Use NEON intrinsics in software renderer #16753
Merged
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Outdated suggestions cannot be applied.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.
While clang/gcc seem to do a better job than MSVC on vectorizing, there were still a lot of cases (especially Vec3s) where it wasn't.
This basically changes all the places we used SSE for software rendering to use NEON. Although I checked several places, I didn't carefully verify each case especially around Vec3s. I also didn't validate carefully that other code around these were prodded to use vectors more, as happens with SSE in MSVC.
In my testing, I was only seeing at most 10% improvement from this in FPS, although power management made it a bit hard to tell.
-[Unknown]