-
-
Notifications
You must be signed in to change notification settings - Fork 3.9k
Parallelize bevy 0.16-rc bottlenecks #18632
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
Conversation
This is an ad-hoc accumulation of perf fixes, might need to split things out. Duplication with #18618 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Makes sense! One minor suggestion but generally agreeable.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Meant to request changes, not approve*
Co-authored-by: Zachary Harrold <zac@harrold.com.au>
I don't see why this is blocking, there is no downside to keeping this as-is. I'd argue changing it would make this more brittle. (It seems out of scope too? I'm just doing the minimum to match the existing code but make it parallel) |
This is a straightforward improvement; other cleanup can wait.
# Objective - Found stuttering and performance degradation while updating big_space stress tests. ## Solution - Identify and fix slow spots using tracy. Patch to verify fixes. ## Testing - Tracy - Before:  - prev_gt parallelization and mutating instead of component insertion:  - parallelize visibility ranges and mesh specialization  --------- Co-authored-by: Zachary Harrold <zac@harrold.com.au>
Objective
Solution
Testing