Function cuda_malloc_async

crates/cust/src/memory/malloc.rs:62–80

Unsafe wrapper around `cuMemAllocAsync` which queues a memory allocation operation on a stream. Retains all of the unsafe semantics of [`cuda_malloc`] with the extra requirement that the memory must not be used until it is allocated on the stream. Therefore, proper stream ordering semantics must be respected. # Safety The memory behind the returned pointer must not be used in any way until the a

(
    stream: &Stream,
    count: usize,
)

/// The memory behind the returned pointer must not be used in any way until the
/// allocation actually takes place in the stream.
pub unsafe fn cuda_malloc_async<T: DeviceCopy>(
    stream: &Stream,
    count: usize,
) -> CudaResult<DevicePointer<T>> {
    let size = count.checked_mul(mem::size_of::<T>()).unwrap_or(0);
    if size == 0 {
        return Err(CudaError::InvalidMemoryAllocation);
    }

    let mut ptr: *mut c_void = ptr::null_mut();
    cuda::cuMemAllocAsync(
        &mut ptr as *mut *mut c_void as *mut u64,
        size,
        stream.as_inner(),
    )
    .to_result()?;
    let ptr = ptr as *mut T;
    Ok(DevicePointer::from_raw(ptr as cuda::CUdeviceptr))
}

/// 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