Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Halevi-Shoup matvec kernel #1552

Open
wants to merge 11 commits into
base: main
Choose a base branch
from
Open

Halevi-Shoup matvec kernel #1552

wants to merge 11 commits into from

Conversation

j2kun
Copy link
Collaborator

@j2kun j2kun commented Mar 12, 2025

Rebased over #1428

@j2kun j2kun marked this pull request as draft March 12, 2025 16:09
@j2kun j2kun force-pushed the linalg-kernels branch 2 times, most recently from 97d03da to 6cce260 Compare March 14, 2025 18:26
j2kun added a commit to j2kun/heir that referenced this pull request Mar 19, 2025
Add gitattributes for bazel-provided merge conflict resolution
in the lockfile.

Added a patch to re2 (transitive dep via or-tools)
due to google/re2#525

Extracted from google#1552
@j2kun j2kun mentioned this pull request Mar 19, 2025
@j2kun j2kun force-pushed the linalg-kernels branch 2 times, most recently from 14643ef to 4a5006b Compare March 19, 2025 16:11
Copy link
Collaborator

@asraa asraa left a comment

Choose a reason for hiding this comment

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

Before I step into the two pass changes... (the attribute changes lgtm)

Comment on lines 87 to 88
values to pad at the end of that axis. The `paddingValue` attribute,
defaulting to zero, describes the value used for padding.
Copy link
Collaborator

Choose a reason for hiding this comment

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

Update here if you go the route of a possible unspecified padding - The paddingValue attr describes the value used for padding. If left unspecified, then the program will allow any value to be present in the padded slots.

Comment on lines +38 to +42
DenseSet<long> insertedDimsSet(insertedDims.asArrayRef().begin(),
insertedDims.asArrayRef().end());
if (insertedDimsSet.size() != insertedDims.size()) {
return emitError() << "insertedDims must all be unique";
}
Copy link
Collaborator

Choose a reason for hiding this comment

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

for the sake of verification, these probably should be within bounds as well? The code below that sets beforeReplication doesn't mind if they're out of range.

@j2kun j2kun marked this pull request as ready for review March 19, 2025 21:21
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