-
-
Notifications
You must be signed in to change notification settings - Fork 336
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
OpenGL: Monotonic UBO allocator #1911
Conversation
Would it be practical to have |
Bloaty Results 🐋Compared to main
Full report: https://maplibre-native.s3.eu-central-1.amazonaws.com/bloaty-results/pr-1911-compared-to-main.txtCompared to d387090 (legacy)
Full report: https://maplibre-native.s3.eu-central-1.amazonaws.com/bloaty-results/pr-1911-compared-to-legacy.txt |
Sure, we can do that. I made it a base mostly out of convenience. |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
!benchmark android |
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Bart Louwers <[email protected]>
Addresses a major performance regression when using UBOs: each buffer instance allocating its own buffer from the API.
This PR creates a new buffer sub-allocation scheme and a means to pool and recycle larger pages of buffer memory. This notably accelerates UBO performance by streaming unsynchronized writes to memory guaranteed to be unused by the GPU, eliminating the possibility of a pipeline stall during buffer updates.
How it works: