[GLUTEN-10933][VL] feat: Support cached the batches in cpu cache#11758
Open
jinchengchenghh wants to merge 1 commit intoapache:mainfrom
Open
[GLUTEN-10933][VL] feat: Support cached the batches in cpu cache#11758jinchengchenghh wants to merge 1 commit intoapache:mainfrom
jinchengchenghh wants to merge 1 commit intoapache:mainfrom
Conversation
jinchengchenghh
force-pushed
the
cudf_shuffle_up
branch
from
7963eb4 to
a2e1099
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cache the batch in cpu cache, and wait for the join threads to fetch one by one, the build threads will start to fetch as soon as possible, but the probe thread need to wait for build finished.
The buffer size is controlled by
spark.gluten.sql.columnar.backend.velox.cudf.shuffleMaxPrefetchBytestemporally, the size may be changed by the remaining memory in the server.Test:
Test in local SF100, adjust the config to enable caching batch.
The log prints
Prefetched 171 batches (24057900 bytes) before blocking on GPU lockNext step:
Prefetch the probe side batch when build starts.
Related issue: #10933