amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-06-29 10:47:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Initialize block sizes for F32 element wise post-op APIs.

Browse Source 
-The block sizes and micro kernel dimensions for the F32OF32 group
of APIs are updated in the element wise operations cntx map.

AMD-Internal: [SWLCSG-3390]

Change-Id: Ic5690b7eb4f7b2559d893f374dd811b00e31e329
This commit is contained in:
Mithun Mohan
2025-02-11 10:08:28 +00:00
committed by Nallani Bhaskar
parent f4e3a4b1c3
commit 4cfbb47b87
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
addon/aocl_gemm/config/lpgemm_blksz_map.h
View File

@@ -70,8 +70,10 @@
#define LPGEMM_SUP_THRES_UPD_MAP_ZEN4_TO_ZEN \
STMACRO(F32F32F32OF32, 512, 200, 240) \
// Block sizes used only elementwise ops APIs
#define LPGEMM_ELTWISE_OPS_BLKSZ_MAP_ZEN4 \
XMACRO(BF16OF32, 144, 1024, 2048, 6, 64) \
XMACRO(F32OF32, 144, 1024, 2048, 6, 64) \
#define LPGEMM_ELTWISE_OPS_BLKSZ_MAP_ZEN