x86 avx512 optimization for mish #5949
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: macos-x64-gpu | |
| on: | |
| push: | |
| branches: [master] | |
| paths: | |
| - '.github/workflows/macos-x64-gpu.yml' | |
| - 'CMakeLists.txt' | |
| - 'cmake/**' | |
| - 'src/*' | |
| - 'src/layer/*' | |
| - 'src/layer/x86/**' | |
| - 'src/layer/vulkan/**' | |
| - 'tests/**' | |
| - 'tools/**' | |
| - '!tools/pnnx/**' | |
| - 'examples/**' | |
| pull_request: | |
| branches: [master] | |
| paths: | |
| - '.github/workflows/macos-x64-gpu.yml' | |
| - 'CMakeLists.txt' | |
| - 'cmake/**' | |
| - 'src/*' | |
| - 'src/layer/*' | |
| - 'src/layer/x86/**' | |
| - 'src/layer/vulkan/**' | |
| - 'tests/**' | |
| - 'tools/**' | |
| - '!tools/pnnx/**' | |
| - 'examples/**' | |
| concurrency: | |
| group: macos-x64-gpu-${{ github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| DEVELOPER_DIR: /Applications/Xcode_13.4.1.app/Contents/Developer | |
| MAC_DEPLOYMENT_TARGET: '10.9' | |
| MAC_ARM64_DEPLOYMENT_TARGET: '11.0' | |
| ENABLE_BITCODE: OFF | |
| ENABLE_ARC: OFF | |
| ENABLE_VISIBILITY: OFF | |
| permissions: | |
| contents: read | |
| jobs: | |
| macos-clang-gpu: | |
| runs-on: macos-12 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| submodules: true | |
| - name: protobuf | |
| run: brew install protobuf opencv3 | |
| - name: cache-openmp | |
| id: cache-openmp | |
| uses: actions/cache@v4 | |
| with: | |
| path: openmp-install | |
| key: openmp-macos-install-20230504 | |
| - name: openmp | |
| if: steps.cache-openmp.outputs.cache-hit != 'true' | |
| run: | | |
| wget https://github.com/llvm/llvm-project/releases/download/llvmorg-11.0.0/openmp-11.0.0.src.tar.xz | |
| tar -xf openmp-11.0.0.src.tar.xz | |
| cd openmp-11.0.0.src | |
| sed -i'' -e '/.size __kmp_unnamed_critical_addr/d' runtime/src/z_Linux_asm.S | |
| sed -i'' -e 's/__kmp_unnamed_critical_addr/___kmp_unnamed_critical_addr/g' runtime/src/z_Linux_asm.S | |
| - name: openmp-build-x86_64 | |
| if: steps.cache-openmp.outputs.cache-hit != 'true' | |
| run: | | |
| cd openmp-11.0.0.src | |
| mkdir -p build-x86_64 && cd build-x86_64 | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../../toolchains/ios.toolchain.cmake -DPLATFORM=MAC -DARCHS="x86_64" \ | |
| -DDEPLOYMENT_TARGET=$MAC_DEPLOYMENT_TARGET -DENABLE_BITCODE=$ENABLE_BITCODE -DENABLE_ARC=$ENABLE_ARC -DENABLE_VISIBILITY=$ENABLE_VISIBILITY \ | |
| -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=install \ | |
| -DPERL_EXECUTABLE=/usr/local/bin/perl \ | |
| -DLIBOMP_ENABLE_SHARED=OFF -DLIBOMP_OMPT_SUPPORT=OFF -DLIBOMP_USE_HWLOC=OFF .. | |
| cmake --build . -j 3 | |
| cmake --build . --target install | |
| - name: openmp-build-arm64 | |
| if: steps.cache-openmp.outputs.cache-hit != 'true' | |
| run: | | |
| cd openmp-11.0.0.src | |
| mkdir -p build-arm64 && cd build-arm64 | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../../toolchains/ios.toolchain.cmake -DPLATFORM=MAC_ARM64 -DARCHS="arm64" \ | |
| -DDEPLOYMENT_TARGET=$MAC_ARM64_DEPLOYMENT_TARGET -DENABLE_BITCODE=$ENABLE_BITCODE -DENABLE_ARC=$ENABLE_ARC -DENABLE_VISIBILITY=$ENABLE_VISIBILITY \ | |
| -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=install \ | |
| -DPERL_EXECUTABLE=/usr/local/bin/perl \ | |
| -DLIBOMP_ENABLE_SHARED=OFF -DLIBOMP_OMPT_SUPPORT=OFF -DLIBOMP_USE_HWLOC=OFF .. | |
| cmake --build . -j 3 | |
| cmake --build . --target install | |
| - name: openmp-merge-fat-library | |
| if: steps.cache-openmp.outputs.cache-hit != 'true' | |
| run: | | |
| mkdir -p $GITHUB_WORKSPACE/openmp-install | |
| cp -a openmp-11.0.0.src/build-x86_64/install/include $GITHUB_WORKSPACE/openmp-install | |
| mkdir -p $GITHUB_WORKSPACE/openmp-install/lib | |
| lipo -create \ | |
| openmp-11.0.0.src/build-x86_64/install/lib/libomp.a \ | |
| openmp-11.0.0.src/build-arm64/install/lib/libomp.a \ | |
| -o $GITHUB_WORKSPACE/openmp-install/lib/libomp.a | |
| - name: install-openmp | |
| run: | | |
| sudo cp $GITHUB_WORKSPACE/openmp-install/include/* $DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/usr/include | |
| sudo cp $GITHUB_WORKSPACE/openmp-install/lib/libomp.a $DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/usr/lib | |
| - name: cache-swiftshader | |
| id: cache-swiftshader | |
| uses: actions/cache@v4 | |
| with: | |
| path: swiftshader-install | |
| key: swiftshader-macos-install-20230420 | |
| - name: checkout-swiftshader | |
| if: steps.cache-swiftshader.outputs.cache-hit != 'true' | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: google/swiftshader | |
| path: swiftshader | |
| ref: dd55e592406dc0bae219df11adec6363840aff4a | |
| - name: checkout-swiftshader-submodules | |
| if: steps.cache-swiftshader.outputs.cache-hit != 'true' | |
| run: | | |
| cd swiftshader | |
| git -c submodule."third_party/git-hooks".update=none submodule update --init --recursive | |
| - name: swiftshader | |
| if: steps.cache-swiftshader.outputs.cache-hit != 'true' | |
| run: | | |
| cd swiftshader | |
| mkdir -p build; cd build | |
| cmake -DCMAKE_INSTALL_PREFIX=install -DSWIFTSHADER_BUILD_EGL=FALSE -DSWIFTSHADER_BUILD_GLESv2=FALSE -DSWIFTSHADER_BUILD_GLES_CM=FALSE -DSWIFTSHADER_BUILD_VULKAN=TRUE -DSWIFTSHADER_BUILD_PVR=FALSE -DSWIFTSHADER_BUILD_TESTS=FALSE -DSWIFTSHADER_ENABLE_ASTC=FALSE -DSWIFTSHADER_WARNINGS_AS_ERRORS=FALSE -DREACTOR_BACKEND=Subzero -DREACTOR_DEFAULT_OPT_LEVEL=Default -DCMAKE_BUILD_TYPE=Release .. | |
| cmake --build . -j 3 | |
| mkdir $GITHUB_WORKSPACE/swiftshader-install | |
| cp Darwin/* $GITHUB_WORKSPACE/swiftshader-install | |
| - name: build | |
| run: | | |
| mkdir build && cd build | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/ios.toolchain.cmake -DPLATFORM=MAC -DARCHS="x86_64" \ | |
| -DDEPLOYMENT_TARGET=$MAC_DEPLOYMENT_TARGET -DENABLE_BITCODE=$ENABLE_BITCODE -DENABLE_ARC=$ENABLE_ARC -DENABLE_VISIBILITY=$ENABLE_VISIBILITY \ | |
| -DOpenMP_C_FLAGS="-Xclang -fopenmp" -DOpenMP_CXX_FLAGS="-Xclang -fopenmp" \ | |
| -DOpenMP_C_LIB_NAMES="libomp" -DOpenMP_CXX_LIB_NAMES="libomp" \ | |
| -DOpenMP_libomp_LIBRARY="$DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/usr/lib/libomp.a" \ | |
| -DVulkan_LIBRARY=$GITHUB_WORKSPACE/swiftshader-install/libvulkan.dylib \ | |
| -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=install \ | |
| -DNCNN_VULKAN=ON -DNCNN_BUILD_TESTS=ON .. | |
| cmake --build . -j 3 | |
| - name: test | |
| run: | | |
| printf "[Processor]\nThreadCount=1\n" > build/tests/SwiftShader.ini | |
| cd build && ctest --output-on-failure -j 3 | |
| - name: build-shared | |
| run: | | |
| mkdir build-shared && cd build-shared | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/ios.toolchain.cmake -DPLATFORM=MAC -DARCHS="x86_64" \ | |
| -DDEPLOYMENT_TARGET=$MAC_DEPLOYMENT_TARGET -DENABLE_BITCODE=$ENABLE_BITCODE -DENABLE_ARC=$ENABLE_ARC -DENABLE_VISIBILITY=$ENABLE_VISIBILITY \ | |
| -DOpenMP_C_FLAGS="-Xclang -fopenmp" -DOpenMP_CXX_FLAGS="-Xclang -fopenmp" \ | |
| -DOpenMP_C_LIB_NAMES="libomp" -DOpenMP_CXX_LIB_NAMES="libomp" \ | |
| -DOpenMP_libomp_LIBRARY="$DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/usr/lib/libomp.a" \ | |
| -DVulkan_LIBRARY=$GITHUB_WORKSPACE/swiftshader-install/libvulkan.dylib \ | |
| -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=install \ | |
| -DNCNN_VULKAN=ON -DNCNN_SHARED_LIB=ON .. | |
| cmake --build . -j 3 |