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

Optimize dovi buffer access, mainly on Intel #198

Merged
merged 1 commit into from Nov 5, 2022

Conversation

nyanmisaka
Copy link
Member

Changes
Intel prefers clEnqueueMapBuffer + clEnqueueUnmapMemObject, instead of clEnqueueWriteBuffer.
Also unify the dovi buffer to lower the function call overhead.

It seems that Intel has not yet enabled zero-copy buffer in OpenCL for DG2, so this optimization works well.
160fps -> 200fps @ 3840x1608
250fps -> 340fps @ 1920x1080

Intel prefers clEnqueueMapBuffer + clEnqueueUnmapMemObject, instead of clEnqueueWriteBuffer.
Also unify the dovi buffer to lower the function call overhead.

https://www.intel.com/content/www/us/en/developer/articles/training/getting-the-most-from-opencl-12-how-to-increase-performance-by-minimizing-buffer-copies-on-intel-processor-graphics.html

Signed-off-by: nyanmisaka <nst799610810@gmail.com>
@nyanmisaka nyanmisaka merged commit 8b3eabb into jellyfin:jellyfin Nov 5, 2022
@nyanmisaka nyanmisaka deleted the dv-buf branch November 5, 2022 05:03
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

Successfully merging this pull request may close these issues.

None yet

2 participants