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

Fixed align problem in S and C precision GEMM kernels.

This commit is contained in:
wangqian 2012-06-20 07:38:39 +08:00
parent 3ef96aa567
commit 6cfcb54a28
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/x86_64/cgemm_kernel_4x8_sandy.S
View File

@ -3578,7 +3578,7 @@ ADDQ $8*SIZE, ptrba;
ADDQ $16*SIZE, ptrbb; ADDQ $16*SIZE, ptrbb;
DECQ k; DECQ k;
JG .L241_bodyB; JG .L241_bodyB;
.align ALIGN_5
.L241_loopE: .L241_loopE:
#ifndef TRMMKERNEL #ifndef TRMMKERNEL
TEST $2, bk; TEST $2, bk;

2
kernel/x86_64/sgemm_kernel_8x8_sandy.S
View File

@ -2412,7 +2412,7 @@ ADDQ $4*SIZE, ptrba;
ADDQ $16*SIZE, ptrbb; ADDQ $16*SIZE, ptrbb;
DECQ k; DECQ k;
JG .L241_bodyB; JG .L241_bodyB;
.align ALIGN_4
.L241_loopE: .L241_loopE:
#ifndef TRMMKERNEL #ifndef TRMMKERNEL
TEST $2, bk; TEST $2, bk;