[MetaSchedule] Handle cases when no features found by FeatureExtractor #14591
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
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
Ubospica
force-pushed
the
tvm-dev/2023-04-12-ms-update
branch
from
80e437a
to
67b7b38
Compare
Ubospica
force-pushed
the
tvm-dev/2023-04-12-ms-update
branch
from
b532991
to
168da76
Compare
junrushao
approved these changes
Apr 12, 2023
|
Nice! Should be ready to get in :-) |
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Outdated suggestions cannot be applied.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 the problem that ops like
topi.fullcannot be correctly tuned.Currently, metaSchedule system adopts a XGBoost model to predict the running performance of an IRModule based on features extracted from it.
However, Some operators like
topi.fullhas so simple IRModule that no feature can be extracted.topi.fullcontains only one BufferStore node with a FloatImm value, soPerStoreFeatureextractor cannot find any feature from it. And the XGBModel also cannot handle cases when there is no features.This PR specifically handles this case in
PerStoreFeatureNodeandXGBModel.Thanks to @junrushao