Replace split_with_sizes_copy with slice_copy #10318
Open
+80
−2
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10318
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 8 New Failures, 2 Unrelated FailuresAs of commit fb7f1cf with merge base 06f912d ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D73312379 |
mcremon-meta
added a commit
that referenced
this pull request
Apr 20, 2025
Summary: This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes: - swapping with q/dq nodes to do it in lower bitwidth - becoming slice_nop when possible (through memory planning constraints) - a few simplification passes on slices - possibly finding patterns with slice/cat being a nop - we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand Differential Revision: D73312379
mcremon-meta
force-pushed
the
export-D73312379
branch
from
c3918b8 to
416edc8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D73312379 |
mcremon-meta
added a commit
that referenced
this pull request
Apr 20, 2025
Summary: Pull Request resolved: #10318 This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes: - swapping with q/dq nodes to do it in lower bitwidth - becoming slice_nop when possible (through memory planning constraints) - a few simplification passes on slices - possibly finding patterns with slice/cat being a nop - we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand Differential Revision: D73312379
mcremon-meta
force-pushed
the
export-D73312379
branch
from
416edc8 to
e9f302e
Compare
mcremon-meta
added a commit
that referenced
this pull request
Apr 21, 2025
Summary: This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes: - swapping with q/dq nodes to do it in lower bitwidth - becoming slice_nop when possible (through memory planning constraints) - a few simplification passes on slices - possibly finding patterns with slice/cat being a nop - we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand Differential Revision: D73312379
mcremon-meta
force-pushed
the
export-D73312379
branch
from
e9f302e to
342fea6
Compare
Summary: Pull Request resolved: #10318 This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes: - swapping with q/dq nodes to do it in lower bitwidth - becoming slice_nop when possible (through memory planning constraints) - a few simplification passes on slices - possibly finding patterns with slice/cat being a nop - we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand Differential Revision: D73312379
|
This pull request was exported from Phabricator. Differential Revision: D73312379 |
mcremon-meta
force-pushed
the
export-D73312379
branch
from
342fea6 to
fb7f1cf
Compare
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.
Summary:
This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace
split_with_sizes. That includes:Differential Revision: D73312379