New 1-nn primitive using cutile - #2552
Open
divyegala wants to merge 8 commits into
Open
Conversation
divyegala
added
feature request
tarang-jain
reviewed
Sep 4, 2026
tarang-jain
reviewed
Sep 4, 2026
tarang-jain
reviewed
Sep 4, 2026
tarang-jain
reviewed
Sep 8, 2026
tarang-jain
reviewed
Sep 8, 2026
Unfortunately, when NVIDIA#2547 was merged, the docs had already managed to drift from the code. This commit catches them up.
tarang-jain
approved these changes
Sep 8, 2026
divyegala
force-pushed
the
cutile-1nn
branch
from
September 8, 2026 20:53
f503aed to
b974e89
Compare
KyleFromNVIDIA
requested changes
Sep 9, 2026
tfeher
requested changes
Sep 9, 2026
tfeher
left a comment
tfeher
left a comment
Contributor
There was a problem hiding this comment.
Thanks Divye for the PR! Looks good overall, I have only minor comments.
Comment on lines
+39
to
+40
| if (lhs_bytes > std::numeric_limits<std::uintptr_t>::max() - lhs_begin || | ||
| rhs_bytes > std::numeric_limits<std::uintptr_t>::max() - rhs_begin) { |
Contributor
There was a problem hiding this comment.
Is this just a theoretical possibility, or do we really have a system where this condition can actually be true?
Contributor
Author
There was a problem hiding this comment.
It is only theoretical, the main motivation was to check for aliasing of sub-views. I reworked it.
KyleFromNVIDIA
approved these changes
Sep 9, 2026
KyleFromNVIDIA
left a comment
KyleFromNVIDIA
left a comment
Member
There was a problem hiding this comment.
Looks good, just one small request. I don't need to approve again.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Relies on #2548. This PR also adds the three ways to do a 1-nn behind a new primitive called
top_1_nn.