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

Merge pull request #2896 from martin-frbg/intrin-double 

Add compiler flag for SSE4 where available
This commit is contained in:
Martin Kroeker 2020-10-15 11:12:35 +02:00 committed by GitHub
parent 9b9ee92d5f ae6ac83991
commit 4c25910da0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile.x86_64
View File

@ -16,6 +16,10 @@ ifdef HAVE_SSSE3
CCOMMON_OPT += -mssse3
FCOMMON_OPT += -mssse3
endif
ifdef HAVE_SSE4_1
CCOMMON_OPT += -msse4.1
FCOMMON_OPT += -msse4.1
endif
endif
endif

2
kernel/Makefile
View File

@ -45,7 +45,7 @@ endif
ifdef TARGET_CORE
ifeq ($(TARGET_CORE), $(filter $(TARGET_CORE),PRESCOTT CORE2 PENRYN DUNNINGTON ATOM NANO SANDYBRIDGE HASWELL NEHALEM ZEN BARCELONA BOBCAT BULLDOZER PILEDRIVER EXCAVATOR STEAMROLLER OPTERON_SSE3))
override CFLAGS += -msse3 -mssse3
override CFLAGS += -msse3 -mssse3 -msse4.1
endif
ifeq ($(TARGET_CORE), COOPERLAKE)
override CFLAGS += -DBUILD_KERNEL -DTABLE_NAME=gotoblas_$(TARGET_CORE)