Slashdot Mirror
AMD's Athlon-64 Benchmarked With UT2003
Sander Sassen writes "Wondering about the performance of AMD's Athlon-64? Want to how well it runs in 64-bit mode? Hardware Analysis managed to run a few benchmarks on a AMD Athlon-64 demo system using the 64-bit version of Epic' Unreal Tournament 2003. There's also an update with the latest about Athlon-64, Opteron and mobile Athlon-64 including streaming video and pictures of a quad Opteron server."
I was about to chime in with similar comments- but it's so much better when the person that did the work (and knows what in the Hell he's talking about) says it.
I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
i would have to say that this article is about as worthless as the bill gates quotations earlier, int terms of actual usefullness and truthfullness. since everything is prerelease and the details are fairly sketchy, im gonna wait for solid numbers before i decide once and for all who i will be loyal to in the proccesor world.
how well are the drivers for the gefore card working? are they playing nice with that k8t400? are the nvidia drivers 64bit or are they being run in "32-bit" mode? how well is OpenGL playing with the 64-bit OS, 64-bit Chip combo and again, how well are the nvidia drivers playing? is the OS running the AGP in AGP mode or is it PCI mode?
i bet i could easily get a P4 2.7 with this graphics card to product similar numbers, or even worse in linux with some effort to use least optimized drivers and setting the graphics card to PCI.
in fact, my P4 2.4x133@2.7x150 with a GF Ti 4600 doesn't post much better numbers, 55fps by stat fps. and thats on a 32bit "system" with fairly mature drivers and everything work "correctly/fullspeed"
im not an AMD zealot, but i wont make me decision based on a game that is notoriously bad at opengl and on a system that is running all beta software/drivers.
Let's not get over-excited... This is of course interresting information, but it's information of a premature chip on a premature platform.
I doubt that any proper conclusions can be drawn from this, apart from what is already known: The Athlon 64 isn't ready yet. If was the release date wouldn't be set for September.
Much like with Doom III, there is always a cool-factor, but the actual facts at hand are very scarse. One thing is probably for sure though... The Hammer core can't compete with the Barton core on the desktop at this point. Otherwise we'd have the Athlon 64 waiting to be released much sooner.
.: Max Romantschuk
I curious... how do the extra bits per clock cycle supposed to increase performance? I mean the number of instructions per second don't increase...
Yuioup
The article said that there will be benchmarks. And there are none. A screen shot of a game does not qualify. I want to see the whole spec or at least the basic ones. And after that I can look at the game snapshot.
Moderator seriously why this posted with such a misleading title?
Those Tom's scores have to be from flyby benchmarks, since there's no way you're getting 200+ average FPS in-game or with a botmatch benchmark. Seeing 2x to 3x higher FPS in flyby mode isn't at all unusual, so comparing the in-game FPS to those benches isn't fair even before you factor in the beta-upon-beta nature of the test.
Encoding a full D1 stream to mpeg2 would certainly take the postulated amount of time.
And forget doing anything else with the computer while it's rendering. It will start dropping frames like mad, and you have to start over.
Unless you're talking about capturing, which you *will* have to be able able to do in real-time to avoid losing frames, how exactly do you manage to lose frames during rendering? The only way I can think of is by working on a preview while the "real" render is made from tape, but that'll require you do to the actual render in real-time too. Frankly, you're not making any sense to me.
Kjella
Live today, because you never know what tomorrow brings
I call BS on that. There was a noticeable improvement when moving from AGP 1x to 2x. The difference was nonexistant when moving from 2x to 4x. Same thing when moving from 4x to 8x. AGP is definitely NOT the bottleneck!
Lesbian Nazi Hookers Abducted by UFOs and Forced Into Weight Loss Programs - -all next week on Town Talk.
There was nothing to this artice. Here is what I learned from reading this article: 1)there's a 64-bit linux port of UT 2003 2)amd likes secrecy 3)the people who were showing off the laptop like Harry Potter wow. now wasn't that informative?
"Some kind of database benchmark." Thanks for that insightful analysis of the 4-way, and pimping your own site on Slashdot. Tasteless!
"Unreal Tournament 2003 runs about 5-10 times quicker on Debian GNU/Linux than Windows 98SE (and Windows is on the faster drive.)"
Your Windows install is completely borked then. There is no way UT run 5-10 times or even 2 times faster under linux than it does under Windows. Its generally accepted that UT2k3 is slower on linux(OpenGL) than on windows(Direct3d) as the developer himself states here. For myself personally(XP1900,512MB,GF4200,~10,000 3dmarks) its defintely much slower in linux and that's a direct result of Epic foolishly(direct3d ain't cross-platform) making UT2k3 a direct3d game from the ground up. Luckily RTCW has no such problems so its what I continue to play daily.
If you wanna get rich, you know that payback is a bitch
There's an updater you can run or download the latest patches for linux and install manually no problem. The versions are the same as the windows patches. I run it on my FreeBSD 4.7-STABLE box and it works great. I can even run the updater to keep it current. Some people have had problems running the updater on FreeBSD but they can still download the patches and manually run them.
Were you trolling or talking about something else?
You shouldn't be benchmarking with a game. The graphics card then plays a big role in the final results. There should be some cpu specific benchmarks that should be used. Wait for the Tom's Hardware tests. Guy has about 10 different benchmarks.
Yeah, I'd say this comparison isn't even as good as apples to oranges... more like apples to pasta. In order to benchmark performance, as many variables as possible need to be the SAME other than the one you're testing. A better test would be: Windows XP running the game vs. Windows XP (coded and compiled for 64 bit for Athlon 64) running a non-beta 64 bit version of the game I'd like to at least see benchmarks comparing the game under SUSE Linux to the 64 bit game under SUSE 64 for Athlon 64 so I can judge for myself rather than taking the reader's word that the frame rates aren't "good".