Trim capacity of piggier allocations#806
Merged
Merged
Conversation
Pushing into initially empty vectors reserves capacity four; the frontier, consumed, internal, and produced vectors hold one element per port and live as long as the operator. The trade is one reallocation per vector at build time for proportionate memory thereafter. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
frankmcsherry
force-pushed
the
capacity_trims
branch
from
6c9db5b to
c72a157
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Measurements
master @
0823096cvs this branch, release, Apple Silicon. RSS sampledvia
psafter construction completes (repeatable to ~0.1 MB); scalingtests 3 runs each.
event_driven1000 × 1000shape_scaling100koperator_scalingsubgraph_scalingPer the heap profile, the trimmed vectors were the second-largest
per-operator item: the
frontiervector alone held 544 B (capacity 4 ×136 B
MutableAntichain) to store one 136 B element. The build-timecost is the extra allocator round-trips from the shrink reallocs,
visible only on the chain-heavy benchmark; scaling tests sit at parity.