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

Update trmm_L.c

This commit is contained in:
wjc404 2020-02-05 10:09:41 +08:00 committed by GitHub
parent 77b8f49556
commit 833bd0f8ff
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
driver/level3/trmm_L.c
View File

@ -135,10 +135,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = js; jjs < js + min_j; jjs += min_jj){ for(jjs = js; jjs < js + min_j; jjs += min_jj){
min_jj = min_j + js - jjs; 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 the best performance */
if (min_jj >= 6*GEMM_UNROLL_N) min_jj = 6*GEMM_UNROLL_N;
#else
if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3; if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3;
else else
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N; if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
#endif
START_RPCC(); START_RPCC();
GEMM_ONCOPY(min_l, min_jj, b + (jjs * ldb) * COMPSIZE, ldb, sb + min_l * (jjs - js) * COMPSIZE); GEMM_ONCOPY(min_l, min_jj, b + (jjs * ldb) * COMPSIZE, ldb, sb + min_l * (jjs - js) * COMPSIZE);
@ -201,10 +205,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = js; jjs < js + min_j; jjs += min_jj){ for(jjs = js; jjs < js + min_j; jjs += min_jj){
min_jj = min_j + js - jjs; 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 the best performance */
if (min_jj >= 6*GEMM_UNROLL_N) min_jj = 6*GEMM_UNROLL_N;
#else
if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3; if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3;
else else
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N; if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
#endif
START_RPCC(); START_RPCC();
GEMM_ONCOPY(min_l, min_jj, b + (ls + jjs * ldb) * COMPSIZE, ldb, sb + min_l * (jjs - js) * COMPSIZE); GEMM_ONCOPY(min_l, min_jj, b + (ls + jjs * ldb) * COMPSIZE, ldb, sb + min_l * (jjs - js) * COMPSIZE);
@ -292,10 +300,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = js; jjs < js + min_j; jjs += min_jj){ for(jjs = js; jjs < js + min_j; jjs += min_jj){
min_jj = min_j + js - jjs; 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 the best performance */
if (min_jj >= 6*GEMM_UNROLL_N) min_jj = 6*GEMM_UNROLL_N;
#else
if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3; if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3;
else else
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N; if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
#endif
START_RPCC(); START_RPCC();
GEMM_ONCOPY(min_l, min_jj, b + (m - min_l + jjs * ldb) * COMPSIZE, ldb, GEMM_ONCOPY(min_l, min_jj, b + (m - min_l + jjs * ldb) * COMPSIZE, ldb,
@ -358,10 +370,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = js; jjs < js + min_j; jjs += min_jj){ for(jjs = js; jjs < js + min_j; jjs += min_jj){
min_jj = min_j + js - jjs; 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 the best performance */
if (min_jj >= 6*GEMM_UNROLL_N) min_jj = 6*GEMM_UNROLL_N;
#else
if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3; if (min_jj > GEMM_UNROLL_N*3) min_jj = GEMM_UNROLL_N*3;
else else
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N; if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
#endif
START_RPCC(); START_RPCC();
GEMM_ONCOPY(min_l, min_jj, b + (ls - min_l + jjs * ldb) * COMPSIZE, ldb, GEMM_ONCOPY(min_l, min_jj, b + (ls - min_l + jjs * ldb) * COMPSIZE, ldb,