Fix M31::new() modular reduction for values >= 2*P #9
+46
−0
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Outdated suggestions cannot be applied.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.
The
M31::new()function performed single-step reduction (val - P), which only handles values in[0, 2*P). Values>= 2*Pwere incorrectly reduced:Changes
Applied double reduction to handle full
u32range:Added boundary tests covering
P,2*P-1,2*P, andu32::MAXThe fix preserves existing behavior for values
< 2*Pwhile correctly reducing the upper boundary cases.Original prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.