> On 2002.03.13 19:21 Brian Paul wrote: > > ... > > > > But if the Mach64 chip is the bottleneck, no amount of > (conventional) > > driver optimization will improve the results. It _really_ > depends on > > the particular application. > > > > -Brian
That means if the triangles are big then pretty few to do with CPU. If you have display lists and much vertex data, then a TCL might give you big advantage. For texturing its advantagoues if the hardware is driven to do multitexturing. Performance optimisation is a rather individual subject. Some applications do never benefit from a particular optimisation. > This is something that intrigues me most for some time now. I > get a little > more than 10 fps on UT with the mach64 driver as it is (just > MMIO), but I > get about 20 steady fps with software rendering on my P3 > Celeron 700Mhz. I > can not understand how come this can be. Even though there > are a lot of > artifacts in the sw rendering, it has a much nicer global appearance. > > Is this the kind of performance that one can expect from a > PIO only card > (I'm thinking of tdfx for example here)? If you want so see specific perfomance, you should try glperf. Thats one of the important feedbacks on your specific works. Regards, Alex. _______________________________________________ Dri-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/dri-devel