2016-08-13 21:33 GMT+02:00 Ilia Mirkin <imir...@alum.mit.edu>: > On Sat, Aug 13, 2016 at 3:26 PM, Connor Abbott <cwabbo...@gmail.com> wrote: >> So, I don't know much about how nv50 ir works, but to me this just >> seems like a pretty slow implementation of a very limited instruction >> scheduler. In addition to the runtime complexity problems you >> mentioned, you're going to get a lot more benefit even from a very >> simple list scheduler compared to this, and it generally only takes a >> few hundred lines to write one. I'd send you some references, but I > > I agree with basically all of the above. I really don't think it's > worth having this super-partial approach. We need a real scheduler, > both pre- and post-ra. Which follows a reasonable strategy. > > I don't think this "just try to dual issue as much as possible > post-ra" attempt really gets at that. It's a neat hack, but ultimately > I don't think it's worth having upstream. It's not something that > we'll be able to build on and improve -- the underlying approach is > too brute force. > > -ilia
right, but that was the code I was testing with and it gave me good results already. Just added it with this in mind, so others could also try this. I was actually toying around with implementing some scheduler stuff, but nothing really got me anywhere, so I kind of stopped. Anyway, the dual issue fixes are worth to include and that's the main reason I actually sent it out _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
