Wonderful, thanks Karl!
-Evan Bollig
On Jul 29, 2013 7:43 PM, "Karl Rupp" <r...@iue.tuwien.ac.at> wrote:
> Hi guys,
>
> as I was recently discussing asynchronous transfer and execution with Evan
> in an MPI context, this is now addressed with
> viennacl::async_copy()
>
> Typical use case:
> std::vector<double> std_x(SIZE);
> viennacl::vector<double> vcl_x(SIZE);
> viennacl::async_copy(std_x, vcl_x); // same as next line
> viennacl::async_copy(std_x.**begin(), vcl_x.begin(), vcl_x.end());
> /* do some other stuff here */
> viennacl::backend::finish(); // sync queue (OpenCL) or device (CUDA)
>
> Copying from device back to host works analogously. This also works with
> vector_range and vector_stride.
>
> There is no async copy for matrices right now, because there are
> essentially always data conversions involved, preventing truly asynchronous
> operations.
>
> Best regards,
> Karli
>
------------------------------------------------------------------------------
Get your SQL database under version control now!
Version control is standard for application code, but databases havent
caught up. So what steps can you take to put your SQL databases under
version control? Why should you start doing it? Read more to find out.
http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
_______________________________________________
ViennaCL-devel mailing list
ViennaCL-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/viennacl-devel
