On Sat, 1 Oct 2011 11:19:20 -0700 Jim Kukunas <james.t.kuku...@linux.intel.com> said:
> On Sat, Oct 01, 2011 at 01:08:46PM +0900, Carsten Haitzler wrote: > > On Fri, 30 Sep 2011 13:31:57 -0700 Jim Kukunas > > <james.t.kuku...@linux.intel.com> said: > > > > some performance comparisons: > > > > http://www.enlightenment.org/~raster/evas/atom-450n-xlib-vs-gl.html > > http://www.enlightenment.org/~raster/evas/celeron-xlib-vs-gl.html > > http://www.enlightenment.org/~raster/evas/i5-2500-xlib-vs-gl.html > > > > slight problem with intel drivers: they want to vsync clients... thus limit > > max framerate to screen refresh (about 60fps). any way to disable that via > > some env var or config? (evas only specifically asks for vsync via opengl > > api's (swapinterval) if asked at init time). so let's assume where the > > tests level out at about 60fps for gl.. gl could do better. the gma3150 is > > still nasty-slow for text (high geometry) stuff. > > I think you can disable vsync by adding the following line to your > Xorg.conf, under the intel device section: > > Option "SwapbuffersWait" "false" i also had to fiddle with /etc/drirc too and throw some magic xml in there. i updated the results not with 3150 and 945gm getting a fairer result with no vsync limiting. -- ------------- 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