Skip to content

GH-135904: Implement assembler optimization for AArch64. #139855

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

GH-135904: Implement assembler optimization for AArch64. #139855

wants to merge 3 commits into from
+79 −6

Conversation

markshannon
Copy link
Member

@markshannon markshannon commented Oct 9, 2025 •
edited by bedevere-app bot
Loading

Implements #135904 for AArch64 to match the optimisation for x86.
Removes a number of unnecessary branches.

@markshannon
Implement assembler optimization for AArch64.
4abdaa1 
Removes a number of unnecessary branches.

Change-Id: I4965fe8d8b79f7d859ff9076d9c53f3ac7f094b2
@markshannon markshannon force-pushed the optimize-jit-cfg-arm branch from 7dff6cc to 4abdaa1 Compare October 9, 2025 15:24
@python-cla-bot
Copy link

python-cla-bot bot commented Oct 9, 2025 •
edited
Loading

All commit authors signed the Contributor License Agreement.

CLA signed

@bedevere-app bedevere-app bot mentioned this pull request Oct 9, 2025
Open
@markshannon
Copy link
Member Author

It looks like there are three issues here:

  • The R_AARCH64_TSTBR14 relocation only allows a jump of 2**15 bytes, which is not enough for the JIT in debug mode. We could maybe workaround this, as it would be nice to have for the release build. But I think we can just drop support for optimising cbz and tbz instructions for now.
  • We don't have the symbol name for 19 bit relocations on Windows. This is an easy fix.
  • The llvm assembler is rejecting b.eq __JIT_ERROR_TARGET because "conditional branch requires assembler-local label", but the code is fine. This might be because the home-brew installed llvm is too old?

@markshannon
AArch64: Don't optimize 14 bit jumps to avoid failures when patching.…
b39e875 
… Add Windows 19 bit jump relocation.

Change-Id: Ib15ce7ab0de315c4dc1f544d600ae669024a4a6d
@markshannon
Add new relocation to match statement for Windows
87015f3
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@brandtbucher brandtbucher Awaiting requested review from brandtbucher brandtbucher is a code owner

@savannahostrowski savannahostrowski Awaiting requested review from savannahostrowski savannahostrowski is a code owner

@diegorusso diegorusso Awaiting requested review from diegorusso diegorusso is a code owner

Assignees

No one assigned

Labels

awaiting core review skip news

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@markshannon