Skip to content

Fix more copy-paste errors in the haswell gemmsup code.#544

Merged
devinamatthews merged 2 commits intomasterfrom
haswell-gemmsup-fpe
Sep 16, 2021
Merged

Fix more copy-paste errors in the haswell gemmsup code.#544
devinamatthews merged 2 commits intomasterfrom
haswell-gemmsup-fpe

Conversation

@devinamatthews
Copy link
Copy Markdown
Member

Fixes #486.

…the Mx1 gemmsup kernels for haswell.

The fix is to use the same (valid) source register twice in the horizontal addition.
@devinamatthews devinamatthews merged commit b6f71fd into master Sep 16, 2021
@devinamatthews devinamatthews deleted the haswell-gemmsup-fpe branch September 16, 2021 17:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Netlib BLAS test xblat3d using BLIS on Intel Broadwell incorrectly signals IEEE_UNDERFLOW_FLAG IEEE_DENORMAL

1 participant