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

s390x: Use new sgemm kernel also for DGEMM and DTRMM on Z14 

Apply our new GEMM kernel implementation, written in C with vector intrinsics,
also for DGEMM and DTRMM on Z14 and newer (i.e., architectures with FP32 SIMD
instructions). As a result, we gain around 10% in performance on z15, in
addition to improving maintainability.

Signed-off-by: Marius Hillenbrand <mhillen@linux.ibm.com>
This commit is contained in:
Marius Hillenbrand 2020-05-19 14:56:34 +02:00
parent bdd795ed03
commit 89fe17f20e
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
kernel/zarch/KERNEL.Z14
View File

@ -87,7 +87,7 @@ CGEMVTKERNEL = cgemv_t_4.c
ZGEMVTKERNEL = zgemv_t_4.c ZGEMVTKERNEL = zgemv_t_4.c
STRMMKERNEL = gemm_vec.c STRMMKERNEL = gemm_vec.c
DTRMMKERNEL = trmm8x4V.S DTRMMKERNEL = gemm_vec.c
CTRMMKERNEL = ctrmm4x4V.S CTRMMKERNEL = ctrmm4x4V.S
ZTRMMKERNEL = ztrmm4x4V.S ZTRMMKERNEL = ztrmm4x4V.S
@ -103,7 +103,7 @@ SGEMMOTCOPY = ../generic/gemm_tcopy_$(SGEMM_UNROLL_N).c
SGEMMONCOPYOBJ = sgemm_oncopy$(TSUFFIX).$(SUFFIX) SGEMMONCOPYOBJ = sgemm_oncopy$(TSUFFIX).$(SUFFIX)
SGEMMOTCOPYOBJ = sgemm_otcopy$(TSUFFIX).$(SUFFIX) SGEMMOTCOPYOBJ = sgemm_otcopy$(TSUFFIX).$(SUFFIX)
DGEMMKERNEL = gemm8x4V.S DGEMMKERNEL = gemm_vec.c
DGEMMINCOPY = ../generic/gemm_ncopy_8.c DGEMMINCOPY = ../generic/gemm_ncopy_8.c
DGEMMITCOPY = ../generic/gemm_tcopy_8.c DGEMMITCOPY = ../generic/gemm_tcopy_8.c
DGEMMONCOPY = ../generic/gemm_ncopy_4.c DGEMMONCOPY = ../generic/gemm_ncopy_4.c