Adding resize(PadOp) vectorization analysis #3321
Open
+465
−63
Conversation
This file contains 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
This reverts commit d0addc4.
jjsjann123
added a commit
that referenced
this pull request
Nov 5, 2024
Added support for lowering TernaryOp:where with vectorization factor. i.e. ``` predicate ? loadGlobalToLocal<...>(&dst[0], &src[i_src]) : dst.set(0.0f) ``` Currently this can only be done via manual scheduling. The follow up PR on vectorization analysis will make this automatically applied in PR #3321
|
!test |
jjsjann123
changed the title
naoyam
reviewed
Nov 7, 2024
Co-authored-by: Naoya Maruyama <naoyam@users.noreply.github.com>
naoyam
reviewed
Nov 8, 2024
|
!test --pybench |
|
Initiated testing with python benchmarks just in case. |
|
Thanks, I'll address the issues you brought up as well as running through some real size problem so we get a taste of the perf impact. 🙇 |
|
!test --pybench |
|
!test --pybench |
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Outdated suggestions cannot be applied.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.
Adding conditional support of reszie in vectorization analysis. This PR allows vectorized load on
PadOpdirectly without using cache load. This PR improves performance of generated kernel.What's in this PR:
Add propagation rule for resize in vectorization analysis. The propagation rule works as:
i. For supported resize: a). project the resize op to the frontier and clear
(frontier.begin(), resize_position); b). add projected extent of the new resize op asgcd(id_from, resize_op->leftExpand(), resize_op->rightExpand)ii. For unsupported resize: clear
[frontier.begin(), resize_position]; no behavior change.updating TensorView::cacheAfter to opt-in a set of uses to cache while leaving other uses unchanged. Necessary for cases where inputs are used by PadOp as well as other operation that relies on cached load for vectorization.
Follow up to #3261.
Work for supporting rope performance. design doc: