Update trmm_L.c
This commit is contained in:
parent
77b8f49556
commit
833bd0f8ff
|
@ -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){
|
||||
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;
|
||||
else
|
||||
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
|
||||
|
||||
#endif
|
||||
START_RPCC();
|
||||
|
||||
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){
|
||||
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;
|
||||
else
|
||||
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
|
||||
|
||||
#endif
|
||||
START_RPCC();
|
||||
|
||||
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){
|
||||
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;
|
||||
else
|
||||
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
|
||||
|
||||
#endif
|
||||
START_RPCC();
|
||||
|
||||
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){
|
||||
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;
|
||||
else
|
||||
if (min_jj > GEMM_UNROLL_N) min_jj = GEMM_UNROLL_N;
|
||||
|
||||
#endif
|
||||
START_RPCC();
|
||||
|
||||
GEMM_ONCOPY(min_l, min_jj, b + (ls - min_l + jjs * ldb) * COMPSIZE, ldb,
|
||||
|
|
Loading…
Reference in New Issue