This repository has been archived by the owner on Mar 12, 2021. It is now read-only.
Don't pool large arrays #169
Merged
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
Codecov Report
@@ Coverage Diff @@
## master #169 +/- ##
==========================================
+ Coverage 83.97% 83.98% +0.01%
==========================================
Files 31 31
Lines 1092 1093 +1
==========================================
+ Hits 917 918 +1
Misses 175 175
Continue to review full report at Codecov.
|
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The pooling allocator is designed for small arrays, and doesn't really make any sense for one that take up a significant amount of GPU memory. This fixes the immediate issue by just not pooling at all for large arrays.
In future, we could extend this by just using a different pooling strategy for arrays of this size. For example, in this regime linear lookups are much less of a big deal (at most we can allocate ~100 arrays of this size anyway) so allocating exact sizes and searching for the smallest buffer to reuse would be sensible.