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

Increase S/D GEMM PQ to match typical L2 size as forNeoverseV1

This commit is contained in:
Martin Kroeker 2024-01-02 18:46:21 +01:00 committed by GitHub
parent 534de14a02
commit 504f9b0c5e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
param.h
View File

@ -3359,13 +3359,13 @@ is a big desktop or server with abundant cache rather than a phone or embedded d
#define ZGEMM_DEFAULT_UNROLL_M 4 #define ZGEMM_DEFAULT_UNROLL_M 4
#define ZGEMM_DEFAULT_UNROLL_N 4 #define ZGEMM_DEFAULT_UNROLL_N 4
#define SGEMM_DEFAULT_P 128 #define SGEMM_DEFAULT_P 240
#define DGEMM_DEFAULT_P 160 #define DGEMM_DEFAULT_P 240
#define CGEMM_DEFAULT_P 128 #define CGEMM_DEFAULT_P 128
#define ZGEMM_DEFAULT_P 128 #define ZGEMM_DEFAULT_P 128
#define SGEMM_DEFAULT_Q 352 #define SGEMM_DEFAULT_Q 640
#define DGEMM_DEFAULT_Q 128 #define DGEMM_DEFAULT_Q 320
#define CGEMM_DEFAULT_Q 224 #define CGEMM_DEFAULT_Q 224
#define ZGEMM_DEFAULT_Q 112 #define ZGEMM_DEFAULT_Q 112