floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

optimized dgemm for 20 threads

Browse Source
This commit is contained in:
Werner Saar
2016-05-16 14:14:25 +02:00
parent 0d1c695508
commit 8310d4d3f7
5 changed files with 191 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile.power
View File

@@ -13,10 +13,10 @@ endif
ifeq ($(CORE), POWER8)
ifeq ($(USE_OPENMP), 1)
COMMON_OPT += -Ofast -mcpu=power8 -mtune=power8 -mvsx -malign-power -DALLOC_SHM -DUSE_OPENMP -fno-fast-math -fopenmp
COMMON_OPT += -Ofast -mcpu=power8 -mtune=power8 -mvsx -malign-power -DUSE_OPENMP -fno-fast-math -fopenmp
FCOMMON_OPT += -O2 -frecursive -mcpu=power8 -mtune=power8 -malign-power -DUSE_OPENMP -fno-fast-math -fopenmp
else
COMMON_OPT += -Ofast -mcpu=power8 -mtune=power8 -mvsx -malign-power -DALLOC_SHM -fno-fast-math
COMMON_OPT += -Ofast -mcpu=power8 -mtune=power8 -mvsx -malign-power -fno-fast-math
FCOMMON_OPT += -O2 -frecursive -mcpu=power8 -mtune=power8 -malign-power -fno-fast-math
endif
endif