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

QF14 summary #413

Closed
classilla opened this issue Jun 29, 2017 · 4 comments
Closed

QF14 summary #413

classilla opened this issue Jun 29, 2017 · 4 comments

Comments

@classilla
Copy link
Owner

https://ehsanakhgari.org/blog/2017-06-23/quantum-flow-engineering-newsletter-14

Much less applies to us now, and this may be the last summary he issues.

Easy:
https://hg.mozilla.org/mozilla-central/rev/50c745be6bd1
https://hg.mozilla.org/mozilla-central/rev/c36dabb0aba6
https://hg.mozilla.org/mozilla-central/rev/c0bb73483afb

@classilla
Copy link
Owner Author

A little more difficult but apparently very helpful:
https://hg.mozilla.org/mozilla-central/rev/8c7dd6a9e935

@classilla
Copy link
Owner Author

This can be done very simply: we just rewrite callPreBarrier in MacroAssembler.h (which is the equivalent function) with a PPC-only variant that does the null check. We can optimize the short branch at the same time.
https://hg.mozilla.org/mozilla-central/rev/231bd9d90fb3

@classilla
Copy link
Owner Author

@classilla
Copy link
Owner Author

The callPreBarrier change regressed benchmarks. I guess the check is too expensive.

classilla added a commit that referenced this issue Jul 3, 2017
classilla added a commit that referenced this issue Jul 3, 2017
classilla added a commit that referenced this issue Jul 13, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant