<table cellspacing="0" cellpadding="0" border="0"><tr><td valign="top" style="font: inherit;">I think the bad result of llvm can be explained because of the lack of muladd support currently. Unigine 3.0 has a lot of geometry and i suspect vertex shader being almost twice bigger than they are in tgsi case does not help. Fwiw with an hd 6950 I have the same performance in unigine 3 high, medium texture, no ssao (it seems to use indirect addressing) with llvm backend as high, high texture, no ssao with fglrx under Windows. Its not a fair comparaison but I think 3.8 kernel may provide the necessary boost to cope up with fglrx. Anyways I have some fps peak at 60fps that does not show up with tgsi backend that I also have with fglrx that makes me think llvm backend generates rather efficient code, but i always cherry pick muladd patches. </td></tr></table> <div id="_origMsg_"> <div style="font-family:arial, helvetica, sans-serif:font-size:10pt"> <div style="font-family:times new roman, new york, times, serif;font-size:12pt"> <hr size="1"> From: Michel Dänzer <michel@daenzer.net>; To: Vadim Girlin <vadimgirlin@gmail.com>; Cc: <mesa-dev@lists.freedesktop.org>; Subject: Re: [Mesa-dev] r600g: status of my work on the shader optimization Sent: Fri, Feb 15, 2013 12:06:20 PM <table cellspacing="0" cellpadding="0" border="0"> <tbody> <tr> <td valign="top" style="font:inherit;">On Fre, 2013-02-15 at 15:00 +0400, Vadim Girlin wrote: > On 02/14/2013 02:42 PM, Christian König wrote: > > > > nice work, I think you've made quite a progress here, but on the other > > hand it should be clear that the LLVM backend is the future and we > > should concentrate on that. > > "LLVM backend is the future" is a pretty abstract argument. I prefer to > operate with real facts. After a year of LLVM backend development what > are the real benefits for the users? What are the real use cases where > the users might prefer LLVM backend? To me this situation looks like the > use of LLVM requires a lot more time and development efforts than the > custom solution, despite the initial expectations. Maybe you are right > and the LLVM backend will become the best alternative for users sometime > in the future, but I only have some today's results: > > Heaven 3.0, all settings high/enabled, 1280x720, HD5750: > default backend : 20.0 fps > llvm backend : 18.8 fps > r600-sb : 38.0 fps > > When I'm looking at these results, the benefits of LLVM-based solution > are not very clear to me. Those are really impressive numbers, but to put things into perspective a little bit: When comparing two solutions, there will always be cases where one beats others like this. I think I've also seen reports of cases where the LLVM backend provides similar speedups over the default one, though of course your branch might still be even better there. Also, it's not like the LLVM backend for r600g has been heavily tuned for performance over the last year. Most of the effort went into support for radeonsi and compute support for r600g. Only recently have people like Vincent started making serious improvements to the LLVM backend for r600g graphics support. It might be possible to apply at least some of the lessons learned from your branch to the LLVM backend as well. -- Earthling Michel Dänzer | <a href="http://www.amd.com" target=_blank >http://www.amd.com</a> Libre software enthusiast | Debian, X and DRI developer _______________________________________________ mesa-dev mailing list <a ymailto="mailto:mesa-dev@lists.freedesktop.org" href="javascript:return">mesa-dev@lists.freedesktop.org</a> <a href="http://lists.freedesktop.org/mailman/listinfo/mesa-dev" target=_blank >http://lists.freedesktop.org/mailman/listinfo/mesa-dev</a> </td> </tr> </tbody> </table> </div> </div> </div>