refactor: Optimize IndexedPriorityQueue::addOrUpdate 20 times faster #11955
+368
−318
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D67626564 |
✅ Deploy Preview for meta-velox canceled.
|
…acebookincubator#11955) Summary: Optimize `IndexedPriorityQueue` to use more compact data structures (binary heap) to leverage cache locality and avoid unnecessary memory allocations. `addOrUpdate` is now about 20 times faster for large data (~1 million elements). This allows us to replace the custom heap implementation in `ApproxMostFrequentStreamSummary` with `IndexedPriorityQueue`. Note that `pop` becomes about twice slower in the new version. This is expected because we shift some of the reordering cost from insertion time to pop time. This shall be good because for each `pop`, we have at least one corresponding `addOrUpdate` which guarantees net performance gain, and in most of the case we do not even have `pop` on critical path (e.g. in case of `ApproxMostFrequentStreamSummary`). Differential Revision: D67626564
Yuhta
force-pushed
the
export-D67626564
branch
from
a37c7ce to
329d396
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67626564 |
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Outdated suggestions cannot be applied.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.
Summary:
Optimize
IndexedPriorityQueueto use more compact data structures (binary heap) to leverage cache locality and avoid unnecessary memory allocations.addOrUpdateis now about 20 times faster for large data (~1 million elements). This allows us to replace the custom heap implementation inApproxMostFrequentStreamSummarywithIndexedPriorityQueue.Note that
popbecomes about twice slower in the new version. This is expected because we shift some of the reordering cost from insertion time to pop time. This shall be good because for eachpop, we have at least one correspondingaddOrUpdatewhich guarantees net performance gain, and in most of the case we donot even have
popon critical path (e.g. in case ofApproxMostFrequentStreamSummary).Differential Revision: D67626564