On Wed, Apr 6, 2016 at 9:15 AM, Derek Gaston <fried...@gmail.com> wrote:
> I would hold off on putting it in libMesh proper for a bit. I'm actually > in the middle of writing a paper on a new ray tracing algorithm that scales > out to 10,000 cores (so far). I plan on putting that algorithm into libMesh > when I'm finished. > > That will probably be sometime this summer (I was targeting SC16, but, > while I have results... I don't have a finished paper yet for various > reasons). > > You can get started with this simple algorithm for now, but if you were to > put it in libMesh I would want to take it back out pretty soon. Cool, sounds good. I don't anticipate needing more than hundreds of cores for the problem of immediate interest, so the more simplistic algorithm will suit us just fine. Tim: Just drop it locally in the QoI you're working on and we can migrate later. Looking forward to seeing your paper, Derek! Best, Paul
------------------------------------------------------------------------------
_______________________________________________ Libmesh-devel mailing list Libmesh-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libmesh-devel
