[MINOR] MatrixBlock Sparse Optimizations #1922
Closed
+747
−234
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
Baunsgaard
force-pushed
the
MMSparseUltraSparse
branch
2 times, most recently
from
b8ee886 to
cd3ccf9
Compare
Sparse Block pushdown operations add a few matrix mult tests fill zero values fix double! Fix sparse empty rows in preaggreaget sparse fix parfor FrameFrom Matrix Tests add
Baunsgaard
force-pushed
the
MMSparseUltraSparse
branch
from
cd3ccf9 to
0c353f6
Compare
Contributor
Author
|
Interestingly, the new list of matrix multiplication tests is have a speed up from 67 sec to 31 sec to execute all the multiplication tests. The main speedup comes from a fix to non zero counts, and the ultra sparse matrix multiplication speedups. |
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Outdated suggestions cannot be applied.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.
This commit adds a specialized kernel for Sparse %*% Ultra Sparse Matrix multiplication, that previously
accessed all cells in rows where there could be a multiplication in the left matrix no matter if it was sparse or not.
The optimization Improve default calls to Decision trees on kaggle playground-series-s3e23 from 100 sec to 30.
Also included is sparse handling of Binary cell operations and a small optimization to Commons math eigen to skip a indirect call.