Bugfix on the memory access for nrm2 AVX2 implementations.

Browse Source

- Since the definition of negative increments is different between BLAS and BLIS,
  there was bug on how the memory was accessed when we were copying the elements
  of a vector with negative increments. Updated the code under the assumption that
  when negative increments are set, the vector is being accessed starting from the end.
  For the BLAS interface, there is an intermediate conversion before calling into the blis layer.

Change-Id: I08343472b418733fad6f7add9e90aa96cdf68285
AMD-Internal: [SWLCSG-1900]

...

This commit is contained in:

Eleni Vlachopoulou

2023-03-04 00:01:38 +05:30

committed by Eleni Vlachopoulou

parent 7dca25d056

commit 1416ab6b5e

1 changed files with 3039 additions and 3067 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

6106

kernels/zen/1/bli_norm2_zen_int.c

File diff suppressed because it is too large Load Diff