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

improve skylakex paralleled sgemm performance

This commit is contained in:
wjc404 2020-01-13 16:26:03 +08:00 committed by GitHub
parent 3a100b2797
commit 1c67567008
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
param.h
View File

@ -1690,18 +1690,13 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#else #else
#define SGEMM_DEFAULT_P 768 #define SGEMM_DEFAULT_P 640
#define DGEMM_DEFAULT_P 384 #define DGEMM_DEFAULT_P 384
#define CGEMM_DEFAULT_P 384 #define CGEMM_DEFAULT_P 384
#define ZGEMM_DEFAULT_P 256 #define ZGEMM_DEFAULT_P 256
#ifdef WINDOWS_ABI #define SGEMM_DEFAULT_Q 320
#define SGEMM_DEFAULT_Q 192
#define DGEMM_DEFAULT_Q 168 #define DGEMM_DEFAULT_Q 168
#else
#define SGEMM_DEFAULT_Q 192
#define DGEMM_DEFAULT_Q 168
#endif
#define CGEMM_DEFAULT_Q 192 #define CGEMM_DEFAULT_Q 192
#define ZGEMM_DEFAULT_Q 128 #define ZGEMM_DEFAULT_Q 128