On Sat, 01 Oct 2011 08:25:16 +0100 Rui Miguel Silva Seabra <r...@1407.org> said:
> Em 01-10-2011 03:36, Carsten Haitzler (The Rasterman) escreveu: > > On Fri, 30 Sep 2011 22:37:07 +0100 Rui Miguel Silva Seabra<r...@1407.org> > > said: > > > >> Em 30-09-2011 18:46, Jim Kukunas escreveu: > >>> On Fri, Sep 30, 2011 at 12:39:20PM +0900, Carsten Haitzler wrote: > >>>> On Thu, 29 Sep 2011 10:42:29 -0700 Jim Kukunas > >>>> <james.t.kuku...@linux.intel.com> said: > >>>> > >>>> well.. lucas committed this without me getting around to my review... i > >>>> found several issues with it. A_MASK_SSE3 was being declared all the time > >>>> and never used in the inline funcs. it was ONLY used in 1 of the c files. > >>>> i moved it there. also you called the C init funcs for rel ops - not the > >>>> sse3 ones. copy& paste bug. also unused return value warnings in cpu > >>>> sse3 detection function. > >>> Whoops. Thanks for fixing these issues. > >>> > >>>> i ran a full expedite run: > >>>> > >>>> http://www.enlightenment.org/~raster/speed.html > >>>> > >>>> (i5-2500 CPU @ 3.30GHz, GeForce GTS 450, e17 running with OpenGL > >>>> compositor). > >>>> > >>>> just as a comparison - after the sse3 speedups, speed vs the nvidia gpu: > >>>> > >>>> http://www.enlightenment.org/~raster/speedgl.html > >>>> > >>>> i haven't tested against an atom yet. > >>> Cool. I think these patches really shine on the atom. > >>> > >>> There is a much bigger difference between 21 frames and 46 frames, then > >>> betweeen 179 frames and 397 frames. > >> That's awesome for my Atom tablet with a GMA3150, also running the Free > >> Software drivers. > >> > >> I notice in raster's comparison that some items get dramatically worse, > >> even though overall it's an amazing improvement which I'm going to > >> compile this weekend :) > > actually only "worse" items are the text rendering. those are between 5-15% > > slower after patches. that was something i was going to bring up that > > slightly disturbed me. it's easy to see the little blob of redness in the > > table: > > > > http://www.enlightenment.org/~raster/speed.html > > > >> Do you think you could visit them specifically, and perhaps make them go > >> much better rather than the current 80% worse or similar? :) > >> > >> Good job, anyway, good job! > I saw, earlier, a lot more reds, some of them with -80%. > > Did you spot a mistake in your measuring and fixed it? Now I don't see > those anymore :) hmm no - that may have been the xlib vs gl u saw... some things are not faster in gl. -- ------------- Codito, ergo sum - "I code, therefore I am" -------------- The Rasterman (Carsten Haitzler) ras...@rasterman.com ------------------------------------------------------------------------------ All of the data generated in your IT infrastructure is seriously valuable. Why? It contains a definitive record of application performance, security threats, fraudulent activity, and more. Splunk takes this data and makes sense of it. IT sense. And common sense. http://p.sf.net/sfu/splunk-d2dcopy2 _______________________________________________ enlightenment-devel mailing list enlightenment-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/enlightenment-devel
