Merge remote-tracking branch 'origin/develop' into power10Copies

Author: Chip-Kerchner

.cirrus.yml

@@ -29,7 +29,7 @@ task:
   - mkdir build
   - cd build
   - cmake -DTARGET=VORTEX -DCMAKE_C_COMPILER=clang -DBUILD_SHARED_LIBS=ON ..
-  - make
+  - make -j 4
 
 task:
   name: AppleM1/GCC/MAKE/OPENMP

CMakeLists.txt

@@ -249,21 +249,22 @@ if (${CMAKE_SYSTEM_NAME} MATCHES "AIX|Android|Linux|FreeBSD|OpenBSD|NetBSD|Drago
   endif()
 endif()
 
-if (APPLE AND DYNAMIC_ARCH AND BUILD_SHARED_LIBS)
+# Seems that this hack doesn't required since macOS 11 Big Sur
+if (APPLE AND BUILD_SHARED_LIBS AND CMAKE_HOST_SYSTEM_VERSION VERSION_LESS 20)
   set (CMAKE_C_USE_RESPONSE_FILE_FOR_OBJECTS 1)
   if (NOT NOFORTRAN)
   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 ar -ru libopenblas.a && exit 0' "
- "sh -c 'ar -ru libopenblas.a ${CMAKE_BINARY_DIR}/driver/others/CMakeFiles/driver_others.dir/xerbla.c.o && exit 0' "
+ "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 '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 -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 -undefined dynamic_lookup -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 ar -ru libopenblas.a && exit 0' "
-   "sh -c '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 -o ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/libopenblas.${OpenBLAS_MAJOR_VERSION}.${OpenBLAS_MINOR_VERSION}.dylib'")
+   "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'")
   endif ()
 endif()
 
@@ -541,7 +542,7 @@ if(NOT NO_LAPACKE)
   ADD_CUSTOM_TARGET(genlapacke
   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 ${CMAKE_INSTALL_INCLUDEDIR}/openblas${SUFFIX64})
+  install (FILES ${CMAKE_BINARY_DIR}/lapacke_mangling.h DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
 endif()
 
 # Install pkg-config files

CONTRIBUTORS.md

@@ -216,3 +216,6 @@ In chronological order:
 
 * Pablo Romero <https://github.com/pablorcum>
   * [2022-08] Fix building from sources for QNX
+
+* Mark Seminatore <https://github.com/mseminatore>
+  * [2023-11-09] Improve Windows threading performance scaling

GotoBLAS_06WeirdPerformance.txt

@@ -11,7 +11,7 @@
    operation is finished.
 
 
-2. Simlar problem may happen under virtual machine. If supervisor
+2. Similar problem may happen under virtual machine. If supervisor
    allocates different cores for each scheduling, BLAS performnace
    will be bad. This is because BLAS also utilizes all cache,
    unexpected re-schedule for different core may result of heavy

Makefile.power

@@ -11,7 +11,19 @@ endif
 
 ifeq ($(CORE), POWER10)
 ifneq ($(C_COMPILER), PGI)
+ifeq ($(C_COMPILER), GCC)
+ifeq ($(GCCVERSIONGTEQ10), 1)
 CCOMMON_OPT += -Ofast -mcpu=power10 -mtune=power10 -mvsx -fno-fast-math
+else ifneq ($(GCCVERSIONGT4), 1)
+$(warning your compiler is too old to fully support POWER9, getting a newer version of gcc is recommended)
+CCOMMON_OPT += -Ofast -mcpu=power8 -mtune=power8 -mvsx -fno-fast-math
+else
+$(warning your compiler is too old to fully support POWER10, getting a newer version of gcc is recommended)
+CCOMMON_OPT += -Ofast -mcpu=power9 -mtune=power9 -mvsx -fno-fast-math
+endif
+else
+CCOMMON_OPT += -Ofast -mcpu=power10 -mtune=power10 -mvsx -fno-fast-math
+endif
 ifeq ($(F_COMPILER), IBM)
 FCOMMON_OPT += -O2 -qrecur -qnosave -qarch=pwr10 -qtune=pwr10 -qfloat=nomaf -qzerosize
 else

Makefile.system

@@ -407,6 +407,7 @@ XCVER = $(shell pkgutil --pkg-info=com.apple.pkg.CLTools_Executables |awk '/vers
 endif
 ifeq (x$(XCVER), x 15)
 CCOMMON_OPT += -Wl,-ld_classic
+FCOMMON_OPT += -Wl,-ld_classic
 endif
 endif
 

README.md

@@ -202,7 +202,7 @@ Please read `GotoBLAS_01Readme.txt` for older CPU models already supported by th
 
 OpenBLAS can be built for multiple targets with runtime detection of the target cpu by specifiying `DYNAMIC_ARCH=1` in Makefile.rule, on the gmake command line or as `-DDYNAMIC_ARCH=TRUE` in cmake.
 
-For **x86_64**, the list of targets this activates contains Prescott, Core2, Nehalem, Barcelona, Sandybridge, Bulldozer, Piledriver, Steamroller, Excavator, Haswell, Zen, SkylakeX. For cpu generations not included in this list, the corresponding older model is used. If you also specify `DYNAMIC_OLDER=1`, specific support for Penryn, Dunnington, Opteron, Opteron/SSE3, Bobcat, Atom and Nano is added. Finally there is an option `DYNAMIC_LIST` that allows to specify an individual list of targets to include instead of the default.
+For **x86_64**, the list of targets this activates contains Prescott, Core2, Nehalem, Barcelona, Sandybridge, Bulldozer, Piledriver, Steamroller, Excavator, Haswell, Zen, SkylakeX, Cooper Lake, Sapphire Rapids. For cpu generations not included in this list, the corresponding older model is used. If you also specify `DYNAMIC_OLDER=1`, specific support for Penryn, Dunnington, Opteron, Opteron/SSE3, Bobcat, Atom and Nano is added. Finally there is an option `DYNAMIC_LIST` that allows to specify an individual list of targets to include instead of the default.
 
 `DYNAMIC_ARCH` is also supported on **x86**, where it translates to Katmai, Coppermine, Northwood, Prescott, Banias,
 Core2, Penryn, Dunnington, Nehalem, Athlon, Opteron, Opteron_SSE3, Barcelona, Bobcat, Atom and Nano.

benchmark/trsv.c

@@ -127,7 +127,7 @@ int main(int argc, char *argv[]){
       long long muls = n*(n+1)/2.0;
       long long adds = (n - 1.0)*n/2.0;
 
-      fprintf(stderr, "%10d   %10.2f MFlops %10.6f sec\n", n,(muls+adds) / timeg * 1.e-6, timeg);
+      fprintf(stderr, "%10d :   %10.2f MFlops %10.6f sec\n", n,(muls+adds) / timeg * 1.e-6, timeg);
       if(a != NULL){
         free(a);
       }

c_check

@@ -199,8 +199,7 @@ if [ "$architecture" = "loongarch64" ]; then
     tmpd="$(mktemp -d)"
     tmplsx="$tmpd/lsx.c"
     codelsx='"vadd.b $vr0, $vr0, $vr0"'
-    lsx_flags='-march=loongarch64 -mlsx'
-    printf "#include <lsxintrin.h>\n\n" >> "$tmplsx"
+    lsx_flags='-march=loongarch64'
     printf "void main(void){ __asm__ volatile(%s);}\n" "$codelsx" >> "$tmplsx"
     args="$lsx_flags -o $tmplsx.o $tmplsx"
     {
@@ -211,8 +210,7 @@ if [ "$architecture" = "loongarch64" ]; then
 
     tmplasx="$tmpd/lasx.c"
     codelasx='"xvadd.b $xr0, $xr0, $xr0"'
-    lasx_flags='-march=loongarch64 -mlasx'
-    printf "#include <lasxintrin.h>\n\n" >> "$tmplasx"
+    lasx_flags='-march=loongarch64'
     printf "void main(void){ __asm__ volatile(%s);}\n" "$codelasx" >> "$tmplasx"
     args="$lasx_flags -o $tmplasx.o $tmplasx"
     {

c_check.pl

@@ -241,8 +241,7 @@
     } else {
 	$tmplsx = new File::Temp( SUFFIX => '.c' , UNLINK => 1 );
 	$codelsx = '"vadd.b $vr0, $vr0, $vr0"';
-	$lsx_flags = "-march=loongarch64 -mlsx";
-	print $tmplsx "#include <lsxintrin.h>\n\n";
+	$lsx_flags = "-march=loongarch64";
 	print $tmplsx "void main(void){ __asm__ volatile($codelsx); }\n";
 
 	$args = "$lsx_flags -o $tmplsx.o $tmplsx";
@@ -257,8 +256,7 @@
 
 	$tmplasx = new File::Temp( SUFFIX => '.c' , UNLINK => 1 );
 	$codelasx = '"xvadd.b $xr0, $xr0, $xr0"';
-	$lasx_flags = "-march=loongarch64 -mlasx";
-	print $tmplasx "#include <lasxintrin.h>\n\n";
+	$lasx_flags = "-march=loongarch64";
 	print $tmplasx "void main(void){ __asm__ volatile($codelasx); }\n";
 
 	$args = "$lasx_flags -o $tmplasx.o $tmplasx";