Merge pull request #4854 from OpenMathLib/develop

merge develop in preparation of the 0.3.28 release

Author: martin-frbg

.cirrus.yml

@@ -41,7 +41,7 @@ macos_instance:
 #  - make CC=gcc-11 FC=gfortran-11 USE_OPENMP=1
 
 macos_instance:
-  image: ghcr.io/cirruslabs/macos-monterey-xcode:latest
+  image: ghcr.io/cirruslabs/macos-sonoma-xcode:latest
 task:
   name: AppleM1/LLVM x86_64 xbuild
   compile_script:
@@ -58,8 +58,8 @@ task:
   - export VALID_ARCHS="i386 x86_64"
   - xcrun --sdk macosx --show-sdk-path
   - xcodebuild -version
-  - export CC=/Applications/Xcode-15.3.0.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang
-  - export CFLAGS="-O2 -unwindlib=none -Wno-macro-redefined -isysroot /Applications/Xcode-15.3.0.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX14.4.sdk -arch x86_64"
+  - export CC=/Applications/Xcode_15.4.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang
+  - export CFLAGS="-O2 -unwindlib=none -Wno-macro-redefined -isysroot /Applications/Xcode_15.4.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX14.5.sdk -arch x86_64"
   - make TARGET=CORE2 DYNAMIC_ARCH=1 NUM_THREADS=32 HOSTCC=clang NOFORTRAN=1 RANLIB="ls -l"
   always:
     config_artifacts:
@@ -70,16 +70,18 @@ task:
 #    type: application/octet-streamm
 
 macos_instance:
-  image: ghcr.io/cirruslabs/macos-monterey-xcode:latest
+  image: ghcr.io/cirruslabs/macos-sonoma-xcode:latest
 task:
   name: AppleM1/LLVM armv8-ios xbuild
   compile_script:
   - #brew install llvm
   - export #PATH=/opt/homebrew/opt/llvm/bin:$PATH
   - export #LDFLAGS="-L/opt/homebrew/opt/llvm/lib"
   - export #CPPFLAGS="-I/opt/homebrew/opt/llvm/include" 
-  - export CC=/Applications/Xcode-15.3.0.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang
-  - export CFLAGS="-O2 -unwindlib=none -Wno-macro-redefined -isysroot /Applications/Xcode-15.3.0.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS17.4.sdk -arch arm64 -miphoneos-version-min=10.0"
+  - export CC=/Applications/Xcode_15.4.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang
+  - export CFLAGS="-O2 -unwindlib=none -Wno-macro-redefined -isysroot /Applications/Xcode_15.4.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS17.5.sdk -arch arm64 -miphoneos-version-min=10.0"
+  - xcrun --sdk iphoneos --show-sdk-path
+  - ls -l /Applications
   - make TARGET=ARMV8 NUM_THREADS=32 HOSTCC=clang NOFORTRAN=1 CROSS=1
   always:
     config_artifacts:
@@ -96,11 +98,11 @@ task:
   - export #LDFLAGS="-L/opt/homebrew/opt/llvm/lib"
   - export #CPPFLAGS="-I/opt/homebrew/opt/llvm/include" 
   - ls /System/Volumes/Data/opt/homebrew
-  - ls -l /System/Volumes/Data/opt/homebrew/Caskroom/
+  - ls -l /System/Volumes/Data/opt/homebrew/Caskroom/android-ndk
   - find /System/Volumes/Data/opt/homebrew -name "armv7a-linux-androideabi*-ranlib"
   - #export CC=/Applications/Xcode-13.4.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang
   - #export CFLAGS="-O2 -unwindlib=none -Wno-macro-redefined -isysroot /Applications/Xcode-13.4.1.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS16.0.sdk -arch arm64 -miphoneos-version-min=10.0"
-  - export CC=/System/Volumes/Data/opt/homebrew/Caskroom/android-ndk/26c/AndroidNDK*.app/Contents/NDK/toolchains/llvm/prebuilt/darwin-x86_64/bin/armv7a-linux-androideabi23-clang
+  - export CC=/System/Volumes/Data/opt/homebrew/Caskroom/android-ndk/26d/AndroidNDK*.app/Contents/NDK/toolchains/llvm/prebuilt/darwin-x86_64/bin/armv7a-linux-androideabi23-clang
   - make TARGET=ARMV7 ARM_SOFTFP_ABI=1 NUM_THREADS=32 HOSTCC=clang NOFORTRAN=1 RANLIB="ls -l"
   always:
     config_artifacts:
@@ -132,7 +134,7 @@ task:
 FreeBSD_task:
   name: FreeBSD-gcc12
   freebsd_instance:
-    image_family: freebsd-13-2
+    image_family: freebsd-13-3
   install_script:
   - pkg update -f && pkg upgrade -y && pkg install -y gmake gcc
   compile_script:
@@ -143,7 +145,7 @@ FreeBSD_task:
 FreeBSD_task:
   name: freebsd-gcc12-ilp64
   freebsd_instance:
-    image_family: freebsd-13-2
+    image_family: freebsd-13-3
   install_script:
   - pkg update -f && pkg upgrade -y && pkg install -y gmake gcc
   compile_script:
@@ -153,10 +155,10 @@ FreeBSD_task:
 FreeBSD_task:
   name: FreeBSD-clang-openmp
   freebsd_instance:
-    image_family: freebsd-13-2
+    image_family: freebsd-13-3
   install_script:
   - pkg update -f && pkg upgrade -y && pkg install -y gmake gcc 
-  - ln -s /usr/local/lib/gcc12/libgfortran.so.5.0.0 /usr/lib/libgfortran.so
+  - ln -s /usr/local/lib/gcc13/libgfortran.so.5.0.0 /usr/lib/libgfortran.so
   compile_script:
   - gmake CC=clang FC=gfortran USE_OPENMP=1 CPP_THREAD_SAFETY_TEST=1
 

.github/workflows/c910v.yml

@@ -84,6 +84,7 @@ jobs:
         run: |
           export PATH=$GITHUB_WORKSPACE/qemu-install/bin/:$PATH
           qemu-riscv64 ./utest/openblas_utest
+          qemu-riscv64 ./utest/openblas_utest_ext
           OPENBLAS_NUM_THREADS=2 qemu-riscv64 ./ctest/xscblat1
           OPENBLAS_NUM_THREADS=2 qemu-riscv64 ./ctest/xdcblat1
           OPENBLAS_NUM_THREADS=2 qemu-riscv64 ./ctest/xccblat1

.github/workflows/codspeed-bench.yml

@@ -0,0 +1,157 @@
+name: Run codspeed benchmarks
+
+on: [push, pull_request]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read # to fetch code (actions/checkout)
+
+jobs:
+  benchmarks:
+    if: "github.repository == 'OpenMathLib/OpenBLAS'"
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        fortran: [gfortran]
+        build: [make]
+        pyver: ["3.12"]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+        with:
+            python-version: ${{ matrix.pyver }}
+
+      - name: Print system information
+        run: |
+          if [ "$RUNNER_OS" == "Linux" ]; then
+            cat /proc/cpuinfo
+          fi
+
+      - name: Install Dependencies
+        run: |
+          if [ "$RUNNER_OS" == "Linux" ]; then
+            sudo apt-get update
+            sudo apt-get install -y gfortran cmake ccache libtinfo5
+          else
+            echo "::error::$RUNNER_OS not supported"
+            exit 1
+          fi
+
+      - name: Compilation cache
+        uses: actions/cache@v3
+        with:
+          path: ~/.ccache
+          # We include the commit sha in the cache key, as new cache entries are
+          # only created if there is no existing entry for the key yet.
+          # GNU make and cmake call the compilers differently. It looks like
+          # that causes the cache to mismatch. Keep the ccache for both build
+          # tools separate to avoid polluting each other.
+          key: ccache-${{ runner.os }}-${{ matrix.build }}-${{ matrix.fortran }}-${{ github.ref }}-${{ github.sha }}
+          # Restore a matching ccache cache entry. Prefer same branch and same Fortran compiler.
+          restore-keys: |
+            ccache-${{ runner.os }}-${{ matrix.build }}-${{ matrix.fortran }}-${{ github.ref }}
+            ccache-${{ runner.os }}-${{ matrix.build }}-${{ matrix.fortran }}
+            ccache-${{ runner.os }}-${{ matrix.build }}
+
+      - name: Write out the .pc
+        run: |
+             cd benchmark/pybench
+             cat > openblas.pc << EOF
+             libdir=${{ github.workspace }}
+             includedir= ${{ github.workspace }}
+             openblas_config= OpenBLAS 0.3.27 DYNAMIC_ARCH NO_AFFINITY Haswell MAX_THREADS=64
+             version=0.0.99
+             extralib=-lm -lpthread -lgfortran -lquadmath -L${{ github.workspace }} -lopenblas
+             Name: openblas
+             Description: OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version
+             Version: ${version}
+             URL: https://github.com/xianyi/OpenBLAS
+             Libs: ${{ github.workspace }}/libopenblas.so -Wl,-rpath,${{ github.workspace }}
+             Libs.private: -lm -lpthread -lgfortran -lquadmath -L${{ github.workspace }} -lopenblas
+             Cflags: -I${{ github.workspace}}
+             EOF
+             cat openblas.pc
+
+      - name: Configure ccache
+        run: |
+          if [ "${{ matrix.build }}" = "make" ]; then
+            # Add ccache to path
+            if [ "$RUNNER_OS" = "Linux" ]; then
+              echo "/usr/lib/ccache" >> $GITHUB_PATH
+            elif [ "$RUNNER_OS" = "macOS" ]; then
+              echo "$(brew --prefix)/opt/ccache/libexec" >> $GITHUB_PATH
+            else
+              echo "::error::$RUNNER_OS not supported"
+              exit 1
+            fi
+          fi
+          # Limit the maximum size and switch on compression to avoid exceeding the total disk or cache quota (5 GB).
+          test -d ~/.ccache || mkdir -p ~/.ccache
+          echo "max_size = 300M" > ~/.ccache/ccache.conf
+          echo "compression = true" >> ~/.ccache/ccache.conf
+          ccache -s
+
+      - name: Build OpenBLAS
+        run: |
+          case "${{ matrix.build }}" in
+            "make")
+              make -j$(nproc) DYNAMIC_ARCH=1 USE_OPENMP=0 FC="ccache ${{ matrix.fortran }}"
+              ;;
+            "cmake")
+              mkdir build && cd build
+              cmake -DDYNAMIC_ARCH=1 \
+                    -DNOFORTRAN=0 \
+                    -DBUILD_WITHOUT_LAPACK=0 \
+                    -DCMAKE_VERBOSE_MAKEFILE=ON \
+                    -DCMAKE_BUILD_TYPE=Release \
+                    -DCMAKE_Fortran_COMPILER=${{ matrix.fortran }} \
+                    -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+                    -DCMAKE_Fortran_COMPILER_LAUNCHER=ccache \
+                    ..
+              cmake --build .
+              ;;
+            *)
+              echo "::error::Configuration not supported"
+              exit 1
+              ;;
+          esac
+
+      - name: Show ccache status
+        continue-on-error: true
+        run: ccache -s
+
+      - name: Install benchmark dependencies
+        run: pip install meson ninja numpy pytest pytest-codspeed --user
+
+      - name: Build the wrapper
+        run: |
+          cd benchmark/pybench
+          export PKG_CONFIG_PATH=$PWD
+          meson setup build  --prefix=$PWD/build-install
+          meson install -C build
+          #
+          # sanity check
+          cd build/openblas_wrap
+          python -c'import _flapack; print(dir(_flapack))'
+
+      - name: Run benchmarks under pytest-benchmark
+        run: |
+          cd benchmark/pybench
+          pip install pytest-benchmark
+          export PYTHONPATH=$PWD/build-install/lib/python${{matrix.pyver}}/site-packages/
+          OPENBLAS_NUM_THREADS=1 pytest benchmarks/bench_blas.py -k 'gesdd'
+
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v2
+        with:
+          token: ${{ secrets.CODSPEED_TOKEN }}
+          run: |
+            cd benchmark/pybench
+            export PYTHONPATH=$PWD/build-install/lib/python${{matrix.pyver}}/site-packages/
+            OPENBLAS_NUM_THREADS=1 pytest benchmarks/bench_blas.py --codspeed
+

.github/workflows/docs.yml

@@ -0,0 +1,40 @@
+name: Publish docs via GitHub Pages
+
+on:
+  push:
+    branches:
+      - develop
+  pull_request:
+    branches:
+      - develop
+
+jobs:
+  build:
+    name: Deploy docs
+    if: "github.repository == 'OpenMathLib/OpenBLAS'"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install MkDocs and doc theme packages
+        run: pip install mkdocs mkdocs-material mkdocs-git-revision-date-localized-plugin
+
+      - name: Build docs site
+        run: mkdocs build
+
+      # mkdocs gh-deploy command only builds to the top-level, hence deploying
+      # with this action instead.
+      # Deploys to http://www.openmathlib.org/OpenBLAS/docs/
+      - name: Deploy docs
+        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+        if: ${{ github.ref == 'refs/heads/develop' }}
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./site
+          destination_dir: docs/