[experimental] [AArch64] Reorder RTA functions by runtime call density#9727
Open
igogo-x86 wants to merge 2 commits intofacebook:masterfrom
Open
[experimental] [AArch64] Reorder RTA functions by runtime call density#9727igogo-x86 wants to merge 2 commits intofacebook:masterfrom
igogo-x86 wants to merge 2 commits intofacebook:masterfrom
Conversation
On AArch64, non-smashable calls to the runtime (movz/movk/blr sequences) are significantly more expensive than on x86 due to instruction encoding overhead. This patch reorders functions during retranslateAll so that functions with the highest runtime call density (weighted by profile execution counts) are placed first in code.hot. The idea is that clustering call-heavy functions near the start of the TC improves icache locality for runtime call sequences. Controlled by two new config options: - Eval.JitRuntimeCallReorder (bool, default: true, AArch64 only) - Eval.JitRuntimeCallReorderLimitMB (uint32, default: 64) Diagnostic output available via TRACE=mcg:6.
|
@facebook-github-bot has imported this pull request. If you are a Meta employee, you can view this in D94090083. (Because this pull request was imported automatically, there will not be any future comments.) |
|
Hi @igogo-x86 We are hitting some assertion errors in CI:
|
Contributor
|
@igogo-x86 has updated the pull request. You must reimport the pull request before landing. |
Contributor
Author
|
Hi, @charles-typ |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
On AArch64, non-smashable calls to the runtime (movz/movk/blr sequences) are significantly more expensive than on x86 due to instruction encoding overhead. This patch reorders functions during retranslateAll so that functions with the highest runtime call density (weighted by profile execution counts) are placed first in code.hot.
The idea is that clustering call-heavy functions near the start of the TC improves icache locality for runtime call sequences.
Controlled by two new config options:
Diagnostic output available via TRACE=mcg:6.