Date: Fri, 4 Jan 2002 17:29:08 -0500 From: Randall Hopper <aa8vb@nc.rr.com> To: Bjarne Wichmann Petersen <nospam.nospam@mekanix.dk> Cc: freebsd-multimedia@FreeBSD.ORG Subject: Re: OpenGL Message-ID: <20020104172908.A62346@nc.rr.com> In-Reply-To: <20020104185158.RCWJ16766.fepD.post.tele.dk@there>; from nospam.nospam@mekanix.dk on Fri, Jan 04, 2002 at 07:52:59PM %2B0100 References: <20020103212324.ILQT16766.fepD.post.tele.dk@there> <20020103152948.M2739-100000@resnet.uoregon.edu> <20020104123901.A1156@nc.rr.com> <20020104185158.RCWJ16766.fepD.post.tele.dk@there>
next in thread | previous in thread | raw e-mail | index | archive | help
--sm4nu43k4a2Rpi4c Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Bjarne Wichmann Petersen: |Randall Hopper: |> 3197 frames in 5.0 seconds = 639.400 FPS | |Ok.. I'm pulling someting like ~667 FPS Scratch -O2. No real difference I found. Next question: can you mail me your XF86Config? Lots of things in there that can influence our results. Thanks! Re: gltron, I'm getting avg 98 with the 320x240. With 640x480 it's over 90 max, but is very dependent on number of cycle tracks (10-98, w/ avg maybe 40. Cool game, but not a great program as far as generating a useful benchmarking number. See how your "benchclock" numbers compare (see attached). This is from the glclock port. Re: tuxracer -- Cool game! I'd never tried that one before. My FPS is in the 70-80 range most of the time (this is at the default 640x480, full screen, music/sounds on). I see the same for bpp_mode's 0,1,&2, so I suspect it's always running 16bpp as that's my X depth. I fired it up with bpp_mode 0 from a 24bpp root, and got the same results. So there's another puzzle for us to solve: why your tuxracer is so slow. Are you sure you're linked with the HW accelerated libGL and not a software-only Mesa libGL (ldd /usr/local/bin/tuxracer | grep 'libGL\.')? Randall -- Randall Hopper aa8vb@nc.rr.com --sm4nu43k4a2Rpi4c Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="bench.log" glclock-4.5 benchmark test. 1. double buffers 339.50 FPS 625359 TPS at 1842 Triangles 2. single buffer 340.40 FPS 627016 TPS at 1842 Triangles 3. environment mapping double buffers 331.53 FPS 619905 TPS at 1870 Triangles 4. environment mapping single buffer 352.07 FPS 656744 TPS at 1870 Triangles 5. bi-linear environment mapping double buffers 340.10 FPS 635987 TPS at 1870 Triangles 6. bi-linear environment mapping single buffer 348.57 FPS 651882 TPS at 1870 Triangles 7. tri-linear environment mapping double buffers 352.63 FPS 659549 TPS at 1870 Triangles 8. tri-linear environment mapping single buffer 358.64 FPS 670582 TPS at 1870 Triangles 9. tri-linear shading texture double buffers 271.27 FPS 507331 TPS at 1870 Triangles 10. tri-linear shading texture single buffer 265.88 FPS 497233 TPS at 1870 Triangles 11. tri-linear transparency texture double buffers 328.47 FPS 614295 TPS at 1870 Triangles 12. tri-linear transparency texture single buffer 327.14 FPS 611864 TPS at 1870 Triangles 13. tri-linear transparency texture with over sampling double buffers 207.96 FPS 444906 TPS at 2140 Triangles 14. tri-linear transparency texture with over sampling single buffer 208.52 FPS 446190 TPS at 2140 Triangles 15. tri-linear shading texture transparency texture double buffers 199.92 FPS 639280 TPS at 3198 Triangles 16. tri-linear shading texture transparency texture single buffer 200.52 FPS 641199 TPS at 3198 Triangles 17. tri-linear shading texture transparency texture high quality clock double buffers 61.60 FPS 853406 TPS at 13854 Triangles 18. tri-linear shading texture transparency texture high quality clock single buffer 62.06 FPS 858948 TPS at 13854 Triangles --sm4nu43k4a2Rpi4c-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-multimedia" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020104172908.A62346>