arm neon optimzation for rmsnorm (#5668) #4931
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: linux-aarch64-cpu-gcc | |
| on: | |
| push: | |
| branches: [master] | |
| paths: | |
| - '.github/workflows/linux-aarch64-cpu-gcc.yml' | |
| - 'toolchains/aarch64-linux-gnu.toolchain.cmake' | |
| - 'CMakeLists.txt' | |
| - 'cmake/**' | |
| - 'src/*' | |
| - 'src/layer/*' | |
| - 'src/layer/arm/**' | |
| - 'tests/**' | |
| pull_request: | |
| branches: [master] | |
| paths: | |
| - '.github/workflows/linux-aarch64-cpu-gcc.yml' | |
| - 'toolchains/aarch64-linux-gnu.toolchain.cmake' | |
| - 'CMakeLists.txt' | |
| - 'cmake/**' | |
| - 'src/*' | |
| - 'src/layer/*' | |
| - 'src/layer/arm/**' | |
| - 'tests/**' | |
| concurrency: | |
| group: linux-aarch64-cpu-gcc-${{ github.ref }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| jobs: | |
| linux-gcc: | |
| runs-on: ubuntu-20.04 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: cache-qemu | |
| id: cache-qemu | |
| uses: actions/cache@v4 | |
| with: | |
| path: qemu-install | |
| key: qemu-aarch64-install-20220502-ubuntu-2004-2 | |
| - name: install-qemu-build-deps | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install autoconf automake autotools-dev ninja-build | |
| - name: checkout-qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: qemu/qemu | |
| path: qemu | |
| ref: f5643914a9e8f79c606a76e6a9d7ea82a3fc3e65 | |
| - name: qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| cd qemu | |
| ./configure --prefix=$GITHUB_WORKSPACE/qemu-install --target-list=aarch64-linux-user --disable-system | |
| make -j$(nproc) | |
| make install | |
| - name: aarch64-gnu-toolchain | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install g++-aarch64-linux-gnu | |
| - name: build | |
| run: | | |
| mkdir build && cd build | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake -DNCNN_ARM82=OFF -DNCNN_ARM82DOT=OFF -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF -DNCNN_BUILD_TESTS=ON .. | |
| cmake --build . -j $(nproc) | |
| - name: test | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) | |
| - name: build-noint8 | |
| run: | | |
| mkdir build-noint8 && cd build-noint8 | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake -DNCNN_ARM82=OFF -DNCNN_ARM82DOT=OFF -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF -DNCNN_BUILD_TESTS=ON .. | |
| cmake --build . -j $(nproc) | |
| - name: test-noint8 | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build-noint8 | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) | |
| - name: build-simplestl-simplemath | |
| run: | | |
| mkdir build-simplestl-simplemath && cd build-simplestl-simplemath | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu-c.toolchain.cmake -DNCNN_STDIO=ON -DNCNN_STRING=ON -DNCNN_SIMPLESTL=ON -DNCNN_SIMPLEMATH=ON -DNCNN_BUILD_TESTS=ON -DNCNN_BUILD_BENCHMARK=OFF -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF .. | |
| cmake --build . -j $(nproc) | |
| - name: test-simplestl-simplemath | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build-simplestl-simplemath | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) | |
| linux-gcc-arm82: | |
| runs-on: ubuntu-20.04 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: cache-qemu | |
| id: cache-qemu | |
| uses: actions/cache@v4 | |
| with: | |
| path: qemu-install | |
| key: qemu-aarch64-install-20220502-ubuntu-2004-2 | |
| - name: install-qemu-build-deps | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install autoconf automake autotools-dev ninja-build | |
| - name: checkout-qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: qemu/qemu | |
| path: qemu | |
| ref: f5643914a9e8f79c606a76e6a9d7ea82a3fc3e65 | |
| - name: qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| cd qemu | |
| ./configure --prefix=$GITHUB_WORKSPACE/qemu-install --target-list=aarch64-linux-user --disable-system | |
| make -j$(nproc) | |
| make install | |
| - name: aarch64-gnu-toolchain | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install g++-aarch64-linux-gnu | |
| - name: build | |
| run: | | |
| mkdir build && cd build | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake -DNCNN_ARM82=ON -DNCNN_ARM82DOT=ON -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF -DNCNN_BUILD_TESTS=ON .. | |
| cmake --build . -j $(nproc) | |
| - name: test | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) | |
| - name: build-noint8 | |
| run: | | |
| mkdir build-noint8 && cd build-noint8 | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake -DNCNN_ARM82=ON -DNCNN_ARM82DOT=ON -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF -DNCNN_BUILD_TESTS=ON -DNCNN_INT8=OFF .. | |
| cmake --build . -j $(nproc) | |
| - name: test-noint8 | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build-noint8 | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) | |
| linux-gcc-arm86: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: cache-qemu | |
| id: cache-qemu | |
| uses: actions/cache@v4 | |
| with: | |
| path: qemu-install | |
| key: qemu-aarch64-install-20230717 | |
| - name: install-qemu-build-deps | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install autoconf automake autotools-dev ninja-build | |
| - name: checkout-qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: qemu/qemu | |
| path: qemu | |
| ref: ed8ad9728a9c0eec34db9dff61dfa2f1dd625637 | |
| - name: qemu | |
| if: steps.cache-qemu.outputs.cache-hit != 'true' | |
| run: | | |
| cd qemu | |
| ./configure --prefix=$GITHUB_WORKSPACE/qemu-install --target-list=aarch64-linux-user --disable-system | |
| make -j$(nproc) | |
| make install | |
| - name: aarch64-gnu-toolchain | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install g++-aarch64-linux-gnu | |
| - name: build | |
| run: | | |
| mkdir build && cd build | |
| cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake -DNCNN_ARM82=ON -DNCNN_ARM82DOT=ON -DNCNN_BUILD_TOOLS=OFF -DNCNN_BUILD_EXAMPLES=OFF -DNCNN_BUILD_TESTS=ON .. | |
| cmake --build . -j $(nproc) | |
| - name: test | |
| run: | | |
| export PATH=$GITHUB_WORKSPACE/qemu-install/bin:$PATH | |
| cd build | |
| TESTS_EXECUTABLE_LOADER=qemu-aarch64 TESTS_EXECUTABLE_LOADER_ARGUMENTS="-L;/usr/aarch64-linux-gnu" ctest --output-on-failure -j $(nproc) |