Merge pull request #3033 from xianyi/develop

Update branch from develop to release 0.3.13

Author: martin-frbg

.travis.yml

@@ -211,44 +211,48 @@ matrix:
 
     - &test-macos
       os: osx
-      osx_image: xcode10.1
+      osx_image: xcode11.5
       before_script:
         - COMMON_FLAGS="DYNAMIC_ARCH=1 NUM_THREADS=32"
-        - brew update
-        - brew install gcc@8 # for gfortran
       script:
         - travis_wait 45 make QUIET_MAKE=1 $COMMON_FLAGS $BTYPE
       env:
-        - BTYPE="TARGET=NEHALEM BINARY=64 INTERFACE64=1 FC=gfortran-8"
+        - BTYPE="TARGET=NEHALEM BINARY=64 INTERFACE64=1 FC=gfortran-9"
 
     - <<: *test-macos
       osx_image: xcode12
       before_script:
         - COMMON_FLAGS="DYNAMIC_ARCH=1 NUM_THREADS=32"
         - brew update
-        - brew install gcc@10 # for gfortran
+        - brew install gcc@10
       script:
         - travis_wait 45 make QUIET_MAKE=1 $COMMON_FLAGS $BTYPE
       env:
         - BTYPE="TARGET=NEHALEM BINARY=64 INTERFACE64=1 FC=gfortran-10"
 
-    - <<: *test-macos
-      osx_image: xcode10.0
-      env:
-        - BTYPE="TARGET=NEHALEM BINARY=32 NOFORTRAN=1"
+  #  - <<: *test-macos
+  #    osx_image: xcode10
+  #    env:
+  #      - BTYPE="TARGET=NEHALEM BINARY=32 NOFORTRAN=1"
 
     - <<: *test-macos
-      osx_image: xcode10.1
+      osx_image: xcode11.5
+      before_script:
+        - COMMON_FLAGS="DYNAMIC_ARCH=1 NUM_THREADS=32"
+        - brew update
       env:
-        - CC="/Applications/Xcode-10.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
-        - CFLAGS="-O2 -Wno-macro-redefined -isysroot /Applications/Xcode-10.1.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS12.1.sdk -arch arm64 -miphoneos-version-min=10.0"
+#        - CC="/Applications/Xcode-10.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
+#        - CFLAGS="-O2 -Wno-macro-redefined -isysroot /Applications/Xcode-10.1.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS12.1.sdk -arch arm64 -miphoneos-version-min=10.0"
+        - CC="/Applications/Xcode-11.5.GM.Seed.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
+        - CFLAGS="-O2 -Wno-macro-redefined -isysroot /Applications/Xcode-11.5.GM.Seed.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS13.5.sdk -arch arm64 -miphoneos-version-min=10.0"
         - BTYPE="TARGET=ARMV8 BINARY=64 HOSTCC=clang NOFORTRAN=1"
-
     - <<: *test-macos
-      osx_image: xcode10.1
+      osx_image: xcode11.5
       env:
-        - CC="/Applications/Xcode-10.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
-        - CFLAGS="-O2 -mno-thumb -Wno-macro-redefined -isysroot /Applications/Xcode-10.1.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS12.1.sdk -arch armv7 -miphoneos-version-min=5.1"
+#        - CC="/Applications/Xcode-10.1.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
+#        - CFLAGS="-O2 -mno-thumb -Wno-macro-redefined -isysroot /Applications/Xcode-10.1.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS12.1.sdk -arch armv7 -miphoneos-version-min=5.1"
+        - CC="/Applications/Xcode-11.5.GM.Seed.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/clang"
+        - CFLAGS="-O2 -mno-thumb -Wno-macro-redefined -isysroot /Applications/Xcode-11.5.GM.Seed.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS13.5.sdk -arch armv7 -miphoneos-version-min=5.1"
         - BTYPE="TARGET=ARMV7 HOSTCC=clang NOFORTRAN=1"
 
     - &test-graviton2

CMakeLists.txt

@@ -6,7 +6,7 @@ cmake_minimum_required(VERSION 2.8.5)
 project(OpenBLAS C ASM)
 set(OpenBLAS_MAJOR_VERSION 0)
 set(OpenBLAS_MINOR_VERSION 3)
-set(OpenBLAS_PATCH_VERSION 12)
+set(OpenBLAS_PATCH_VERSION 13)
 set(OpenBLAS_VERSION "${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.${OpenBLAS_PATCH_VERSION}")
 
 # Adhere to GNU filesystem layout conventions

CONTRIBUTORS.md

@@ -190,4 +190,7 @@ In chronological order:
   * [2020-09-07] Fix builds with clang on IBM z, including dynamic architecture support
 
 * Danfeng Zhang <https://github.com/craft-zhang>
-  * [2020-05-20] Improve performance of SGEMM and STRMM on Arm Cortex-A53
+  * [2020-05-20] Improve performance of SGEMM and STRMM on Arm Cortex-A53
+
+* PingTouGe Semiconductor Co., Ltd.
+  * [2020-10] Add RISC-V Vector (0.7.1) support. Optimize BLAS kernels for Xuantie C910

Changelog.txt

@@ -1,4 +1,54 @@
 OpenBLAS ChangeLog
+====================================================================
+Version 0.3.13
+ 12-Dec-2020
+ 
+ common:
+	* Added a generic bfloat16 SBGEMV kernel
+	* Fixed a potentially severe memory leak after fork in OpenMP builds
+	  that was introduced in 0.3.12
+	* Added detection of the Fujitsu Fortran compiler
+	* Added detection of the (e)gfortran compiler on OpenBSD
+	* Added support for overriding the default name of the library independently
+	  from symbol suffixing in the gmake builds (already supported in cmake)
+
+RISCV:
+	* Added a RISC V port optimized for C910V
+
+POWER:
+	* Added optimized POWER10 kernels for SAXPY, CAXPY, SDOT, DDOT and DGEMV_N
+	* Improved DGEMM performance on POWER10
+	* Improved STRSM and DTRSM performance on POWER9 and POWER10
+	* Fixed segmemtation faults in DYNAMIC_ARCH builds
+ 	* Fixed compilation with the PGI compiler
+
+x86:
+	* Fixed compilation of kernels that require SSE2 intrinsics since 0.3.12
+	
+x86_64:
+	* Added an optimized bfloat16 SBGEMV kernel for SkylakeX and Cooperlake
+	* Improved the performance of SASUM and DASUM kernels through parallelization
+	* Improved the performance of SROT and DROT kernels
+	* Improved the performance of multithreaded xSYRK
+	* Fixed OpenMP builds that use the LLVM Clang compiler together with GNU gfortran
+	  (where linking of both the LLVM libomp and GNU libgomp could lead to lockups or
+	  wrong results)
+	* Fixed miscompilations by old gcc 4.6
+	* Fixed misdetection of AVX2 capability in some Sandybridge cpus
+	* Fixed lockups in builds combining DYNAMIC_ARCH with TARGET=GENERIC on OpenBSD
+
+ARM64:
+	* Fixed segmemtation faults in DYNAMIC_ARCH builds
+
+MIPS:
+	* Improved kernels for Loongson 3R3 ("3A") and 3R4 ("3B") models, including MSA
+	* Fixed bugs in the MSA kernels for CGEMM, CTRMM, CGEMV and ZGEMV
+	* Added handling of zero increments in the MSA kernels for SSWAP and DSWAP
+	* Added DYNAMIC_ARCH support for MIPS64 (currently Loongson3R3/3R4 only)
+
+SPARC:
+	* Fixed building 32 and 64 bit SPARC kernels with the SolarisStudio compilers
+
 ====================================================================
 Version 0.3.12
  24-Oct-2020

Makefile

@@ -268,7 +268,11 @@ ifeq ($(NOFORTRAN), $(filter 0,$(NOFORTRAN)))
 	-@echo "POPTS       = $(LAPACK_FPFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "FFLAGS_NOOPT       = -O0 $(LAPACK_NOOPT)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "PNOOPT      = $(LAPACK_FPFLAGS) -O0" >> $(NETLIB_LAPACK_DIR)/make.inc
+ifeq ($(C_COMPILER)$(F_COMPILER)$(USE_OPENMP), CLANGGFORTRAN1)
+	-@echo "LDFLAGS     = $(FFLAGS) $(EXTRALIB) -lomp" >> $(NETLIB_LAPACK_DIR)/make.inc
+else
 	-@echo "LDFLAGS     = $(FFLAGS) $(EXTRALIB)" >> $(NETLIB_LAPACK_DIR)/make.inc
+endif
 	-@echo "CC          = $(CC)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "override CFLAGS      = $(LAPACK_CFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "AR          = $(AR)" >> $(NETLIB_LAPACK_DIR)/make.inc

Makefile.arm

@@ -12,3 +12,8 @@ ifeq ($(CORE), ARMV6)
 CCOMMON_OPT += -mfpu=vfp
 FCOMMON_OPT += -mfpu=vfp
 endif
+
+ifdef HAVE_NEON
+CCOMMON_OPT += -mfpu=neon
+FCOMMON_OPT += -mfpu=neon
+endif

Makefile.install

@@ -9,7 +9,7 @@ OPENBLAS_INCLUDE_DIR := $(PREFIX)/include
 OPENBLAS_LIBRARY_DIR := $(PREFIX)/lib
 OPENBLAS_BINARY_DIR := $(PREFIX)/bin
 OPENBLAS_BUILD_DIR := $(CURDIR)
-OPENBLAS_CMAKE_DIR := $(OPENBLAS_LIBRARY_DIR)/cmake/openblas
+OPENBLAS_CMAKE_DIR := $(OPENBLAS_LIBRARY_DIR)/cmake/$(LIBSONAMEBASE)
 OPENBLAS_CMAKE_CONFIG := OpenBLASConfig.cmake
 OPENBLAS_CMAKE_CONFIG_VERSION := OpenBLASConfigVersion.cmake
 OPENBLAS_PKGCONFIG_DIR := $(OPENBLAS_LIBRARY_DIR)/pkgconfig
@@ -150,13 +150,13 @@ endif
 endif
 
 #Generating openblas.pc
-	@echo Generating openblas.pc in "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)"
-	@echo 'libdir='$(OPENBLAS_LIBRARY_DIR) > "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
-	@echo 'includedir='$(OPENBLAS_INCLUDE_DIR) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
-	@echo 'openblas_config= USE_64BITINT='$(USE_64BITINT) 'DYNAMIC_ARCH='$(DYNAMIC_ARCH) 'DYNAMIC_OLDER='$(DYNAMIC_OLDER) 'NO_CBLAS='$(NO_CBLAS) 'NO_LAPACK='$(NO_LAPACK) 'NO_LAPACKE='$(NO_LAPACKE) 'NO_AFFINITY='$(NO_AFFINITY) 'USE_OPENMP='$(USE_OPENMP) $(CORE) 'MAX_THREADS='$(NUM_THREADS)>> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
-	@echo 'version='$(VERSION) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
-	@echo 'extralib='$(PKG_EXTRALIB) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
-	@cat openblas.pc.in >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/openblas.pc"
+	@echo Generating $(LIBSONAMEBASE).pc in "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)"
+	@echo 'libdir='$(OPENBLAS_LIBRARY_DIR) > "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
+	@echo 'includedir='$(OPENBLAS_INCLUDE_DIR) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
+	@echo 'openblas_config= USE_64BITINT='$(USE_64BITINT) 'DYNAMIC_ARCH='$(DYNAMIC_ARCH) 'DYNAMIC_OLDER='$(DYNAMIC_OLDER) 'NO_CBLAS='$(NO_CBLAS) 'NO_LAPACK='$(NO_LAPACK) 'NO_LAPACKE='$(NO_LAPACKE) 'NO_AFFINITY='$(NO_AFFINITY) 'USE_OPENMP='$(USE_OPENMP) $(CORE) 'MAX_THREADS='$(NUM_THREADS)>> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
+	@echo 'version='$(VERSION) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
+	@echo 'extralib='$(PKG_EXTRALIB) >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
+	@cat openblas.pc.in >> "$(DESTDIR)$(OPENBLAS_PKGCONFIG_DIR)/$(LIBSONAMEBASE).pc"
 
 
 #Generating OpenBLASConfig.cmake

Makefile.prebuild

@@ -41,6 +41,10 @@ ifeq ($(TARGET), I6500)
 TARGET_FLAGS = -mips64r6
 endif
 
+ifeq ($(TARGET), C910V)
+TARGET_FLAGS = -march=rv64gcvxthead -mabi=lp64v
+endif
+
 all: getarch_2nd
 	./getarch_2nd  0 >> $(TARGET_MAKE)
 	./getarch_2nd  1 >> $(TARGET_CONF)

Makefile.riscv64

@@ -0,0 +1,4 @@
+ifeq ($(CORE), C910V)
+CCOMMON_OPT += -march=rv64gcvxthead -mabi=lp64v
+FCOMMON_OPT += -march=rv64gcvxthead -mabi=lp64v -static
+endif

Makefile.rule

@@ -3,7 +3,7 @@
 #
 
 # This library's version
-VERSION = 0.3.12
+VERSION = 0.3.13
 
 # If you set the suffix, the library name will be libopenblas_$(LIBNAMESUFFIX).a
 # and libopenblas_$(LIBNAMESUFFIX).so. Meanwhile, the soname in shared library