[Datpath] Improve Booth Encoding based on the sign-extension trick #8903
Conversation
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
…size of the compressor tree
uenoku
approved these changes
Aug 29, 2025
Member
uenoku
left a comment
uenoku
left a comment
There was a problem hiding this comment.
Looks really awesome! Could you add normal FileCheck tests and LEC for partial products with zero/sign extension?
Contributor
Author
|
Now with tests added :) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Reduce the number of partial product bits generated using a classical sign-extension trick where repeated bits can be optimised away. Currently only implemented when the inputs to a partial product operator are zero-extended. Current folding mechanisms are unable to recognise the zero-padding in a single step (although canonicalization will incrementally strip away). The KnownBits analysis is able to recognise this at some efficiency penalty - although this could be improved using bounded depth traversal.
A future PR will exploit this simplified partial product array via timing driven compression and improve the algorithm further to detect sign-extended inputs.