Browse Source

Update level3.c

tags/v0.3.8^2
wjc404 GitHub 6 years ago
parent
commit
1c3e20ce48
No known key found for this signature in database GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
  1. +5
    -2
      driver/level3/level3.c

+ 5
- 2
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();


Loading…
Cancel
Save