[PWGCF/Femto] ~35% faster track-track mixing: hoist the per-window track slice#16663
Open
ktf wants to merge 1 commit into
Open
[PWGCF/Femto] ~35% faster track-track mixing: hoist the per-window track slice#16663ktf wants to merge 1 commit into
ktf wants to merge 1 commit into
Conversation
ktf
requested review from
alibuild,
ariedel-cern,
lauraser,
shouqiye,
victor-gonzalez and
wrzesaCERN
as code owners
|
O2 linter results: ❌ 0 errors, |
github-actions
Bot
changed the title
Member
Author
|
@aalkin this is one of the hotspots for the slicing we were discussing today. This actually avoids half of the cost by moving the construction outside. |
ktf
changed the title
Member
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In processMixedEvent the partner partitions are sliced per
(collision1, collision2) pair, but collision1 is fixed across its entire
mixing window. sliceByCached only caches the offset/count — it re-runs
arrow::Table::Slice on every call (a per-column ArrayData allocation +
shared_ptr refcount storm) — so at mixing depth D, collision1's track
slice was rebuilt D times per window for no reason.
Hoist sliceParticle1 into a std::optional declared before the
combinations loop and (re)materialize it only when collision1.globalIndex()
changes, i.e. once per window. collision2 genuinely varies per pair and is
left untouched.