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

Merge 5f8744d4e4 into 453b9e4886

This commit is contained in:
Christopher Sidebottom 2024-11-02 12:55:04 +00:00 committed by GitHub
parent 453b9e4886 5f8744d4e4
commit 7f44d27bcc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
param.h
View File

@ -3671,8 +3671,10 @@ Until then, just keep it different than DGEMM_DEFAULT_UNROLL_N to keep copy rout
#if defined(XDOUBLE) || defined(DOUBLE)
#define SWITCH_RATIO 8
#define GEMM_PREFERED_SIZE 4
#else
#define SWITCH_RATIO 16
#define GEMM_PREFERED_SIZE 8
#endif
#define SGEMM_DEFAULT_UNROLL_M 4 // Actually 1VL (8) but kept seperate to keep copies seperate
@ -3689,13 +3691,13 @@ Until then, just keep it different than DGEMM_DEFAULT_UNROLL_N to keep copy rout
#define ZGEMM_DEFAULT_UNROLL_N 4
#define ZGEMM_DEFAULT_UNROLL_MN 16
#define SGEMM_DEFAULT_P 128
#define DGEMM_DEFAULT_P 160
#define SGEMM_DEFAULT_P 240
#define DGEMM_DEFAULT_P 240
#define CGEMM_DEFAULT_P 128
#define ZGEMM_DEFAULT_P 128
#define SGEMM_DEFAULT_Q 352
#define DGEMM_DEFAULT_Q 128
#define SGEMM_DEFAULT_Q 640
#define DGEMM_DEFAULT_Q 320
#define CGEMM_DEFAULT_Q 224
#define ZGEMM_DEFAULT_Q 112
@ -3706,6 +3708,14 @@ Until then, just keep it different than DGEMM_DEFAULT_UNROLL_N to keep copy rout
#else /* Other/undetected ARMv8 cores */
#if defined(XDOUBLE) || defined(DOUBLE)
#define SWITCH_RATIO 8
#define GEMM_PREFERED_SIZE 4
#else
#define SWITCH_RATIO 16
#define GEMM_PREFERED_SIZE 8
#endif
#define SGEMM_DEFAULT_UNROLL_M 16
#define SGEMM_DEFAULT_UNROLL_N 4
@ -3718,13 +3728,13 @@ Until then, just keep it different than DGEMM_DEFAULT_UNROLL_N to keep copy rout
#define ZGEMM_DEFAULT_UNROLL_M 4
#define ZGEMM_DEFAULT_UNROLL_N 4
#define SGEMM_DEFAULT_P 128
#define DGEMM_DEFAULT_P 160
#define SGEMM_DEFAULT_P 240
#define DGEMM_DEFAULT_P 240
#define CGEMM_DEFAULT_P 128
#define ZGEMM_DEFAULT_P 128
#define SGEMM_DEFAULT_Q 352
#define DGEMM_DEFAULT_Q 128
#define SGEMM_DEFAULT_Q 640
#define DGEMM_DEFAULT_Q 320
#define CGEMM_DEFAULT_Q 224
#define ZGEMM_DEFAULT_Q 112