Allow adjusting loop unroll aggressiveness #350
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
LegNeato
requested changes
Jan 20, 2026
Contributor
LegNeato
left a comment
LegNeato
left a comment
There was a problem hiding this comment.
Looks great, thanks! But I think there is one unrelated change?
|
|
||
| [dependencies] | ||
| glam = { version = ">=0.22", default-features = false, features = ["libm", "cuda", "bytemuck"] } | ||
| glam = { version = ">=0.27", default-features = false, features = ["libm", "cuda", "bytemuck"] } |
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Outdated suggestions cannot be applied.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.
In C++ CUDA, there's
#pragma unroll, which allows you to force a loop to be unrolled. Rust does not have such an equivalent, but LLVM will decide whether to unroll your loop based on heuristics. If you set the LLVM option-unroll-thresholdto a large number, you can make LLVM be more aggressive in its unrolling of loops.This gave my Rust code a 10x speed improvement for some kernels, due to being able to index arrays at compile time, removing the need for local memory, stack frames, and function calls.
N.B. there is the
unrollcrate but it only supports unrolling loops with integer bounds. The LLVM approach allows unrolling loops over iterators also.