Linux 3D AGP GPU Roundup: More Cutting Edge Penguin Performance
by Kristopher Kubicki on October 4, 2004 12:05 AM EST- Posted in
- Linux
The Test
Below, you can see our test rig configuration.| Performance Test Configuration | |
| Processor(s): | AMD Athlon 64 3800+ (130nm, 2.4GHz, 512KB L2 Cache) |
| RAM: | 2 x 512MB Mushkin PC-3200 CL2 (400MHz) |
| Motherboard(s): | MSI K8T Neo2 (Socket 939) |
| Memory Timings: | Default |
| Hard Drives: | Seagate 7200.7 120GB SATA |
| Video Cards: | GeForce 6800 Ultra 256MB GeForce 6800 128MB GeForceFX 5950 Ultra 256MB GeForceFX 5900 Ultra 128MB GeForce 5900 128MB GeForceFX 5700 Ultra GeForceFX 5600XT Radeon X800 Pro 256MB Radeon 9800XT 256MB Radeon 9700 Pro 128MB Radeon 9600XT 128MB |
| Operating System(s): | SuSE 9.1 Professional kernel 2.6.8-14-default |
| Driver: | (ATI) SuSE 9.1 Supplement fglrx 3.12.0 NVIDIA 1.0-6111 |
You may have noticed that we are running an extremely new version of the Linux kernel, and very new ATI and NVIDIA drivers as well. For all intents and purposes, we are running a completely default SuSE 9.1 Professional install with the SuSE 9.2-RC3 kernel and brand new drivers. This was not an easy accomplishment, but was unfortunately the only manner in which we could install a platform compatible with both ATI and NVIDIA video cards on the Socket 939 architecture.
Our testing procedure is very simple. We take our various video cards and run respective time demos while using our AnandTech FrameGetter tool. We rely on in-game benchmarks for some of our tests as well - since FG will not run on Wine games. We post the average frames per second scores calculated by the utility. Remember, FG calculates the frames per second every second, but it also tells us the time that our demo ran, and how many frames it took. This average is posted for most benchmarks.
However, when testing our games, we find that some interesting patterns sometimes occur. For these instances, we have specially crafted the FG program to record our timedemo by taking the frames per second every second and dumping this data into a text file. We explained this in our initial FG announcement. Some graphs, particularly Wolfenstein and Unreal Tournament, have particularly fascinating trends, which we explore more in the evaluation.
All of our benchmarks are run three times and the highest scores obtained are taken - and as a general trend, the highest score is usually the second or third pass at the timedemo. Why don't we take the median values and standard deviation? For one, IO bottlenecks tend to occur due to the hard drive and memory, even though they "theoretically" should behave the same every time that we run the program. Memory hogs like UT2004, which tend to also load a lot of data off the hard drive, are notorious for behaving strangely on the first few passes.
Since we had issues with the ATI driver running Anisotropic Filtering, we did not run any tests with AF on. However, many of our games have sets of benchmarks with 4X Anti Aliasing disabled and enabled. At the end of this analysis, we also have a small section showing some of the differences with the various AA and anisotropic filters enabled.
Facebook
Twitter
RSS
33 Comments
View All Comments
adt6247 - Monday, October 4, 2004 - link
Good article. The one thing that I thought was lacking is the comparison to FPS's under Windows. That would be incredibly useful.One more thing -- nVidia actually has a graphical configuration panel for Linux. I forget what it's called; I use it all the time to set AA/AF settings on my box, but my machine is at home, and I'm at work now. I'll post later with the name of the binary.
adt6247 - Monday, October 4, 2004 - link
KristopherKubicki - Monday, October 4, 2004 - link
Ziast: Fixed.Kristopher
Ziast - Monday, October 4, 2004 - link
Nice article except for this glaring mistake:"All in all, just getting the ATI drivers on something that isn't Red Hat feels like way too much work for basic OpenGL support. Keep in mind that we even run SuSE, a Red Hat derivative."
SuSe Linux was first released in 1993. Red Hat Linux was not released until 1994. Just because SuSe uses RPM doesn't mean it's a Red Hat derivative.
Papineau - Monday, October 4, 2004 - link
Two RFEs, one for the article, the other for FG.For the article: Would it be possible to graph the ratio of FPS from one card to the other one over time? That would help to know if a card is "always 1.5 times faster than the other", or "sometimes even, sometimes faster, usually slower than the other".
For FG: Why modify the executable file? Why not use LD_PRELOAD/LD_LIBRARY_PATH to load the lib you want to insert (libFG), and then have it call the system's libGL and libSDL? It seems a bit "bad practice" to modify the benchmarked executable.
Term - Monday, October 4, 2004 - link
#6I get more FPS with Linux in both Quake1(World) and Quake3 (single and dual cpu) then with Windows2000. Thow I suspect that if you have a newer card then you might not, due to the drivers.
Cygni - Monday, October 4, 2004 - link
When 64bit Windows finally ships, and the entire Athlon64 and Opteron user base switches over, including many gamers, the pressure will be on for ATI, and judging by how good their driver team has been in the 32bit Win sector these last few months, hopefully they can rise to the challenge.As far as Linux drivers for speed? I hate to break the news to alot of people, but gaming on Linux is a HUGE chore with little payoff. Ive spent HOURS with clean installs of Mandrake to play games I already have for Windows... only to, of course, see that they are slower than their windows counterpart. Linux is great for alot of stuff, and ive always got a computer somewhere running Mandrake 9.1... but it just ISNT for gaming right now, which I think the review helped illustrate nicely.
ViRGE - Monday, October 4, 2004 - link
I wouldn't be too excited about ATI's 64bit Linux plans, let alone even their 64bit Windows plans. Their only 64bit drivers are over 4 months old, and don't support any of the X-series of cards, which really limits their usefulness. ATI has said before that they may not ship another build until some time in 2005.raylpc - Monday, October 4, 2004 - link
"we received some information from ATI about some upcoming Linux announcements which they are working on"I remember ATi is working on some "plan", so the actual driver release could be way after. Well, nvidia is probably the next card I'm going to get.
Saist - Monday, October 4, 2004 - link
my first thought was:how in the world can an Geforce FX MATCH and BEAT the R300 architecture. I guess if you ever wanted empirical proof that ATi has ignored Linux, this is it.