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

Fix the integer overflow issue for large matrix size 

For large matrix, e.g. M=N=K, and M>1290, int mnk=M*N*K will overflow.
This will lead to wrong branching to single-threading. The performance
is downgraded significantly.

Signed-off-by: Wang, Long <long1.wang@intel.com>
This commit is contained in:
Wang, Long 2019-11-20 11:50:37 +08:00
parent 73128f3883
commit 0caf1434c9
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/sgemm_kernel_16x4_skylakex.c
View File

@ -1215,7 +1215,7 @@ CNAME(BLASLONG m, BLASLONG n, BLASLONG k, float alpha, float * __restrict A, flo
int sgemm_kernel_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K) int sgemm_kernel_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K)
{ {
int mnk = M * N * K; unsigned long mnk = M * N * K;
/* large matrixes -> not performant */ /* large matrixes -> not performant */
if (mnk >= 28 * 512 * 512) if (mnk >= 28 * 512 * 512)
return 0; return 0;

2
kernel/x86_64/sgemm_kernel_16x4_skylakex_2.c
View File

@ -452,7 +452,7 @@ CNAME(BLASLONG m, BLASLONG n, BLASLONG k, float alpha, float * __restrict__ A, f
int sgemm_kernel_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K) int sgemm_kernel_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K)
{ {
int mnk = M * N * K; unsigned long mnk = M * N * K;
/* large matrixes -> not performant */ /* large matrixes -> not performant */
if (mnk >= 28 * 512 * 512) if (mnk >= 28 * 512 * 512)
return 0; return 0;