amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-04-20 07:38:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed kernel selection logic of DTRSM for zen5 architecture.

Browse Source 
- Instead of native, we are wrongly selecting TRSM small, now its fixed.

AMD-Internal: [SWLCSG-3338]
Change-Id: I7a06a483fd874c71562a924b50118e0fc9e3b213
This commit is contained in:
Shubham Sharma
2025-03-21 12:52:21 +00:00
committed by Shubham Sharma
parent eaa76dfe28
commit 350c7186e5
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
frame/compat/bla_trsm_amd.c
View File

@@ -1224,7 +1224,7 @@ void dtrsm_blis_impl
}
else //if ( blis_side == BLIS_RIGHT )
{
if ( n0 < 1812 || m0 < 3220 )
if ( (n0 < 1812 || m0 < 3220) && (m0 < 14000) )
{
ker_ft = bli_trsm_small_mt_ZEN5;
}