-
Notifications
You must be signed in to change notification settings - Fork 225
fix(nvvm): use PassMode::Cast for align(16) ADTs#362
Merged
LegNeato merged 1 commit intoRust-GPU:mainfrom Feb 26, 2026
Merged
Conversation
Contributor
The NVVM backend was defaulting to PassMode::Direct for all ADTs. On NVPTX, LLVM often aligns generic aggregate types to 8 bytes, even if the Rust type requires 16-byte alignment. This caused the kernel to read arguments from incorrect offsets, leading to crashes.
The Fix:
- High Alignment (>= 16): For structs requiring 16+ byte alignment, force
PassMode::Castusingi128units. This compels LLVM to emit.param .align 16(or
.b128) in PTX, guaranteeing the correct ABI contract. - Standard Alignment: For other ADTs, explicitly set
attrs.pointee_alignwhen using
PassMode::Directto ensure LLVM respects the type's alignment attribute.
Fixes #361
Contributor
|
I'm not really qualified to review this as I am shaky on the LLVM side, but let's land it and see how it goes. Thank you! |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.