amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-13 10:35:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enabled optimised packed routines on zen3

Browse Source 
Change-Id: I5eb57f8ab2cccd20d0f778ada539fd1474cf6338
This commit is contained in:
managalv
2021-05-03 22:54:49 +05:30
committed by Mangala V
parent c1fa9abe32
commit c420bd63e2
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
config/zen3/bli_cntx_init_zen3.c
View File

@@ -65,12 +65,18 @@ void bli_cntx_init_zen3( cntx_t* cntx )
// packm kernels
bli_cntx_set_packm_kers
(
2,
BLIS_PACKM_8XK_KER, BLIS_DOUBLE, bli_dpackm_8xk_gen_zen,
BLIS_PACKM_6XK_KER, BLIS_DOUBLE, bli_dpackm_6xk_gen_zen,
cntx
);
(
8,
BLIS_PACKM_6XK_KER, BLIS_FLOAT, bli_spackm_haswell_asm_6xk,
BLIS_PACKM_16XK_KER, BLIS_FLOAT, bli_spackm_haswell_asm_16xk,
BLIS_PACKM_6XK_KER, BLIS_DOUBLE, bli_dpackm_haswell_asm_6xk,
BLIS_PACKM_8XK_KER, BLIS_DOUBLE, bli_dpackm_haswell_asm_8xk,
BLIS_PACKM_3XK_KER, BLIS_SCOMPLEX, bli_cpackm_haswell_asm_3xk,
BLIS_PACKM_8XK_KER, BLIS_SCOMPLEX, bli_cpackm_haswell_asm_8xk,
BLIS_PACKM_3XK_KER, BLIS_DCOMPLEX, bli_zpackm_haswell_asm_3xk,
BLIS_PACKM_4XK_KER, BLIS_DCOMPLEX, bli_zpackm_haswell_asm_4xk,
cntx
);
// Update the context with optimized level-1f kernels.
bli_cntx_set_l1f_kers