Skip to content

Commit 074d9bf

Browse files
authored
Merge pull request #3104 from martin-frbg/issue3103
Enable optimized Haswell/AVX2 kernels for sasum/dasum and srot/drot on Ryzen
2 parents f368626 + 47691c0 commit 074d9bf

File tree

5 files changed

+6
-4
lines changed

5 files changed

+6
-4
lines changed

kernel/x86_64/KERNEL.ZEN

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -97,3 +97,5 @@ ZTRSMKERNEL_RT = ../generic/trsm_kernel_RT.c
9797
CGEMM3MKERNEL = cgemm3m_kernel_8x4_haswell.c
9898
ZGEMM3MKERNEL = zgemm3m_kernel_4x4_haswell.c
9999

100+
SROTKERNEL = srot.c
101+
DROTKERNEL = drot.c

kernel/x86_64/dasum.c

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66

77
#if defined(SKYLAKEX)
88
#include "dasum_microk_skylakex-2.c"
9-
#elif defined(HASWELL)
9+
#elif defined(HASWELL) || defined(ZEN)
1010
#include "dasum_microk_haswell-2.c"
1111
#endif
1212

kernel/x86_64/drot.c

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
#if defined(SKYLAKEX)
44
#include "drot_microk_skylakex-2.c"
5-
#elif defined(HASWELL)
5+
#elif defined(HASWELL) || defined(ZEN)
66
#include "drot_microk_haswell-2.c"
77
#endif
88

kernel/x86_64/sasum.c

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111

1212
#if defined(SKYLAKEX)
1313
#include "sasum_microk_skylakex-2.c"
14-
#elif defined(HASWELL)
14+
#elif defined(HASWELL) || defined(ZEN)
1515
#include "sasum_microk_haswell-2.c"
1616
#endif
1717

kernel/x86_64/srot.c

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
#if defined(SKYLAKEX)
44
#include "srot_microk_skylakex-2.c"
5-
#elif defined(HASWELL)
5+
#elif defined(HASWELL) || defined(ZEN)
66
#include "srot_microk_haswell-2.c"
77
#endif
88

0 commit comments

Comments
 (0)