Merge branch 'develop' into win_tidy

Author: mseminatore

.github/workflows/c910v.yml

@@ -14,8 +14,8 @@ jobs:
     if: "github.repository == 'OpenMathLib/OpenBLAS'"
     runs-on: ubuntu-latest
     env:
-      xuetie_toolchain: https://occ-oss-prod.oss-cn-hangzhou.aliyuncs.com/resource//1663142514282
-      toolchain_file_name: Xuantie-900-gcc-linux-5.10.4-glibc-x86_64-V2.6.1-20220906.tar.gz
+      xuetie_toolchain: https://occ-oss-prod.oss-cn-hangzhou.aliyuncs.com/resource//1698113812618
+      toolchain_file_name: Xuantie-900-gcc-linux-5.10.4-glibc-x86_64-V2.8.0-20231018.tar.gz
     strategy:
       fail-fast: false
       matrix:
@@ -76,7 +76,7 @@ jobs:
         run: |
             wget ${xuetie_toolchain}/${toolchain_file_name}
             tar -xvf ${toolchain_file_name} -C /opt
-            export PATH="/opt/Xuantie-900-gcc-linux-5.10.4-glibc-x86_64-V2.6.1/bin:$PATH"
+            export PATH="/opt/Xuantie-900-gcc-linux-5.10.4-glibc-x86_64-V2.8.0/bin:$PATH"
 
             make CC='ccache ${{ matrix.triple }}-gcc -static' FC='ccache ${{ matrix.triple }}-gfortran -static' ${{ matrix.opts }} HOSTCC='ccache gcc' -j$(nproc)
 

.github/workflows/loongarch64.yml

@@ -16,13 +16,13 @@ jobs:
         include:
           - target: LOONGSONGENERIC
             triple:  loongarch64-unknown-linux-gnu
-            opts: NO_SHARED=1 TARGET=LOONGSONGENERIC
+            opts: NO_SHARED=1 DYNAMIC_ARCH=1 TARGET=LOONGSONGENERIC
           - target: LOONGSON3R5
             triple: loongarch64-unknown-linux-gnu
-            opts: NO_SHARED=1 TARGET=LOONGSON3R5
+            opts: NO_SHARED=1 DYNAMIC_ARCH=1 TARGET=LOONGSON3R5
           - target: LOONGSON2K1000
             triple: loongarch64-unknown-linux-gnu
-            opts: NO_SHARED=1 TARGET=LOONGSON2K1000
+            opts: NO_SHARED=1 DYNAMIC_ARCH=1 TARGET=LOONGSON2K1000
           - target: DYNAMIC_ARCH
             triple: loongarch64-unknown-linux-gnu
             opts: NO_SHARED=1 DYNAMIC_ARCH=1 TARGET=GENERIC
@@ -40,8 +40,9 @@ jobs:
 
       - name: Download and install loongarch64-toolchain
         run: |
-          wget https://github.com/loongson/build-tools/releases/download/2022.09.06/loongarch64-clfs-7.3-cross-tools-gcc-glibc.tar.xz
-          tar -xf loongarch64-clfs-7.3-cross-tools-gcc-glibc.tar.xz -C /opt
+          wget https://github.com/sunhaiyong1978/CLFS-for-LoongArch/releases/download/8.1/CLFS-loongarch64-8.1-x86_64-cross-tools-gcc-glibc.tar.xz
+          #wget https://github.com/loongson/build-tools/releases/download/2023.08.08/CLFS-loongarch64-8.1-x86_64-cross-tools-gcc-glibc.tar.xz
+          tar -xf CLFS-loongarch64-8.1-x86_64-cross-tools-gcc-glibc.tar.xz -C /opt
 
       - name: Set env
         run: |

CMakeLists.txt

@@ -8,7 +8,7 @@ project(OpenBLAS C ASM)
 
 set(OpenBLAS_MAJOR_VERSION 0)
 set(OpenBLAS_MINOR_VERSION 3)
-set(OpenBLAS_PATCH_VERSION 25.dev)
+set(OpenBLAS_PATCH_VERSION 26.dev)
 
 set(OpenBLAS_VERSION "${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.${OpenBLAS_PATCH_VERSION}")
 
@@ -256,15 +256,15 @@ if (APPLE AND BUILD_SHARED_LIBS AND CMAKE_HOST_SYSTEM_VERSION VERSION_LESS 20)
   set (CMAKE_Fortran_USE_RESPONSE_FILE_FOR_OBJECTS 1)
   set (CMAKE_Fortran_CREATE_SHARED_LIBRARY
  "sh -c 'cat ${CMAKE_BINARY_DIR}/CMakeFiles/openblas_shared.dir/objects*.rsp | xargs -n 1024 ${CMAKE_AR} -ru libopenblas.a && exit 0' "
- "sh -c '${CMAKE_AR} -ru libopenblas.a ${CMAKE_BINARY_DIR}/driver/others/CMakeFiles/driver_others.dir/xerbla.c.o && exit 0' "
+ "sh -c '${CMAKE_AR} -rs libopenblas.a ${CMAKE_BINARY_DIR}/driver/others/CMakeFiles/driver_others.dir/xerbla.c.o && exit 0' "
  "sh -c 'echo \"\" | ${CMAKE_Fortran_COMPILER} -o dummy.o -c -x f95-cpp-input - '"
- "sh -c '${CMAKE_Fortran_COMPILER} -fpic -shared -Wl,-all_load -Wl,-force_load,libopenblas.a -Wl,-noall_load dummy.o -undefined dynamic_lookup -o ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libopenblas.${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.dylib'"
+ "sh -c '${CMAKE_Fortran_COMPILER} -fpic -shared -Wl,-all_load -Wl,-force_load,libopenblas.a -Wl,-noall_load dummy.o -o ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libopenblas.${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.dylib'"
  "sh -c 'ls -l ${CMAKE_BINARY_DIR}/lib'")
   else ()
   set (CMAKE_C_CREATE_SHARED_LIBRARY
    "sh -c 'cat ${CMAKE_BINARY_DIR}/CMakeFiles/openblas_shared.dir/objects*.rsp | xargs -n 1024 ${CMAKE_AR} -ru libopenblas.a && exit 0' "
-   "sh -c '${CMAKE_AR} -ru libopenblas.a ${CMAKE_BINARY_DIR}/driver/others/CMakeFiles/driver_others.dir/xerbla.c.o && exit 0' "
-   "sh -c '${CMAKE_C_COMPILER} -fpic -shared -Wl,-all_load -Wl,-force_load,libopenblas.a -Wl,-noall_load -undefined dynamic_lookup -o ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libopenblas.${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.dylib'")
+   "sh -c '${CMAKE_AR} -rs libopenblas.a ${CMAKE_BINARY_DIR}/driver/others/CMakeFiles/driver_others.dir/xerbla.c.o && exit 0' "
+   "sh -c '${CMAKE_C_COMPILER} -fpic -shared -Wl,-all_load -Wl,-force_load,libopenblas.a -Wl,-noall_load -o ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libopenblas.${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.dylib'")
   endif ()
 endif()
 

CONTRIBUTORS.md

@@ -220,4 +220,6 @@ In chronological order:
 * Mark Seminatore <https://github.com/mseminatore>
   * [2023-11-09] Improve Windows threading performance scaling
   * [2024-02-09] Introduce MT_TRACE facility and improve code consistency
-  
+
+* Dirreke <https://github.com/mseminatore>
+  * [2024-01-16] Add basic support for the CSKY architecture

Changelog.txt

@@ -1,4 +1,49 @@
 OpenBLAS ChangeLog
+====================================================================
+Version 0.3.26
+ 2-Jan-2024
+
+general:
+- improved the version of openblas.pc that is created by the CMAKE build
+- fixed a CMAKE-specific build problem on older versions of MacOS
+- worked around linking problems on old versions of MacOS
+- corrected installation location of the lapacke_mangling header in CMAKE builds
+- added type declarations for complex variables to the MSVC-specific parts of the LAPACK header
+- significantly sped up ?GESV for small problem sizes by introducing a lower bound for multithreading
+- imported additions and corrections from the Reference-LAPACK project:
+  - added new LAPACK functions for truncated QR with pivoting (Reference-LAPACK PRs 891&941)
+  - handle miscalculation of minimum work array size in corner cases (Reference-LAPACK PR 942)
+  - fixed use of uninitialized variables in ?GEDMD and improved inline documentation (PR 959)
+  - fixed use of uninitialized variables (and consequential failures) in ?BBCSD (PR 967)
+  - added tests for the recently introduced Dynamic Mode Decomposition functions (PR 736)
+  - fixed several memory leaks in the LAPACK testsuite (PR 953)
+  - fixed counting of testsuite results by the Python script (PR 954)
+   
+x86-64:
+- fixed computation of CASUM on SkylakeX and newer targets in the special
+  case that AVX512 is not supported by the compiler or operating environment
+- fixed potential undefined behaviour in the CASUM/ZASUM kernels for AVX512 targets
+- worked around a problem in the pre-AVX kernels for GEMV
+- sped up the thread management code on MS Windows
+
+arm64:
+- fixed building of the LAPACK testsuite with Xcode 15 on Apple M1 and newer
+- sped up the thread management code on MS Windows
+- sped up SGEMM and DGEMM on Neoverse V1 and N1
+- sped up ?DOT on SVE-capable targets
+- reduced the number of targets in DYNAMIC_ARCH builds by eliminating functionally equivalent ones
+- included support for Apple M1 and newer targets in DYNAMIC_ARCH builds
+
+power:
+- improved the SGEMM kernel for POWER10
+- fixed compilation with (very) old versions of gcc
+- fixed detection of old 32bit PPC targets in CMAKE-based builds
+- added autodetection of the POWERPC 7400 subtype
+- fixed CMAKE-based compilation for PPCG4 and PPC970 targets
+
+loongarch64:
+- added and improved optimized kernels for almost all BLAS functions
+
 ====================================================================
 Version 0.3.25
  12-Nov-2023

Makefile.arm64

@@ -104,19 +104,25 @@ ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8.4-a -mtune=neoverse-v1
 endif
 else
-CCOMMON_OPT += -march=armv8.4-a+sve -mtune=native
+CCOMMON_OPT += -march=armv8.4-a+sve 
+ifneq ($(CROSS), 1)
+CCOMMON_OPT += -mtune=native
+endif
 ifneq ($(F_COMPILER), NAG)
-FCOMMON_OPT += -march=armv8.4-a -mtune=native
+FCOMMON_OPT += -march=armv8.4-a 
+ifneq ($(CROSS), 1)
+FCOMMON_OPT += -mtune=native
+endif
 endif
 endif
 else
-CCOMMON_OPT += -march=armv8.2-a -mtune=cortex-a72
+CCOMMON_OPT += -march=armv8.2-a+sve -mtune=cortex-a72
 ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8.2-a -mtune=cortex-a72
 endif
 endif
 else
-CCOMMON_OPT += -march=armv8-a -mtune=cortex-a72
+CCOMMON_OPT += -march=armv8-a+sve -mtune=cortex-a72
 ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8-a -mtune=cortex-a72
 endif
@@ -132,25 +138,31 @@ ifeq (1, $(filter 1,$(GCCMINORVERSIONGTEQ4) $(GCCVERSIONGTEQ11) $(ISCLANG)))
 ifneq ($(OSNAME), Darwin)
 CCOMMON_OPT += -march=armv8.5-a+sve+sve2+bf16 -mtune=neoverse-n2
 else
-CCOMMON_OPT += -march=armv8.2-a -mtune=cortex-a72
+CCOMMON_OPT += -march=armv8.2-a+sve -mtune=cortex-a72
 endif
 ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8.5-a+sve+sve2+bf16 -mtune=neoverse-n2
 endif
 else
-CCOMMON_OPT += -march=armv8.5-a+sve -mtune=native
+CCOMMON_OPT += -march=armv8.5-a+sve
+ifneq ($(CROSS), 1)
+CCOMMON_OPT += -mtune=native
+endif
 ifneq ($(F_COMPILER), NAG)
-FCOMMON_OPT += -march=armv8.5-a -mtune=native
+FCOMMON_OPT += -march=armv8.5-a 
+ifneq ($(CROSS), 1)
+FCOMMON_OPT += -mtune=native
+endif
 endif
 endif
 else
-CCOMMON_OPT += -march=armv8.2-a -mtune=cortex-a72
+CCOMMON_OPT += -march=armv8.2-a+sve -mtune=cortex-a72
 ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8.2-a -mtune=cortex-a72
 endif
 endif
 else
-CCOMMON_OPT += -march=armv8-a -mtune=cortex-a72
+CCOMMON_OPT += -march=armv8-a+sve -mtune=cortex-a72
 ifneq ($(F_COMPILER), NAG)
 FCOMMON_OPT += -march=armv8-a -mtune=cortex-a72
 endif

Makefile.csky

@@ -0,0 +1,4 @@
+ifeq ($(CORE), CK860FV)
+CCOMMON_OPT += -march=ck860v -mcpu=ck860fv -mfdivdu -mhard-float
+FCOMMON_OPT += -march=ck860v -mcpu=ck860fv -mfdivdu -mhard-float -static
+endif

Makefile.prebuild

@@ -55,6 +55,26 @@ ifeq ($(TARGET), C910V)
 TARGET_FLAGS = -march=rv64gcv0p7_zfh_xtheadc -mabi=lp64d
 endif
 
+ifeq ($(TARGET), CK860FV)
+TARGET_FLAGS = -march=ck860v -mcpu=ck860fv -mfdivdu -mhard-float
+endif
+
+ifeq ($(TARGET), x280)
+TARGET_FLAGS = -march=rv64imafdcv_zba_zbb_zfh -mabi=lp64d
+endif
+
+ifeq ($(TARGET), RISCV64_ZVL256B)
+TARGET_FLAGS = -march=rv64imafdcv -mabi=lp64d
+endif
+
+ifeq ($(TARGET), RISCV64_ZVL128B)
+TARGET_FLAGS = -march=rv64imafdcv -mabi=lp64d
+endif
+
+ifeq ($(TARGET), RISCV64_GENERIC)
+TARGET_FLAGS = -march=rv64imafdc -mabi=lp64d
+endif
+
 all: getarch_2nd
 	./getarch_2nd  0 >> $(TARGET_MAKE)
 	./getarch_2nd  1 >> $(TARGET_CONF)

Makefile.riscv64

@@ -2,3 +2,19 @@ ifeq ($(CORE), C910V)
 CCOMMON_OPT += -march=rv64imafdcv0p7_zfh_xtheadc -mabi=lp64d -mtune=c920
 FCOMMON_OPT += -march=rv64imafdcv0p7_zfh_xtheadc -mabi=lp64d -mtune=c920 -static
 endif
+ifeq ($(CORE), x280)
+CCOMMON_OPT += -march=rv64imafdcv_zba_zbb_zfh_zvl512b -mabi=lp64d -ffast-math
+FCOMMON_OPT += -march=rv64imafdcv_zba_zbb_zfh -mabi=lp64d -static
+endif
+ifeq ($(CORE), RISCV64_ZVL256B)
+CCOMMON_OPT += -march=rv64imafdcv_zvl256b -mabi=lp64d
+FCOMMON_OPT += -march=rv64imafdcv -mabi=lp64d -static
+endif
+ifeq ($(CORE), RISCV64_ZVL128B)
+CCOMMON_OPT += -march=rv64imafdcv -mabi=lp64d 
+FCOMMON_OPT += -march=rv64imafdcv -mabi=lp64d -static
+endif
+ifeq ($(CORE), RISCV64_GENERIC)
+CCOMMON_OPT += -march=rv64imafdc -mabi=lp64d
+FCOMMON_OPT += -march=rv64imafdc -mabi=lp64d -static
+endif

Makefile.rule

@@ -3,7 +3,7 @@
 #
 
 # This library's version
-VERSION = 0.3.25.dev
+VERSION = 0.3.26.dev
 
 # If you set the suffix, the library name will be libopenblas_$(LIBNAMESUFFIX).a
 # and libopenblas_$(LIBNAMESUFFIX).so. Meanwhile, the soname in shared library