Skip to content

fix(cuda): push element count, not byte length, for slice kernel args #6

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

Open
haixuanTao wants to merge 2 commits into
base: main
Choose a base branch
from
+16 −3
Open

fix(cuda): push element count, not byte length, for slice kernel args #6

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a0a71b3
fix(cuda): push element count, not byte length, for slice kernel args
Jun 8, 2026
2552c99
style: fix rustfmt formatting on slice element-count fix
claude Jun 16, 2026
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
19 changes: 16 additions & 3 deletions crates/khal/src/backend/any_backend.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1304,7 +1304,12 @@ impl<'b, T: DeviceValue> crate::ShaderArgs<'b> for GpuBuffer<T> {
}
#[cfg(feature = "cuda")]
(GpuBuffer::Cuda(buffer), GpuDispatch::Cuda(dispatch)) => {
dispatch.set_arg(binding, buffer.device_ptr_raw(), buffer.byte_len());
// cuda-oxide `&[T]` slice ABI wants an ELEMENT count, but byte_len is bytes;
// push element count so kernel `slice.len()` is correct (off-by-size_of
// otherwise -> OOB reads, e.g. gpu_init_sort_dispatch / lbvh). Arrays,
// scalars and uniforms ignore this value, so they are unaffected.
let elem_count = buffer.byte_len() / std::mem::size_of::<T>() as u64;
dispatch.set_arg(binding, buffer.device_ptr_raw(), elem_count);
Ok(())
}
#[cfg(feature = "metal")]
Expand Down Expand Up @@ -1336,7 +1341,11 @@ impl<'b, T: DeviceValue> crate::ShaderArgs<'b> for GpuBufferSlice<'_, T> {
}
#[cfg(feature = "cuda")]
(GpuBufferSlice::Cuda(slice), GpuDispatch::Cuda(dispatch)) => {
dispatch.set_arg(binding, slice.offset_ptr(), slice.byte_len);
dispatch.set_arg(
binding,
slice.offset_ptr(),
slice.byte_len / std::mem::size_of::<T>() as u64,
);
Ok(())
}
#[cfg(feature = "metal")]
Expand Down Expand Up @@ -1373,7 +1382,11 @@ impl<'b, T: DeviceValue> crate::ShaderArgs<'b> for GpuBufferSliceMut<'_, T> {
}
#[cfg(feature = "cuda")]
(GpuBufferSliceMut::Cuda(slice), GpuDispatch::Cuda(dispatch)) => {
dispatch.set_arg(binding, slice.offset_ptr(), slice.byte_len);
dispatch.set_arg(
binding,
slice.offset_ptr(),
slice.byte_len / std::mem::size_of::<T>() as u64,
);
Ok(())
}
#[cfg(feature = "metal")]
Expand Down
Loading