Fix modulo bias in device Random_int rejection sampling#5545
Merged
Conversation
The CUDA/HIP device path of Random_int used `rand > (RAND_M - RAND_M % n)`
as its rejection bound, which accepts L+1 values where L is the largest
multiple of n ≤ RAND_M. The extra value L maps to residue 0, biasing the
output toward 0 — up to ~2× for large n (e.g., n = 2^31).
Change `>` to `>=` so the accepted set is exactly {0, …, L-1}, a perfect
multiple of n, giving a uniform distribution.
atmyers
approved these changes
Jul 8, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The CUDA/HIP device path of Random_int used
rand > (RAND_M - RAND_M % n)as its rejection bound, which accepts L+1 values where L is the largest multiple of n ≤ RAND_M. The extra value L maps to residue 0, biasing the output toward 0 — up to ~2× for large n (e.g., n = 2^31).Change
>to>=so the accepted set is exactly {0, …, L-1}, a perfect multiple of n, giving a uniform distribution.