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

Merge pull request #3104 from martin-frbg/issue3103 

Enable optimized Haswell/AVX2 kernels for sasum/dasum and srot/drot on Ryzen
This commit is contained in:
Martin Kroeker 2021-02-11 15:42:47 +01:00 committed by GitHub
parent f36862603a 47691c031f
commit 074d9bff7f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/x86_64/KERNEL.ZEN
View File

@ -97,3 +97,5 @@ ZTRSMKERNEL_RT = ../generic/trsm_kernel_RT.c
CGEMM3MKERNEL = cgemm3m_kernel_8x4_haswell.c
ZGEMM3MKERNEL = zgemm3m_kernel_4x4_haswell.c
SROTKERNEL = srot.c
DROTKERNEL = drot.c

2
kernel/x86_64/dasum.c
View File

@ -6,7 +6,7 @@
#if defined(SKYLAKEX)
#include "dasum_microk_skylakex-2.c"
#elif defined(HASWELL)
#elif defined(HASWELL) || defined(ZEN)
#include "dasum_microk_haswell-2.c"
#endif

2
kernel/x86_64/drot.c
View File

@ -2,7 +2,7 @@
#if defined(SKYLAKEX)
#include "drot_microk_skylakex-2.c"
#elif defined(HASWELL)
#elif defined(HASWELL) || defined(ZEN)
#include "drot_microk_haswell-2.c"
#endif

2
kernel/x86_64/sasum.c
View File

@ -11,7 +11,7 @@
#if defined(SKYLAKEX)
#include "sasum_microk_skylakex-2.c"
#elif defined(HASWELL)
#elif defined(HASWELL) || defined(ZEN)
#include "sasum_microk_haswell-2.c"
#endif

2
kernel/x86_64/srot.c
View File

@ -2,7 +2,7 @@
#if defined(SKYLAKEX)
#include "srot_microk_skylakex-2.c"
#elif defined(HASWELL)
#elif defined(HASWELL) || defined(ZEN)
#include "srot_microk_haswell-2.c"
#endif