Add row norm scaling #38
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
This allows for easier caching. In particular we can cache/compute weighting before the SM is moved to the GPU. Since GPU arrays don't implement a hash function this allows for performant hash computations that dont have to rely on @allowscalar
…r for single patch algo
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Outdated suggestions cannot be applied.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.
CGNR and co. run into float32 overflows for certain reconstructions (in particular OpenMPIData).
This PR adds a new weighting type which scales each row/freq. component by 1 over its rownorm. This scaling moves the data range where it does not result in overflows (for the recos I tested).
Furthermore this PR adds a composite weighting op which allows a user to combine multiple weighting types.
It also implements weighting for Multi Patch Operators as well as restructures the caching of weighting parameters