pub struct GpuMainOverride { /* private fields */ }Expand description
A rank-local CUDA scope nested inside another engine’s PP stage scope.
CUDA contexts are a per-thread stack. The stream override alone is not enough: every rank-local allocation and launch must make that rank’s context current, then restore the caller’s context before the PP owner resumes issuing work.
Trait Implementations§
Source§impl Drop for GpuMainOverride
impl Drop for GpuMainOverride
Auto Trait Implementations§
impl !Send for GpuMainOverride
impl !Sync for GpuMainOverride
impl Freeze for GpuMainOverride
impl RefUnwindSafe for GpuMainOverride
impl Unpin for GpuMainOverride
impl UnsafeUnpin for GpuMainOverride
impl UnwindSafe for GpuMainOverride
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more