[Perf Improvement] Stage monolith linesearch search vector#52
Merged
yaoliu13 merged 1 commit intoamd-integrationfrom May 1, 2026
Merged
[Perf Improvement] Stage monolith linesearch search vector#52yaoliu13 merged 1 commit intoamd-integrationfrom
yaoliu13 merged 1 commit intoamd-integrationfrom
Conversation
Author
|
/run_ci |
Author
|
/run-ci |
Author
|
Looks the perf gain is gone with latest amd-integration. Should investigate further. |
Avoid rereading the linesearch search vector from global memory on AMDGPU while preserving the default CPU path and test correctness. [Perf Improvement] Reduce monolith linesearch state traffic Keep linesearch counters and convergence state local inside the monolith loop to avoid hot global field round-trips while preserving solver behavior. [Perf Improvement] Restore solver previous cost state Keep the monolith linesearch traffic reductions while preserving prev_cost as observable solver state for CPU correctness checks.
peizhang56
force-pushed
the
perf/monolith-linesearch
branch
from
44d96dd to
e81265e
Compare
Author
|
/run-ci |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Use linesearch in monolith to reduce the register pressure.