Function cuda_free_async

crates/cust/src/memory/malloc.rs:90–99

Unsafe wrapper around `cuMemFreeAsync` which queues a memory allocation free operation on a stream. Retains all of the unsafe semantics of [`cuda_free`] with the extra requirement that the memory must not be used after it is dropped. Therefore, proper stream ordering semantics must be respected. # Safety The pointer must be valid.

(
    stream: &Stream,
    p: DevicePointer<T>,
)

///
/// The pointer must be valid.
pub unsafe fn cuda_free_async<T: DeviceCopy>(
    stream: &Stream,
    p: DevicePointer<T>,
) -> CudaResult<()> {
    if mem::size_of::<T>() == 0 {
        return Err(CudaError::InvalidMemoryAllocation);
    }

    cuda::cuMemFreeAsync(p.as_raw(), stream.as_inner()).to_result()
}

/// Unsafe wrapper around the `cuMemAllocManaged` function, which allocates some unified memory and
/// returns a [`UnifiedPointer`](struct.UnifiedPointer.html) pointing to it. The memory is not cleared.