Skip to content
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.

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

SPU LLVM: Avoid sinking stores out of non-loops #15714

Merged
merged 3 commits into from
Jun 19, 2024
Merged

Conversation

elad335
Copy link
Contributor

@elad335 elad335 commented Jun 18, 2024

Doing so in code not belonging to loops is non-beneficiary and may result in adverse effects on performance because the value has to be carried farther until the store.

@elad335 elad335 added Optimization Optimizes existing code LLVM Related to LLVM instruction decoders labels Jun 18, 2024
@elad335 elad335 force-pushed the analyser branch 4 times, most recently from 0f4cfcc to 14bc0a1 Compare June 18, 2024 16:34
@elad335
Copy link
Contributor Author

elad335 commented Jun 18, 2024

Added a Linux-specific fix for GETLLAR wait.

@cipherxof
Copy link
Contributor

Seems slightly better on Linux. Note #15686 is reverted.

Before:
Screenshot from 2024-06-18 13-24-22

After:
Screenshot from 2024-06-18 13-20-51

@elad335
Copy link
Contributor Author

elad335 commented Jun 19, 2024

what about windows?

@cipherxof
Copy link
Contributor

what about windows?

Master:
image

PR:
image

@elad335 elad335 merged commit 6497144 into RPCS3:master Jun 19, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
LLVM Related to LLVM instruction decoders Optimization Optimizes existing code
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants