amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-04-19 23:28:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed undefined behavior trsm ukr bug in bdd46f9.

Browse Source 
Details:
- Fixed a bug that mainfested anytime a configuration was used in which
  optimized microkernels were registered and the trsm operation (or
  kernel) was invoked. The bug resulted from the optimized microkernels'
  register blocksizes conflicting with the hard-coded values--expressed
  in the form of constant loop bounds--used in the new reference trsm
  ukernels that were introduced in bdd46f9. The fix was easy: reverting
  back to the implementation that uses variable-bound loops, which
  amounted to changing an #if 0 to #if 1 (since I preserved the older
  implementation in the file alongside the new code based on constant-
  bound loops). It should be noted that this fix must be permanent,
  since the trsm kernel code with constant-bound loops can never work
  with gemm ukernels that use different register blocksizes.
This commit is contained in:
Field G. Van Zee
2019-01-24 18:01:15 -06:00
parent bdd46f9ee8
commit 180f8e42e1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ref_kernels/3/bli_trsm_ref.c
View File

@@ -34,7 +34,7 @@
#include "blis.h"
#if 1
#if 0
// An implementation that attempts to facilitate emission of vectorized
// instructions via constant loop bounds + #pragma omp simd directives.