Open
Conversation
It's my understanding that all big vendors run sqrt and sin/cos on the same hardware. So if running sin then cos you saturate the pipeline with sin calls, stall on that, then saturate the pipeline with cos calls. It also allows for vendor-specific optimizations for sincos if those exist. Current implementation saturates the same pipeline for special functions when calling cos, then goes through FMA twice to compute 1 - c^2, then the same pipeline that would be used for sin but used to compute the sqrt, and then a sign inversion. Not only is it slower (if my understanding is correct) it's also less precise near multiples of pi (although that's probably unimportant near zero).
This file contains hidden or 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
It's my understanding that all big vendors run sqrt and sin/cos on the same hardware. So if running sin then cos you saturate the pipeline with sin calls, stall on that, then saturate the pipeline with cos calls. It also allows for vendor-specific optimizations for sincos if those exist.
Current implementation saturates the same pipeline for special functions when calling cos, then goes through FMA twice to compute 1 - c^2, then the same pipeline that would be used for sin but used to compute the sqrt, and then a sign inversion. Not only is it slower (if my understanding is correct) it's also less precise near multiples of pi (although that's probably unimportant near zero).