Merge branch 'develop' into jn/build-exe

Author: martin-frbg

.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 }}"

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 +270,8 @@ 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
+
+* Fadi Arafeh <fadi.arafeh@arm.com>
+  * [2026-03-05] Accelerate SVE128 SBGEMM/BGEMM

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

Jenkinsfile.pwr

@@ -1,16 +1,31 @@
 pipeline {
-    agent { 
-        docker {
-            image 'osuosl/ubuntu-ppc64le:18.04'
-        }
-    }
+    agent none
     stages {
-        stage('Build') {
+        stage('GCC build') {
+            agent {
+                docker {
+                    image 'osuosl/ubuntu-ppc64le:18.04' // gcc 7, gfortran 7
+                }
+            }
             steps {
+                checkout scm
                 sh 'sudo apt update'
                 sh 'sudo apt install gfortran -y'
                 sh 'make clean && make'
             }
         }
+        stage('Clang build') {
+            agent {
+                docker {
+                    image 'osuosl/ubuntu-ppc64le:20.04' // clang 10, gfortran 9
+                }
+            }
+            steps {
+                checkout scm
+                sh 'sudo apt update'
+                sh 'sudo apt install -y clang gfortran'
+                sh 'make clean && make CC=clang'
+            }
+        }
     }
 }

Makefile.arm64

@@ -61,6 +61,11 @@ endif
 ifeq ($(CORE), ARMV9SME)
 CCOMMON_OPT += -march=armv9-a+sve2+sme
 FCOMMON_OPT += -march=armv9-a+sve2
+ifdef OS_WINDOWS
+ifeq ($(C_COMPILER), CLANG)
+CCOMMON_OPT += --aarch64-stack-hazard-size=0
+endif
+endif
 endif
 
 ifeq ($(CORE), CORTEXA53)
@@ -303,6 +308,20 @@ FCOMMON_OPT += -march=armv8.3-a
 endif
 endif
 
+ifeq ($(CORE), VORTEXM4)
+ifneq ($(C_COMPILER), GCC)
+ifeq ($(APPLECLANG),1)
+CCOMMON_OPT += -march=armv8.4-a+sme
+else
+CCOMMON_OPT += -march=armv8.4-a+sme
+override LDFLAGS += -lclang_rt_builtins-aarch64
+endif
+else
+CCOMMON_OPT += -march=armv8.4-a
+endif
+FCOMMON_OPT += -march=armv8.4-a
+endif
+
 ifeq (1, $(filter 1,$(GCCVERSIONGTEQ9) $(ISCLANG)))
 ifeq ($(CORE), TSV110)
 CCOMMON_OPT += -march=armv8.2-a -mtune=tsv110

Makefile.install

@@ -93,9 +93,27 @@ endif
 
 ifneq ($(OSNAME), AIX)
 ifneq ($(NO_LAPACKE), 1)
+	@cp $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapacke.h lapacke_h.tmp
+ifdef SYMBOLPREFIX
+	@sed 's/LAPACKE_[a-z1-9].[^() ]*/$(SYMBOLPREFIX)&/g' lapacke_h.tmp > lapacke.tmp2
+	@mv lapacke.tmp2 lapacke_h.tmp
+endif
+ifdef SYMBOLSUFFIX
+	@sed 's/LAPACKE_[a-z1-9].[^() ]*/&$(SYMBOLSUFFIX)/g' lapacke_h.tmp > lapacke.tmp2
+	@mv lapacke.tmp2 lapacke_h.tmp
+endif
+	@-install -m644 lapacke_h.tmp "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapacke.h"
 	@echo Copying LAPACKE header files to $(DESTDIR)$(OPENBLAS_INCLUDE_DIR)
-	@-install -m644 $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapack.h "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapack.h"
-	@-install -m644 $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapacke.h "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapacke.h"
+	@cp $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapack.h lapack_h.tmp
+ifdef SYMBOLPREFIX
+	@sed 's/LAPACK_[a-z1-9]*(\.\.\.)/$(SYMBOLPREFIX)&/g' lapack_h.tmp > lapack.tmp2
+	@mv lapack.tmp2 lapack_h.tmp
+endif
+ifdef SYMBOLSUFFIX
+	@sed 's/\(#define $(SYMBOLPREFIX)LAPACK_[a-z1-9].*\)\((...)\)/\1$(SYMBOLSUFFIX)\2/g' lapack_h.tmp > lapack.tmp2
+	@mv lapack.tmp2 lapack_h.tmp
+endif
+	@-install -m644 lapack_h.tmp "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapack.h"
 	@-install -m644 $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapacke_config.h "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapacke_config.h"
 	@-install -m644 $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapacke_mangling_with_flags.h.in "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapacke_mangling.h"
 	@-install -m644 $(NETLIB_LAPACK_DIR)/LAPACKE/include/lapacke_utils.h "$(DESTDIR)$(OPENBLAS_INCLUDE_DIR)/lapacke_utils.h"

Makefile.rule

@@ -3,7 +3,7 @@
 #
 
 # This library's version
-VERSION = 0.3.30.dev
+VERSION = 0.3.31.dev
 
 # If you set this prefix, the library name will be lib$(LIBNAMESUFFIX)openblas.a
 # and lib$(LIBNAMESUFFIX)openblas.so, with a matching soname in the shared library

Makefile.system

@@ -331,6 +331,7 @@ HAVE_SSE5=
 HAVE_AVX=
 HAVE_AVX2=
 HAVE_FMA3=
+HAVE_SME=
 include $(TOPDIR)/Makefile_kernel.conf
 endif
 
@@ -427,7 +428,7 @@ ifndef MACOSX_DEPLOYMENT_TARGET
 ifeq ($(ARCH), arm64)
 export MACOSX_DEPLOYMENT_TARGET=11.0
 export NO_SVE = 1
-export NO_SME = 1
+# export NO_SME = 1
 else
 export MACOSX_DEPLOYMENT_TARGET=10.8
 endif
@@ -721,6 +722,11 @@ DYNAMIC_CORE += A64FX
 endif
 ifneq ($(NO_SME), 1)
 DYNAMIC_CORE += ARMV9SME
+ifeq ($(OSNAME), Darwin)
+ifneq ($(C_COMPILER), GCC)
+DYNAMIC_CORE += VORTEXM4
+endif
+endif
 endif
 DYNAMIC_CORE += THUNDERX
 DYNAMIC_CORE += THUNDERX2T99
@@ -1904,6 +1910,7 @@ ifndef NO_MSA
   export HAVE_MSA
   export MSA_FLAGS
 endif
+export HAVE_SME
 export KERNELDIR
 export FUNCTION_PROFILE
 export TARGET_CORE