Skip to content

Conversation

@lezcano
Copy link
Contributor

@lezcano lezcano commented Nov 6, 2025

The previous code was a bit too eager adding reps in this case. So
much so that after doing that we wouldn't have enough registers as to
fully vectorise the ldmatrix/stmatrix

Fixes the regression reported in #8328

…trix

The previous code was a bit too eager adding `reps` in this case. So
much so that after doing that we wouldn't have enough registers as to
fully vectorise the ldmatrix/stmatrix

Fixes the regression reported in #8328
@lezcano lezcano requested a review from ptillet as a code owner November 6, 2025 17:39
@lezcano lezcano requested a review from ThomasRaoux November 6, 2025 17:39
Copy link
Collaborator

@ThomasRaoux ThomasRaoux left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@lezcano lezcano enabled auto-merge (squash) November 6, 2025 23:02
@lezcano lezcano merged commit a5b948c into main Nov 6, 2025
17 of 18 checks passed
@lezcano lezcano deleted the fully_vec_cvt branch November 6, 2025 23:18
jwu10003 pushed a commit to jwu10003/triton that referenced this pull request Nov 7, 2025
…trix (triton-lang#8655)

The previous code was a bit too eager adding `reps` in this case. So
much so that after doing that we wouldn't have enough registers as to
fully vectorise the ldmatrix/stmatrix

Fixes the regression reported in
triton-lang#8328
tmoreau89 pushed a commit to tmoreau89/triton that referenced this pull request Dec 1, 2025
…trix (triton-lang#8655)

The previous code was a bit too eager adding `reps` in this case. So
much so that after doing that we wouldn't have enough registers as to
fully vectorise the ldmatrix/stmatrix

Fixes the regression reported in
triton-lang#8328
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.

2 participants