3DPtr = kernel->getDataSet()->getRelaxationFactor();
if (relaxationFactor3DPtr)
arrPresence.isRelaxationFactorPresent = true;
else
arrPresence.isRelaxationFactorPresent = false;
- SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr =
- block->getKernel()->getDataSet()->getPhaseField();
- if (phaseField3DPtr)
- arrPresence.isPhaseFieldPresent = true;
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr1 = kernel->getDataSet()->getPhaseField();
+ if (phaseField3DPtr1)
+ arrPresence.isPhaseField1Present = true;
+ else
+ arrPresence.isPhaseField1Present = false;
+
+ SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> phaseField3DPtr2 = kernel->getDataSet()->getPhaseField2();
+ if (phaseField3DPtr2)
+ arrPresence.isPhaseField2Present = true;
else
- arrPresence.isPhaseFieldPresent = false;
+ arrPresence.isPhaseField2Present = false;
firstBlock = false;
}
- if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsF->getDataVector().begin(),
- localDistributionsF->getDataVector().end());
- if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsF->getDataVector().begin(),
- nonLocalDistributionsF->getDataVector().end());
- if (zeroDistributionsF && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) &&
- (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsF->getDataVector().begin(),
- zeroDistributionsF->getDataVector().end());
-
- if (localDistributionsH && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) &&
- (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), localDistributionsH->getDataVector().begin(),
- localDistributionsH->getDataVector().end());
- if (nonLocalDistributionsH && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) &&
- (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), nonLocalDistributionsH->getDataVector().begin(),
- nonLocalDistributionsH->getDataVector().end());
- if (zeroDistributionsH && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) &&
- (dataSetParamStr3.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), zeroDistributionsH->getDataVector().begin(),
- zeroDistributionsH->getDataVector().end());
+ if (localDistributionsF && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), localDistributionsF->getDataVector().begin(), localDistributionsF->getDataVector().end());
+ if (nonLocalDistributionsF && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), nonLocalDistributionsF->getDataVector().begin(), nonLocalDistributionsF->getDataVector().end());
+ if (zeroDistributionsF && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayF.insert(doubleValuesArrayF.end(), zeroDistributionsF->getDataVector().begin(), zeroDistributionsF->getDataVector().end());
+
+ if (multiPhase)
+ {
+ if (localDistributionsH1 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), localDistributionsH1->getDataVector().begin(), localDistributionsH1->getDataVector().end());
+ if (nonLocalDistributionsH1 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), nonLocalDistributionsH1->getDataVector().begin(), nonLocalDistributionsH1->getDataVector().end());
+ if (zeroDistributionsH1 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH1.insert(doubleValuesArrayH1.end(), zeroDistributionsH1->getDataVector().begin(), zeroDistributionsH1->getDataVector().end());
+ }
+
+ /*if (localDistributionsH2 && (dataSetParamStr1.nx[0] > 0) && (dataSetParamStr1.nx[1] > 0) && (dataSetParamStr1.nx[2] > 0) && (dataSetParamStr1.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), localDistributionsH2->getDataVector().begin(), localDistributionsH2->getDataVector().end());
+ if (nonLocalDistributionsH2 && (dataSetParamStr2.nx[0] > 0) && (dataSetParamStr2.nx[1] > 0) && (dataSetParamStr2.nx[2] > 0) && (dataSetParamStr2.nx[3] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), nonLocalDistributionsH2->getDataVector().begin(), nonLocalDistributionsH2->getDataVector().end());
+ if (zeroDistributionsH2 && (dataSetParamStr3.nx[0] > 0) && (dataSetParamStr3.nx[1] > 0) && (dataSetParamStr3.nx[2] > 0))
+ doubleValuesArrayH2.insert(doubleValuesArrayH2.end(), zeroDistributionsH2->getDataVector().begin(), zeroDistributionsH2->getDataVector().end());*/
ic++;
}
@@ -303,10 +316,10 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -315,15 +328,17 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + 3 * sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + 3 * sizeof(dataSetParam) + blocksCount * (sizeof(DataSetRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + 3 * sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + 3 * sizeof(dataSetParam) + blocksCount * (sizeof(DataSetRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -342,7 +357,7 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
#endif
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -351,27 +366,54 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
MPI_File_write_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
// each process writes common parameters of a dataSet
MPI_File_write_at(file_handler, write_offset, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), &dataSetParamStr2, 1,
- dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + 2 * sizeof(dataSetParam)), &dataSetParamStr3, 1,
- dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + 2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
// each process writes data identifying blocks
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + 3 * sizeof(dataSetParam)), dataSetArray, blocksCount,
- dataSetType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + 3 * sizeof(dataSetParam)), dataSetArray, blocksCount, dataSetType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
- if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + 3 * sizeof(dataSetParam) + blocksCount * sizeof(DataSetRestart)),
- &doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+ if (doubleValuesArrayF.size() > 0)
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + 3 * sizeof(dataSetParam) + blocksCount * sizeof(DataSetRestart)),
+ &doubleValuesArrayF[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
+ //------------------------------------------------------------------------------------------------------------------
+ if (multiPhase)
+ {
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ // each process writes the dataSet arrays
+ if (doubleValuesArrayH1.size() > 0)
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH1[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);
+ }
+
+ //--------------------------------------------------------------------------------------------------------------------
+ /*filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ // each process writes the dataSet arrays
+ if (doubleValuesArrayH1.size() > 0)
+ MPI_File_write_at(file_handler, write_offset, &doubleValuesArrayH2[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+
+ MPI_File_sync(file_handler);
+ MPI_File_close(&file_handler);*/
+
+ //--------------------------------
MPI_Type_free(&dataSetDoubleType);
delete[] dataSetArray;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeDataSet time: " << finish - start << " s");
}
@@ -403,8 +445,11 @@ void MPIIORestartCoProcessor::writeDataSet(int step)
if (arrPresence.isRelaxationFactorPresent)
writeRelaxationFactor(step);
- if (arrPresence.isPhaseFieldPresent)
- writePhaseField(step);
+ if (arrPresence.isPhaseField1Present)
+ writePhaseField(step, 1);
+
+ if (arrPresence.isPhaseField2Present)
+ writePhaseField(step, 2);
}
void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
@@ -418,7 +463,8 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -427,10 +473,10 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
std::vector<double> doubleValuesArray; // double-values of the AverageDensityArray in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageDensityArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -438,13 +484,13 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> averageDensityArray;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
- dataSetSmallArray[ic].x2 = block->getX2();
- dataSetSmallArray[ic].x3 = block->getX3();
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x2 = block->getX2();
+ dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
averageDensityArray = block->getKernel()->getDataSet()->getAverageDensity();
@@ -462,10 +508,8 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), averageDensityArray->getDataVector().begin(),
- averageDensityArray->getDataVector().end());
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
+ doubleValuesArray.insert(doubleValuesArray.end(), averageDensityArray->getDataVector().begin(), averageDensityArray->getDataVector().end());
ic++;
}
@@ -475,10 +519,10 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageDensityArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -487,15 +531,17 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -524,19 +570,18 @@ void MPIIORestartCoProcessor::writeAverageDensityArray(int step)
// each process writes common parameters of a dataSet
MPI_File_write_at(file_handler, write_offset, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
// each process writes data identifying blocks
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageDensityArray time: " << finish - start << " s");
}
@@ -555,7 +600,8 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -564,10 +610,10 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageVelocityArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -575,13 +621,13 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageVelocityArray3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
- dataSetSmallArray[ic].x2 = block->getX2();
- dataSetSmallArray[ic].x3 = block->getX3();
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x2 = block->getX2();
+ dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
AverageVelocityArray3DPtr = block->getKernel()->getDataSet()->getAverageVelocity();
@@ -593,16 +639,13 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
dataSetParamStr.nx[1] = static_cast<int>(AverageVelocityArray3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(AverageVelocityArray3DPtr->getNX3());
dataSetParamStr.nx[3] = static_cast<int>(AverageVelocityArray3DPtr->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), AverageVelocityArray3DPtr->getDataVector().begin(),
- AverageVelocityArray3DPtr->getDataVector().end());
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
+ doubleValuesArray.insert(doubleValuesArray.end(), AverageVelocityArray3DPtr->getDataVector().begin(), AverageVelocityArray3DPtr->getDataVector().end());
ic++;
}
@@ -612,10 +655,10 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageVelocityArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -624,15 +667,16 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ } else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -661,19 +705,18 @@ void MPIIORestartCoProcessor::writeAverageVelocityArray(int step)
// each process writes common parameters of a dataSet
MPI_File_write_at(file_handler, write_offset, &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
// each process writes data identifying blocks
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageVelocityArray time: " << finish - start << " s");
}
@@ -692,7 +735,8 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -701,10 +745,10 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageFluktuationsArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -712,11 +756,11 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageFluctArray3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
dataSetSmallArray[ic].x2 = block->getX2();
dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
@@ -730,14 +774,12 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
dataSetParamStr.nx[1] = static_cast<int>(AverageFluctArray3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(AverageFluctArray3DPtr->getNX3());
dataSetParamStr.nx[3] = static_cast<int>(AverageFluctArray3DPtr->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&(dataSetParamStr.nx[3] > 0))
doubleValuesArray.insert(doubleValuesArray.end(), AverageFluctArray3DPtr->getDataVector().begin(),
AverageFluctArray3DPtr->getDataVector().end());
@@ -749,10 +791,10 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageFluktuationsArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -761,15 +803,16 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ } else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -788,8 +831,7 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
#endif
MPI_File file_handler;
- std::string filename =
- path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpAverageFluktuationsArray.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpAverageFluktuationsArray.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -803,15 +845,15 @@ void MPIIORestartCoProcessor::writeAverageFluktuationsArray(int step)
dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageFluktuationsArray time: " << finish - start << " s");
}
@@ -830,7 +872,8 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -839,10 +882,10 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageTripleArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -850,11 +893,11 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> AverageTripleArray3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
dataSetSmallArray[ic].x2 = block->getX2();
dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
@@ -868,16 +911,13 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
dataSetParamStr.nx[1] = static_cast<int>(AverageTripleArray3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(AverageTripleArray3DPtr->getNX3());
dataSetParamStr.nx[3] = static_cast<int>(AverageTripleArray3DPtr->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), AverageTripleArray3DPtr->getDataVector().begin(),
- AverageTripleArray3DPtr->getDataVector().end());
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
+ doubleValuesArray.insert(doubleValuesArray.end(), AverageTripleArray3DPtr->getDataVector().begin(), AverageTripleArray3DPtr->getDataVector().end());
ic++;
}
@@ -887,10 +927,10 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeAverageTripleArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -899,15 +939,17 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -940,8 +982,7 @@ void MPIIORestartCoProcessor::writeAverageTripleArray(int step)
dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
@@ -967,7 +1008,8 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -976,10 +1018,10 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeShearStressValArray start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -987,11 +1029,11 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
int ic = 0;
SPtr<CbArray4D<LBMReal, IndexerX4X3X2X1>> ShearStressValArray3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
dataSetSmallArray[ic].x2 = block->getX2();
dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
@@ -1005,14 +1047,12 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
dataSetParamStr.nx[1] = static_cast<int>(ShearStressValArray3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(ShearStressValArray3DPtr->getNX3());
dataSetParamStr.nx[3] = static_cast<int>(ShearStressValArray3DPtr->getNX4());
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
- if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) &&
- (dataSetParamStr.nx[3] > 0))
+ if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0) && (dataSetParamStr.nx[3] > 0))
doubleValuesArray.insert(doubleValuesArray.end(), ShearStressValArray3DPtr->getDataVector().begin(),
ShearStressValArray3DPtr->getDataVector().end());
@@ -1024,10 +1064,10 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeShearStressValArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -1036,15 +1076,17 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -1077,15 +1119,15 @@ void MPIIORestartCoProcessor::writeShearStressValArray(int step)
dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeShearStressValArray time: " << finish - start << " s");
}
@@ -1104,7 +1146,8 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1113,10 +1156,10 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeRelaxationFactor start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -1124,11 +1167,11 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
int ic = 0;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> RelaxationFactor3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
- dataSetSmallArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
dataSetSmallArray[ic].x2 = block->getX2();
dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
@@ -1142,8 +1185,7 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
dataSetParamStr.nx[1] = static_cast<int>(RelaxationFactor3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(RelaxationFactor3DPtr->getNX3());
dataSetParamStr.nx[3] = 1;
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
@@ -1160,10 +1202,10 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeRelaxationFactor start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -1172,15 +1214,17 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -1213,15 +1257,15 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeRelaxationFactor time: " << finish - start << " s");
}
@@ -1229,7 +1273,7 @@ void MPIIORestartCoProcessor::writeRelaxationFactor(int step)
delete[] dataSetSmallArray;
}
-void MPIIORestartCoProcessor::writePhaseField(int step)
+void MPIIORestartCoProcessor::writePhaseField(int step, int fieldN)
{
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
@@ -1240,7 +1284,8 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1249,10 +1294,10 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
std::vector<double> doubleValuesArray; // double-values (arrays of f's) in all blocks
dataSetParam dataSetParamStr;
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writePhaseField start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
bool firstBlock = true;
@@ -1260,7 +1305,8 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
int ic = 0;
SPtr<CbArray3D<LBMReal, IndexerX3X2X1>> PhaseField3DPtr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // blocks of the current level
{
dataSetSmallArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
@@ -1268,7 +1314,10 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
dataSetSmallArray[ic].x3 = block->getX3();
dataSetSmallArray[ic].level = block->getLevel();
- PhaseField3DPtr = block->getKernel()->getDataSet()->getPhaseField();
+ if(fieldN == 1)
+ PhaseField3DPtr = block->getKernel()->getDataSet()->getPhaseField();
+ else
+ PhaseField3DPtr = block->getKernel()->getDataSet()->getPhaseField2();
if (firstBlock) // when first (any) valid block...
{
@@ -1277,28 +1326,25 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
dataSetParamStr.nx[1] = static_cast<int>(PhaseField3DPtr->getNX2());
dataSetParamStr.nx[2] = static_cast<int>(PhaseField3DPtr->getNX3());
dataSetParamStr.nx[3] = 1;
- doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
firstBlock = false;
}
-
if ((dataSetParamStr.nx[0] > 0) && (dataSetParamStr.nx[1] > 0) && (dataSetParamStr.nx[2] > 0))
- doubleValuesArray.insert(doubleValuesArray.end(), PhaseField3DPtr->getDataVector().begin(),
- PhaseField3DPtr->getDataVector().end());
+ doubleValuesArray.insert(doubleValuesArray.end(), PhaseField3DPtr->getDataVector().begin(), PhaseField3DPtr->getDataVector().end());
ic++;
}
}
-
+
// register new MPI-types depending on the block-specific information
MPI_Type_contiguous(doubleCountInBlock, MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writePhaseField start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
// write to the file
@@ -1307,15 +1353,17 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
MPI_Offset write_offset = (MPI_Offset)(size * sizeof(int));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_write_offset = write_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_write_offset = write_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
@@ -1334,7 +1382,9 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
#endif
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField.bin";
+ std::string filename;
+ if(fieldN == 1) filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField1.bin";
+ else filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField2.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_CREATE | MPI_MODE_WRONLY, info, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -1348,15 +1398,15 @@ void MPIIORestartCoProcessor::writePhaseField(int step)
dataSetSmallType, MPI_STATUS_IGNORE);
// each process writes the dataSet arrays
if (doubleValuesArray.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writePhaseField time: " << finish - start << " s");
}
@@ -1370,10 +1420,10 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeBoundaryConds start collect data rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
int blocksCount = 0; // quantity of blocks in the grid, max 2147483648 blocks!
@@ -1384,7 +1434,8 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
std::vector<SPtr<Block3D>> blocksVector[25];
int minInitLevel = this->grid->getCoarsestInitializedLevel();
int maxInitLevel = this->grid->getFinestInitializedLevel();
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
grid->getBlocks(level, rank, blocksVector[level]);
blocksCount += static_cast<int>(blocksVector[level].size());
}
@@ -1394,27 +1445,31 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
std::vector<int> bcindexmatrixV;
std::vector<int> indexContainerV;
bool bcindexmatrixCountNotInit = true;
- int ic = 0;
+ int ic = 0;
SPtr<BCArray3D> bcArr;
- for (int level = minInitLevel; level <= maxInitLevel; level++) {
+ for (int level = minInitLevel; level <= maxInitLevel; level++)
+ {
for (SPtr<Block3D> block : blocksVector[level]) // all the blocks of the current level
{
bcArr = block->getKernel()->getBCProcessor()->getBCArray();
- bcAddArray[ic].x1 =
- block->getX1(); // coordinates of the block needed to find it while regenerating the grid
+ bcAddArray[ic].x1 = block->getX1(); // coordinates of the block needed to find it while regenerating the grid
bcAddArray[ic].x2 = block->getX2();
bcAddArray[ic].x3 = block->getX3();
bcAddArray[ic].level = block->getLevel();
bcAddArray[ic].boundCond_count = 0; // how many BoundaryConditions in this block
bcAddArray[ic].indexContainer_count = 0; // how many indexContainer-values in this block
- for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++) {
+ for (std::size_t bc = 0; bc < bcArr->getBCVectorSize(); bc++)
+ {
BoundaryCondition *bouCond = new BoundaryCondition();
- if (bcArr->bcvector[bc] == NULL) {
+ if (bcArr->bcvector[bc] == NULL)
+ {
memset(bouCond, 0, sizeof(BoundaryCondition));
- } else {
+ }
+ else
+ {
bouCond->noslipBoundaryFlags = bcArr->bcvector[bc]->getNoSlipBoundary();
bouCond->slipBoundaryFlags = bcArr->bcvector[bc]->getSlipBoundary();
bouCond->velocityBoundaryFlags = bcArr->bcvector[bc]->getVelocityBoundary();
@@ -1445,15 +1500,15 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
// the quantity of elements in the bcindexmatrix array (CbArray3D<int, IndexerX3X2X1>) in bcArray(BCArray3D)
// is always equal, this will be the size of the "write-read-block" in MPI_write_.../MPI_read-functions when
// writing/reading BoundConds
- if (bcindexmatrixCountNotInit) {
+ if (bcindexmatrixCountNotInit)
+ {
boundCondParamStr.nx1 = static_cast<int>(bcArr->bcindexmatrix.getNX1());
boundCondParamStr.nx2 = static_cast<int>(bcArr->bcindexmatrix.getNX2());
boundCondParamStr.nx3 = static_cast<int>(bcArr->bcindexmatrix.getNX3());
boundCondParamStr.bcindexmatrixCount = static_cast<int>(bcArr->bcindexmatrix.getDataVector().size());
bcindexmatrixCountNotInit = false;
}
- bcindexmatrixV.insert(bcindexmatrixV.end(), bcArr->bcindexmatrix.getDataVector().begin(),
- bcArr->bcindexmatrix.getDataVector().end());
+ bcindexmatrixV.insert(bcindexmatrixV.end(), bcArr->bcindexmatrix.getDataVector().begin(), bcArr->bcindexmatrix.getDataVector().end());
indexContainerV.insert(indexContainerV.end(), bcArr->indexContainer.begin(), bcArr->indexContainer.end());
bcAddArray[ic].indexContainer_count = static_cast<int>(bcArr->indexContainer.size());
@@ -1470,7 +1525,8 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
int bcBlockCount = (int)(count_boundCond / BLOCK_SIZE);
if (bcBlockCount * BLOCK_SIZE < (int)count_boundCond)
bcBlockCount += 1;
- for (int i = (int)count_boundCond; i < bcBlockCount * BLOCK_SIZE; i++) {
+ for (int i = (int)count_boundCond; i < bcBlockCount * BLOCK_SIZE; i++)
+ {
BoundaryCondition *bouCond = new BoundaryCondition();
memset(bouCond, 0, sizeof(BoundaryCondition));
bcVector.push_back(*bouCond);
@@ -1485,11 +1541,15 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
MPI_Offset write_offset = (MPI_Offset)(size * (3 * sizeof(int) + sizeof(boundCondParam)));
size_t next_write_offset = 0;
- if (size > 1) {
- if (rank == 0) {
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
next_write_offset = write_offset + byteCount;
MPI_Send(&next_write_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&write_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
next_write_offset = write_offset + byteCount;
if (rank < size - 1)
@@ -1497,10 +1557,10 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
}
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::writeBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
@@ -1526,14 +1586,11 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
// each process writes the quantity of it's blocks
MPI_File_write_at(file_handler, write_offset1, &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
// each process writes the quantity of "big blocks" of BLOCK_SIZE of boundary conditions
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + sizeof(int)), &bcBlockCount, 1, MPI_INT,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + sizeof(int)), &bcBlockCount, 1, MPI_INT, MPI_STATUS_IGNORE);
// each process writes the quantity of indexContainer elements in all blocks
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + 2 * sizeof(int)), &count_indexContainer, 1, MPI_INT,
- MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + 2 * sizeof(int)), &count_indexContainer, 1, MPI_INT, MPI_STATUS_IGNORE);
// each process writes the quantity of bcindexmatrix elements in every block
- MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + 3 * sizeof(int)), &boundCondParamStr, 1,
- boundCondParamType, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset1 + 3 * sizeof(int)), &boundCondParamStr, 1, boundCondParamType, MPI_STATUS_IGNORE);
// each process writes data identifying the blocks
MPI_File_write_at(file_handler, write_offset, bcAddArray, blocksCount, boundCondTypeAdd, MPI_STATUS_IGNORE);
@@ -1543,23 +1600,19 @@ void MPIIORestartCoProcessor::writeBoundaryConds(int step)
bcBlockCount, boundCondType1000, MPI_STATUS_IGNORE);
// each process writes bcindexmatrix values
if (bcindexmatrixV.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + blocksCount * sizeof(BCAddRestart) +
- bcBlockCount * BLOCK_SIZE * sizeof(BoundaryCondition)),
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + blocksCount * sizeof(BCAddRestart) + bcBlockCount * BLOCK_SIZE * sizeof(BoundaryCondition)),
&bcindexmatrixV[0], blocksCount, bcindexmatrixType, MPI_STATUS_IGNORE);
// each process writes indexContainer values
if (indexContainerV.size() > 0)
- MPI_File_write_at(file_handler,
- (MPI_Offset)(write_offset + blocksCount * sizeof(BCAddRestart) +
- bcBlockCount * BLOCK_SIZE * sizeof(BoundaryCondition) +
- blocksCount * boundCondParamStr.bcindexmatrixCount * sizeof(int)),
- &indexContainerV[0], count_indexContainer, MPI_INT, MPI_STATUS_IGNORE);
+ MPI_File_write_at(file_handler, (MPI_Offset)(write_offset + blocksCount * sizeof(BCAddRestart) + bcBlockCount * BLOCK_SIZE * sizeof(BoundaryCondition) +
+ blocksCount * boundCondParamStr.bcindexmatrixCount * sizeof(int)), &indexContainerV[0], count_indexContainer, MPI_INT, MPI_STATUS_IGNORE);
MPI_File_sync(file_handler);
MPI_File_close(&file_handler);
MPI_Type_free(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::writeBoundaryConds time: " << finish - start << " s");
}
@@ -1593,17 +1646,18 @@ void MPIIORestartCoProcessor::readDataSet(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readDataSet start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
+
double start, finish;
if (comm->isRoot())
start = MPI_Wtime();
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSet.bin";
+ std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetF.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -1611,6 +1665,7 @@ void MPIIORestartCoProcessor::readDataSet(int step)
// calculate the read offset
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
+ bool multiPhase = false;
// read count of blocks
int blocksCount = 0;
@@ -1618,122 +1673,146 @@ void MPIIORestartCoProcessor::readDataSet(int step)
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
MPI_File_read_at(file_handler, read_offset, &dataSetParamStr1, 1, dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), &dataSetParamStr2, 1,
- dataSetParamType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + 2 * sizeof(dataSetParam)), &dataSetParamStr3, 1,
- dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), &dataSetParamStr2, 1, dataSetParamType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + 2 * sizeof(dataSetParam)), &dataSetParamStr3, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetRestart *dataSetArray = new DataSetRestart[blocksCount];
- double doubleCountInBlock =
- (dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
+ double doubleCountInBlock = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3] +
dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3] +
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3]) * 2;
- std::vector<double> doubleValuesArray(size_t(blocksCount * doubleCountInBlock)); // double-values in all blocks
+ dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+ std::vector<double> doubleValuesArrayF(size_t(blocksCount * doubleCountInBlock)); // double-values in all blocks Fdistributions
+ std::vector<double> doubleValuesArrayH1; // double-values in all blocks H1distributions
+ //std::vector<double> doubleValuesArrayH2; // double-values in all blocks H2distributions
// define MPI_types depending on the block-specific information
MPI_Type_contiguous(int(doubleCountInBlock), MPI_DOUBLE, &dataSetDoubleType);
MPI_Type_commit(&dataSetDoubleType);
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + 3 * sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetRestart) + size_t(doubleCountInBlock) * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + 3 * sizeof(dataSetParam) + blocksCount * (sizeof(DataSetRestart) + size_t(doubleCountInBlock) * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + 3 * sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetRestart) + size_t(doubleCountInBlock) * sizeof(double));
+ next_read_offset = read_offset + 3 * sizeof(dataSetParam) + blocksCount * (sizeof(DataSetRestart) + size_t(doubleCountInBlock) * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + 3 * sizeof(dataSetParam)), dataSetArray, blocksCount,
- dataSetType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + 3 * sizeof(dataSetParam) + blocksCount * sizeof(DataSetRestart)),
- &doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + 3 * sizeof(dataSetParam)), dataSetArray, blocksCount, dataSetType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + 3 * sizeof(dataSetParam) + blocksCount * sizeof(DataSetRestart)),
+ &doubleValuesArrayF[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+ MPI_File_close(&file_handler);
+
+ //-------------------------------------- H1 -----------------------------
+ MPI_Offset fsize;
+ filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH1.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+ MPI_File_get_size(file_handler, &fsize);
+ if (fsize > 0)
+ {
+ multiPhase = true;
+ doubleValuesArrayH1.resize(blocksCount * doubleCountInBlock);
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayH1[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+ }
MPI_File_close(&file_handler);
+
+ //-------------------------------------- H2 -----------------------------
+ /*filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpDataSetH2.bin";
+ rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
+ if (rc != MPI_SUCCESS)
+ throw UbException(UB_EXARGS, "couldn't open file " + filename);
+
+ doubleValuesArrayH2.resize(blocksCount * doubleCountInBlock);
+ MPI_File_read_at(file_handler, read_offset, &doubleValuesArrayH2[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
+ MPI_File_close(&file_handler);*/
+
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readDataSet time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readDataSet start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
-
+
size_t index = 0;
- std::vector<double> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
- std::vector<double> vectorsOfValuesH1, vectorsOfValuesH2, vectorsOfValuesH3;
- size_t vectorSize1 =
- dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
- size_t vectorSize2 =
- dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
- size_t vectorSize3 =
- dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
-
- for (int n = 0; n < blocksCount; n++) {
- vectorsOfValuesF1.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize1);
- index += vectorSize1;
-
- vectorsOfValuesF2.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize2);
- index += vectorSize2;
-
- vectorsOfValuesF3.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize3);
- index += vectorSize3;
-
- vectorsOfValuesH1.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize1);
+ std::vector<LBMReal> vectorsOfValuesF1, vectorsOfValuesF2, vectorsOfValuesF3;
+ std::vector<LBMReal> vectorsOfValuesH11, vectorsOfValuesH12, vectorsOfValuesH13;
+ //std::vector<LBMReal> vectorsOfValuesH21, vectorsOfValuesH22, vectorsOfValuesH23;
+ size_t vectorSize1 = dataSetParamStr1.nx[0] * dataSetParamStr1.nx[1] * dataSetParamStr1.nx[2] * dataSetParamStr1.nx[3];
+ size_t vectorSize2 = dataSetParamStr2.nx[0] * dataSetParamStr2.nx[1] * dataSetParamStr2.nx[2] * dataSetParamStr2.nx[3];
+ size_t vectorSize3 = dataSetParamStr3.nx[0] * dataSetParamStr3.nx[1] * dataSetParamStr3.nx[2] * dataSetParamStr3.nx[3];
+
+ for (int n = 0; n < blocksCount; n++)
+ {
+ vectorsOfValuesF1.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize1);
+ if (multiPhase)
+ vectorsOfValuesH11.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize1);
+ //vectorsOfValuesH21.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize1);
index += vectorSize1;
- vectorsOfValuesH2.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize2);
+ vectorsOfValuesF2.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize2);
+ if (multiPhase)
+ vectorsOfValuesH12.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize2);
+ //vectorsOfValuesH22.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize2);
index += vectorSize2;
- vectorsOfValuesH3.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + vectorSize3);
+ vectorsOfValuesF3.assign(doubleValuesArrayF.data() + index, doubleValuesArrayF.data() + index + vectorSize3);
+ if (multiPhase)
+ vectorsOfValuesH13.assign(doubleValuesArrayH1.data() + index, doubleValuesArrayH1.data() + index + vectorSize3);
+ //vectorsOfValuesH23.assign(doubleValuesArrayH2.data() + index, doubleValuesArrayH2.data() + index + vectorSize3);
index += vectorSize3;
SPtr<DistributionArray3D> mFdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)
- ->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF1, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesF2, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
vectorsOfValuesF3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX1(dataSetParamStr1.nx1);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX2(dataSetParamStr1.nx2);
dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mFdistributions)->setNX3(dataSetParamStr1.nx3);
- SPtr<DistributionArray3D> mHdistributions(new D3Q27EsoTwist3DSplittedVector());
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH1, dataSetParamStr1.nx[0],
- dataSetParamStr1.nx[1], dataSetParamStr1.nx[2],
- dataSetParamStr1.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH2, dataSetParamStr2.nx[0],
- dataSetParamStr2.nx[1], dataSetParamStr2.nx[2],
- dataSetParamStr2.nx[3])));
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)
- ->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
- vectorsOfValuesH3, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
-
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX1(dataSetParamStr1.nx1);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX2(dataSetParamStr1.nx2);
- dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mHdistributions)->setNX3(dataSetParamStr1.nx3);
-
+ SPtr<DistributionArray3D> mH1distributions(new D3Q27EsoTwist3DSplittedVector());
+ if (multiPhase)
+ {
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH11, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH12, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH13, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH1distributions)->setNX3(dataSetParamStr1.nx3);
+ }
+ /*SPtr<DistributionArray3D> mH2distributions(new D3Q27EsoTwist3DSplittedVector());
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH21, dataSetParamStr1.nx[0], dataSetParamStr1.nx[1], dataSetParamStr1.nx[2], dataSetParamStr1.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNonLocalDistributions(CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
+ new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValuesH22, dataSetParamStr2.nx[0], dataSetParamStr2.nx[1], dataSetParamStr2.nx[2], dataSetParamStr2.nx[3])));
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setZeroDistributions(CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr(new CbArray3D<LBMReal, IndexerX3X2X1>(
+ vectorsOfValuesH23, dataSetParamStr3.nx[0], dataSetParamStr3.nx[1], dataSetParamStr3.nx[2])));
+
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX1(dataSetParamStr1.nx1);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX2(dataSetParamStr1.nx2);
+ dynamicPointerCast<D3Q27EsoTwist3DSplittedVector>(mH2distributions)->setNX3(dataSetParamStr1.nx3);*/
+
// find the nesessary block and fill it
- SPtr<Block3D> block =
- grid->getBlock(dataSetArray[n].x1, dataSetArray[n].x2, dataSetArray[n].x3, dataSetArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetArray[n].x1, dataSetArray[n].x2, dataSetArray[n].x3, dataSetArray[n].level);
+
this->lbmKernel->setBlock(block);
SPtr<LBMKernel> kernel = this->lbmKernel->clone();
kernel->setGhostLayerWidth(dataSetArray[n].ghostLayerWidth);
@@ -1741,17 +1820,22 @@ void MPIIORestartCoProcessor::readDataSet(int step)
kernel->setDeltaT(dataSetArray[n].deltaT);
kernel->setCompressible(dataSetArray[n].compressible);
kernel->setWithForcing(dataSetArray[n].withForcing);
+ kernel->setCollisionFactorMultiphase(dataSetArray[n].collFactorL, dataSetArray[n].collFactorG);
+ kernel->setDensityRatio(dataSetArray[n].densityRatio);
+
SPtr<DataSet3D> dataSetPtr = SPtr<DataSet3D>(new DataSet3D());
dataSetPtr->setFdistributions(mFdistributions);
- dataSetPtr->setHdistributions(mHdistributions);
+ if (multiPhase)
+ dataSetPtr->setHdistributions(mH1distributions);
+ //dataSetPtr->setH2distributions(mH2distributions);
kernel->setDataSet(dataSetPtr);
block->setKernel(kernel);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readDataSet end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetArray;
@@ -1785,8 +1869,11 @@ void MPIIORestartCoProcessor::readDataSet(int step)
if (arrPresence.isRelaxationFactorPresent)
readRelaxationFactor(step);
- if (arrPresence.isPhaseFieldPresent)
- readPhaseField(step);
+ if (arrPresence.isPhaseField1Present)
+ readPhaseField(step, 1);
+
+ if (arrPresence.isPhaseField2Present)
+ readPhaseField(step, 2);
}
void MPIIORestartCoProcessor::readAverageDensityArray(int step)
@@ -1795,10 +1882,10 @@ void MPIIORestartCoProcessor::readAverageDensityArray(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageDensityArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -1816,12 +1903,10 @@ void MPIIORestartCoProcessor::readAverageDensityArray(int step)
memset(&dataSetParamStr, 0, sizeof(dataSetParam));
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -1832,61 +1917,59 @@ void MPIIORestartCoProcessor::readAverageDensityArray(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageDensityArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageDensityArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
// fill mAverageDensity arrays
SPtr<AverageValuesArray3D> mAverageDensity;
- mAverageDensity = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1],
- dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
+ mAverageDensity = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues,
+ dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setAverageDensity(mAverageDensity);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageDensityArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -1898,10 +1981,10 @@ void MPIIORestartCoProcessor::readAverageVelocityArray(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageVelocityArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -1917,12 +2000,10 @@ void MPIIORestartCoProcessor::readAverageVelocityArray(int step)
int blocksCount = 0;
dataSetParam dataSetParamStr;
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -1933,61 +2014,59 @@ void MPIIORestartCoProcessor::readAverageVelocityArray(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageVelocityArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageVelocityArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
// fill mAverageVelocity array
SPtr<AverageValuesArray3D> mAverageVelocity;
- mAverageVelocity = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1],
- dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
+ mAverageVelocity = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0],
+ dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setAverageVelocity(mAverageVelocity);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageVelocityArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -1999,10 +2078,10 @@ void MPIIORestartCoProcessor::readAverageFluktuationsArray(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageFluktuationsArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -2019,12 +2098,10 @@ void MPIIORestartCoProcessor::readAverageFluktuationsArray(int step)
int blocksCount = 0;
dataSetParam dataSetParamStr;
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -2035,62 +2112,59 @@ void MPIIORestartCoProcessor::readAverageFluktuationsArray(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageFluktuationsArray time: " << finish - start << " s");
- UBLOG(logINFO,
- "MPIIORestartCoProcessor::readAverageFluktuationsArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageFluktuationsArray start of restore of data, rank = " << rank);
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
// fill AverageFluktuations array
SPtr<AverageValuesArray3D> mAverageFluktuations;
- mAverageFluktuations = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1],
- dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
+ mAverageFluktuations = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues,
+ dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setAverageFluctuations(mAverageFluktuations);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageFluktuationsArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -2102,10 +2176,10 @@ void MPIIORestartCoProcessor::readAverageTripleArray(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageTripleArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -2121,12 +2195,10 @@ void MPIIORestartCoProcessor::readAverageTripleArray(int step)
int blocksCount = 0;
dataSetParam dataSetParamStr;
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -2137,61 +2209,59 @@ void MPIIORestartCoProcessor::readAverageTripleArray(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageTripleArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageTripleArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
// fill AverageTriplecorrelations array
SPtr<AverageValuesArray3D> mAverageTriplecorrelations;
- mAverageTriplecorrelations = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1],
- dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
+ mAverageTriplecorrelations = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues,
+ dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setAverageTriplecorrelations(mAverageTriplecorrelations);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readAverageTripleArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -2203,10 +2273,10 @@ void MPIIORestartCoProcessor::readShearStressValArray(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readShearStressValArray start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -2222,12 +2292,10 @@ void MPIIORestartCoProcessor::readShearStressValArray(int step)
int blocksCount = 0;
dataSetParam dataSetParamStr;
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -2238,61 +2306,59 @@ void MPIIORestartCoProcessor::readShearStressValArray(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readShearStressValArray time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readShearStressValArray start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
// fill ShearStressValuesArray array
SPtr<ShearStressValuesArray3D> mShearStressValues;
- mShearStressValues = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(
- new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1],
- dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
+ mShearStressValues = CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr(new CbArray4D<LBMReal, IndexerX4X3X2X1>(vectorsOfValues,
+ dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2], dataSetParamStr.nx[3]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setShearStressValues(mShearStressValues);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readShearStressValArray end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -2304,10 +2370,10 @@ void MPIIORestartCoProcessor::readRelaxationFactor(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readRelaxationFactor start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -2323,12 +2389,10 @@ void MPIIORestartCoProcessor::readRelaxationFactor(int step)
int blocksCount = 0;
dataSetParam dataSetParamStr;
MPI_File_read_at(file_handler, (MPI_Offset)(rank * sizeof(int)), &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(size * sizeof(int)), &dataSetParamStr, 1, dataSetParamType, MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -2339,41 +2403,41 @@ void MPIIORestartCoProcessor::readRelaxationFactor(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readRelaxationFactor time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readRelaxationFactor start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
size_t nextVectorSize =
dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
+ std::vector<LBMReal> vectorsOfValues;
for (int n = 0; n < blocksCount; n++) {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
@@ -2384,37 +2448,38 @@ void MPIIORestartCoProcessor::readRelaxationFactor(int step)
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
block->getKernel()->getDataSet()->setRelaxationFactor(mRelaxationFactor);
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readRelaxationFactor end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
}
-void MPIIORestartCoProcessor::readPhaseField(int step)
+void MPIIORestartCoProcessor::readPhaseField(int step, int fieldN)
{
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readPhaseField start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
start = MPI_Wtime();
MPI_File file_handler;
- std::string filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField.bin";
+ std::string filename;
+ if(fieldN == 1) filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField1.bin";
+ else filename = path + "/mpi_io_cp/mpi_io_cp_" + UbSystem::toString(step) + "/cpPhaseField2.bin";
int rc = MPI_File_open(MPI_COMM_WORLD, filename.c_str(), MPI_MODE_RDONLY, MPI_INFO_NULL, &file_handler);
if (rc != MPI_SUCCESS)
throw UbException(UB_EXARGS, "couldn't open file " + filename);
@@ -2427,8 +2492,7 @@ void MPIIORestartCoProcessor::readPhaseField(int step)
MPI_STATUS_IGNORE);
DataSetSmallRestart *dataSetSmallArray = new DataSetSmallRestart[blocksCount];
- int doubleCountInBlock =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ int doubleCountInBlock = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
std::vector<double> doubleValuesArray(blocksCount * doubleCountInBlock); // double-values in all blocks
// define MPI_types depending on the block-specific information
@@ -2439,42 +2503,43 @@ void MPIIORestartCoProcessor::readPhaseField(int step)
MPI_Offset read_offset = (MPI_Offset)(size * sizeof(int));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + sizeof(dataSetParam) +
- blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
+ next_read_offset = read_offset + sizeof(dataSetParam) + blocksCount * (sizeof(DataSetSmallRestart) + doubleCountInBlock * sizeof(double));
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
}
}
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount,
- dataSetSmallType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam)), dataSetSmallArray, blocksCount, dataSetSmallType, MPI_STATUS_IGNORE);
if (doubleCountInBlock > 0)
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + sizeof(dataSetParam) + blocksCount * sizeof(DataSetSmallRestart)),
&doubleValuesArray[0], blocksCount, dataSetDoubleType, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&dataSetDoubleType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readPhaseField time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readPhaseField start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
size_t index = 0;
- size_t nextVectorSize =
- dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
- std::vector<double> vectorsOfValues;
- for (int n = 0; n < blocksCount; n++) {
+ size_t nextVectorSize = dataSetParamStr.nx[0] * dataSetParamStr.nx[1] * dataSetParamStr.nx[2] * dataSetParamStr.nx[3];
+ std::vector<LBMReal> vectorsOfValues;
+
+ for (int n = 0; n < blocksCount; n++)
+ {
vectorsOfValues.assign(doubleValuesArray.data() + index, doubleValuesArray.data() + index + nextVectorSize);
index += nextVectorSize;
@@ -2484,15 +2549,18 @@ void MPIIORestartCoProcessor::readPhaseField(int step)
vectorsOfValues, dataSetParamStr.nx[0], dataSetParamStr.nx[1], dataSetParamStr.nx[2]));
// find the nesessary block and fill it
- SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3,
- dataSetSmallArray[n].level);
- block->getKernel()->getDataSet()->setPhaseField(mPhaseField);
+ SPtr<Block3D> block = grid->getBlock(dataSetSmallArray[n].x1, dataSetSmallArray[n].x2, dataSetSmallArray[n].x3, dataSetSmallArray[n].level);
+ if(fieldN == 1)
+ block->getKernel()->getDataSet()->setPhaseField(mPhaseField);
+ else
+ block->getKernel()->getDataSet()->setPhaseField2(mPhaseField);
+
}
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readPhaseField end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
delete[] dataSetSmallArray;
@@ -2504,10 +2572,10 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
UBLOG(logINFO, "MPIIORestartCoProcessor::readBoundaryConds start MPI IO rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
double start, finish;
if (comm->isRoot())
@@ -2527,14 +2595,11 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
// read count of blocks
MPI_File_read_at(file_handler, read_offset1, &blocksCount, 1, MPI_INT, MPI_STATUS_IGNORE);
// read count of big BoundaryCondition blocks
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + sizeof(int)), &dataCount1000, 1, MPI_INT,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + sizeof(int)), &dataCount1000, 1, MPI_INT, MPI_STATUS_IGNORE);
// read count of indexContainer values in all blocks
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + 2 * sizeof(int)), &dataCount2, 1, MPI_INT,
- MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + 2 * sizeof(int)), &dataCount2, 1, MPI_INT, MPI_STATUS_IGNORE);
// read count of bcindexmatrix values in every block
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + 3 * sizeof(int)), &boundCondParamStr, 1,
- boundCondParamType, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset1 + 3 * sizeof(int)), &boundCondParamStr, 1, boundCondParamType, MPI_STATUS_IGNORE);
MPI_Type_contiguous(boundCondParamStr.bcindexmatrixCount, MPI_INT, &bcindexmatrixType);
MPI_Type_commit(&bcindexmatrixType);
@@ -2550,16 +2615,18 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
MPI_Offset read_offset = (MPI_Offset)(size * (3 * sizeof(int) + sizeof(boundCondParam)));
size_t next_read_offset = 0;
- if (size > 1) {
- if (rank == 0) {
- next_read_offset = read_offset + blocksCount * sizeof(BCAddRestart) +
- dataCount * sizeof(BoundaryCondition) +
+ if (size > 1)
+ {
+ if (rank == 0)
+ {
+ next_read_offset = read_offset + blocksCount * sizeof(BCAddRestart) + dataCount * sizeof(BoundaryCondition) +
(blocksCount * boundCondParamStr.bcindexmatrixCount + dataCount2) * sizeof(int);
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, 1, 5, MPI_COMM_WORLD);
- } else {
+ }
+ else
+ {
MPI_Recv(&read_offset, 1, MPI_LONG_LONG_INT, rank - 1, 5, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
- next_read_offset = read_offset + blocksCount * sizeof(BCAddRestart) +
- dataCount * sizeof(BoundaryCondition) +
+ next_read_offset = read_offset + blocksCount * sizeof(BCAddRestart) + dataCount * sizeof(BoundaryCondition) +
(blocksCount * boundCondParamStr.bcindexmatrixCount + dataCount2) * sizeof(int);
if (rank < size - 1)
MPI_Send(&next_read_offset, 1, MPI_LONG_LONG_INT, rank + 1, 5, MPI_COMM_WORLD);
@@ -2567,27 +2634,21 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
}
MPI_File_read_at(file_handler, read_offset, bcAddArray, blocksCount, boundCondTypeAdd, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart)), &bcArray[0],
- dataCount1000, boundCondType1000, MPI_STATUS_IGNORE);
- MPI_File_read_at(
- file_handler,
- (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart) + dataCount * sizeof(BoundaryCondition)),
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart)), &bcArray[0], dataCount1000, boundCondType1000, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart) + dataCount * sizeof(BoundaryCondition)),
&intArray1[0], blocksCount, bcindexmatrixType, MPI_STATUS_IGNORE);
- MPI_File_read_at(file_handler,
- (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart) +
- dataCount * sizeof(BoundaryCondition) +
- blocksCount * boundCondParamStr.bcindexmatrixCount * sizeof(int)),
- &intArray2[0], dataCount2, MPI_INT, MPI_STATUS_IGNORE);
+ MPI_File_read_at(file_handler, (MPI_Offset)(read_offset + blocksCount * sizeof(BCAddRestart) + dataCount * sizeof(BoundaryCondition) +
+ blocksCount * boundCondParamStr.bcindexmatrixCount * sizeof(int)), &intArray2[0], dataCount2, MPI_INT, MPI_STATUS_IGNORE);
MPI_File_close(&file_handler);
MPI_Type_free(&bcindexmatrixType);
- if (comm->isRoot()) {
+ if (comm->isRoot())
+ {
finish = MPI_Wtime();
UBLOG(logINFO, "MPIIORestartCoProcessor::readBoundaryConds time: " << finish - start << " s");
UBLOG(logINFO, "MPIIORestartCoProcessor::readBoundaryConds start of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
int index = 0, index1 = 0, index2 = 0;
@@ -2595,16 +2656,19 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
std::vector<int> bcindexmatrixV;
std::vector<int> indexContainerV;
- for (int n = 0; n < blocksCount; n++) {
+ for (int n = 0; n < blocksCount; n++)
+ {
bcVector.resize(0);
bcindexmatrixV.resize(0);
indexContainerV.resize(0);
- for (int ibc = 0; ibc < bcAddArray[n].boundCond_count; ibc++) {
+ for (int ibc = 0; ibc < bcAddArray[n].boundCond_count; ibc++)
+ {
SPtr<BoundaryConditions> bc;
if (memcmp(&bcArray[index], nullBouCond, sizeof(BoundaryCondition)) == 0)
bc = SPtr<BoundaryConditions>();
- else {
+ else
+ {
bc = SPtr<BoundaryConditions>(new BoundaryConditions);
bc->noslipBoundaryFlags = bcArray[index].noslipBoundaryFlags;
bc->slipBoundaryFlags = bcArray[index].slipBoundaryFlags;
@@ -2639,8 +2703,7 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
for (int b2 = 0; b2 < bcAddArray[n].indexContainer_count; b2++)
indexContainerV.push_back(intArray2[index2++]);
- CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2,
- boundCondParamStr.nx3);
+ CbArray3D<int, IndexerX3X2X1> bcim(bcindexmatrixV, boundCondParamStr.nx1, boundCondParamStr.nx2, boundCondParamStr.nx3);
SPtr<Block3D> block = grid->getBlock(bcAddArray[n].x1, bcAddArray[n].x2, bcAddArray[n].x3, bcAddArray[n].level);
SPtr<BCProcessor> bcProc = bcProcessor->clone(block->getKernel());
@@ -2661,8 +2724,7 @@ void MPIIORestartCoProcessor::readBoundaryConds(int step)
if (comm->isRoot()) {
UBLOG(logINFO, "MPIIORestartCoProcessor::readBoundaryConds end of restore of data, rank = " << rank);
- UBLOG(logINFO, "Physical Memory currently used by current process: "
- << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
+ UBLOG(logINFO, "Physical Memory currently used by current process: " << Utilities::getPhysMemUsedByMe() / 1073741824.0 << " GB");
}
}
//////////////////////////////////////////////////////////////////////////
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.h b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.h
index cbcf8c553943aa325f415cd123ae1fbe0bf4dcf3..57f559769a06d9a87a968ada73fbaba712da789b 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.h
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/MPIIORestartCoProcessor.h
@@ -4,6 +4,7 @@
#include <mpi.h>
//#include <PointerDefinitions.h>
#include <string>
+#include <vector>
#include "MPIIOCoProcessor.h"
#include "MPIIODataStructures.h"
@@ -35,8 +36,8 @@ public:
void writeAverageTripleArray(int step);
void writeShearStressValArray(int step);
void writeRelaxationFactor(int step);
- void writePhaseField(int step);
- //! Writes the boundary conditions of the blocks into the file cpBC.bin
+ void writePhaseField(int step, int num);
+ //! Writes the boundary conditions of the blocks into the file cpBC.bin
void writeBoundaryConds(int step);
//! Reads the blocks of the grid from the file cpBlocks.bin
@@ -49,7 +50,7 @@ public:
void readAverageTripleArray(int step);
void readShearStressValArray(int step);
void readRelaxationFactor(int step);
- void readPhaseField(int step);
+ void readPhaseField(int step, int num);
//! Reads the boundary conditions of the blocks from the file cpBC.bin
void readBoundaryConds(int step);
//! The function sets LBMKernel
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/PressureCoefficientCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/PressureCoefficientCoProcessor.cpp
index b350f441b3b237032ca24cd4a3743c3cf629a89e..1c7e47f52e721069b20a6b3c27d1e71857ef74ab 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/PressureCoefficientCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/PressureCoefficientCoProcessor.cpp
@@ -42,8 +42,8 @@ void PressureCoefficientCoProcessor::collectData(double step)
//////////////////////////////////////////////////////////////////////////
void PressureCoefficientCoProcessor::calculateRho()
{
- double f[D3Q27System::ENDF + 1];
- double vx1, vx2, vx3, rho;
+ LBMReal f[D3Q27System::ENDF + 1];
+ LBMReal vx1, vx2, vx3, rho;
std::vector<double> values;
std::vector<double> rvalues;
diff --git a/src/cpu/VirtualFluidsCore/CoProcessors/WriteMacroscopicQuantitiesCoProcessor.cpp b/src/cpu/VirtualFluidsCore/CoProcessors/WriteMacroscopicQuantitiesCoProcessor.cpp
index 3519c83a529314e1135f3d76e21c3b2c3c3f8cba..e98d6ac874ace46659bc2903b3c67a0f9f93fa24 100644
--- a/src/cpu/VirtualFluidsCore/CoProcessors/WriteMacroscopicQuantitiesCoProcessor.cpp
+++ b/src/cpu/VirtualFluidsCore/CoProcessors/WriteMacroscopicQuantitiesCoProcessor.cpp
@@ -211,33 +211,25 @@ void WriteMacroscopicQuantitiesCoProcessor::addDataMQ(SPtr<Block3D> block)
distributions->getDistribution(f, ix1, ix2, ix3);
calcMacros(f, rho, vx1, vx2, vx3);
- double press = D3Q27System::getPressure(f); // D3Q27System::calcPress(f,rho,vx1,vx2,vx3);
+ //double press = D3Q27System::getPressure(f); // D3Q27System::calcPress(f,rho,vx1,vx2,vx3);
if (UbMath::isNaN(rho) || UbMath::isInfinity(rho))
- // UB_THROW( UbException(UB_EXARGS,"rho is not a number (nan or -1.#IND) or infinity number
- // -1.#INF in block="+block->toString()+",
- // node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
- rho = 999.0;
- if (UbMath::isNaN(press) || UbMath::isInfinity(press))
+ UB_THROW( UbException(UB_EXARGS,"rho is not a number (nan or -1.#IND) or infinity number -1.#INF in block="+block->toString()+",node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
+ //rho = 999.0;
+ //if (UbMath::isNaN(press) || UbMath::isInfinity(press))
// UB_THROW( UbException(UB_EXARGS,"press is not a number (nan or -1.#IND) or infinity number
// -1.#INF in block="+block->toString()+",
// node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
- press = 999.0;
+ //press = 999.0;
if (UbMath::isNaN(vx1) || UbMath::isInfinity(vx1))
- // UB_THROW( UbException(UB_EXARGS,"vx1 is not a number (nan or -1.#IND) or infinity number
- // -1.#INF in block="+block->toString()+",
- // node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
- vx1 = 999.0;
+ UB_THROW( UbException(UB_EXARGS,"vx1 is not a number (nan or -1.#IND) or infinity number -1.#INF in block="+block->toString()+", node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
+ //vx1 = 999.0;
if (UbMath::isNaN(vx2) || UbMath::isInfinity(vx2))
- // UB_THROW( UbException(UB_EXARGS,"vx2 is not a number (nan or -1.#IND) or infinity number
- // -1.#INF in block="+block->toString()+",
- // node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
- vx2 = 999.0;
+ UB_THROW( UbException(UB_EXARGS,"vx2 is not a number (nan or -1.#IND) or infinity number -1.#INF in block="+block->toString()+", node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
+ //vx2 = 999.0;
if (UbMath::isNaN(vx3) || UbMath::isInfinity(vx3))
- // UB_THROW( UbException(UB_EXARGS,"vx3 is not a number (nan or -1.#IND) or infinity number
- // -1.#INF in block="+block->toString()+",
- // node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
- vx3 = 999.0;
+ UB_THROW( UbException(UB_EXARGS,"vx3 is not a number (nan or -1.#IND) or infinity number -1.#INF in block="+block->toString()+", node="+UbSystem::toString(ix1)+","+UbSystem::toString(ix2)+","+UbSystem::toString(ix3)));
+ //vx3 = 999.0;
data[index++].push_back(rho);
data[index++].push_back(vx1);
diff --git a/src/cpu/VirtualFluidsCore/Connectors/FullDirectConnector.h b/src/cpu/VirtualFluidsCore/Connectors/FullDirectConnector.h
index 6d8877ee909183dcb4088ccb77f6726e83447ba8..fb04de68aaa4ab360e38ae83c9d47d077c05e59f 100644
--- a/src/cpu/VirtualFluidsCore/Connectors/FullDirectConnector.h
+++ b/src/cpu/VirtualFluidsCore/Connectors/FullDirectConnector.h
@@ -48,9 +48,9 @@ public:
void sendVectors() override;
protected:
- virtual inline void updatePointers() = 0;
+ virtual void updatePointers() = 0;
void exchangeData();
- virtual inline void exchangeData(int x1From, int x2From, int x3From, int x1To, int x2To, int x3To) = 0;
+ virtual void exchangeData(int x1From, int x2From, int x3From, int x1To, int x2To, int x3To) = 0;
int maxX1;
int maxX2;
diff --git a/src/cpu/VirtualFluidsCore/Connectors/FullVectorConnector.h b/src/cpu/VirtualFluidsCore/Connectors/FullVectorConnector.h
index c2853d4a81bdb3497e235a9115f7cf5260425117..39fc3d1afa3fb958b09d128bd67a5aca42acbc03 100644
--- a/src/cpu/VirtualFluidsCore/Connectors/FullVectorConnector.h
+++ b/src/cpu/VirtualFluidsCore/Connectors/FullVectorConnector.h
@@ -55,11 +55,11 @@ public:
void distributeReceiveVectors() override;
protected:
- virtual inline void updatePointers() = 0;
+ virtual void updatePointers() = 0;
void fillData();
void distributeData();
- virtual inline void fillData(vector_type &sdata, int &index, int x1, int x2, int x3) = 0;
- virtual inline void distributeData(vector_type &rdata, int &index, int x1, int x2, int x3) = 0;
+ virtual void fillData(vector_type &sdata, int &index, int x1, int x2, int x3) = 0;
+ virtual void distributeData(vector_type &rdata, int &index, int x1, int x2, int x3) = 0;
int maxX1;
int maxX2;
diff --git a/src/cpu/VirtualFluidsCore/Data/DataSet3D.h b/src/cpu/VirtualFluidsCore/Data/DataSet3D.h
index b8b541546f3c2cccb49ff09c859b8c97c2e22f63..e53e38a74daea2a2a40ca53eff1aa1f4febcc27a 100644
--- a/src/cpu/VirtualFluidsCore/Data/DataSet3D.h
+++ b/src/cpu/VirtualFluidsCore/Data/DataSet3D.h
@@ -91,23 +91,18 @@ public:
protected:
private:
SPtr<DistributionArray3D> fdistributions;
-
SPtr<DistributionArray3D> hdistributions;
-
//SPtr<DistributionArray3D> h1distributions;
SPtr<DistributionArray3D> h2distributions;
-
+
SPtr<AverageValuesArray3D> averageValues;
-
SPtr<AverageValuesArray3D> averageDensity;
SPtr<AverageValuesArray3D> averageVelocity;
SPtr<AverageValuesArray3D> averageFluktuations;
SPtr<AverageValuesArray3D> averageTriplecorrelations;
-
SPtr<ShearStressValuesArray3D> shearStressValues;
SPtr<RelaxationFactorArray3D> relaxationFactor;
-
SPtr<PhaseFieldArray3D> phaseField;
SPtr<PhaseFieldArray3D> phaseField2;
};
diff --git a/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.cpp b/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.cpp
index e7144a7c6f67d1a9feb8a5883a046420750f1c1b..37c6c47f05215b1d210ef943e639b1cb957ca63d 100644
--- a/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.cpp
+++ b/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.cpp
@@ -58,7 +58,7 @@ void D3Q27TriFaceMeshInteractor::initInteractor(const double &timeStep)
setQs(timeStep);
}
//////////////////////////////////////////////////////////////////////////
-bool D3Q27TriFaceMeshInteractor::setDifferencesToGbObject3D(const SPtr<Block3D> block/*,const double& orgX1,const double& orgX2,const double& orgX3,const double& blockLengthX1,const double& blockLengthX2,const double& blockLengthX3, const double& timestep*/)
+bool D3Q27TriFaceMeshInteractor::setDifferencesToGbObject3D(const SPtr<Block3D> block)
{
if (!block)
return false;
diff --git a/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.h b/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.h
index ebd707a41ca454cb1e8b22f0020cfd98cadfab36..9ac8bfc48a4fda3612b0781d93496cce723d2cd8 100644
--- a/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.h
+++ b/src/cpu/VirtualFluidsCore/Interactors/D3Q27TriFaceMeshInteractor.h
@@ -42,7 +42,7 @@ public:
void setQs(const double &timeStep);
void refineBlockGridToLevel(int level, double startDistance, double stopDistance);
- bool setDifferencesToGbObject3D(const SPtr<Block3D> block/*,const double& orgX1,const double& orgX2,const double& orgX3,const double& blockLengthX1,const double& blockLengthX2,const double& blockLengthX3, const double& timestep=0*/) override;
+ bool setDifferencesToGbObject3D(const SPtr<Block3D> block) override;
void setRegardPointInObjectTest(bool opt) { this->regardPIOTest = opt; }
diff --git a/src/cpu/VirtualFluidsCore/Interactors/Interactor3D.h b/src/cpu/VirtualFluidsCore/Interactors/Interactor3D.h
index 74627b76addaf6badaea678d1c4a20b274234b3a..9727bf636085c7c0d24a9108acc71925af36e5d1 100644
--- a/src/cpu/VirtualFluidsCore/Interactors/Interactor3D.h
+++ b/src/cpu/VirtualFluidsCore/Interactors/Interactor3D.h
@@ -76,12 +76,7 @@ public:
SPtr<Grid3D> getGrid3D() const { return grid.lock(); }
void setGrid3D(SPtr<Grid3D> grid) { this->grid = grid; }
virtual SPtr<GbObject3D> getGbObject3D() const { return geoObject3D; }
- virtual bool setDifferencesToGbObject3D(const SPtr<Block3D>)
- {
- // UBLOG(logINFO, "Interactor3D::setDifferencesToGbObject3D()");
- return false;
- }
-
+ virtual bool setDifferencesToGbObject3D(const SPtr<Block3D>) = 0;
virtual std::vector<SPtr<Block3D>> &getBcBlocks() { return this->bcBlocks; }
virtual void removeBcBlocks() { this->bcBlocks.clear(); }
virtual std::vector<SPtr<Block3D>> &getSolidBlockSet() { return this->solidBlocks; }
diff --git a/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.cpp b/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.cpp
index 280562ebfaff7ccaa61055fa7caed0a4cac4d666..20851b019a3a0abd2c8865c7c40530e73bcf6245 100644
--- a/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.cpp
+++ b/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.cpp
@@ -5,8 +5,9 @@
#include "D3Q27EsoTwist3DSplittedVector.h"
#include "D3Q27System.h"
#include "DataSet3D.h"
+#include "Block3D.h"
-//#define PROOF_CORRECTNESS
+#define PROOF_CORRECTNESS
//////////////////////////////////////////////////////////////////////////
BGKLBMKernel::BGKLBMKernel() { this->compressible = false; }
@@ -22,6 +23,7 @@ void BGKLBMKernel::initDataSet()
SPtr<LBMKernel> BGKLBMKernel::clone()
{
SPtr<LBMKernel> kernel(new BGKLBMKernel());
+ kernel->setNX(nx);
std::dynamic_pointer_cast<BGKLBMKernel>(kernel)->initDataSet();
kernel->setCollisionFactor(this->collFactor);
kernel->setBCProcessor(bcProcessor->clone(kernel));
@@ -30,10 +32,12 @@ SPtr<LBMKernel> BGKLBMKernel::clone()
kernel->setForcingX2(muForcingX2);
kernel->setForcingX3(muForcingX3);
kernel->setIndex(ix1, ix2, ix3);
+ kernel->setDeltaT(deltaT);
+ kernel->setBlock(block.lock());
return kernel;
}
//////////////////////////////////////////////////////////////////////////
-void BGKLBMKernel::calculate(int /*step*/)
+void BGKLBMKernel::calculate(int step)
{
using namespace D3Q27System;
using namespace UbMath;
@@ -250,7 +254,10 @@ void BGKLBMKernel::calculate(int /*step*/)
if (dif > 10.0E-15 || dif < -10.0E-15)
#endif
{
- UB_THROW(UbException(UB_EXARGS, "rho is not correct"));
+ UB_THROW(UbException(UB_EXARGS, "rho="+UbSystem::toString(drho)+", rho_post="+UbSystem::toString(rho_post)
+ +" dif="+UbSystem::toString(dif)
+ +" rho is not correct for node "+UbSystem::toString(x1)+","+UbSystem::toString(x2)+","+UbSystem::toString(x3)
+ +" in " + block.lock()->toString()+" step = "+UbSystem::toString(step)));
}
#endif
//////////////////////////////////////////////////////////////////////////
diff --git a/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.h b/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.h
index e998267c083c604d6387acf71d2e069315e595c8..9d17a8cc7677db7a142f4340dcdeaf38e268d214 100644
--- a/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.h
+++ b/src/cpu/VirtualFluidsCore/LBM/BGKLBMKernel.h
@@ -1,5 +1,5 @@
-#ifndef LBMKERNELETD3Q27BGK_H
-#define LBMKERNELETD3Q27BGK_H
+#ifndef BGKLBMKernel_H
+#define BGKLBMKernel_H
#include "LBMKernel.h"
#include "basics/container/CbArray3D.h"
diff --git a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.cpp b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.cpp
index daed493b9cc1afddbd92acabcd551da0f463ea26..9c52f5e0469ce5b6c6e08136f25d3c027d36bdbd 100644
--- a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.cpp
+++ b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.cpp
@@ -39,6 +39,7 @@
#include "Block3D.h"
#include "BCArray3D.h"
+
#define PROOF_CORRECTNESS
using namespace UbMath;
diff --git a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.h b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.h
index 10cfd49264bb829eac1fc6b9bedeee3b6eace265..3052f50e3e48925ed21a3c3af68cc2d247c88a02 100644
--- a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.h
+++ b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernel.h
@@ -144,4 +144,4 @@ inline void CumulantK17LBMKernel::backwardChimera(LBMReal& mfa, LBMReal& mfb, LB
mfa = ma;
}
-#endif // CumulantK17LBMKernel_h__
\ No newline at end of file
+#endif // CumulantK17LBMKernel_h__
diff --git a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.cpp b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..2bdc7ce97be90a45b2bebb3dca53f3eb609bec3b
--- /dev/null
+++ b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.cpp
@@ -0,0 +1,337 @@
+//=======================================================================================
+// ____ ____ __ ______ __________ __ __ __ __
+// \ \ | | | | | _ \ |___ ___| | | | | / \ | |
+// \ \ | | | | | |_) | | | | | | | / \ | |
+// \ \ | | | | | _ / | | | | | | / /\ \ | |
+// \ \ | | | | | | \ \ | | | \__/ | / ____ \ | |____
+// \ \ | | |__| |__| \__\ |__| \________/ /__/ \__\ |_______|
+// \ \ | | ________________________________________________________________
+// \ \ | | | ______________________________________________________________|
+// \ \| | | | __ __ __ __ ______ _______
+// \ | | |_____ | | | | | | | | | _ \ / _____)
+// \ | | _____| | | | | | | | | | | \ \ \_______
+// \ | | | | |_____ | \_/ | | | | |_/ / _____ |
+// \ _____| |__| |________| \_______/ |__| |______/ (_______/
+//
+// This file is part of VirtualFluids. VirtualFluids is free software: you can
+// redistribute it and/or modify it under the terms of the GNU General Public
+// License as published by the Free Software Foundation, either version 3 of
+// the License, or (at your option) any later version.
+//
+// VirtualFluids is distributed in the hope that it will be useful, but WITHOUT
+// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+// for more details.
+//
+// You should have received a copy of the GNU General Public License along
+// with VirtualFluids (see COPYING.txt). If not, see <http://www.gnu.org/licenses/>.
+//
+//! \file CumulantK17LBMKernel.cpp
+//! \ingroup LBM
+//! \author Konstantin Kutscher, Martin Geier
+//=======================================================================================
+#include <lbm/KernelParameter.h>
+#include <lbm/CumulantChimera.h>
+#include <lbm/constants/D3Q27.h>
+
+#include "CumulantK17LBMKernelUnified.h"
+#include "D3Q27System.h"
+#include "D3Q27EsoTwist3DSplittedVector.h"
+#include <cmath>
+#include "DataSet3D.h"
+#include "LBMKernel.h"
+#include "Block3D.h"
+#include "BCArray3D.h"
+
+
+//#define PROOF_CORRECTNESS
+
+using namespace UbMath;
+
+//////////////////////////////////////////////////////////////////////////
+CumulantK17LBMKernelUnified::CumulantK17LBMKernelUnified()
+{
+ this->compressible = true;
+}
+//////////////////////////////////////////////////////////////////////////
+void CumulantK17LBMKernelUnified::initDataSet()
+{
+ SPtr<DistributionArray3D> d(new D3Q27EsoTwist3DSplittedVector(nx[0] + 2, nx[1] + 2, nx[2] + 2, -999.9));
+ dataSet->setFdistributions(d);
+}
+//////////////////////////////////////////////////////////////////////////
+SPtr<LBMKernel> CumulantK17LBMKernelUnified::clone()
+{
+ SPtr<LBMKernel> kernel(new CumulantK17LBMKernelUnified());
+ kernel->setNX(nx);
+ std::dynamic_pointer_cast<CumulantK17LBMKernelUnified>(kernel)->initDataSet();
+ kernel->setCollisionFactor(this->collFactor);
+ kernel->setBCProcessor(bcProcessor->clone(kernel));
+ kernel->setWithForcing(withForcing);
+ kernel->setForcingX1(muForcingX1);
+ kernel->setForcingX2(muForcingX2);
+ kernel->setForcingX3(muForcingX3);
+ kernel->setIndex(ix1, ix2, ix3);
+ kernel->setDeltaT(deltaT);
+ kernel->setBlock(block.lock());
+
+ return kernel;
+}
+//////////////////////////////////////////////////////////////////////////
+void CumulantK17LBMKernelUnified::calculate(int step)
+{
+ //////////////////////////////////////////////////////////////////////////
+ //! Cumulant K17 Kernel is based on
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+ //! and
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.07.004"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.07.004 ]</b></a>
+ //!
+ //! The cumulant kernel is executed in the following steps
+ //!
+ ////////////////////////////////////////////////////////////////////////////////
+ //! - Get node index coordinates from thredIdx, blockIdx, blockDim and gridDim.
+ //!
+
+ using namespace std;
+
+ //initializing of forcing stuff
+ if (withForcing)
+ {
+ muForcingX1.DefineVar("x1", &muX1); muForcingX1.DefineVar("x2", &muX2); muForcingX1.DefineVar("x3", &muX3);
+ muForcingX2.DefineVar("x1", &muX1); muForcingX2.DefineVar("x2", &muX2); muForcingX2.DefineVar("x3", &muX3);
+ muForcingX3.DefineVar("x1", &muX1); muForcingX3.DefineVar("x2", &muX2); muForcingX3.DefineVar("x3", &muX3);
+
+ muDeltaT = deltaT;
+
+ muForcingX1.DefineVar("dt", &muDeltaT);
+ muForcingX2.DefineVar("dt", &muDeltaT);
+ muForcingX3.DefineVar("dt", &muDeltaT);
+
+ muNu = (1.0 / 3.0) * (1.0 / collFactor - 1.0 / 2.0);
+
+ muForcingX1.DefineVar("nu", &muNu);
+ muForcingX2.DefineVar("nu", &muNu);
+ muForcingX3.DefineVar("nu", &muNu);
+ }
+ /////////////////////////////////////
+
+ localDistributions = dynamic_pointer_cast<D3Q27EsoTwist3DSplittedVector>(dataSet->getFdistributions())->getLocalDistributions();
+ nonLocalDistributions = dynamic_pointer_cast<D3Q27EsoTwist3DSplittedVector>(dataSet->getFdistributions())->getNonLocalDistributions();
+ restDistributions = dynamic_pointer_cast<D3Q27EsoTwist3DSplittedVector>(dataSet->getFdistributions())->getZeroDistributions();
+
+ SPtr<BCArray3D> bcArray = this->getBCProcessor()->getBCArray();
+
+ const int bcArrayMaxX1 = (int)bcArray->getNX1();
+ const int bcArrayMaxX2 = (int)bcArray->getNX2();
+ const int bcArrayMaxX3 = (int)bcArray->getNX3();
+
+ int minX1 = ghostLayerWidth;
+ int minX2 = ghostLayerWidth;
+ int minX3 = ghostLayerWidth;
+ int maxX1 = bcArrayMaxX1 - ghostLayerWidth;
+ int maxX2 = bcArrayMaxX2 - ghostLayerWidth;
+ int maxX3 = bcArrayMaxX3 - ghostLayerWidth;
+
+ LBMReal omega = collFactor;
+
+ for (int x3 = minX3; x3 < maxX3; x3++)
+ {
+ for (int x2 = minX2; x2 < maxX2; x2++)
+ {
+ for (int x1 = minX1; x1 < maxX1; x1++)
+ {
+ if (!bcArray->isSolid(x1, x2, x3) && !bcArray->isUndefined(x1, x2, x3))
+ {
+ int x1p = x1 + 1;
+ int x2p = x2 + 1;
+ int x3p = x3 + 1;
+ //////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////
+ //! - Read distributions: style of reading and writing the distributions from/to stored arrays dependent on timestep is based on the esoteric twist algorithm
+ //! <a href="https://doi.org/10.3390/computation5020019"><b>[ M. Geier et al. (2017), DOI:10.3390/computation5020019 ]</b></a>
+ //!
+ ////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////
+
+ //E N T
+ //c c c
+ //////////
+ //W S B
+ //a a a
+
+ //Rest is b
+
+ //mfxyz
+ //a - negative
+ //b - null
+ //c - positive
+
+ // a b c
+ //-1 0 1
+
+ LBMReal mfcbb = (*this->localDistributions)(D3Q27System::ET_E, x1, x2, x3);
+ LBMReal mfbcb = (*this->localDistributions)(D3Q27System::ET_N, x1, x2, x3);
+ LBMReal mfbbc = (*this->localDistributions)(D3Q27System::ET_T, x1, x2, x3);
+ LBMReal mfccb = (*this->localDistributions)(D3Q27System::ET_NE, x1, x2, x3);
+ LBMReal mfacb = (*this->localDistributions)(D3Q27System::ET_NW, x1p, x2, x3);
+ LBMReal mfcbc = (*this->localDistributions)(D3Q27System::ET_TE, x1, x2, x3);
+ LBMReal mfabc = (*this->localDistributions)(D3Q27System::ET_TW, x1p, x2, x3);
+ LBMReal mfbcc = (*this->localDistributions)(D3Q27System::ET_TN, x1, x2, x3);
+ LBMReal mfbac = (*this->localDistributions)(D3Q27System::ET_TS, x1, x2p, x3);
+ LBMReal mfccc = (*this->localDistributions)(D3Q27System::ET_TNE, x1, x2, x3);
+ LBMReal mfacc = (*this->localDistributions)(D3Q27System::ET_TNW, x1p, x2, x3);
+ LBMReal mfcac = (*this->localDistributions)(D3Q27System::ET_TSE, x1, x2p, x3);
+ LBMReal mfaac = (*this->localDistributions)(D3Q27System::ET_TSW, x1p, x2p, x3);
+
+ LBMReal mfabb = (*this->nonLocalDistributions)(D3Q27System::ET_W, x1p, x2, x3);
+ LBMReal mfbab = (*this->nonLocalDistributions)(D3Q27System::ET_S, x1, x2p, x3);
+ LBMReal mfbba = (*this->nonLocalDistributions)(D3Q27System::ET_B, x1, x2, x3p);
+ LBMReal mfaab = (*this->nonLocalDistributions)(D3Q27System::ET_SW, x1p, x2p, x3);
+ LBMReal mfcab = (*this->nonLocalDistributions)(D3Q27System::ET_SE, x1, x2p, x3);
+ LBMReal mfaba = (*this->nonLocalDistributions)(D3Q27System::ET_BW, x1p, x2, x3p);
+ LBMReal mfcba = (*this->nonLocalDistributions)(D3Q27System::ET_BE, x1, x2, x3p);
+ LBMReal mfbaa = (*this->nonLocalDistributions)(D3Q27System::ET_BS, x1, x2p, x3p);
+ LBMReal mfbca = (*this->nonLocalDistributions)(D3Q27System::ET_BN, x1, x2, x3p);
+ LBMReal mfaaa = (*this->nonLocalDistributions)(D3Q27System::ET_BSW, x1p, x2p, x3p);
+ LBMReal mfcaa = (*this->nonLocalDistributions)(D3Q27System::ET_BSE, x1, x2p, x3p);
+ LBMReal mfaca = (*this->nonLocalDistributions)(D3Q27System::ET_BNW, x1p, x2, x3p);
+ LBMReal mfcca = (*this->nonLocalDistributions)(D3Q27System::ET_BNE, x1, x2, x3p);
+
+ LBMReal mfbbb = (*this->restDistributions)(x1, x2, x3);
+
+
+ LBMReal forces[3] = {0., 0., 0.};
+ if (withForcing)
+ {
+ muX1 = static_cast<double>(x1 - 1 + ix1 * maxX1);
+ muX2 = static_cast<double>(x2 - 1 + ix2 * maxX2);
+ muX3 = static_cast<double>(x3 - 1 + ix3 * maxX3);
+
+ forcingX1 = muForcingX1.Eval();
+ forcingX2 = muForcingX2.Eval();
+ forcingX3 = muForcingX3.Eval();
+
+ forces[0] = forcingX1 * deltaT;
+ forces[1] = forcingX2 * deltaT;
+ forces[2] = forcingX3 * deltaT;
+ }
+
+ vf::lbm::Distribution27 distribution;
+
+ distribution.f[vf::lbm::dir::PZZ] = mfcbb;
+ distribution.f[vf::lbm::dir::MZZ] = mfabb;
+ distribution.f[vf::lbm::dir::ZPZ] = mfbcb;
+ distribution.f[vf::lbm::dir::ZMZ] = mfbab;
+ distribution.f[vf::lbm::dir::ZZP] = mfbbc;
+ distribution.f[vf::lbm::dir::ZZM] = mfbba;
+ distribution.f[vf::lbm::dir::PPZ] = mfccb;
+ distribution.f[vf::lbm::dir::MMZ] = mfaab;
+ distribution.f[vf::lbm::dir::PMZ] = mfcab;
+ distribution.f[vf::lbm::dir::MPZ] = mfacb;
+ distribution.f[vf::lbm::dir::PZP] = mfcbc;
+ distribution.f[vf::lbm::dir::MZM] = mfaba;
+ distribution.f[vf::lbm::dir::PZM] = mfcba;
+ distribution.f[vf::lbm::dir::MZP] = mfabc;
+ distribution.f[vf::lbm::dir::ZPP] = mfbcc;
+ distribution.f[vf::lbm::dir::ZMM] = mfbaa;
+ distribution.f[vf::lbm::dir::ZPM] = mfbca;
+ distribution.f[vf::lbm::dir::ZMP] = mfbac;
+ distribution.f[vf::lbm::dir::PPP] = mfccc;
+ distribution.f[vf::lbm::dir::MPP] = mfacc;
+ distribution.f[vf::lbm::dir::PMP] = mfcac;
+ distribution.f[vf::lbm::dir::MMP] = mfaac;
+ distribution.f[vf::lbm::dir::PPM] = mfcca;
+ distribution.f[vf::lbm::dir::MPM] = mfaca;
+ distribution.f[vf::lbm::dir::PMM] = mfcaa;
+ distribution.f[vf::lbm::dir::MMM] = mfaaa;
+ distribution.f[vf::lbm::dir::ZZZ] = mfbbb;
+
+ vf::lbm::KernelParameter parameter {distribution, omega, forces};
+ vf::lbm::cumulantChimera(parameter, vf::lbm::setRelaxationRatesK17);
+
+ mfcbb = distribution.f[vf::lbm::dir::PZZ];
+ mfabb = distribution.f[vf::lbm::dir::MZZ];
+ mfbcb = distribution.f[vf::lbm::dir::ZPZ];
+ mfbab = distribution.f[vf::lbm::dir::ZMZ];
+ mfbbc = distribution.f[vf::lbm::dir::ZZP];
+ mfbba = distribution.f[vf::lbm::dir::ZZM];
+ mfccb = distribution.f[vf::lbm::dir::PPZ];
+ mfaab = distribution.f[vf::lbm::dir::MMZ];
+ mfcab = distribution.f[vf::lbm::dir::PMZ];
+ mfacb = distribution.f[vf::lbm::dir::MPZ];
+ mfcbc = distribution.f[vf::lbm::dir::PZP];
+ mfaba = distribution.f[vf::lbm::dir::MZM];
+ mfcba = distribution.f[vf::lbm::dir::PZM];
+ mfabc = distribution.f[vf::lbm::dir::MZP];
+ mfbcc = distribution.f[vf::lbm::dir::ZPP];
+ mfbaa = distribution.f[vf::lbm::dir::ZMM];
+ mfbca = distribution.f[vf::lbm::dir::ZPM];
+ mfbac = distribution.f[vf::lbm::dir::ZMP];
+ mfccc = distribution.f[vf::lbm::dir::PPP];
+ mfacc = distribution.f[vf::lbm::dir::MPP];
+ mfcac = distribution.f[vf::lbm::dir::PMP];
+ mfaac = distribution.f[vf::lbm::dir::MMP];
+ mfcca = distribution.f[vf::lbm::dir::PPM];
+ mfaca = distribution.f[vf::lbm::dir::MPM];
+ mfcaa = distribution.f[vf::lbm::dir::PMM];
+ mfaaa = distribution.f[vf::lbm::dir::MMM];
+ mfbbb = distribution.f[vf::lbm::dir::ZZZ];
+
+ //////////////////////////////////////////////////////////////////////////
+ //proof correctness
+ //////////////////////////////////////////////////////////////////////////
+#ifdef PROOF_CORRECTNESS
+ LBMReal drho_post = (mfaaa + mfaac + mfaca + mfcaa + mfacc + mfcac + mfccc + mfcca)
+ + (mfaab + mfacb + mfcab + mfccb) + (mfaba + mfabc + mfcba + mfcbc) + (mfbaa + mfbac + mfbca + mfbcc)
+ + (mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc) + mfbbb;
+ LBMReal dif = distribution.getDensity_() - drho_post;
+#ifdef SINGLEPRECISION
+ if (dif > 10.0E-7 || dif < -10.0E-7)
+#else
+ if (dif > 10.0E-15 || dif < -10.0E-15)
+#endif
+ {
+ UB_THROW(UbException(UB_EXARGS, "rho=" + UbSystem::toString(distribution.getDensity_()) + ", rho_post=" + UbSystem::toString(drho_post)
+ + " dif=" + UbSystem::toString(dif)
+ + " rho is not correct for node " + UbSystem::toString(x1) + "," + UbSystem::toString(x2) + "," + UbSystem::toString(x3)
+ + " in " + block.lock()->toString() + " step = " + UbSystem::toString(step)));
+ }
+#endif
+
+ (*this->localDistributions)(D3Q27System::ET_E, x1, x2, x3) = mfcbb;
+ (*this->localDistributions)(D3Q27System::ET_N, x1, x2, x3) = mfbcb;
+ (*this->localDistributions)(D3Q27System::ET_T, x1, x2, x3) = mfbbc;
+ (*this->localDistributions)(D3Q27System::ET_NE, x1, x2, x3) = mfccb;
+ (*this->localDistributions)(D3Q27System::ET_NW, x1p, x2, x3) = mfacb;
+ (*this->localDistributions)(D3Q27System::ET_TE, x1, x2, x3) = mfcbc;
+ (*this->localDistributions)(D3Q27System::ET_TW, x1p, x2, x3) = mfabc;
+ (*this->localDistributions)(D3Q27System::ET_TN, x1, x2, x3) = mfbcc;
+ (*this->localDistributions)(D3Q27System::ET_TS, x1, x2p, x3) = mfbac;
+ (*this->localDistributions)(D3Q27System::ET_TNE, x1, x2, x3) = mfccc;
+ (*this->localDistributions)(D3Q27System::ET_TNW, x1p, x2, x3) = mfacc;
+ (*this->localDistributions)(D3Q27System::ET_TSE, x1, x2p, x3) = mfcac;
+ (*this->localDistributions)(D3Q27System::ET_TSW, x1p, x2p, x3) = mfaac;
+
+ (*this->nonLocalDistributions)(D3Q27System::ET_W, x1p, x2, x3) = mfabb;
+ (*this->nonLocalDistributions)(D3Q27System::ET_S, x1, x2p, x3) = mfbab;
+ (*this->nonLocalDistributions)(D3Q27System::ET_B, x1, x2, x3p) = mfbba;
+ (*this->nonLocalDistributions)(D3Q27System::ET_SW, x1p, x2p, x3) = mfaab;
+ (*this->nonLocalDistributions)(D3Q27System::ET_SE, x1, x2p, x3) = mfcab;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BW, x1p, x2, x3p) = mfaba;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BE, x1, x2, x3p) = mfcba;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BS, x1, x2p, x3p) = mfbaa;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BN, x1, x2, x3p) = mfbca;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BSW, x1p, x2p, x3p) = mfaaa;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BSE, x1, x2p, x3p) = mfcaa;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BNW, x1p, x2, x3p) = mfaca;
+ (*this->nonLocalDistributions)(D3Q27System::ET_BNE, x1, x2, x3p) = mfcca;
+ (*this->restDistributions)(x1, x2, x3) = mfbbb;
+ //////////////////////////////////////////////////////////////////////////
+
+ }
+ }
+ }
+ }
+}
+//////////////////////////////////////////////////////////////////////////
+
diff --git a/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.h b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.h
new file mode 100644
index 0000000000000000000000000000000000000000..175fdd4cba2a0c8ce47248f5de6672f34dda0cc3
--- /dev/null
+++ b/src/cpu/VirtualFluidsCore/LBM/CumulantK17LBMKernelUnified.h
@@ -0,0 +1,77 @@
+//=======================================================================================
+// ____ ____ __ ______ __________ __ __ __ __
+// \ \ | | | | | _ \ |___ ___| | | | | / \ | |
+// \ \ | | | | | |_) | | | | | | | / \ | |
+// \ \ | | | | | _ / | | | | | | / /\ \ | |
+// \ \ | | | | | | \ \ | | | \__/ | / ____ \ | |____
+// \ \ | | |__| |__| \__\ |__| \________/ /__/ \__\ |_______|
+// \ \ | | ________________________________________________________________
+// \ \ | | | ______________________________________________________________|
+// \ \| | | | __ __ __ __ ______ _______
+// \ | | |_____ | | | | | | | | | _ \ / _____)
+// \ | | _____| | | | | | | | | | | \ \ \_______
+// \ | | | | |_____ | \_/ | | | | |_/ / _____ |
+// \ _____| |__| |________| \_______/ |__| |______/ (_______/
+//
+// This file is part of VirtualFluids. VirtualFluids is free software: you can
+// redistribute it and/or modify it under the terms of the GNU General Public
+// License as published by the Free Software Foundation, either version 3 of
+// the License, or (at your option) any later version.
+//
+// VirtualFluids is distributed in the hope that it will be useful, but WITHOUT
+// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+// for more details.
+//
+// You should have received a copy of the GNU General Public License along
+// with VirtualFluids (see COPYING.txt). If not, see <http://www.gnu.org/licenses/>.
+//
+//! \file CumulantK17LBMKernel.h
+//! \ingroup LBM
+//! \author Konstantin Kutscher, Martin Geier
+//=======================================================================================
+
+#ifndef CumulantK17LBMKernelUnified_h__
+#define CumulantK17LBMKernelUnified_h__
+
+#include "LBMKernel.h"
+#include "BCProcessor.h"
+#include "D3Q27System.h"
+#include "basics/utilities/UbTiming.h"
+#include "basics/container/CbArray4D.h"
+#include "basics/container/CbArray3D.h"
+
+//! \brief Compressible cumulant LBM kernel.
+//! \details LBM implementation that use Cascaded Cumulant Lattice Boltzmann method for D3Q27 model
+//!
+//! The model is publisched in
+//! <a href="http://dx.doi.org/10.1016/j.jcp.2017.05.040"><b>[ Geier et al., (2017), 10.1016/j.jcp.2017.05.040]</b></a>,
+//! <a href="http://dx.doi.org/10.1016/j.jcp.2017.07.004"><b>[ Geier et al., (2017), 10.1016/j.jcp.2017.07.004]</b></a>
+//!
+class CumulantK17LBMKernelUnified : public LBMKernel
+{
+public:
+ CumulantK17LBMKernelUnified();
+ ~CumulantK17LBMKernelUnified() = default;
+ void calculate(int step) override;
+ SPtr<LBMKernel> clone() override;
+ double getCalculationTime() override { return .0; }
+
+protected:
+ virtual void initDataSet();
+ LBMReal f[D3Q27System::ENDF + 1];
+
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr localDistributions;
+ CbArray4D<LBMReal, IndexerX4X3X2X1>::CbArray4DPtr nonLocalDistributions;
+ CbArray3D<LBMReal, IndexerX3X2X1>::CbArray3DPtr restDistributions;
+
+ mu::value_type muX1, muX2, muX3;
+ mu::value_type muDeltaT;
+ mu::value_type muNu;
+ LBMReal forcingX1;
+ LBMReal forcingX2;
+ LBMReal forcingX3;
+};
+
+
+#endif // CumulantK17LBMKernel_h__
\ No newline at end of file
diff --git a/src/cpu/VirtualFluidsCore/LBM/D3Q27System.cpp b/src/cpu/VirtualFluidsCore/LBM/D3Q27System.cpp
index 5e88242fa23bdf37386f4f4d293ed7c2c33750ee..105603b35d043799672a58fda83ba503af70b703 100644
--- a/src/cpu/VirtualFluidsCore/LBM/D3Q27System.cpp
+++ b/src/cpu/VirtualFluidsCore/LBM/D3Q27System.cpp
@@ -1,5 +1,7 @@
#include "D3Q27System.h"
+#include "lbm/MacroscopicQuantities.h"
+
namespace D3Q27System
{
using namespace UbMath;
@@ -18,4 +20,31 @@ const int INVDIR[] = { INV_E, INV_W, INV_N, INV_S, INV_T, INV_B, INV
INV_NW, INV_TE, INV_BW, INV_BE, INV_TW, INV_TN, INV_BS, INV_BN, INV_TS,
INV_TNE, INV_TNW, INV_TSE, INV_TSW, INV_BNE, INV_BNW, INV_BSE, INV_BSW };
+
+
+
+LBMReal getDensity(const LBMReal *const &f /*[27]*/)
+{
+ return vf::lbm::getDensity(f);
+}
+
+LBMReal getIncompVelocityX1(const LBMReal *const &f /*[27]*/)
+{
+ return vf::lbm::getIncompressibleVelocityX1(f);
+}
+
+LBMReal getIncompVelocityX2(const LBMReal *const &f /*[27]*/)
+{
+ return vf::lbm::getIncompressibleVelocityX2(f);
+}
+
+LBMReal getIncompVelocityX3(const LBMReal *const &f /*[27]*/)
+{
+ return vf::lbm::getIncompressibleVelocityX3(f);
+}
+
+
+
+
+
} // namespace D3Q27System
\ No newline at end of file
diff --git a/src/cpu/VirtualFluidsCore/LBM/D3Q27System.h b/src/cpu/VirtualFluidsCore/LBM/D3Q27System.h
index 8f8c376459ce0b9bd4d0b7691655c173a6d4e149..04fe8a819b143db8cc935fc893faa514805060a6 100644
--- a/src/cpu/VirtualFluidsCore/LBM/D3Q27System.h
+++ b/src/cpu/VirtualFluidsCore/LBM/D3Q27System.h
@@ -42,6 +42,7 @@
#include "UbException.h"
#include "UbMath.h"
+
//! \brief namespace for global system-functions
namespace D3Q27System
{
@@ -147,36 +148,21 @@ static const int ET_BNW = 11;
static const int ET_TSW = 12;
static const int ET_BNE = 12;
+
//////////////////////////////////////////////////////////////////////////
// MACROSCOPIC VALUES
/*=====================================================================*/
-static LBMReal getDensity(const LBMReal *const &f /*[27]*/)
-{
- return ((f[TNE] + f[BSW]) + (f[TSE] + f[BNW])) + ((f[BSE] + f[TNW]) + (f[TSW] + f[BNE])) +
- (((f[NE] + f[SW]) + (f[SE] + f[NW])) + ((f[TE] + f[BW]) + (f[BE] + f[TW])) +
- ((f[BN] + f[TS]) + (f[TN] + f[BS]))) +
- ((f[E] + f[W]) + (f[N] + f[S]) + (f[T] + f[B])) + f[REST];
-}
+LBMReal getDensity(const LBMReal *const &f /*[27]*/);
/*=====================================================================*/
static LBMReal getPressure(const LBMReal *const &f /*[27]*/) { return REAL_CAST(UbMath::c1o3) * getDensity(f); }
/*=====================================================================*/
-static LBMReal getIncompVelocityX1(const LBMReal *const &f /*[27]*/)
-{
- return ((((f[TNE] - f[BSW]) + (f[TSE] - f[BNW])) + ((f[BSE] - f[TNW]) + (f[BNE] - f[TSW]))) +
- (((f[BE] - f[TW]) + (f[TE] - f[BW])) + ((f[SE] - f[NW]) + (f[NE] - f[SW]))) + (f[E] - f[W]));
-}
+LBMReal getIncompVelocityX1(const LBMReal *const &f /*[27]*/);
/*=====================================================================*/
-static LBMReal getIncompVelocityX2(const LBMReal *const &f /*[27]*/)
-{
- return ((((f[TNE] - f[BSW]) + (f[BNW] - f[TSE])) + ((f[TNW] - f[BSE]) + (f[BNE] - f[TSW]))) +
- (((f[BN] - f[TS]) + (f[TN] - f[BS])) + ((f[NW] - f[SE]) + (f[NE] - f[SW]))) + (f[N] - f[S]));
-}
+LBMReal getIncompVelocityX2(const LBMReal *const &f /*[27]*/);
/*=====================================================================*/
-static LBMReal getIncompVelocityX3(const LBMReal *const &f /*[27]*/)
-{
- return ((((f[TNE] - f[BSW]) + (f[TSE] - f[BNW])) + ((f[TNW] - f[BSE]) + (f[TSW] - f[BNE]))) +
- (((f[TS] - f[BN]) + (f[TN] - f[BS])) + ((f[TW] - f[BE]) + (f[TE] - f[BW]))) + (f[T] - f[B]));
-}
+LBMReal getIncompVelocityX3(const LBMReal *const &f /*[27]*/);
+
+
/*=====================================================================*/
static void calcDensity(const LBMReal *const &f /*[27]*/, LBMReal &rho)
{
diff --git a/src/cpu/VirtualFluidsCore/LBM/ILBMKernel.h b/src/cpu/VirtualFluidsCore/LBM/ILBMKernel.h
index 4dbe8eee09a37c0c220f47619b72bade2e6ec527..bde61d9d314b61327ff8f8a2a71d2864d50cc7f5 100644
--- a/src/cpu/VirtualFluidsCore/LBM/ILBMKernel.h
+++ b/src/cpu/VirtualFluidsCore/LBM/ILBMKernel.h
@@ -36,6 +36,8 @@
#include <PointerDefinitions.h>
+#include "LBMSystem.h"
+
class BCProcessor;
class DataSet3D;
@@ -57,7 +59,7 @@ public:
virtual void setCollisionFactor(double collFactor) = 0;
virtual bool isInsideOfDomain(const int &x1, const int &x2, const int &x3) const = 0;
virtual int getGhostLayerWidth() const = 0;
- virtual double getDeltaT() const = 0;
+ virtual LBMReal getDeltaT() const = 0;
virtual bool getWithForcing() const = 0;
};
diff --git a/src/cpu/VirtualFluidsCore/LBM/LBMKernel.cpp b/src/cpu/VirtualFluidsCore/LBM/LBMKernel.cpp
index f3d168733db86ea03a72a9741ba819ed6874a0c1..fa0fd08c9ac1da11483dad6061c96fd3672ad3a4 100644
--- a/src/cpu/VirtualFluidsCore/LBM/LBMKernel.cpp
+++ b/src/cpu/VirtualFluidsCore/LBM/LBMKernel.cpp
@@ -201,13 +201,13 @@ void LBMKernel::setDensityRatio(double densityRatio) { this->densityRatio = dens
//////////////////////////////////////////////////////////////////////////
double LBMKernel::getDensityRatio() const { return densityRatio; }
//////////////////////////////////////////////////////////////////////////
-void LBMKernel::setMultiphaseModelParameters(double beta, double kappa)
+void LBMKernel::setMultiphaseModelParameters(LBMReal beta, LBMReal kappa)
{
this->beta = beta;
this->kappa = kappa;
}
//////////////////////////////////////////////////////////////////////////
-void LBMKernel::getMultiphaseModelParameters(double &beta, double &kappa)
+void LBMKernel::getMultiphaseModelParameters(LBMReal &beta, LBMReal &kappa)
{
beta = this->beta;
kappa = this->kappa;
diff --git a/src/cpu/VirtualFluidsCore/LBM/LBMKernel.h b/src/cpu/VirtualFluidsCore/LBM/LBMKernel.h
index 5c3e067656e2fc5cb06046e28c0442b15c180050..5e211f87b3c5170589838bd71f8f7c22c2d4a431 100644
--- a/src/cpu/VirtualFluidsCore/LBM/LBMKernel.h
+++ b/src/cpu/VirtualFluidsCore/LBM/LBMKernel.h
@@ -53,6 +53,7 @@ public:
public:
LBMKernel();
+ virtual ~LBMKernel() = default;
virtual SPtr<LBMKernel> clone() = 0;
@@ -117,8 +118,8 @@ public:
double getCollisionFactorG() const;
void setDensityRatio(double densityRatio);
double getDensityRatio() const;
- void setMultiphaseModelParameters(double beta, double kappa);
- void getMultiphaseModelParameters(double &beta, double &kappa);
+ void setMultiphaseModelParameters(LBMReal beta, LBMReal kappa);
+ void getMultiphaseModelParameters(LBMReal &beta, LBMReal &kappa);
void setContactAngle(double contactAngle);
double getContactAngle() const;
void setPhiL(double phiL);
diff --git a/src/cpu/VirtualFluidsCore/LBM/LBMSystem.h b/src/cpu/VirtualFluidsCore/LBM/LBMSystem.h
index d24775aef0fbe6822fbdc03d42e2acfeb3021430..14b4d223b2e07e3dbca9947cefd89de045bfb3cf 100644
--- a/src/cpu/VirtualFluidsCore/LBM/LBMSystem.h
+++ b/src/cpu/VirtualFluidsCore/LBM/LBMSystem.h
@@ -37,6 +37,8 @@
#include <iostream>
#include <string>
+#include "basics/Core/DataTypes.h"
+
//! \brief namespace for global system-functions
namespace LBMSystem
@@ -45,10 +47,10 @@ namespace LBMSystem
//#define SINGLEPRECISION
#ifdef SINGLEPRECISION
-typedef float real;
+//using real = float;
#define REAL_CAST(x) ((LBMSystem::real)(x))
#else
-using real = double;
+//using real = double;
#define REAL_CAST(x) (x)
#endif
@@ -82,6 +84,7 @@ static real calcOmega2(real viscosity, real deltaT) { return REAL_CAST(1.0 / (4.
} // namespace LBMSystem
// some typedefs for global namespace
-using LBMReal = LBMSystem::real;
+//using LBMReal = LBMSystem::real;
+using LBMReal = real;
#endif
diff --git a/src/cpu/VirtualFluidsCore/Parallel/MPICommunicator.h b/src/cpu/VirtualFluidsCore/Parallel/MPICommunicator.h
index 3c25cc78f74e7a4efbca436bc0dc07b62ce4fa6e..cd63d8f1db9e27ab3572a26693355c88a303104f 100644
--- a/src/cpu/VirtualFluidsCore/Parallel/MPICommunicator.h
+++ b/src/cpu/VirtualFluidsCore/Parallel/MPICommunicator.h
@@ -19,7 +19,7 @@ class MPICommunicator : public Communicator
{
private:
MPICommunicator();
- MPICommunicator(const MPICommunicator &) {}
+ MPICommunicator(const MPICommunicator &) = default;
public:
~MPICommunicator() override;
diff --git a/src/cpu/VirtualFluidsCore/Parallel/MPIIODataStructures.h b/src/cpu/VirtualFluidsCore/Parallel/MPIIODataStructures.h
index 8b284fc2f768472a4115c61cd567ce0b37b7f4e9..c8bd2d0797af86858b40a1a29a154107f04e46c8 100644
--- a/src/cpu/VirtualFluidsCore/Parallel/MPIIODataStructures.h
+++ b/src/cpu/VirtualFluidsCore/Parallel/MPIIODataStructures.h
@@ -59,6 +59,9 @@ struct dataSetParam {
struct DataSetRestart {
double collFactor;
double deltaT;
+ double collFactorL; // for Multiphase model
+ double collFactorG; // for Multiphase model
+ double densityRatio;// for Multiphase model
int x1;
int x2;
int x3;
@@ -74,6 +77,9 @@ struct DataSetRestart {
struct DataSetMigration {
double collFactor;
double deltaT;
+ double collFactorL; // for Multiphase model
+ double collFactorG; // for Multiphase model
+ double densityRatio;// for Multiphase model
int globalID;
int ghostLayerWidth;
bool compressible;
@@ -164,7 +170,8 @@ struct DSArraysPresence {
bool isAverageTripleArrayPresent;
bool isShearStressValArrayPresent;
bool isRelaxationFactorPresent;
- bool isPhaseFieldPresent;
+ bool isPhaseField1Present;
+ bool isPhaseField2Present;
};
} // namespace MPIIODataStructures
#endif
\ No newline at end of file
diff --git a/src/cpu/VirtualFluidsCore/Utilities/CheckpointConverter.cpp b/src/cpu/VirtualFluidsCore/Utilities/CheckpointConverter.cpp
index 914659afa685814842904e9622c31b875d6a2207..b66eff480e99102edf332cfd750e0d2b6965ba83 100644
--- a/src/cpu/VirtualFluidsCore/Utilities/CheckpointConverter.cpp
+++ b/src/cpu/VirtualFluidsCore/Utilities/CheckpointConverter.cpp
@@ -77,7 +77,7 @@ CheckpointConverter::CheckpointConverter(SPtr<Grid3D> grid, const std::string &p
//---------------------------------------
MPI_Datatype typesDataSetRead[3] = { MPI_DOUBLE, MPI_INT, MPI_CHAR };
- int blocksDataSetRead[3] = { 2, 5, 2 };
+ int blocksDataSetRead[3] = { 3, 5, 2 };
MPI_Aint offsetsDataSetRead[3], lbDataSetRead, extentDataSetRead;
offsetsDataSetRead[0] = 0;
@@ -358,6 +358,7 @@ void CheckpointConverter::convertDataSet(int step, int procCount)
dataSetWriteArray[nb].deltaT = dataSetReadArray[nb].deltaT;
dataSetWriteArray[nb].compressible = dataSetReadArray[nb].compressible;
dataSetWriteArray[nb].withForcing = dataSetReadArray[nb].withForcing;
+// dataSetWriteArray[nb].densityRatio = dataSetReadArray[nb].densityRatio;
write_offset = (MPI_Offset)(3 * sizeof(dataSetParam) + dataSetWriteArray[nb].globalID * sizeofOneDataSet);
MPI_File_write_at(file_handlerW, write_offset, &dataSetWriteArray[nb], 1, dataSetTypeWrite,
diff --git a/src/cpu/VirtualFluidsCore/Visitors/BoundaryConditionsBlockVisitor.cpp b/src/cpu/VirtualFluidsCore/Visitors/BoundaryConditionsBlockVisitor.cpp
index b4eafda902448564800bb1479f7ac60f74c4b77d..a6372fc31712899dab0b8edaf919a141663991ca 100644
--- a/src/cpu/VirtualFluidsCore/Visitors/BoundaryConditionsBlockVisitor.cpp
+++ b/src/cpu/VirtualFluidsCore/Visitors/BoundaryConditionsBlockVisitor.cpp
@@ -98,6 +98,7 @@ void BoundaryConditionsBlockVisitor::visit(SPtr<Grid3D> grid, SPtr<Block3D> bloc
if (bca) {
bca = bca->clone();
+ bca->setBlock(block);
bca->setNodeIndex(x1, x2, x3);
bca->setBcPointer(bcPtr);
bca->addDistributions(distributions);
diff --git a/src/cpu/pythonbindings/CMakeLists.txt b/src/cpu/pythonbindings/CMakeLists.txt
index 4c728febe0e669fa308d45158c7fae4ce3762c05..3b4e7e5a1506899710dc03ea275c0d4ac1cff66d 100644
--- a/src/cpu/pythonbindings/CMakeLists.txt
+++ b/src/cpu/pythonbindings/CMakeLists.txt
@@ -12,4 +12,5 @@ target_compile_definitions(pymuparser PRIVATE VF_METIS VF_MPI)
target_link_libraries(pyfluids PRIVATE simulationconfig VirtualFluidsCore muparser basics)
target_link_libraries(pymuparser PRIVATE muparser)
-
+target_include_directories(pyfluids PRIVATE ${CMAKE_SOURCE_DIR}/src/)
+target_include_directories(pyfluids PRIVATE ${CMAKE_BINARY_DIR})
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/VirtualfluidsModule.cpp b/src/cpu/pythonbindings/src/VirtualfluidsModule.cpp
index 61c6005b9fbdd1108d9ffff374763cad95a5c40e..564dc1838d48a92340fa5491779177b299bcb270 100644
--- a/src/cpu/pythonbindings/src/VirtualfluidsModule.cpp
+++ b/src/cpu/pythonbindings/src/VirtualfluidsModule.cpp
@@ -6,14 +6,17 @@
#include "submodules/simulationparameters.cpp"
#include "submodules/writer.cpp"
-namespace py = pybind11;
-
-PYBIND11_MODULE(pyfluids, m)
+namespace py_bindings
{
- makeBoundaryConditionsModule(m);
- makeSimulationModule(m);
- makeGeometryModule(m);
- makeKernelModule(m);
- makeParametersModule(m);
- makeWriterModule(m);
+ namespace py = pybind11;
+
+ PYBIND11_MODULE(pyfluids, m)
+ {
+ boundaryconditions::makeModule(m);
+ simulation::makeModule(m);
+ geometry::makeModule(m);
+ kernel::makeModule(m);
+ parameters::makeModule(m);
+ writer::makeModule(m);
+ }
}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/boundaryconditions.cpp b/src/cpu/pythonbindings/src/submodules/boundaryconditions.cpp
index ef8b923fd9aa2feea9c81da686df38cb891a4f84..3bff7bc069ca20fe1c0cf3d1847b9714e0381505 100644
--- a/src/cpu/pythonbindings/src/submodules/boundaryconditions.cpp
+++ b/src/cpu/pythonbindings/src/submodules/boundaryconditions.cpp
@@ -7,56 +7,58 @@
#include <BoundaryConditions/VelocityBCAdapter.h>
#include <BoundaryConditions/NoSlipBCAlgorithm.h>
#include <BoundaryConditions/VelocityBCAlgorithm.h>
+#include <BoundaryConditions/HighViscosityNoSlipBCAlgorithm.h>
-namespace py = pybind11;
-using namespace py::literals;
+namespace boundaryconditions
+{
+ namespace py = pybind11;
+ using namespace py::literals;
-template<class Adapter>
-using py_bc_class = py::class_<Adapter, BCAdapter, std::shared_ptr<Adapter>>;
+ template<class adapter, class algorithm,
+ class = std::enable_if_t<std::is_base_of<BCAdapter, adapter>::value>,
+ class = std::enable_if_t<std::is_base_of<BCAlgorithm, algorithm>::value>>
+ class PyBoundaryCondition : public adapter
+ {
+ public:
+ template<typename ...Args>
+ PyBoundaryCondition(Args &&... args) : adapter(std::forward<Args>(args)...)
+ {
+ this->setBcAlgorithm(std::make_shared<algorithm>());
+ }
+ };
-template<class Adapter, class Algorithm, typename ...Args>
-std::shared_ptr<Adapter> create(Args... args)
-{
- auto adapter = std::make_shared<Adapter>(args...);
- adapter->setBcAlgorithm(std::make_shared<Algorithm>());
- return adapter;
-}
+ template<class adapter, class algorithm>
+ using bc_class = py::class_<PyBoundaryCondition<adapter, algorithm>, BCAdapter,
+ std::shared_ptr<PyBoundaryCondition<adapter, algorithm>>>;
-template<class Algorithm>
-void add_constructors_to_velocity_bc(py_bc_class<VelocityBCAdapter> &cls)
-{
- auto firstConstructor = &create<VelocityBCAdapter, Algorithm, bool &, bool &, bool &, mu::Parser &, double &, double &>;
- auto secondConstructor = &create<VelocityBCAdapter, Algorithm,
- bool &, bool &, bool &, mu::Parser &, mu::Parser &, mu::Parser &, double &, double &>;
- auto thirdConstructor = &create<VelocityBCAdapter, Algorithm,
- double &, double &, double &, double &, double &, double &, double &, double &, double &>;
-
- cls.def(py::init(&create<VelocityBCAdapter, Algorithm>))
- .def(py::init(firstConstructor),
- "vx1"_a, "vx2"_a, "vx3"_a, "function"_a, "start_time"_a, "end_time"_a)
- .def(py::init(secondConstructor),
- "vx1"_a, "vx2"_a, "vx3"_a,
- "function_vx1"_a, "function_vx2"_a, "function_vx2"_a,
- "start_time"_a, "end_time"_a)
- .def(py::init(thirdConstructor),
- "vx1"_a, "vx1_start_time"_a, "vx1_end_time"_a,
- "vx2"_a, "vx2_start_time"_a, "vx2_end_time"_a,
- "vx3"_a, "vx3_start_time"_a, "vx3_end_time"_a);
-}
-
-void makeBoundaryConditionsModule(py::module_ &parentModule)
-{
- py::module_ bcModule = parentModule.def_submodule("boundaryconditions");
+ void makeModule(py::module_ &parentModule)
+ {
+ py::module_ bcModule = parentModule.def_submodule("boundaryconditions");
+
+ auto _ = py::class_<BCAdapter, std::shared_ptr<BCAdapter>>(bcModule, "BCAdapter");
- py::class_<BCAdapter, std::shared_ptr<BCAdapter>>(bcModule, "BCAdapter");
+ bc_class<NoSlipBCAdapter, NoSlipBCAlgorithm>(bcModule, "NoSlipBoundaryCondition")
+ .def(py::init());
- py_bc_class<NoSlipBCAdapter>(bcModule, "NoSlipBoundaryCondition")
- .def(py::init(&create<NoSlipBCAdapter, NoSlipBCAlgorithm>));
+ bc_class<NoSlipBCAdapter, HighViscosityNoSlipBCAlgorithm>(bcModule, "HighViscosityNoSlipBoundaryCondition")
+ .def(py::init());
- auto velocityBoundaryCondition = py_bc_class<VelocityBCAdapter>(bcModule, "VelocityBoundaryCondition");
- add_constructors_to_velocity_bc<VelocityBCAlgorithm>(velocityBoundaryCondition);
+ bc_class<VelocityBCAdapter, VelocityBCAlgorithm>(bcModule, "VelocityBoundaryCondition")
+ .def(py::init())
+ .def(py::init<bool &, bool &, bool &, mu::Parser &, double &, double &>(),
+ "vx1"_a, "vx2"_a, "vx3"_a,
+ "function"_a, "start_time"_a, "end_time"_a)
+ .def(py::init<bool &, bool &, bool &, mu::Parser &, mu::Parser &, mu::Parser &, double &, double &>(),
+ "vx1"_a, "vx2"_a, "vx3"_a,
+ "function_vx1"_a, "function_vx2"_a, "function_vx2"_a,
+ "start_time"_a, "end_time"_a)
+ .def(py::init<double &, double &, double &, double &, double &, double &, double &, double &, double &>(),
+ "vx1"_a, "vx1_start_time"_a, "vx1_end_time"_a,
+ "vx2"_a, "vx2_start_time"_a, "vx2_end_time"_a,
+ "vx3"_a, "vx3_start_time"_a, "vx3_end_time"_a);
- py_bc_class<DensityBCAdapter>(bcModule, "DensityBoundaryCondition")
- .def(py::init(&create<DensityBCAdapter, NonReflectingOutflowBCAlgorithm>));
-}
+ bc_class<DensityBCAdapter, NonReflectingOutflowBCAlgorithm>(bcModule, "NonReflectingOutflow")
+ .def(py::init());
+ }
+}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/geometry.cpp b/src/cpu/pythonbindings/src/submodules/geometry.cpp
index 884ced7b92ddae8a30a8f482e4b22dcbfa37beec..b7ff4dd761258d41687589d2dd89c3479093753e 100644
--- a/src/cpu/pythonbindings/src/submodules/geometry.cpp
+++ b/src/cpu/pythonbindings/src/submodules/geometry.cpp
@@ -5,76 +5,80 @@
#include <geometry3d/GbLine3D.h>
#include <Interactors/Interactor3D.h>
-namespace py = pybind11;
-template<class GeoObject>
-using py_geometry = py::class_<GeoObject, GbObject3D, std::shared_ptr<GeoObject>>;
-
-std::string GbPoint3D_repr_(const GbPoint3D &instance)
+namespace geometry
{
- std::ostringstream stream;
- stream << "<GbPoint3D"
- << " x1: " << instance.getX1Coordinate()
- << " x2: " << instance.getX2Coordinate()
- << " x3: " << instance.getX3Coordinate() << ">";
+ namespace py = pybind11;
- return stream.str();
-}
+ template<class GeoObject>
+ using py_geometry = py::class_<GeoObject, GbObject3D, std::shared_ptr<GeoObject>>;
-void makeGeometryModule(py::module_ &parentModule)
-{
- py::module geometry = parentModule.def_submodule("geometry");
+ std::string GbPoint3D_repr_(const GbPoint3D &instance)
+ {
+ std::ostringstream stream;
+ stream << "<GbPoint3D"
+ << " x1: " << instance.getX1Coordinate()
+ << " x2: " << instance.getX2Coordinate()
+ << " x3: " << instance.getX3Coordinate() << ">";
+
+ return stream.str();
+ }
+
+ void makeModule(py::module_ &parentModule)
+ {
+ py::module geometry = parentModule.def_submodule("geometry");
+
+ py::class_<GbObject3D, std::shared_ptr<GbObject3D>>(geometry, "GbObject3D");
- py::class_<GbObject3D, std::shared_ptr<GbObject3D>>(geometry, "GbObject3D");
+ py_geometry<GbPoint3D>(geometry, "GbPoint3D")
+ .def(py::init())
+ .def(py::init<double &, double &, double &>())
+ .def(py::init<GbPoint3D *>())
+ .def_property("x1", &GbPoint3D::getX1Coordinate, &GbPoint3D::setX1)
+ .def_property("x2", &GbPoint3D::getX2Coordinate, &GbPoint3D::setX2)
+ .def_property("x3", &GbPoint3D::getX3Coordinate, &GbPoint3D::setX3)
+ .def("get_distance", &GbPoint3D::getDistance)
+ .def("__repr__", &GbPoint3D_repr_);
- py_geometry<GbPoint3D>(geometry, "GbPoint3D")
- .def(py::init())
- .def(py::init<double &, double &, double &>())
- .def(py::init<GbPoint3D *>())
- .def_property("x1", &GbPoint3D::getX1Coordinate, &GbPoint3D::setX1)
- .def_property("x2", &GbPoint3D::getX2Coordinate, &GbPoint3D::setX2)
- .def_property("x3", &GbPoint3D::getX3Coordinate, &GbPoint3D::setX3)
- .def("get_distance", &GbPoint3D::getDistance)
- .def("__repr__", [&](const GbPoint3D &instance)
- { return GbPoint3D_repr_(instance); });
+ py_geometry<GbCuboid3D>(geometry, "GbCuboid3D")
+ .def(py::init())
+ .def(py::init<double &, double &, double &, double &, double &, double &>())
+ .def(py::init<GbPoint3D *, GbPoint3D *>())
+ .def(py::init<GbCuboid3D *>())
+ .def_property("point1", &GbCuboid3D::getPoint1, &GbCuboid3D::setPoint1)
+ .def_property("point2", &GbCuboid3D::getPoint2, &GbCuboid3D::setPoint2)
+ .def("__repr__", [&](GbCuboid3D &instance)
+ {
+ std::ostringstream stream;
+ stream << "<GbCuboid3D" << std::endl
+ << "point1: " << GbPoint3D_repr_(instance.getPoint1()) << std::endl
+ << "point2: " << GbPoint3D_repr_(instance.getPoint2()) << ">";
+ return stream.str();
+ });
- py_geometry<GbCuboid3D>(geometry, "GbCuboid3D")
- .def(py::init())
- .def(py::init<double &, double &, double &, double &, double &, double &>())
- .def(py::init<GbPoint3D *, GbPoint3D *>())
- .def(py::init<GbCuboid3D *>())
- .def_property("point1", &GbCuboid3D::getPoint1, &GbCuboid3D::setPoint1)
- .def_property("point2", &GbCuboid3D::getPoint2, &GbCuboid3D::setPoint2)
- .def("__repr__", [&](GbCuboid3D instance)
- {
- std::ostringstream stream;
- stream << "<GbCuboid3D" << std::endl
- << "point1: " << GbPoint3D_repr_(instance.getPoint1()) << std::endl
- << "point2: " << GbPoint3D_repr_(instance.getPoint2()) << ">";
- return stream.str();
- });
+ py_geometry<GbLine3D>(geometry, "GbLine3D")
+ .def(py::init())
+ .def(py::init<GbPoint3D *, GbPoint3D *>())
+ .def(py::init<GbLine3D>())
+ .def_property("point1", &GbLine3D::getPoint1, &GbLine3D::setPoint1)
+ .def_property("point2", &GbLine3D::getPoint2, &GbLine3D::setPoint2)
+ .def("__repr__", [&](GbLine3D &instance)
+ {
+ std::ostringstream stream;
+ stream << "<GbLine3D" << std::endl
+ << "point1: " << GbPoint3D_repr_(instance.getPoint1()) << std::endl
+ << "point2: " << GbPoint3D_repr_(instance.getPoint2()) << ">";
+ return stream.str();
+ });
- py_geometry<GbLine3D>(geometry, "GbLine3D")
- .def(py::init())
- .def(py::init<GbPoint3D *, GbPoint3D *>())
- .def(py::init<GbLine3D>())
- .def_property("point1", &GbLine3D::getPoint1, &GbLine3D::setPoint1)
- .def_property("point2", &GbLine3D::getPoint2, &GbLine3D::setPoint2)
- .def("__repr__", [&](GbLine3D instance)
- {
- std::ostringstream stream;
- stream << "<GbLine3D" << std::endl
- << "point1: " << GbPoint3D_repr_(instance.getPoint1()) << std::endl
- << "point2: " << GbPoint3D_repr_(instance.getPoint2()) << ">";
- return stream.str();
- });
+ py::class_<Interactor3D, std::shared_ptr<Interactor3D>>(geometry, "State")
+ .def_readonly_static("SOLID", &Interactor3D::SOLID)
+ .def_readonly_static("INVERSESOLID", &Interactor3D::INVERSESOLID)
+ .def_readonly_static("TIMEDEPENDENT", &Interactor3D::TIMEDEPENDENT)
+ .def_readonly_static("FLUID", &Interactor3D::FLUID)
+ .def_readonly_static("MOVEABLE", &Interactor3D::MOVEABLE)
+ .def_readonly_static("CHANGENOTNECESSARY", &Interactor3D::CHANGENOTNECESSARY);
+ }
- py::class_<Interactor3D, std::shared_ptr<Interactor3D>>(geometry, "State")
- .def_readonly_static("SOLID", &Interactor3D::SOLID)
- .def_readonly_static("INVERSESOLID", &Interactor3D::INVERSESOLID)
- .def_readonly_static("TIMEDEPENDENT", &Interactor3D::TIMEDEPENDENT)
- .def_readonly_static("FLUID", &Interactor3D::FLUID)
- .def_readonly_static("MOVEABLE", &Interactor3D::MOVEABLE)
- .def_readonly_static("CHANGENOTNECESSARY", &Interactor3D::CHANGENOTNECESSARY);
}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/kernel.cpp b/src/cpu/pythonbindings/src/submodules/kernel.cpp
index 0e2e23c8c6a8ff56ea01c277e9825e7eb78c5c02..fb291790632cc2041410f60a14fca8d966283343 100644
--- a/src/cpu/pythonbindings/src/submodules/kernel.cpp
+++ b/src/cpu/pythonbindings/src/submodules/kernel.cpp
@@ -3,39 +3,43 @@
#include <simulationconfig/KernelFactory.h>
#include <simulationconfig/KernelConfigStructs.h>
-
-namespace py = pybind11;
-
-
-void makeKernelModule(py::module_ &parentModule)
+namespace kernel
{
- py::module kernelModule = parentModule.def_submodule("kernel");
-
- py::enum_<KernelFactory::KernelType>(kernelModule, "KernelType")
- .value("BGK", KernelFactory::BGK)
- .value("CompressibleCumulantFourthOrderViscosity",
- KernelFactory::COMPRESSIBLE_CUMULANT_4TH_ORDER_VISCOSITY);
-
-
- py::class_<LBMKernelConfiguration, std::shared_ptr<LBMKernelConfiguration>>(kernelModule, "LBMKernel")
- .def(py::init<KernelFactory::KernelType>())
- .def_readwrite("use_forcing", &LBMKernelConfiguration::useForcing)
- .def_readwrite("forcing_in_x1", &LBMKernelConfiguration::forcingX1)
- .def_readwrite("forcing_in_x2", &LBMKernelConfiguration::forcingX2)
- .def_readwrite("forcing_in_x3", &LBMKernelConfiguration::forcingX3)
- .def("set_forcing", [](LBMKernelConfiguration &kernelConfig, double x1, double x2, double x3) {
- kernelConfig.forcingX1 = x1;
- kernelConfig.forcingX2 = x2;
- kernelConfig.forcingX3 = x3;
- })
- .def("__repr__", [](LBMKernelConfiguration &kernelConfig) {
- std::ostringstream stream;
- stream << "<" << kernelConfig.kernelType << std::endl
- << "Use forcing: " << kernelConfig.useForcing << std::endl
- << "Forcing in x1: " << kernelConfig.forcingX1 << std::endl
- << "Forcing in x2: " << kernelConfig.forcingX2 << std::endl
- << "Forcing in x3: " << kernelConfig.forcingX3 << ">" << std::endl;
+ namespace py = pybind11;
+
+ void makeModule(py::module_ &parentModule)
+ {
+ py::module kernelModule = parentModule.def_submodule("kernel");
+
+ py::enum_<KernelFactory::KernelType>(kernelModule, "KernelType")
+ .value("BGK", KernelFactory::BGK)
+ .value("CompressibleCumulantFourthOrderViscosity",
+ KernelFactory::COMPRESSIBLE_CUMULANT_4TH_ORDER_VISCOSITY);
+
+ py::class_<LBMKernelConfiguration, std::shared_ptr<LBMKernelConfiguration>>(kernelModule, "LBMKernel")
+ .def(py::init<KernelFactory::KernelType>())
+ .def_readwrite("type", &LBMKernelConfiguration::kernelType)
+ .def_readwrite("use_forcing", &LBMKernelConfiguration::useForcing)
+ .def_readwrite("forcing_in_x1", &LBMKernelConfiguration::forcingX1)
+ .def_readwrite("forcing_in_x2", &LBMKernelConfiguration::forcingX2)
+ .def_readwrite("forcing_in_x3", &LBMKernelConfiguration::forcingX3)
+ .def("set_forcing", [](LBMKernelConfiguration &kernelConfig, double x1, double x2, double x3)
+ {
+ kernelConfig.forcingX1 = x1;
+ kernelConfig.forcingX2 = x2;
+ kernelConfig.forcingX3 = x3;
+ })
+ .def("__repr__", [](LBMKernelConfiguration &kernelConfig)
+ {
+ std::ostringstream stream;
+ stream << "<" << kernelConfig.kernelType << std::endl
+ << "Use forcing: " << kernelConfig.useForcing << std::endl
+ << "Forcing in x1: " << kernelConfig.forcingX1 << std::endl
+ << "Forcing in x2: " << kernelConfig.forcingX2 << std::endl
+ << "Forcing in x3: " << kernelConfig.forcingX3 << ">" << std::endl;
+
+ return stream.str();
+ });
+ }
- return stream.str();
- });
}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/simulationconfig.cpp b/src/cpu/pythonbindings/src/submodules/simulationconfig.cpp
index a525691bdf8dd9a4a0a3994b607816fba509c7a5..60af4e36af4dca67e9262dd9f5ee1f46d5b7bb58 100644
--- a/src/cpu/pythonbindings/src/submodules/simulationconfig.cpp
+++ b/src/cpu/pythonbindings/src/submodules/simulationconfig.cpp
@@ -1,18 +1,22 @@
#include <pybind11/pybind11.h>
#include <simulationconfig/Simulation.h>
-namespace py = pybind11;
-
-void makeSimulationModule(py::module_ &parentModule)
+namespace simulation
{
- py::class_<Simulation, std::shared_ptr<Simulation>>(parentModule, "Simulation")
- .def(py::init())
- .def("set_writer", &Simulation::setWriterConfiguration)
- .def("set_grid_parameters", &Simulation::setGridParameters)
- .def("set_physical_parameters", &Simulation::setPhysicalParameters)
- .def("set_runtime_parameters", &Simulation::setRuntimeParameters)
- .def("set_kernel_config", &Simulation::setKernelConfiguration)
- .def("add_object", &Simulation::addObject)
- .def("add_bc_adapter", &Simulation::addBCAdapter)
- .def("run_simulation", &Simulation::run);
+ namespace py = pybind11;
+
+ void makeModule(py::module_ &parentModule)
+ {
+ py::class_<Simulation, std::shared_ptr<Simulation>>(parentModule, "Simulation")
+ .def(py::init())
+ .def("set_writer", &Simulation::setWriterConfiguration)
+ .def("set_grid_parameters", &Simulation::setGridParameters)
+ .def("set_physical_parameters", &Simulation::setPhysicalParameters)
+ .def("set_runtime_parameters", &Simulation::setRuntimeParameters)
+ .def("set_kernel_config", &Simulation::setKernelConfiguration)
+ .def("add_object", &Simulation::addObject)
+ .def("add_bc_adapter", &Simulation::addBCAdapter)
+ .def("run_simulation", &Simulation::run);
+ }
+
}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/simulationparameters.cpp b/src/cpu/pythonbindings/src/submodules/simulationparameters.cpp
index f59d1c0ec0473c537f0cc334044bcd113f822687..acc272f2ee412cfbafd9007b4b18610cfd0a1e9b 100644
--- a/src/cpu/pythonbindings/src/submodules/simulationparameters.cpp
+++ b/src/cpu/pythonbindings/src/submodules/simulationparameters.cpp
@@ -3,54 +3,57 @@
#include <complex>
#include <simulationconfig/SimulationParameters.h>
-namespace py = pybind11;
-
-void makeParametersModule(py::module_ &parentModule)
+namespace parameters
{
- py::module parametersModule = parentModule.def_submodule("parameters");
-
- py::class_<PhysicalParameters, std::shared_ptr<PhysicalParameters>>(parametersModule, "PhysicalParameters")
- .def(py::init())
- .def_readwrite("bulk_viscosity_factor", &PhysicalParameters::bulkViscosityFactor,
- "The viscosity of the fluid will be multiplied with this factor to calculate its bulk viscosity. Default is 1.0")
- .def_readwrite("lattice_viscosity", &PhysicalParameters::latticeViscosity, "Lattice viscosity");
-
- py::class_<GridParameters, std::shared_ptr<GridParameters>>(parametersModule, "GridParameters")
- .def(py::init())
- .def_readwrite("node_distance", &GridParameters::nodeDistance)
- .def_readwrite("reference_direction_index", &GridParameters::referenceDirectionIndex)
- .def_readwrite("number_of_nodes_per_direction", &GridParameters::numberOfNodesPerDirection)
- .def_readwrite("blocks_per_direction", &GridParameters::blocksPerDirection)
- .def_readwrite("periodic_boundary_in_x1", &GridParameters::periodicBoundaryInX1)
- .def_readwrite("periodic_boundary_in_x2", &GridParameters::periodicBoundaryInX2)
- .def_readwrite("periodic_boundary_in_x3", &GridParameters::periodicBoundaryInX3)
- .def_property_readonly("bounding_box", &GridParameters::boundingBox);
-
- py::class_<BoundingBox, std::shared_ptr<BoundingBox>>(parametersModule, "BoundingBox")
- .def_readonly("min_x1", &BoundingBox::minX1)
- .def_readonly("min_x2", &BoundingBox::minX2)
- .def_readonly("min_x3", &BoundingBox::minX3)
- .def_readonly("max_x1", &BoundingBox::maxX1)
- .def_readonly("max_x2", &BoundingBox::maxX2)
- .def_readonly("max_x3", &BoundingBox::maxX3)
- .def("__repr__", [](BoundingBox &self)
- {
- std::ostringstream stream;
- stream << "<BoundingBox" << std::endl
- << "min x1: " << self.minX1 << std::endl
- << "min x2: " << self.minX2 << std::endl
- << "min x3: " << self.minX3 << std::endl
- << "max x1: " << self.maxX1 << std::endl
- << "max x2: " << self.maxX2 << std::endl
- << "max x3: " << self.maxX3 << std::endl << ">";
-
- return stream.str();
- });
-
- py::class_<RuntimeParameters, std::shared_ptr<RuntimeParameters>>(parametersModule, "RuntimeParameters")
- .def(py::init())
- .def_readwrite("number_of_timesteps", &RuntimeParameters::numberOfTimeSteps)
- .def_readwrite("timestep_log_interval", &RuntimeParameters::timeStepLogInterval)
- .def_readwrite("number_of_threads", &RuntimeParameters::numberOfThreads);
-
+ namespace py = pybind11;
+
+ void makeModule(py::module_ &parentModule)
+ {
+ py::module parametersModule = parentModule.def_submodule("parameters");
+
+ py::class_<PhysicalParameters, std::shared_ptr<PhysicalParameters>>(parametersModule, "PhysicalParameters")
+ .def(py::init())
+ .def_readwrite("bulk_viscosity_factor", &PhysicalParameters::bulkViscosityFactor,
+ "The viscosity of the fluid will be multiplied with this factor to calculate its bulk viscosity. Default is 1.0")
+ .def_readwrite("lattice_viscosity", &PhysicalParameters::latticeViscosity, "Lattice viscosity");
+
+ py::class_<GridParameters, std::shared_ptr<GridParameters>>(parametersModule, "GridParameters")
+ .def(py::init())
+ .def_readwrite("node_distance", &GridParameters::nodeDistance)
+ .def_readwrite("reference_direction_index", &GridParameters::referenceDirectionIndex)
+ .def_readwrite("number_of_nodes_per_direction", &GridParameters::numberOfNodesPerDirection)
+ .def_readwrite("blocks_per_direction", &GridParameters::blocksPerDirection)
+ .def_readwrite("periodic_boundary_in_x1", &GridParameters::periodicBoundaryInX1)
+ .def_readwrite("periodic_boundary_in_x2", &GridParameters::periodicBoundaryInX2)
+ .def_readwrite("periodic_boundary_in_x3", &GridParameters::periodicBoundaryInX3)
+ .def_property_readonly("bounding_box", &GridParameters::boundingBox);
+
+ py::class_<BoundingBox, std::shared_ptr<BoundingBox>>(parametersModule, "BoundingBox")
+ .def_readonly("min_x1", &BoundingBox::minX1)
+ .def_readonly("min_x2", &BoundingBox::minX2)
+ .def_readonly("min_x3", &BoundingBox::minX3)
+ .def_readonly("max_x1", &BoundingBox::maxX1)
+ .def_readonly("max_x2", &BoundingBox::maxX2)
+ .def_readonly("max_x3", &BoundingBox::maxX3)
+ .def("__repr__", [](BoundingBox &self)
+ {
+ std::ostringstream stream;
+ stream << "<BoundingBox" << std::endl
+ << "min x1: " << self.minX1 << std::endl
+ << "min x2: " << self.minX2 << std::endl
+ << "min x3: " << self.minX3 << std::endl
+ << "max x1: " << self.maxX1 << std::endl
+ << "max x2: " << self.maxX2 << std::endl
+ << "max x3: " << self.maxX3 << std::endl << ">";
+
+ return stream.str();
+ });
+
+ py::class_<RuntimeParameters, std::shared_ptr<RuntimeParameters>>(parametersModule, "RuntimeParameters")
+ .def(py::init())
+ .def_readwrite("number_of_timesteps", &RuntimeParameters::numberOfTimeSteps)
+ .def_readwrite("timestep_log_interval", &RuntimeParameters::timeStepLogInterval)
+ .def_readwrite("number_of_threads", &RuntimeParameters::numberOfThreads);
+
+ }
}
\ No newline at end of file
diff --git a/src/cpu/pythonbindings/src/submodules/writer.cpp b/src/cpu/pythonbindings/src/submodules/writer.cpp
index 40819e4766eb30a442967067f954fef5508a4707..d5ec527a27caf63d9a3066c51e1f675b307fe0b2 100644
--- a/src/cpu/pythonbindings/src/submodules/writer.cpp
+++ b/src/cpu/pythonbindings/src/submodules/writer.cpp
@@ -1,18 +1,21 @@
#include <pybind11/pybind11.h>
#include <simulationconfig/WriterConfiguration.h>
-namespace py = pybind11;
-
-void makeWriterModule(py::module_ &parentModule)
+namespace writer
{
- py::module writerModule = parentModule.def_submodule("writer");
+ namespace py = pybind11;
+
+ void makeModule(py::module_ &parentModule)
+ {
+ py::module writerModule = parentModule.def_submodule("writer");
- py::enum_<OutputFormat>(writerModule, "OutputFormat")
- .value("ASCII", OutputFormat::ASCII)
- .value("BINARY", OutputFormat::BINARY);
+ py::enum_<OutputFormat>(writerModule, "OutputFormat")
+ .value("ASCII", OutputFormat::ASCII)
+ .value("BINARY", OutputFormat::BINARY);
- py::class_<WriterConfiguration>(writerModule, "Writer")
- .def(py::init())
- .def_readwrite("output_path", &WriterConfiguration::outputPath)
- .def_readwrite("output_format", &WriterConfiguration::outputFormat);
+ py::class_<WriterConfiguration>(writerModule, "Writer")
+ .def(py::init())
+ .def_readwrite("output_path", &WriterConfiguration::outputPath)
+ .def_readwrite("output_format", &WriterConfiguration::outputFormat);
+ }
}
\ No newline at end of file
diff --git a/src/cpu/simulationconfig/CMakeLists.txt b/src/cpu/simulationconfig/CMakeLists.txt
index 2e5e7f2eb9cba467e1ecbe3ec9cea13b3a3f322d..95ee969a049fd65cfadc6cc95d814e788a02aa8e 100644
--- a/src/cpu/simulationconfig/CMakeLists.txt
+++ b/src/cpu/simulationconfig/CMakeLists.txt
@@ -1,20 +1,8 @@
-cmake_minimum_required(VERSION 3.1)
project(simulationconfig)
-set(VFBUILDER_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/include)
-file(GLOB HEADERS
- ${VFBUILDER_INCLUDE_DIR}/simulationconfig/*.h
- ${VFBUILDER_INCLUDE_DIR}/simulationconfig/boundaryconditions/*.h)
+vf_add_library(NAME simulationconfig PUBLIC_LINK VirtualFluidsCore basics muparser)
-file(GLOB SRC ${CMAKE_CURRENT_SOURCE_DIR}/src/*.cpp)
-
-add_library(simulationconfig STATIC ${SRC} ${HEADERS})
-
-set_target_properties(simulationconfig PROPERTIES CXX_STANDARD 14 POSITION_INDEPENDENT_CODE ON)
-
-target_include_directories(simulationconfig PUBLIC ${VFBUILDER_INCLUDE_DIR})
-target_link_libraries(simulationconfig PRIVATE VirtualFluidsCore basics muparser)
-target_compile_definitions(simulationconfig PRIVATE VF_METIS VF_MPI)
-target_include_directories(simulationconfig PUBLIC ${CMAKE_BINARY_DIR})
+set_target_properties(simulationconfig PROPERTIES POSITION_INDEPENDENT_CODE ON)
+target_include_directories(simulationconfig PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include)
diff --git a/src/cpu/simulationconfig/include/simulationconfig/AbstractLBMSystem.h b/src/cpu/simulationconfig/include/simulationconfig/AbstractLBMSystem.h
index 0c3ac72db2d3cb3488860227171f2fd27600c028..156649c6fd3c060117e8247efab2765f56f7c77b 100644
--- a/src/cpu/simulationconfig/include/simulationconfig/AbstractLBMSystem.h
+++ b/src/cpu/simulationconfig/include/simulationconfig/AbstractLBMSystem.h
@@ -7,6 +7,8 @@
class AbstractLBMSystem {
public:
+ virtual ~AbstractLBMSystem() = default;
+
virtual int getNumberOfDirections() = 0;
virtual std::shared_ptr<Interactor3D> makeInteractor() = 0;
diff --git a/src/cpu/simulationconfig/include/simulationconfig/KernelFactory.h b/src/cpu/simulationconfig/include/simulationconfig/KernelFactory.h
index 6b151d96f9c538bcfbf3aeb693afd56e36e6cf35..6f984849bea91a832d0d778107feacb3cfdbdca6 100644
--- a/src/cpu/simulationconfig/include/simulationconfig/KernelFactory.h
+++ b/src/cpu/simulationconfig/include/simulationconfig/KernelFactory.h
@@ -20,6 +20,7 @@ public:
};
KernelFactory() = default;
+ virtual ~KernelFactory() = default;
std::shared_ptr<LBMKernel> makeKernel(KernelType kernelType);
diff --git a/src/cpu/simulationconfig/include/simulationconfig/Simulation.h b/src/cpu/simulationconfig/include/simulationconfig/Simulation.h
index 47f8b0e6ef1c844a70efcf0faedd5cbcdb7dbc05..4bf800c2375347ab7040424bdb2e4c53d5cc2bf8 100644
--- a/src/cpu/simulationconfig/include/simulationconfig/Simulation.h
+++ b/src/cpu/simulationconfig/include/simulationconfig/Simulation.h
@@ -63,7 +63,9 @@ public:
void run();
private:
- std::shared_ptr<GbObject3D> makeSimulationBoundingBox() const;
+ bool isMainProcess();
+
+ std::shared_ptr<GbObject3D> makeSimulationBoundingBox();
void writeBlocksToFile() const;
@@ -84,6 +86,12 @@ private:
void setKernelForcing(const std::shared_ptr<LBMKernel> &kernel, std::shared_ptr<LBMUnitConverter> &converter) const;
+
+ void setConnectors();
+
+ void initializeDistributions();
+
+ std::shared_ptr<CoProcessor> makeNupsCoProcessor() const;
};
#endif
\ No newline at end of file
diff --git a/src/cpu/simulationconfig/src/Simulation.cpp b/src/cpu/simulationconfig/src/Simulation.cpp
index 6d80a1cfa2cc62d2575d1e8f67193b879f217b90..f4fbad090fc60e424e777b4f601243eef8eb151e 100644
--- a/src/cpu/simulationconfig/src/Simulation.cpp
+++ b/src/cpu/simulationconfig/src/Simulation.cpp
@@ -65,6 +65,8 @@ Simulation::addObject(const std::shared_ptr<GbObject3D> &object, const std::shar
const bool is_in = registeredAdapters.find(bcAdapter) != registeredAdapters.end();
if (!is_in) addBCAdapter(bcAdapter);
this->interactors.push_back(lbmSystem->makeInteractor(object, this->grid, bcAdapter, state));
+ if (communicator->getProcessID() != 0) return;
+
GbSystem3D::writeGeoObject(object, writerConfig.outputPath + folderPath, writerConfig.getWriter());
}
@@ -99,19 +101,20 @@ void Simulation::run()
grid->setPeriodicX2(gridParameters->periodicBoundaryInX2);
grid->setPeriodicX3(gridParameters->periodicBoundaryInX3);
- int &numberOfNodesInReferenceDirection = gridParameters->numberOfNodesPerDirection[gridParameters->referenceDirectionIndex];
+ //int &numberOfNodesInReferenceDirection = gridParameters->numberOfNodesPerDirection[gridParameters->referenceDirectionIndex];
std::shared_ptr<LBMUnitConverter> converter = makeLBMUnitConverter();
int &nodesInX1 = gridParameters->numberOfNodesPerDirection[0];
int &nodesInX2 = gridParameters->numberOfNodesPerDirection[1];
int &nodesInX3 = gridParameters->numberOfNodesPerDirection[2];
- logSimulationData(nodesInX1, nodesInX2, nodesInX3);
+
+ if (isMainProcess())
+ logSimulationData(nodesInX1, nodesInX2, nodesInX3);
setBlockSize(nodesInX1, nodesInX2, nodesInX3);
auto gridCube = makeSimulationBoundingBox();
generateBlockGrid(gridCube);
-
setKernelForcing(lbmKernel, converter);
setBoundaryConditionProcessor(lbmKernel);
@@ -125,55 +128,44 @@ void Simulation::run()
intHelper.selectBlocks();
-
int numberOfProcesses = communicator->getNumberOfProcesses();
SetKernelBlockVisitor kernelVisitor(lbmKernel, physicalParameters->latticeViscosity,
numberOfProcesses);
grid->accept(kernelVisitor);
intHelper.setBC();
- double bulkViscosity = physicalParameters->latticeViscosity * physicalParameters->bulkViscosityFactor;
- //auto iProcessor = std::make_shared<CompressibleOffsetMomentsInterpolationProcessor>();
- //iProcessor->setBulkViscosity(physicalParameters->latticeViscosity, bulkViscosity);
-
- //SetConnectorsBlockVisitor setConnsVisitor(communicator, true,
- // lbmSystem->getNumberOfDirections(),
- // physicalParameters->latticeViscosity, iProcessor);
- OneDistributionSetConnectorsBlockVisitor setConnsVisitor(communicator);
- grid->accept(setConnsVisitor);
-
- InitDistributionsBlockVisitor initVisitor;
- grid->accept(initVisitor);
- grid->accept(setConnsVisitor);
+ writeBlocksToFile(); // important: run this after metis & intHelper.selectBlocks()
+ setConnectors();
+ initializeDistributions();
grid->accept(bcVisitor);
-
writeBoundaryConditions();
- // important: run this after metis & intHelper.selectBlocks()
- writeBlocksToFile();
+
+#ifdef _OPENMP
+ omp_set_num_threads(simulationParameters->numberOfThreads);
+ if (isMainProcess())
+ UBLOG(logINFO, "OpenMP is set to run with " << simulationParameters->numberOfThreads << " threads")
+#endif
auto visualizationScheduler = std::make_shared<UbScheduler>(simulationParameters->timeStepLogInterval);
auto mqCoProcessor = makeMacroscopicQuantitiesCoProcessor(converter,
visualizationScheduler);
- std::shared_ptr<UbScheduler> nupsScheduler(new UbScheduler(100, 100));
- std::shared_ptr<CoProcessor> nupsCoProcessor(
- new NUPSCounterCoProcessor(grid, nupsScheduler, simulationParameters->numberOfThreads, communicator));
-
-
-#ifdef _OPENMP
- omp_set_num_threads(simulationParameters->numberOfThreads);
- UBLOG(logINFO, "OpenMP is set to run with " << omp_get_num_threads() << " threads")
-#endif
+ auto nupsCoProcessor = makeNupsCoProcessor();
auto calculator = std::make_shared<BasicCalculator>(grid, visualizationScheduler,
simulationParameters->numberOfTimeSteps);
calculator->addCoProcessor(nupsCoProcessor);
calculator->addCoProcessor(mqCoProcessor);
- UBLOG(logINFO, "Simulation-start")
+ if (isMainProcess()) UBLOG(logINFO, "Simulation-start")
calculator->calculate();
- UBLOG(logINFO, "Simulation-end")
+ if (isMainProcess()) UBLOG(logINFO, "Simulation-end")
+}
+
+bool Simulation::isMainProcess()
+{
+ return communicator->getProcessID() == 0;
}
void
@@ -224,18 +216,7 @@ Simulation::makeLBMUnitConverter()
return std::make_shared<LBMUnitConverter>();
}
-std::shared_ptr<CoProcessor>
-Simulation::makeMacroscopicQuantitiesCoProcessor(const std::shared_ptr<LBMUnitConverter> &converter,
- const std::shared_ptr<UbScheduler> &visualizationScheduler) const
-{
- auto mqCoProcessor = std::make_shared<WriteMacroscopicQuantitiesCoProcessor>(grid, visualizationScheduler,
- writerConfig.outputPath,
- writerConfig.getWriter(),
- converter,
- communicator);
- mqCoProcessor->process(0);
- return mqCoProcessor;
-}
+
void Simulation::writeBoundaryConditions() const
{
@@ -248,8 +229,9 @@ void Simulation::writeBoundaryConditions() const
void Simulation::writeBlocksToFile() const
{
UBLOG(logINFO, "Write block grid to VTK-file")
+ auto scheduler = std::make_shared<UbScheduler>(1);
auto ppblocks = std::make_shared<WriteBlocksCoProcessor>(grid,
- std::make_shared<UbScheduler>(1),
+ scheduler,
writerConfig.outputPath,
writerConfig.getWriter(),
communicator);
@@ -258,17 +240,56 @@ void Simulation::writeBlocksToFile() const
}
std::shared_ptr<GbObject3D>
-Simulation::makeSimulationBoundingBox() const
+Simulation::makeSimulationBoundingBox()
{
auto box = gridParameters->boundingBox();
+ auto gridCube = std::make_shared<GbCuboid3D>(box->minX1, box->minX2, box->minX3, box->maxX1, box->maxX2,
+ box->maxX3);
- UBLOG(logINFO, "Bounding box dimensions = [("
- << box->minX1 << ", " << box->minX2 << ", " << box->minX3 << "); ("
- << box->maxX1 << ", " << box->maxX2 << ", " << box->maxX3 << ")]")
+ if (isMainProcess())
+ {
+ UBLOG(logINFO, "Bounding box dimensions = [("
+ << box->minX1 << ", " << box->minX2 << ", " << box->minX3 << "); ("
+ << box->maxX1 << ", " << box->maxX2 << ", " << box->maxX3 << ")]")
+
+ GbSystem3D::writeGeoObject(gridCube.get(), writerConfig.outputPath + "/geo/gridCube", writerConfig.getWriter());
+ }
- auto gridCube = std::make_shared<GbCuboid3D>(box->minX1, box->minX2, box->minX3, box->maxX1, box->maxX2, box->maxX3);
- GbSystem3D::writeGeoObject(gridCube.get(), writerConfig.outputPath + "/geo/gridCube", writerConfig.getWriter());
return gridCube;
}
+void Simulation::setConnectors()
+{
+ OneDistributionSetConnectorsBlockVisitor setConnsVisitor(communicator);
+ grid->accept(setConnsVisitor);
+}
+
+void Simulation::initializeDistributions()
+{
+ InitDistributionsBlockVisitor initVisitor;
+ grid->accept(initVisitor);
+}
+
+std::shared_ptr<CoProcessor>
+Simulation::makeMacroscopicQuantitiesCoProcessor(const std::shared_ptr<LBMUnitConverter> &converter,
+ const std::shared_ptr<UbScheduler> &visualizationScheduler) const
+{
+ auto mqCoProcessor = std::make_shared<WriteMacroscopicQuantitiesCoProcessor>(grid, visualizationScheduler,
+ writerConfig.outputPath,
+ writerConfig.getWriter(),
+ converter,
+ communicator);
+ mqCoProcessor->process(0);
+ return mqCoProcessor;
+}
+
+std::shared_ptr<CoProcessor> Simulation::makeNupsCoProcessor() const
+{
+ auto scheduler = std::make_shared<UbScheduler>(100, 100);
+ return std::make_shared<NUPSCounterCoProcessor>(grid, scheduler,
+ simulationParameters->numberOfThreads,
+ communicator);
+}
+
+
Simulation::~Simulation() = default;
diff --git a/src/gpu/GridGenerator/CMakeLists.txt b/src/gpu/GridGenerator/CMakeLists.txt
index 29d77897ac4e6138057ec2b4f13f5f942bdb0e01..844e933d5c053aaeef38085c5c5a9e01721ff6aa 100644
--- a/src/gpu/GridGenerator/CMakeLists.txt
+++ b/src/gpu/GridGenerator/CMakeLists.txt
@@ -6,11 +6,5 @@ vf_add_library(PRIVATE_LINK basics OpenMP::OpenMP_CXX)
vf_get_library_name(library_name)
set_target_properties(${library_name} PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
-# according to linker error when building static libraries.
-# https://stackoverflow.com/questions/50033435/cmake-cuda-separate-compilation-static-lib-link-error-on-windows-but-not-on-ubun
-if (NOT BUILD_SHARED_LIBRARY)
- set_target_properties(${library_name} PROPERTIES CUDA_RESOLVE_DEVICE_SYMBOLS ON)
-endif()
-
# we want to suppress all cuda warnings so far for this library.
target_compile_options(${library_name} PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:-Xcudafe "-w" >)
diff --git a/src/gpu/VirtualFluids_GPU/CMakeLists.txt b/src/gpu/VirtualFluids_GPU/CMakeLists.txt
index ce1bb9d921f114b3d06143901355c56ab24b77fd..5c93599449cb4e5cef1c0112670068aa4e76abb3 100644
--- a/src/gpu/VirtualFluids_GPU/CMakeLists.txt
+++ b/src/gpu/VirtualFluids_GPU/CMakeLists.txt
@@ -5,10 +5,19 @@ if(MSVC)
set(additional_libraries ws2_32 Traffic) # ws_32 throws an error on Phoenix
endif()
-vf_add_library(PRIVATE_LINK ${additional_libraries} GridGenerator basics MPI::MPI_CXX)
+vf_add_library(PUBLIC_LINK basics lbmCuda PRIVATE_LINK ${additional_libraries} GridGenerator MPI::MPI_CXX)
+
#SET(TPN_WIN32 "/EHsc")
#https://stackoverflow.com/questions/6832666/lnk2019-when-including-asio-headers-solution-generated-with-cmake
#https://stackoverflow.com/questions/27442885/syntax-error-with-stdnumeric-limitsmax
+set_target_properties(VirtualFluids_GPU PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+
vf_add_tests()
+
+if(BUILD_VF_UNIT_TESTS)
+ set_target_properties(VirtualFluids_GPUTests PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+ set_source_files_properties(Kernel/Utilities/DistributionHelperTests.cpp PROPERTIES LANGUAGE CUDA)
+endif()
diff --git a/src/gpu/VirtualFluids_GPU/DataStructureInitializer/GridProvider.cpp b/src/gpu/VirtualFluids_GPU/DataStructureInitializer/GridProvider.cpp
index 2b2a2e68d0980b4d3aa4b27a04bd8ce703704a05..957935756163795945e9ac1c4762e0eb825239ee 100644
--- a/src/gpu/VirtualFluids_GPU/DataStructureInitializer/GridProvider.cpp
+++ b/src/gpu/VirtualFluids_GPU/DataStructureInitializer/GridProvider.cpp
@@ -118,6 +118,12 @@ void GridProvider::allocAndCopyForcing()
{
cudaMemoryManager->cudaAllocForcing();
cudaMemoryManager->cudaCopyForcingToDevice();
+
+ for (int level = para->getCoarse(); level <= para->getFine(); level++)
+ {
+ cudaMemoryManager->cudaAllocLevelForcing(level);
+ cudaMemoryManager->cudaCopyLevelForcingToDevice(level);
+ }
}
void GridProvider::allocAndCopyQuadricLimiters()
diff --git a/src/gpu/VirtualFluids_GPU/GPU/CalcMac27.cu b/src/gpu/VirtualFluids_GPU/GPU/CalcMac27.cu
index ce3082817776d5b8ed6237b027354956df3a8777..562140eb24bad470604b5782a816a4e60d5000f3 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/CalcMac27.cu
+++ b/src/gpu/VirtualFluids_GPU/GPU/CalcMac27.cu
@@ -12,6 +12,11 @@
using namespace vf::lbm::constant;
+#include "lbm/MacroscopicQuantities.h"
+
+#include "../Kernel/Utilities/DistributionHelper.cuh"
+
+
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void LBCalcMac27( real* vxD,
real* vyD,
@@ -22,196 +27,37 @@ extern "C" __global__ void LBCalcMac27( real* vxD,
unsigned int* neighborY,
unsigned int* neighborZ,
unsigned int size_Mat,
- real* DD,
- bool evenOrOdd)
+ real* distributions,
+ bool isEvenTimestep)
{
- Distributions27 D;
- if (evenOrOdd==true)
- {
- D.f[dirE ] = &DD[dirE *size_Mat];
- D.f[dirW ] = &DD[dirW *size_Mat];
- D.f[dirN ] = &DD[dirN *size_Mat];
- D.f[dirS ] = &DD[dirS *size_Mat];
- D.f[dirT ] = &DD[dirT *size_Mat];
- D.f[dirB ] = &DD[dirB *size_Mat];
- D.f[dirNE ] = &DD[dirNE *size_Mat];
- D.f[dirSW ] = &DD[dirSW *size_Mat];
- D.f[dirSE ] = &DD[dirSE *size_Mat];
- D.f[dirNW ] = &DD[dirNW *size_Mat];
- D.f[dirTE ] = &DD[dirTE *size_Mat];
- D.f[dirBW ] = &DD[dirBW *size_Mat];
- D.f[dirBE ] = &DD[dirBE *size_Mat];
- D.f[dirTW ] = &DD[dirTW *size_Mat];
- D.f[dirTN ] = &DD[dirTN *size_Mat];
- D.f[dirBS ] = &DD[dirBS *size_Mat];
- D.f[dirBN ] = &DD[dirBN *size_Mat];
- D.f[dirTS ] = &DD[dirTS *size_Mat];
- D.f[dirZERO] = &DD[dirZERO*size_Mat];
- D.f[dirTNE ] = &DD[dirTNE *size_Mat];
- D.f[dirTSW ] = &DD[dirTSW *size_Mat];
- D.f[dirTSE ] = &DD[dirTSE *size_Mat];
- D.f[dirTNW ] = &DD[dirTNW *size_Mat];
- D.f[dirBNE ] = &DD[dirBNE *size_Mat];
- D.f[dirBSW ] = &DD[dirBSW *size_Mat];
- D.f[dirBSE ] = &DD[dirBSE *size_Mat];
- D.f[dirBNW ] = &DD[dirBNW *size_Mat];
- }
- else
- {
- D.f[dirW ] = &DD[dirE *size_Mat];
- D.f[dirE ] = &DD[dirW *size_Mat];
- D.f[dirS ] = &DD[dirN *size_Mat];
- D.f[dirN ] = &DD[dirS *size_Mat];
- D.f[dirB ] = &DD[dirT *size_Mat];
- D.f[dirT ] = &DD[dirB *size_Mat];
- D.f[dirSW ] = &DD[dirNE *size_Mat];
- D.f[dirNE ] = &DD[dirSW *size_Mat];
- D.f[dirNW ] = &DD[dirSE *size_Mat];
- D.f[dirSE ] = &DD[dirNW *size_Mat];
- D.f[dirBW ] = &DD[dirTE *size_Mat];
- D.f[dirTE ] = &DD[dirBW *size_Mat];
- D.f[dirTW ] = &DD[dirBE *size_Mat];
- D.f[dirBE ] = &DD[dirTW *size_Mat];
- D.f[dirBS ] = &DD[dirTN *size_Mat];
- D.f[dirTN ] = &DD[dirBS *size_Mat];
- D.f[dirTS ] = &DD[dirBN *size_Mat];
- D.f[dirBN ] = &DD[dirTS *size_Mat];
- D.f[dirZERO] = &DD[dirZERO*size_Mat];
- D.f[dirTNE ] = &DD[dirBSW *size_Mat];
- D.f[dirTSW ] = &DD[dirBNE *size_Mat];
- D.f[dirTSE ] = &DD[dirBNW *size_Mat];
- D.f[dirTNW ] = &DD[dirBSE *size_Mat];
- D.f[dirBNE ] = &DD[dirTSW *size_Mat];
- D.f[dirBSW ] = &DD[dirTNE *size_Mat];
- D.f[dirBSE ] = &DD[dirTNW *size_Mat];
- D.f[dirBNW ] = &DD[dirTSE *size_Mat];
- }
- ////////////////////////////////////////////////////////////////////////////////
- unsigned int k; // Zugriff auf arrays im device
- //
- unsigned int tx = threadIdx.x; // Thread index = lokaler i index
- unsigned int by = blockIdx.x; // Block index x
- unsigned int bz = blockIdx.y; // Block index y
- unsigned int x = tx + STARTOFFX; // Globaler x-Index
- unsigned int y = by + STARTOFFY; // Globaler y-Index
- unsigned int z = bz + STARTOFFZ; // Globaler z-Index
-
- const unsigned sizeX = blockDim.x;
- const unsigned sizeY = gridDim.x;
- const unsigned nx = sizeX + 2 * STARTOFFX;
- const unsigned ny = sizeY + 2 * STARTOFFY;
-
- k = nx*(ny*z + y) + x;
- //////////////////////////////////////////////////////////////////////////
- //index
- unsigned int kzero= k;
- unsigned int ke = k;
- unsigned int kw = neighborX[k];
- unsigned int kn = k;
- unsigned int ks = neighborY[k];
- unsigned int kt = k;
- unsigned int kb = neighborZ[k];
- unsigned int ksw = neighborY[kw];
- unsigned int kne = k;
- unsigned int kse = ks;
- unsigned int knw = kw;
- unsigned int kbw = neighborZ[kw];
- unsigned int kte = k;
- unsigned int kbe = kb;
- unsigned int ktw = kw;
- unsigned int kbs = neighborZ[ks];
- unsigned int ktn = k;
- unsigned int kbn = kb;
- unsigned int kts = ks;
- unsigned int ktse = ks;
- unsigned int kbnw = kbw;
- unsigned int ktnw = kw;
- unsigned int kbse = kbs;
- unsigned int ktsw = ksw;
- unsigned int kbne = kb;
- unsigned int ktne = k;
- unsigned int kbsw = neighborZ[ksw];
- //unsigned int nxny = nx*ny;
- //unsigned int kzero= k;
- //unsigned int ke = k;
- //unsigned int kw = k + 1;
- //unsigned int kn = k;
- //unsigned int ks = k + nx;
- //unsigned int kt = k;
- //unsigned int kb = k + nxny;
- //unsigned int ksw = k + nx + 1;
- //unsigned int kne = k;
- //unsigned int kse = k + nx;
- //unsigned int knw = k + 1;
- //unsigned int kbw = k + nxny + 1;
- //unsigned int kte = k;
- //unsigned int kbe = k + nxny;
- //unsigned int ktw = k + 1;
- //unsigned int kbs = k + nxny + nx;
- //unsigned int ktn = k;
- //unsigned int kbn = k + nxny;
- //unsigned int kts = k + nx;
- //unsigned int ktse = k + nx;
- //unsigned int kbnw = k + nxny + 1;
- //unsigned int ktnw = k + 1;
- //unsigned int kbse = k + nxny + nx;
- //unsigned int ktsw = k + nx + 1;
- //unsigned int kbne = k + nxny;
- //unsigned int ktne = k;
- //unsigned int kbsw = k + nxny + nx + 1;
- //////////////////////////////////////////////////////////////////////////
+ const unsigned int tx = threadIdx.x; // Thread index = lokaler i index
+ const unsigned int by = blockIdx.x; // Block index x
+ const unsigned int bz = blockIdx.y; // Block index y
+ const unsigned int x = tx + STARTOFFX; // Globaler x-Index
+ const unsigned int y = by + STARTOFFY; // Globaler y-Index
+ const unsigned int z = bz + STARTOFFZ; // Globaler z-Index
+
+ const unsigned nx = blockDim.x + 2 * STARTOFFX;
+ const unsigned ny = gridDim.x + 2 * STARTOFFY;
+
+ const unsigned int k = nx*(ny*z + y) + x; // Zugriff auf arrays im device
+
rhoD[k] = c0o1;
vxD[k] = c0o1;
vyD[k] = c0o1;
vzD[k] = c0o1;
- if(geoD[k] == GEO_FLUID)
- {
- rhoD[k] = (D.f[dirE ])[ke ]+ (D.f[dirW ])[kw ]+
- (D.f[dirN ])[kn ]+ (D.f[dirS ])[ks ]+
- (D.f[dirT ])[kt ]+ (D.f[dirB ])[kb ]+
- (D.f[dirNE ])[kne ]+ (D.f[dirSW ])[ksw ]+
- (D.f[dirSE ])[kse ]+ (D.f[dirNW ])[knw ]+
- (D.f[dirTE ])[kte ]+ (D.f[dirBW ])[kbw ]+
- (D.f[dirBE ])[kbe ]+ (D.f[dirTW ])[ktw ]+
- (D.f[dirTN ])[ktn ]+ (D.f[dirBS ])[kbs ]+
- (D.f[dirBN ])[kbn ]+ (D.f[dirTS ])[kts ]+
- (D.f[dirZERO])[kzero]+
- (D.f[dirTNE ])[ktne]+ (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]+ (D.f[dirBSW ])[kbsw]+
- (D.f[dirBSE ])[kbse]+ (D.f[dirBNW ])[kbnw];
-
- vxD[k] = (D.f[dirE ])[ke ]- (D.f[dirW ])[kw ]+
- (D.f[dirNE ])[kne ]- (D.f[dirSW ])[ksw ]+
- (D.f[dirSE ])[kse ]- (D.f[dirNW ])[knw ]+
- (D.f[dirTE ])[kte ]- (D.f[dirBW ])[kbw ]+
- (D.f[dirBE ])[kbe ]- (D.f[dirTW ])[ktw ]+
- (D.f[dirTNE ])[ktne]- (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]- (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]+
- (D.f[dirBSE ])[kbse]- (D.f[dirBNW ])[kbnw];
-
- vyD[k] = (D.f[dirN ])[kn ]- (D.f[dirS ])[ks ]+
- (D.f[dirNE ])[kne ]- (D.f[dirSW ])[ksw ]-
- (D.f[dirSE ])[kse ]+ (D.f[dirNW ])[knw ]+
- (D.f[dirTN ])[ktn ]- (D.f[dirBS ])[kbs ]+
- (D.f[dirBN ])[kbn ]- (D.f[dirTS ])[kts ]+
- (D.f[dirTNE ])[ktne]- (D.f[dirTSW ])[ktsw]-
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]-
- (D.f[dirBSE ])[kbse]+ (D.f[dirBNW ])[kbnw];
-
- vzD[k] = (D.f[dirT ])[kt ]- (D.f[dirB ])[kb ]+
- (D.f[dirTE ])[kte ]- (D.f[dirBW ])[kbw ]-
- (D.f[dirBE ])[kbe ]+ (D.f[dirTW ])[ktw ]+
- (D.f[dirTN ])[ktn ]- (D.f[dirBS ])[kbs ]-
- (D.f[dirBN ])[kbn ]+ (D.f[dirTS ])[kts ]+
- (D.f[dirTNE ])[ktne]+ (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]-
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]-
- (D.f[dirBSE ])[kbse]- (D.f[dirBNW ])[kbnw];
- }
+ if(!vf::gpu::isValidFluidNode(k, size_Mat, geoD[k]))
+ return;
+
+ vf::gpu::DistributionWrapper distr_wrapper(distributions, size_Mat, isEvenTimestep, k, neighborX, neighborY, neighborZ);
+ const auto& distribution = distr_wrapper.distribution;
+
+ rhoD[k] = vf::lbm::getDensity(distribution.f);
+ vxD[k] = vf::lbm::getIncompressibleVelocityX1(distribution.f);
+ vyD[k] = vf::lbm::getIncompressibleVelocityX2(distribution.f);
+ vzD[k] = vf::lbm::getIncompressibleVelocityX3(distribution.f);
+
}
@@ -412,251 +258,34 @@ extern "C" __global__ void LBCalcMacSP27( real* vxD,
}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
////////////////////////////////////////////////////////////////////////////////
-extern "C" __global__ void LBCalcMacCompSP27( real* vxD,
- real* vyD,
- real* vzD,
- real* rhoD,
- real* pressD,
- unsigned int* geoD,
- unsigned int* neighborX,
- unsigned int* neighborY,
- unsigned int* neighborZ,
- unsigned int size_Mat,
- real* DD,
- bool evenOrOdd)
+extern "C" __global__ void LBCalcMacCompSP27(real *vxD, real *vyD, real *vzD, real *rhoD, real *pressD,
+ unsigned int *geoD, unsigned int *neighborX, unsigned int *neighborY,
+ unsigned int *neighborZ, unsigned int size_Mat, real *distributions,
+ bool isEvenTimestep)
{
- Distributions27 D;
- if (evenOrOdd==true)
- {
- D.f[dirE ] = &DD[dirE *size_Mat];
- D.f[dirW ] = &DD[dirW *size_Mat];
- D.f[dirN ] = &DD[dirN *size_Mat];
- D.f[dirS ] = &DD[dirS *size_Mat];
- D.f[dirT ] = &DD[dirT *size_Mat];
- D.f[dirB ] = &DD[dirB *size_Mat];
- D.f[dirNE ] = &DD[dirNE *size_Mat];
- D.f[dirSW ] = &DD[dirSW *size_Mat];
- D.f[dirSE ] = &DD[dirSE *size_Mat];
- D.f[dirNW ] = &DD[dirNW *size_Mat];
- D.f[dirTE ] = &DD[dirTE *size_Mat];
- D.f[dirBW ] = &DD[dirBW *size_Mat];
- D.f[dirBE ] = &DD[dirBE *size_Mat];
- D.f[dirTW ] = &DD[dirTW *size_Mat];
- D.f[dirTN ] = &DD[dirTN *size_Mat];
- D.f[dirBS ] = &DD[dirBS *size_Mat];
- D.f[dirBN ] = &DD[dirBN *size_Mat];
- D.f[dirTS ] = &DD[dirTS *size_Mat];
- D.f[dirZERO] = &DD[dirZERO*size_Mat];
- D.f[dirTNE ] = &DD[dirTNE *size_Mat];
- D.f[dirTSW ] = &DD[dirTSW *size_Mat];
- D.f[dirTSE ] = &DD[dirTSE *size_Mat];
- D.f[dirTNW ] = &DD[dirTNW *size_Mat];
- D.f[dirBNE ] = &DD[dirBNE *size_Mat];
- D.f[dirBSW ] = &DD[dirBSW *size_Mat];
- D.f[dirBSE ] = &DD[dirBSE *size_Mat];
- D.f[dirBNW ] = &DD[dirBNW *size_Mat];
- }
- else
- {
- D.f[dirW ] = &DD[dirE *size_Mat];
- D.f[dirE ] = &DD[dirW *size_Mat];
- D.f[dirS ] = &DD[dirN *size_Mat];
- D.f[dirN ] = &DD[dirS *size_Mat];
- D.f[dirB ] = &DD[dirT *size_Mat];
- D.f[dirT ] = &DD[dirB *size_Mat];
- D.f[dirSW ] = &DD[dirNE *size_Mat];
- D.f[dirNE ] = &DD[dirSW *size_Mat];
- D.f[dirNW ] = &DD[dirSE *size_Mat];
- D.f[dirSE ] = &DD[dirNW *size_Mat];
- D.f[dirBW ] = &DD[dirTE *size_Mat];
- D.f[dirTE ] = &DD[dirBW *size_Mat];
- D.f[dirTW ] = &DD[dirBE *size_Mat];
- D.f[dirBE ] = &DD[dirTW *size_Mat];
- D.f[dirBS ] = &DD[dirTN *size_Mat];
- D.f[dirTN ] = &DD[dirBS *size_Mat];
- D.f[dirTS ] = &DD[dirBN *size_Mat];
- D.f[dirBN ] = &DD[dirTS *size_Mat];
- D.f[dirZERO] = &DD[dirZERO*size_Mat];
- D.f[dirTNE ] = &DD[dirBSW *size_Mat];
- D.f[dirTSW ] = &DD[dirBNE *size_Mat];
- D.f[dirTSE ] = &DD[dirBNW *size_Mat];
- D.f[dirTNW ] = &DD[dirBSE *size_Mat];
- D.f[dirBNE ] = &DD[dirTSW *size_Mat];
- D.f[dirBSW ] = &DD[dirTNE *size_Mat];
- D.f[dirBSE ] = &DD[dirTNW *size_Mat];
- D.f[dirBNW ] = &DD[dirTSE *size_Mat];
- }
- ////////////////////////////////////////////////////////////////////////////////
- const unsigned x = threadIdx.x; // Globaler x-Index
- const unsigned y = blockIdx.x; // Globaler y-Index
- const unsigned z = blockIdx.y; // Globaler z-Index
-
- const unsigned nx = blockDim.x;
- const unsigned ny = gridDim.x;
-
- const unsigned k = nx*(ny*z + y) + x;
- //////////////////////////////////////////////////////////////////////////
-
- if(k<size_Mat)
- {
- //////////////////////////////////////////////////////////////////////////
- //index
- unsigned int kzero= k;
- unsigned int ke = k;
- unsigned int kw = neighborX[k];
- unsigned int kn = k;
- unsigned int ks = neighborY[k];
- unsigned int kt = k;
- unsigned int kb = neighborZ[k];
- unsigned int ksw = neighborY[kw];
- unsigned int kne = k;
- unsigned int kse = ks;
- unsigned int knw = kw;
- unsigned int kbw = neighborZ[kw];
- unsigned int kte = k;
- unsigned int kbe = kb;
- unsigned int ktw = kw;
- unsigned int kbs = neighborZ[ks];
- unsigned int ktn = k;
- unsigned int kbn = kb;
- unsigned int kts = ks;
- unsigned int ktse = ks;
- unsigned int kbnw = kbw;
- unsigned int ktnw = kw;
- unsigned int kbse = kbs;
- unsigned int ktsw = ksw;
- unsigned int kbne = kb;
- unsigned int ktne = k;
- unsigned int kbsw = neighborZ[ksw];
- //////////////////////////////////////////////////////////////////////////
- pressD[k] = c0o1;
- rhoD[k] = c0o1;
- vxD[k] = c0o1;
- vyD[k] = c0o1;
- vzD[k] = c0o1;
-
- if(geoD[k] == GEO_FLUID || geoD[k] == GEO_PM_0 || geoD[k] == GEO_PM_1 || geoD[k] == GEO_PM_2)
- {
- rhoD[k] = (D.f[dirE ])[ke ]+ (D.f[dirW ])[kw ]+
- (D.f[dirN ])[kn ]+ (D.f[dirS ])[ks ]+
- (D.f[dirT ])[kt ]+ (D.f[dirB ])[kb ]+
- (D.f[dirNE ])[kne ]+ (D.f[dirSW ])[ksw ]+
- (D.f[dirSE ])[kse ]+ (D.f[dirNW ])[knw ]+
- (D.f[dirTE ])[kte ]+ (D.f[dirBW ])[kbw ]+
- (D.f[dirBE ])[kbe ]+ (D.f[dirTW ])[ktw ]+
- (D.f[dirTN ])[ktn ]+ (D.f[dirBS ])[kbs ]+
- (D.f[dirBN ])[kbn ]+ (D.f[dirTS ])[kts ]+
- (D.f[dirZERO])[kzero]+
- (D.f[dirTNE ])[ktne]+ (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]+ (D.f[dirBSW ])[kbsw]+
- (D.f[dirBSE ])[kbse]+ (D.f[dirBNW ])[kbnw];
-
- vxD[k] = ((D.f[dirE ])[ke ]- (D.f[dirW ])[kw ]+
- (D.f[dirNE ])[kne ]- (D.f[dirSW ])[ksw ]+
- (D.f[dirSE ])[kse ]- (D.f[dirNW ])[knw ]+
- (D.f[dirTE ])[kte ]- (D.f[dirBW ])[kbw ]+
- (D.f[dirBE ])[kbe ]- (D.f[dirTW ])[ktw ]+
- (D.f[dirTNE ])[ktne]- (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]- (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]+
- (D.f[dirBSE ])[kbse]- (D.f[dirBNW ])[kbnw]) / (c1o1 + rhoD[k]);
-
- vyD[k] = ((D.f[dirN ])[kn ]- (D.f[dirS ])[ks ]+
- (D.f[dirNE ])[kne ]- (D.f[dirSW ])[ksw ]-
- (D.f[dirSE ])[kse ]+ (D.f[dirNW ])[knw ]+
- (D.f[dirTN ])[ktn ]- (D.f[dirBS ])[kbs ]+
- (D.f[dirBN ])[kbn ]- (D.f[dirTS ])[kts ]+
- (D.f[dirTNE ])[ktne]- (D.f[dirTSW ])[ktsw]-
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]-
- (D.f[dirBSE ])[kbse]+ (D.f[dirBNW ])[kbnw]) / (c1o1 + rhoD[k]);
-
- vzD[k] = ((D.f[dirT ])[kt ]- (D.f[dirB ])[kb ]+
- (D.f[dirTE ])[kte ]- (D.f[dirBW ])[kbw ]-
- (D.f[dirBE ])[kbe ]+ (D.f[dirTW ])[ktw ]+
- (D.f[dirTN ])[ktn ]- (D.f[dirBS ])[kbs ]-
- (D.f[dirBN ])[kbn ]+ (D.f[dirTS ])[kts ]+
- (D.f[dirTNE ])[ktne]+ (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]-
- (D.f[dirBNE ])[kbne]- (D.f[dirBSW ])[kbsw]-
- (D.f[dirBSE ])[kbse]- (D.f[dirBNW ])[kbnw]) / (c1o1 + rhoD[k]);
-
- pressD[k] = ((D.f[dirE ])[ke ]+ (D.f[dirW ])[kw ]+
- (D.f[dirN ])[kn ]+ (D.f[dirS ])[ks ]+
- (D.f[dirT ])[kt ]+ (D.f[dirB ])[kb ]+
- c2o1*(
- (D.f[dirNE ])[kne ]+ (D.f[dirSW ])[ksw ]+
- (D.f[dirSE ])[kse ]+ (D.f[dirNW ])[knw ]+
- (D.f[dirTE ])[kte ]+ (D.f[dirBW ])[kbw ]+
- (D.f[dirBE ])[kbe ]+ (D.f[dirTW ])[ktw ]+
- (D.f[dirTN ])[ktn ]+ (D.f[dirBS ])[kbs ]+
- (D.f[dirBN ])[kbn ]+ (D.f[dirTS ])[kts ])+
- c3o1*(
- (D.f[dirTNE ])[ktne]+ (D.f[dirTSW ])[ktsw]+
- (D.f[dirTSE ])[ktse]+ (D.f[dirTNW ])[ktnw]+
- (D.f[dirBNE ])[kbne]+ (D.f[dirBSW ])[kbsw]+
- (D.f[dirBSE ])[kbse]+ (D.f[dirBNW ])[kbnw])-
- rhoD[k]-(vxD[k] * vxD[k] + vyD[k] * vyD[k] + vzD[k] * vzD[k]) * (c1o1+rhoD[k])) * c1o2+rhoD[k]; // times zero for incompressible case
- //achtung op hart gesetzt Annahme op = 1 ; ^^^^(1.0/op-0.5)=0.5
-
- }
- }
+ const unsigned k = vf::gpu::getNodeIndex();
+
+ pressD[k] = c0o1;
+ rhoD[k] = c0o1;
+ vxD[k] = c0o1;
+ vyD[k] = c0o1;
+ vzD[k] = c0o1;
+
+ if (!vf::gpu::isValidFluidNode(k, size_Mat, geoD[k]))
+ return;
+
+ vf::gpu::DistributionWrapper distr_wrapper(distributions, size_Mat, isEvenTimestep, k, neighborX, neighborY,
+ neighborZ);
+ const auto &distribution = distr_wrapper.distribution;
+
+ rhoD[k] = vf::lbm::getDensity(distribution.f);
+ vxD[k] = vf::lbm::getCompressibleVelocityX1(distribution.f, rhoD[k]);
+ vyD[k] = vf::lbm::getCompressibleVelocityX2(distribution.f, rhoD[k]);
+ vzD[k] = vf::lbm::getCompressibleVelocityX3(distribution.f, rhoD[k]);
+ pressD[k] = vf::lbm::getPressure(distribution.f, rhoD[k], vxD[k], vyD[k], vzD[k]);
}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void LBCalcMacThS7( real* Conc,
unsigned int* geoD,
diff --git a/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.cpp b/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.cpp
index 6c1585bd689a5f2e2da603d5e9fdb81cbc175aab..aeafe342f0680763fbbffe63cf1c6760e61c2102 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.cpp
+++ b/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.cpp
@@ -6,6 +6,8 @@
#include <Parameter/Parameter.h>
+#include <lbm/constants/NumericConstants.h>
+
void CudaMemoryManager::cudaAllocFull(int lev)
{
checkCudaErrors( cudaMallocHost((void**) &(parameter->getParH(lev)->geo ), parameter->getParH(lev)->mem_size_int ));
@@ -404,6 +406,44 @@ void CudaMemoryManager::cudaFreeForcing()
{
checkCudaErrors( cudaFreeHost(parameter->getForcesHost()));
}
+
+void CudaMemoryManager::cudaAllocLevelForcing(int level)
+{
+ real fx_t{ 1. }, fy_t{ 1. }, fz_t{ 1. };
+ for (int i = 0; i < level; i++) {
+ fx_t *= vf::lbm::constant::c2o1;
+ fy_t *= vf::lbm::constant::c2o1;
+ fz_t *= vf::lbm::constant::c2o1;
+ }
+
+ const unsigned int mem_size = sizeof(real) * 3;
+
+ //Host
+ checkCudaErrors( cudaMallocHost((void**) &(parameter->getParH(level)->forcing), mem_size));
+ parameter->getParH(level)->forcing[0] = parameter->forcingH[0] / fx_t;
+ parameter->getParH(level)->forcing[1] = parameter->forcingH[1] / fy_t;
+ parameter->getParH(level)->forcing[2] = parameter->forcingH[2] / fz_t;
+
+ //Device
+ checkCudaErrors( cudaMalloc((void**) ¶meter->getParD(level)->forcing, mem_size));
+ //////////////////////////////////////////////////////////////////////////
+ const double tmp = (double)mem_size;
+ setMemsizeGPU(tmp, false);
+}
+
+void CudaMemoryManager::cudaCopyLevelForcingToDevice(int level)
+{
+ unsigned int mem_size = sizeof(real) * 3;
+ checkCudaErrors( cudaMemcpy(parameter->getParD(level)->forcing, parameter->getParH(level)->forcing, mem_size, cudaMemcpyHostToDevice));
+}
+
+void CudaMemoryManager::cudaFreeLevelForcing(int level)
+{
+ checkCudaErrors( cudaFreeHost(parameter->getParH(level)->forcing));
+ checkCudaErrors( cudaFree(parameter->getParD(level)->forcing));
+}
+
+
//quadric Limiters
void CudaMemoryManager::cudaAllocQuadricLimiters()
{
diff --git a/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.h b/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.h
index c26db65afd384ac7a4e6c436c4dea2c46647ae95..4853205f510348a954fbc8dcdaed72385a30d559 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.h
+++ b/src/gpu/VirtualFluids_GPU/GPU/CudaMemoryManager.h
@@ -78,6 +78,10 @@ public:
void cudaCopyForcingToHost();
void cudaFreeForcing();
+ void cudaAllocLevelForcing(int level);
+ void cudaCopyLevelForcingToDevice(int level);
+ void cudaFreeLevelForcing(int level);
+
void cudaAllocQuadricLimiters();
void cudaCopyQuadricLimitersToDevice();
void cudaFreeQuadricLimiters();
diff --git a/src/gpu/VirtualFluids_GPU/GPU/Cumulant27chim.cu b/src/gpu/VirtualFluids_GPU/GPU/Cumulant27chim.cu
index bb34a11a7337a499f8558a48d27c3547932618a6..9dc75cfa6019a29350263f9a554aa9a489566cfa 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/Cumulant27chim.cu
+++ b/src/gpu/VirtualFluids_GPU/GPU/Cumulant27chim.cu
@@ -1,10 +1,35 @@
-// _ ___ __ __________ _ __ ______________ __
-// | | / (_)____/ /___ ______ _/ / ____/ /_ __(_)___/ /____ / ___/ __ / / / /
-// | | / / / ___/ __/ / / / __ `/ / /_ / / / / / / __ / ___/ / /___/ /_/ / / / /
-// | |/ / / / / /_/ /_/ / /_/ / / __/ / / /_/ / / /_/ (__ ) / /_) / ____/ /__/ /
-// |___/_/_/ \__/\__,_/\__,_/_/_/ /_/\__,_/_/\__,_/____/ \____/_/ \_____/
+//=======================================================================================
+// ____ ____ __ ______ __________ __ __ __ __
+// \ \ | | | | | _ \ |___ ___| | | | | / \ | |
+// \ \ | | | | | |_) | | | | | | | / \ | |
+// \ \ | | | | | _ / | | | | | | / /\ \ | |
+// \ \ | | | | | | \ \ | | | \__/ | / ____ \ | |____
+// \ \ | | |__| |__| \__\ |__| \________/ /__/ \__\ |_______|
+// \ \ | | ________________________________________________________________
+// \ \ | | | ______________________________________________________________|
+// \ \| | | | __ __ __ __ ______ _______
+// \ | | |_____ | | | | | | | | | _ \ / _____)
+// \ | | _____| | | | | | | | | | | \ \ \_______
+// \ | | | | |_____ | \_/ | | | | |_/ / _____ |
+// \ _____| |__| |________| \_______/ |__| |______/ (_______/
//
-//////////////////////////////////////////////////////////////////////////
+// This file is part of VirtualFluids. VirtualFluids is free software: you can
+// redistribute it and/or modify it under the terms of the GNU General Public
+// License as published by the Free Software Foundation, either version 3 of
+// the License, or (at your option) any later version.
+//
+// VirtualFluids is distributed in the hope that it will be useful, but WITHOUT
+// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+// for more details.
+//
+// You should have received a copy of the GNU General Public License along
+// with VirtualFluids (see COPYING.txt). If not, see <http://www.gnu.org/licenses/>.
+//
+//! \file Cumulant27chim.cu
+//! \ingroup GPU
+//! \author Martin Schoenherr
+//=======================================================================================
/* Device code */
#include "LBM/LB.h"
#include "LBM/D3Q27.h"
@@ -13,951 +38,882 @@
using namespace vf::lbm::constant;
#include "math.h"
-
-////////////////////////////////////////////////////////////////////////////////
-inline __device__ void forwardInverseChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real Kinverse, real K) {
- real m2 = mfa + mfc;
- real m1 = mfc - mfa;
- real m0 = m2 + mfb;
- mfa = m0;
- m0 *= Kinverse;
- m0 += c1o1;
- mfb = (m1*Kinverse - m0 * vv) * K;
- mfc = ((m2 - c2o1* m1 * vv)*Kinverse + v2 * m0) * K;
-}
-
-inline __device__ void backwardInverseChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real Kinverse, real K) {
- real m0 = (((mfc - mfb) * c1o2 + mfb * vv)*Kinverse + (mfa*Kinverse + c1o1) * (v2 - vv) * c1o2) * K;
- real m1 = (((mfa - mfc) - c2o1 * mfb * vv)*Kinverse + (mfa*Kinverse + c1o1) * ( -v2)) * K;
- mfc = (((mfc + mfb) * c1o2 + mfb * vv)*Kinverse + (mfa*Kinverse + c1o1) * (v2 + vv) * c1o2) * K;
- mfa = m0;
- mfb = m1;
-}
-////////////////////////////////////////////////////////////////////////////////
-
-
-
-
-
-inline __device__ void forwardChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real K) {
-
- real m2 = mfa + mfc;
- real m1 = mfc - mfa;
- real m0 = m2 + mfb;
- mfa = m0;
- //m0 += K;
- mfb = (m1 - K*vv) - m0 * vv;
- mfc = ((m2 - c2o1* m1 * vv) + v2*K) + v2 * m0;
- //m0 += K;
- //mfb = m1 - m0 * vv;
- //mfc = m2 - two* m1 * vv + v2 * m0;
-}
-
-inline __device__ void forwardChimera(real &mfa, real &mfb, real &mfc, real vv, real v2) {
- real m1 = (mfa + mfc) + mfb;
- real m2 = mfc - mfa;
- mfc = (mfc + mfa) + (v2*m1 - c2o1*vv*m2);
- mfb = m2 - vv*m1;
- mfa = m1;
-}
-
-
-inline __device__ void backwardChimera(real &mfa, real &mfb, real &mfc, real vv, real v2) {
- real ma = (mfc + mfa*(v2 - vv))*c1o2 + mfb*(vv - c1o2);
- real mb = ((mfa - mfc) - mfa*v2) - c2o1*mfb*vv;
- mfc = (mfc + mfa*(v2 + vv))*c1o2 + mfb*(vv + c1o2);
- mfb = mb;
- mfa = ma;
-}
-
-
-inline __device__ void backwardChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real K) {
- real m0 = (mfc - mfb)* c1o2 + mfb * (vv)+(mfa + K) * (v2 - vv) * c1o2;
- real m1 = (mfa - mfc) - c2o1* mfb * vv + (mfa + K) * (-v2);
- mfc = (mfc + mfb)* c1o2 + mfb * (vv)+(mfa + K) * (v2 + vv) * c1o2;
- mfa = m0;
- mfb = m1;
-
-}
-
-
-
-
+#include <lbm/Chimera.h>
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void Cumulant_One_preconditioned_errorDiffusion_chim_Comp_SP_27(
- real omega,
- unsigned int* bcMatD,
- unsigned int* neighborX,
- unsigned int* neighborY,
- unsigned int* neighborZ,
- real* DDStart,
- int size_Mat,
- int level,
- real* forces,
- bool EvenOrOdd)
+ real omega,
+ unsigned int* bcMatD,
+ unsigned int* neighborX,
+ unsigned int* neighborY,
+ unsigned int* neighborZ,
+ real* DDStart,
+ int size_Mat,
+ int level,
+ real* forces,
+ bool EvenOrOdd)
{
- ////////////////////////////////////////////////////////////////////////////////
- const unsigned x = threadIdx.x; // Globaler x-Index
- const unsigned y = blockIdx.x; // Globaler y-Index
- const unsigned z = blockIdx.y; // Globaler z-Index
-
- const unsigned nx = blockDim.x;
- const unsigned ny = gridDim.x;
-
- const unsigned k = nx*(ny*z + y) + x;
- //////////////////////////////////////////////////////////////////////////
-
- if (k<size_Mat)
- {
- ////////////////////////////////////////////////////////////////////////////////
- unsigned int BC;
- BC = bcMatD[k];
-
- if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
- {
- Distributions27 D;
- if (EvenOrOdd == true)
- {
- D.f[dirE] = &DDStart[dirE *size_Mat];
- D.f[dirW] = &DDStart[dirW *size_Mat];
- D.f[dirN] = &DDStart[dirN *size_Mat];
- D.f[dirS] = &DDStart[dirS *size_Mat];
- D.f[dirT] = &DDStart[dirT *size_Mat];
- D.f[dirB] = &DDStart[dirB *size_Mat];
- D.f[dirNE] = &DDStart[dirNE *size_Mat];
- D.f[dirSW] = &DDStart[dirSW *size_Mat];
- D.f[dirSE] = &DDStart[dirSE *size_Mat];
- D.f[dirNW] = &DDStart[dirNW *size_Mat];
- D.f[dirTE] = &DDStart[dirTE *size_Mat];
- D.f[dirBW] = &DDStart[dirBW *size_Mat];
- D.f[dirBE] = &DDStart[dirBE *size_Mat];
- D.f[dirTW] = &DDStart[dirTW *size_Mat];
- D.f[dirTN] = &DDStart[dirTN *size_Mat];
- D.f[dirBS] = &DDStart[dirBS *size_Mat];
- D.f[dirBN] = &DDStart[dirBN *size_Mat];
- D.f[dirTS] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirTNE] = &DDStart[dirTNE *size_Mat];
- D.f[dirTSW] = &DDStart[dirTSW *size_Mat];
- D.f[dirTSE] = &DDStart[dirTSE *size_Mat];
- D.f[dirTNW] = &DDStart[dirTNW *size_Mat];
- D.f[dirBNE] = &DDStart[dirBNE *size_Mat];
- D.f[dirBSW] = &DDStart[dirBSW *size_Mat];
- D.f[dirBSE] = &DDStart[dirBSE *size_Mat];
- D.f[dirBNW] = &DDStart[dirBNW *size_Mat];
- }
- else
- {
- D.f[dirW] = &DDStart[dirE *size_Mat];
- D.f[dirE] = &DDStart[dirW *size_Mat];
- D.f[dirS] = &DDStart[dirN *size_Mat];
- D.f[dirN] = &DDStart[dirS *size_Mat];
- D.f[dirB] = &DDStart[dirT *size_Mat];
- D.f[dirT] = &DDStart[dirB *size_Mat];
- D.f[dirSW] = &DDStart[dirNE *size_Mat];
- D.f[dirNE] = &DDStart[dirSW *size_Mat];
- D.f[dirNW] = &DDStart[dirSE *size_Mat];
- D.f[dirSE] = &DDStart[dirNW *size_Mat];
- D.f[dirBW] = &DDStart[dirTE *size_Mat];
- D.f[dirTE] = &DDStart[dirBW *size_Mat];
- D.f[dirTW] = &DDStart[dirBE *size_Mat];
- D.f[dirBE] = &DDStart[dirTW *size_Mat];
- D.f[dirBS] = &DDStart[dirTN *size_Mat];
- D.f[dirTN] = &DDStart[dirBS *size_Mat];
- D.f[dirTS] = &DDStart[dirBN *size_Mat];
- D.f[dirBN] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirBSW] = &DDStart[dirTNE *size_Mat];
- D.f[dirBNE] = &DDStart[dirTSW *size_Mat];
- D.f[dirBNW] = &DDStart[dirTSE *size_Mat];
- D.f[dirBSE] = &DDStart[dirTNW *size_Mat];
- D.f[dirTSW] = &DDStart[dirBNE *size_Mat];
- D.f[dirTNE] = &DDStart[dirBSW *size_Mat];
- D.f[dirTNW] = &DDStart[dirBSE *size_Mat];
- D.f[dirTSE] = &DDStart[dirBNW *size_Mat];
- }
-
- ////////////////////////////////////////////////////////////////////////////////
- //index
- //unsigned int kzero= k;
- //unsigned int ke = k;
- unsigned int kw = neighborX[k];
- //unsigned int kn = k;
- unsigned int ks = neighborY[k];
- //unsigned int kt = k;
- unsigned int kb = neighborZ[k];
- unsigned int ksw = neighborY[kw];
- //unsigned int kne = k;
- //unsigned int kse = ks;
- //unsigned int knw = kw;
- unsigned int kbw = neighborZ[kw];
- //unsigned int kte = k;
- //unsigned int kbe = kb;
- //unsigned int ktw = kw;
- unsigned int kbs = neighborZ[ks];
- //unsigned int ktn = k;
- //unsigned int kbn = kb;
- //unsigned int kts = ks;
- //unsigned int ktse = ks;
- //unsigned int kbnw = kbw;
- //unsigned int ktnw = kw;
- //unsigned int kbse = kbs;
- //unsigned int ktsw = ksw;
- //unsigned int kbne = kb;
- //unsigned int ktne = k;
- unsigned int kbsw = neighborZ[ksw];
-
-
-
- //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- real mfcbb = (D.f[dirE])[k];//[ke ];// + c2over27 ;(D.f[dirE ])[k ];//ke
- real mfabb = (D.f[dirW])[kw];//[kw ];// + c2over27 ;(D.f[dirW ])[kw ];
- real mfbcb = (D.f[dirN])[k];//[kn ];// + c2over27 ;(D.f[dirN ])[k ];//kn
- real mfbab = (D.f[dirS])[ks];//[ks ];// + c2over27 ;(D.f[dirS ])[ks ];
- real mfbbc = (D.f[dirT])[k];//[kt ];// + c2over27 ;(D.f[dirT ])[k ];//kt
- real mfbba = (D.f[dirB])[kb];//[kb ];// + c2over27 ;(D.f[dirB ])[kb ];
- real mfccb = (D.f[dirNE])[k];//[kne ];// + c1over54 ;(D.f[dirNE ])[k ];//kne
- real mfaab = (D.f[dirSW])[ksw];//[ksw ];// + c1over54 ;(D.f[dirSW ])[ksw];
- real mfcab = (D.f[dirSE])[ks];//[kse ];// + c1over54 ;(D.f[dirSE ])[ks ];//kse
- real mfacb = (D.f[dirNW])[kw];//[knw ];// + c1over54 ;(D.f[dirNW ])[kw ];//knw
- real mfcbc = (D.f[dirTE])[k];//[kte ];// + c1over54 ;(D.f[dirTE ])[k ];//kte
- real mfaba = (D.f[dirBW])[kbw];//[kbw ];// + c1over54 ;(D.f[dirBW ])[kbw];
- real mfcba = (D.f[dirBE])[kb];//[kbe ];// + c1over54 ;(D.f[dirBE ])[kb ];//kbe
- real mfabc = (D.f[dirTW])[kw];//[ktw ];// + c1over54 ;(D.f[dirTW ])[kw ];//ktw
- real mfbcc = (D.f[dirTN])[k];//[ktn ];// + c1over54 ;(D.f[dirTN ])[k ];//ktn
- real mfbaa = (D.f[dirBS])[kbs];//[kbs ];// + c1over54 ;(D.f[dirBS ])[kbs];
- real mfbca = (D.f[dirBN])[kb];//[kbn ];// + c1over54 ;(D.f[dirBN ])[kb ];//kbn
- real mfbac = (D.f[dirTS])[ks];//[kts ];// + c1over54 ;(D.f[dirTS ])[ks ];//kts
- real mfbbb = (D.f[dirZERO])[k];//[kzero];// + c8over27 ;(D.f[dirZERO])[k ];//kzero
- real mfccc = (D.f[dirTNE])[k];//[ktne ];// + c1over216;(D.f[dirTNE ])[k ];//ktne
- real mfaac = (D.f[dirTSW])[ksw];//[ktsw ];// + c1over216;(D.f[dirTSW ])[ksw];//ktsw
- real mfcac = (D.f[dirTSE])[ks];//[ktse ];// + c1over216;(D.f[dirTSE ])[ks ];//ktse
- real mfacc = (D.f[dirTNW])[kw];//[ktnw ];// + c1over216;(D.f[dirTNW ])[kw ];//ktnw
- real mfcca = (D.f[dirBNE])[kb];//[kbne ];// + c1over216;(D.f[dirBNE ])[kb ];//kbne
- real mfaaa = (D.f[dirBSW])[kbsw];//[kbsw ];// + c1over216;(D.f[dirBSW ])[kbsw];
- real mfcaa = (D.f[dirBSE])[kbs];//[kbse ];// + c1over216;(D.f[dirBSE ])[kbs];//kbse
- real mfaca = (D.f[dirBNW])[kbw];//[kbnw ];// + c1over216;(D.f[dirBNW ])[kbw];//kbnw
- ////////////////////////////////////////////////////////////////////////////////////
- real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
-
- real rho = c1o1 + drho;
- ////////////////////////////////////////////////////////////////////////////////////
- real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
- (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
- (mfcbb - mfabb)) / rho;
- real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
- (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
- (mfbcb - mfbab)) / rho;
- real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
- (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
- (mfbbc - mfbba)) / rho;
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
- real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
- real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
- vvx += fx*c1o2;
- vvy += fy*c1o2;
- vvz += fz*c1o2;
- ////////////////////////////////////////////////////////////////////////////////////
- //real omega = omega_in;
- ////////////////////////////////////////////////////////////////////////////////////
- //fast
- //real oMdrho = c1o1; // comp special
- //real m0, m1, m2;
- real vx2;
- real vy2;
- real vz2;
- vx2 = vvx*vvx;
- vy2 = vvy*vvy;
- vz2 = vvz*vvz;
- ////////////////////////////////////////////////////////////////////////////////////
- //real wadjust;
- //real qudricLimitP = c1o100;// * 0.0001f;
- //real qudricLimitM = c1o100;// * 0.0001f;
- //real qudricLimitD = c1o100;// * 0.001f;
- //real s9 = minusomega;
- //test
- //s9 = 0.;
-
-
- //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- real EQcbb = c0o1;
- real EQabb = c0o1;
- real EQbcb = c0o1;
- real EQbab = c0o1;
- real EQbbc = c0o1;
- real EQbba = c0o1;
- real EQccb = c0o1;
- real EQaab = c0o1;
- real EQcab = c0o1;
- real EQacb = c0o1;
- real EQcbc = c0o1;
- real EQaba = c0o1;
- real EQcba = c0o1;
- real EQabc = c0o1;
- real EQbcc = c0o1;
- real EQbaa = c0o1;
- real EQbca = c0o1;
- real EQbac = c0o1;
- real EQbbb = c0o1;
- real EQccc = drho * c1o27;
- real EQaac = drho * c1o3;
- real EQcac = drho * c1o9;
- real EQacc = drho * c1o9;
- real EQcca = drho * c1o9;
- real EQaaa = drho;
- real EQcaa = drho * c1o3;
- real EQaca = drho * c1o3;
- ////////////////////////////////////////////////////////////////////////////////////
- backwardChimeraWithK(EQaaa, EQaab, EQaac, vvz, vz2, c1o1);
- backwardChimeraWithK(EQaca, EQacb, EQacc, vvz, vz2, c1o3);
- ///////////////////////////////////////////////////////////
- EQcaa = EQaca; EQcab = EQacb; EQcac = EQacc;
- ///////////////////////////////////////////////////////////
- backwardChimeraWithK(EQcca, EQccb, EQccc, vvz, vz2, c1o9);
-
- backwardChimeraWithK(EQaaa, EQaba, EQaca, vvy, vy2, c1o6);
- backwardChimeraWithK(EQaab, EQabb, EQacb, vvy, vy2, c2o3);
- backwardChimeraWithK(EQaac, EQabc, EQacc, vvy, vy2, c1o6);
- backwardChimeraWithK(EQcaa, EQcba, EQcca, vvy, vy2, c1o18);
- backwardChimeraWithK(EQcab, EQcbb, EQccb, vvy, vy2, c2o9);
- backwardChimeraWithK(EQcac, EQcbc, EQccc, vvy, vy2, c1o18);
-
- backwardChimeraWithK(EQaaa, EQbaa, EQcaa, vvx, vx2, c1o36);
- backwardChimeraWithK(EQaab, EQbab, EQcab, vvx, vx2, c1o9);
- backwardChimeraWithK(EQaac, EQbac, EQcac, vvx, vx2, c1o36);
- backwardChimeraWithK(EQaba, EQbba, EQcba, vvx, vx2, c1o9);
- backwardChimeraWithK(EQabb, EQbbb, EQcbb, vvx, vx2, c4o9);
- backwardChimeraWithK(EQabc, EQbbc, EQcbc, vvx, vx2, c1o9);
- backwardChimeraWithK(EQaca, EQbca, EQcca, vvx, vx2, c1o36);
- backwardChimeraWithK(EQacb, EQbcb, EQccb, vvx, vx2, c1o9);
- backwardChimeraWithK(EQacc, EQbcc, EQccc, vvx, vx2, c1o36);
-
- ////////////////////////////////////////////////////////////////////////////////////
- //Pre-condition
- mfcbb -= EQcbb;
- mfabb -= EQabb;
- mfbcb -= EQbcb;
- mfbab -= EQbab;
- mfbbc -= EQbbc;
- mfbba -= EQbba;
- mfccb -= EQccb;
- mfaab -= EQaab;
- mfcab -= EQcab;
- mfacb -= EQacb;
- mfcbc -= EQcbc;
- mfaba -= EQaba;
- mfcba -= EQcba;
- mfabc -= EQabc;
- mfbcc -= EQbcc;
- mfbaa -= EQbaa;
- mfbca -= EQbca;
- mfbac -= EQbac;
- mfbbb -= EQbbb;
- mfccc -= EQccc;
- mfaac -= EQaac;
- mfcac -= EQcac;
- mfacc -= EQacc;
- mfcca -= EQcca;
- mfaaa -= EQaaa;
- mfcaa -= EQcaa;
- mfaca -= EQaca;
-
- ////////////////////////////////////////////////////////////////////////////////////
- //Hin
- ////////////////////////////////////////////////////////////////////////////////////
- forwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
- forwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- forwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
- forwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- forwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- forwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- forwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
- forwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- forwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
-
- forwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
- forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- forwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
- forwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
- forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- forwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
- forwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
- forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- forwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
-
- forwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
- forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- forwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
- forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- forwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
- forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- forwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
-
- //////////////////////////////////////////////////////////////////////////////////////
- ////Hin
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Z - Dir
- //forwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c4o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Y - Dir
- //forwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c2o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c2o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// X - Dir
- //forwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, one);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
-
-
- ////////////////////////////////////////////////////////////////////////////////////
- // Cumulants
- ////////////////////////////////////////////////////////////////////////////////////
- real OxxPyyPzz = c1o1; //omega; // one; //set the bulk viscosity one is high / two is very low and zero is (too) high
-
- ////////////////////////////////////////////////////////////
- //3.
- //////////////////////////////
- real OxyyPxzz = c1o1;
- real OxyyMxzz = c1o1;
- //real Oxyz = c1o1;
- ////////////////////////////////////////////////////////////
- //4.
- //////////////////////////////
- real O4 = c1o1;
- ////////////////////////////////////////////////////////////
- //5.
- //////////////////////////////
- real O5 = c1o1;
- ////////////////////////////////////////////////////////////
- //6.
- //////////////////////////////
- real O6 = c1o1;
- ////////////////////////////////////////////////////////////
-
-
- //central moments to cumulants
- //4.
- real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
- real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
- real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
-
- real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
- real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
- real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
-
- //5.
- real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
- real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
- real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
-
- //6.
-
- real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
- - c1o3 * (mfacc + mfcac + mfcca) / rho
- - c1o9 * (mfcaa + mfaca + mfaac) / rho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
- + c1o27*((drho * drho - drho) / (rho*rho)));
-
-
-
-
- //2.
- // linear combinations
- real mxxPyyPzz = mfcaa + mfaca + mfaac;
- real mxxMyy = mfcaa - mfaca;
- real mxxMzz = mfcaa - mfaac;
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
- {
- real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
- real dyuy = dxux + omega * c3o2 * mxxMyy;
- real dzuz = dxux + omega * c3o2 * mxxMzz;
-
- //relax
- mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz) - c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
- mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
- mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
-
- }
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- ////no correction
- //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
- //mxxMyy += -(-omega) * (-mxxMyy);
- //mxxMzz += -(-omega) * (-mxxMzz);
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- mfabb += omega * (-mfabb);
- mfbab += omega * (-mfbab);
- mfbba += omega * (-mfbba);
-
- //////////////////////////////////////////////////////////////////////////
-
- // linear combinations back
- mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
- mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
- mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
-
- //3.
- // linear combinations
-
- real mxxyPyzz = mfcba + mfabc;
- real mxxyMyzz = mfcba - mfabc;
-
- real mxxzPyyz = mfcab + mfacb;
- real mxxzMyyz = mfcab - mfacb;
-
- real mxyyPxzz = mfbca + mfbac;
- real mxyyMxzz = mfbca - mfbac;
-
- //relax
- //////////////////////////////////////////////////////////////////////////
- mfbbb += OxyyMxzz * (-mfbbb);
- mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
- mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
- mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
- mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
- mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
- mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
- //////////////////////////////////////////////////////////////////////////
-
- mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
- mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
- mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
- mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
- mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
- mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
-
- //4.
- //////////////////////////////////////////////////////////////////////////
- CUMacc += O4 * (-CUMacc);
- CUMcac += O4 * (-CUMcac);
- CUMcca += O4 * (-CUMcca);
-
- CUMbbc += O4 * (-CUMbbc);
- CUMbcb += O4 * (-CUMbcb);
- CUMcbb += O4 * (-CUMcbb);
- //////////////////////////////////////////////////////////////////////////
-
-
- //5.
- CUMbcc += O5 * (-CUMbcc);
- CUMcbc += O5 * (-CUMcbc);
- CUMccb += O5 * (-CUMccb);
-
- //6.
- CUMccc += O6 * (-CUMccc);
-
-
-
- //back cumulants to central moments
- //4.
- mfcbb = CUMcbb + ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
- mfbcb = CUMbcb + ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
- mfbbc = CUMbbc + ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
-
- mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
- mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
- mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
-
- //5.
- mfbcc = CUMbcc + ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
- mfcbc = CUMcbc + ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
- mfccb = CUMccb + ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
-
- //6.
- mfccc = CUMccc - ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
- - c1o3 * (mfacc + mfcac + mfcca) / rho
- - c1o9 * (mfcaa + mfaca + mfaac) / rho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
- + c1o27*((drho * drho - drho) / (rho*rho)));
-
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- mfbaa = -mfbaa;
- mfaba = -mfaba;
- mfaab = -mfaab;
- ////////////////////////////////////////////////////////////////////////////////////
-
-
- ////////////////////////////////////////////////////////////////////////////////////
- //back
- ////////////////////////////////////////////////////////////////////////////////////
- backwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
- backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- backwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
- backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- backwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
- backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- backwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
-
- backwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
- backwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- backwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
- backwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
- backwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- backwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
- backwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
- backwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- backwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
-
- backwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
- backwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- backwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
- backwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- backwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- backwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- backwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
- backwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- backwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
-
- ////////////////////////////////////////////////////////////////////////////////////
- //mfcbb += EQcbb;
- //mfabb += EQabb;
- //mfbcb += EQbcb;
- //mfbab += EQbab;
- //mfbbc += EQbbc;
- //mfbba += EQbba;
- //mfccb += EQccb;
- //mfaab += EQaab;
- //mfcab += EQcab;
- //mfacb += EQacb;
- //mfcbc += EQcbc;
- //mfaba += EQaba;
- //mfcba += EQcba;
- //mfabc += EQabc;
- //mfbcc += EQbcc;
- //mfbaa += EQbaa;
- //mfbca += EQbca;
- //mfbac += EQbac;
- //mfbbb += EQbbb;
- //mfccc += EQccc;
- //mfaac += EQaac;
- //mfcac += EQcac;
- //mfacc += EQacc;
- //mfcca += EQcca;
- //mfaaa += EQaaa;
- //mfcaa += EQcaa;
- //mfaca += EQaca;
- ////////////////////////////////////////////////////////////////////////////////////
- ////Error diffusion
- real fTEMP = mfbbb + EQbbb;
- real delta0 = mfbbb - (fTEMP - EQbbb);
- delta0 *= c1o4;
- mfbbb = fTEMP;
-
-
- fTEMP = mfcbb + EQcbb;
- real deltacbb = mfcbb - (fTEMP - EQcbb);
- mfcbb = fTEMP;
- //mfcbb+=EQcbb;
-
- fTEMP = mfabb + EQabb;
- real deltaabb = mfabb - (fTEMP - EQabb);
- mfabb = fTEMP;
- //mfabb+=EQabb;
-
- fTEMP = mfbcb + EQbcb;
- real deltabcb = mfbcb - (fTEMP - EQbcb);
- mfbcb = fTEMP;
- //mfbcb+=EQbcb;
-
- fTEMP = mfbab + EQbab;
- real deltabab = mfbab - (fTEMP - EQbab);
- mfbab = fTEMP;
- //mfbab+=EQbab;
-
- fTEMP = mfbbc + EQbbc;
- real deltabbc = mfbbc - (fTEMP - EQbbc);
- mfbbc = fTEMP;
- //mfbbc+=EQbbc;
-
- fTEMP = mfbba + EQbba;
- real deltabba = mfbba - (fTEMP - EQbba);
- mfbba = fTEMP;
- //mfbba+=EQbba;
-
- EQccb += (delta0 + c1o2*(deltacbb + deltabcb));
- fTEMP = mfccb + EQccb;
- real deltaccb = mfccb - (fTEMP - EQccb);
- mfccb = fTEMP;
- //mfccb+=EQccb+(delta0+c1o2*(deltacbb+deltabcb));
-
- EQaab += (delta0 + c1o2*(deltaabb + deltabab));
- fTEMP = mfaab + EQaab;
- real deltaaab = mfaab - (fTEMP - EQaab);
- mfaab = fTEMP;
- //mfaab+=EQaab+(delta0+c1o2*(deltaabb+deltabab));
-
- EQcab += (delta0 + c1o2*(deltacbb + deltabab));
- fTEMP = mfcab + EQcab;
- real deltacab = mfcab - (fTEMP - EQcab);
- mfcab = fTEMP;
- //mfcab+=EQcab+(delta0+c1o2*(deltacbb+deltabab));
-
- EQacb += (delta0 + c1o2*(deltaabb + deltabcb));
- fTEMP = mfacb + EQacb;
- real deltaacb = mfacb - (fTEMP - EQacb);
- mfacb = fTEMP;
- //mfacb+=EQacb+(delta0+c1o2*(deltaabb+deltabcb));
-
- EQcbc += (delta0 + c1o2*(deltacbb + deltabbc));
- fTEMP = mfcbc + EQcbc;
- real deltacbc = mfcbc - (fTEMP - EQcbc);
- mfcbc = fTEMP;
- //mfcbc+=EQcbc+(delta0+c1o2*(deltacbb+deltabbc));
-
- EQaba += (delta0 + c1o2*(deltaabb + deltabba));
- fTEMP = mfaba + EQaba;
- real deltaaba = mfaba - (fTEMP - EQaba);
- mfaba = fTEMP;
- //mfaba+=EQaba+(delta0+c1o2*(deltaabb+deltabba));
-
- EQcba += (delta0 + c1o2*(deltacbb + deltabba));
- fTEMP = mfcba + EQcba;
- real deltacba = mfcba - (fTEMP - EQcba);
- mfcba = fTEMP;
- //mfcba+=EQcba+(delta0+c1o2*(deltacbb+deltabba));
-
- EQabc += (delta0 + c1o2*(deltaabb + deltabbc));
- fTEMP = mfabc + EQabc;
- real deltaabc = mfabc - (fTEMP - EQabc);
- mfabc = fTEMP;
- //mfabc+=EQabc+(delta0+c1o2*(deltaabb+deltabbc));
-
- EQbcc += (delta0 + c1o2*(deltabcb + deltabbc));
- fTEMP = mfbcc + EQbcc;
- real deltabcc = mfbcc - (fTEMP - EQbcc);
- mfbcc = fTEMP;
- //mfbcc+=EQbcc+(delta0+c1o2*(deltabcb+deltabbc));
-
- EQbaa += (delta0 + c1o2*(deltabab + deltabba));
- fTEMP = mfbaa + EQbaa;
- real deltabaa = mfbaa - (fTEMP - EQbaa);
- mfbaa = fTEMP;
- //mfbaa+=EQbaa+(delta0+c1o2*(deltabab+deltabba));
-
- EQbca += (delta0 + c1o2*(deltabcb + deltabba));
- fTEMP = mfbca + EQbca;
- real deltabca = mfbca - (fTEMP - EQbca);
- mfbca = fTEMP;
- //mfbca+=EQbca+(delta0+c1o2*(deltabcb+deltabba));
-
- EQbac += (delta0 + c1o2*(deltabab + deltabbc));
- fTEMP = mfbac + EQbac;
- real deltabac = mfbac - (fTEMP - EQbac);
- mfbac = fTEMP;
- //mfbac+=EQbac+(delta0+c1o2*(deltabab+deltabbc));
-
- mfccc += EQccc - (delta0 + c1o4*(deltacbb + deltabcb + deltabbc) - c1o2*(deltabcc + deltacbc + deltaccb));
- mfaac += EQaac - (delta0 + c1o4*(deltaabb + deltabab + deltabbc) - c1o2*(deltabac + deltaabc + deltaaab));
- mfcac += EQcac - (delta0 + c1o4*(deltacbb + deltabab + deltabbc) - c1o2*(deltabac + deltacbc + deltacab));
- mfacc += EQacc - (delta0 + c1o4*(deltaabb + deltabcb + deltabbc) - c1o2*(deltabcc + deltaabc + deltaacb));
- mfcca += EQcca - (delta0 + c1o4*(deltacbb + deltabcb + deltabba) - c1o2*(deltabca + deltacba + deltaccb));
- mfaaa += EQaaa - (delta0 + c1o4*(deltaabb + deltabab + deltabba) - c1o2*(deltabaa + deltaaba + deltaaab));
- mfcaa += EQcaa - (delta0 + c1o4*(deltacbb + deltabab + deltabba) - c1o2*(deltabaa + deltacba + deltacab));
- mfaca += EQaca - (delta0 + c1o4*(deltaabb + deltabcb + deltabba) - c1o2*(deltabca + deltaaba + deltaacb));
-
-
-
- //////////////////////////////////////////////////////////////////////////////////////
- ////back
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Z - Dir
- //backwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, one);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o3);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Y - Dir
- //backwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaab, mfabb, mfacb, vvy, vy2, c2o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbaa, mfbba, mfbca, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbab, mfbbb, mfbcb, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbac, mfbbc, mfbcc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o18);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcab, mfcbb, mfccb, vvy, vy2, c2o9);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// X - Dir
- //backwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaba, mfbba, mfcba, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaab, mfbab, mfcab, vvx, vx2, c1o9);
- /////////////b////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfabb, mfbbb, mfcbb, vvx, vx2, c4o9);
- /////////////b////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfacb, mfbcb, mfccb, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o36);
- /////////////c////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfabc, mfbbc, mfcbc, vvx, vx2, c1o9);
- /////////////c////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
-
- ////////////////////////////////////////////////////////////////////////////////////////
- //real drhoPost =
- // ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- // (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- // ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
- //mfbbb += drho - drhoPost;
- ////////////////////////////////////////////////////////////////////////////////////
- (D.f[dirE])[k] = mfabb;//(D.f[ dirE ])[ke ] = mfabb;// - c2over27 ; (D.f[ dirE ])[k ]
- (D.f[dirW])[kw] = mfcbb;//(D.f[ dirW ])[kw ] = mfcbb;// - c2over27 ; (D.f[ dirW ])[kw ]
- (D.f[dirN])[k] = mfbab;//(D.f[ dirN ])[kn ] = mfbab;// - c2over27 ; (D.f[ dirN ])[k ]
- (D.f[dirS])[ks] = mfbcb;//(D.f[ dirS ])[ks ] = mfbcb;// - c2over27 ; (D.f[ dirS ])[ks ]
- (D.f[dirT])[k] = mfbba;//(D.f[ dirT ])[kt ] = mfbba;// - c2over27 ; (D.f[ dirT ])[k ]
- (D.f[dirB])[kb] = mfbbc;//(D.f[ dirB ])[kb ] = mfbbc;// - c2over27 ; (D.f[ dirB ])[kb ]
- (D.f[dirNE])[k] = mfaab;//(D.f[ dirNE ])[kne ] = mfaab;// - c1over54 ; (D.f[ dirNE ])[k ]
- (D.f[dirSW])[ksw] = mfccb;//(D.f[ dirSW ])[ksw ] = mfccb;// - c1over54 ; (D.f[ dirSW ])[ksw ]
- (D.f[dirSE])[ks] = mfacb;//(D.f[ dirSE ])[kse ] = mfacb;// - c1over54 ; (D.f[ dirSE ])[ks ]
- (D.f[dirNW])[kw] = mfcab;//(D.f[ dirNW ])[knw ] = mfcab;// - c1over54 ; (D.f[ dirNW ])[kw ]
- (D.f[dirTE])[k] = mfaba;//(D.f[ dirTE ])[kte ] = mfaba;// - c1over54 ; (D.f[ dirTE ])[k ]
- (D.f[dirBW])[kbw] = mfcbc;//(D.f[ dirBW ])[kbw ] = mfcbc;// - c1over54 ; (D.f[ dirBW ])[kbw ]
- (D.f[dirBE])[kb] = mfabc;//(D.f[ dirBE ])[kbe ] = mfabc;// - c1over54 ; (D.f[ dirBE ])[kb ]
- (D.f[dirTW])[kw] = mfcba;//(D.f[ dirTW ])[ktw ] = mfcba;// - c1over54 ; (D.f[ dirTW ])[kw ]
- (D.f[dirTN])[k] = mfbaa;//(D.f[ dirTN ])[ktn ] = mfbaa;// - c1over54 ; (D.f[ dirTN ])[k ]
- (D.f[dirBS])[kbs] = mfbcc;//(D.f[ dirBS ])[kbs ] = mfbcc;// - c1over54 ; (D.f[ dirBS ])[kbs ]
- (D.f[dirBN])[kb] = mfbac;//(D.f[ dirBN ])[kbn ] = mfbac;// - c1over54 ; (D.f[ dirBN ])[kb ]
- (D.f[dirTS])[ks] = mfbca;//(D.f[ dirTS ])[kts ] = mfbca;// - c1over54 ; (D.f[ dirTS ])[ks ]
- (D.f[dirZERO])[k] = mfbbb;//(D.f[ dirZERO])[kzero] = mfbbb;// - c8over27 ; (D.f[ dirZERO])[k ]
- (D.f[dirTNE])[k] = mfaaa;//(D.f[ dirTNE ])[ktne ] = mfaaa;// - c1over216; (D.f[ dirTNE ])[k ]
- (D.f[dirTSE])[ks] = mfaca;//(D.f[ dirTSE ])[ktse ] = mfaca;// - c1over216; (D.f[ dirTSE ])[ks ]
- (D.f[dirBNE])[kb] = mfaac;//(D.f[ dirBNE ])[kbne ] = mfaac;// - c1over216; (D.f[ dirBNE ])[kb ]
- (D.f[dirBSE])[kbs] = mfacc;//(D.f[ dirBSE ])[kbse ] = mfacc;// - c1over216; (D.f[ dirBSE ])[kbs ]
- (D.f[dirTNW])[kw] = mfcaa;//(D.f[ dirTNW ])[ktnw ] = mfcaa;// - c1over216; (D.f[ dirTNW ])[kw ]
- (D.f[dirTSW])[ksw] = mfcca;//(D.f[ dirTSW ])[ktsw ] = mfcca;// - c1over216; (D.f[ dirTSW ])[ksw ]
- (D.f[dirBNW])[kbw] = mfcac;//(D.f[ dirBNW ])[kbnw ] = mfcac;// - c1over216; (D.f[ dirBNW ])[kbw ]
- (D.f[dirBSW])[kbsw] = mfccc;//(D.f[ dirBSW ])[kbsw ] = mfccc;// - c1over216; (D.f[ dirBSW ])[kbsw]
- ////////////////////////////////////////////////////////////////////////////////////
- }
- }
+ ////////////////////////////////////////////////////////////////////////////////
+ const unsigned x = threadIdx.x; // Globaler x-Index
+ const unsigned y = blockIdx.x; // Globaler y-Index
+ const unsigned z = blockIdx.y; // Globaler z-Index
+
+ const unsigned nx = blockDim.x;
+ const unsigned ny = gridDim.x;
+
+ const unsigned k = nx*(ny*z + y) + x;
+ //////////////////////////////////////////////////////////////////////////
+
+ if (k<size_Mat)
+ {
+ ////////////////////////////////////////////////////////////////////////////////
+ unsigned int BC;
+ BC = bcMatD[k];
+
+ if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
+ {
+ Distributions27 D;
+ if (EvenOrOdd == true)
+ {
+ D.f[dirE] = &DDStart[dirE *size_Mat];
+ D.f[dirW] = &DDStart[dirW *size_Mat];
+ D.f[dirN] = &DDStart[dirN *size_Mat];
+ D.f[dirS] = &DDStart[dirS *size_Mat];
+ D.f[dirT] = &DDStart[dirT *size_Mat];
+ D.f[dirB] = &DDStart[dirB *size_Mat];
+ D.f[dirNE] = &DDStart[dirNE *size_Mat];
+ D.f[dirSW] = &DDStart[dirSW *size_Mat];
+ D.f[dirSE] = &DDStart[dirSE *size_Mat];
+ D.f[dirNW] = &DDStart[dirNW *size_Mat];
+ D.f[dirTE] = &DDStart[dirTE *size_Mat];
+ D.f[dirBW] = &DDStart[dirBW *size_Mat];
+ D.f[dirBE] = &DDStart[dirBE *size_Mat];
+ D.f[dirTW] = &DDStart[dirTW *size_Mat];
+ D.f[dirTN] = &DDStart[dirTN *size_Mat];
+ D.f[dirBS] = &DDStart[dirBS *size_Mat];
+ D.f[dirBN] = &DDStart[dirBN *size_Mat];
+ D.f[dirTS] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirTNE] = &DDStart[dirTNE *size_Mat];
+ D.f[dirTSW] = &DDStart[dirTSW *size_Mat];
+ D.f[dirTSE] = &DDStart[dirTSE *size_Mat];
+ D.f[dirTNW] = &DDStart[dirTNW *size_Mat];
+ D.f[dirBNE] = &DDStart[dirBNE *size_Mat];
+ D.f[dirBSW] = &DDStart[dirBSW *size_Mat];
+ D.f[dirBSE] = &DDStart[dirBSE *size_Mat];
+ D.f[dirBNW] = &DDStart[dirBNW *size_Mat];
+ }
+ else
+ {
+ D.f[dirW] = &DDStart[dirE *size_Mat];
+ D.f[dirE] = &DDStart[dirW *size_Mat];
+ D.f[dirS] = &DDStart[dirN *size_Mat];
+ D.f[dirN] = &DDStart[dirS *size_Mat];
+ D.f[dirB] = &DDStart[dirT *size_Mat];
+ D.f[dirT] = &DDStart[dirB *size_Mat];
+ D.f[dirSW] = &DDStart[dirNE *size_Mat];
+ D.f[dirNE] = &DDStart[dirSW *size_Mat];
+ D.f[dirNW] = &DDStart[dirSE *size_Mat];
+ D.f[dirSE] = &DDStart[dirNW *size_Mat];
+ D.f[dirBW] = &DDStart[dirTE *size_Mat];
+ D.f[dirTE] = &DDStart[dirBW *size_Mat];
+ D.f[dirTW] = &DDStart[dirBE *size_Mat];
+ D.f[dirBE] = &DDStart[dirTW *size_Mat];
+ D.f[dirBS] = &DDStart[dirTN *size_Mat];
+ D.f[dirTN] = &DDStart[dirBS *size_Mat];
+ D.f[dirTS] = &DDStart[dirBN *size_Mat];
+ D.f[dirBN] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirBSW] = &DDStart[dirTNE *size_Mat];
+ D.f[dirBNE] = &DDStart[dirTSW *size_Mat];
+ D.f[dirBNW] = &DDStart[dirTSE *size_Mat];
+ D.f[dirBSE] = &DDStart[dirTNW *size_Mat];
+ D.f[dirTSW] = &DDStart[dirBNE *size_Mat];
+ D.f[dirTNE] = &DDStart[dirBSW *size_Mat];
+ D.f[dirTNW] = &DDStart[dirBSE *size_Mat];
+ D.f[dirTSE] = &DDStart[dirBNW *size_Mat];
+ }
+
+ ////////////////////////////////////////////////////////////////////////////////
+ //index
+ //unsigned int kzero= k;
+ //unsigned int ke = k;
+ unsigned int kw = neighborX[k];
+ //unsigned int kn = k;
+ unsigned int ks = neighborY[k];
+ //unsigned int kt = k;
+ unsigned int kb = neighborZ[k];
+ unsigned int ksw = neighborY[kw];
+ //unsigned int kne = k;
+ //unsigned int kse = ks;
+ //unsigned int knw = kw;
+ unsigned int kbw = neighborZ[kw];
+ //unsigned int kte = k;
+ //unsigned int kbe = kb;
+ //unsigned int ktw = kw;
+ unsigned int kbs = neighborZ[ks];
+ //unsigned int ktn = k;
+ //unsigned int kbn = kb;
+ //unsigned int kts = ks;
+ //unsigned int ktse = ks;
+ //unsigned int kbnw = kbw;
+ //unsigned int ktnw = kw;
+ //unsigned int kbse = kbs;
+ //unsigned int ktsw = ksw;
+ //unsigned int kbne = kb;
+ //unsigned int ktne = k;
+ unsigned int kbsw = neighborZ[ksw];
+
+
+
+ //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ real mfcbb = (D.f[dirE])[k];//[ke ];// + c2over27 ;(D.f[dirE ])[k ];//ke
+ real mfabb = (D.f[dirW])[kw];//[kw ];// + c2over27 ;(D.f[dirW ])[kw ];
+ real mfbcb = (D.f[dirN])[k];//[kn ];// + c2over27 ;(D.f[dirN ])[k ];//kn
+ real mfbab = (D.f[dirS])[ks];//[ks ];// + c2over27 ;(D.f[dirS ])[ks ];
+ real mfbbc = (D.f[dirT])[k];//[kt ];// + c2over27 ;(D.f[dirT ])[k ];//kt
+ real mfbba = (D.f[dirB])[kb];//[kb ];// + c2over27 ;(D.f[dirB ])[kb ];
+ real mfccb = (D.f[dirNE])[k];//[kne ];// + c1over54 ;(D.f[dirNE ])[k ];//kne
+ real mfaab = (D.f[dirSW])[ksw];//[ksw ];// + c1over54 ;(D.f[dirSW ])[ksw];
+ real mfcab = (D.f[dirSE])[ks];//[kse ];// + c1over54 ;(D.f[dirSE ])[ks ];//kse
+ real mfacb = (D.f[dirNW])[kw];//[knw ];// + c1over54 ;(D.f[dirNW ])[kw ];//knw
+ real mfcbc = (D.f[dirTE])[k];//[kte ];// + c1over54 ;(D.f[dirTE ])[k ];//kte
+ real mfaba = (D.f[dirBW])[kbw];//[kbw ];// + c1over54 ;(D.f[dirBW ])[kbw];
+ real mfcba = (D.f[dirBE])[kb];//[kbe ];// + c1over54 ;(D.f[dirBE ])[kb ];//kbe
+ real mfabc = (D.f[dirTW])[kw];//[ktw ];// + c1over54 ;(D.f[dirTW ])[kw ];//ktw
+ real mfbcc = (D.f[dirTN])[k];//[ktn ];// + c1over54 ;(D.f[dirTN ])[k ];//ktn
+ real mfbaa = (D.f[dirBS])[kbs];//[kbs ];// + c1over54 ;(D.f[dirBS ])[kbs];
+ real mfbca = (D.f[dirBN])[kb];//[kbn ];// + c1over54 ;(D.f[dirBN ])[kb ];//kbn
+ real mfbac = (D.f[dirTS])[ks];//[kts ];// + c1over54 ;(D.f[dirTS ])[ks ];//kts
+ real mfbbb = (D.f[dirZERO])[k];//[kzero];// + c8over27 ;(D.f[dirZERO])[k ];//kzero
+ real mfccc = (D.f[dirTNE])[k];//[ktne ];// + c1over216;(D.f[dirTNE ])[k ];//ktne
+ real mfaac = (D.f[dirTSW])[ksw];//[ktsw ];// + c1over216;(D.f[dirTSW ])[ksw];//ktsw
+ real mfcac = (D.f[dirTSE])[ks];//[ktse ];// + c1over216;(D.f[dirTSE ])[ks ];//ktse
+ real mfacc = (D.f[dirTNW])[kw];//[ktnw ];// + c1over216;(D.f[dirTNW ])[kw ];//ktnw
+ real mfcca = (D.f[dirBNE])[kb];//[kbne ];// + c1over216;(D.f[dirBNE ])[kb ];//kbne
+ real mfaaa = (D.f[dirBSW])[kbsw];//[kbsw ];// + c1over216;(D.f[dirBSW ])[kbsw];
+ real mfcaa = (D.f[dirBSE])[kbs];//[kbse ];// + c1over216;(D.f[dirBSE ])[kbs];//kbse
+ real mfaca = (D.f[dirBNW])[kbw];//[kbnw ];// + c1over216;(D.f[dirBNW ])[kbw];//kbnw
+ ////////////////////////////////////////////////////////////////////////////////////
+ real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+
+ real rho = c1o1 + drho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
+ (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
+ (mfcbb - mfabb)) / rho;
+ real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
+ (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
+ (mfbcb - mfbab)) / rho;
+ real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
+ (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
+ (mfbbc - mfbba)) / rho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
+ real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
+ real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
+ vvx += fx*c1o2;
+ vvy += fy*c1o2;
+ vvz += fz*c1o2;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real omega = omega_in;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //fast
+ //real oMdrho = c1o1; // comp special
+ //real m0, m1, m2;
+ real vx2;
+ real vy2;
+ real vz2;
+ vx2 = vvx*vvx;
+ vy2 = vvy*vvy;
+ vz2 = vvz*vvz;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real wadjust;
+ //real qudricLimitP = c1o100;// * 0.0001f;
+ //real qudricLimitM = c1o100;// * 0.0001f;
+ //real qudricLimitD = c1o100;// * 0.001f;
+ //real s9 = minusomega;
+ //test
+ //s9 = 0.;
+
+
+ //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ real EQcbb = c0o1;
+ real EQabb = c0o1;
+ real EQbcb = c0o1;
+ real EQbab = c0o1;
+ real EQbbc = c0o1;
+ real EQbba = c0o1;
+ real EQccb = c0o1;
+ real EQaab = c0o1;
+ real EQcab = c0o1;
+ real EQacb = c0o1;
+ real EQcbc = c0o1;
+ real EQaba = c0o1;
+ real EQcba = c0o1;
+ real EQabc = c0o1;
+ real EQbcc = c0o1;
+ real EQbaa = c0o1;
+ real EQbca = c0o1;
+ real EQbac = c0o1;
+ real EQbbb = c0o1;
+ real EQccc = drho * c1o27;
+ real EQaac = drho * c1o3;
+ real EQcac = drho * c1o9;
+ real EQacc = drho * c1o9;
+ real EQcca = drho * c1o9;
+ real EQaaa = drho;
+ real EQcaa = drho * c1o3;
+ real EQaca = drho * c1o3;
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::backwardChimeraWithK(EQaaa, EQaab, EQaac, vvz, vz2, c1o1);
+ vf::lbm::backwardChimeraWithK(EQaca, EQacb, EQacc, vvz, vz2, c1o3);
+ ///////////////////////////////////////////////////////////
+ EQcaa = EQaca; EQcab = EQacb; EQcac = EQacc;
+ ///////////////////////////////////////////////////////////
+ vf::lbm::backwardChimeraWithK(EQcca, EQccb, EQccc, vvz, vz2, c1o9);
+
+ vf::lbm::backwardChimeraWithK(EQaaa, EQaba, EQaca, vvy, vy2, c1o6);
+ vf::lbm::backwardChimeraWithK(EQaab, EQabb, EQacb, vvy, vy2, c2o3);
+ vf::lbm::backwardChimeraWithK(EQaac, EQabc, EQacc, vvy, vy2, c1o6);
+ vf::lbm::backwardChimeraWithK(EQcaa, EQcba, EQcca, vvy, vy2, c1o18);
+ vf::lbm::backwardChimeraWithK(EQcab, EQcbb, EQccb, vvy, vy2, c2o9);
+ vf::lbm::backwardChimeraWithK(EQcac, EQcbc, EQccc, vvy, vy2, c1o18);
+
+ vf::lbm::backwardChimeraWithK(EQaaa, EQbaa, EQcaa, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQaab, EQbab, EQcab, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQaac, EQbac, EQcac, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQaba, EQbba, EQcba, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQabb, EQbbb, EQcbb, vvx, vx2, c4o9);
+ vf::lbm::backwardChimeraWithK(EQabc, EQbbc, EQcbc, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQaca, EQbca, EQcca, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQacb, EQbcb, EQccb, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQacc, EQbcc, EQccc, vvx, vx2, c1o36);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //Pre-condition
+ mfcbb -= EQcbb;
+ mfabb -= EQabb;
+ mfbcb -= EQbcb;
+ mfbab -= EQbab;
+ mfbbc -= EQbbc;
+ mfbba -= EQbba;
+ mfccb -= EQccb;
+ mfaab -= EQaab;
+ mfcab -= EQcab;
+ mfacb -= EQacb;
+ mfcbc -= EQcbc;
+ mfaba -= EQaba;
+ mfcba -= EQcba;
+ mfabc -= EQabc;
+ mfbcc -= EQbcc;
+ mfbaa -= EQbaa;
+ mfbca -= EQbca;
+ mfbac -= EQbac;
+ mfbbb -= EQbbb;
+ mfccc -= EQccc;
+ mfaac -= EQaac;
+ mfcac -= EQcac;
+ mfacc -= EQacc;
+ mfcca -= EQcca;
+ mfaaa -= EQaaa;
+ mfcaa -= EQcaa;
+ mfaca -= EQaca;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //Hin
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::forwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
+ vf::lbm::forwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ vf::lbm::forwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
+ vf::lbm::forwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ vf::lbm::forwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ vf::lbm::forwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ vf::lbm::forwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
+ vf::lbm::forwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ vf::lbm::forwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
+
+ vf::lbm::forwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
+ vf::lbm::forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::forwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
+ vf::lbm::forwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
+ vf::lbm::forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::forwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
+ vf::lbm::forwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
+ vf::lbm::forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::forwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
+
+ vf::lbm::forwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
+ vf::lbm::forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::forwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
+ vf::lbm::forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::forwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
+ vf::lbm::forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::forwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////Hin
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Z - Dir
+ //forwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c4o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Y - Dir
+ //forwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c2o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c2o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// X - Dir
+ //forwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, one);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Cumulants
+ ////////////////////////////////////////////////////////////////////////////////////
+ real OxxPyyPzz = c1o1; //omega; // one; //set the bulk viscosity one is high / two is very low and zero is (too) high
+
+ ////////////////////////////////////////////////////////////
+ //3.
+ //////////////////////////////
+ real OxyyPxzz = c1o1;
+ real OxyyMxzz = c1o1;
+ //real Oxyz = c1o1;
+ ////////////////////////////////////////////////////////////
+ //4.
+ //////////////////////////////
+ real O4 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //5.
+ //////////////////////////////
+ real O5 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //6.
+ //////////////////////////////
+ real O6 = c1o1;
+ ////////////////////////////////////////////////////////////
+
+
+ //central moments to cumulants
+ //4.
+ real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
+ real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
+ real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
+
+ real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
+ real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
+ real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
+
+ //5.
+ real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
+ real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
+ real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
+
+ //6.
+
+ real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
+ - c1o3 * (mfacc + mfcac + mfcca) / rho
+ - c1o9 * (mfcaa + mfaca + mfaac) / rho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
+ + c1o27*((drho * drho - drho) / (rho*rho)));
+
+
+
+
+ //2.
+ // linear combinations
+ real mxxPyyPzz = mfcaa + mfaca + mfaac;
+ real mxxMyy = mfcaa - mfaca;
+ real mxxMzz = mfcaa - mfaac;
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
+ {
+ real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
+ real dyuy = dxux + omega * c3o2 * mxxMyy;
+ real dzuz = dxux + omega * c3o2 * mxxMzz;
+
+ //relax
+ mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz) - c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
+ mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
+ mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
+
+ }
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ ////no correction
+ //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
+ //mxxMyy += -(-omega) * (-mxxMyy);
+ //mxxMzz += -(-omega) * (-mxxMzz);
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ mfabb += omega * (-mfabb);
+ mfbab += omega * (-mfbab);
+ mfbba += omega * (-mfbba);
+
+ //////////////////////////////////////////////////////////////////////////
+
+ // linear combinations back
+ mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
+
+ //3.
+ // linear combinations
+
+ real mxxyPyzz = mfcba + mfabc;
+ real mxxyMyzz = mfcba - mfabc;
+
+ real mxxzPyyz = mfcab + mfacb;
+ real mxxzMyyz = mfcab - mfacb;
+
+ real mxyyPxzz = mfbca + mfbac;
+ real mxyyMxzz = mfbca - mfbac;
+
+ //relax
+ //////////////////////////////////////////////////////////////////////////
+ mfbbb += OxyyMxzz * (-mfbbb);
+ mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
+ mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
+ mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
+ mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
+ mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
+ mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
+ //////////////////////////////////////////////////////////////////////////
+
+ mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
+ mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
+ mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
+ mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
+ mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
+ mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
+
+ //4.
+ //////////////////////////////////////////////////////////////////////////
+ CUMacc += O4 * (-CUMacc);
+ CUMcac += O4 * (-CUMcac);
+ CUMcca += O4 * (-CUMcca);
+
+ CUMbbc += O4 * (-CUMbbc);
+ CUMbcb += O4 * (-CUMbcb);
+ CUMcbb += O4 * (-CUMcbb);
+ //////////////////////////////////////////////////////////////////////////
+
+
+ //5.
+ CUMbcc += O5 * (-CUMbcc);
+ CUMcbc += O5 * (-CUMcbc);
+ CUMccb += O5 * (-CUMccb);
+
+ //6.
+ CUMccc += O6 * (-CUMccc);
+
+
+
+ //back cumulants to central moments
+ //4.
+ mfcbb = CUMcbb + ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
+ mfbcb = CUMbcb + ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
+ mfbbc = CUMbbc + ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
+
+ mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
+ mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
+ mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
+
+ //5.
+ mfbcc = CUMbcc + ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
+ mfcbc = CUMcbc + ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
+ mfccb = CUMccb + ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
+
+ //6.
+ mfccc = CUMccc - ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
+ - c1o3 * (mfacc + mfcac + mfcca) / rho
+ - c1o9 * (mfcaa + mfaca + mfaac) / rho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
+ + c1o27*((drho * drho - drho) / (rho*rho)));
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ mfbaa = -mfbaa;
+ mfaba = -mfaba;
+ mfaab = -mfaab;
+ ////////////////////////////////////////////////////////////////////////////////////
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //back
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::backwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
+ vf::lbm::backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ vf::lbm::backwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
+ vf::lbm::backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ vf::lbm::backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ vf::lbm::backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ vf::lbm::backwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
+ vf::lbm::backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ vf::lbm::backwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
+
+ vf::lbm::backwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
+ vf::lbm::backwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::backwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
+ vf::lbm::backwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
+ vf::lbm::backwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::backwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
+ vf::lbm::backwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
+ vf::lbm::backwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::backwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
+
+ vf::lbm::backwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
+ vf::lbm::backwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::backwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
+ vf::lbm::backwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::backwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::backwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::backwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
+ vf::lbm::backwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::backwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //mfcbb += EQcbb;
+ //mfabb += EQabb;
+ //mfbcb += EQbcb;
+ //mfbab += EQbab;
+ //mfbbc += EQbbc;
+ //mfbba += EQbba;
+ //mfccb += EQccb;
+ //mfaab += EQaab;
+ //mfcab += EQcab;
+ //mfacb += EQacb;
+ //mfcbc += EQcbc;
+ //mfaba += EQaba;
+ //mfcba += EQcba;
+ //mfabc += EQabc;
+ //mfbcc += EQbcc;
+ //mfbaa += EQbaa;
+ //mfbca += EQbca;
+ //mfbac += EQbac;
+ //mfbbb += EQbbb;
+ //mfccc += EQccc;
+ //mfaac += EQaac;
+ //mfcac += EQcac;
+ //mfacc += EQacc;
+ //mfcca += EQcca;
+ //mfaaa += EQaaa;
+ //mfcaa += EQcaa;
+ //mfaca += EQaca;
+ ////////////////////////////////////////////////////////////////////////////////////
+ ////Error diffusion
+ real fTEMP = mfbbb + EQbbb;
+ real delta0 = mfbbb - (fTEMP - EQbbb);
+ delta0 *= c1o4;
+ mfbbb = fTEMP;
+
+
+ fTEMP = mfcbb + EQcbb;
+ real deltacbb = mfcbb - (fTEMP - EQcbb);
+ mfcbb = fTEMP;
+ //mfcbb+=EQcbb;
+
+ fTEMP = mfabb + EQabb;
+ real deltaabb = mfabb - (fTEMP - EQabb);
+ mfabb = fTEMP;
+ //mfabb+=EQabb;
+
+ fTEMP = mfbcb + EQbcb;
+ real deltabcb = mfbcb - (fTEMP - EQbcb);
+ mfbcb = fTEMP;
+ //mfbcb+=EQbcb;
+
+ fTEMP = mfbab + EQbab;
+ real deltabab = mfbab - (fTEMP - EQbab);
+ mfbab = fTEMP;
+ //mfbab+=EQbab;
+
+ fTEMP = mfbbc + EQbbc;
+ real deltabbc = mfbbc - (fTEMP - EQbbc);
+ mfbbc = fTEMP;
+ //mfbbc+=EQbbc;
+
+ fTEMP = mfbba + EQbba;
+ real deltabba = mfbba - (fTEMP - EQbba);
+ mfbba = fTEMP;
+ //mfbba+=EQbba;
+
+ EQccb += (delta0 + c1o2*(deltacbb + deltabcb));
+ fTEMP = mfccb + EQccb;
+ real deltaccb = mfccb - (fTEMP - EQccb);
+ mfccb = fTEMP;
+ //mfccb+=EQccb+(delta0+c1o2*(deltacbb+deltabcb));
+
+ EQaab += (delta0 + c1o2*(deltaabb + deltabab));
+ fTEMP = mfaab + EQaab;
+ real deltaaab = mfaab - (fTEMP - EQaab);
+ mfaab = fTEMP;
+ //mfaab+=EQaab+(delta0+c1o2*(deltaabb+deltabab));
+
+ EQcab += (delta0 + c1o2*(deltacbb + deltabab));
+ fTEMP = mfcab + EQcab;
+ real deltacab = mfcab - (fTEMP - EQcab);
+ mfcab = fTEMP;
+ //mfcab+=EQcab+(delta0+c1o2*(deltacbb+deltabab));
+
+ EQacb += (delta0 + c1o2*(deltaabb + deltabcb));
+ fTEMP = mfacb + EQacb;
+ real deltaacb = mfacb - (fTEMP - EQacb);
+ mfacb = fTEMP;
+ //mfacb+=EQacb+(delta0+c1o2*(deltaabb+deltabcb));
+
+ EQcbc += (delta0 + c1o2*(deltacbb + deltabbc));
+ fTEMP = mfcbc + EQcbc;
+ real deltacbc = mfcbc - (fTEMP - EQcbc);
+ mfcbc = fTEMP;
+ //mfcbc+=EQcbc+(delta0+c1o2*(deltacbb+deltabbc));
+
+ EQaba += (delta0 + c1o2*(deltaabb + deltabba));
+ fTEMP = mfaba + EQaba;
+ real deltaaba = mfaba - (fTEMP - EQaba);
+ mfaba = fTEMP;
+ //mfaba+=EQaba+(delta0+c1o2*(deltaabb+deltabba));
+
+ EQcba += (delta0 + c1o2*(deltacbb + deltabba));
+ fTEMP = mfcba + EQcba;
+ real deltacba = mfcba - (fTEMP - EQcba);
+ mfcba = fTEMP;
+ //mfcba+=EQcba+(delta0+c1o2*(deltacbb+deltabba));
+
+ EQabc += (delta0 + c1o2*(deltaabb + deltabbc));
+ fTEMP = mfabc + EQabc;
+ real deltaabc = mfabc - (fTEMP - EQabc);
+ mfabc = fTEMP;
+ //mfabc+=EQabc+(delta0+c1o2*(deltaabb+deltabbc));
+
+ EQbcc += (delta0 + c1o2*(deltabcb + deltabbc));
+ fTEMP = mfbcc + EQbcc;
+ real deltabcc = mfbcc - (fTEMP - EQbcc);
+ mfbcc = fTEMP;
+ //mfbcc+=EQbcc+(delta0+c1o2*(deltabcb+deltabbc));
+
+ EQbaa += (delta0 + c1o2*(deltabab + deltabba));
+ fTEMP = mfbaa + EQbaa;
+ real deltabaa = mfbaa - (fTEMP - EQbaa);
+ mfbaa = fTEMP;
+ //mfbaa+=EQbaa+(delta0+c1o2*(deltabab+deltabba));
+
+ EQbca += (delta0 + c1o2*(deltabcb + deltabba));
+ fTEMP = mfbca + EQbca;
+ real deltabca = mfbca - (fTEMP - EQbca);
+ mfbca = fTEMP;
+ //mfbca+=EQbca+(delta0+c1o2*(deltabcb+deltabba));
+
+ EQbac += (delta0 + c1o2*(deltabab + deltabbc));
+ fTEMP = mfbac + EQbac;
+ real deltabac = mfbac - (fTEMP - EQbac);
+ mfbac = fTEMP;
+ //mfbac+=EQbac+(delta0+c1o2*(deltabab+deltabbc));
+
+ mfccc += EQccc - (delta0 + c1o4*(deltacbb + deltabcb + deltabbc) - c1o2*(deltabcc + deltacbc + deltaccb));
+ mfaac += EQaac - (delta0 + c1o4*(deltaabb + deltabab + deltabbc) - c1o2*(deltabac + deltaabc + deltaaab));
+ mfcac += EQcac - (delta0 + c1o4*(deltacbb + deltabab + deltabbc) - c1o2*(deltabac + deltacbc + deltacab));
+ mfacc += EQacc - (delta0 + c1o4*(deltaabb + deltabcb + deltabbc) - c1o2*(deltabcc + deltaabc + deltaacb));
+ mfcca += EQcca - (delta0 + c1o4*(deltacbb + deltabcb + deltabba) - c1o2*(deltabca + deltacba + deltaccb));
+ mfaaa += EQaaa - (delta0 + c1o4*(deltaabb + deltabab + deltabba) - c1o2*(deltabaa + deltaaba + deltaaab));
+ mfcaa += EQcaa - (delta0 + c1o4*(deltacbb + deltabab + deltabba) - c1o2*(deltabaa + deltacba + deltacab));
+ mfaca += EQaca - (delta0 + c1o4*(deltaabb + deltabcb + deltabba) - c1o2*(deltabca + deltaaba + deltaacb));
+
+
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////back
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Z - Dir
+ //backwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, one);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o3);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Y - Dir
+ //backwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaab, mfabb, mfacb, vvy, vy2, c2o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbaa, mfbba, mfbca, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbab, mfbbb, mfbcb, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbac, mfbbc, mfbcc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o18);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcab, mfcbb, mfccb, vvy, vy2, c2o9);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// X - Dir
+ //backwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaba, mfbba, mfcba, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaab, mfbab, mfcab, vvx, vx2, c1o9);
+ /////////////b////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfabb, mfbbb, mfcbb, vvx, vx2, c4o9);
+ /////////////b////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfacb, mfbcb, mfccb, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o36);
+ /////////////c////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfabc, mfbbc, mfcbc, vvx, vx2, c1o9);
+ /////////////c////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+
+ ////////////////////////////////////////////////////////////////////////////////////////
+ //real drhoPost =
+ // ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ // (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ // ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+ //mfbbb += drho - drhoPost;
+ ////////////////////////////////////////////////////////////////////////////////////
+ (D.f[dirE])[k] = mfabb;//(D.f[ dirE ])[ke ] = mfabb;// - c2over27 ; (D.f[ dirE ])[k ]
+ (D.f[dirW])[kw] = mfcbb;//(D.f[ dirW ])[kw ] = mfcbb;// - c2over27 ; (D.f[ dirW ])[kw ]
+ (D.f[dirN])[k] = mfbab;//(D.f[ dirN ])[kn ] = mfbab;// - c2over27 ; (D.f[ dirN ])[k ]
+ (D.f[dirS])[ks] = mfbcb;//(D.f[ dirS ])[ks ] = mfbcb;// - c2over27 ; (D.f[ dirS ])[ks ]
+ (D.f[dirT])[k] = mfbba;//(D.f[ dirT ])[kt ] = mfbba;// - c2over27 ; (D.f[ dirT ])[k ]
+ (D.f[dirB])[kb] = mfbbc;//(D.f[ dirB ])[kb ] = mfbbc;// - c2over27 ; (D.f[ dirB ])[kb ]
+ (D.f[dirNE])[k] = mfaab;//(D.f[ dirNE ])[kne ] = mfaab;// - c1over54 ; (D.f[ dirNE ])[k ]
+ (D.f[dirSW])[ksw] = mfccb;//(D.f[ dirSW ])[ksw ] = mfccb;// - c1over54 ; (D.f[ dirSW ])[ksw ]
+ (D.f[dirSE])[ks] = mfacb;//(D.f[ dirSE ])[kse ] = mfacb;// - c1over54 ; (D.f[ dirSE ])[ks ]
+ (D.f[dirNW])[kw] = mfcab;//(D.f[ dirNW ])[knw ] = mfcab;// - c1over54 ; (D.f[ dirNW ])[kw ]
+ (D.f[dirTE])[k] = mfaba;//(D.f[ dirTE ])[kte ] = mfaba;// - c1over54 ; (D.f[ dirTE ])[k ]
+ (D.f[dirBW])[kbw] = mfcbc;//(D.f[ dirBW ])[kbw ] = mfcbc;// - c1over54 ; (D.f[ dirBW ])[kbw ]
+ (D.f[dirBE])[kb] = mfabc;//(D.f[ dirBE ])[kbe ] = mfabc;// - c1over54 ; (D.f[ dirBE ])[kb ]
+ (D.f[dirTW])[kw] = mfcba;//(D.f[ dirTW ])[ktw ] = mfcba;// - c1over54 ; (D.f[ dirTW ])[kw ]
+ (D.f[dirTN])[k] = mfbaa;//(D.f[ dirTN ])[ktn ] = mfbaa;// - c1over54 ; (D.f[ dirTN ])[k ]
+ (D.f[dirBS])[kbs] = mfbcc;//(D.f[ dirBS ])[kbs ] = mfbcc;// - c1over54 ; (D.f[ dirBS ])[kbs ]
+ (D.f[dirBN])[kb] = mfbac;//(D.f[ dirBN ])[kbn ] = mfbac;// - c1over54 ; (D.f[ dirBN ])[kb ]
+ (D.f[dirTS])[ks] = mfbca;//(D.f[ dirTS ])[kts ] = mfbca;// - c1over54 ; (D.f[ dirTS ])[ks ]
+ (D.f[dirZERO])[k] = mfbbb;//(D.f[ dirZERO])[kzero] = mfbbb;// - c8over27 ; (D.f[ dirZERO])[k ]
+ (D.f[dirTNE])[k] = mfaaa;//(D.f[ dirTNE ])[ktne ] = mfaaa;// - c1over216; (D.f[ dirTNE ])[k ]
+ (D.f[dirTSE])[ks] = mfaca;//(D.f[ dirTSE ])[ktse ] = mfaca;// - c1over216; (D.f[ dirTSE ])[ks ]
+ (D.f[dirBNE])[kb] = mfaac;//(D.f[ dirBNE ])[kbne ] = mfaac;// - c1over216; (D.f[ dirBNE ])[kb ]
+ (D.f[dirBSE])[kbs] = mfacc;//(D.f[ dirBSE ])[kbse ] = mfacc;// - c1over216; (D.f[ dirBSE ])[kbs ]
+ (D.f[dirTNW])[kw] = mfcaa;//(D.f[ dirTNW ])[ktnw ] = mfcaa;// - c1over216; (D.f[ dirTNW ])[kw ]
+ (D.f[dirTSW])[ksw] = mfcca;//(D.f[ dirTSW ])[ktsw ] = mfcca;// - c1over216; (D.f[ dirTSW ])[ksw ]
+ (D.f[dirBNW])[kbw] = mfcac;//(D.f[ dirBNW ])[kbnw ] = mfcac;// - c1over216; (D.f[ dirBNW ])[kbw ]
+ (D.f[dirBSW])[kbsw] = mfccc;//(D.f[ dirBSW ])[kbsw ] = mfccc;// - c1over216; (D.f[ dirBSW ])[kbsw]
+ ////////////////////////////////////////////////////////////////////////////////////
+ }
+ }
}
////////////////////////////////////////////////////////////////////////////////
@@ -1002,758 +958,758 @@ extern "C" __global__ void Cumulant_One_preconditioned_errorDiffusion_chim_Comp_
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void Cumulant_One_preconditioned_chim_Comp_SP_27(
- real omega,
- unsigned int* bcMatD,
- unsigned int* neighborX,
- unsigned int* neighborY,
- unsigned int* neighborZ,
- real* DDStart,
- int size_Mat,
- int level,
- real* forces,
- bool EvenOrOdd)
+ real omega,
+ unsigned int* bcMatD,
+ unsigned int* neighborX,
+ unsigned int* neighborY,
+ unsigned int* neighborZ,
+ real* DDStart,
+ int size_Mat,
+ int level,
+ real* forces,
+ bool EvenOrOdd)
{
- ////////////////////////////////////////////////////////////////////////////////
- const unsigned x = threadIdx.x; // Globaler x-Index
- const unsigned y = blockIdx.x; // Globaler y-Index
- const unsigned z = blockIdx.y; // Globaler z-Index
-
- const unsigned nx = blockDim.x;
- const unsigned ny = gridDim.x;
-
- const unsigned k = nx*(ny*z + y) + x;
- //////////////////////////////////////////////////////////////////////////
-
- if (k<size_Mat)
- {
- ////////////////////////////////////////////////////////////////////////////////
- unsigned int BC;
- BC = bcMatD[k];
-
- if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
- {
- Distributions27 D;
- if (EvenOrOdd == true)
- {
- D.f[dirE] = &DDStart[dirE *size_Mat];
- D.f[dirW] = &DDStart[dirW *size_Mat];
- D.f[dirN] = &DDStart[dirN *size_Mat];
- D.f[dirS] = &DDStart[dirS *size_Mat];
- D.f[dirT] = &DDStart[dirT *size_Mat];
- D.f[dirB] = &DDStart[dirB *size_Mat];
- D.f[dirNE] = &DDStart[dirNE *size_Mat];
- D.f[dirSW] = &DDStart[dirSW *size_Mat];
- D.f[dirSE] = &DDStart[dirSE *size_Mat];
- D.f[dirNW] = &DDStart[dirNW *size_Mat];
- D.f[dirTE] = &DDStart[dirTE *size_Mat];
- D.f[dirBW] = &DDStart[dirBW *size_Mat];
- D.f[dirBE] = &DDStart[dirBE *size_Mat];
- D.f[dirTW] = &DDStart[dirTW *size_Mat];
- D.f[dirTN] = &DDStart[dirTN *size_Mat];
- D.f[dirBS] = &DDStart[dirBS *size_Mat];
- D.f[dirBN] = &DDStart[dirBN *size_Mat];
- D.f[dirTS] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirTNE] = &DDStart[dirTNE *size_Mat];
- D.f[dirTSW] = &DDStart[dirTSW *size_Mat];
- D.f[dirTSE] = &DDStart[dirTSE *size_Mat];
- D.f[dirTNW] = &DDStart[dirTNW *size_Mat];
- D.f[dirBNE] = &DDStart[dirBNE *size_Mat];
- D.f[dirBSW] = &DDStart[dirBSW *size_Mat];
- D.f[dirBSE] = &DDStart[dirBSE *size_Mat];
- D.f[dirBNW] = &DDStart[dirBNW *size_Mat];
- }
- else
- {
- D.f[dirW] = &DDStart[dirE *size_Mat];
- D.f[dirE] = &DDStart[dirW *size_Mat];
- D.f[dirS] = &DDStart[dirN *size_Mat];
- D.f[dirN] = &DDStart[dirS *size_Mat];
- D.f[dirB] = &DDStart[dirT *size_Mat];
- D.f[dirT] = &DDStart[dirB *size_Mat];
- D.f[dirSW] = &DDStart[dirNE *size_Mat];
- D.f[dirNE] = &DDStart[dirSW *size_Mat];
- D.f[dirNW] = &DDStart[dirSE *size_Mat];
- D.f[dirSE] = &DDStart[dirNW *size_Mat];
- D.f[dirBW] = &DDStart[dirTE *size_Mat];
- D.f[dirTE] = &DDStart[dirBW *size_Mat];
- D.f[dirTW] = &DDStart[dirBE *size_Mat];
- D.f[dirBE] = &DDStart[dirTW *size_Mat];
- D.f[dirBS] = &DDStart[dirTN *size_Mat];
- D.f[dirTN] = &DDStart[dirBS *size_Mat];
- D.f[dirTS] = &DDStart[dirBN *size_Mat];
- D.f[dirBN] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirBSW] = &DDStart[dirTNE *size_Mat];
- D.f[dirBNE] = &DDStart[dirTSW *size_Mat];
- D.f[dirBNW] = &DDStart[dirTSE *size_Mat];
- D.f[dirBSE] = &DDStart[dirTNW *size_Mat];
- D.f[dirTSW] = &DDStart[dirBNE *size_Mat];
- D.f[dirTNE] = &DDStart[dirBSW *size_Mat];
- D.f[dirTNW] = &DDStart[dirBSE *size_Mat];
- D.f[dirTSE] = &DDStart[dirBNW *size_Mat];
- }
-
- ////////////////////////////////////////////////////////////////////////////////
- //index
- //unsigned int kzero= k;
- //unsigned int ke = k;
- unsigned int kw = neighborX[k];
- //unsigned int kn = k;
- unsigned int ks = neighborY[k];
- //unsigned int kt = k;
- unsigned int kb = neighborZ[k];
- unsigned int ksw = neighborY[kw];
- //unsigned int kne = k;
- //unsigned int kse = ks;
- //unsigned int knw = kw;
- unsigned int kbw = neighborZ[kw];
- //unsigned int kte = k;
- //unsigned int kbe = kb;
- //unsigned int ktw = kw;
- unsigned int kbs = neighborZ[ks];
- //unsigned int ktn = k;
- //unsigned int kbn = kb;
- //unsigned int kts = ks;
- //unsigned int ktse = ks;
- //unsigned int kbnw = kbw;
- //unsigned int ktnw = kw;
- //unsigned int kbse = kbs;
- //unsigned int ktsw = ksw;
- //unsigned int kbne = kb;
- //unsigned int ktne = k;
- unsigned int kbsw = neighborZ[ksw];
-
-
-
- //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- real mfcbb = (D.f[dirE])[k];//[ke ];// + c2over27 ;(D.f[dirE ])[k ];//ke
- real mfabb = (D.f[dirW])[kw];//[kw ];// + c2over27 ;(D.f[dirW ])[kw ];
- real mfbcb = (D.f[dirN])[k];//[kn ];// + c2over27 ;(D.f[dirN ])[k ];//kn
- real mfbab = (D.f[dirS])[ks];//[ks ];// + c2over27 ;(D.f[dirS ])[ks ];
- real mfbbc = (D.f[dirT])[k];//[kt ];// + c2over27 ;(D.f[dirT ])[k ];//kt
- real mfbba = (D.f[dirB])[kb];//[kb ];// + c2over27 ;(D.f[dirB ])[kb ];
- real mfccb = (D.f[dirNE])[k];//[kne ];// + c1over54 ;(D.f[dirNE ])[k ];//kne
- real mfaab = (D.f[dirSW])[ksw];//[ksw ];// + c1over54 ;(D.f[dirSW ])[ksw];
- real mfcab = (D.f[dirSE])[ks];//[kse ];// + c1over54 ;(D.f[dirSE ])[ks ];//kse
- real mfacb = (D.f[dirNW])[kw];//[knw ];// + c1over54 ;(D.f[dirNW ])[kw ];//knw
- real mfcbc = (D.f[dirTE])[k];//[kte ];// + c1over54 ;(D.f[dirTE ])[k ];//kte
- real mfaba = (D.f[dirBW])[kbw];//[kbw ];// + c1over54 ;(D.f[dirBW ])[kbw];
- real mfcba = (D.f[dirBE])[kb];//[kbe ];// + c1over54 ;(D.f[dirBE ])[kb ];//kbe
- real mfabc = (D.f[dirTW])[kw];//[ktw ];// + c1over54 ;(D.f[dirTW ])[kw ];//ktw
- real mfbcc = (D.f[dirTN])[k];//[ktn ];// + c1over54 ;(D.f[dirTN ])[k ];//ktn
- real mfbaa = (D.f[dirBS])[kbs];//[kbs ];// + c1over54 ;(D.f[dirBS ])[kbs];
- real mfbca = (D.f[dirBN])[kb];//[kbn ];// + c1over54 ;(D.f[dirBN ])[kb ];//kbn
- real mfbac = (D.f[dirTS])[ks];//[kts ];// + c1over54 ;(D.f[dirTS ])[ks ];//kts
- real mfbbb = (D.f[dirZERO])[k];//[kzero];// + c8over27 ;(D.f[dirZERO])[k ];//kzero
- real mfccc = (D.f[dirTNE])[k];//[ktne ];// + c1over216;(D.f[dirTNE ])[k ];//ktne
- real mfaac = (D.f[dirTSW])[ksw];//[ktsw ];// + c1over216;(D.f[dirTSW ])[ksw];//ktsw
- real mfcac = (D.f[dirTSE])[ks];//[ktse ];// + c1over216;(D.f[dirTSE ])[ks ];//ktse
- real mfacc = (D.f[dirTNW])[kw];//[ktnw ];// + c1over216;(D.f[dirTNW ])[kw ];//ktnw
- real mfcca = (D.f[dirBNE])[kb];//[kbne ];// + c1over216;(D.f[dirBNE ])[kb ];//kbne
- real mfaaa = (D.f[dirBSW])[kbsw];//[kbsw ];// + c1over216;(D.f[dirBSW ])[kbsw];
- real mfcaa = (D.f[dirBSE])[kbs];//[kbse ];// + c1over216;(D.f[dirBSE ])[kbs];//kbse
- real mfaca = (D.f[dirBNW])[kbw];//[kbnw ];// + c1over216;(D.f[dirBNW ])[kbw];//kbnw
- ////////////////////////////////////////////////////////////////////////////////////
- real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
-
- real rho = c1o1 + drho;
- ////////////////////////////////////////////////////////////////////////////////////
- real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
- (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
- (mfcbb - mfabb)) / rho;
- real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
- (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
- (mfbcb - mfbab)) / rho;
- real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
- (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
- (mfbbc - mfbba)) / rho;
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
- real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
- real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
- vvx += fx*c1o2;
- vvy += fy*c1o2;
- vvz += fz*c1o2;
- ////////////////////////////////////////////////////////////////////////////////////
- //real omega = omega_in;
- ////////////////////////////////////////////////////////////////////////////////////
- //fast
- //real oMdrho = c1o1; // comp special
- //real m0, m1, m2;
- real vx2;
- real vy2;
- real vz2;
- vx2 = vvx*vvx;
- vy2 = vvy*vvy;
- vz2 = vvz*vvz;
- ////////////////////////////////////////////////////////////////////////////////////
- //real wadjust;
- //real qudricLimitP = c1o100;// * 0.0001f;
- //real qudricLimitM = c1o100;// * 0.0001f;
- //real qudricLimitD = c1o100;// * 0.001f;
- //real s9 = minusomega;
- //test
- //s9 = 0.;
-
-
- //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- real EQcbb = c0o1;
- real EQabb = c0o1;
- real EQbcb = c0o1;
- real EQbab = c0o1;
- real EQbbc = c0o1;
- real EQbba = c0o1;
- real EQccb = c0o1;
- real EQaab = c0o1;
- real EQcab = c0o1;
- real EQacb = c0o1;
- real EQcbc = c0o1;
- real EQaba = c0o1;
- real EQcba = c0o1;
- real EQabc = c0o1;
- real EQbcc = c0o1;
- real EQbaa = c0o1;
- real EQbca = c0o1;
- real EQbac = c0o1;
- real EQbbb = c0o1;
- real EQccc = drho * c1o27;
- real EQaac = drho * c1o3;
- real EQcac = drho * c1o9;
- real EQacc = drho * c1o9;
- real EQcca = drho * c1o9;
- real EQaaa = drho;
- real EQcaa = drho * c1o3;
- real EQaca = drho * c1o3;
- ////////////////////////////////////////////////////////////////////////////////////
- backwardChimeraWithK(EQaaa, EQaab, EQaac, vvz, vz2, c1o1);
- backwardChimeraWithK(EQaca, EQacb, EQacc, vvz, vz2, c1o3);
- ///////////////////////////////////////////////////////////
- EQcaa = EQaca; EQcab = EQacb; EQcac = EQacc;
- ///////////////////////////////////////////////////////////
- backwardChimeraWithK(EQcca, EQccb, EQccc, vvz, vz2, c1o9);
-
- backwardChimeraWithK(EQaaa, EQaba, EQaca, vvy, vy2, c1o6);
- backwardChimeraWithK(EQaab, EQabb, EQacb, vvy, vy2, c2o3);
- backwardChimeraWithK(EQaac, EQabc, EQacc, vvy, vy2, c1o6);
- backwardChimeraWithK(EQcaa, EQcba, EQcca, vvy, vy2, c1o18);
- backwardChimeraWithK(EQcab, EQcbb, EQccb, vvy, vy2, c2o9);
- backwardChimeraWithK(EQcac, EQcbc, EQccc, vvy, vy2, c1o18);
-
- backwardChimeraWithK(EQaaa, EQbaa, EQcaa, vvx, vx2, c1o36);
- backwardChimeraWithK(EQaab, EQbab, EQcab, vvx, vx2, c1o9);
- backwardChimeraWithK(EQaac, EQbac, EQcac, vvx, vx2, c1o36);
- backwardChimeraWithK(EQaba, EQbba, EQcba, vvx, vx2, c1o9);
- backwardChimeraWithK(EQabb, EQbbb, EQcbb, vvx, vx2, c4o9);
- backwardChimeraWithK(EQabc, EQbbc, EQcbc, vvx, vx2, c1o9);
- backwardChimeraWithK(EQaca, EQbca, EQcca, vvx, vx2, c1o36);
- backwardChimeraWithK(EQacb, EQbcb, EQccb, vvx, vx2, c1o9);
- backwardChimeraWithK(EQacc, EQbcc, EQccc, vvx, vx2, c1o36);
-
- ////////////////////////////////////////////////////////////////////////////////////
- //Pre-condition
- mfcbb -= EQcbb;
- mfabb -= EQabb;
- mfbcb -= EQbcb;
- mfbab -= EQbab;
- mfbbc -= EQbbc;
- mfbba -= EQbba;
- mfccb -= EQccb;
- mfaab -= EQaab;
- mfcab -= EQcab;
- mfacb -= EQacb;
- mfcbc -= EQcbc;
- mfaba -= EQaba;
- mfcba -= EQcba;
- mfabc -= EQabc;
- mfbcc -= EQbcc;
- mfbaa -= EQbaa;
- mfbca -= EQbca;
- mfbac -= EQbac;
- mfbbb -= EQbbb;
- mfccc -= EQccc;
- mfaac -= EQaac;
- mfcac -= EQcac;
- mfacc -= EQacc;
- mfcca -= EQcca;
- mfaaa -= EQaaa;
- mfcaa -= EQcaa;
- mfaca -= EQaca;
-
- ////////////////////////////////////////////////////////////////////////////////////
- //Hin
- ////////////////////////////////////////////////////////////////////////////////////
- forwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
- forwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- forwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
- forwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- forwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- forwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- forwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
- forwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- forwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
-
- forwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
- forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- forwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
- forwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
- forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- forwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
- forwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
- forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- forwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
-
- forwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
- forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- forwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
- forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- forwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
- forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- forwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
-
- //////////////////////////////////////////////////////////////////////////////////////
- ////Hin
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Z - Dir
- //forwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c4o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Y - Dir
- //forwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c2o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c2o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //// mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// X - Dir
- //forwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, one);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- //////////////////////////////////////////////////////////////////////////////////////
- //forwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
-
-
- ////////////////////////////////////////////////////////////////////////////////////
- // Cumulants
- ////////////////////////////////////////////////////////////////////////////////////
- real OxxPyyPzz = c1o1; //omega; // one; //set the bulk viscosity one is high / two is very low and zero is (too) high
-
- ////////////////////////////////////////////////////////////
- //3.
- //////////////////////////////
- real OxyyPxzz = c1o1;
- real OxyyMxzz = c1o1;
- //real Oxyz = c1o1;
- ////////////////////////////////////////////////////////////
- //4.
- //////////////////////////////
- real O4 = c1o1;
- ////////////////////////////////////////////////////////////
- //5.
- //////////////////////////////
- real O5 = c1o1;
- ////////////////////////////////////////////////////////////
- //6.
- //////////////////////////////
- real O6 = c1o1;
- ////////////////////////////////////////////////////////////
-
-
- //central moments to cumulants
- //4.
- real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
- real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
- real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
-
- real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
- real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
- real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
-
- //5.
- real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
- real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
- real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
-
- //6.
-
- real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
- - c1o3 * (mfacc + mfcac + mfcca) / rho
- - c1o9 * (mfcaa + mfaca + mfaac) / rho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
- + c1o27*((drho * drho - drho) / (rho*rho)));
-
-
-
-
- //2.
- // linear combinations
- real mxxPyyPzz = mfcaa + mfaca + mfaac;
- real mxxMyy = mfcaa - mfaca;
- real mxxMzz = mfcaa - mfaac;
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
- {
- real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
- real dyuy = dxux + omega * c3o2 * mxxMyy;
- real dzuz = dxux + omega * c3o2 * mxxMzz;
-
- //relax
- mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz) - c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
- mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
- mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
-
- }
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- ////no correction
- //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
- //mxxMyy += -(-omega) * (-mxxMyy);
- //mxxMzz += -(-omega) * (-mxxMzz);
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- mfabb += omega * (-mfabb);
- mfbab += omega * (-mfbab);
- mfbba += omega * (-mfbba);
-
- //////////////////////////////////////////////////////////////////////////
-
- // linear combinations back
- mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
- mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
- mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
-
- //3.
- // linear combinations
-
- real mxxyPyzz = mfcba + mfabc;
- real mxxyMyzz = mfcba - mfabc;
-
- real mxxzPyyz = mfcab + mfacb;
- real mxxzMyyz = mfcab - mfacb;
-
- real mxyyPxzz = mfbca + mfbac;
- real mxyyMxzz = mfbca - mfbac;
-
- //relax
- //////////////////////////////////////////////////////////////////////////
- mfbbb += OxyyMxzz * (-mfbbb);
- mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
- mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
- mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
- mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
- mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
- mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
- //////////////////////////////////////////////////////////////////////////
-
- mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
- mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
- mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
- mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
- mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
- mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
-
- //4.
- //////////////////////////////////////////////////////////////////////////
- CUMacc += O4 * (-CUMacc);
- CUMcac += O4 * (-CUMcac);
- CUMcca += O4 * (-CUMcca);
-
- CUMbbc += O4 * (-CUMbbc);
- CUMbcb += O4 * (-CUMbcb);
- CUMcbb += O4 * (-CUMcbb);
- //////////////////////////////////////////////////////////////////////////
-
-
- //5.
- CUMbcc += O5 * (-CUMbcc);
- CUMcbc += O5 * (-CUMcbc);
- CUMccb += O5 * (-CUMccb);
-
- //6.
- CUMccc += O6 * (-CUMccc);
-
-
-
- //back cumulants to central moments
- //4.
- mfcbb = CUMcbb + ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
- mfbcb = CUMbcb + ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
- mfbbc = CUMbbc + ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
-
- mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
- mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
- mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
-
- //5.
- mfbcc = CUMbcc + ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
- mfcbc = CUMcbc + ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
- mfccb = CUMccb + ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
-
- //6.
- mfccc = CUMccc - ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
- - c1o3 * (mfacc + mfcac + mfcca) / rho
- - c1o9 * (mfcaa + mfaca + mfaac) / rho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
- + c1o27*((drho * drho - drho) / (rho*rho)));
-
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- mfbaa = -mfbaa;
- mfaba = -mfaba;
- mfaab = -mfaab;
- ////////////////////////////////////////////////////////////////////////////////////
-
-
- ////////////////////////////////////////////////////////////////////////////////////
- //back
- ////////////////////////////////////////////////////////////////////////////////////
- backwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
- backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- backwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
- backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- backwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
- backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- backwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
-
- backwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
- backwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
- backwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
- backwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
- backwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
- backwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
- backwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
- backwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
- backwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
-
- backwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
- backwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
- backwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
- backwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
- backwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
- backwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
- backwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
- backwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
- backwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
-
- ////////////////////////////////////////////////////////////////////////////////////
- mfcbb+=EQcbb;
- mfabb+=EQabb;
- mfbcb+=EQbcb;
- mfbab+=EQbab;
- mfbbc+=EQbbc;
- mfbba+=EQbba;
- mfccb+=EQccb;
- mfaab+=EQaab;
- mfcab+=EQcab;
- mfacb+=EQacb;
- mfcbc+=EQcbc;
- mfaba+=EQaba;
- mfcba+=EQcba;
- mfabc+=EQabc;
- mfbcc+=EQbcc;
- mfbaa+=EQbaa;
- mfbca+=EQbca;
- mfbac+=EQbac;
- mfbbb+=EQbbb;
- mfccc+=EQccc;
- mfaac+=EQaac;
- mfcac+=EQcac;
- mfacc+=EQacc;
- mfcca+=EQcca;
- mfaaa+=EQaaa;
- mfcaa+=EQcaa;
- mfaca+=EQaca;
-
-
- //////////////////////////////////////////////////////////////////////////////////////
- ////back
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Z - Dir
- //backwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, one);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o3);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// Y - Dir
- //backwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaab, mfabb, mfacb, vvy, vy2, c2o3);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o6);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbaa, mfbba, mfbca, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbab, mfbbb, mfbcb, vvz, vz2);
- ///////////b//////////////////////////////////////////////////////////////////////////
- //backwardChimera(mfbac, mfbbc, mfbcc, vvz, vz2);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o18);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcab, mfcbb, mfccb, vvy, vy2, c2o9);
- ///////////c//////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- ////mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- //////////////////////////////////////////////////////////////////////////////////////
- //// X - Dir
- //backwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaba, mfbba, mfcba, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaab, mfbab, mfcab, vvx, vx2, c1o9);
- /////////////b////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfabb, mfbbb, mfcbb, vvx, vx2, c4o9);
- /////////////b////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfacb, mfbcb, mfccb, vvx, vx2, c1o9);
- //////////////////////////////////////////////////////////////////////////////////////
- //////////////////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o36);
- /////////////c////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfabc, mfbbc, mfcbc, vvx, vx2, c1o9);
- /////////////c////////////////////////////////////////////////////////////////////////
- //backwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o36);
- //////////////////////////////////////////////////////////////////////////////////////
-
- //////////////////////////////////////////////////////////////////////////////////////
- real drhoPost =
- ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
- mfbbb += drho - drhoPost;
- ////////////////////////////////////////////////////////////////////////////////////
- (D.f[dirE])[k] = mfabb;//(D.f[ dirE ])[ke ] = mfabb;// - c2over27 ; (D.f[ dirE ])[k ]
- (D.f[dirW])[kw] = mfcbb;//(D.f[ dirW ])[kw ] = mfcbb;// - c2over27 ; (D.f[ dirW ])[kw ]
- (D.f[dirN])[k] = mfbab;//(D.f[ dirN ])[kn ] = mfbab;// - c2over27 ; (D.f[ dirN ])[k ]
- (D.f[dirS])[ks] = mfbcb;//(D.f[ dirS ])[ks ] = mfbcb;// - c2over27 ; (D.f[ dirS ])[ks ]
- (D.f[dirT])[k] = mfbba;//(D.f[ dirT ])[kt ] = mfbba;// - c2over27 ; (D.f[ dirT ])[k ]
- (D.f[dirB])[kb] = mfbbc;//(D.f[ dirB ])[kb ] = mfbbc;// - c2over27 ; (D.f[ dirB ])[kb ]
- (D.f[dirNE])[k] = mfaab;//(D.f[ dirNE ])[kne ] = mfaab;// - c1over54 ; (D.f[ dirNE ])[k ]
- (D.f[dirSW])[ksw] = mfccb;//(D.f[ dirSW ])[ksw ] = mfccb;// - c1over54 ; (D.f[ dirSW ])[ksw ]
- (D.f[dirSE])[ks] = mfacb;//(D.f[ dirSE ])[kse ] = mfacb;// - c1over54 ; (D.f[ dirSE ])[ks ]
- (D.f[dirNW])[kw] = mfcab;//(D.f[ dirNW ])[knw ] = mfcab;// - c1over54 ; (D.f[ dirNW ])[kw ]
- (D.f[dirTE])[k] = mfaba;//(D.f[ dirTE ])[kte ] = mfaba;// - c1over54 ; (D.f[ dirTE ])[k ]
- (D.f[dirBW])[kbw] = mfcbc;//(D.f[ dirBW ])[kbw ] = mfcbc;// - c1over54 ; (D.f[ dirBW ])[kbw ]
- (D.f[dirBE])[kb] = mfabc;//(D.f[ dirBE ])[kbe ] = mfabc;// - c1over54 ; (D.f[ dirBE ])[kb ]
- (D.f[dirTW])[kw] = mfcba;//(D.f[ dirTW ])[ktw ] = mfcba;// - c1over54 ; (D.f[ dirTW ])[kw ]
- (D.f[dirTN])[k] = mfbaa;//(D.f[ dirTN ])[ktn ] = mfbaa;// - c1over54 ; (D.f[ dirTN ])[k ]
- (D.f[dirBS])[kbs] = mfbcc;//(D.f[ dirBS ])[kbs ] = mfbcc;// - c1over54 ; (D.f[ dirBS ])[kbs ]
- (D.f[dirBN])[kb] = mfbac;//(D.f[ dirBN ])[kbn ] = mfbac;// - c1over54 ; (D.f[ dirBN ])[kb ]
- (D.f[dirTS])[ks] = mfbca;//(D.f[ dirTS ])[kts ] = mfbca;// - c1over54 ; (D.f[ dirTS ])[ks ]
- (D.f[dirZERO])[k] = mfbbb;//(D.f[ dirZERO])[kzero] = mfbbb;// - c8over27 ; (D.f[ dirZERO])[k ]
- (D.f[dirTNE])[k] = mfaaa;//(D.f[ dirTNE ])[ktne ] = mfaaa;// - c1over216; (D.f[ dirTNE ])[k ]
- (D.f[dirTSE])[ks] = mfaca;//(D.f[ dirTSE ])[ktse ] = mfaca;// - c1over216; (D.f[ dirTSE ])[ks ]
- (D.f[dirBNE])[kb] = mfaac;//(D.f[ dirBNE ])[kbne ] = mfaac;// - c1over216; (D.f[ dirBNE ])[kb ]
- (D.f[dirBSE])[kbs] = mfacc;//(D.f[ dirBSE ])[kbse ] = mfacc;// - c1over216; (D.f[ dirBSE ])[kbs ]
- (D.f[dirTNW])[kw] = mfcaa;//(D.f[ dirTNW ])[ktnw ] = mfcaa;// - c1over216; (D.f[ dirTNW ])[kw ]
- (D.f[dirTSW])[ksw] = mfcca;//(D.f[ dirTSW ])[ktsw ] = mfcca;// - c1over216; (D.f[ dirTSW ])[ksw ]
- (D.f[dirBNW])[kbw] = mfcac;//(D.f[ dirBNW ])[kbnw ] = mfcac;// - c1over216; (D.f[ dirBNW ])[kbw ]
- (D.f[dirBSW])[kbsw] = mfccc;//(D.f[ dirBSW ])[kbsw ] = mfccc;// - c1over216; (D.f[ dirBSW ])[kbsw]
- ////////////////////////////////////////////////////////////////////////////////////
- }
- }
+ ////////////////////////////////////////////////////////////////////////////////
+ const unsigned x = threadIdx.x; // Globaler x-Index
+ const unsigned y = blockIdx.x; // Globaler y-Index
+ const unsigned z = blockIdx.y; // Globaler z-Index
+
+ const unsigned nx = blockDim.x;
+ const unsigned ny = gridDim.x;
+
+ const unsigned k = nx*(ny*z + y) + x;
+ //////////////////////////////////////////////////////////////////////////
+
+ if (k<size_Mat)
+ {
+ ////////////////////////////////////////////////////////////////////////////////
+ unsigned int BC;
+ BC = bcMatD[k];
+
+ if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
+ {
+ Distributions27 D;
+ if (EvenOrOdd == true)
+ {
+ D.f[dirE] = &DDStart[dirE *size_Mat];
+ D.f[dirW] = &DDStart[dirW *size_Mat];
+ D.f[dirN] = &DDStart[dirN *size_Mat];
+ D.f[dirS] = &DDStart[dirS *size_Mat];
+ D.f[dirT] = &DDStart[dirT *size_Mat];
+ D.f[dirB] = &DDStart[dirB *size_Mat];
+ D.f[dirNE] = &DDStart[dirNE *size_Mat];
+ D.f[dirSW] = &DDStart[dirSW *size_Mat];
+ D.f[dirSE] = &DDStart[dirSE *size_Mat];
+ D.f[dirNW] = &DDStart[dirNW *size_Mat];
+ D.f[dirTE] = &DDStart[dirTE *size_Mat];
+ D.f[dirBW] = &DDStart[dirBW *size_Mat];
+ D.f[dirBE] = &DDStart[dirBE *size_Mat];
+ D.f[dirTW] = &DDStart[dirTW *size_Mat];
+ D.f[dirTN] = &DDStart[dirTN *size_Mat];
+ D.f[dirBS] = &DDStart[dirBS *size_Mat];
+ D.f[dirBN] = &DDStart[dirBN *size_Mat];
+ D.f[dirTS] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirTNE] = &DDStart[dirTNE *size_Mat];
+ D.f[dirTSW] = &DDStart[dirTSW *size_Mat];
+ D.f[dirTSE] = &DDStart[dirTSE *size_Mat];
+ D.f[dirTNW] = &DDStart[dirTNW *size_Mat];
+ D.f[dirBNE] = &DDStart[dirBNE *size_Mat];
+ D.f[dirBSW] = &DDStart[dirBSW *size_Mat];
+ D.f[dirBSE] = &DDStart[dirBSE *size_Mat];
+ D.f[dirBNW] = &DDStart[dirBNW *size_Mat];
+ }
+ else
+ {
+ D.f[dirW] = &DDStart[dirE *size_Mat];
+ D.f[dirE] = &DDStart[dirW *size_Mat];
+ D.f[dirS] = &DDStart[dirN *size_Mat];
+ D.f[dirN] = &DDStart[dirS *size_Mat];
+ D.f[dirB] = &DDStart[dirT *size_Mat];
+ D.f[dirT] = &DDStart[dirB *size_Mat];
+ D.f[dirSW] = &DDStart[dirNE *size_Mat];
+ D.f[dirNE] = &DDStart[dirSW *size_Mat];
+ D.f[dirNW] = &DDStart[dirSE *size_Mat];
+ D.f[dirSE] = &DDStart[dirNW *size_Mat];
+ D.f[dirBW] = &DDStart[dirTE *size_Mat];
+ D.f[dirTE] = &DDStart[dirBW *size_Mat];
+ D.f[dirTW] = &DDStart[dirBE *size_Mat];
+ D.f[dirBE] = &DDStart[dirTW *size_Mat];
+ D.f[dirBS] = &DDStart[dirTN *size_Mat];
+ D.f[dirTN] = &DDStart[dirBS *size_Mat];
+ D.f[dirTS] = &DDStart[dirBN *size_Mat];
+ D.f[dirBN] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirBSW] = &DDStart[dirTNE *size_Mat];
+ D.f[dirBNE] = &DDStart[dirTSW *size_Mat];
+ D.f[dirBNW] = &DDStart[dirTSE *size_Mat];
+ D.f[dirBSE] = &DDStart[dirTNW *size_Mat];
+ D.f[dirTSW] = &DDStart[dirBNE *size_Mat];
+ D.f[dirTNE] = &DDStart[dirBSW *size_Mat];
+ D.f[dirTNW] = &DDStart[dirBSE *size_Mat];
+ D.f[dirTSE] = &DDStart[dirBNW *size_Mat];
+ }
+
+ ////////////////////////////////////////////////////////////////////////////////
+ //index
+ //unsigned int kzero= k;
+ //unsigned int ke = k;
+ unsigned int kw = neighborX[k];
+ //unsigned int kn = k;
+ unsigned int ks = neighborY[k];
+ //unsigned int kt = k;
+ unsigned int kb = neighborZ[k];
+ unsigned int ksw = neighborY[kw];
+ //unsigned int kne = k;
+ //unsigned int kse = ks;
+ //unsigned int knw = kw;
+ unsigned int kbw = neighborZ[kw];
+ //unsigned int kte = k;
+ //unsigned int kbe = kb;
+ //unsigned int ktw = kw;
+ unsigned int kbs = neighborZ[ks];
+ //unsigned int ktn = k;
+ //unsigned int kbn = kb;
+ //unsigned int kts = ks;
+ //unsigned int ktse = ks;
+ //unsigned int kbnw = kbw;
+ //unsigned int ktnw = kw;
+ //unsigned int kbse = kbs;
+ //unsigned int ktsw = ksw;
+ //unsigned int kbne = kb;
+ //unsigned int ktne = k;
+ unsigned int kbsw = neighborZ[ksw];
+
+
+
+ //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ real mfcbb = (D.f[dirE])[k];//[ke ];// + c2over27 ;(D.f[dirE ])[k ];//ke
+ real mfabb = (D.f[dirW])[kw];//[kw ];// + c2over27 ;(D.f[dirW ])[kw ];
+ real mfbcb = (D.f[dirN])[k];//[kn ];// + c2over27 ;(D.f[dirN ])[k ];//kn
+ real mfbab = (D.f[dirS])[ks];//[ks ];// + c2over27 ;(D.f[dirS ])[ks ];
+ real mfbbc = (D.f[dirT])[k];//[kt ];// + c2over27 ;(D.f[dirT ])[k ];//kt
+ real mfbba = (D.f[dirB])[kb];//[kb ];// + c2over27 ;(D.f[dirB ])[kb ];
+ real mfccb = (D.f[dirNE])[k];//[kne ];// + c1over54 ;(D.f[dirNE ])[k ];//kne
+ real mfaab = (D.f[dirSW])[ksw];//[ksw ];// + c1over54 ;(D.f[dirSW ])[ksw];
+ real mfcab = (D.f[dirSE])[ks];//[kse ];// + c1over54 ;(D.f[dirSE ])[ks ];//kse
+ real mfacb = (D.f[dirNW])[kw];//[knw ];// + c1over54 ;(D.f[dirNW ])[kw ];//knw
+ real mfcbc = (D.f[dirTE])[k];//[kte ];// + c1over54 ;(D.f[dirTE ])[k ];//kte
+ real mfaba = (D.f[dirBW])[kbw];//[kbw ];// + c1over54 ;(D.f[dirBW ])[kbw];
+ real mfcba = (D.f[dirBE])[kb];//[kbe ];// + c1over54 ;(D.f[dirBE ])[kb ];//kbe
+ real mfabc = (D.f[dirTW])[kw];//[ktw ];// + c1over54 ;(D.f[dirTW ])[kw ];//ktw
+ real mfbcc = (D.f[dirTN])[k];//[ktn ];// + c1over54 ;(D.f[dirTN ])[k ];//ktn
+ real mfbaa = (D.f[dirBS])[kbs];//[kbs ];// + c1over54 ;(D.f[dirBS ])[kbs];
+ real mfbca = (D.f[dirBN])[kb];//[kbn ];// + c1over54 ;(D.f[dirBN ])[kb ];//kbn
+ real mfbac = (D.f[dirTS])[ks];//[kts ];// + c1over54 ;(D.f[dirTS ])[ks ];//kts
+ real mfbbb = (D.f[dirZERO])[k];//[kzero];// + c8over27 ;(D.f[dirZERO])[k ];//kzero
+ real mfccc = (D.f[dirTNE])[k];//[ktne ];// + c1over216;(D.f[dirTNE ])[k ];//ktne
+ real mfaac = (D.f[dirTSW])[ksw];//[ktsw ];// + c1over216;(D.f[dirTSW ])[ksw];//ktsw
+ real mfcac = (D.f[dirTSE])[ks];//[ktse ];// + c1over216;(D.f[dirTSE ])[ks ];//ktse
+ real mfacc = (D.f[dirTNW])[kw];//[ktnw ];// + c1over216;(D.f[dirTNW ])[kw ];//ktnw
+ real mfcca = (D.f[dirBNE])[kb];//[kbne ];// + c1over216;(D.f[dirBNE ])[kb ];//kbne
+ real mfaaa = (D.f[dirBSW])[kbsw];//[kbsw ];// + c1over216;(D.f[dirBSW ])[kbsw];
+ real mfcaa = (D.f[dirBSE])[kbs];//[kbse ];// + c1over216;(D.f[dirBSE ])[kbs];//kbse
+ real mfaca = (D.f[dirBNW])[kbw];//[kbnw ];// + c1over216;(D.f[dirBNW ])[kbw];//kbnw
+ ////////////////////////////////////////////////////////////////////////////////////
+ real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+
+ real rho = c1o1 + drho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
+ (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
+ (mfcbb - mfabb)) / rho;
+ real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
+ (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
+ (mfbcb - mfbab)) / rho;
+ real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
+ (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
+ (mfbbc - mfbba)) / rho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
+ real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
+ real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
+ vvx += fx*c1o2;
+ vvy += fy*c1o2;
+ vvz += fz*c1o2;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real omega = omega_in;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //fast
+ //real oMdrho = c1o1; // comp special
+ //real m0, m1, m2;
+ real vx2;
+ real vy2;
+ real vz2;
+ vx2 = vvx*vvx;
+ vy2 = vvy*vvy;
+ vz2 = vvz*vvz;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real wadjust;
+ //real qudricLimitP = c1o100;// * 0.0001f;
+ //real qudricLimitM = c1o100;// * 0.0001f;
+ //real qudricLimitD = c1o100;// * 0.001f;
+ //real s9 = minusomega;
+ //test
+ //s9 = 0.;
+
+
+ //////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ real EQcbb = c0o1;
+ real EQabb = c0o1;
+ real EQbcb = c0o1;
+ real EQbab = c0o1;
+ real EQbbc = c0o1;
+ real EQbba = c0o1;
+ real EQccb = c0o1;
+ real EQaab = c0o1;
+ real EQcab = c0o1;
+ real EQacb = c0o1;
+ real EQcbc = c0o1;
+ real EQaba = c0o1;
+ real EQcba = c0o1;
+ real EQabc = c0o1;
+ real EQbcc = c0o1;
+ real EQbaa = c0o1;
+ real EQbca = c0o1;
+ real EQbac = c0o1;
+ real EQbbb = c0o1;
+ real EQccc = drho * c1o27;
+ real EQaac = drho * c1o3;
+ real EQcac = drho * c1o9;
+ real EQacc = drho * c1o9;
+ real EQcca = drho * c1o9;
+ real EQaaa = drho;
+ real EQcaa = drho * c1o3;
+ real EQaca = drho * c1o3;
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::backwardChimeraWithK(EQaaa, EQaab, EQaac, vvz, vz2, c1o1);
+ vf::lbm::backwardChimeraWithK(EQaca, EQacb, EQacc, vvz, vz2, c1o3);
+ ///////////////////////////////////////////////////////////
+ EQcaa = EQaca; EQcab = EQacb; EQcac = EQacc;
+ ///////////////////////////////////////////////////////////
+ vf::lbm::backwardChimeraWithK(EQcca, EQccb, EQccc, vvz, vz2, c1o9);
+
+ vf::lbm::backwardChimeraWithK(EQaaa, EQaba, EQaca, vvy, vy2, c1o6);
+ vf::lbm::backwardChimeraWithK(EQaab, EQabb, EQacb, vvy, vy2, c2o3);
+ vf::lbm::backwardChimeraWithK(EQaac, EQabc, EQacc, vvy, vy2, c1o6);
+ vf::lbm::backwardChimeraWithK(EQcaa, EQcba, EQcca, vvy, vy2, c1o18);
+ vf::lbm::backwardChimeraWithK(EQcab, EQcbb, EQccb, vvy, vy2, c2o9);
+ vf::lbm::backwardChimeraWithK(EQcac, EQcbc, EQccc, vvy, vy2, c1o18);
+
+ vf::lbm::backwardChimeraWithK(EQaaa, EQbaa, EQcaa, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQaab, EQbab, EQcab, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQaac, EQbac, EQcac, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQaba, EQbba, EQcba, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQabb, EQbbb, EQcbb, vvx, vx2, c4o9);
+ vf::lbm::backwardChimeraWithK(EQabc, EQbbc, EQcbc, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQaca, EQbca, EQcca, vvx, vx2, c1o36);
+ vf::lbm::backwardChimeraWithK(EQacb, EQbcb, EQccb, vvx, vx2, c1o9);
+ vf::lbm::backwardChimeraWithK(EQacc, EQbcc, EQccc, vvx, vx2, c1o36);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //Pre-condition
+ mfcbb -= EQcbb;
+ mfabb -= EQabb;
+ mfbcb -= EQbcb;
+ mfbab -= EQbab;
+ mfbbc -= EQbbc;
+ mfbba -= EQbba;
+ mfccb -= EQccb;
+ mfaab -= EQaab;
+ mfcab -= EQcab;
+ mfacb -= EQacb;
+ mfcbc -= EQcbc;
+ mfaba -= EQaba;
+ mfcba -= EQcba;
+ mfabc -= EQabc;
+ mfbcc -= EQbcc;
+ mfbaa -= EQbaa;
+ mfbca -= EQbca;
+ mfbac -= EQbac;
+ mfbbb -= EQbbb;
+ mfccc -= EQccc;
+ mfaac -= EQaac;
+ mfcac -= EQcac;
+ mfacc -= EQacc;
+ mfcca -= EQcca;
+ mfaaa -= EQaaa;
+ mfcaa -= EQcaa;
+ mfaca -= EQaca;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //Hin
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::forwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
+ vf::lbm::forwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ vf::lbm::forwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
+ vf::lbm::forwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ vf::lbm::forwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ vf::lbm::forwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ vf::lbm::forwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
+ vf::lbm::forwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ vf::lbm::forwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
+
+ vf::lbm::forwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
+ vf::lbm::forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::forwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
+ vf::lbm::forwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
+ vf::lbm::forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::forwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
+ vf::lbm::forwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
+ vf::lbm::forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::forwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
+
+ vf::lbm::forwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
+ vf::lbm::forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::forwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
+ vf::lbm::forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::forwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
+ vf::lbm::forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::forwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////Hin
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Z - Dir
+ //forwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c4o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Y - Dir
+ //forwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c2o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c2o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// X - Dir
+ //forwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, one);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //forwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Cumulants
+ ////////////////////////////////////////////////////////////////////////////////////
+ real OxxPyyPzz = c1o1; //omega; // one; //set the bulk viscosity one is high / two is very low and zero is (too) high
+
+ ////////////////////////////////////////////////////////////
+ //3.
+ //////////////////////////////
+ real OxyyPxzz = c1o1;
+ real OxyyMxzz = c1o1;
+ //real Oxyz = c1o1;
+ ////////////////////////////////////////////////////////////
+ //4.
+ //////////////////////////////
+ real O4 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //5.
+ //////////////////////////////
+ real O5 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //6.
+ //////////////////////////////
+ real O6 = c1o1;
+ ////////////////////////////////////////////////////////////
+
+
+ //central moments to cumulants
+ //4.
+ real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
+ real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
+ real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
+
+ real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
+ real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
+ real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
+
+ //5.
+ real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
+ real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
+ real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
+
+ //6.
+
+ real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
+ - c1o3 * (mfacc + mfcac + mfcca) / rho
+ - c1o9 * (mfcaa + mfaca + mfaac) / rho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
+ + c1o27*((drho * drho - drho) / (rho*rho)));
+
+
+
+
+ //2.
+ // linear combinations
+ real mxxPyyPzz = mfcaa + mfaca + mfaac;
+ real mxxMyy = mfcaa - mfaca;
+ real mxxMzz = mfcaa - mfaac;
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
+ {
+ real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
+ real dyuy = dxux + omega * c3o2 * mxxMyy;
+ real dzuz = dxux + omega * c3o2 * mxxMzz;
+
+ //relax
+ mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz) - c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
+ mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
+ mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
+
+ }
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ ////no correction
+ //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
+ //mxxMyy += -(-omega) * (-mxxMyy);
+ //mxxMzz += -(-omega) * (-mxxMzz);
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ mfabb += omega * (-mfabb);
+ mfbab += omega * (-mfbab);
+ mfbba += omega * (-mfbba);
+
+ //////////////////////////////////////////////////////////////////////////
+
+ // linear combinations back
+ mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
+
+ //3.
+ // linear combinations
+
+ real mxxyPyzz = mfcba + mfabc;
+ real mxxyMyzz = mfcba - mfabc;
+
+ real mxxzPyyz = mfcab + mfacb;
+ real mxxzMyyz = mfcab - mfacb;
+
+ real mxyyPxzz = mfbca + mfbac;
+ real mxyyMxzz = mfbca - mfbac;
+
+ //relax
+ //////////////////////////////////////////////////////////////////////////
+ mfbbb += OxyyMxzz * (-mfbbb);
+ mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
+ mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
+ mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
+ mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
+ mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
+ mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
+ //////////////////////////////////////////////////////////////////////////
+
+ mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
+ mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
+ mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
+ mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
+ mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
+ mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
+
+ //4.
+ //////////////////////////////////////////////////////////////////////////
+ CUMacc += O4 * (-CUMacc);
+ CUMcac += O4 * (-CUMcac);
+ CUMcca += O4 * (-CUMcca);
+
+ CUMbbc += O4 * (-CUMbbc);
+ CUMbcb += O4 * (-CUMbcb);
+ CUMcbb += O4 * (-CUMcbb);
+ //////////////////////////////////////////////////////////////////////////
+
+
+ //5.
+ CUMbcc += O5 * (-CUMbcc);
+ CUMcbc += O5 * (-CUMcbc);
+ CUMccb += O5 * (-CUMccb);
+
+ //6.
+ CUMccc += O6 * (-CUMccc);
+
+
+
+ //back cumulants to central moments
+ //4.
+ mfcbb = CUMcbb + ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) / rho;
+ mfbcb = CUMbcb + ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) / rho;
+ mfbbc = CUMbbc + ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) / rho;
+
+ mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) / rho - c1o9*(drho / rho));
+ mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) / rho - c1o9*(drho / rho));
+ mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) / rho - c1o9*(drho / rho));
+
+ //5.
+ mfbcc = CUMbcc + ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) / rho;
+ mfcbc = CUMcbc + ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) / rho;
+ mfccb = CUMccb + ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) / rho;
+
+ //6.
+ mfccc = CUMccc - ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) / rho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) / (rho * rho)
+ - c1o3 * (mfacc + mfcac + mfcca) / rho
+ - c1o9 * (mfcaa + mfaca + mfaac) / rho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) / (rho * rho) * c2o3
+ + c1o27*((drho * drho - drho) / (rho*rho)));
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ mfbaa = -mfbaa;
+ mfaba = -mfaba;
+ mfaab = -mfaab;
+ ////////////////////////////////////////////////////////////////////////////////////
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //back
+ ////////////////////////////////////////////////////////////////////////////////////
+ vf::lbm::backwardChimera(mfaaa, mfaab, mfaac, vvz, vz2);
+ vf::lbm::backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ vf::lbm::backwardChimera(mfaca, mfacb, mfacc, vvz, vz2);
+ vf::lbm::backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ vf::lbm::backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ vf::lbm::backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ vf::lbm::backwardChimera(mfcaa, mfcab, mfcac, vvz, vz2);
+ vf::lbm::backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ vf::lbm::backwardChimera(mfcca, mfccb, mfccc, vvz, vz2);
+
+ vf::lbm::backwardChimera(mfaaa, mfaba, mfaca, vvy, vy2);
+ vf::lbm::backwardChimera(mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::backwardChimera(mfaac, mfabc, mfacc, vvy, vy2);
+ vf::lbm::backwardChimera(mfbaa, mfbba, mfbca, vvy, vy2);
+ vf::lbm::backwardChimera(mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::backwardChimera(mfbac, mfbbc, mfbcc, vvy, vy2);
+ vf::lbm::backwardChimera(mfcaa, mfcba, mfcca, vvy, vy2);
+ vf::lbm::backwardChimera(mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::backwardChimera(mfcac, mfcbc, mfccc, vvy, vy2);
+
+ vf::lbm::backwardChimera(mfaaa, mfbaa, mfcaa, vvx, vx2);
+ vf::lbm::backwardChimera(mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::backwardChimera(mfaac, mfbac, mfcac, vvx, vx2);
+ vf::lbm::backwardChimera(mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::backwardChimera(mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::backwardChimera(mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::backwardChimera(mfaca, mfbca, mfcca, vvx, vx2);
+ vf::lbm::backwardChimera(mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::backwardChimera(mfacc, mfbcc, mfccc, vvx, vx2);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ mfcbb+=EQcbb;
+ mfabb+=EQabb;
+ mfbcb+=EQbcb;
+ mfbab+=EQbab;
+ mfbbc+=EQbbc;
+ mfbba+=EQbba;
+ mfccb+=EQccb;
+ mfaab+=EQaab;
+ mfcab+=EQcab;
+ mfacb+=EQacb;
+ mfcbc+=EQcbc;
+ mfaba+=EQaba;
+ mfcba+=EQcba;
+ mfabc+=EQabc;
+ mfbcc+=EQbcc;
+ mfbaa+=EQbaa;
+ mfbca+=EQbca;
+ mfbac+=EQbac;
+ mfbbb+=EQbbb;
+ mfccc+=EQccc;
+ mfaac+=EQaac;
+ mfcac+=EQcac;
+ mfacc+=EQacc;
+ mfcca+=EQcca;
+ mfaaa+=EQaaa;
+ mfcaa+=EQcaa;
+ mfaca+=EQaca;
+
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////back
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Z - Dir
+ //backwardChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, one);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfaba, mfabb, mfabc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c1o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbaa, mfbab, mfbac, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbba, mfbbb, mfbbc, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbca, mfbcb, mfbcc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c1o3);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfcba, mfcbb, mfcbc, vvz, vz2);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// Y - Dir
+ //backwardChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaab, mfabb, mfacb, vvy, vy2, c2o3);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c1o6);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbaa, mfbba, mfbca, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbab, mfbbb, mfbcb, vvz, vz2);
+ ///////////b//////////////////////////////////////////////////////////////////////////
+ //backwardChimera(mfbac, mfbbc, mfbcc, vvz, vz2);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c1o18);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcab, mfcbb, mfccb, vvy, vy2, c2o9);
+ ///////////c//////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c1o18);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ ////mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ //////////////////////////////////////////////////////////////////////////////////////
+ //// X - Dir
+ //backwardChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaba, mfbba, mfcba, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaab, mfbab, mfcab, vvx, vx2, c1o9);
+ /////////////b////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfabb, mfbbb, mfcbb, vvx, vx2, c4o9);
+ /////////////b////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfacb, mfbcb, mfccb, vvx, vx2, c1o9);
+ //////////////////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c1o36);
+ /////////////c////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfabc, mfbbc, mfcbc, vvx, vx2, c1o9);
+ /////////////c////////////////////////////////////////////////////////////////////////
+ //backwardChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c1o36);
+ //////////////////////////////////////////////////////////////////////////////////////
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ real drhoPost =
+ ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+ mfbbb += drho - drhoPost;
+ ////////////////////////////////////////////////////////////////////////////////////
+ (D.f[dirE])[k] = mfabb;//(D.f[ dirE ])[ke ] = mfabb;// - c2over27 ; (D.f[ dirE ])[k ]
+ (D.f[dirW])[kw] = mfcbb;//(D.f[ dirW ])[kw ] = mfcbb;// - c2over27 ; (D.f[ dirW ])[kw ]
+ (D.f[dirN])[k] = mfbab;//(D.f[ dirN ])[kn ] = mfbab;// - c2over27 ; (D.f[ dirN ])[k ]
+ (D.f[dirS])[ks] = mfbcb;//(D.f[ dirS ])[ks ] = mfbcb;// - c2over27 ; (D.f[ dirS ])[ks ]
+ (D.f[dirT])[k] = mfbba;//(D.f[ dirT ])[kt ] = mfbba;// - c2over27 ; (D.f[ dirT ])[k ]
+ (D.f[dirB])[kb] = mfbbc;//(D.f[ dirB ])[kb ] = mfbbc;// - c2over27 ; (D.f[ dirB ])[kb ]
+ (D.f[dirNE])[k] = mfaab;//(D.f[ dirNE ])[kne ] = mfaab;// - c1over54 ; (D.f[ dirNE ])[k ]
+ (D.f[dirSW])[ksw] = mfccb;//(D.f[ dirSW ])[ksw ] = mfccb;// - c1over54 ; (D.f[ dirSW ])[ksw ]
+ (D.f[dirSE])[ks] = mfacb;//(D.f[ dirSE ])[kse ] = mfacb;// - c1over54 ; (D.f[ dirSE ])[ks ]
+ (D.f[dirNW])[kw] = mfcab;//(D.f[ dirNW ])[knw ] = mfcab;// - c1over54 ; (D.f[ dirNW ])[kw ]
+ (D.f[dirTE])[k] = mfaba;//(D.f[ dirTE ])[kte ] = mfaba;// - c1over54 ; (D.f[ dirTE ])[k ]
+ (D.f[dirBW])[kbw] = mfcbc;//(D.f[ dirBW ])[kbw ] = mfcbc;// - c1over54 ; (D.f[ dirBW ])[kbw ]
+ (D.f[dirBE])[kb] = mfabc;//(D.f[ dirBE ])[kbe ] = mfabc;// - c1over54 ; (D.f[ dirBE ])[kb ]
+ (D.f[dirTW])[kw] = mfcba;//(D.f[ dirTW ])[ktw ] = mfcba;// - c1over54 ; (D.f[ dirTW ])[kw ]
+ (D.f[dirTN])[k] = mfbaa;//(D.f[ dirTN ])[ktn ] = mfbaa;// - c1over54 ; (D.f[ dirTN ])[k ]
+ (D.f[dirBS])[kbs] = mfbcc;//(D.f[ dirBS ])[kbs ] = mfbcc;// - c1over54 ; (D.f[ dirBS ])[kbs ]
+ (D.f[dirBN])[kb] = mfbac;//(D.f[ dirBN ])[kbn ] = mfbac;// - c1over54 ; (D.f[ dirBN ])[kb ]
+ (D.f[dirTS])[ks] = mfbca;//(D.f[ dirTS ])[kts ] = mfbca;// - c1over54 ; (D.f[ dirTS ])[ks ]
+ (D.f[dirZERO])[k] = mfbbb;//(D.f[ dirZERO])[kzero] = mfbbb;// - c8over27 ; (D.f[ dirZERO])[k ]
+ (D.f[dirTNE])[k] = mfaaa;//(D.f[ dirTNE ])[ktne ] = mfaaa;// - c1over216; (D.f[ dirTNE ])[k ]
+ (D.f[dirTSE])[ks] = mfaca;//(D.f[ dirTSE ])[ktse ] = mfaca;// - c1over216; (D.f[ dirTSE ])[ks ]
+ (D.f[dirBNE])[kb] = mfaac;//(D.f[ dirBNE ])[kbne ] = mfaac;// - c1over216; (D.f[ dirBNE ])[kb ]
+ (D.f[dirBSE])[kbs] = mfacc;//(D.f[ dirBSE ])[kbse ] = mfacc;// - c1over216; (D.f[ dirBSE ])[kbs ]
+ (D.f[dirTNW])[kw] = mfcaa;//(D.f[ dirTNW ])[ktnw ] = mfcaa;// - c1over216; (D.f[ dirTNW ])[kw ]
+ (D.f[dirTSW])[ksw] = mfcca;//(D.f[ dirTSW ])[ktsw ] = mfcca;// - c1over216; (D.f[ dirTSW ])[ksw ]
+ (D.f[dirBNW])[kbw] = mfcac;//(D.f[ dirBNW ])[kbnw ] = mfcac;// - c1over216; (D.f[ dirBNW ])[kbw ]
+ (D.f[dirBSW])[kbsw] = mfccc;//(D.f[ dirBSW ])[kbsw ] = mfccc;// - c1over216; (D.f[ dirBSW ])[kbsw]
+ ////////////////////////////////////////////////////////////////////////////////////
+ }
+ }
}
////////////////////////////////////////////////////////////////////////////////
@@ -1798,483 +1754,483 @@ extern "C" __global__ void Cumulant_One_preconditioned_chim_Comp_SP_27(
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void Cumulant_One_chim_Comp_SP_27(
- real omega,
- unsigned int* bcMatD,
- unsigned int* neighborX,
- unsigned int* neighborY,
- unsigned int* neighborZ,
- real* DDStart,
- int size_Mat,
- int level,
- real* forces,
- bool EvenOrOdd)
+ real omega,
+ unsigned int* bcMatD,
+ unsigned int* neighborX,
+ unsigned int* neighborY,
+ unsigned int* neighborZ,
+ real* DDStart,
+ int size_Mat,
+ int level,
+ real* forces,
+ bool EvenOrOdd)
{
- ////////////////////////////////////////////////////////////////////////////////
- const unsigned x = threadIdx.x; // Globaler x-Index
- const unsigned y = blockIdx.x; // Globaler y-Index
- const unsigned z = blockIdx.y; // Globaler z-Index
-
- const unsigned nx = blockDim.x;
- const unsigned ny = gridDim.x;
-
- const unsigned k = nx*(ny*z + y) + x;
- //////////////////////////////////////////////////////////////////////////
-
- if (k<size_Mat)
- {
- ////////////////////////////////////////////////////////////////////////////////
- unsigned int BC;
- BC = bcMatD[k];
-
- if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
- {
- Distributions27 D;
- if (EvenOrOdd == true)
- {
- D.f[dirE ] = &DDStart[dirE *size_Mat];
- D.f[dirW ] = &DDStart[dirW *size_Mat];
- D.f[dirN ] = &DDStart[dirN *size_Mat];
- D.f[dirS ] = &DDStart[dirS *size_Mat];
- D.f[dirT ] = &DDStart[dirT *size_Mat];
- D.f[dirB ] = &DDStart[dirB *size_Mat];
- D.f[dirNE ] = &DDStart[dirNE *size_Mat];
- D.f[dirSW ] = &DDStart[dirSW *size_Mat];
- D.f[dirSE ] = &DDStart[dirSE *size_Mat];
- D.f[dirNW ] = &DDStart[dirNW *size_Mat];
- D.f[dirTE ] = &DDStart[dirTE *size_Mat];
- D.f[dirBW ] = &DDStart[dirBW *size_Mat];
- D.f[dirBE ] = &DDStart[dirBE *size_Mat];
- D.f[dirTW ] = &DDStart[dirTW *size_Mat];
- D.f[dirTN ] = &DDStart[dirTN *size_Mat];
- D.f[dirBS ] = &DDStart[dirBS *size_Mat];
- D.f[dirBN ] = &DDStart[dirBN *size_Mat];
- D.f[dirTS ] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirTNE ] = &DDStart[dirTNE *size_Mat];
- D.f[dirTSW ] = &DDStart[dirTSW *size_Mat];
- D.f[dirTSE ] = &DDStart[dirTSE *size_Mat];
- D.f[dirTNW ] = &DDStart[dirTNW *size_Mat];
- D.f[dirBNE ] = &DDStart[dirBNE *size_Mat];
- D.f[dirBSW ] = &DDStart[dirBSW *size_Mat];
- D.f[dirBSE ] = &DDStart[dirBSE *size_Mat];
- D.f[dirBNW ] = &DDStart[dirBNW *size_Mat];
- }
- else
- {
- D.f[dirW ] = &DDStart[dirE *size_Mat];
- D.f[dirE ] = &DDStart[dirW *size_Mat];
- D.f[dirS ] = &DDStart[dirN *size_Mat];
- D.f[dirN ] = &DDStart[dirS *size_Mat];
- D.f[dirB ] = &DDStart[dirT *size_Mat];
- D.f[dirT ] = &DDStart[dirB *size_Mat];
- D.f[dirSW ] = &DDStart[dirNE *size_Mat];
- D.f[dirNE ] = &DDStart[dirSW *size_Mat];
- D.f[dirNW ] = &DDStart[dirSE *size_Mat];
- D.f[dirSE ] = &DDStart[dirNW *size_Mat];
- D.f[dirBW ] = &DDStart[dirTE *size_Mat];
- D.f[dirTE ] = &DDStart[dirBW *size_Mat];
- D.f[dirTW ] = &DDStart[dirBE *size_Mat];
- D.f[dirBE ] = &DDStart[dirTW *size_Mat];
- D.f[dirBS ] = &DDStart[dirTN *size_Mat];
- D.f[dirTN ] = &DDStart[dirBS *size_Mat];
- D.f[dirTS ] = &DDStart[dirBN *size_Mat];
- D.f[dirBN ] = &DDStart[dirTS *size_Mat];
- D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
- D.f[dirBSW ] = &DDStart[dirTNE *size_Mat];
- D.f[dirBNE ] = &DDStart[dirTSW *size_Mat];
- D.f[dirBNW ] = &DDStart[dirTSE *size_Mat];
- D.f[dirBSE ] = &DDStart[dirTNW *size_Mat];
- D.f[dirTSW ] = &DDStart[dirBNE *size_Mat];
- D.f[dirTNE ] = &DDStart[dirBSW *size_Mat];
- D.f[dirTNW ] = &DDStart[dirBSE *size_Mat];
- D.f[dirTSE ] = &DDStart[dirBNW *size_Mat];
- }
- ////////////////////////////////////////////////////////////////////////////////
- //index
- unsigned int kw = neighborX[k];
- unsigned int ks = neighborY[k];
- unsigned int kb = neighborZ[k];
- unsigned int ksw = neighborY[kw];
- unsigned int kbw = neighborZ[kw];
- unsigned int kbs = neighborZ[ks];
- unsigned int kbsw = neighborZ[ksw];
- ////////////////////////////////////////////////////////////////////////////////////
- real mfcbb = (D.f[dirE ])[k ];
- real mfabb = (D.f[dirW ])[kw ];
- real mfbcb = (D.f[dirN ])[k ];
- real mfbab = (D.f[dirS ])[ks ];
- real mfbbc = (D.f[dirT ])[k ];
- real mfbba = (D.f[dirB ])[kb ];
- real mfccb = (D.f[dirNE ])[k ];
- real mfaab = (D.f[dirSW ])[ksw ];
- real mfcab = (D.f[dirSE ])[ks ];
- real mfacb = (D.f[dirNW ])[kw ];
- real mfcbc = (D.f[dirTE ])[k ];
- real mfaba = (D.f[dirBW ])[kbw ];
- real mfcba = (D.f[dirBE ])[kb ];
- real mfabc = (D.f[dirTW ])[kw ];
- real mfbcc = (D.f[dirTN ])[k ];
- real mfbaa = (D.f[dirBS ])[kbs ];
- real mfbca = (D.f[dirBN ])[kb ];
- real mfbac = (D.f[dirTS ])[ks ];
- real mfbbb = (D.f[dirZERO])[k ];
- real mfccc = (D.f[dirTNE ])[k ];
- real mfaac = (D.f[dirTSW ])[ksw ];
- real mfcac = (D.f[dirTSE ])[ks ];
- real mfacc = (D.f[dirTNW ])[kw ];
- real mfcca = (D.f[dirBNE ])[kb ];
- real mfaaa = (D.f[dirBSW ])[kbsw];
- real mfcaa = (D.f[dirBSE ])[kbs ];
- real mfaca = (D.f[dirBNW ])[kbw ];
- ////////////////////////////////////////////////////////////////////////////////////
- real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
-
- real rho = c1o1 + drho;
- real OOrho = c1o1 / rho;
- ////////////////////////////////////////////////////////////////////////////////////
- real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
- (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
- (mfcbb - mfabb)) * OOrho;
- real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
- (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
- (mfbcb - mfbab)) * OOrho;
- real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
- (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
- (mfbbc - mfbba)) * OOrho;
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
- real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
- real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
- vvx += fx*c1o2;
- vvy += fy*c1o2;
- vvz += fz*c1o2;
- ////////////////////////////////////////////////////////////////////////////////////
- //real omega = omega_in;
- ////////////////////////////////////////////////////////////////////////////////////
- //fast
- //real oMdrho = c1o1; // comp special
- //real m0, m1, m2;
- real vx2;
- real vy2;
- real vz2;
- vx2 = vvx*vvx;
- vy2 = vvy*vvy;
- vz2 = vvz*vvz;
- ////////////////////////////////////////////////////////////////////////////////////
- //real wadjust;
- //real qudricLimitP = c1o100;// * 0.0001f;
- //real qudricLimitM = c1o100;// * 0.0001f;
- //real qudricLimitD = c1o100;// * 0.001f;
- ////////////////////////////////////////////////////////////////////////////////////
- //Hin
- ////////////////////////////////////////////////////////////////////////////////////
- // mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // Z - Dir
- forwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, 36.0f, c1o36);
- forwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, 9.0f , c1o9 );
- forwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, 36.0f, c1o36);
- forwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, 9.0f , c1o9 );
- forwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, 2.25f, c4o9 );
- forwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, 9.0f , c1o9 );
- forwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, 36.0f, c1o36);
- forwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, 9.0f , c1o9 );
- forwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, 36.0f, c1o36);
-
- ////////////////////////////////////////////////////////////////////////////////////
- // mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // Y - Dir
- forwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, 6.0f , c1o6 );
- forwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
- forwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, 18.0f, c1o18);
- forwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, 1.5f , c2o3 );
- forwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
- forwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, 4.5f , c2o9 );
- forwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, 6.0f , c1o6 );
- forwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
- forwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, 18.0f, c1o18);
-
- ////////////////////////////////////////////////////////////////////////////////////
- // mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // X - Dir
- forwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
- forwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
- forwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, 3.0f, c1o3);
- forwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
- forwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
- forwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
- forwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, 3.0f, c1o3);
- forwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
- forwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, 9.0f, c1o9);
-
- ////////////////////////////////////////////////////////////////////////////////////
- // Cumulants
- ////////////////////////////////////////////////////////////////////////////////////
- real OxxPyyPzz = c1o1;
- ////////////////////////////////////////////////////////////
- //3.
- //////////////////////////////
- real OxyyPxzz = c1o1;
- real OxyyMxzz = c1o1;
- //real Oxyz = c1o1;
- ////////////////////////////////////////////////////////////
- //4.
- //////////////////////////////
- real O4 = c1o1;
- ////////////////////////////////////////////////////////////
- //5.
- //////////////////////////////
- real O5 = c1o1;
- ////////////////////////////////////////////////////////////
- //6.
- //////////////////////////////
- real O6 = c1o1;
- ////////////////////////////////////////////////////////////
-
-
- //central moments to cumulants
- //4.
- real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) * OOrho;
- real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) * OOrho;
- real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) * OOrho;
-
- real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) * OOrho - c1o9*(drho * OOrho));
- real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) * OOrho - c1o9*(drho * OOrho));
- real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) * OOrho - c1o9*(drho * OOrho));
-
- //5.
- real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) * OOrho;
- real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) * OOrho;
- real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) * OOrho;
-
- //6.
- real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
- - c1o3 * (mfacc + mfcac + mfcca) * OOrho
- - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
- + c1o27*((drho * drho - drho) * OOrho * OOrho ));
-
-
- //2.
- // linear combinations
- real mxxPyyPzz = mfcaa + mfaca + mfaac;
- real mxxMyy = mfcaa - mfaca;
- real mxxMzz = mfcaa - mfaac;
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
- {
- real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
- real dyuy = dxux + omega * c3o2 * mxxMyy;
- real dzuz = dxux + omega * c3o2 * mxxMzz;
-
- //relax
- mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz)- c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
- mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
- mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
-
- }
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
-
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- ////no correction
- //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
- //mxxMyy += -(-omega) * (-mxxMyy);
- //mxxMzz += -(-omega) * (-mxxMzz);
- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
- mfabb += omega * (-mfabb);
- mfbab += omega * (-mfbab);
- mfbba += omega * (-mfbba);
-
- //////////////////////////////////////////////////////////////////////////
-
- // linear combinations back
- mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
- mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
- mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
-
- //3.
- // linear combinations
-
- real mxxyPyzz = mfcba + mfabc;
- real mxxyMyzz = mfcba - mfabc;
-
- real mxxzPyyz = mfcab + mfacb;
- real mxxzMyyz = mfcab - mfacb;
-
- real mxyyPxzz = mfbca + mfbac;
- real mxyyMxzz = mfbca - mfbac;
-
- //relax
- //////////////////////////////////////////////////////////////////////////
- mfbbb += OxyyMxzz * (-mfbbb);
- mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
- mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
- mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
- mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
- mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
- mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
- //////////////////////////////////////////////////////////////////////////
-
- mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
- mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
- mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
- mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
- mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
- mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
-
- //4.
- //////////////////////////////////////////////////////////////////////////
- CUMacc += O4 * (-CUMacc);
- CUMcac += O4 * (-CUMcac);
- CUMcca += O4 * (-CUMcca);
-
- CUMbbc += O4 * (-CUMbbc);
- CUMbcb += O4 * (-CUMbcb);
- CUMcbb += O4 * (-CUMcbb);
- //////////////////////////////////////////////////////////////////////////
-
-
- //5.
- CUMbcc += O5 * (-CUMbcc);
- CUMcbc += O5 * (-CUMcbc);
- CUMccb += O5 * (-CUMccb);
-
- //6.
- CUMccc += O6 * (-CUMccc);
-
-
-
- //back cumulants to central moments
- //4.
- mfcbb = CUMcbb + c1o3*((c3o1*mfcaa + c1o1) * mfabb + c6o1 * mfbba * mfbab) * OOrho;
- mfbcb = CUMbcb + c1o3*((c3o1*mfaca + c1o1) * mfbab + c6o1 * mfbba * mfabb) * OOrho;
- mfbbc = CUMbbc + c1o3*((c3o1*mfaac + c1o1) * mfbba + c6o1 * mfbab * mfabb) * OOrho;
-
- mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba)*c9o1 + c3o1 * (mfcaa + mfaca)) * OOrho - (drho * OOrho))*c1o9;
- mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab)*c9o1 + c3o1 * (mfcaa + mfaac)) * OOrho - (drho * OOrho))*c1o9;
- mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb)*c9o1 + c3o1 * (mfaac + mfaca)) * OOrho - (drho * OOrho))*c1o9;
-
- //5.
- mfbcc = CUMbcc + c1o3 *(c3o1*(mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + (mfbca + mfbac)) * OOrho;
- mfcbc = CUMcbc + c1o3 *(c3o1*(mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + (mfcba + mfabc)) * OOrho;
- mfccb = CUMccb + c1o3 *(c3o1*(mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + (mfacb + mfcab)) * OOrho;
-
- //6.
- mfccc =
- CUMccc - ((-c4o1 * mfbbb * mfbbb
- - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
- - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
- - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
- + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
- + c2o1 * (mfcaa * mfaca * mfaac)
- + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
- - c1o3 * (mfacc + mfcac + mfcca) * OOrho
- - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
- + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
- + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
- + c1o27*((drho * drho - drho) * OOrho * OOrho ));
-
- ////////////////////////////////////////////////////////////////////////////////////
- //the force be with you
- mfbaa = -mfbaa;
- mfaba = -mfaba;
- mfaab = -mfaab;
- ////////////////////////////////////////////////////////////////////////////////////
-
-
- ////////////////////////////////////////////////////////////////////////////////////
- //back
- ////////////////////////////////////////////////////////////////////////////////////
- //mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // X - Dir
- backwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
- backwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
- backwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, 3.0f, c1o3);
- backwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
- backwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
- backwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
- backwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, 3.0f, c1o3);
- backwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
- backwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, 9.0f, c1o9);
-
- ////////////////////////////////////////////////////////////////////////////////////
- //mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // Y - Dir
- backwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, 6.0f , c1o6 );
- backwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
- backwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, 18.0f, c1o18);
- backwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, 1.5f , c2o3 );
- backwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
- backwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, 4.5f , c2o9 );
- backwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, 6.0f , c1o6 );
- backwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
- backwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, 18.0f, c1o18);
-
- ////////////////////////////////////////////////////////////////////////////////////
- //mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
- ////////////////////////////////////////////////////////////////////////////////////
- // Z - Dir
- backwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, 36.0f, c1o36);
- backwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, 9.0f , c1o9 );
- backwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, 36.0f, c1o36);
- backwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, 9.0f , c1o9 );
- backwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, 2.25f, c4o9 );
- backwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, 9.0f , c1o9 );
- backwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, 36.0f, c1o36);
- backwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, 9.0f , c1o9 );
- backwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, 36.0f, c1o36);
-
- //////////////////////////////////////////////////////////////////////////////////////
- real drhoPost =
- ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
- (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
- ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
- mfbbb += drho - drhoPost;
- ////////////////////////////////////////////////////////////////////////////////////
- (D.f[dirE ])[k ] = mfabb;
- (D.f[dirW ])[kw ] = mfcbb;
- (D.f[dirN ])[k ] = mfbab;
- (D.f[dirS ])[ks ] = mfbcb;
- (D.f[dirT ])[k ] = mfbba;
- (D.f[dirB ])[kb ] = mfbbc;
- (D.f[dirNE ])[k ] = mfaab;
- (D.f[dirSW ])[ksw ] = mfccb;
- (D.f[dirSE ])[ks ] = mfacb;
- (D.f[dirNW ])[kw ] = mfcab;
- (D.f[dirTE ])[k ] = mfaba;
- (D.f[dirBW ])[kbw ] = mfcbc;
- (D.f[dirBE ])[kb ] = mfabc;
- (D.f[dirTW ])[kw ] = mfcba;
- (D.f[dirTN ])[k ] = mfbaa;
- (D.f[dirBS ])[kbs ] = mfbcc;
- (D.f[dirBN ])[kb ] = mfbac;
- (D.f[dirTS ])[ks ] = mfbca;
- (D.f[dirZERO])[k ] = mfbbb;
- (D.f[dirTNE ])[k ] = mfaaa;
- (D.f[dirTSE ])[ks ] = mfaca;
- (D.f[dirBNE ])[kb ] = mfaac;
- (D.f[dirBSE ])[kbs ] = mfacc;
- (D.f[dirTNW ])[kw ] = mfcaa;
- (D.f[dirTSW ])[ksw ] = mfcca;
- (D.f[dirBNW ])[kbw ] = mfcac;
- (D.f[dirBSW ])[kbsw] = mfccc;
- }
- }
+ ////////////////////////////////////////////////////////////////////////////////
+ const unsigned x = threadIdx.x; // Globaler x-Index
+ const unsigned y = blockIdx.x; // Globaler y-Index
+ const unsigned z = blockIdx.y; // Globaler z-Index
+
+ const unsigned nx = blockDim.x;
+ const unsigned ny = gridDim.x;
+
+ const unsigned k = nx*(ny*z + y) + x;
+ //////////////////////////////////////////////////////////////////////////
+
+ if (k<size_Mat)
+ {
+ ////////////////////////////////////////////////////////////////////////////////
+ unsigned int BC;
+ BC = bcMatD[k];
+
+ if (BC >= GEO_FLUID/*(BC != GEO_SOLID) && (BC != GEO_VOID)*/)
+ {
+ Distributions27 D;
+ if (EvenOrOdd == true)
+ {
+ D.f[dirE ] = &DDStart[dirE *size_Mat];
+ D.f[dirW ] = &DDStart[dirW *size_Mat];
+ D.f[dirN ] = &DDStart[dirN *size_Mat];
+ D.f[dirS ] = &DDStart[dirS *size_Mat];
+ D.f[dirT ] = &DDStart[dirT *size_Mat];
+ D.f[dirB ] = &DDStart[dirB *size_Mat];
+ D.f[dirNE ] = &DDStart[dirNE *size_Mat];
+ D.f[dirSW ] = &DDStart[dirSW *size_Mat];
+ D.f[dirSE ] = &DDStart[dirSE *size_Mat];
+ D.f[dirNW ] = &DDStart[dirNW *size_Mat];
+ D.f[dirTE ] = &DDStart[dirTE *size_Mat];
+ D.f[dirBW ] = &DDStart[dirBW *size_Mat];
+ D.f[dirBE ] = &DDStart[dirBE *size_Mat];
+ D.f[dirTW ] = &DDStart[dirTW *size_Mat];
+ D.f[dirTN ] = &DDStart[dirTN *size_Mat];
+ D.f[dirBS ] = &DDStart[dirBS *size_Mat];
+ D.f[dirBN ] = &DDStart[dirBN *size_Mat];
+ D.f[dirTS ] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirTNE ] = &DDStart[dirTNE *size_Mat];
+ D.f[dirTSW ] = &DDStart[dirTSW *size_Mat];
+ D.f[dirTSE ] = &DDStart[dirTSE *size_Mat];
+ D.f[dirTNW ] = &DDStart[dirTNW *size_Mat];
+ D.f[dirBNE ] = &DDStart[dirBNE *size_Mat];
+ D.f[dirBSW ] = &DDStart[dirBSW *size_Mat];
+ D.f[dirBSE ] = &DDStart[dirBSE *size_Mat];
+ D.f[dirBNW ] = &DDStart[dirBNW *size_Mat];
+ }
+ else
+ {
+ D.f[dirW ] = &DDStart[dirE *size_Mat];
+ D.f[dirE ] = &DDStart[dirW *size_Mat];
+ D.f[dirS ] = &DDStart[dirN *size_Mat];
+ D.f[dirN ] = &DDStart[dirS *size_Mat];
+ D.f[dirB ] = &DDStart[dirT *size_Mat];
+ D.f[dirT ] = &DDStart[dirB *size_Mat];
+ D.f[dirSW ] = &DDStart[dirNE *size_Mat];
+ D.f[dirNE ] = &DDStart[dirSW *size_Mat];
+ D.f[dirNW ] = &DDStart[dirSE *size_Mat];
+ D.f[dirSE ] = &DDStart[dirNW *size_Mat];
+ D.f[dirBW ] = &DDStart[dirTE *size_Mat];
+ D.f[dirTE ] = &DDStart[dirBW *size_Mat];
+ D.f[dirTW ] = &DDStart[dirBE *size_Mat];
+ D.f[dirBE ] = &DDStart[dirTW *size_Mat];
+ D.f[dirBS ] = &DDStart[dirTN *size_Mat];
+ D.f[dirTN ] = &DDStart[dirBS *size_Mat];
+ D.f[dirTS ] = &DDStart[dirBN *size_Mat];
+ D.f[dirBN ] = &DDStart[dirTS *size_Mat];
+ D.f[dirZERO] = &DDStart[dirZERO*size_Mat];
+ D.f[dirBSW ] = &DDStart[dirTNE *size_Mat];
+ D.f[dirBNE ] = &DDStart[dirTSW *size_Mat];
+ D.f[dirBNW ] = &DDStart[dirTSE *size_Mat];
+ D.f[dirBSE ] = &DDStart[dirTNW *size_Mat];
+ D.f[dirTSW ] = &DDStart[dirBNE *size_Mat];
+ D.f[dirTNE ] = &DDStart[dirBSW *size_Mat];
+ D.f[dirTNW ] = &DDStart[dirBSE *size_Mat];
+ D.f[dirTSE ] = &DDStart[dirBNW *size_Mat];
+ }
+ ////////////////////////////////////////////////////////////////////////////////
+ //index
+ unsigned int kw = neighborX[k];
+ unsigned int ks = neighborY[k];
+ unsigned int kb = neighborZ[k];
+ unsigned int ksw = neighborY[kw];
+ unsigned int kbw = neighborZ[kw];
+ unsigned int kbs = neighborZ[ks];
+ unsigned int kbsw = neighborZ[ksw];
+ ////////////////////////////////////////////////////////////////////////////////////
+ real mfcbb = (D.f[dirE ])[k ];
+ real mfabb = (D.f[dirW ])[kw ];
+ real mfbcb = (D.f[dirN ])[k ];
+ real mfbab = (D.f[dirS ])[ks ];
+ real mfbbc = (D.f[dirT ])[k ];
+ real mfbba = (D.f[dirB ])[kb ];
+ real mfccb = (D.f[dirNE ])[k ];
+ real mfaab = (D.f[dirSW ])[ksw ];
+ real mfcab = (D.f[dirSE ])[ks ];
+ real mfacb = (D.f[dirNW ])[kw ];
+ real mfcbc = (D.f[dirTE ])[k ];
+ real mfaba = (D.f[dirBW ])[kbw ];
+ real mfcba = (D.f[dirBE ])[kb ];
+ real mfabc = (D.f[dirTW ])[kw ];
+ real mfbcc = (D.f[dirTN ])[k ];
+ real mfbaa = (D.f[dirBS ])[kbs ];
+ real mfbca = (D.f[dirBN ])[kb ];
+ real mfbac = (D.f[dirTS ])[ks ];
+ real mfbbb = (D.f[dirZERO])[k ];
+ real mfccc = (D.f[dirTNE ])[k ];
+ real mfaac = (D.f[dirTSW ])[ksw ];
+ real mfcac = (D.f[dirTSE ])[ks ];
+ real mfacc = (D.f[dirTNW ])[kw ];
+ real mfcca = (D.f[dirBNE ])[kb ];
+ real mfaaa = (D.f[dirBSW ])[kbsw];
+ real mfcaa = (D.f[dirBSE ])[kbs ];
+ real mfaca = (D.f[dirBNW ])[kbw ];
+ ////////////////////////////////////////////////////////////////////////////////////
+ real drho = ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+
+ real rho = c1o1 + drho;
+ real OOrho = c1o1 / rho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ real vvx = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfcaa - mfacc) + (mfcca - mfaac))) +
+ (((mfcba - mfabc) + (mfcbc - mfaba)) + ((mfcab - mfacb) + (mfccb - mfaab))) +
+ (mfcbb - mfabb)) * OOrho;
+ real vvy = ((((mfccc - mfaaa) + (mfaca - mfcac)) + ((mfacc - mfcaa) + (mfcca - mfaac))) +
+ (((mfbca - mfbac) + (mfbcc - mfbaa)) + ((mfacb - mfcab) + (mfccb - mfaab))) +
+ (mfbcb - mfbab)) * OOrho;
+ real vvz = ((((mfccc - mfaaa) + (mfcac - mfaca)) + ((mfacc - mfcaa) + (mfaac - mfcca))) +
+ (((mfbac - mfbca) + (mfbcc - mfbaa)) + ((mfabc - mfcba) + (mfcbc - mfaba))) +
+ (mfbbc - mfbba)) * OOrho;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ real fx = forces[0] / (pow((double)c2o1, (double)level)); //zero;//0.0032653/(pow(two,level)); //0.000000005;//(two/1600000.0) / 120.0; //
+ real fy = forces[1] / (pow((double)c2o1, (double)level)); //zero;
+ real fz = forces[2] / (pow((double)c2o1, (double)level)); //zero;
+ vvx += fx*c1o2;
+ vvy += fy*c1o2;
+ vvz += fz*c1o2;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real omega = omega_in;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //fast
+ //real oMdrho = c1o1; // comp special
+ //real m0, m1, m2;
+ real vx2;
+ real vy2;
+ real vz2;
+ vx2 = vvx*vvx;
+ vy2 = vvy*vvy;
+ vz2 = vvz*vvz;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //real wadjust;
+ //real qudricLimitP = c1o100;// * 0.0001f;
+ //real qudricLimitM = c1o100;// * 0.0001f;
+ //real qudricLimitD = c1o100;// * 0.001f;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //Hin
+ ////////////////////////////////////////////////////////////////////////////////////
+ // mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Z - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, 2.25f, c4o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, 36.0f, c1o36);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // mit 1/6, 0, 1/18, 2/3, 0, 2/9, 1/6, 0, 1/18 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Y - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, 6.0f , c1o6 );
+ vf::lbm::forwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, 18.0f, c1o18);
+ vf::lbm::forwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, 1.5f , c2o3 );
+ vf::lbm::forwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, 4.5f , c2o9 );
+ vf::lbm::forwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, 6.0f , c1o6 );
+ vf::lbm::forwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, 18.0f, c1o18);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // X - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
+ vf::lbm::forwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, 3.0f, c1o3);
+ vf::lbm::forwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::forwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::forwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, 3.0f, c1o3);
+ vf::lbm::forwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, 9.0f, c1o9);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Cumulants
+ ////////////////////////////////////////////////////////////////////////////////////
+ real OxxPyyPzz = c1o1;
+ ////////////////////////////////////////////////////////////
+ //3.
+ //////////////////////////////
+ real OxyyPxzz = c1o1;
+ real OxyyMxzz = c1o1;
+ //real Oxyz = c1o1;
+ ////////////////////////////////////////////////////////////
+ //4.
+ //////////////////////////////
+ real O4 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //5.
+ //////////////////////////////
+ real O5 = c1o1;
+ ////////////////////////////////////////////////////////////
+ //6.
+ //////////////////////////////
+ real O6 = c1o1;
+ ////////////////////////////////////////////////////////////
+
+
+ //central moments to cumulants
+ //4.
+ real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) * OOrho;
+ real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) * OOrho;
+ real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) * OOrho;
+
+ real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) * OOrho - c1o9*(drho * OOrho));
+ real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) * OOrho - c1o9*(drho * OOrho));
+ real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) * OOrho - c1o9*(drho * OOrho));
+
+ //5.
+ real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) * OOrho;
+ real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) * OOrho;
+ real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) * OOrho;
+
+ //6.
+ real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
+ - c1o3 * (mfacc + mfcac + mfcca) * OOrho
+ - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
+ + c1o27*((drho * drho - drho) * OOrho * OOrho ));
+
+
+ //2.
+ // linear combinations
+ real mxxPyyPzz = mfcaa + mfaca + mfaac;
+ real mxxMyy = mfcaa - mfaca;
+ real mxxMzz = mfcaa - mfaac;
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ //incl. correction (hat noch nicht so gut funktioniert...Optimierungsbedarf??)
+ {
+ real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
+ real dyuy = dxux + omega * c3o2 * mxxMyy;
+ real dzuz = dxux + omega * c3o2 * mxxMzz;
+
+ //relax
+ mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz)- c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);//-magicBulk*OxxPyyPzz;
+ mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
+ mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
+
+ }
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ ////no correction
+ //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);//-magicBulk*OxxPyyPzz;
+ //mxxMyy += -(-omega) * (-mxxMyy);
+ //mxxMzz += -(-omega) * (-mxxMzz);
+ /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+ mfabb += omega * (-mfabb);
+ mfbab += omega * (-mfbab);
+ mfbba += omega * (-mfbba);
+
+ //////////////////////////////////////////////////////////////////////////
+
+ // linear combinations back
+ mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
+
+ //3.
+ // linear combinations
+
+ real mxxyPyzz = mfcba + mfabc;
+ real mxxyMyzz = mfcba - mfabc;
+
+ real mxxzPyyz = mfcab + mfacb;
+ real mxxzMyyz = mfcab - mfacb;
+
+ real mxyyPxzz = mfbca + mfbac;
+ real mxyyMxzz = mfbca - mfbac;
+
+ //relax
+ //////////////////////////////////////////////////////////////////////////
+ mfbbb += OxyyMxzz * (-mfbbb);
+ mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
+ mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
+ mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
+ mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
+ mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
+ mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
+ //////////////////////////////////////////////////////////////////////////
+
+ mfcba = (mxxyMyzz + mxxyPyzz) * c1o2;
+ mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
+ mfcab = (mxxzMyyz + mxxzPyyz) * c1o2;
+ mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
+ mfbca = (mxyyMxzz + mxyyPxzz) * c1o2;
+ mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
+
+ //4.
+ //////////////////////////////////////////////////////////////////////////
+ CUMacc += O4 * (-CUMacc);
+ CUMcac += O4 * (-CUMcac);
+ CUMcca += O4 * (-CUMcca);
+
+ CUMbbc += O4 * (-CUMbbc);
+ CUMbcb += O4 * (-CUMbcb);
+ CUMcbb += O4 * (-CUMcbb);
+ //////////////////////////////////////////////////////////////////////////
+
+
+ //5.
+ CUMbcc += O5 * (-CUMbcc);
+ CUMcbc += O5 * (-CUMcbc);
+ CUMccb += O5 * (-CUMccb);
+
+ //6.
+ CUMccc += O6 * (-CUMccc);
+
+
+
+ //back cumulants to central moments
+ //4.
+ mfcbb = CUMcbb + c1o3*((c3o1*mfcaa + c1o1) * mfabb + c6o1 * mfbba * mfbab) * OOrho;
+ mfbcb = CUMbcb + c1o3*((c3o1*mfaca + c1o1) * mfbab + c6o1 * mfbba * mfabb) * OOrho;
+ mfbbc = CUMbbc + c1o3*((c3o1*mfaac + c1o1) * mfbba + c6o1 * mfbab * mfabb) * OOrho;
+
+ mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba)*c9o1 + c3o1 * (mfcaa + mfaca)) * OOrho - (drho * OOrho))*c1o9;
+ mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab)*c9o1 + c3o1 * (mfcaa + mfaac)) * OOrho - (drho * OOrho))*c1o9;
+ mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb)*c9o1 + c3o1 * (mfaac + mfaca)) * OOrho - (drho * OOrho))*c1o9;
+
+ //5.
+ mfbcc = CUMbcc + c1o3 *(c3o1*(mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + (mfbca + mfbac)) * OOrho;
+ mfcbc = CUMcbc + c1o3 *(c3o1*(mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + (mfcba + mfabc)) * OOrho;
+ mfccb = CUMccb + c1o3 *(c3o1*(mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + (mfacb + mfcab)) * OOrho;
+
+ //6.
+ mfccc =
+ CUMccc - ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
+ - c1o3 * (mfacc + mfcac + mfcca) * OOrho
+ - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
+ + c1o27*((drho * drho - drho) * OOrho * OOrho ));
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //the force be with you
+ mfbaa = -mfbaa;
+ mfaba = -mfaba;
+ mfaab = -mfaab;
+ ////////////////////////////////////////////////////////////////////////////////////
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //back
+ ////////////////////////////////////////////////////////////////////////////////////
+ //mit 1, 0, 1/3, 0, 0, 0, 1/3, 0, 1/9 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // X - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
+ vf::lbm::backwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, 3.0f, c1o3);
+ vf::lbm::backwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::backwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::backwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, 3.0f, c1o3);
+ vf::lbm::backwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, 9.0f, c1o9);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //mit 1/6, 2/3, 1/6, 0, 0, 0, 1/18, 2/9, 1/18 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Y - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, 6.0f , c1o6 );
+ vf::lbm::backwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, 18.0f, c1o18);
+ vf::lbm::backwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, 1.5f , c2o3 );
+ vf::lbm::backwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, 4.5f , c2o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, 6.0f , c1o6 );
+ vf::lbm::backwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, 18.0f, c1o18);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //mit 1/36, 1/9, 1/36, 1/9, 4/9, 1/9, 1/36, 1/9, 1/36 Konditionieren
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Z - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, 2.25f, c4o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, 36.0f, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, 9.0f , c1o9 );
+ vf::lbm::backwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, 36.0f, c1o36);
+
+ //////////////////////////////////////////////////////////////////////////////////////
+ real drhoPost =
+ ((((mfccc + mfaaa) + (mfaca + mfcac)) + ((mfacc + mfcaa) + (mfaac + mfcca))) +
+ (((mfbac + mfbca) + (mfbaa + mfbcc)) + ((mfabc + mfcba) + (mfaba + mfcbc)) + ((mfacb + mfcab) + (mfaab + mfccb))) +
+ ((mfabb + mfcbb) + (mfbab + mfbcb) + (mfbba + mfbbc))) + mfbbb;
+ mfbbb += drho - drhoPost;
+ ////////////////////////////////////////////////////////////////////////////////////
+ (D.f[dirE ])[k ] = mfabb;
+ (D.f[dirW ])[kw ] = mfcbb;
+ (D.f[dirN ])[k ] = mfbab;
+ (D.f[dirS ])[ks ] = mfbcb;
+ (D.f[dirT ])[k ] = mfbba;
+ (D.f[dirB ])[kb ] = mfbbc;
+ (D.f[dirNE ])[k ] = mfaab;
+ (D.f[dirSW ])[ksw ] = mfccb;
+ (D.f[dirSE ])[ks ] = mfacb;
+ (D.f[dirNW ])[kw ] = mfcab;
+ (D.f[dirTE ])[k ] = mfaba;
+ (D.f[dirBW ])[kbw ] = mfcbc;
+ (D.f[dirBE ])[kb ] = mfabc;
+ (D.f[dirTW ])[kw ] = mfcba;
+ (D.f[dirTN ])[k ] = mfbaa;
+ (D.f[dirBS ])[kbs ] = mfbcc;
+ (D.f[dirBN ])[kb ] = mfbac;
+ (D.f[dirTS ])[ks ] = mfbca;
+ (D.f[dirZERO])[k ] = mfbbb;
+ (D.f[dirTNE ])[k ] = mfaaa;
+ (D.f[dirTSE ])[ks ] = mfaca;
+ (D.f[dirBNE ])[kb ] = mfaac;
+ (D.f[dirBSE ])[kbs ] = mfacc;
+ (D.f[dirTNW ])[kw ] = mfcaa;
+ (D.f[dirTSW ])[ksw ] = mfcca;
+ (D.f[dirBNW ])[kbw ] = mfcac;
+ (D.f[dirBSW ])[kbsw] = mfccc;
+ }
+ }
}
////////////////////////////////////////////////////////////////////////////////
diff --git a/src/gpu/VirtualFluids_GPU/GPU/GPU_Interface.h b/src/gpu/VirtualFluids_GPU/GPU/GPU_Interface.h
index 3589bcea15dd73771ff0f7579401e65da7010389..dfdbac44d197e55e3e78eb794692fd9443cb7ab6 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/GPU_Interface.h
+++ b/src/gpu/VirtualFluids_GPU/GPU/GPU_Interface.h
@@ -131,6 +131,7 @@ extern "C" void KernelKumNewSP27( unsigned int numberOfThreads,
int size_Mat,
bool EvenOrOdd);
+
extern "C" void CumulantOnePreconditionedErrorDiffusionChimCompSP27(
unsigned int numberOfThreads,
real s9,
diff --git a/src/gpu/VirtualFluids_GPU/GPU/GPU_Kernels.cuh b/src/gpu/VirtualFluids_GPU/GPU/GPU_Kernels.cuh
index b41724df488f7aea97ed5e9e2bcf9282ff6bc370..288db43e7bcd36dc4d187982b86178d345601094 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/GPU_Kernels.cuh
+++ b/src/gpu/VirtualFluids_GPU/GPU/GPU_Kernels.cuh
@@ -140,7 +140,6 @@ extern "C" __global__ void LB_Kernel_Kum_Comp_SP_27(real s9,
int size_Mat,
bool EvenOrOdd);
-
extern "C" __global__ void Cumulant_One_preconditioned_errorDiffusion_chim_Comp_SP_27(
real omega,
unsigned int* bcMatD,
diff --git a/src/gpu/VirtualFluids_GPU/GPU/LBMKernel.cu b/src/gpu/VirtualFluids_GPU/GPU/LBMKernel.cu
index a203cca15bfd0fccac53d1d86555a023063ea86a..8b80e5ea9dbed3deef4c4332b2d43bf62ba9e48b 100644
--- a/src/gpu/VirtualFluids_GPU/GPU/LBMKernel.cu
+++ b/src/gpu/VirtualFluids_GPU/GPU/LBMKernel.cu
@@ -353,6 +353,7 @@ extern "C" void KernelKumNewCompSP27(unsigned int numberOfThreads,
// EvenOrOdd);
//getLastCudaError("LB_Kernel_Kum_New_Comp_SP_27 execution failed");
}
+
//////////////////////////////////////////////////////////////////////////
extern "C" void CumulantOnePreconditionedErrorDiffusionChimCompSP27(unsigned int numberOfThreads,
real s9,
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernel.h b/src/gpu/VirtualFluids_GPU/Kernel/Kernel.h
index 8932dadb3f92256cba279121193f94dbabdc0a6d..213127e64c5e7bfe2b3d4c9d1154c11d374f9552 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/Kernel.h
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernel.h
@@ -1,26 +1,19 @@
-#ifndef KERNEL_H
-#define KERNEL_H
+#ifndef GPU_KERNEL_H
+#define GPU_KERNEL_H
-#include <DataTypes.h>
-
-#include <cuda_runtime.h>
-#include <helper_functions.h>
-#include <helper_cuda.h>
+#include <vector>
#include "Kernel/Utilities/KernelGroup.h"
#include "PreProcessor/PreProcessorType.h"
-#include <vector>
-
-
class Kernel
{
public:
- virtual ~Kernel() = default;
- virtual void run() = 0;
+ virtual ~Kernel() = default;
+ virtual void run() = 0;
- virtual bool checkParameter() = 0;
- virtual std::vector<PreProcessorType> getPreProcessorTypes() = 0;
- virtual KernelGroup getKernelGroup() = 0;
+ virtual bool checkParameter() = 0;
+ virtual std::vector<PreProcessorType> getPreProcessorTypes() = 0;
+ virtual KernelGroup getKernelGroup() = 0;
};
-#endif
\ No newline at end of file
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.cpp b/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.cpp
index 6d06d4c9175c7935bb609c2e342b29c50c42846d..5e4c5aa08e37e88008da13466bfeed6893ec94f6 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.cpp
+++ b/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.cpp
@@ -2,26 +2,26 @@
#include "Kernel/Utilities/CheckParameterStrategy/CheckParameterStrategy.h"
-bool KernelImp::checkParameter()
-{
- return checkStrategy->checkParameter(para);
+bool KernelImp::checkParameter()
+{
+ return checkStrategy->checkParameter(para);
}
-std::vector<PreProcessorType> KernelImp::getPreProcessorTypes()
-{
- return myPreProcessorTypes;
+std::vector<PreProcessorType> KernelImp::getPreProcessorTypes()
+{
+ return myPreProcessorTypes;
}
-KernelGroup KernelImp::getKernelGroup()
-{
- return myKernelGroup;
+KernelGroup KernelImp::getKernelGroup()
+{
+ return myKernelGroup;
}
void KernelImp::setCheckParameterStrategy(std::shared_ptr<CheckParameterStrategy> strategy)
{
- this->checkStrategy = strategy;
+ this->checkStrategy = strategy;
}
-KernelImp::KernelImp()
-{
-}
+KernelImp::KernelImp(std::shared_ptr<Parameter> para, int level) : para(para), level(level) {}
+
+KernelImp::KernelImp() {}
\ No newline at end of file
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.h b/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.h
index f902a7aaec82acd1eb0a55e97f5a4f31f4334575..08b71d42e79564d9eac887289a1ae36824095c46 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.h
+++ b/src/gpu/VirtualFluids_GPU/Kernel/KernelImp.h
@@ -5,28 +5,33 @@
#include <memory>
+#include "Utilities/CudaGrid.h"
+
class CheckParameterStrategy;
class Parameter;
class KernelImp : public Kernel
{
public:
- virtual void run() = 0;
+ virtual void run() = 0;
- bool checkParameter();
- std::vector<PreProcessorType> getPreProcessorTypes();
- KernelGroup getKernelGroup();
+ bool checkParameter();
+ std::vector<PreProcessorType> getPreProcessorTypes();
+ KernelGroup getKernelGroup();
- void setCheckParameterStrategy(std::shared_ptr<CheckParameterStrategy> strategy);
+ void setCheckParameterStrategy(std::shared_ptr<CheckParameterStrategy> strategy);
protected:
- KernelImp();
+ KernelImp(std::shared_ptr<Parameter> para, int level);
+ KernelImp();
- std::shared_ptr< Parameter> para;
- std::shared_ptr<CheckParameterStrategy> checkStrategy;
- int level;
- std::vector<PreProcessorType> myPreProcessorTypes;
- KernelGroup myKernelGroup;
+ std::shared_ptr<Parameter> para;
+ std::shared_ptr<CheckParameterStrategy> checkStrategy;
+ int level;
+ std::vector<PreProcessorType> myPreProcessorTypes;
+ KernelGroup myKernelGroup;
+ vf::gpu::CudaGrid cudaGrid;
};
-#endif
\ No newline at end of file
+
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.cu b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.cu
new file mode 100644
index 0000000000000000000000000000000000000000..4c82851996646590d8c246df5f940b58a308d52c
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.cu
@@ -0,0 +1,56 @@
+#include "BGKUnified.h"
+
+#include <stdexcept>
+
+#include "Parameter/Parameter.h"
+#include "../RunLBMKernel.cuh"
+#include "Kernel/Utilities/CudaGrid.h"
+
+#include <lbm/BGK.h>
+
+
+namespace vf
+{
+namespace gpu
+{
+
+
+BGKUnified::BGKUnified(std::shared_ptr<Parameter> para, int level)
+ : KernelImp(para, level)
+{
+#ifndef BUILD_CUDA_LTO
+ throw std::invalid_argument("To use the BKGUnified kernel, pass -DBUILD_CUDA_LTO=ON to cmake. Requires: CUDA 11.2 & cc 5.0");
+#endif
+
+ myPreProcessorTypes.push_back(InitCompSP27);
+
+ myKernelGroup = BasicKernel;
+
+ this->cudaGrid = CudaGrid(para->getParD(level)->numberofthreads, para->getParD(level)->size_Mat_SP);
+}
+
+
+void BGKUnified::run()
+{
+ GPUKernelParameter kernelParameter{ para->getParD(level)->omega,
+ para->getParD(level)->geoSP,
+ para->getParD(level)->neighborX_SP,
+ para->getParD(level)->neighborY_SP,
+ para->getParD(level)->neighborZ_SP,
+ para->getParD(level)->d0SP.f[0],
+ (int)para->getParD(level)->size_Mat_SP,
+ nullptr, /* forces not used in bgk kernel */
+ para->getParD(level)->evenOrOdd };
+
+ auto lambda = [] __device__(lbm::KernelParameter parameter) {
+ return lbm::bgk(parameter);
+ };
+
+ runKernel<<<cudaGrid.grid, cudaGrid.threads>>>(lambda, kernelParameter);
+
+ getLastCudaError("LB_Kernel_BGKUnified execution failed");
+}
+
+
+}
+}
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.h b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.h
new file mode 100644
index 0000000000000000000000000000000000000000..762eaaa5935bd01fa6ae002521a40e45cd239dfd
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.h
@@ -0,0 +1,22 @@
+#ifndef GPU_BKGUnified_H
+#define GPU_BKGUnified_H
+
+#include "Kernel/KernelImp.h"
+
+namespace vf
+{
+namespace gpu
+{
+
+class BGKUnified : public KernelImp
+{
+public:
+ BGKUnified(std::shared_ptr<Parameter> para, int level);
+
+ void run();
+};
+
+}
+}
+
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15/CumulantK15Comp_Device.cuh b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15/CumulantK15Comp_Device.cuh
index 6a8eede33bc210eacad184afb42a7011dd684708..208fbec553507812bfe4339577734292b248c027 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15/CumulantK15Comp_Device.cuh
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15/CumulantK15Comp_Device.cuh
@@ -14,4 +14,4 @@ extern "C" __global__ void LB_Kernel_CumulantK15Comp( real omega,
int level,
real* forces,
bool EvenOrOdd);
-#endif
\ No newline at end of file
+#endif
\ No newline at end of file
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.cu b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.cu
new file mode 100644
index 0000000000000000000000000000000000000000..b6f5d21ccf909f1ce3bcf11a4558f4771d87d021
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.cu
@@ -0,0 +1,54 @@
+#include "CumulantK15Unified.h"
+
+#include <stdexcept>
+
+#include "../RunLBMKernel.cuh"
+
+#include "Parameter/Parameter.h"
+
+#include <lbm/CumulantChimera.h>
+
+namespace vf
+{
+namespace gpu
+{
+
+CumulantK15Unified::CumulantK15Unified(std::shared_ptr<Parameter> para, int level)
+ : KernelImp(para, level)
+{
+#ifndef BUILD_CUDA_LTO
+ throw std::invalid_argument(
+ "To use the CumulantK15Unified kernel, pass -DBUILD_CUDA_LTO=ON to cmake. Requires: CUDA 11.2 & cc 5.0");
+#endif
+
+ myPreProcessorTypes.push_back(InitCompSP27);
+
+ myKernelGroup = BasicKernel;
+
+ this->cudaGrid = CudaGrid(para->getParD(level)->numberofthreads, para->getParD(level)->size_Mat_SP);
+}
+
+void CumulantK15Unified::run()
+{
+ GPUKernelParameter kernelParameter{ para->getParD(level)->omega,
+ para->getParD(level)->geoSP,
+ para->getParD(level)->neighborX_SP,
+ para->getParD(level)->neighborY_SP,
+ para->getParD(level)->neighborZ_SP,
+ para->getParD(level)->d0SP.f[0],
+ (int)para->getParD(level)->size_Mat_SP,
+ para->getParD(level)->forcing,
+ para->getParD(level)->evenOrOdd };
+
+ auto lambda = [] __device__(lbm::KernelParameter parameter) {
+ return lbm::cumulantChimera(parameter, lbm::setRelaxationRatesK15);
+ };
+
+ vf::gpu::runKernel<<<cudaGrid.grid, cudaGrid.threads>>>(lambda, kernelParameter);
+
+ getLastCudaError("LB_Kernel_CumulantK15Comp execution failed");
+}
+
+
+}
+}
\ No newline at end of file
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.h b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.h
new file mode 100644
index 0000000000000000000000000000000000000000..8756253950484e00773af89327589c3d8f157729
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.h
@@ -0,0 +1,21 @@
+#ifndef CUMULANT_K15_UNIFIED_COMP_H
+#define CUMULANT_K15_UNIFIED_COMP_H
+
+#include "Kernel/KernelImp.h"
+
+namespace vf
+{
+namespace gpu
+{
+class CumulantK15Unified : public KernelImp
+{
+public:
+ CumulantK15Unified(std::shared_ptr<Parameter> para, int level);
+
+ void run();
+};
+
+}
+}
+
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.cu b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.cu
new file mode 100644
index 0000000000000000000000000000000000000000..989fce0c5e797ef90d644845f6c502bee700f6e1
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.cu
@@ -0,0 +1,56 @@
+#include "CumulantK17Unified.h"
+
+#include <stdexcept>
+
+#include "Parameter/Parameter.h"
+#include "../RunLBMKernel.cuh"
+#include "Kernel/Utilities/CudaGrid.h"
+
+#include <lbm/CumulantChimera.h>
+
+namespace vf
+{
+namespace gpu
+{
+
+
+CumulantK17Unified::CumulantK17Unified(std::shared_ptr<Parameter> para, int level)
+ : KernelImp(para, level)
+{
+#ifndef BUILD_CUDA_LTO
+ throw std::invalid_argument("To use the CumulantK17Unified kernel, pass -DBUILD_CUDA_LTO=ON to cmake. Requires: CUDA 11.2 & cc 5.0");
+#endif
+
+ myPreProcessorTypes.push_back(InitCompSP27);
+
+ myKernelGroup = BasicKernel;
+
+ this->cudaGrid = CudaGrid(para->getParD(level)->numberofthreads, para->getParD(level)->size_Mat_SP);
+}
+
+
+
+void CumulantK17Unified::run()
+{
+ GPUKernelParameter kernelParameter{ para->getParD(level)->omega,
+ para->getParD(level)->geoSP,
+ para->getParD(level)->neighborX_SP,
+ para->getParD(level)->neighborY_SP,
+ para->getParD(level)->neighborZ_SP,
+ para->getParD(level)->d0SP.f[0],
+ (int)para->getParD(level)->size_Mat_SP,
+ para->getParD(level)->forcing,
+ para->getParD(level)->evenOrOdd };
+
+ auto lambda = [] __device__(lbm::KernelParameter parameter) {
+ return lbm::cumulantChimera(parameter, lbm::setRelaxationRatesK17);
+ };
+
+ runKernel<<<cudaGrid.grid, cudaGrid.threads>>>(lambda, kernelParameter);
+
+ getLastCudaError("LB_Kernel_CumulantK17Unified execution failed");
+}
+
+
+}
+}
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.h b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.h
new file mode 100644
index 0000000000000000000000000000000000000000..af8470b717ad7a98e7a3fcd507976353d9e8bd41
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.h
@@ -0,0 +1,23 @@
+#ifndef CUMULANT_K17_UNIFIED_H
+#define CUMULANT_K17_UNIFIED_H
+
+#include "Kernel/KernelImp.h"
+
+namespace vf
+{
+namespace gpu
+{
+
+
+class CumulantK17Unified : public KernelImp
+{
+public:
+ CumulantK17Unified(std::shared_ptr<Parameter> para, int level);
+
+ void run();
+};
+
+}
+}
+
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/FluidFlowCompStrategy.h b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/FluidFlowCompStrategy.h
index 5bdf2e9bb0f00e3e2ae3642baa42545079f93c2c..c9a6675bd7a4b82442c55b23bac6f9b49b811938 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/FluidFlowCompStrategy.h
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/FluidFlowCompStrategy.h
@@ -15,4 +15,4 @@ private:
FluidFlowCompStrategy();
};
-#endif
\ No newline at end of file
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/RunLBMKernel.cuh b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/RunLBMKernel.cuh
new file mode 100644
index 0000000000000000000000000000000000000000..b4097851b251b7447f6ce06856d0b9187999a20b
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Kernels/BasicKernels/FluidFlow/Compressible/RunLBMKernel.cuh
@@ -0,0 +1,59 @@
+#ifndef GPU_CUMULANT_KERNEL_H
+#define GPU_CUMULANT_KERNEL_H
+
+
+#include <DataTypes.h>
+#include <cuda_runtime.h>
+
+#include <lbm/KernelParameter.h>
+
+#include "Kernel/Utilities/DistributionHelper.cuh"
+
+namespace vf
+{
+namespace gpu
+{
+
+
+struct GPUKernelParameter
+{
+ real omega;
+ unsigned int* typeOfGridNode;
+ unsigned int* neighborX;
+ unsigned int* neighborY;
+ unsigned int* neighborZ;
+ real* distributions;
+ int size_Mat;
+ real* forces;
+ bool isEvenTimestep;
+};
+
+template<typename KernelFunctor>
+__global__ void runKernel(KernelFunctor kernel, GPUKernelParameter kernelParameter)
+{
+ const uint k = getNodeIndex();
+ const uint nodeType = kernelParameter.typeOfGridNode[k];
+
+ if (!isValidFluidNode(k, kernelParameter.size_Mat, nodeType))
+ return;
+
+ DistributionWrapper distributionWrapper {
+ kernelParameter.distributions,
+ kernelParameter.size_Mat,
+ kernelParameter.isEvenTimestep,
+ k,
+ kernelParameter.neighborX,
+ kernelParameter.neighborY,
+ kernelParameter.neighborZ
+ };
+
+ lbm::KernelParameter parameter {distributionWrapper.distribution, kernelParameter.omega, kernelParameter.forces};
+ kernel(parameter);
+
+ distributionWrapper.write();
+}
+
+}
+}
+
+#endif
\ No newline at end of file
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.cpp b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..fa17bf449915eba509dbabbe71f556c19fa43bcf
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.cpp
@@ -0,0 +1,27 @@
+#include "CudaGrid.h"
+
+
+
+namespace vf
+{
+namespace gpu
+{
+
+CudaGrid::CudaGrid(unsigned int numberOfThreads, unsigned int size_matrix)
+{
+ int Grid = (size_matrix / numberOfThreads) + 1;
+ int Grid1, Grid2;
+ if (Grid > 512) {
+ Grid1 = 512;
+ Grid2 = (Grid / Grid1) + 1;
+ } else {
+ Grid1 = 1;
+ Grid2 = Grid;
+ }
+
+ grid = dim3(Grid1, Grid2);
+ threads = dim3(numberOfThreads, 1, 1);
+}
+
+}
+}
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.h b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.h
new file mode 100644
index 0000000000000000000000000000000000000000..27a18a58843b0de064009ab0f837518e3bb44b9d
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/CudaGrid.h
@@ -0,0 +1,25 @@
+#ifndef GPU_CUDA_GRID_H
+#define GPU_CUDA_GRID_H
+
+
+#include <cuda_runtime.h>
+
+namespace vf
+{
+namespace gpu
+{
+
+
+struct CudaGrid
+{
+ dim3 threads;
+ dim3 grid;
+
+ CudaGrid(unsigned int numberOfEntities, unsigned int threadsPerBlock);
+ CudaGrid() = default;
+};
+
+}
+}
+
+#endif
\ No newline at end of file
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cu b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cu
new file mode 100644
index 0000000000000000000000000000000000000000..bbb01d95410612d36d55f1e0113175a8741b9ade
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cu
@@ -0,0 +1,169 @@
+#include "DistributionHelper.cuh"
+
+#include <cuda_runtime.h>
+
+#include "LBM/D3Q27.h"
+
+#include <lbm/constants/NumericConstants.h>
+#include <lbm/constants/D3Q27.h>
+
+namespace vf
+{
+namespace gpu
+{
+
+__device__ __host__ DistributionReferences27 getDistributionReferences27(real *distributions, unsigned int size_Mat, bool isEvenTimestep)
+{
+ DistributionReferences27 distribution_references;
+
+ if (isEvenTimestep) {
+ distribution_references.f[dirE] = &distributions[dirE * size_Mat];
+ distribution_references.f[dirW] = &distributions[dirW * size_Mat];
+ distribution_references.f[dirN] = &distributions[dirN * size_Mat];
+ distribution_references.f[dirS] = &distributions[dirS * size_Mat];
+ distribution_references.f[dirT] = &distributions[dirT * size_Mat];
+ distribution_references.f[dirB] = &distributions[dirB * size_Mat];
+ distribution_references.f[dirNE] = &distributions[dirNE * size_Mat];
+ distribution_references.f[dirSW] = &distributions[dirSW * size_Mat];
+ distribution_references.f[dirSE] = &distributions[dirSE * size_Mat];
+ distribution_references.f[dirNW] = &distributions[dirNW * size_Mat];
+ distribution_references.f[dirTE] = &distributions[dirTE * size_Mat];
+ distribution_references.f[dirBW] = &distributions[dirBW * size_Mat];
+ distribution_references.f[dirBE] = &distributions[dirBE * size_Mat];
+ distribution_references.f[dirTW] = &distributions[dirTW * size_Mat];
+ distribution_references.f[dirTN] = &distributions[dirTN * size_Mat];
+ distribution_references.f[dirBS] = &distributions[dirBS * size_Mat];
+ distribution_references.f[dirBN] = &distributions[dirBN * size_Mat];
+ distribution_references.f[dirTS] = &distributions[dirTS * size_Mat];
+ distribution_references.f[dirREST] = &distributions[dirREST * size_Mat];
+ distribution_references.f[dirTNE] = &distributions[dirTNE * size_Mat];
+ distribution_references.f[dirTSW] = &distributions[dirTSW * size_Mat];
+ distribution_references.f[dirTSE] = &distributions[dirTSE * size_Mat];
+ distribution_references.f[dirTNW] = &distributions[dirTNW * size_Mat];
+ distribution_references.f[dirBNE] = &distributions[dirBNE * size_Mat];
+ distribution_references.f[dirBSW] = &distributions[dirBSW * size_Mat];
+ distribution_references.f[dirBSE] = &distributions[dirBSE * size_Mat];
+ distribution_references.f[dirBNW] = &distributions[dirBNW * size_Mat];
+ } else {
+ distribution_references.f[dirW] = &distributions[dirE * size_Mat];
+ distribution_references.f[dirE] = &distributions[dirW * size_Mat];
+ distribution_references.f[dirS] = &distributions[dirN * size_Mat];
+ distribution_references.f[dirN] = &distributions[dirS * size_Mat];
+ distribution_references.f[dirB] = &distributions[dirT * size_Mat];
+ distribution_references.f[dirT] = &distributions[dirB * size_Mat];
+ distribution_references.f[dirSW] = &distributions[dirNE * size_Mat];
+ distribution_references.f[dirNE] = &distributions[dirSW * size_Mat];
+ distribution_references.f[dirNW] = &distributions[dirSE * size_Mat];
+ distribution_references.f[dirSE] = &distributions[dirNW * size_Mat];
+ distribution_references.f[dirBW] = &distributions[dirTE * size_Mat];
+ distribution_references.f[dirTE] = &distributions[dirBW * size_Mat];
+ distribution_references.f[dirTW] = &distributions[dirBE * size_Mat];
+ distribution_references.f[dirBE] = &distributions[dirTW * size_Mat];
+ distribution_references.f[dirBS] = &distributions[dirTN * size_Mat];
+ distribution_references.f[dirTN] = &distributions[dirBS * size_Mat];
+ distribution_references.f[dirTS] = &distributions[dirBN * size_Mat];
+ distribution_references.f[dirBN] = &distributions[dirTS * size_Mat];
+ distribution_references.f[dirREST] = &distributions[dirREST * size_Mat];
+ distribution_references.f[dirBSW] = &distributions[dirTNE * size_Mat];
+ distribution_references.f[dirBNE] = &distributions[dirTSW * size_Mat];
+ distribution_references.f[dirBNW] = &distributions[dirTSE * size_Mat];
+ distribution_references.f[dirBSE] = &distributions[dirTNW * size_Mat];
+ distribution_references.f[dirTSW] = &distributions[dirBNE * size_Mat];
+ distribution_references.f[dirTNE] = &distributions[dirBSW * size_Mat];
+ distribution_references.f[dirTNW] = &distributions[dirBSE * size_Mat];
+ distribution_references.f[dirTSE] = &distributions[dirBNW * size_Mat];
+ }
+ return distribution_references;
+}
+
+__device__ DistributionWrapper::DistributionWrapper(real *distributions, unsigned int size_Mat, bool isEvenTimestep,
+ uint k, uint *neighborX, uint *neighborY, uint *neighborZ)
+ : distribution_references(getDistributionReferences27(distributions, size_Mat, isEvenTimestep)), k(k), kw(neighborX[k]), ks(neighborY[k]),
+ kb(neighborZ[k]), ksw(neighborY[kw]), kbw(neighborZ[kw]), kbs(neighborZ[ks]), kbsw(neighborZ[ksw])
+{
+ read();
+}
+
+__device__ void DistributionWrapper::read()
+{
+ distribution.f[vf::lbm::dir::PZZ] = (distribution_references.f[dirE])[k];
+ distribution.f[vf::lbm::dir::MZZ] = (distribution_references.f[dirW])[kw];
+ distribution.f[vf::lbm::dir::ZPZ] = (distribution_references.f[dirN])[k];
+ distribution.f[vf::lbm::dir::ZMZ] = (distribution_references.f[dirS])[ks];
+ distribution.f[vf::lbm::dir::ZZP] = (distribution_references.f[dirT])[k];
+ distribution.f[vf::lbm::dir::ZZM] = (distribution_references.f[dirB])[kb];
+ distribution.f[vf::lbm::dir::PPZ] = (distribution_references.f[dirNE])[k];
+ distribution.f[vf::lbm::dir::MMZ] = (distribution_references.f[dirSW])[ksw];
+ distribution.f[vf::lbm::dir::PMZ] = (distribution_references.f[dirSE])[ks];
+ distribution.f[vf::lbm::dir::MPZ] = (distribution_references.f[dirNW])[kw];
+ distribution.f[vf::lbm::dir::PZP] = (distribution_references.f[dirTE])[k];
+ distribution.f[vf::lbm::dir::MZM] = (distribution_references.f[dirBW])[kbw];
+ distribution.f[vf::lbm::dir::PZM] = (distribution_references.f[dirBE])[kb];
+ distribution.f[vf::lbm::dir::MZP] = (distribution_references.f[dirTW])[kw];
+ distribution.f[vf::lbm::dir::ZPP] = (distribution_references.f[dirTN])[k];
+ distribution.f[vf::lbm::dir::ZMM] = (distribution_references.f[dirBS])[kbs];
+ distribution.f[vf::lbm::dir::ZPM] = (distribution_references.f[dirBN])[kb];
+ distribution.f[vf::lbm::dir::ZMP] = (distribution_references.f[dirTS])[ks];
+ distribution.f[vf::lbm::dir::PPP] = (distribution_references.f[dirTNE])[k];
+ distribution.f[vf::lbm::dir::MPP] = (distribution_references.f[dirTNW])[kw];
+ distribution.f[vf::lbm::dir::PMP] = (distribution_references.f[dirTSE])[ks];
+ distribution.f[vf::lbm::dir::MMP] = (distribution_references.f[dirTSW])[ksw];
+ distribution.f[vf::lbm::dir::PPM] = (distribution_references.f[dirBNE])[kb];
+ distribution.f[vf::lbm::dir::MPM] = (distribution_references.f[dirBNW])[kbw];
+ distribution.f[vf::lbm::dir::PMM] = (distribution_references.f[dirBSE])[kbs];
+ distribution.f[vf::lbm::dir::MMM] = (distribution_references.f[dirBSW])[kbsw];
+ distribution.f[vf::lbm::dir::ZZZ] = (distribution_references.f[dirREST])[k];
+}
+
+__device__ void DistributionWrapper::write()
+{
+ (distribution_references.f[dirE])[k] = distribution.f[vf::lbm::dir::PZZ];
+ (distribution_references.f[dirW])[kw] = distribution.f[vf::lbm::dir::MZZ];
+ (distribution_references.f[dirN])[k] = distribution.f[vf::lbm::dir::ZPZ];
+ (distribution_references.f[dirS])[ks] = distribution.f[vf::lbm::dir::ZMZ];
+ (distribution_references.f[dirT])[k] = distribution.f[vf::lbm::dir::ZZP];
+ (distribution_references.f[dirB])[kb] = distribution.f[vf::lbm::dir::ZZM];
+ (distribution_references.f[dirNE])[k] = distribution.f[vf::lbm::dir::PPZ];
+ (distribution_references.f[dirSW])[ksw] = distribution.f[vf::lbm::dir::MMZ];
+ (distribution_references.f[dirSE])[ks] = distribution.f[vf::lbm::dir::PMZ];
+ (distribution_references.f[dirNW])[kw] = distribution.f[vf::lbm::dir::MPZ];
+ (distribution_references.f[dirTE])[k] = distribution.f[vf::lbm::dir::PZP];
+ (distribution_references.f[dirBW])[kbw] = distribution.f[vf::lbm::dir::MZM];
+ (distribution_references.f[dirBE])[kb] = distribution.f[vf::lbm::dir::PZM];
+ (distribution_references.f[dirTW])[kw] = distribution.f[vf::lbm::dir::MZP];
+ (distribution_references.f[dirTN])[k] = distribution.f[vf::lbm::dir::ZPP];
+ (distribution_references.f[dirBS])[kbs] = distribution.f[vf::lbm::dir::ZMM];
+ (distribution_references.f[dirBN])[kb] = distribution.f[vf::lbm::dir::ZPM];
+ (distribution_references.f[dirTS])[ks] = distribution.f[vf::lbm::dir::ZMP];
+ (distribution_references.f[dirTNE])[k] = distribution.f[vf::lbm::dir::PPP];
+ (distribution_references.f[dirTNW])[kw] = distribution.f[vf::lbm::dir::MPP];
+ (distribution_references.f[dirTSE])[ks] = distribution.f[vf::lbm::dir::PMP];
+ (distribution_references.f[dirTSW])[ksw] = distribution.f[vf::lbm::dir::MMP];
+ (distribution_references.f[dirBNE])[kb] = distribution.f[vf::lbm::dir::PPM];
+ (distribution_references.f[dirBNW])[kbw] = distribution.f[vf::lbm::dir::MPM];
+ (distribution_references.f[dirBSE])[kbs] = distribution.f[vf::lbm::dir::PMM];
+ (distribution_references.f[dirBSW])[kbsw] = distribution.f[vf::lbm::dir::MMM];
+ (distribution_references.f[dirREST])[k] = distribution.f[vf::lbm::dir::ZZZ];
+}
+
+__device__ unsigned int getNodeIndex()
+{
+ const unsigned x = threadIdx.x;
+ const unsigned y = blockIdx.x;
+ const unsigned z = blockIdx.y;
+
+ const unsigned nx = blockDim.x;
+ const unsigned ny = gridDim.x;
+
+ return nx * (ny * z + y) + x;
+}
+
+__device__ bool isValidFluidNode(uint k, int size_Mat, uint nodeType)
+{
+ return (k < size_Mat) &&
+ (nodeType == GEO_FLUID || nodeType == GEO_PM_0 || nodeType == GEO_PM_1 || nodeType == GEO_PM_2);
+}
+
+
+} // namespace gpu
+} // namespace vf
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cuh b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cuh
new file mode 100644
index 0000000000000000000000000000000000000000..935030701924233d959fb69b74a7c3087feb0834
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelper.cuh
@@ -0,0 +1,98 @@
+//=======================================================================================
+// ____ ____ __ ______ __________ __ __ __ __
+// \ \ | | | | | _ \ |___ ___| | | | | / \ | |
+// \ \ | | | | | |_) | | | | | | | / \ | |
+// \ \ | | | | | _ / | | | | | | / /\ \ | |
+// \ \ | | | | | | \ \ | | | \__/ | / ____ \ | |____
+// \ \ | | |__| |__| \__\ |__| \________/ /__/ \__\ |_______|
+// \ \ | | ________________________________________________________________
+// \ \ | | | ______________________________________________________________|
+// \ \| | | | __ __ __ __ ______ _______
+// \ | | |_____ | | | | | | | | | _ \ / _____)
+// \ | | _____| | | | | | | | | | | \ \ \_______
+// \ | | | | |_____ | \_/ | | | | |_/ / _____ |
+// \ _____| |__| |________| \_______/ |__| |______/ (_______/
+//
+// This file is part of VirtualFluids. VirtualFluids is free software: you can
+// redistribute it and/or modify it under the terms of the GNU General Public
+// License as published by the Free Software Foundation, either version 3 of
+// the License, or (at your option) any later version.
+//
+// VirtualFluids is distributed in the hope that it will be useful, but WITHOUT
+// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+// for more details.
+//
+// You should have received a copy of the GNU General Public License along
+// with VirtualFluids (see COPYING.txt). If not, see <http://www.gnu.org/licenses/>.
+//
+//! \file Cumulant27chim.cu
+//! \ingroup GPU
+//! \author Martin Schoenherr, Soeren Peters
+//=======================================================================================
+#ifndef DISTRIBUTUION_HELPER_CUH
+#define DISTRIBUTUION_HELPER_CUH
+
+#include "LBM/LB.h"
+
+#include <lbm/KernelParameter.h>
+
+namespace vf
+{
+namespace gpu
+{
+
+/**
+* Getting references to the 27 directions.
+* @params distributions 1D real* array containing all data (number of elements = 27 * matrix_size)
+* @params matrix_size number of discretizations nodes
+* @params isEvenTimestep: stored data dependent on timestep is based on the esoteric twist algorithm
+* @return a data struct containing the addresses to the 27 directions within the 1D distribution array
+*/
+__device__ __host__ DistributionReferences27 getDistributionReferences27(real* distributions, unsigned int matrix_size, bool isEvenTimestep);
+
+
+/**
+* Holds the references to all directions and the concrete distributions for a single node.
+* After instantiation the distributions are read to the member "distribution" from "distribution_references".
+* After computation the data can be written back to "distribution_references".
+*/
+struct DistributionWrapper
+{
+ __device__ DistributionWrapper(
+ real* distributions,
+ unsigned int size_Mat,
+ bool isEvenTimestep,
+ uint k,
+ uint* neighborX,
+ uint* neighborY,
+ uint* neighborZ);
+
+ __device__ void read();
+
+ __device__ void write();
+
+ // origin distributions to read from and write to after computation
+ DistributionReferences27 distribution_references;
+
+ // distribution pass to kernel computation
+ vf::lbm::Distribution27 distribution;
+
+ const uint k;
+ const uint kw;
+ const uint ks;
+ const uint kb;
+ const uint ksw;
+ const uint kbw;
+ const uint kbs;
+ const uint kbsw;
+};
+
+__device__ unsigned int getNodeIndex();
+
+__device__ bool isValidFluidNode(uint k, int size_Mat, uint nodeType);
+
+}
+}
+
+#endif
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelperTests.cpp b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelperTests.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..46d3fe890fd2f412251044cce6ade51f08ba0185
--- /dev/null
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/DistributionHelperTests.cpp
@@ -0,0 +1,93 @@
+#include <gmock/gmock.h>
+
+#include "DistributionHelper.cuh"
+
+#include "LBM/D3Q27.h"
+
+
+auto RealEq = [](auto value) {
+#ifdef VF_DOUBLE_ACCURACY
+ return testing::DoubleEq(value);
+#else
+ return testing::FloatEq(value);
+#endif
+};
+
+
+TEST(DistributionHelperTests, getPointerToDistribution_WhenEvenTimeStep_ShouldBeEqualToInput)
+{
+ real distributions_in[27];
+ for (int i = 0; i < 27; i++)
+ distributions_in[i] = i;
+ const uint size_Mat = 1;
+ const bool isEvenTimeStep = true;
+
+ Distributions27 distribution_out = vf::gpu::getDistributionReferences27(distributions_in, size_Mat, isEvenTimeStep);
+
+ EXPECT_THAT(*distribution_out.f[dirE], RealEq(distributions_in[dirE]));
+ EXPECT_THAT(*distribution_out.f[dirW], RealEq(distributions_in[dirW]));
+ EXPECT_THAT(*distribution_out.f[dirN], RealEq(distributions_in[dirN]));
+ EXPECT_THAT(*distribution_out.f[dirS], RealEq(distributions_in[dirS]));
+ EXPECT_THAT(*distribution_out.f[dirT], RealEq(distributions_in[dirT]));
+ EXPECT_THAT(*distribution_out.f[dirB], RealEq(distributions_in[dirB]));
+ EXPECT_THAT(*distribution_out.f[dirNE], RealEq(distributions_in[dirNE]));
+ EXPECT_THAT(*distribution_out.f[dirSW], RealEq(distributions_in[dirSW]));
+ EXPECT_THAT(*distribution_out.f[dirSE], RealEq(distributions_in[dirSE]));
+ EXPECT_THAT(*distribution_out.f[dirNW], RealEq(distributions_in[dirNW]));
+ EXPECT_THAT(*distribution_out.f[dirTE], RealEq(distributions_in[dirTE]));
+ EXPECT_THAT(*distribution_out.f[dirBW], RealEq(distributions_in[dirBW]));
+ EXPECT_THAT(*distribution_out.f[dirBE], RealEq(distributions_in[dirBE]));
+ EXPECT_THAT(*distribution_out.f[dirTW], RealEq(distributions_in[dirTW]));
+ EXPECT_THAT(*distribution_out.f[dirTN], RealEq(distributions_in[dirTN]));
+ EXPECT_THAT(*distribution_out.f[dirBS], RealEq(distributions_in[dirBS]));
+ EXPECT_THAT(*distribution_out.f[dirBN], RealEq(distributions_in[dirBN]));
+ EXPECT_THAT(*distribution_out.f[dirTS], RealEq(distributions_in[dirTS]));
+ EXPECT_THAT(*distribution_out.f[dirREST], RealEq(distributions_in[dirREST]));
+ EXPECT_THAT(*distribution_out.f[dirTNE], RealEq(distributions_in[dirTNE]));
+ EXPECT_THAT(*distribution_out.f[dirTSW], RealEq(distributions_in[dirTSW]));
+ EXPECT_THAT(*distribution_out.f[dirTSE], RealEq(distributions_in[dirTSE]));
+ EXPECT_THAT(*distribution_out.f[dirTNW], RealEq(distributions_in[dirTNW]));
+ EXPECT_THAT(*distribution_out.f[dirBNE], RealEq(distributions_in[dirBNE]));
+ EXPECT_THAT(*distribution_out.f[dirBSW], RealEq(distributions_in[dirBSW]));
+ EXPECT_THAT(*distribution_out.f[dirBSE], RealEq(distributions_in[dirBSE]));
+ EXPECT_THAT(*distribution_out.f[dirBNW], RealEq(distributions_in[dirBNW]));
+}
+
+TEST(DistributionHelperTests, getPointerToDistribution_WhenOddTimeStep_ShouldBeSwapped)
+{
+ real distributions_in[27];
+ for (int i = 0; i < 27; i++)
+ distributions_in[i] = i;
+ const int size_Mat = 1;
+ const bool isEvenTimeStep = false;
+
+ Distributions27 distribution_out = vf::gpu::getDistributionReferences27(distributions_in, size_Mat, isEvenTimeStep);
+
+ EXPECT_THAT(*distribution_out.f[dirW], RealEq(distributions_in[dirE]));
+ EXPECT_THAT(*distribution_out.f[dirE], RealEq(distributions_in[dirW]));
+ EXPECT_THAT(*distribution_out.f[dirS], RealEq(distributions_in[dirN]));
+ EXPECT_THAT(*distribution_out.f[dirN], RealEq(distributions_in[dirS]));
+ EXPECT_THAT(*distribution_out.f[dirB], RealEq(distributions_in[dirT]));
+ EXPECT_THAT(*distribution_out.f[dirT], RealEq(distributions_in[dirB]));
+ EXPECT_THAT(*distribution_out.f[dirSW], RealEq(distributions_in[dirNE]));
+ EXPECT_THAT(*distribution_out.f[dirNE], RealEq(distributions_in[dirSW]));
+ EXPECT_THAT(*distribution_out.f[dirNW], RealEq(distributions_in[dirSE]));
+ EXPECT_THAT(*distribution_out.f[dirSE], RealEq(distributions_in[dirNW]));
+ EXPECT_THAT(*distribution_out.f[dirBW], RealEq(distributions_in[dirTE]));
+ EXPECT_THAT(*distribution_out.f[dirTE], RealEq(distributions_in[dirBW]));
+ EXPECT_THAT(*distribution_out.f[dirTW], RealEq(distributions_in[dirBE]));
+ EXPECT_THAT(*distribution_out.f[dirBE], RealEq(distributions_in[dirTW]));
+ EXPECT_THAT(*distribution_out.f[dirBS], RealEq(distributions_in[dirTN]));
+ EXPECT_THAT(*distribution_out.f[dirTN], RealEq(distributions_in[dirBS]));
+ EXPECT_THAT(*distribution_out.f[dirTS], RealEq(distributions_in[dirBN]));
+ EXPECT_THAT(*distribution_out.f[dirBN], RealEq(distributions_in[dirTS]));
+ EXPECT_THAT(*distribution_out.f[dirREST], RealEq(distributions_in[dirREST]));
+ EXPECT_THAT(*distribution_out.f[dirBSW], RealEq(distributions_in[dirTNE]));
+ EXPECT_THAT(*distribution_out.f[dirBNE], RealEq(distributions_in[dirTSW]));
+ EXPECT_THAT(*distribution_out.f[dirBNW], RealEq(distributions_in[dirTSE]));
+ EXPECT_THAT(*distribution_out.f[dirBSE], RealEq(distributions_in[dirTNW]));
+ EXPECT_THAT(*distribution_out.f[dirTSW], RealEq(distributions_in[dirBNE]));
+ EXPECT_THAT(*distribution_out.f[dirTNE], RealEq(distributions_in[dirBSW]));
+ EXPECT_THAT(*distribution_out.f[dirTNW], RealEq(distributions_in[dirBSE]));
+ EXPECT_THAT(*distribution_out.f[dirTSE], RealEq(distributions_in[dirBNW]));
+}
diff --git a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/KernelFactory/KernelFactoryImp.cpp b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/KernelFactory/KernelFactoryImp.cpp
index b0d167974275a227b99da6a0ac8e32e1f2976c13..5f63df1c9afc17a62a9a47ce82401ebba4453872 100644
--- a/src/gpu/VirtualFluids_GPU/Kernel/Utilities/KernelFactory/KernelFactoryImp.cpp
+++ b/src/gpu/VirtualFluids_GPU/Kernel/Utilities/KernelFactory/KernelFactoryImp.cpp
@@ -4,16 +4,19 @@
//LBM kernel (compressible)
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGK/BGKCompSP27.h"
+#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKUnified/BGKUnified.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/BGKPlus/BGKPlusCompSP27.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/Cascade/CascadeCompSP27.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/Cumulant/CumulantCompSP27.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17/CumulantK17Comp.h"
+#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Unified/CumulantK17Unified.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17chim/CumulantK17CompChim.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK17Bulk/CumulantK17BulkComp.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantAll4/CumulantAll4CompSP27.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK18/CumulantK18Comp.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK20/CumulantK20Comp.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15/CumulantK15Comp.h"
+#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Unified/CumulantK15Unified.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Bulk/CumulantK15BulkComp.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/CumulantK15Sponge/CumulantK15SpongeComp.h"
#include "Kernel/Kernels/BasicKernels/FluidFlow/Compressible/MRT/MRTCompSP27.h"
@@ -96,13 +99,17 @@ void KernelFactoryImp::setKernelAtLevel(std::vector<std::shared_ptr<Kernel>> ker
std::shared_ptr<Kernel> KernelFactoryImp::makeKernel(std::shared_ptr<Parameter> para, std::string kernel, int level)
{
+ printf("Instantiating Kernel: %s\n", kernel.c_str());
std::shared_ptr<KernelImp> newKernel;
std::shared_ptr<CheckParameterStrategy> checkStrategy;
- if ( kernel == "BGKCompSP27") {
- newKernel = BGKCompSP27::getNewInstance(para, level); // compressible
- checkStrategy = FluidFlowCompStrategy::getInstance(); // ||
- } else if (kernel == "BGKPlusCompSP27") { // \/
+ if (kernel == "BGKCompSP27") {
+ newKernel = BGKCompSP27::getNewInstance(para, level); // compressible
+ checkStrategy = FluidFlowCompStrategy::getInstance(); // ||
+ } else if (kernel == "BGKUnified") { // \/
+ newKernel = std::make_shared<vf::gpu::BGKUnified>(para, level);
+ checkStrategy = FluidFlowCompStrategy::getInstance();
+ } else if (kernel == "BGKPlusCompSP27") {
newKernel = BGKPlusCompSP27::getNewInstance(para, level);
checkStrategy = FluidFlowCompStrategy::getInstance();
} else if (kernel == "MRTCompSP27") {
@@ -117,6 +124,12 @@ std::shared_ptr<Kernel> KernelFactoryImp::makeKernel(std::shared_ptr<Parameter>
} else if (kernel == "CumulantK17Comp") {
newKernel = CumulantK17Comp::getNewInstance(para, level);
checkStrategy = FluidFlowCompStrategy::getInstance();
+ } else if (kernel == "CumulantK15Unified") {
+ newKernel = std::make_shared<vf::gpu::CumulantK15Unified>(para, level);
+ checkStrategy = FluidFlowCompStrategy::getInstance();
+ } else if (kernel == "CumulantK17Unified") {
+ newKernel = std::make_shared<vf::gpu::CumulantK17Unified>(para, level);
+ checkStrategy = FluidFlowCompStrategy::getInstance();
} else if (kernel == "CumulantK17BulkComp") {
newKernel = CumulantK17BulkComp::getNewInstance(para, level);
checkStrategy = FluidFlowCompStrategy::getInstance();
diff --git a/src/gpu/VirtualFluids_GPU/LBM/D3Q27.h b/src/gpu/VirtualFluids_GPU/LBM/D3Q27.h
index 546dccd463a96ad3173517d09f222acde11e2448..5e769b603e7c6677b7f9e1189f5c4fe27051f795 100644
--- a/src/gpu/VirtualFluids_GPU/LBM/D3Q27.h
+++ b/src/gpu/VirtualFluids_GPU/LBM/D3Q27.h
@@ -21,6 +21,7 @@
#define dirBN /*f17*/ 16
#define dirTS /*f18*/ 17
#define dirZERO /*f0 */ 18
+#define dirREST /*f0 */ 18
#define dirTNE /*f */ 19
#define dirBNE /*f */ 20
diff --git a/src/gpu/VirtualFluids_GPU/LBM/LB.h b/src/gpu/VirtualFluids_GPU/LBM/LB.h
index f5f91738739b95f897a1192cb7c1d77a6cfea9cb..52f932c7b751b0d31e9bf733a4f3b5c439a6755f 100644
--- a/src/gpu/VirtualFluids_GPU/LBM/LB.h
+++ b/src/gpu/VirtualFluids_GPU/LBM/LB.h
@@ -144,7 +144,7 @@ typedef struct Distri19{
// Distribution functions f 27
typedef struct Distri27{
real* f[27];
-} Distributions27;
+} Distributions27, DistributionReferences27;
//Q for second order BCs
typedef struct QforBC{
diff --git a/src/gpu/VirtualFluids_GPU/LBM/Simulation.cpp b/src/gpu/VirtualFluids_GPU/LBM/Simulation.cpp
index f61bd5571f60b5feb771f351a7877cb15a5842cb..9a4cd41cea8996db4a8e3ed92b44121c3d549f45 100644
--- a/src/gpu/VirtualFluids_GPU/LBM/Simulation.cpp
+++ b/src/gpu/VirtualFluids_GPU/LBM/Simulation.cpp
@@ -1,4 +1,10 @@
#include "Simulation.h"
+
+#include <stdio.h>
+#include <vector>
+
+#include <helper_timer.h>
+
#include "LBM/LB.h"
#include "Communication/Communicator.h"
#include "Communication/ExchangeData27.h"
@@ -85,12 +91,13 @@ void Simulation::init(SPtr<Parameter> para, SPtr<GridProvider> gridProvider, std
para->setNumprocs(comm->getNummberOfProcess());
devCheck(comm->mapCudaDevice(para->getMyID(), para->getNumprocs(), para->getDevices(), para->getMaxDev()));
+ para->initParameter();
+
gridProvider->allocAndCopyForcing();
gridProvider->allocAndCopyQuadricLimiters();
gridProvider->setDimensions();
gridProvider->setBoundingBox();
- para->initParameter();
para->setRe(para->getVelocity() * (real)1.0 / para->getViscosity());
para->setPhi((real) 0.0);
para->setlimitOfNodesForVTK(30000000); //max 30 Million nodes per VTK file
diff --git a/src/gpu/VirtualFluids_GPU/LBM/Simulation.h b/src/gpu/VirtualFluids_GPU/LBM/Simulation.h
index ae46034ce3e6080e0b9f03a92dd0326d640c6f32..d6c6702c4db8a671d4f6dbfea4c90cdf8f48356d 100644
--- a/src/gpu/VirtualFluids_GPU/LBM/Simulation.h
+++ b/src/gpu/VirtualFluids_GPU/LBM/Simulation.h
@@ -5,13 +5,12 @@
#include <vector>
#include <PointerDefinitions.h>
-
-
#include "Output/LogWriter.hpp"
#include "GPU/KineticEnergyAnalyzer.h"
#include "GPU/EnstrophyAnalyzer.h"
#include "Utilities/Buffer2D.hpp"
#include "LBM/LB.h"
+
#include "VirtualFluids_GPU_export.h"
namespace vf
diff --git a/src/gpu/VirtualFluids_GPU/Parameter/Parameter.h b/src/gpu/VirtualFluids_GPU/Parameter/Parameter.h
index 25946704edcad12513d1b8a2c70cd551eb1dd619..ccb13e83bcc68b9c9d85725666a02ea1c23ec293 100644
--- a/src/gpu/VirtualFluids_GPU/Parameter/Parameter.h
+++ b/src/gpu/VirtualFluids_GPU/Parameter/Parameter.h
@@ -186,6 +186,7 @@ struct ParameterStruct{
//velocities to fit the force
real *VxForce, *VyForce, *VzForce;
//////////////////////////////////////////////////////////////////////////
+ real *forcing;
//Measure Points/////////
std::vector<MeasurePoints> MP;
diff --git a/src/gpu/VirtualFluids_GPU/Restart/RestartObjectTests.cpp b/src/gpu/VirtualFluids_GPU/Restart/RestartObjectTests.cpp
index a9b485ab25871066c201e631b97022bc6f7e08fb..c30f514c60ba1af2fb852ed8a68b36121ebced04 100644
--- a/src/gpu/VirtualFluids_GPU/Restart/RestartObjectTests.cpp
+++ b/src/gpu/VirtualFluids_GPU/Restart/RestartObjectTests.cpp
@@ -8,7 +8,7 @@ void saveAndLoad()
{
std::shared_ptr<RestartObject> write_object = std::make_shared<Type>();
- write_object->fs = std::vector<std::vector<float>> {
+ write_object->fs = std::vector<std::vector<real>> {
{ 1,2,3 },
{ 4,5,6 }
};
diff --git a/src/lbm/BGK.cpp b/src/lbm/BGK.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..fa3af6777a0492687768dd4945cbf1e9b186f514
--- /dev/null
+++ b/src/lbm/BGK.cpp
@@ -0,0 +1,140 @@
+#include "BGK.h"
+
+
+#include <basics/Core/DataTypes.h>
+#include <basics/Core/RealConstants.h>
+
+#include "constants/NumericConstants.h"
+#include "constants/D3Q27.h"
+
+#include "MacroscopicQuantities.h"
+
+namespace vf
+{
+namespace lbm
+{
+
+using namespace constant;
+
+
+
+__host__ __device__ void bgk(KernelParameter parameter)
+{
+ auto& distribution = parameter.distribution;
+ const auto omega = parameter.omega;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Read distributions: style of reading and writing the distributions from/to
+ //! stored arrays dependent on timestep is based on the esoteric twist algorithm
+ //! <a href="https://doi.org/10.3390/computation5020019"><b>[ M. Geier et al. (2017), DOI:10.3390/computation5020019 ]</b></a>
+ //!
+ real mfcbb = distribution.f[dir::PZZ];
+ real mfabb = distribution.f[dir::MZZ];
+ real mfbcb = distribution.f[dir::ZPZ];
+ real mfbab = distribution.f[dir::ZMZ];
+ real mfbbc = distribution.f[dir::ZZP];
+ real mfbba = distribution.f[dir::ZZM];
+ real mfccb = distribution.f[dir::PPZ];
+ real mfaab = distribution.f[dir::MMZ];
+ real mfcab = distribution.f[dir::PMZ];
+ real mfacb = distribution.f[dir::MPZ];
+ real mfcbc = distribution.f[dir::PZP];
+ real mfaba = distribution.f[dir::MZM];
+ real mfcba = distribution.f[dir::PZM];
+ real mfabc = distribution.f[dir::MZP];
+ real mfbcc = distribution.f[dir::ZPP];
+ real mfbaa = distribution.f[dir::ZMM];
+ real mfbca = distribution.f[dir::ZPM];
+ real mfbac = distribution.f[dir::ZMP];
+ real mfccc = distribution.f[dir::PPP];
+ real mfacc = distribution.f[dir::MPP];
+ real mfcac = distribution.f[dir::PMP];
+ real mfaac = distribution.f[dir::MMP];
+ real mfcca = distribution.f[dir::PPM];
+ real mfaca = distribution.f[dir::MPM];
+ real mfcaa = distribution.f[dir::PMM];
+ real mfaaa = distribution.f[dir::MMM];
+ real mfbbb = distribution.f[dir::ZZZ];
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Acquire macroscopic quantities
+ const real drho = getDensity(distribution.f);
+ const real rho = c1o1 + drho;
+ const real OOrho = constant::c1o1 / (constant::c1o1 + drho);
+
+ const real vvx = getIncompressibleVelocityX1(distribution.f) * OOrho;
+ const real vvy = getIncompressibleVelocityX2(distribution.f) * OOrho;
+ const real vvz = getIncompressibleVelocityX3(distribution.f) * OOrho;
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - BGK computation
+ const real cusq = c3o2*(vvx*vvx + vvy*vvy + vvz*vvz);
+
+ mfbbb = mfbbb *(c1o1 + (-omega)) - (-omega)* c8o27* (drho - rho * cusq);
+ mfcbb = mfcbb *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(vvx)+c9o2*(vvx)*(vvx)-cusq));
+ mfabb = mfabb *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(-vvx) + c9o2*(-vvx)*(-vvx) - cusq));
+ mfbcb = mfbcb *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(vvy)+c9o2*(vvy)*(vvy)-cusq));
+ mfbab = mfbab *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(-vvy) + c9o2*(-vvy)*(-vvy) - cusq));
+ mfbbc = mfbbc *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(vvz)+c9o2*(vvz)*(vvz)-cusq));
+ mfbba = mfbba *(c1o1 + (-omega)) - (-omega)* c2o27* (drho + rho * (c3o1*(-vvz) + c9o2*(-vvz)*(-vvz) - cusq));
+ mfccb = mfccb *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvx + vvy) + c9o2*(vvx + vvy)*(vvx + vvy) - cusq));
+ mfaab = mfaab *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvx - vvy) + c9o2*(-vvx - vvy)*(-vvx - vvy) - cusq));
+ mfcab = mfcab *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvx - vvy) + c9o2*(vvx - vvy)*(vvx - vvy) - cusq));
+ mfacb = mfacb *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvx + vvy) + c9o2*(-vvx + vvy)*(-vvx + vvy) - cusq));
+ mfcbc = mfcbc *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvx + vvz) + c9o2*(vvx + vvz)*(vvx + vvz) - cusq));
+ mfaba = mfaba *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvx - vvz) + c9o2*(-vvx - vvz)*(-vvx - vvz) - cusq));
+ mfcba = mfcba *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvx - vvz) + c9o2*(vvx - vvz)*(vvx - vvz) - cusq));
+ mfabc = mfabc *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvx + vvz) + c9o2*(-vvx + vvz)*(-vvx + vvz) - cusq));
+ mfbcc = mfbcc *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvy + vvz) + c9o2*(vvy + vvz)*(vvy + vvz) - cusq));
+ mfbaa = mfbaa *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvy - vvz) + c9o2*(-vvy - vvz)*(-vvy - vvz) - cusq));
+ mfbca = mfbca *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(vvy - vvz) + c9o2*(vvy - vvz)*(vvy - vvz) - cusq));
+ mfbac = mfbac *(c1o1 + (-omega)) - (-omega)* c1o54* (drho + rho * (c3o1*(-vvy + vvz) + c9o2*(-vvy + vvz)*(-vvy + vvz) - cusq));
+ mfccc = mfccc *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(vvx + vvy + vvz) + c9o2*(vvx + vvy + vvz)*(vvx + vvy + vvz) - cusq));
+ mfaaa = mfaaa *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(-vvx - vvy - vvz) + c9o2*(-vvx - vvy - vvz)*(-vvx - vvy - vvz) - cusq));
+ mfcca = mfcca *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(vvx + vvy - vvz) + c9o2*(vvx + vvy - vvz)*(vvx + vvy - vvz) - cusq));
+ mfaac = mfaac *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(-vvx - vvy + vvz) + c9o2*(-vvx - vvy + vvz)*(-vvx - vvy + vvz) - cusq));
+ mfcac = mfcac *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(vvx - vvy + vvz) + c9o2*(vvx - vvy + vvz)*(vvx - vvy + vvz) - cusq));
+ mfaca = mfaca *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(-vvx + vvy - vvz) + c9o2*(-vvx + vvy - vvz)*(-vvx + vvy - vvz) - cusq));
+ mfcaa = mfcaa *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(vvx - vvy - vvz) + c9o2*(vvx - vvy - vvz)*(vvx - vvy - vvz) - cusq));
+ mfacc = mfacc *(c1o1 + (-omega)) - (-omega)* c1o216*(drho + rho * (c3o1*(-vvx + vvy + vvz) + c9o2*(-vvx + vvy + vvz)*(-vvx + vvy + vvz) - cusq));
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Write distributions: style of reading and writing the distributions from/to
+ //! stored arrays dependent on timestep is based on the esoteric twist algorithm
+ //! <a href="https://doi.org/10.3390/computation5020019"><b>[ M. Geier et al. (2017), DOI:10.3390/computation5020019 ]</b></a>
+ //!
+ distribution.f[dir::MZZ] = mfcbb;
+ distribution.f[dir::PZZ] = mfabb;
+ distribution.f[dir::ZMZ] = mfbcb;
+ distribution.f[dir::ZPZ] = mfbab;
+ distribution.f[dir::ZZM] = mfbbc;
+ distribution.f[dir::ZZP] = mfbba;
+ distribution.f[dir::MMZ] = mfccb;
+ distribution.f[dir::PPZ] = mfaab;
+ distribution.f[dir::MPZ] = mfcab;
+ distribution.f[dir::PMZ] = mfacb;
+ distribution.f[dir::MZM] = mfcbc;
+ distribution.f[dir::PZP] = mfaba;
+ distribution.f[dir::MZP] = mfcba;
+ distribution.f[dir::PZM] = mfabc;
+ distribution.f[dir::ZMM] = mfbcc;
+ distribution.f[dir::ZPP] = mfbaa;
+ distribution.f[dir::ZMP] = mfbca;
+ distribution.f[dir::ZPM] = mfbac;
+ distribution.f[dir::MMM] = mfccc;
+ distribution.f[dir::PMM] = mfacc;
+ distribution.f[dir::MPM] = mfcac;
+ distribution.f[dir::PPM] = mfaac;
+ distribution.f[dir::MMP] = mfcca;
+ distribution.f[dir::PMP] = mfaca;
+ distribution.f[dir::MPP] = mfcaa;
+ distribution.f[dir::PPP] = mfaaa;
+ distribution.f[dir::ZZZ] = mfbbb;
+}
+
+
+}
+}
+
diff --git a/src/lbm/BGK.h b/src/lbm/BGK.h
new file mode 100644
index 0000000000000000000000000000000000000000..2c82f5bd445ee008954add02fd0d6d6093364e90
--- /dev/null
+++ b/src/lbm/BGK.h
@@ -0,0 +1,24 @@
+#ifndef LBM_BGK_H
+#define LBM_BGK_H
+
+#ifndef __host__
+#define __host__
+#endif
+#ifndef __device__
+#define __device__
+#endif
+
+#include <basics/Core/DataTypes.h>
+
+#include "KernelParameter.h"
+
+namespace vf
+{
+namespace lbm
+{
+
+__host__ __device__ void bgk(KernelParameter parameter);
+
+}
+}
+#endif
diff --git a/src/lbm/CMakeLists.txt b/src/lbm/CMakeLists.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6e9f76793825ccf4e4e9e921e9fd4b6ab3584707
--- /dev/null
+++ b/src/lbm/CMakeLists.txt
@@ -0,0 +1,10 @@
+project(lbm LANGUAGES CXX)
+
+vf_add_library(NAME lbm PUBLIC_LINK basics)
+
+if(BUILD_VF_GPU)
+ add_subdirectory(cuda)
+endif()
+
+
+vf_add_tests()
diff --git a/src/lbm/Chimera.h b/src/lbm/Chimera.h
new file mode 100644
index 0000000000000000000000000000000000000000..6ffa0918aac4e6303efe4db82aa98ee645dc63e8
--- /dev/null
+++ b/src/lbm/Chimera.h
@@ -0,0 +1,121 @@
+#ifndef LBM_CHIMERA_H
+#define LBM_CHIMERA_H
+
+#ifndef __host__
+#define __host__
+#endif
+#ifndef __device__
+#define __device__
+#endif
+
+#include <basics/Core/DataTypes.h>
+
+#include <lbm/constants/NumericConstants.h>
+
+namespace vf
+{
+namespace lbm
+{
+
+using namespace constant;
+
+////////////////////////////////////////////////////////////////////////////////
+//! \brief forward chimera transformation \ref forwardInverseChimeraWithK
+//! Transformation from distributions to central moments according to Eq. (6)-(14) in
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+//! Modified for lower round-off errors.
+////////////////////////////////////////////////////////////////////////////////
+inline __host__ __device__ void forwardInverseChimeraWithK(real &mfa, real &mfb, real &mfc, real vv,
+ real v2, real Kinverse, real K)
+{
+ const real m2 = mfa + mfc;
+ const real m1 = mfc - mfa;
+ real m0 = m2 + mfb;
+
+ mfa = m0;
+ m0 *= Kinverse;
+ m0 += c1o1;
+ mfb = (m1 * Kinverse - m0 * vv) * K;
+ mfc = ((m2 - c2o1 * m1 * vv) * Kinverse + v2 * m0) * K;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+//! \brief backward chimera transformation \ref backwardInverseChimeraWithK
+//! Transformation from central moments to distributions according to Eq. (57)-(65) in
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+//! ] Modified for lower round-off errors.
+////////////////////////////////////////////////////////////////////////////////
+inline __host__ __device__ void backwardInverseChimeraWithK(real &mfa, real &mfb, real &mfc, real vv,
+ real v2, real Kinverse, real K)
+{
+ const real m0 = (((mfc - mfb) * c1o2 + mfb * vv) * Kinverse + (mfa * Kinverse + c1o1) * (v2 - vv) * c1o2) * K;
+ const real m1 = (((mfa - mfc) - c2o1 * mfb * vv) * Kinverse + (mfa * Kinverse + c1o1) * (-v2)) * K;
+
+ mfc = (((mfc + mfb) * c1o2 + mfb * vv) * Kinverse + (mfa * Kinverse + c1o1) * (v2 + vv) * c1o2) * K;
+ mfa = m0;
+ mfb = m1;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+//! \brief forward chimera transformation \ref forwardChimera
+//! Transformation from distributions to central moments according to Eq. (6)-(14) in
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+//! for \f$ K_{abc}=0 \f$. This is to avoid unnessary floating point operations.
+//! Modified for lower round-off errors.
+////////////////////////////////////////////////////////////////////////////////
+inline __host__ __device__ void forwardChimera(real &mfa, real &mfb, real &mfc, real vv, real v2)
+{
+ const real m1 = (mfa + mfc) + mfb;
+ const real m2 = mfc - mfa;
+
+ mfc = (mfc + mfa) + (v2 * m1 - c2o1 * vv * m2);
+ mfb = m2 - vv * m1;
+ mfa = m1;
+}
+
+////////////////////////////////////////////////////////////////////////////////
+//! \brief backward chimera transformation \ref backwardChimera
+//! Transformation from central moments to distributions according to Eq. (57)-(65) in
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+//! for \f$ K_{abc}=0 \f$. This is to avoid unnessary floating point operations.
+//! Modified for lower round-off errors.
+////////////////////////////////////////////////////////////////////////////////
+inline __host__ __device__ void backwardChimera(real &mfa, real &mfb, real &mfc, real vv, real v2)
+{
+ const real ma = (mfc + mfa * (v2 - vv)) * c1o2 + mfb * (vv - c1o2);
+ const real mb = ((mfa - mfc) - mfa * v2) - c2o1 * mfb * vv;
+
+ mfc = (mfc + mfa * (v2 + vv)) * c1o2 + mfb * (vv + c1o2);
+ mfb = mb;
+ mfa = ma;
+}
+
+
+inline __host__ __device__ void forwardChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real K)
+{
+
+ const real m2 = mfa + mfc;
+ const real m1 = mfc - mfa;
+ const real m0 = m2 + mfb;
+ mfa = m0;
+ //m0 += K;
+ mfb = (m1 - K*vv) - m0 * vv;
+ mfc = ((m2 - c2o1* m1 * vv) + v2*K) + v2 * m0;
+ //m0 += K;
+ //mfb = m1 - m0 * vv;
+ //mfc = m2 - two* m1 * vv + v2 * m0;
+}
+
+
+inline __host__ __device__ void backwardChimeraWithK(real &mfa, real &mfb, real &mfc, real vv, real v2, real K)
+{
+ const real m0 = (mfc - mfb)* c1o2 + mfb * (vv)+(mfa + K) * (v2 - vv) * c1o2;
+ const real m1 = (mfa - mfc) - c2o1* mfb * vv + (mfa + K) * (-v2);
+ mfc = (mfc + mfb)* c1o2 + mfb * (vv)+(mfa + K) * (v2 + vv) * c1o2;
+ mfa = m0;
+ mfb = m1;
+}
+
+}
+}
+#endif
diff --git a/src/lbm/ChimeraTests.cpp b/src/lbm/ChimeraTests.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..01abbe82764c276f53a4cdd479d333536199c3a9
--- /dev/null
+++ b/src/lbm/ChimeraTests.cpp
@@ -0,0 +1,133 @@
+#include <gmock/gmock.h>
+
+#include "Chimera.h"
+
+#ifdef VF_DOUBLE_ACCURACY
+#define REAL_EQ(a) testing::DoubleEq(a)
+#else
+#define REAL_EQ(a) testing::FloatEq(a)
+#endif
+
+/*
+* InverseChimeraWithK
+*/
+TEST(ChimeraTest, forwardInverseChimeraWithK)
+{
+ real mfa = 1;
+ real mfb = 1;
+ real mfc = 1;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ const real K = 1.;
+ const real Kinverse = 1 / K;
+
+ vf::lbm::forwardInverseChimeraWithK(mfa, mfb, mfc, vv, v2, K, Kinverse);
+
+ EXPECT_THAT(mfa, REAL_EQ(3.)); // mfa + mfb + mfc
+ EXPECT_THAT(mfb, REAL_EQ(-4.)); // -(mfa + mfb + mfc + 1)
+ EXPECT_THAT(mfc, REAL_EQ(6.)); // (mfa + mfc) + (mfa + mfb + mfc + 1)
+}
+
+
+TEST(ChimeraTest, backwardInverseChimeraWithK)
+{
+ // starting with the result values from the test above.
+ real mfa = 3.;
+ real mfb = -4.;
+ real mfc = 6.;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ const real K = 1.;
+ const real Kinverse = 1 / K;
+
+ vf::lbm::backwardInverseChimeraWithK(mfa, mfb, mfc, vv, v2, K, Kinverse);
+
+ // resulting in the start values from the test above.
+ EXPECT_THAT(mfa, REAL_EQ(1.));
+ EXPECT_THAT(mfb, REAL_EQ(1.));
+ EXPECT_THAT(mfc, REAL_EQ(1.));
+}
+
+/*
+* Chimera
+*/
+TEST(ChimeraTest, forwardChimera)
+{
+ real mfa = 1;
+ real mfb = 1;
+ real mfc = 1;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ vf::lbm::forwardChimera(mfa, mfb, mfc, vv, v2);
+
+ EXPECT_THAT(mfa, REAL_EQ(3.)); // mfa + mfb + mfc
+ EXPECT_THAT(mfb, REAL_EQ(-3.)); // -(mfa + mfb + mfc)
+ EXPECT_THAT(mfc, REAL_EQ(5.)); // (mfa + mfc) + (mfa + mfb + mfc)
+}
+
+
+TEST(ChimeraTest, backwardChimera)
+{
+ // starting with the result values from the test above.
+ real mfa = 3.;
+ real mfb = -3.;
+ real mfc = 5.;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ vf::lbm::backwardChimera(mfa, mfb, mfc, vv, v2);
+
+ // resulting in the start values from the test above.
+ EXPECT_THAT(mfa, REAL_EQ(1.));
+ EXPECT_THAT(mfb, REAL_EQ(1.));
+ EXPECT_THAT(mfc, REAL_EQ(1.));
+}
+
+/*
+* ChimeraWithK
+*/
+TEST(ChimeraTest, forwardChimeraWithK)
+{
+ real mfa = 1;
+ real mfb = 1;
+ real mfc = 1;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ const real K = 1.;
+
+ vf::lbm::forwardChimeraWithK(mfa, mfb, mfc, vv, v2, K);
+
+ EXPECT_THAT(mfa, REAL_EQ(3.)); // mfa + mfb + mfc
+ EXPECT_THAT(mfb, REAL_EQ(-4.)); // -(mfa + mfb + mfc)
+ EXPECT_THAT(mfc, REAL_EQ(6.)); // (mfa + mfc) + (mfa + mfb + mfc)
+}
+
+
+TEST(ChimeraTest, backwardChimeraWithK)
+{
+ // starting with the result values from the test above.
+ real mfa = 3.;
+ real mfb = -4.;
+ real mfc = 6.;
+
+ const real vv = 1.;
+ const real v2 = 1.;
+
+ const real K = 1.;
+
+ vf::lbm::backwardChimeraWithK(mfa, mfb, mfc, vv, v2, K);
+
+ // resulting in the start values from the test above.
+ EXPECT_THAT(mfa, REAL_EQ(1.));
+ EXPECT_THAT(mfb, REAL_EQ(1.));
+ EXPECT_THAT(mfc, REAL_EQ(1.));
+}
diff --git a/src/lbm/CumulantChimera.cpp b/src/lbm/CumulantChimera.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..65dc9b1f82f409447fda54fc0bc5f460533aad1b
--- /dev/null
+++ b/src/lbm/CumulantChimera.cpp
@@ -0,0 +1,453 @@
+#include "CumulantChimera.h"
+
+#include <cmath>
+
+#include <basics/Core/DataTypes.h>
+#include <basics/Core/RealConstants.h>
+
+#include "constants/NumericConstants.h"
+#include "constants/D3Q27.h"
+
+#include "Chimera.h"
+#include "MacroscopicQuantities.h"
+
+namespace vf
+{
+namespace lbm
+{
+
+using namespace constant;
+
+
+////////////////////////////////////////////////////////////////////////////////////
+//! - Setting relaxation rates for non-hydrodynamic cumulants (default values). Variable names and equations according to
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+//! => [NAME IN PAPER]=[NAME IN CODE]=[DEFAULT VALUE].
+//! - Trace of second order cumulants \f$ C_{200}+C_{020}+C_{002} \f$ used to adjust bulk viscosity:\f$\omega_2=OxxPyyPzz=1.0 \f$.
+//! - Third order cumulants \f$ C_{120}+C_{102}, C_{210}+C_{012}, C_{201}+C_{021} \f$: \f$ \omega_3=OxyyPxzz \f$ set according to Eq. (111) with simplifications assuming \f$ \omega_2=1.0\f$.
+//! - Third order cumulants \f$ C_{120}-C_{102}, C_{210}-C_{012}, C_{201}-C_{021} \f$: \f$ \omega_4 = OxyyMxzz \f$ set according to Eq. (112) with simplifications assuming \f$ \omega_2 = 1.0\f$.
+//! - Third order cumulants \f$ C_{111} \f$: \f$ \omega_5 = Oxyz \f$ set according to Eq. (113) with simplifications assuming \f$ \omega_2 = 1.0\f$ (modify for different bulk viscosity).
+//! - Fourth order cumulants \f$ C_{220}, C_{202}, C_{022}, C_{211}, C_{121}, C_{112} \f$: for simplification all set to the same default value \f$ \omega_6=\omega_7=\omega_8=O4=1.0 \f$.
+//! - Fifth order cumulants \f$ C_{221}, C_{212}, C_{122}\f$: \f$\omega_9=O5=1.0\f$.
+//! - Sixth order cumulant \f$ C_{222}\f$: \f$\omega_{10}=O6=1.0\f$.
+//////////////////////////////////////////////////////////////////////////
+__host__ __device__ void setRelaxationRatesK17(real omega, real &OxxPyyPzz, real &OxyyPxzz, real &OxyyMxzz, real &Oxyz,
+ real &O4, real &O5, real &O6)
+{
+ OxxPyyPzz = c1o1;
+
+ OxyyPxzz = c8o1 * (-c2o1 + omega) * (c1o1 + c2o1 * omega) / (-c8o1 - c14o1 * omega + c7o1 * omega * omega);
+ OxyyMxzz = c8o1 * (-c2o1 + omega) * (-c7o1 + c4o1 * omega) / (c56o1 - c50o1 * omega + c9o1 * omega * omega);
+ Oxyz = c24o1 * (-c2o1 + omega) * (-c2o1 - c7o1 * omega + c3o1 * omega * omega) /
+ (c48o1 + c152o1 * omega - c130o1 * omega * omega + c29o1 * omega * omega * omega);
+
+ O4 = c1o1;
+
+ O5 = c1o1;
+
+ O6 = c1o1;
+}
+
+
+__host__ __device__ void setRelaxationRatesK15(real omega, real &OxxPyyPzz, real &OxyyPxzz, real &OxyyMxzz, real &Oxyz,
+ real &O4, real &O5, real &O6)
+{
+ OxxPyyPzz = c1o1;
+
+ OxyyPxzz = c1o1;
+ OxyyMxzz = c1o1;
+ Oxyz = c1o1;
+
+ O4 = c1o1;
+
+ O5 = c1o1;
+
+ O6 = c1o1;
+}
+
+//////////////////////////////////////////////////////////////////////////
+//! Cumulant K17 Kernel is based on \ref
+//! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05.040 ]</b></a>
+//! and \ref
+//! <a href="https://doi.org/10.1016/j.jcp.2017.07.004"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.07.004 ]</b></a>
+//////////////////////////////////////////////////////////////////////////
+__host__ __device__ void cumulantChimera(KernelParameter parameter, RelaxationRatesFunctor setRelaxationRates)
+{
+ auto& distribution = parameter.distribution;
+ const auto omega = parameter.omega;
+ const auto* forces = parameter.forces;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Read distributions: style of reading and writing the distributions from/to
+ //! stored arrays dependent on timestep is based on the esoteric twist algorithm
+ //! <a href="https://doi.org/10.3390/computation5020019"><b>[ M. Geier et al. (2017), DOI:10.3390/computation5020019 ]</b></a>
+ //!
+ real mfcbb = distribution.f[dir::PZZ];
+ real mfabb = distribution.f[dir::MZZ];
+ real mfbcb = distribution.f[dir::ZPZ];
+ real mfbab = distribution.f[dir::ZMZ];
+ real mfbbc = distribution.f[dir::ZZP];
+ real mfbba = distribution.f[dir::ZZM];
+ real mfccb = distribution.f[dir::PPZ];
+ real mfaab = distribution.f[dir::MMZ];
+ real mfcab = distribution.f[dir::PMZ];
+ real mfacb = distribution.f[dir::MPZ];
+ real mfcbc = distribution.f[dir::PZP];
+ real mfaba = distribution.f[dir::MZM];
+ real mfcba = distribution.f[dir::PZM];
+ real mfabc = distribution.f[dir::MZP];
+ real mfbcc = distribution.f[dir::ZPP];
+ real mfbaa = distribution.f[dir::ZMM];
+ real mfbca = distribution.f[dir::ZPM];
+ real mfbac = distribution.f[dir::ZMP];
+ real mfccc = distribution.f[dir::PPP];
+ real mfacc = distribution.f[dir::MPP];
+ real mfcac = distribution.f[dir::PMP];
+ real mfaac = distribution.f[dir::MMP];
+ real mfcca = distribution.f[dir::PPM];
+ real mfaca = distribution.f[dir::MPM];
+ real mfcaa = distribution.f[dir::PMM];
+ real mfaaa = distribution.f[dir::MMM];
+ real mfbbb = distribution.f[dir::ZZZ];
+
+
+ const real drho = getDensity(distribution.f);
+ const real OOrho = c1o1 / (c1o1 + drho);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Add half of the acceleration (body force) to the velocity as in Eq. (42) \ref
+ //! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+ //!
+ const real vvx = getIncompressibleVelocityX1(distribution.f) * OOrho + forces[0] * c1o2;
+ const real vvy = getIncompressibleVelocityX2(distribution.f) * OOrho + forces[0] * c1o2;
+ const real vvz = getIncompressibleVelocityX3(distribution.f) * OOrho + forces[0] * c1o2;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ // calculate the square of velocities for this lattice node
+ const real vx2 = vvx*vvx;
+ const real vy2 = vvy*vvy;
+ const real vz2 = vvz*vvz;
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Chimera transform from well conditioned distributions to central moments as defined in Appendix J in \ref
+ //! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+ //! see also Eq. (6)-(14) in \ref
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Z - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c36o1, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::forwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c36o1, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c9o1, c1o9);
+ vf::lbm::forwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c9o4, c4o9);
+ vf::lbm::forwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::forwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c36o1, c1o36);
+ vf::lbm::forwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::forwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c36o1, c1o36);
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Y - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c6o1, c1o6);
+ vf::lbm::forwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c18o1, c1o18);
+ vf::lbm::forwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c3o2, c2o3);
+ vf::lbm::forwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c9o2, c2o9);
+ vf::lbm::forwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c6o1, c1o6);
+ vf::lbm::forwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::forwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c18o1, c1o18);
+ ////////////////////////////////////////////////////////////////////////////////////
+ // X - Dir
+ vf::lbm::forwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
+ vf::lbm::forwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c3o1, c1o3);
+ vf::lbm::forwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::forwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::forwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c3o1, c1o3);
+ vf::lbm::forwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::forwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c3o1, c1o9);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Setting relaxation rates for non-hydrodynamic cumulants (default values). Variable names and equations
+ real OxxPyyPzz;
+ real OxyyPxzz;
+ real OxyyMxzz;
+ real Oxyz;
+ real O4;
+ real O5;
+ real O6;
+
+ setRelaxationRates(omega, OxxPyyPzz, OxyyPxzz, OxyyMxzz, Oxyz, O4, O5, O6);
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - A and B: parameters for fourth order convergence of the diffusion term according to Eq. (114) and (115)
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //! with simplifications assuming \f$ \omega_2 = 1.0 \f$ (modify for different bulk viscosity).
+ //!
+ const real A = (c4o1 + c2o1*omega - c3o1*omega*omega) / (c2o1 - c7o1*omega + c5o1*omega*omega);
+ const real B = (c4o1 + c28o1*omega - c14o1*omega*omega) / (c6o1 - c21o1*omega + c15o1*omega*omega);
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Compute cumulants from central moments according to Eq. (20)-(23) in
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ ////////////////////////////////////////////////////////////
+ //4.
+ real CUMcbb = mfcbb - ((mfcaa + c1o3) * mfabb + c2o1 * mfbba * mfbab) * OOrho;
+ real CUMbcb = mfbcb - ((mfaca + c1o3) * mfbab + c2o1 * mfbba * mfabb) * OOrho;
+ real CUMbbc = mfbbc - ((mfaac + c1o3) * mfbba + c2o1 * mfbab * mfabb) * OOrho;
+ real CUMcca = mfcca - (((mfcaa * mfaca + c2o1 * mfbba * mfbba) + c1o3 * (mfcaa + mfaca)) * OOrho - c1o9*(drho * OOrho));
+ real CUMcac = mfcac - (((mfcaa * mfaac + c2o1 * mfbab * mfbab) + c1o3 * (mfcaa + mfaac)) * OOrho - c1o9*(drho * OOrho));
+ real CUMacc = mfacc - (((mfaac * mfaca + c2o1 * mfabb * mfabb) + c1o3 * (mfaac + mfaca)) * OOrho - c1o9*(drho * OOrho));
+ ////////////////////////////////////////////////////////////
+ //5.
+ real CUMbcc = mfbcc - ((mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + c1o3 * (mfbca + mfbac)) * OOrho;
+ real CUMcbc = mfcbc - ((mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + c1o3 * (mfcba + mfabc)) * OOrho;
+ real CUMccb = mfccb - ((mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + c1o3 * (mfacb + mfcab)) * OOrho;
+ ////////////////////////////////////////////////////////////
+ //6.
+ real CUMccc = mfccc + ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
+ - c1o3 * (mfacc + mfcac + mfcca) * OOrho
+ - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
+ + c1o27*((drho * drho - drho) * OOrho * OOrho));
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Compute linear combinations of second and third order cumulants
+ //!
+ ////////////////////////////////////////////////////////////
+ //2.
+ real mxxPyyPzz = mfcaa + mfaca + mfaac;
+ real mxxMyy = mfcaa - mfaca;
+ real mxxMzz = mfcaa - mfaac;
+ ////////////////////////////////////////////////////////////
+ //3.
+ real mxxyPyzz = mfcba + mfabc;
+ real mxxyMyzz = mfcba - mfabc;
+ real mxxzPyyz = mfcab + mfacb;
+ real mxxzMyyz = mfcab - mfacb;
+ real mxyyPxzz = mfbca + mfbac;
+ real mxyyMxzz = mfbca - mfbac;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //incl. correction
+ ////////////////////////////////////////////////////////////
+ //! - Compute velocity gradients from second order cumulants according to Eq. (27)-(32)
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //! Further explanations of the correction in viscosity in Appendix H of
+ //! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+ //! Note that the division by rho is omitted here as we need rho times the gradients later.
+ //!
+ const real Dxy = -c3o1*omega*mfbba;
+ const real Dxz = -c3o1*omega*mfbab;
+ const real Dyz = -c3o1*omega*mfabb;
+ const real dxux = c1o2 * (-omega) *(mxxMyy + mxxMzz) + c1o2 * OxxPyyPzz * (mfaaa - mxxPyyPzz);
+ const real dyuy = dxux + omega * c3o2 * mxxMyy;
+ const real dzuz = dxux + omega * c3o2 * mxxMzz;
+ ////////////////////////////////////////////////////////////
+ //! - Relaxation of second order cumulants with correction terms according to Eq. (33)-(35) in
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz) - c3o1 * (c1o1 - c1o2 * OxxPyyPzz) * (vx2 * dxux + vy2 * dyuy + vz2 * dzuz);
+ mxxMyy += omega * (-mxxMyy) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vy2 * dyuy);
+ mxxMzz += omega * (-mxxMzz) - c3o1 * (c1o1 + c1o2 * (-omega)) * (vx2 * dxux - vz2 * dzuz);
+ ////////////////////////////////////////////////////////////////////////////////////
+ ////no correction
+ //mxxPyyPzz += OxxPyyPzz*(mfaaa - mxxPyyPzz);
+ //mxxMyy += -(-omega) * (-mxxMyy);
+ //mxxMzz += -(-omega) * (-mxxMzz);
+ //////////////////////////////////////////////////////////////////////////
+ mfabb += omega * (-mfabb);
+ mfbab += omega * (-mfbab);
+ mfbba += omega * (-mfbba);
+ ////////////////////////////////////////////////////////////////////////////////////
+ //relax
+ //////////////////////////////////////////////////////////////////////////
+ // incl. limiter
+ //! Set relaxation limiters for third order cumulants to default value \f$ \lambda=0.001 \f$ according to section 6 in \ref
+ //! - Relaxation of third order cumulants including limiter according to Eq. (116)-(123)
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+
+ const real qudricLimitP = c1o100;
+ const real qudricLimitM = c1o100;
+ const real qudricLimitD = c1o100;
+
+ real wadjust = Oxyz + (c1o1 - Oxyz)*abs_internal(mfbbb) / (abs_internal(mfbbb) + qudricLimitD);
+ mfbbb += wadjust * (-mfbbb);
+ wadjust = OxyyPxzz + (c1o1 - OxyyPxzz)*abs_internal(mxxyPyzz) / (abs_internal(mxxyPyzz) + qudricLimitP);
+ mxxyPyzz += wadjust * (-mxxyPyzz);
+ wadjust = OxyyMxzz + (c1o1 - OxyyMxzz)*abs_internal(mxxyMyzz) / (abs_internal(mxxyMyzz) + qudricLimitM);
+ mxxyMyzz += wadjust * (-mxxyMyzz);
+ wadjust = OxyyPxzz + (c1o1 - OxyyPxzz)*abs_internal(mxxzPyyz) / (abs_internal(mxxzPyyz) + qudricLimitP);
+ mxxzPyyz += wadjust * (-mxxzPyyz);
+ wadjust = OxyyMxzz + (c1o1 - OxyyMxzz)*abs_internal(mxxzMyyz) / (abs_internal(mxxzMyyz) + qudricLimitM);
+ mxxzMyyz += wadjust * (-mxxzMyyz);
+ wadjust = OxyyPxzz + (c1o1 - OxyyPxzz)*abs_internal(mxyyPxzz) / (abs_internal(mxyyPxzz) + qudricLimitP);
+ mxyyPxzz += wadjust * (-mxyyPxzz);
+ wadjust = OxyyMxzz + (c1o1 - OxyyMxzz)*abs_internal(mxyyMxzz) / (abs_internal(mxyyMxzz) + qudricLimitM);
+ mxyyMxzz += wadjust * (-mxyyMxzz);
+ //////////////////////////////////////////////////////////////////////////
+ // no limiter
+ //mfbbb += OxyyMxzz * (-mfbbb);
+ //mxxyPyzz += OxyyPxzz * (-mxxyPyzz);
+ //mxxyMyzz += OxyyMxzz * (-mxxyMyzz);
+ //mxxzPyyz += OxyyPxzz * (-mxxzPyyz);
+ //mxxzMyyz += OxyyMxzz * (-mxxzMyyz);
+ //mxyyPxzz += OxyyPxzz * (-mxyyPxzz);
+ //mxyyMxzz += OxyyMxzz * (-mxyyMxzz);
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Compute inverse linear combinations of second and third order cumulants
+ //!
+ mfcaa = c1o3 * (mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaca = c1o3 * (-c2o1* mxxMyy + mxxMzz + mxxPyyPzz);
+ mfaac = c1o3 * (mxxMyy - c2o1* mxxMzz + mxxPyyPzz);
+ mfcba = ( mxxyMyzz + mxxyPyzz) * c1o2;
+ mfabc = (-mxxyMyzz + mxxyPyzz) * c1o2;
+ mfcab = ( mxxzMyyz + mxxzPyyz) * c1o2;
+ mfacb = (-mxxzMyyz + mxxzPyyz) * c1o2;
+ mfbca = ( mxyyMxzz + mxyyPxzz) * c1o2;
+ mfbac = (-mxyyMxzz + mxyyPxzz) * c1o2;
+ //////////////////////////////////////////////////////////////////////////
+ //////////////////////////////////////////////////////////////////////////
+ //4.
+ // no limiter
+ //! - Relax fourth order cumulants to modified equilibrium for fourth order convergence of diffusion according to Eq. (43)-(48)
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ CUMacc = -O4*(c1o1 / omega - c1o2) * (dyuy + dzuz) * c2o3 * A + (c1o1 - O4) * (CUMacc);
+ CUMcac = -O4*(c1o1 / omega - c1o2) * (dxux + dzuz) * c2o3 * A + (c1o1 - O4) * (CUMcac);
+ CUMcca = -O4*(c1o1 / omega - c1o2) * (dyuy + dxux) * c2o3 * A + (c1o1 - O4) * (CUMcca);
+ CUMbbc = -O4*(c1o1 / omega - c1o2) * Dxy * c1o3 * B + (c1o1 - O4) * (CUMbbc);
+ CUMbcb = -O4*(c1o1 / omega - c1o2) * Dxz * c1o3 * B + (c1o1 - O4) * (CUMbcb);
+ CUMcbb = -O4*(c1o1 / omega - c1o2) * Dyz * c1o3 * B + (c1o1 - O4) * (CUMcbb);
+ //////////////////////////////////////////////////////////////////////////
+ //5.
+ CUMbcc += O5 * (-CUMbcc);
+ CUMcbc += O5 * (-CUMcbc);
+ CUMccb += O5 * (-CUMccb);
+ //////////////////////////////////////////////////////////////////////////
+ //6.
+ CUMccc += O6 * (-CUMccc);
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Compute central moments from post collision cumulants according to Eq. (53)-(56) in
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ //////////////////////////////////////////////////////////////////////////
+ //4.
+ mfcbb = CUMcbb + c1o3*((c3o1*mfcaa + c1o1) * mfabb + c6o1 * mfbba * mfbab) * OOrho;
+ mfbcb = CUMbcb + c1o3*((c3o1*mfaca + c1o1) * mfbab + c6o1 * mfbba * mfabb) * OOrho;
+ mfbbc = CUMbbc + c1o3*((c3o1*mfaac + c1o1) * mfbba + c6o1 * mfbab * mfabb) * OOrho;
+ mfcca = CUMcca + (((mfcaa * mfaca + c2o1 * mfbba * mfbba)*c9o1 + c3o1 * (mfcaa + mfaca)) * OOrho - (drho * OOrho))*c1o9;
+ mfcac = CUMcac + (((mfcaa * mfaac + c2o1 * mfbab * mfbab)*c9o1 + c3o1 * (mfcaa + mfaac)) * OOrho - (drho * OOrho))*c1o9;
+ mfacc = CUMacc + (((mfaac * mfaca + c2o1 * mfabb * mfabb)*c9o1 + c3o1 * (mfaac + mfaca)) * OOrho - (drho * OOrho))*c1o9;
+ //////////////////////////////////////////////////////////////////////////
+ //5.
+ mfbcc = CUMbcc + c1o3 *(c3o1*(mfaac * mfbca + mfaca * mfbac + c4o1 * mfabb * mfbbb + c2o1 * (mfbab * mfacb + mfbba * mfabc)) + (mfbca + mfbac)) * OOrho;
+ mfcbc = CUMcbc + c1o3 *(c3o1*(mfaac * mfcba + mfcaa * mfabc + c4o1 * mfbab * mfbbb + c2o1 * (mfabb * mfcab + mfbba * mfbac)) + (mfcba + mfabc)) * OOrho;
+ mfccb = CUMccb + c1o3 *(c3o1*(mfcaa * mfacb + mfaca * mfcab + c4o1 * mfbba * mfbbb + c2o1 * (mfbab * mfbca + mfabb * mfcba)) + (mfacb + mfcab)) * OOrho;
+ //////////////////////////////////////////////////////////////////////////
+ //6.
+ mfccc = CUMccc - ((-c4o1 * mfbbb * mfbbb
+ - (mfcaa * mfacc + mfaca * mfcac + mfaac * mfcca)
+ - c4o1 * (mfabb * mfcbb + mfbab * mfbcb + mfbba * mfbbc)
+ - c2o1 * (mfbca * mfbac + mfcba * mfabc + mfcab * mfacb)) * OOrho
+ + (c4o1 * (mfbab * mfbab * mfaca + mfabb * mfabb * mfcaa + mfbba * mfbba * mfaac)
+ + c2o1 * (mfcaa * mfaca * mfaac)
+ + c16o1 * mfbba * mfbab * mfabb) * OOrho * OOrho
+ - c1o3 * (mfacc + mfcac + mfcca) * OOrho
+ - c1o9 * (mfcaa + mfaca + mfaac) * OOrho
+ + (c2o1 * (mfbab * mfbab + mfabb * mfabb + mfbba * mfbba)
+ + (mfaac * mfaca + mfaac * mfcaa + mfaca * mfcaa) + c1o3 *(mfaac + mfaca + mfcaa)) * OOrho * OOrho * c2o3
+ + c1o27*((drho * drho - drho) * OOrho * OOrho));
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Add acceleration (body force) to first order cumulants according to Eq. (85)-(87) in
+ //! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+ //!
+ mfbaa = -mfbaa;
+ mfaba = -mfaba;
+ mfaab = -mfaab;
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Chimera transform from central moments to well conditioned distributions as defined in Appendix J in
+ //! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+ //! see also Eq. (88)-(96) in
+ //! <a href="https://doi.org/10.1016/j.jcp.2017.05.040"><b>[ M. Geier et al. (2017), DOI:10.1016/j.jcp.2017.05 040 ]</b></a>
+ //!
+ ////////////////////////////////////////////////////////////////////////////////////
+ // X - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfbaa, mfcaa, vvx, vx2, c1o1, c1o1);
+ vf::lbm::backwardChimera( mfaba, mfbba, mfcba, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfaca, mfbca, mfcca, vvx, vx2, c3o1, c1o3);
+ vf::lbm::backwardChimera( mfaab, mfbab, mfcab, vvx, vx2);
+ vf::lbm::backwardChimera( mfabb, mfbbb, mfcbb, vvx, vx2);
+ vf::lbm::backwardChimera( mfacb, mfbcb, mfccb, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfaac, mfbac, mfcac, vvx, vx2, c3o1, c1o3);
+ vf::lbm::backwardChimera( mfabc, mfbbc, mfcbc, vvx, vx2);
+ vf::lbm::backwardInverseChimeraWithK(mfacc, mfbcc, mfccc, vvx, vx2, c9o1, c1o9);
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Y - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfaba, mfaca, vvy, vy2, c6o1, c1o6);
+ vf::lbm::backwardChimera( mfaab, mfabb, mfacb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfaac, mfabc, mfacc, vvy, vy2, c18o1, c1o18);
+ vf::lbm::backwardInverseChimeraWithK(mfbaa, mfbba, mfbca, vvy, vy2, c3o2, c2o3);
+ vf::lbm::backwardChimera( mfbab, mfbbb, mfbcb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfbac, mfbbc, mfbcc, vvy, vy2, c9o2, c2o9);
+ vf::lbm::backwardInverseChimeraWithK(mfcaa, mfcba, mfcca, vvy, vy2, c6o1, c1o6);
+ vf::lbm::backwardChimera( mfcab, mfcbb, mfccb, vvy, vy2);
+ vf::lbm::backwardInverseChimeraWithK(mfcac, mfcbc, mfccc, vvy, vy2, c18o1, c1o18);
+ ////////////////////////////////////////////////////////////////////////////////////
+ // Z - Dir
+ vf::lbm::backwardInverseChimeraWithK(mfaaa, mfaab, mfaac, vvz, vz2, c36o1, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfaba, mfabb, mfabc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::backwardInverseChimeraWithK(mfaca, mfacb, mfacc, vvz, vz2, c36o1, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfbaa, mfbab, mfbac, vvz, vz2, c9o1, c1o9);
+ vf::lbm::backwardInverseChimeraWithK(mfbba, mfbbb, mfbbc, vvz, vz2, c9o4, c4o9);
+ vf::lbm::backwardInverseChimeraWithK(mfbca, mfbcb, mfbcc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::backwardInverseChimeraWithK(mfcaa, mfcab, mfcac, vvz, vz2, c36o1, c1o36);
+ vf::lbm::backwardInverseChimeraWithK(mfcba, mfcbb, mfcbc, vvz, vz2, c9o1, c1o9);
+ vf::lbm::backwardInverseChimeraWithK(mfcca, mfccb, mfccc, vvz, vz2, c36o1, c1o36);
+
+
+ ////////////////////////////////////////////////////////////////////////////////////
+ //! - Write distributions: style of reading and writing the distributions from/to
+ //! stored arrays dependent on timestep is based on the esoteric twist algorithm
+ //! <a href="https://doi.org/10.3390/computation5020019"><b>[ M. Geier et al. (2017), DOI:10.3390/computation5020019 ]</b></a>
+ //!
+ distribution.f[dir::MZZ] = mfcbb;
+ distribution.f[dir::PZZ] = mfabb;
+ distribution.f[dir::ZMZ] = mfbcb;
+ distribution.f[dir::ZPZ] = mfbab;
+ distribution.f[dir::ZZM] = mfbbc;
+ distribution.f[dir::ZZP] = mfbba;
+ distribution.f[dir::MMZ] = mfccb;
+ distribution.f[dir::PPZ] = mfaab;
+ distribution.f[dir::MPZ] = mfcab;
+ distribution.f[dir::PMZ] = mfacb;
+ distribution.f[dir::MZM] = mfcbc;
+ distribution.f[dir::PZP] = mfaba;
+ distribution.f[dir::MZP] = mfcba;
+ distribution.f[dir::PZM] = mfabc;
+ distribution.f[dir::ZMM] = mfbcc;
+ distribution.f[dir::ZPP] = mfbaa;
+ distribution.f[dir::ZMP] = mfbca;
+ distribution.f[dir::ZPM] = mfbac;
+ distribution.f[dir::MMM] = mfccc;
+ distribution.f[dir::PMM] = mfacc;
+ distribution.f[dir::MPM] = mfcac;
+ distribution.f[dir::PPM] = mfaac;
+ distribution.f[dir::MMP] = mfcca;
+ distribution.f[dir::PMP] = mfaca;
+ distribution.f[dir::MPP] = mfcaa;
+ distribution.f[dir::PPP] = mfaaa;
+ distribution.f[dir::ZZZ] = mfbbb;
+}
+
+
+}
+}
+
diff --git a/src/lbm/CumulantChimera.h b/src/lbm/CumulantChimera.h
new file mode 100644
index 0000000000000000000000000000000000000000..e8740c7d3f5b988a6fdc5c3b16ab6a90e0a28b83
--- /dev/null
+++ b/src/lbm/CumulantChimera.h
@@ -0,0 +1,34 @@
+#ifndef LBM_CUMULANT_CHIMERA_H
+#define LBM_CUMULANT_CHIMERA_H
+
+#ifndef __host__
+#define __host__
+#endif
+#ifndef __device__
+#define __device__
+#endif
+
+#include <basics/Core/DataTypes.h>
+
+#include "KernelParameter.h"
+
+namespace vf
+{
+namespace lbm
+{
+
+__host__ __device__ void setRelaxationRatesK17(real omega, real &OxxPyyPzz, real &OxyyPxzz, real &OxyyMxzz, real &Oxyz,
+ real &O4, real &O5, real &O6);
+
+__host__ __device__ void setRelaxationRatesK15(real omega, real &OxxPyyPzz, real &OxyyPxzz, real &OxyyMxzz, real &Oxyz,
+ real &O4, real &O5, real &O6);
+
+using RelaxationRatesFunctor = void(*)(real omega, real &OxxPyyPzz, real &OxyyPxzz, real &OxyyMxzz, real &Oxyz,
+ real &O4, real &O5, real &O6);
+
+
+__host__ __device__ void cumulantChimera(KernelParameter parameter, RelaxationRatesFunctor setRelaxationRates);
+
+}
+}
+#endif
diff --git a/src/lbm/KernelParameter.cpp b/src/lbm/KernelParameter.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..e039214d218ef19f35e8adf927f36d3a6f1aa355
--- /dev/null
+++ b/src/lbm/KernelParameter.cpp
@@ -0,0 +1,33 @@
+#include "KernelParameter.h"
+
+#include <cmath>
+
+#include "MacroscopicQuantities.h"
+
+
+namespace vf
+{
+namespace lbm
+{
+
+
+
+inline __host__ __device__ real Distribution27::getDensity_() const
+{
+ return getDensity(f);
+}
+
+
+
+__host__ __device__ real abs_internal(real value)
+{
+#ifdef __CUDA_ARCH__
+ return ::abs(value);
+#else
+ return std::abs(value);
+#endif
+}
+
+
+}
+}
diff --git a/src/lbm/KernelParameter.h b/src/lbm/KernelParameter.h
new file mode 100644
index 0000000000000000000000000000000000000000..95226628110637f3794c8a1f7e6f6c1f6dda937b
--- /dev/null
+++ b/src/lbm/KernelParameter.h
@@ -0,0 +1,43 @@
+#ifndef LBM_KERNEL_PARAMETER_H
+#define LBM_KERNEL_PARAMETER_H
+
+#ifndef __host__
+#define __host__
+#endif
+#ifndef __device__
+#define __device__
+#endif
+
+#include <basics/Core/DataTypes.h>
+
+
+namespace vf
+{
+namespace lbm
+{
+
+struct Distribution27
+{
+ real f[27];
+
+ __host__ __device__ real getDensity_() const;
+};
+
+
+__host__ __device__ real abs_internal(real value);
+
+
+struct KernelParameter
+{
+ Distribution27& distribution;
+ real omega;
+ real* forces;
+};
+
+
+
+
+}
+}
+
+#endif
diff --git a/src/lbm/MacroscopicQuantities.h b/src/lbm/MacroscopicQuantities.h
new file mode 100644
index 0000000000000000000000000000000000000000..c37791294ff5b4edad21795f4ce0a32a18c5d236
--- /dev/null
+++ b/src/lbm/MacroscopicQuantities.h
@@ -0,0 +1,98 @@
+#ifndef LBM_CALCMAC_H
+#define LBM_CALCMAC_H
+
+#ifndef __host__
+#define __host__
+#endif
+#ifndef __device__
+#define __device__
+#endif
+
+#include <basics/Core/DataTypes.h>
+
+#include "constants/NumericConstants.h"
+#include "constants/D3Q27.h"
+
+namespace vf
+{
+namespace lbm
+{
+
+////////////////////////////////////////////////////////////////////////////////////
+//! - Calculate density and velocity using pyramid summation for low round-off errors as in Eq. (J1)-(J3) \ref
+//! <a href="https://doi.org/10.1016/j.camwa.2015.05.001"><b>[ M. Geier et al. (2015), DOI:10.1016/j.camwa 2015.05.001 ]</b></a>
+//!
+
+inline __host__ __device__ real getDensity(const real *const &f /*[27]*/)
+{
+ return ((f[dir::TNE] + f[dir::BSW]) + (f[dir::TSE] + f[dir::BNW])) + ((f[dir::BSE] + f[dir::TNW]) + (f[dir::TSW] + f[dir::BNE])) +
+ (((f[dir::NE] + f[dir::SW]) + (f[dir::SE] + f[dir::NW])) + ((f[dir::TE] + f[dir::BW]) + (f[dir::BE] + f[dir::TW])) +
+ ((f[dir::BN] + f[dir::TS]) + (f[dir::TN] + f[dir::BS]))) +
+ ((f[dir::E] + f[dir::W]) + (f[dir::N] + f[dir::S]) + (f[dir::T] + f[dir::B])) + f[dir::REST];
+}
+
+/*
+* Incompressible Macroscopic Quantities
+*/
+inline __host__ __device__ real getIncompressibleVelocityX1(const real *const &f /*[27]*/)
+{
+ return ((((f[dir::TNE] - f[dir::BSW]) + (f[dir::TSE] - f[dir::BNW])) + ((f[dir::BSE] - f[dir::TNW]) + (f[dir::BNE] - f[dir::TSW]))) +
+ (((f[dir::BE] - f[dir::TW]) + (f[dir::TE] - f[dir::BW])) + ((f[dir::SE] - f[dir::NW]) + (f[dir::NE] - f[dir::SW]))) + (f[dir::E] - f[dir::W]));
+}
+
+
+inline __host__ __device__ real getIncompressibleVelocityX2(const real *const &f /*[27]*/)
+{
+ return ((((f[dir::TNE] - f[dir::BSW]) + (f[dir::BNW] - f[dir::TSE])) + ((f[dir::TNW] - f[dir::BSE]) + (f[dir::BNE] - f[dir::TSW]))) +
+ (((f[dir::BN] - f[dir::TS]) + (f[dir::TN] - f[dir::BS])) + ((f[dir::NW] - f[dir::SE]) + (f[dir::NE] - f[dir::SW]))) + (f[dir::N] - f[dir::S]));
+}
+
+
+inline __host__ __device__ real getIncompressibleVelocityX3(const real *const &f /*[27]*/)
+{
+ return ((((f[dir::TNE] - f[dir::BSW]) + (f[dir::TSE] - f[dir::BNW])) + ((f[dir::TNW] - f[dir::BSE]) + (f[dir::TSW] - f[dir::BNE]))) +
+ (((f[dir::TS] - f[dir::BN]) + (f[dir::TN] - f[dir::BS])) + ((f[dir::TW] - f[dir::BE]) + (f[dir::TE] - f[dir::BW]))) + (f[dir::T] - f[dir::B]));
+}
+
+
+
+/*
+* Compressible Macroscopic Quantities
+*/
+inline __host__ __device__ real getCompressibleVelocityX1(const real *const &f27, const real& rho)
+{
+ return getIncompressibleVelocityX1(f27) / (rho + constant::c1o1);
+}
+
+
+inline __host__ __device__ real getCompressibleVelocityX2(const real *const &f27, const real& rho)
+{
+ return getIncompressibleVelocityX2(f27) / (rho + constant::c1o1);
+}
+
+
+inline __host__ __device__ real getCompressibleVelocityX3(const real *const &f27, const real& rho)
+{
+ return getIncompressibleVelocityX3(f27) / (rho + constant::c1o1);
+}
+
+/*
+* Pressure
+*/
+inline __host__ __device__ real getPressure(const real *const &f27, const real& rho, const real& vx, const real& vy, const real& vz)
+{
+ return (f27[dir::E] + f27[dir::W] + f27[dir::N] + f27[dir::S] + f27[dir::T] + f27[dir::B] +
+ constant::c2o1 * (f27[dir::NE] + f27[dir::SW] + f27[dir::SE] + f27[dir::NW] + f27[dir::TE] +
+ f27[dir::BW] + f27[dir::BE] + f27[dir::TW] + f27[dir::TN] + f27[dir::BS] +
+ f27[dir::BN] + f27[dir::TS]) +
+ constant::c3o1 * (f27[dir::TNE] + f27[dir::TSW] + f27[dir::TSE] + f27[dir::TNW] +
+ f27[dir::BNE] + f27[dir::BSW] + f27[dir::BSE] + f27[dir::BNW]) -
+ rho - (vx * vx + vy * vy + vz * vz) * (constant::c1o1 + rho)) *
+ constant::c1o2 + rho; // times zero for incompressible case
+ // Attention: op defined directly to op = 1 ; ^^^^(1.0/op-0.5)=0.5
+}
+
+}
+}
+
+#endif
diff --git a/src/lbm/MacroscopicQuantitiesTests.cpp b/src/lbm/MacroscopicQuantitiesTests.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..52f89943a3e6a99fcab13eba22de9959229a289d
--- /dev/null
+++ b/src/lbm/MacroscopicQuantitiesTests.cpp
@@ -0,0 +1,71 @@
+#include <gmock/gmock.h>
+
+#include "MacroscopicQuantities.h"
+#include "constants/D3Q27.h"
+
+
+/*
+* given distributions, which are all one.
+*/
+real f[27] = {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1};
+
+using namespace vf::lbm;
+
+
+TEST(MacroscopicQuantitiesTest, check_density)
+{
+ const double density = getDensity(f);
+
+ const double expected_density = 27.;
+ ASSERT_THAT(density, testing::DoubleEq(expected_density));
+}
+
+TEST(MacroscopicQuantitiesTest, whenFsAreEqual_velocityInEachDirectionShouldBeZero)
+{
+ const double velocityX1 = getIncompressibleVelocityX1(f);
+ const double velocityX2 = getIncompressibleVelocityX2(f);
+ const double velocityX3 = getIncompressibleVelocityX3(f);
+
+ const double expected_velocity = 0.;
+ EXPECT_THAT(velocityX1, testing::DoubleEq(expected_velocity));
+ EXPECT_THAT(velocityX2, testing::DoubleEq(expected_velocity));
+ EXPECT_THAT(velocityX3, testing::DoubleEq(expected_velocity));
+}
+
+TEST(MacroscopicQuantitiesTest, givenAllFsAreOne_when_Eis2_velocityInX1ShouldBeOne)
+{
+ f[dir::E] = 2.;
+
+ const double velocityX1 = getIncompressibleVelocityX1(f);
+ const double velocityX2 = getIncompressibleVelocityX2(f);
+ const double velocityX3 = getIncompressibleVelocityX3(f);
+
+ const double expected_velocity_x1 = 1.;
+ const double expected_velocity_x2 = 0.;
+ const double expected_velocity_x3 = 0.;
+
+ EXPECT_THAT(velocityX1, testing::DoubleEq(expected_velocity_x1));
+ EXPECT_THAT(velocityX2, testing::DoubleEq(expected_velocity_x2));
+ EXPECT_THAT(velocityX3, testing::DoubleEq(expected_velocity_x3));
+}
+
+TEST(MacroscopicQuantitiesTest, givenAllFsAreOne_when_Nis2_velocityInX2ShouldBeOne)
+{
+ f[dir::N] = 2.;
+
+ const double velocity = getIncompressibleVelocityX2(f);
+
+ const double expected_velocity = 1.;
+ ASSERT_THAT(velocity, testing::DoubleEq(expected_velocity));
+}
+
+
+TEST(MacroscopicQuantitiesTest, givenAllFsAreOne_when_Tis2_velocityInX3ShouldBeOne)
+{
+ f[dir::T] = 2.;
+
+ const double velocity = getIncompressibleVelocityX3(f);
+
+ const double expected_velocity = 1.;
+ ASSERT_THAT(velocity, testing::DoubleEq(expected_velocity));
+}
diff --git a/src/lbm/constants/D3Q27.h b/src/lbm/constants/D3Q27.h
new file mode 100644
index 0000000000000000000000000000000000000000..0b2cbfdd44e84af590fa2c2be4bf319cbfd4c815
--- /dev/null
+++ b/src/lbm/constants/D3Q27.h
@@ -0,0 +1,71 @@
+#ifndef LBM_D3Q27_H
+#define LBM_D3Q27_H
+
+namespace vf
+{
+namespace lbm
+{
+namespace dir
+{
+
+static constexpr int E = 0;
+static constexpr int W = 1;
+static constexpr int N = 2;
+static constexpr int S = 3;
+static constexpr int T = 4;
+static constexpr int B = 5;
+static constexpr int NE = 6;
+static constexpr int SW = 7;
+static constexpr int SE = 8;
+static constexpr int NW = 9;
+static constexpr int TE = 10;
+static constexpr int BW = 11;
+static constexpr int BE = 12;
+static constexpr int TW = 13;
+static constexpr int TN = 14;
+static constexpr int BS = 15;
+static constexpr int BN = 16;
+static constexpr int TS = 17;
+static constexpr int TNE = 18;
+static constexpr int TNW = 19;
+static constexpr int TSE = 20;
+static constexpr int TSW = 21;
+static constexpr int BNE = 22;
+static constexpr int BNW = 23;
+static constexpr int BSE = 24;
+static constexpr int BSW = 25;
+static constexpr int REST = 26;
+
+static constexpr int PZZ = 0;
+static constexpr int MZZ = 1;
+static constexpr int ZPZ = 2;
+static constexpr int ZMZ = 3;
+static constexpr int ZZP = 4;
+static constexpr int ZZM = 5;
+static constexpr int PPZ = 6;
+static constexpr int MMZ = 7;
+static constexpr int PMZ = 8;
+static constexpr int MPZ = 9;
+static constexpr int PZP = 10;
+static constexpr int MZM = 11;
+static constexpr int PZM = 12;
+static constexpr int MZP = 13;
+static constexpr int ZPP = 14;
+static constexpr int ZMM = 15;
+static constexpr int ZPM = 16;
+static constexpr int ZMP = 17;
+static constexpr int PPP = 18;
+static constexpr int MPP = 19;
+static constexpr int PMP = 20;
+static constexpr int MMP = 21;
+static constexpr int PPM = 22;
+static constexpr int MPM = 23;
+static constexpr int PMM = 24;
+static constexpr int MMM = 25;
+static constexpr int ZZZ = 26;
+
+}
+}
+}
+
+#endif
diff --git a/src/lbm/cuda/CMakeLists.txt b/src/lbm/cuda/CMakeLists.txt
new file mode 100644
index 0000000000000000000000000000000000000000..be16988a480650cbab416652655af9766bcf8ec7
--- /dev/null
+++ b/src/lbm/cuda/CMakeLists.txt
@@ -0,0 +1,12 @@
+project(lbmCuda LANGUAGES CUDA CXX)
+
+
+vf_add_library(NAME lbmCuda BUILDTYPE static PUBLIC_LINK basics FOLDER ../../lbm)
+
+
+set_target_properties(lbmCuda PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+set_source_files_properties(../KernelParameter.cpp PROPERTIES LANGUAGE CUDA)
+
+set_source_files_properties(../CumulantChimera.cpp PROPERTIES LANGUAGE CUDA)
+set_source_files_properties(../BGK.cpp PROPERTIES LANGUAGE CUDA)
\ No newline at end of file