On Wed, 15 Feb 2012 15:55:15 -0800, "Eli Stevens (Gmail)" 
<wickedg...@gmail.com> wrote:
> I was wondering if there was a rough estimate of when / what would
> trigger 3d grids being supported in pycuda (is it only formal removal
> of the stateful interface in cuda that would cause this to happen?).
> We are running into issues where the real solution is to have a Z-grid
> > 1, and I'm trying to determine if implementing a workaround for only
> having 2d grids is worthwhile.  Thanks for any info!

If you have a little bit of time to spend on this, I'd recommend simply
implementing the new-style launch interface, and making PyCUDA use that
in the case of 3-dimensional grids. I imagine that would be about the
same amount of effort as implementing the workaround you speak of, and
it would remove the problem from this world once and for all. :)

If you need help getting started on this, let me know.


> PS - Apologies for the thread necromancy.

No problem--my mailer is up to the job. I like it!

Attachment: pgp9jXhH5WUgN.pgp
Description: PGP signature

PyCUDA mailing list

Reply via email to