Use cublas<t>matinvBatched() for N <= 32 #739
Merged
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
Use the cublas<t>matinvBatched() family of functions to invert linear systems of size N <= 32. This has two advantages over the more general pair of getrfBatched() and getriBatched() functions: 1. Higher performance with the single kernel than with split kernels. 2. The matinv functions support in-place transforms and do not modify the input in the case of out-of-place transforms, so we do not need a temporary input work buffer if the input is a tensor view.
|
/build |
cliffburdick
approved these changes
Aug 27, 2024
|
/build |
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Outdated suggestions cannot be applied.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.
Use the cublasmatinvBatched() family of functions to invert linear systems of size N <= 32. This has two advantages over the more general pair of getrfBatched() and getriBatched() functions: