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

Update level3_thread.c

This commit is contained in:
wjc404 2020-02-04 20:33:08 +08:00 committed by GitHub
parent 1c3e20ce48
commit 77b8f49556
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
driver/level3/level3_thread.c
View File

@ -365,12 +365,16 @@ static int inner_thread(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n,
/* Split local region of B into parts */
for(jjs = js; jjs < MIN(n_to, js + div_n); jjs += min_jj){
min_jj = MIN(n_to, js + div_n) - jjs;
#ifdef SKYLAKEX
/* the current AVX512 s/d/c/z GEMM kernel requires n>=6*GEMM_UNROLL_N to achieve the 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
/* Copy part of local region of B into workspace */
START_RPCC();
OCOPY_OPERATION(min_l, min_jj, b, ldb, ls, jjs,