Sven Verdoolaege
Sven Verdoolaege
On Fri, Jun 08, 2018 at 10:03:18AM -0700, Nicolas Vasilache wrote: > So I think I would go the following route, but this probably requires a second set of eyes...
On Tue, Jun 12, 2018 at 06:51:13AM -0700, Nicolas Vasilache wrote: > > I don't agree with this reasoning. It's not because we _can_ do something that we necessarily need...
On Tue, Jun 12, 2018 at 06:57:31AM -0700, Nicolas Vasilache wrote: > Also, note that there is a tradeoff: > 1. hardcoding the strides in the kernel which forces us...
On Wed, Apr 25, 2018 at 03:25:21PM +0000, ftynse wrote: > Reviving this. I made Sema look inside the subscript expressions on the LHS so it no longer complains at...
On Wed, Feb 28, 2018 at 08:51:54AM +0000, ftynse wrote: > Anything will confuse users :) The mere fact of us having this discussion is evidence that the choices are...
On Tue, Feb 20, 2018 at 05:49:58AM -0800, Priya Goyal wrote: > + void createWrapper( > + const std::vector& inputs, > + const std::vector& outputs, > + const std::string& fname)...
On Sun, Jun 03, 2018 at 11:09:09PM -0700, ftynse wrote: > > Fundamentally, is there a way to figure out the launch config from already-tuned .{cuda,options} files? > > No....
On Fri, Jun 22, 2018 at 04:52:38AM -0700, ftynse wrote: > Syntactic disambiguation. A particularly nasty interplay between templates and type inference. The syntax of a template is checked when...
On Fri, Jun 29, 2018 at 05:50:56AM -0700, ftynse wrote: > I like the general idea. What worries me is the need to manually introduce member functions in the class...
On Fri, Jun 29, 2018 at 05:50:56AM -0700, ftynse wrote: > I like the general idea. What worries me is the need to manually introduce member functions in the class...