Cache the set of active transfers in receive arbiter #319
+452
−437
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
|
Check-perf-impact results: (000e2892abb21ddd1ae413a5c86d7d95) ❓ No new benchmark data submitted. ❓ |
Pull Request Test Coverage Report for Build 12789562762Details
💛 - Coveralls |
fknorr
force-pushed
the
active-transfer-cache
branch
from
65604a0 to
03efe77
Compare
fknorr
force-pushed
the
active-transfer-cache
branch
from
03efe77 to
2218430
Compare
|
Check-perf-impact results: (c8fb992b35322012b54e351345fdf71a) ❓ No new benchmark data submitted. ❓ |
|
Check-perf-impact results: (deac89ab3c981780086a8f2d08cf6170) 🚀 Significant speedup (<0.80x) in some microbenchmark results: benchmark intrusive graph dependency handling with N nodes - 100 / creating nodes Relative execution time per category: (mean of relative medians)
|
fknorr
force-pushed
the
active-transfer-cache
branch
from
5849f0d to
5afe621
Compare
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Outdated suggestions cannot be applied.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.
receive_arbitertracks atransferfor every transfer id it learns through an inbound pilot, so long-running programs likewave_sim -T 10000will fill the transfer map quickly. It's anunordered_mapso lookups shouldn't suffer, but we iterate over it inpoll_communicator, which has linear complexity (initially found by @psalz).We only need to poll transfers for which we have already seen the
receive_instruction. This PR avoids the linear growth by caching the set of active transfers in a vector, and iterating over that.I've used the opportunity to refactor the code a bit and use
std::erase_ifin the many places we had erase-remove idiom before.