Fix event dependency bugs and initial displacement initialization - #3072
Merged
Merged
Conversation
ndgrigorian
requested review from
antonwolfy and
vlad-perevezentsev
as code owners
September 19, 2026 05:59
Contributor
|
View rendered docs @ https://intelpython.github.io/dpnp/index.html |
Collaborator
Contributor
|
Array API standard conformance tests for dpnp=0.21.0dev11=py314ha0e2e8e_9 ran successfully. |
The strided kernel of `full` was launched waiting only on the event which copies the packed shape and strides to the device, dropping dependent events passed to the binding removed unnecessary events added to `copy_for_reshape` `simplify_iteration_three_strides` and `simplify_iteration_four_strides` zeroed only `disp1` and `disp2`, which is not the case for other stride simplifications
ndgrigorian
force-pushed
the
fix-depends-and-disp-init
branch
from
September 25, 2026 17:03
cd335ce to
fe516a1
Compare
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
antonwolfy
approved these changes
Sep 28, 2026
antonwolfy
left a comment
Contributor
There was a problem hiding this comment.
Thank you @ndgrigorian, I have only the small nit with PR number in changelog, for which pushed the fix.
@vlad-perevezentsev, please check if any new comment, otherwise we are ready to merge that PR.
vlad-perevezentsev
approved these changes
Sep 28, 2026
vlad-perevezentsev
left a comment
Contributor
There was a problem hiding this comment.
No more comments from my side
LGTM
Thank you @ndgrigorian
github-actions Bot
added a commit
that referenced
this pull request
Sep 28, 2026
) This PR fixes bugs in libtensor: * `copy_for_reshape` default-constructed events unnecessarily * `fill` dropped its `depends` when constructing strides on device * Stride simplification did not consistently set initial displacements to 0 147a64a
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
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.
This PR fixes bugs in libtensor:
copy_for_reshapedefault-constructed events unnecessarilyfilldropped itsdependswhen constructing strides on device