On Wednesday 06 July 2005 09:15, Silvan wrote: > > Could it be an HT difference too? This is not an HT processor.
Neither is mine, and AFAIK hyperthreading makes a difference for multitasking, not single processes. > Although we all need to bear in mind that even as crappy as this > performance is, it's still on the very good end of the range of hardware > people are running RG on. No question about that. The fact that the old canvas was running more smoothly on that machine means I have to improve things. > and forth twice, so I only did it once. I'm really about to fall over in > my chair here, but it looks to me like -O3 made everything tremendously > worse. > > > -O0, back and forth twice > -> CompositionModelImpl::getRectanglesIn: CPU: 1160 calls, 1010ms, > 870.69us/call [...] > -O3, back and forth once > -> CompositionView::drawArea: CPU: 513 calls, 10410ms, 20292.4us/call Yikes. For the record, what gcc version are you using ? Though I haven't tried with -O3 either... you might want to try with -O2, in some cases pushing optimisation too much does worsen performance. -- Guillaume. http://www.telegraph-road.org ------------------------------------------------------- SF.Net email is sponsored by: Discover Easy Linux Migration Strategies from IBM. Find simple to follow Roadmaps, straightforward articles, informative Webcasts and more! Get everything you need to get up to speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click _______________________________________________ Rosegarden-devel mailing list Rosegarden-devel@lists.sourceforge.net - use the link below to unsubscribe https://lists.sourceforge.net/lists/listinfo/rosegarden-devel
