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

Merge pull request #3855 from Mousius/more-switch-ratio-tuning 

SWITCH_RATIO for Arm(R) Neoverse(TM) architecture
This commit is contained in:
Martin Kroeker 2023-04-18 22:45:51 +02:00 committed by GitHub
parent efcf71255a 5b165420b5
commit c628030669
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 18 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
param.h
View File

@ -1,5 +1,5 @@
/***************************************************************************** /*****************************************************************************
Copyright (c) 2011-2014, The OpenBLAS Project Copyright (c) 2011-2023, The OpenBLAS Project
All rights reserved. All rights reserved.
Redistribution and use in source and binary forms, with or without Redistribution and use in source and binary forms, with or without
@ -3338,6 +3338,12 @@ is a big desktop or server with abundant cache rather than a phone or embedded d
#elif defined(NEOVERSEN1) #elif defined(NEOVERSEN1)
#if defined(XDOUBLE) || defined(DOUBLE)
#define SWITCH_RATIO 8
#else
#define SWITCH_RATIO 16
#endif
#define SGEMM_DEFAULT_UNROLL_M 16 #define SGEMM_DEFAULT_UNROLL_M 16
#define SGEMM_DEFAULT_UNROLL_N 4 #define SGEMM_DEFAULT_UNROLL_N 4
@ -3367,7 +3373,11 @@ is a big desktop or server with abundant cache rather than a phone or embedded d
#elif defined(NEOVERSEV1) #elif defined(NEOVERSEV1)
#define SWITCH_RATIO 16 #if defined(XDOUBLE) || defined(DOUBLE)
#define SWITCH_RATIO 8
#else
#define SWITCH_RATIO 16
#endif
#define SGEMM_DEFAULT_UNROLL_M 16 #define SGEMM_DEFAULT_UNROLL_M 16
#define SGEMM_DEFAULT_UNROLL_N 4 #define SGEMM_DEFAULT_UNROLL_N 4
@ -3398,6 +3408,12 @@ is a big desktop or server with abundant cache rather than a phone or embedded d
#elif defined(NEOVERSEN2) #elif defined(NEOVERSEN2)
#if defined(XDOUBLE) || defined(DOUBLE)
#define SWITCH_RATIO 8
#else
#define SWITCH_RATIO 16
#endif
#undef SBGEMM_ALIGN_K #undef SBGEMM_ALIGN_K
#define SBGEMM_ALIGN_K 4 #define SBGEMM_ALIGN_K 4