Hi Paul, On 06/15/13 01:12, Paul McIntosh wrote: > I have done a couple of experiments with very large displays (e.g. 7680x4800, > 7680x3200) and the performance has (understandably) dropped significantly. > > Are there any tricks to improving the performance or is it not worth trying? > I recall multi-threaded builds but have not had a chance to try them out. > > The tests so far have been on less than optimal links - we will be trying a > long hall 1G network soon (across Australia) and possibly a shorter 10G link > (from one facility on campus to another). Would bigger pipes solve the issue > or is the bottle neck be elsewhere? I've done some similar tests, mostly at 3840x2160 over a 10G link. I seemed to hit a bottleneck of about 10 fps, but so far assumed it was the readback from the GPU that was the problem (GTX680 in a PCI Express x16 slot), judging from the vglrun +pr output. I still need to verify this in some way, but it is yet another piece of the pipeline that might cause problems for attaining good performance.
Regards, Paul ------------------------------------------------------------------------------ This SF.net email is sponsored by Windows: Build for Windows Store. http://p.sf.net/sfu/windows-dev2dev _______________________________________________ VirtualGL-Users mailing list VirtualGL-Users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/virtualgl-users
