From b918109005702681af21887c1fa6c9610b650d78 Mon Sep 17 00:00:00 2001 From: slaren <2141330+slaren@users.noreply.github.com> Date: Wed, 10 May 2023 23:27:59 +0200 Subject: [PATCH 1/2] testing clang-tidy test test test test test test Revert "test" This reverts commit 6aa68df4c38798d99f891891e0cbd702c532edb1. test test test --- .clang-tidy | 19 + .github/workflows/build.yml | 589 ----------------------------- .github/workflows/docker.yml | 65 ---- .github/workflows/editorconfig.yml | 17 - .github/workflows/tidy-review.yml | 23 ++ 5 files changed, 42 insertions(+), 671 deletions(-) create mode 100644 .clang-tidy delete mode 100644 .github/workflows/build.yml delete mode 100644 .github/workflows/docker.yml delete mode 100644 .github/workflows/editorconfig.yml create mode 100644 .github/workflows/tidy-review.yml diff --git a/.clang-tidy b/.clang-tidy new file mode 100644 index 00000000000..d123553ef32 --- /dev/null +++ b/.clang-tidy @@ -0,0 +1,19 @@ +--- +Checks: > + bugprone-*, + -bugprone-easily-swappable-parameters, + -bugprone-implicit-widening-of-multiplication-result, + -bugprone-narrowing-conversions, + readability-*, + -readability-avoid-unconditional-preprocessor-if, + -readability-function-cognitive-complexity, + -readability-identifier-length, + -readability-implicit-bool-conversion, + -readability-magic-numbers, + -readability-uppercase-literal-suffix, + clang-analyzer-*, + -clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling, + concurrency-*, + performance-*, + portability-*, +FormatStyle: none diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml deleted file mode 100644 index a5938bf9368..00000000000 --- a/.github/workflows/build.yml +++ /dev/null @@ -1,589 +0,0 @@ -name: CI - -on: - workflow_dispatch: # allows manual triggering - inputs: - create_release: - description: 'Create new release' - required: true - type: boolean - push: - branches: - - master - paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp'] - pull_request: - types: [opened, synchronize, reopened] - paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp'] - -env: - BRANCH_NAME: ${{ github.head_ref || github.ref_name }} - -jobs: - ubuntu-focal-make: - runs-on: ubuntu-20.04 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential gcc-8 - - - name: Build - id: make_build - run: | - CC=gcc-8 make - - ubuntu-latest-cmake: - runs-on: ubuntu-latest - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential - - - name: Build - id: cmake_build - run: | - mkdir build - cd build - cmake .. - cmake --build . --config Release - - - name: Test - id: cmake_test - run: | - cd build - ctest --verbose - - ubuntu-latest-cmake-sanitizer: - runs-on: ubuntu-latest - - continue-on-error: true - - strategy: - matrix: - sanitizer: [ADDRESS, THREAD, UNDEFINED] - build_type: [Debug, Release] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential - - - name: Build - id: cmake_build - run: | - mkdir build - cd build - cmake .. -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} - cmake --build . --config ${{ matrix.build_type }} - - - name: Test - id: cmake_test - run: | - cd build - ctest --verbose - - macOS-latest-make: - runs-on: macos-latest - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Dependencies - id: depends - run: | - brew update - - - name: Build - id: make_build - run: | - make - - macOS-latest-cmake: - runs-on: macos-latest - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Dependencies - id: depends - run: | - brew update - - - name: Build - id: cmake_build - run: | - mkdir build - cd build - cmake -DLLAMA_AVX2=OFF .. - cmake --build . --config Release - - - name: Test - id: cmake_test - run: | - cd build - ctest --verbose - - windows-latest-cmake: - runs-on: windows-latest - env: - OPENBLAS_VERSION: 0.3.23 - OPENCL_VERSION: 2023.04.17 - CLBLAST_VERSION: 1.5.3 - - strategy: - matrix: - include: - - build: 'avx2' - defines: '' - - build: 'avx' - defines: '-DLLAMA_AVX2=OFF' - - build: 'avx512' - defines: '-DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON' - - build: 'clblast' - defines: '-DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"' - - build: 'openblas' - defines: '-DLLAMA_OPENBLAS=ON -DBLAS_LIBRARIES="/LIBPATH:$env:RUNNER_TEMP/openblas/lib" -DOPENBLAS_INC="$env:RUNNER_TEMP/openblas/include"' - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - name: Download OpenCL SDK - id: get_opencl - if: ${{ matrix.build == 'clblast' }} - run: | - curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip" - mkdir $env:RUNNER_TEMP/opencl - tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl - - - name: Download CLBlast - id: get_clblast - if: ${{ matrix.build == 'clblast' }} - run: | - curl.exe -o $env:RUNNER_TEMP/clblast.zip -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-Windows-x64.zip" - curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE" - mkdir $env:RUNNER_TEMP/clblast - tar.exe -xvf $env:RUNNER_TEMP/clblast.zip -C $env:RUNNER_TEMP/clblast - foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) { - $txt = Get-Content -Path $f -Raw - $txt.Replace('C:/dependencies/opencl/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8 - } - - - name: Download OpenBLAS - id: get_openblas - if: ${{ matrix.build == 'openblas' }} - run: | - curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip" - curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE" - mkdir $env:RUNNER_TEMP/openblas - tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas - $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) - $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) - $lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe') - & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll - - - name: Build - id: cmake_build - run: | - mkdir build - cd build - cmake .. ${{ matrix.defines }} - cmake --build . --config Release - cp ../LICENSE ./bin/Release/llama.cpp.txt - - - name: Add clblast.dll - id: add_clblast_dll - if: ${{ matrix.build == 'clblast' }} - run: | - cp $env:RUNNER_TEMP/clblast/lib/clblast.dll ./build/bin/Release - cp $env:RUNNER_TEMP/CLBlast.LICENSE.txt ./build/bin/Release/CLBlast-${env:CLBLAST_VERSION}.txt - - - name: Add libopenblas.dll - id: add_libopenblas_dll - if: ${{ matrix.build == 'openblas' }} - run: | - cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll - cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt - - - name: Check AVX512F support - id: check_avx512f - if: ${{ matrix.build == 'avx512' }} - continue-on-error: true - run: | - cd build - $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath) - $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim())) - $cl = $(join-path $msvc 'bin\Hostx64\x64\cl.exe') - echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c - & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main - .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO" - - - name: Test - id: cmake_test - if: ${{ matrix.build != 'clblast' && (matrix.build != 'avx512' || env.HAS_AVX512F == '1') }} # Test AVX-512 only when possible - run: | - cd build - ctest -C Release --verbose - - - name: Get commit hash - id: commit - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - uses: pr-mpt/actions-commit-hash@v2 - - - name: Pack artifacts - id: pack_artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - run: | - 7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\* - - - name: Upload artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - uses: actions/upload-artifact@v3 - with: - path: | - llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip - - windows-latest-cmake-cublas: - runs-on: windows-latest - - strategy: - matrix: - cuda: ['12.1.0', '11.7.1'] - build: ['cublas'] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v1 - - - uses: Jimver/cuda-toolkit@v0.2.10 - id: cuda-toolkit - with: - cuda: ${{ matrix.cuda }} - # TODO(green-sky): _dev seems to fail, and non dev are not enought - #sub-packages: '["nvcc", "cudart", "cublas", "cudart_dev", "cublas_dev"]' - - - name: Build - id: cmake_build - run: | - mkdir build - cd build - cmake .. -DLLAMA_CUBLAS=ON - cmake --build . --config Release - - - name: Get commit hash - id: commit - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - uses: pr-mpt/actions-commit-hash@v2 - - - name: Pack artifacts - id: pack_artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - run: | - 7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\* - - - name: Upload artifacts - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - uses: actions/upload-artifact@v3 - with: - path: | - llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip - - - name: Copy and pack Cuda runtime - if: ${{ matrix.cuda == '12.1.0' }} - # TODO(green-sky): paths are cuda 12 specific - run: | - echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}" - mkdir '.\build\bin\cudart\' - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_12.dll" '.\build\bin\cudart\' - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_12.dll" '.\build\bin\cudart\' - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_12.dll" '.\build\bin\cudart\' - 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\* - - - name: Copy and pack Cuda runtime - if: ${{ matrix.cuda == '11.7.1' }} - # TODO(green-sky): paths are cuda 11 specific - run: | - echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}" - mkdir '.\build\bin\cudart\' - ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_110.dll" '.\build\bin\cudart\' - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_11.dll" '.\build\bin\cudart\' - cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_11.dll" '.\build\bin\cudart\' - 7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\* - - - name: Upload Cuda runtime - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - uses: actions/upload-artifact@v3 - with: - path: | - cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip - - release: - if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} - - runs-on: ubuntu-latest - - needs: - - ubuntu-focal-make - - ubuntu-latest-cmake - - macOS-latest-make - - macOS-latest-cmake - - windows-latest-cmake - - windows-latest-cmake-cublas - - steps: - - name: Download artifacts - id: download-artifact - uses: actions/download-artifact@v3 - - - name: Get commit hash - id: commit - uses: pr-mpt/actions-commit-hash@v2 - - - name: Create release - id: create_release - uses: anzz1/action-create-release@v1 - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - with: - tag_name: ${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }} - - - name: Upload release - id: upload_release - uses: actions/github-script@v3 - with: - github-token: ${{secrets.GITHUB_TOKEN}} - script: | - const path = require('path'); - const fs = require('fs'); - const release_id = '${{ steps.create_release.outputs.id }}'; - for (let file of await fs.readdirSync('./artifact')) { - if (path.extname(file) === '.zip') { - console.log('uploadReleaseAsset', file); - await github.repos.uploadReleaseAsset({ - owner: context.repo.owner, - repo: context.repo.repo, - release_id: release_id, - name: file, - data: await fs.readFileSync(`./artifact/${file}`) - }); - } - } - -# ubuntu-latest-gcc: -# runs-on: ubuntu-latest -# -# strategy: -# matrix: -# build: [Debug, Release] -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Dependencies -# run: | -# sudo apt-get update -# sudo apt-get install build-essential -# sudo apt-get install cmake -# -# - name: Configure -# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -# -# - name: Build -# run: | -# make -# -# ubuntu-latest-clang: -# runs-on: ubuntu-latest -# -# strategy: -# matrix: -# build: [Debug, Release] -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Dependencies -# run: | -# sudo apt-get update -# sudo apt-get install build-essential -# sudo apt-get install cmake -# -# - name: Configure -# run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang -# -# - name: Build -# run: | -# make -# -# ubuntu-latest-gcc-sanitized: -# runs-on: ubuntu-latest -# -# strategy: -# matrix: -# sanitizer: [ADDRESS, THREAD, UNDEFINED] -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Dependencies -# run: | -# sudo apt-get update -# sudo apt-get install build-essential -# sudo apt-get install cmake -# -# - name: Configure -# run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -# -# - name: Build -# run: | -# make -# -# windows: -# runs-on: windows-latest -# -# strategy: -# matrix: -# build: [Release] -# arch: [Win32, x64] -# include: -# - arch: Win32 -# s2arc: x86 -# - arch: x64 -# s2arc: x64 -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Add msbuild to PATH -# uses: microsoft/setup-msbuild@v1 -# -# - name: Configure -# run: > -# cmake -S . -B ./build -A ${{ matrix.arch }} -# -DCMAKE_BUILD_TYPE=${{ matrix.build }} -# -# - name: Build -# run: | -# cd ./build -# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} -# -# - name: Upload binaries -# uses: actions/upload-artifact@v1 -# with: -# name: llama-bin-${{ matrix.arch }} -# path: build/bin/${{ matrix.build }} -# -# windows-blas: -# runs-on: windows-latest -# -# strategy: -# matrix: -# build: [Release] -# arch: [Win32, x64] -# blas: [ON] -# include: -# - arch: Win32 -# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip -# s2arc: x86 -# - arch: x64 -# obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip -# s2arc: x64 -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Add msbuild to PATH -# uses: microsoft/setup-msbuild@v1 -# -# - name: Fetch OpenBLAS -# if: matrix.blas == 'ON' -# run: | -# C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }} -# 7z x blas.zip -oblas -y -# copy blas/include/cblas.h . -# copy blas/include/openblas_config.h . -# echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV -# -# - name: Configure -# run: > -# cmake -S . -B ./build -A ${{ matrix.arch }} -# -DCMAKE_BUILD_TYPE=${{ matrix.build }} -# -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }} -# -DCMAKE_LIBRARY_PATH="$env:blasdir/lib" -# -# - name: Build -# run: | -# cd ./build -# msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} -# -# - name: Copy libopenblas.dll -# if: matrix.blas == 'ON' -# run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }} -# -# - name: Upload binaries -# if: matrix.blas == 'ON' -# uses: actions/upload-artifact@v1 -# with: -# name: llama-blas-bin-${{ matrix.arch }} -# path: build/bin/${{ matrix.build }} -# -# emscripten: -# runs-on: ubuntu-latest -# -# strategy: -# matrix: -# build: [Release] -# -# steps: -# - name: Clone -# uses: actions/checkout@v1 -# -# - name: Dependencies -# run: | -# wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz -# tar -xvf master.tar.gz -# emsdk-master/emsdk update -# emsdk-master/emsdk install latest -# emsdk-master/emsdk activate latest -# -# - name: Configure -# run: echo "tmp" -# -# - name: Build -# run: | -# pushd emsdk-master -# source ./emsdk_env.sh -# popd -# emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -# make diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml deleted file mode 100644 index 379fbd7ad35..00000000000 --- a/.github/workflows/docker.yml +++ /dev/null @@ -1,65 +0,0 @@ -# This workflow uses actions that are not certified by GitHub. -# They are provided by a third-party and are governed by -# separate terms of service, privacy policy, and support -# documentation. - -# GitHub recommends pinning actions to a commit SHA. -# To get a newer version, you will need to update the SHA. -# You can also reference a tag or branch, but the action may change without warning. - -name: Publish Docker image - -on: - pull_request: - push: - branches: - - master - -jobs: - push_to_registry: - name: Push Docker image to Docker Hub - if: github.event.pull_request.draft == false - - runs-on: ubuntu-latest - env: - COMMIT_SHA: ${{ github.sha }} - strategy: - matrix: - config: - - { tag: "light", dockerfile: ".devops/main.Dockerfile" } - - { tag: "full", dockerfile: ".devops/full.Dockerfile" } - steps: - - name: Check out the repo - uses: actions/checkout@v3 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v2 - - - name: Set up Docker Buildx - uses: docker/setup-buildx-action@v2 - - - name: Log in to Docker Hub - uses: docker/login-action@v2 - with: - registry: ghcr.io - username: ${{ github.repository_owner }} - password: ${{ secrets.GITHUB_TOKEN }} - - - name: Build and push Docker image (versioned) - if: github.event_name == 'push' - uses: docker/build-push-action@v4 - with: - context: . - push: true - platforms: linux/amd64,linux/arm64 - tags: "ghcr.io/ggerganov/llama.cpp:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}" - file: ${{ matrix.config.dockerfile }} - - - name: Build and push Docker image (tagged) - uses: docker/build-push-action@v4 - with: - context: . - push: ${{ github.event_name == 'push' }} - platforms: linux/amd64,linux/arm64 - tags: "ghcr.io/ggerganov/llama.cpp:${{ matrix.config.tag }}" - file: ${{ matrix.config.dockerfile }} diff --git a/.github/workflows/editorconfig.yml b/.github/workflows/editorconfig.yml deleted file mode 100644 index b4e535acf1f..00000000000 --- a/.github/workflows/editorconfig.yml +++ /dev/null @@ -1,17 +0,0 @@ -name: EditorConfig Checker - -on: - push: - branches: - - master - pull_request: - branches: - - master - -jobs: - editorconfig: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v3 - - uses: editorconfig-checker/action-editorconfig-checker@main - - run: editorconfig-checker diff --git a/.github/workflows/tidy-review.yml b/.github/workflows/tidy-review.yml new file mode 100644 index 00000000000..1f7c7939992 --- /dev/null +++ b/.github/workflows/tidy-review.yml @@ -0,0 +1,23 @@ +name: clang-tidy review + +on: + push: + branches: + - master + pull_request: + branches: + - master + +jobs: + clang-tidy-review: + runs-on: ubuntu-latest + + steps: + - uses: actions/checkout@v3 + + - uses: ZedThree/clang-tidy-review@v0.13.0 + id: review + with: + lgtm_comment_body: '' + build_dir: build + cmake_command: cmake . -B build -DCMAKE_EXPORT_COMPILE_COMMANDS=on From ac2b781c119dabc8488e50497609a06009837fe8 Mon Sep 17 00:00:00 2001 From: slaren <2141330+slaren@users.noreply.github.com> Date: Thu, 11 May 2023 20:39:11 +0200 Subject: [PATCH 2/2] test --- examples/benchmark/benchmark-matmult.cpp | 524 +++++++++++------------ 1 file changed, 262 insertions(+), 262 deletions(-) diff --git a/examples/benchmark/benchmark-matmult.cpp b/examples/benchmark/benchmark-matmult.cpp index 6117ae3abf8..32d8ae73c33 100644 --- a/examples/benchmark/benchmark-matmult.cpp +++ b/examples/benchmark/benchmark-matmult.cpp @@ -1,262 +1,262 @@ -#include -#include "ggml.h" -#include "build-info.h" -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -float tensor_sum_elements(struct ggml_tensor * tensor) { - float sum = 0; - if (tensor->type==GGML_TYPE_F32) { - for (int j = 0; j < tensor->ne[1]; j++) { - for (int k = 0; k < tensor->ne[0]; k++) { - sum += ((float *) tensor->data)[j*tensor->ne[0]+k]; - } - } - } - return sum; -} - - -/* - These are mapping to unknown - GGML_TYPE_I8, - GGML_TYPE_I16, - GGML_TYPE_I32, - GGML_TYPE_COUNT, -*/ - -#define TENSOR_TYPE_AS_STR(TYPE) TYPE == GGML_TYPE_F32 ? "FP32" : TYPE == GGML_TYPE_F16 ? "FP16" : TYPE == GGML_TYPE_Q4_0 ? "Q4_0" : TYPE == GGML_TYPE_Q4_1 ? "Q4_1" : "UNKNOWN" - -#define TENSOR_DUMP(TENSOR) printf("%15s: type = %i (%5s) ne = %5d x %5d x %5d, nb = (%5li, %5li, %5li) - ", #TENSOR, \ - TENSOR->type,TENSOR_TYPE_AS_STR(TENSOR->type),\ - (int) TENSOR->ne[0], (int) TENSOR->ne[1], (int) TENSOR->ne[2], TENSOR->nb[0], TENSOR->nb[1], TENSOR->nb[2]); \ - { float sum = tensor_sum_elements(TENSOR); printf("Sum of tensor %s is %6.2f\n",#TENSOR, sum); } - -struct benchmark_params_struct { - int32_t n_threads = 1; - int32_t n_iterations = 10; -}; - -void print_usage(int /*argc*/, char ** argv, struct benchmark_params_struct params) { - fprintf(stderr, "usage: %s [options]\n", argv[0]); - fprintf(stderr, "\n"); - fprintf(stderr, "options:\n"); - fprintf(stderr, " -h, --help show this help message and exit\n"); - fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); - fprintf(stderr, " -i N, --iter N number of iterations to use during computation (default: %d)\n", params.n_iterations); - fprintf(stderr, "\n"); -} - -int main(int argc, char ** argv) { - - - struct benchmark_params_struct benchmark_params; - - bool invalid_param = false; - std::string arg; - for (int i = 1; i < argc; i++) { - arg = argv[i]; - - if (arg == "-t" || arg == "--threads") { - if (++i >= argc) { - invalid_param = true; - break; - } - benchmark_params.n_threads = std::stoi(argv[i]); - } else if (arg == "-i" || arg == "--iter") { - if (++i >= argc) { - invalid_param = true; - break; - } - benchmark_params.n_iterations = std::stoi(argv[i]); - } else if (arg == "-h" || arg == "--help") { - print_usage(argc, argv, benchmark_params); - exit(0); - } - if (invalid_param) { - fprintf(stderr, "error: invalid parameter for argument: %s\n", arg.c_str()); - print_usage(argc, argv, benchmark_params); - exit(1); - } - } - - fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT); - printf("Starting Test\n"); - - // create the ggml context - struct ggml_context * ctx; - //const int sizex = 4096; - //const int sizey = 11008; - -#undef VERBOSE_DEBUGGING -#ifndef VERBOSE_DEBUGGING - const int sizey = 4096; - const int sizex = 11008; - const int sizez = 128; -#else - /* Working - let's increase size */ - const int sizey = 1; - const int sizex = (8*32); - const int sizez = 1; - - /*const int sizey = 1; - const int sizex = 3*(8*32); - const int sizez = 1;*/ -#endif - - //printf("Memsize required = %i\n", sizex*sizex); - - size_t ctx_size = 0; - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); - ctx_size += sizex*sizez*ggml_type_sizef(GGML_TYPE_F32); - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_Q4_0); - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_Q4_0); - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); // BLAS - ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); // BLAS - ctx_size += 1024*1024*16; - - printf("Allocating Memory of size %li bytes, %li MB\n",ctx_size, (ctx_size/1024/1024)); - - struct ggml_init_params params = { - /*.mem_size =*/ ctx_size, - /*.mem_buffer =*/ NULL, - /* no_alloc =*/ 0 - }; - - ctx = ggml_init(params); - if (!ctx) { - fprintf(stderr, "%s: ggml_init() failed\n", __func__); - return 1; - } - - - printf("Creating new tensors\n"); - // printf("Creating new tensor m1\n"); - struct ggml_tensor * m11 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizey); - ggml_set_f32(m11, 1.0f); - - // printf("Creating new tensor m1\n"); - struct ggml_tensor * m12 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizey); - ggml_set_f32(m12, 1.5f); - - // printf("Creating new tensor m2\n"); - struct ggml_tensor * m2 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizez); - ggml_set_f32(m2, 2.0f); - - printf("\n------ Test 1 - Matrix Mult via F32 code ------------------------------------------------------------------------------\n"); - // printf("Creating new tensor m11xm2\n"); - struct ggml_tensor * m11xm2 = ggml_mul_mat(ctx, m11, m2); - - // printf("Creating compute graph\n"); - struct ggml_cgraph gf = ggml_build_forward(m11xm2); - - gf.n_threads=benchmark_params.n_threads; - printf("cgraph->n_threads=%i\n",gf.n_threads); - - TENSOR_DUMP(m11); - TENSOR_DUMP(m2); - - ggml_graph_compute(ctx, &gf); - - TENSOR_DUMP(gf.nodes[0]); - - printf("\n------ Test 2 - Matrix Mult via Q4_0 code ------------------------------------------------------------------------------\n"); - - int32_t nelements = sizex*sizey; - int32_t ne[2] = { sizex, sizey }; - - std::vector hist_cur(1 << 4, 0); - - // Set up a the benchmark matrices - // printf("Creating new tensor q11 & Running quantize\n"); - struct ggml_tensor * q11 = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, sizex, sizey); - ggml_quantize_q4_0((const float *) m11->data, q11->data, nelements, ne[0], hist_cur.data()); - - // Set up a the compute graph - // printf("Creating new tensor q31\n"); - struct ggml_tensor * q31 = ggml_mul_mat(ctx, q11, m2); - - // printf("Creating compute graph\n"); - struct ggml_cgraph gf31 = ggml_build_forward(q31); - gf31.n_threads=benchmark_params.n_threads; - - // Set up a second graph computation to make sure we override the CPU cache lines - // printf("Creating new tensor q12 & Running quantize\n"); - struct ggml_tensor * q12 = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, sizex, sizey); - ggml_quantize_q4_0((const float *) m12->data, q12->data, nelements, ne[0], hist_cur.data()); - - // printf("Creating new tensor q32\n"); - struct ggml_tensor * q32 = ggml_mul_mat(ctx, q12, m2); - - //printf("Creating compute graph\n"); - struct ggml_cgraph gf32 = ggml_build_forward(q32); - gf32.n_threads=benchmark_params.n_threads; - printf("cgraph->n_threads=%i\n",gf31.n_threads); - - const int dimx = sizex; - const int dimy = sizey; - const int dimz = sizez; - long long int flops_per_dot_product = dimy + dimy; - long long int flops_per_matrix = flops_per_dot_product * dimx * dimz; ; - printf("Matrix Multiplication of (%i,%i,%i) x (%i,%i,%i) - about %6.2f gFLOPS\n\n", sizex, sizey, 1, sizex, sizez, 1, 1.0f*flops_per_matrix / 1000 / 1000 / 1000); - - - // Let's use the F32 result from above as a reference for the q4_0 multiplication - float sum_of_F32_reference = tensor_sum_elements(gf.nodes[0]); - - - printf("Iteration;NThreads; SizeX; SizeY; SizeZ; Required_FLOPS; Elapsed_u_Seconds; FLOPS_per_u_Second\n"); - printf("==============================================================================================\n"); - - for (int i=0;i allowed_delta) { - printf("\nABORT - ERROR in Matrix Multiplication result - expected %6.2f, got %6.2f (delta %6.2f > allowed_delta %6.2f)\n", - sum_of_F32_reference, - sum_of_Q4_result, - delta, - allowed_delta - ); - exit(0); - } - - // Running a different graph computation to make sure we override the CPU cache lines - ggml_graph_compute(ctx, &gf32); - - } - -} +#include +#include "ggml.h" +#include "build-info.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +float tensor_sum_elements(struct ggml_tensor * tensor) { + float sum = 0; + if (tensor->type==GGML_TYPE_F32) { + for (int j = 0; j < tensor->ne[1]; j++) { + for (int k = 0; k < tensor->ne[0]; k++) { + sum += ((float *) tensor->data)[j*tensor->ne[0]+k]; + } + } + } + return sum; +} + + +/* + These are mapping to unknown + GGML_TYPE_I8, + GGML_TYPE_I16, + GGML_TYPE_I32, + GGML_TYPE_COUNT, +*/ + +#define TENSOR_TYPE_AS_STR(TYPE) TYPE == GGML_TYPE_F32 ? "FP32" : TYPE == GGML_TYPE_F16 ? "FP16" : TYPE == GGML_TYPE_Q4_0 ? "Q4_0" : TYPE == GGML_TYPE_Q4_1 ? "Q4_1" : "UNKNOWN" + +#define TENSOR_DUMP(TENSOR) printf("%15s: type = %i (%5s) ne = %5d x %5d x %5d, nb = (%5li, %5li, %5li) - ", #TENSOR, \ + TENSOR->type,TENSOR_TYPE_AS_STR(TENSOR->type),\ + (int) TENSOR->ne[0], (int) TENSOR->ne[1], (int) TENSOR->ne[2], TENSOR->nb[0], TENSOR->nb[1], TENSOR->nb[2]); \ + { float sum = tensor_sum_elements(TENSOR); printf("Sum of tensor %s is %6.2f\n",#TENSOR, sum); } + +struct benchmark_params_struct { + int32_t n_threads = 1; + int32_t n_iterations = 10; +}; + +void print_usage(int /*argc*/, char ** argv, struct benchmark_params_struct params) { + fprintf(stderr, "usage: %s [options]\n", argv[0]); + fprintf(stderr, "\n"); + fprintf(stderr, "options:\n"); + fprintf(stderr, " -h, --help show this help message and exit\n"); + fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); + fprintf(stderr, " -i N, --iter N number of iterations to use during computation (default: %d)\n", params.n_iterations); + fprintf(stderr, "\n"); +} + +int main(int argc, char ** argv) { + + + struct benchmark_params_struct benchmark_params; + + bool invalid_param = false; + std::string arg; + for (int i = 1; i < argc; i++) { + arg = argv[i]; + + if (arg == "-t" || arg == "--threads") { + if (++i >= argc) { + invalid_param = true; + break; + } + benchmark_params.n_threads = std::stoi(argv[i]); + } else if (arg == "-i" || arg == "--iter") { + if (++i >= argc) { + invalid_param = true; + break; + } + benchmark_params.n_iterations = std::stoi(argv[i]); + } else if (arg == "-h" || arg == "--help") { + print_usage(argc, argv, benchmark_params); + exit(0); + } + if (invalid_param) { + fprintf(stderr, "error: invalid parameter for argument: %s\n", arg.c_str()); + print_usage(argc, argv, benchmark_params); + exit(1); + } + } + + fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT); + printf("Starting Test\n"); + + // create the ggml context + struct ggml_context * ctx; + //const int sizex = 4096; + //const int sizey = 11008; + +#undef VERBOSE_DEBUGGING +#ifndef VERBOSE_DEBUGGING + const int sizey = 4096; + const int sizex = 11008; + const int sizez = 128; +#else + /* Working - let's increase size */ + const int sizey = 1; + const int sizex = (8*32); + const int sizez = 1; + + /*const int sizey = 1; + const int sizex = 3*(8*32); + const int sizez = 1;*/ +#endif + + //printf("Memsize required = %i\n", sizex*sizex); + + size_t ctx_size = 0; + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); + ctx_size += sizex*sizez*ggml_type_sizef(GGML_TYPE_F32); + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_Q4_0); + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_Q4_0); + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); // BLAS + ctx_size += sizex*sizey*ggml_type_sizef(GGML_TYPE_F32); // BLAS + ctx_size += 1024*1024*16; + + printf("Allocating Memory of size %li bytes, %li MB\n",ctx_size, (ctx_size/1024/1024)); + + struct ggml_init_params params = { + /*.mem_size =*/ ctx_size, + /*.mem_buffer =*/ NULL, + /* no_alloc =*/ 0 + }; + + ctx = ggml_init(params); + if (!ctx) { + fprintf(stderr, "%s: ggml_init() failed\n", __func__); + return 1; + } + + + printf("Creating new tensors\n"); + // printf("Creating new tensor m1\n"); + struct ggml_tensor * m11 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizey); + ggml_set_f32(m11, 1.0f); + + // printf("Creating new tensor m1\n"); + struct ggml_tensor * m12 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizey); + ggml_set_f32(m12, 1.5f); + + // printf("Creating new tensor m2\n"); + struct ggml_tensor * m2 = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, sizex, sizez); + ggml_set_f32(m2, 2.0f); + + printf("\n------ Test 1 - Matrix Mult via F32 code ------------------------------------------------------------------------------\n"); + // printf("Creating new tensor m11xm2\n"); + struct ggml_tensor * m11xm2 = ggml_mul_mat(ctx, m11, m2); + + // printf("Creating compute graph\n"); + struct ggml_cgraph gf = ggml_build_forward(m11xm2); + + gf.n_threads=benchmark_params.n_threads; + printf("cgraph->n_threads=%i\n",gf.n_threads); + + TENSOR_DUMP(m11); + TENSOR_DUMP(m2); + + ggml_graph_compute(ctx, &gf); + + TENSOR_DUMP(gf.nodes[0]); + + printf("\n------ Test 2 - Matrix Mult via Q4_0 code ------------------------------------------------------------------------------\n"); + + int32_t nelements = sizex*sizey; + int32_t ne[2] = { sizex, sizey }; + + std::vector hist_cur(1 << 4, 0); + + // Set up a the benchmark matrices + // printf("Creating new tensor q11 & Running quantize\n"); + struct ggml_tensor * q11 = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, sizex, sizey); + ggml_quantize_q4_0((const float *) m11->data, q11->data, nelements, ne[0], hist_cur.data()); + + // Set up a the compute graph + // printf("Creating new tensor q31\n"); + struct ggml_tensor * q31 = ggml_mul_mat(ctx, q11, m2); + + // printf("Creating compute graph\n"); + struct ggml_cgraph gf31 = ggml_build_forward(q31); + gf31.n_threads=benchmark_params.n_threads; + + // Set up a second graph computation to make sure we override the CPU cache lines + // printf("Creating new tensor q12 & Running quantize\n"); + struct ggml_tensor * q12 = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, sizex, sizey); + ggml_quantize_q4_0((const float *) m12->data, q12->data, nelements, ne[0], hist_cur.data()); + + // printf("Creating new tensor q32\n"); + struct ggml_tensor * q32 = ggml_mul_mat(ctx, q12, m2); + + //printf("Creating compute graph\n"); + struct ggml_cgraph gf32 = ggml_build_forward(q32); + gf32.n_threads=benchmark_params.n_threads; + printf("cgraph->n_threads=%i\n",gf31.n_threads); + + const int dimx = sizex; + const int dimy = sizey; + const int dimz = sizez; + long long int flops_per_dot_product = dimy + dimy; + long long int flops_per_matrix = flops_per_dot_product * dimx * dimz; ; + printf("Matrix Multiplication of (%i,%i,%i) x (%i,%i,%i) - about %6.2f gFLOPS\n\n", sizex, sizey, 1, sizex, sizez, 1, 1.0f*flops_per_matrix / 1000 / 1000 / 1000); + + + // Let's use the F32 result from above as a reference for the q4_0 multiplication + float sum_of_F32_reference = tensor_sum_elements(gf.nodes[0]); + + + printf("Iteration;NThreads; SizeX; SizeY; SizeZ; Required_FLOPS; Elapsed_u_Seconds; FLOPS_per_u_Second\n"); + printf("==============================================================================================\n"); + + for (int i=0;i allowed_delta) { + printf("\nABORT - ERROR in Matrix Multiplication result - expected %6.2f, got %6.2f (delta %6.2f > allowed_delta %6.2f)\n", + sum_of_F32_reference, + sum_of_Q4_result, + delta, + allowed_delta + ); + exit(0); + } + + // Running a different graph computation to make sure we override the CPU cache lines + ggml_graph_compute(ctx, &gf32); + + } + +}