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

Update level3.c

This commit is contained in:
wjc404 2020-02-04 20:30:23 +08:00 committed by GitHub
parent 83b6be7976
commit 1c3e20ce48
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
driver/level3/level3.c
View File

@ -332,13 +332,16 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n,
#else
for(jjs = js; jjs < js + min_j; jjs += min_jj){
min_jj = min_j + js - jjs;
#ifdef SKYLAKEX
/* the current AVX512 s/d/c/z GEMM kernel requires n>=6*GEMM_UNROLL_N to achieve best performance */
if (min_jj >= 6*GEMM_UNROLL_N) min_jj = 6*GEMM_UNROLL_N;
#else
if (min_jj >= 3*GEMM_UNROLL_N) min_jj = 3*GEMM_UNROLL_N;
else
if (min_jj >= 2*GEMM_UNROLL_N) min_jj = 2*GEMM_UNROLL_N;
else
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
#endif
START_RPCC();