ICB matrix optimization #4718
Draft
ICB matrix optimization #4718
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
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Outdated suggestions cannot be applied.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.
tl;dr FXC often emits immediate a 4x4 identity or scaling matrix as an immediate constant buffer, this experimentally transforms that to a vec4 constant and implements indexing by doing a component-wise
index == n ? value : 0.The theory here is that this should be more efficient because we replace a memory load with a few ALU ops, in practice however this seems to be worse (at least on RADV) because we're replacing one memory load that the driver will try its best to optimize with a whole bunch of VALU ops that are redundantly spammed everywhere because CSE apparently doesn't want to help us out.
Leaving this open for perf test / discussion for now, but unfortunately this appears to be a bit of a dud.