Skip to content

fix(cuda): sync memory subtree streams before drop #2175

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 23, 2025
Merged

fix(cuda): sync memory subtree streams before drop #2175

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions crates/vm/src/system/cuda/memory.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,3 +231,12 @@ impl MemoryInventoryGPU {
ret
}
}

impl Drop for PersistentMemoryInventoryGPU {
fn drop(&mut self) {
// Drop merkle subtrees first so their individual streams synchronize before dropping the
// initial memory buffers. This prevents buffers from dropping before build_async completes.
self.merkle_tree.drop_subtrees();
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

IS this enough? Strange. I don't see a sync in MemoryMerkleSubTree drop. There is no drop impl there

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's just the CudaStream drop implementation. When you remove a subtree, the subtree drops, which drops the stream, which forces a sync.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Aha, nice

self.initial_memory.clear();
}
}