Support for cudaMemcpy2DToArrayAsync about managedcuda

[dennisai]

I tried writing the following code, and it seems to work!

private void CopyToArray2D(
    CudaPitchedDeviceVariable<float> src,
    CudaArray2D dst,
    CudaStream stream)
{
    CUDAMemCpy2D copyParams = new CUDAMemCpy2D();
    CUResult copyResult;

    copyParams.srcDevice = src.DevicePointer;
    copyParams.srcMemoryType = CUMemoryType.Device;
    copyParams.srcPitch = src.Pitch;
    copyParams.dstArray = dst.CUArray;
    copyParams.dstMemoryType = CUMemoryType.Array;
    copyParams.Height = src.Height;
    copyParams.WidthInBytes = src.WidthInBytes;

    if (stream != null)
    {
        copyResult = DriverAPINativeMethods.AsynchronousMemcpy_v2
            .cuMemcpy2DAsync_v2(ref copyParams, stream.Stream);
    }
    else
    {
        copyResult = DriverAPINativeMethods.SynchronousMemcpy_v2
            .cuMemcpy2D_v2(ref copyParams);
    }
        
    if (copyResult != CUResult.Success)
    {
        throw new CudaException(copyResult);
    }
}