Vulkan: Experimental fix for self-dependency barriers during render pass. (performance testing needed) #431
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Performance seems unchanged on Windows Nvidia and Intel Xe drivers, at least nothing that would be discernible beyond random noise. If the impact is this low on three completely different implementations then this should be safe to merge, at least performance-wise. |
goeiecool9999
added a commit
to goeiecool9999/Cemu
that referenced
this pull request
Nov 10, 2022
…renderpass (cemu-project#431)" This reverts commit a129d22.
lijunyu-cn
added a commit
to lijunyu-cn/Cemu
that referenced
this pull request
Sep 29, 2023
…renderpass (cemu-project#431)" This reverts commit a129d22.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This change ends the current render pass when cemu detects a self-dependency within it. This fixes #267.
However the performance implications of separating the draw calls into multiple render passes and the broader barriers are unknown.
My test in breath of the wild showed an acceptable reduction in worst %.1 framerate from 69.7fps to 56.3fps. with 97th percentile being down only 2 fps from 102 to 100.(Bad testing methodology)Different GPUs/OS's/drivers may get different outcomes so this change requires performance testing.
Accurate barriers must be enabled for this to work