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

Update trmm_R.c

This commit is contained in:
wjc404 2020-02-05 10:15:02 +08:00 committed by GitHub
parent 833bd0f8ff
commit 2f96a2c55b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 30 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
driver/level3/trmm_R.c
View File

@ -122,10 +122,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = 0; jjs < ls - js; jjs += min_jj){ for(jjs = 0; jjs < ls - js; jjs += min_jj){
min_jj = ls - js - jjs; min_jj = ls - 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
#ifndef TRANSA #ifndef TRANSA
GEMM_ONCOPY(min_l, min_jj, a + (ls + (js + jjs) * lda) * COMPSIZE, lda, sb + min_l * jjs * COMPSIZE); GEMM_ONCOPY(min_l, min_jj, a + (ls + (js + jjs) * lda) * COMPSIZE, lda, sb + min_l * jjs * COMPSIZE);
#else #else
@ -142,10 +146,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = 0; jjs < min_l; jjs += min_jj){ for(jjs = 0; jjs < min_l; jjs += min_jj){
min_jj = min_l - jjs; min_jj = min_l - 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
#ifndef TRANSA #ifndef TRANSA
TRMM_OLNCOPY(min_l, min_jj, a, lda, ls, ls + jjs, sb + min_l * (ls - js + jjs) * COMPSIZE); TRMM_OLNCOPY(min_l, min_jj, a, lda, ls, ls + jjs, sb + min_l * (ls - js + jjs) * COMPSIZE);
#else #else
@ -195,10 +203,14 @@ 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
#ifndef TRANSA #ifndef TRANSA
GEMM_ONCOPY(min_l, min_jj, a + (ls + jjs * lda) * COMPSIZE, lda, sb + min_l * (jjs - js) * COMPSIZE); GEMM_ONCOPY(min_l, min_jj, a + (ls + jjs * lda) * COMPSIZE, lda, sb + min_l * (jjs - js) * COMPSIZE);
#else #else
@ -246,10 +258,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = 0; jjs < min_l; jjs += min_jj){ for(jjs = 0; jjs < min_l; jjs += min_jj){
min_jj = min_l - jjs; min_jj = min_l - 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
#ifndef TRANSA #ifndef TRANSA
TRMM_OUNCOPY(min_l, min_jj, a, lda, ls, ls + jjs, sb + min_l * jjs * COMPSIZE); TRMM_OUNCOPY(min_l, min_jj, a, lda, ls, ls + jjs, sb + min_l * jjs * COMPSIZE);
#else #else
@ -267,10 +283,14 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, FLOAT *sa, FLO
for(jjs = 0; jjs < js - ls - min_l; jjs += min_jj){ for(jjs = 0; jjs < js - ls - min_l; jjs += min_jj){
min_jj = js - ls - min_l - jjs; min_jj = js - ls - min_l - 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
#ifndef TRANSA #ifndef TRANSA
GEMM_ONCOPY(min_l, min_jj, a + (ls + (ls + min_l + jjs) * lda) * COMPSIZE, lda, GEMM_ONCOPY(min_l, min_jj, a + (ls + (ls + min_l + jjs) * lda) * COMPSIZE, lda,
sb + min_l * (min_l + jjs) * COMPSIZE); sb + min_l * (min_l + jjs) * COMPSIZE);
@ -324,10 +344,14 @@ 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
#ifndef TRANSA #ifndef TRANSA
GEMM_ONCOPY(min_l, min_jj, a + (ls + (jjs - min_j) * lda) * COMPSIZE, lda, sb + min_l * (jjs - js) * COMPSIZE); GEMM_ONCOPY(min_l, min_jj, a + (ls + (jjs - min_j) * lda) * COMPSIZE, lda, sb + min_l * (jjs - js) * COMPSIZE);
#else #else