Merge remote-tracking branch 'origin' into develop

Author: ChipKerchner

.cirrus.yml

@@ -151,7 +151,7 @@ FreeBSD_task:
     image_family: freebsd-14-3
   install_script:
   - pkg update -f && pkg upgrade -y && pkg install -y gmake gcc 
-  - ln -s /usr/local/lib/gcc13/libgfortran.so.5.0.0 /usr/lib/libgfortran.so
+  - ln -s /usr/local/lib/gcc14/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/apple_m.yml

@@ -99,6 +99,7 @@ jobs:
         run: |
           export CPPFLAGS="-I/opt/homebrew/opt/llvm/include"
           export CC="/opt/homebrew/opt/llvm/bin/clang"
+          export RANLIB=llvm-ranlib
           case "${{ matrix.build }}" in
             "make")
               make -j$(nproc) DYNAMIC_ARCH=1 USE_OPENMP=${{matrix.openmp}} INTERFACE64=${{matrix.ilp64}} FC="ccache ${{ matrix.fortran }}"

.github/workflows/dynamic_arch.yml

@@ -1,6 +1,6 @@
 name: continuous build
 
-on: [push, pull_request]
+on: [push, pull_request, workflow_dispatch]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
@@ -11,18 +11,25 @@ permissions:
 
 jobs:
   build:
-    if: "github.repository == 'OpenMathLib/OpenBLAS'"
+    if: "github.repository == 'OpenMathLib/OpenBLAS' || github.event_name == 'workflow_dispatch'"
     runs-on: ${{ matrix.os }}
 
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-latest]
+        os: [ubuntu-latest, macos-latest, ubuntu-24.04-arm]
+        cc: [gcc, clang, clang-21]
         fortran: [gfortran, flang]
         build: [cmake, make]
         exclude:
+          - os: macos-latest
+            cc: gcc
+          - os: macos-latest
+            cc: clang-21
           - os: macos-latest
             fortran: flang
+          - os: ubuntu-24.04-arm
+            fortran: flang
 
     steps:
       - name: Checkout repository
@@ -42,10 +49,23 @@ jobs:
       - name: Install Dependencies
         run: |
           if [ "$RUNNER_OS" == "Linux" ]; then
+            cat << EOF | sudo tee -a /etc/apt/apt.conf.d/01norecommend
+          APT::Install-Recommends "0";
+          APT::Install-Suggests "0";
+          EOF
             sudo apt-get update
-            sudo apt-get install -y gfortran cmake ccache
-            wget http://security.ubuntu.com/ubuntu/pool/universe/n/ncurses/libtinfo5_6.3-2ubuntu0.1_amd64.deb
-            sudo apt install ./libtinfo5_6.3-2ubuntu0.1_amd64.deb
+            sudo apt-get install -y ccache
+            if [ "${{ matrix.cc }}" == "clang-21" ]; then
+                wget https://apt.llvm.org/llvm.sh
+                chmod +x llvm.sh
+                sudo ./llvm.sh 21
+            fi
+            if [ "${{ matrix.fortran }}" == "flang" ]; then
+              wget http://security.ubuntu.com/ubuntu/pool/universe/n/ncurses/libtinfo5_6.3-2ubuntu0.1_amd64.deb
+              sudo apt install ./libtinfo5_6.3-2ubuntu0.1_amd64.deb
+            else
+              sudo apt-get install -y ${{ matrix.fortran }}
+            fi
           elif [ "$RUNNER_OS" == "macOS" ]; then
             # It looks like "gfortran" isn't working correctly unless "gcc" is re-installed.
             brew reinstall gcc
@@ -64,12 +84,12 @@ jobs:
           # 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 }}-${{ github.sha }}
+          key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build }}-${{ matrix.cc }}-${{ 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 }}-${{ matrix.build }}
+            ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build }}-${{ matrix.cc }}-${{ matrix.fortran }}-${{ github.ref }}
+            ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build }}-${{ matrix.cc }}-${{ matrix.fortran }}
+            ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build }}-${{ matrix.cc }}
 
       - name: Configure ccache
         run: |
@@ -89,7 +109,7 @@ jobs:
           echo "max_size = 300M" > ~/.ccache/ccache.conf
           echo "compression = true" >> ~/.ccache/ccache.conf
           ccache -s
-          
+
       - name: Add gfortran runtime to link path
         if: matrix.build == 'make' && runner.os == 'macOS'
         run: |
@@ -110,7 +130,7 @@ jobs:
           fi
           case "${{ matrix.build }}" in
             "make")
-              make -j$(nproc) DYNAMIC_ARCH=1 USE_OPENMP=0 FC="ccache ${{ matrix.fortran }}"
+              make -j$(nproc) DYNAMIC_ARCH=1 USE_OPENMP=0 CC="ccache ${{ matrix.cc }}" FC="ccache ${{ matrix.fortran }}"
               ;;
             "cmake")
               mkdir build && cd build
@@ -119,6 +139,7 @@ jobs:
                     -DBUILD_WITHOUT_LAPACK=0 \
                     -DCMAKE_VERBOSE_MAKEFILE=ON \
                     -DCMAKE_BUILD_TYPE=Release \
+                    -DCMAKE_C_COMPILER=${{ matrix.cc }} \
                     -DCMAKE_Fortran_COMPILER=${{ matrix.fortran }} \
                     -DCMAKE_C_COMPILER_LAUNCHER=ccache \
                     -DCMAKE_Fortran_COMPILER_LAUNCHER=ccache \
@@ -142,13 +163,13 @@ jobs:
             "make")
               MAKE_FLAGS='DYNAMIC_ARCH=1 USE_OPENMP=0'
               echo "::group::Tests in 'test' directory"
-              make -C test $MAKE_FLAGS FC="ccache ${{ matrix.fortran }}"
+              make -C test $MAKE_FLAGS CC="ccache ${{ matrix.cc }}" FC="ccache ${{ matrix.fortran }}"
               echo "::endgroup::"
               echo "::group::Tests in 'ctest' directory"
-              make -C ctest $MAKE_FLAGS FC="ccache ${{ matrix.fortran }}"
+              make -C ctest $MAKE_FLAGS CC="ccache ${{ matrix.cc }}" FC="ccache ${{ matrix.fortran }}"
               echo "::endgroup::"
               echo "::group::Tests in 'utest' directory"
-              make -C utest $MAKE_FLAGS FC="ccache ${{ matrix.fortran }}"
+              make -C utest $MAKE_FLAGS CC="ccache ${{ matrix.cc }}" FC="ccache ${{ matrix.fortran }}"
               echo "::endgroup::"
               ;;
             "cmake")
@@ -372,15 +393,15 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
-        
+
       - name: Install Dependencies
         run: |
           sudo apt-get update
           sudo apt-get install -y gcc gfortran make
-          
+
       - name: Build OpenBLAS
         run: |
-          make -j${nproc} 
+          make -j${nproc}
           make -j${nproc} lapack-test
-    
-          
+
+

.github/workflows/riscv64_vector.yml

@@ -140,6 +140,8 @@ jobs:
           while IFS= read -r -d $'\0' LOG; do cat $LOG ; FAILURES=1 ; done < <(grep -lZ FAIL ./test_out/*)
           if [[ ! -z $FAILURES ]]; then echo "==========" ; echo "== FAIL ==" ; echo "==========" ; echo ; exit 1 ; fi
           if [ "${{matrix.target}}" == "RISCV64_ZVL256B" ]; then
+          qemu-riscv64 test/test_sbgemm &
+          qemu-riscv64 test/test_sbgemv &
           qemu-riscv64 test/test_shgemm &
           qemu-riscv64 test/test_shgemv &
           qemu-riscv64 test/test_bgemm

CMakeLists.txt

@@ -9,7 +9,7 @@ project(OpenBLAS C ASM)
 
 set(OpenBLAS_MAJOR_VERSION 0)
 set(OpenBLAS_MINOR_VERSION 3)
-set(OpenBLAS_PATCH_VERSION 30.dev)
+set(OpenBLAS_PATCH_VERSION 31.dev)
 
 set(OpenBLAS_VERSION "${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.${OpenBLAS_PATCH_VERSION}")
 
@@ -308,8 +308,8 @@ if (USE_OPENMP)
   endif()
 endif()
 
-# Fix "Argument list too long" for macOS with POWERPC or Intel CPUs 
-if(APPLE AND (NOT CMAKE_HOST_SYSTEM_PROCESSOR STREQUAL "arm64"))
+# Fix "Argument list too long" for macOS - mostly seen with older OS versions on POWERPC or Intel CPUs 
+if(APPLE)
   # Use response files
   set(CMAKE_C_USE_RESPONSE_FILE_FOR_OBJECTS 1)
   # Always build static library first
@@ -708,6 +708,39 @@ if(NOT NO_LAPACKE)
   COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_CURRENT_SOURCE_DIR}/lapack-netlib/LAPACKE/include/lapacke_mangling_with_flags.h.in "${CMAKE_BINARY_DIR}/lapacke_mangling.h"
   )
   install (FILES ${CMAKE_BINARY_DIR}/lapacke_mangling.h DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
+  if (NOT (x${SYMBOLPREFIX}${SYMBOLSUFFIX} STREQUAL "x"))
+  message (STATUS "Generating lapacke.h in ${CMAKE_INSTALL_INCLUDEDIR}")
+  set(LAPACKE_H ${CMAKE_BINARY_DIR}/generated/lapacke.h)
+  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/lapack-netlib/LAPACKE/include/lapacke.h LAPACKE_H_CONTENTS)
+  if (NOT ${SYMBOLPREFIX} STREQUAL "")
+	  string(REGEX REPLACE "(LAPACKE_*)" " ${SYMBOLPREFIX}\\1" LAPACKE_H_CONTENTS_NEW	"${LAPACKE_H_CONTENTS}")
+	  string(REPLACE "_ ${SYMBOLPREFIX}LAPACKE_H_"  "_LAPACKE_H_" LAPACKE_H_CONTENTS ${LAPACKE_H_CONTENTS_NEW})
+	  string(REPLACE "${SYMBOLPREFIX}LAPACKE_malloc"  "LAPACKE_malloc" LAPACKE_H_CONTENTS_NEW ${LAPACKE_H_CONTENTS})
+	  string(REPLACE "${SYMBOLPREFIX}LAPACKE_free"  "LAPACKE_free" LAPACKE_H_CONTENTS ${LAPACKE_H_CONTENTS_NEW})
+	  set(LAPACKE_H_CONTENTS_NEW ${LAPACKE_H_CONTENTS})
+  endif()
+  if (NOT ${SYMBOLSUFFIX} STREQUAL "")
+	  string(REGEX REPLACE "(${SYMBOLPREFIX}LAPACKE_[a-z1-9]*[^ (]*)" "\\1${SYMBOLSUFFIX}" LAPACKE_H_CONTENTS_NEW	"${LAPACKE_H_CONTENTS}")
+	  string(REPLACE "#define${SYMBOLSUFFIX}"  "#define" LAPACKE_H_CONTENTS ${LAPACKE_H_CONTENTS_NEW})
+	  string(REPLACE "LAPACKE_malloc${SYMBOLSUFFIX}"  "LAPACKE_malloc" LAPACKE_H_CONTENTS_NEW ${LAPACKE_H_CONTENTS})
+	  string(REPLACE "LAPACKE_free${SYMBOLSUFFIX}"  "LAPACKE_free" LAPACKE_H_CONTENTS ${LAPACKE_H_CONTENTS_NEW})
+	  set(LAPACKE_H_CONTENTS_NEW ${LAPACKE_H_CONTENTS})
+  endif()
+  file(WRITE ${LAPACKE_H} "${LAPACKE_H_CONTENTS_NEW}")
+  install (FILES ${LAPACKE_H} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
+  message (STATUS "Generating lapack.h in ${CMAKE_INSTALL_INCLUDEDIR}")
+  set(LAPACK_H ${CMAKE_BINARY_DIR}/generated/lapack.h)
+  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/lapack-netlib/LAPACKE/include/lapack.h LAPACK_H_CONTENTS)
+  if (NOT ${SYMBOLPREFIX} STREQUAL "")
+	  string(REGEX REPLACE "(LAPACK_[a-z1-9]*[ \(][.\)]*)" "${SYMBOLPREFIX}\\1" LAPACK_H_CONTENTS_NEW	"${LAPACK_H_CONTENTS}")
+	  set(LAPACK_H_CONTENTS ${LAPACK_H_CONTENTS_NEW})
+  endif()
+  if (NOT ${SYMBOLSUFFIX} STREQUAL "")
+	  string(REGEX REPLACE "(${SYMBOLPREFIX}LAPACK_[a-z1-9]*)([ \(].\)" "\\1${SYMBOLSUFFIX}\\2" LAPACK_H_CONTENTS_NEW	"${LAPACK_H_CONTENTS}")
+  endif()
+  file(WRITE ${LAPACK_H} "${LAPACK_H_CONTENTS_NEW}")
+  install (FILES ${LAPACK_H} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
+endif()
 endif()
 
 # Install pkg-config files

CONTRIBUTORS.md

@@ -29,6 +29,9 @@
 * Annop Wongwathanarat <annop.wongwathanarat@arm.com>
   * Optimizations and other improvements targeting AArch64
 
+* Anna Mayne <anna.mayne@arm.com>
+  * Optimizations and other improvements targeting AArch64
+
 ## Previous Developers
 
 * Zaheer Chothia <zaheer.chothia@gmail.com>
@@ -267,3 +270,5 @@ In chronological order:
   * [2025-05-29] Optimise axpby kernel for RISCV64_ZVL256B
   * [2025-06-05] Optimise hbmv kernel for RISCV64_ZVL256B
 
+* Anna Mayne <anna.mayne@arm.com>
+  * [2025-11-19] Update thread throttling profile for SGEMV on NEOVERSEV1 and NEOVERSEV2

Changelog.txt

@@ -1,4 +1,120 @@
 OpenBLAS ChangeLog
+====================================================================
+Version 0.3.31
+15-Jan-2025
+
+general:
+ - reverted a matrix partitioning optimization from 0.3.30 that could lead to 
+   race conditions and subsequent invalid results in GEMM
+ - added the bfloat16 extensions BGEMM and BGEMV
+ - added a BLAS interface for the ?GEMM_BATCH extensions
+ - added the BLAS extensions ?GEMM_BATCH_STRIDED and their CBLAS interface
+ - added the basic infrastructure for half-precision float (FP16) format 
+   using SH prefix
+ - reimplemented the LAPACK SLAED3/DLAED3 function using multithreading, thereby
+   improving the performance of the SSYEVD/DSYEVD eigensolver for symmetric matrices 
+   on all platforms
+ - limited the number of retries for initial memory allocation to avoid infinite
+   hanging on low-memory systems
+ - fixed a thread lockup situation encountered with python 3.9 or older and numpy
+ - introduced a problem size threshold for multithreading in STRMV/DTRMV
+ - introduced a problem size threshold for multithreading in CHER/CHER2/CHPR/CHPR2
+   and ZHER/ZHER2/ZHPR/ZHPR2
+ - improved the problem size thresholds for multithreading in SGER/DGER
+ - improved autodetection of the Fortran compiler
+ - fixed passing of the INTERFACE64=1 option to the flang-new compiler
+ - fixed a potential deadlock in multithreaded code after calling fork()
+ - fixed builds using CMake on FreeBSD
+ - fixed builds using CMake from within Cygwin on Windows
+ - fixed builds using CMake and the NVHPC compiler on ARM64
+ - fixed CMake build error from misdetecting compiler or OpenMP versions
+ - improved contents of the CMake-generated OpenBLASConfig.cmake file
+ - added support for cross-compilation to RISCV targets via CMake
+ - fixed cross-compilation to x86 targets from non-x86 architectures
+ - fixed failure to install cblas.h if NO_CBLAS=0 was specified
+ - fixed missing user-defined pre- and postfixes on functions in lapack.h,lapacke.h 
+ - included fixes from the Reference-LAPACK project:
+   - fix ordering bug in ?LAED/?LASD (Reference-LAPACK PR 1140)
+   - revert changes in ?GEEV from PR 1129 (Reference-LAPACK PR 1142)
+   - fix workspace allocation in LAPACKE_?TRSEN (Reference-LAPACK PR 1144)
+
+riscv:
+ - added optimized SBGEMM kernels for ZVL128B and ZVL256B targets
+ - added optimized SHGEMM kernels for ZVL128B and ZVL256B targets
+ - added optimized SBGEMV and SHGEMV kernels for ZVL128B/ZVL256B
+ - improved performance of the GEMV kernel for ZVL256B
+ - improved the performance of the CROT and ZROT kernels for ZVL128B and x280
+ - improved the detection of RVV1.0 capability 
+ - improved performance of the matrix packing helper functions for ZVL128B and ZVL256B
+ - improved performance of OMATCOPY for ZVL128B and ZVL256B
+
+arm:
+ - fixed spurious executable stack in the getarch utility
+
+arm64:
+ - fixed spurious executable stack in the getarch utility
+ - fixed compiler warnings arising from the timer macro RPCC
+ - fixed cache size detection for Qualcomm Oryon under Windows on Arm
+ - fixed argument handling in the default SVE kernel for SDOT/DDOT
+ - building the BFLOAT16 kernels is now enabled by default
+ - improved the overall performance of GEMM,SYMM and HEMM on A64FX
+ - improved the performance of SDOT/DDOT on A64FX
+ - improved the multithreading performance of SDOT/DDOT on A64FX by
+   introduction of a throttling table matching thread count to problem size
+ - improved the performance of SGER/DGER on A64FX and NEOVERSEV1
+ - improved the multithreading performance of GEMM on A64FX and NEOVERSEV1
+ - improved the performance of the GEMV kernel for SVE-capable targets
+ - improved the multithreading performance of SGEMM on NEOVERSEV1 and V2
+ - added optimized SAXPY/DAXPY SVE kernels for A64FX and NEOVERSEV1
+ - added optimized BGEMM and BGEMV kernels for NEOVERSEV1
+ - added an optimized BGEMM kernel for NEOVERSEN2
+ - added support for the NEOVERSEV2 cpu
+ - added dedicated support for the Apple M4 cpu as VORTEXM4
+ - added optimized SGEMM/SSYMM/STRMM/SSYRK/SSYR2K for SME-capable targets
+   (ARMV9SME and VORTEXM4)
+ - improved the precision of the SNRM2 kernel
+ - added cpu autodetection and compiler settings for Ampere One processors
+ - fixed cpu autodetection for Apple M systems running Linux
+ - fixed building on MacOS with AppleClang,gfortran and xcode v16 or newer
+ - fixed several errors in the C code replacements for the complex and double
+   precision complex LAPACK functions that get used (only) when compiling with
+   Microsoft C and NOFORTRAN=1 under MS Windows
+
+power:
+ - added initial support for the POWER11 architecture
+ - improved performance of DGEMM and DGEMV on POWER10
+ - fixed the default compiler flags to use "-O3" instead of the possibly unsafe 
+   "-Ofast"
+ - fixed building under MacOS (for old G4 Macs) with CMake
+ - fixed potential miscompilation of DGEMV and other assembly kernels by gcc15.1
+ - fixed compilation with recent versions of flang
+
+loongarch64:
+ - fixed warnings and potential inaccuracies arising from incorrect saving of registers
+ - fixed enumeration of logical cores on big NUMA servers
+ - fixed building with LLVM and the INTERFACE64=1 option
+
+x86:
+ - fixed building the GEMM3M kernels for the GENERIC target
+ - fixed several errors in the C code replacements for the complex and double
+   precision complex LAPACK functions that get used (only) when compiling with
+   Microsoft C and NOFORTRAN=1 under MS Windows
+
+x86_64:
+ - added cpu autodetection for Intel Lunar Lake (Core Ultra 200V)
+ - changed all ?MIN and ?MAX assembly kernels to use unaligned operations 
+ - fixed several errors in the C code replacements for the complex and double
+   precision complex LAPACK functions that get used (only) when compiling with
+   Microsoft C and NOFORTRAN=1 under MS Windows
+ - fixed potential crashes in builds for Cooper Lake, Sapphire Rapids or Zen5 cpus
+   under MS Windows
+
+zarch:
+ - added support for building with CMake
+
+sparc:
+ - fixed a potential crash in the DNRM2 kernel
+
 ====================================================================
 Version 0.3.30
 19-Jun-2025