Optimize SparseCore input preprocessing by eliminating buffer copies. #567
Conversation
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
copybara-service
bot
force-pushed
the
test_831179831
branch
8 times, most recently
from
3fafae7 to
54444da
Compare
* Introducing `OutputBufferViews`, allowing
the caller to pass views of the destination buffers.
* Modifying `CsrArraysPerHost` to optionally use `Eigen::Map` to wrap
these buffers when provided. We can avoid populating large CSR arrays in the preprocessing return values and skip the data copy step.
PiperOrigin-RevId: 831179831
copybara-service
bot
force-pushed
the
test_831179831
branch
from
54444da to
8628804
Compare
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Outdated suggestions cannot be applied.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.
Optimize SparseCore input preprocessing by eliminating buffer copies.
OutputBufferViews, allowingthe caller to pass views of the destination buffers.
CsrArraysPerHostto optionally useEigen::Mapto wrapthese buffers when provided. We can avoid populating large CSR arrays in the preprocessing return values and skip the data copy step.