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."
As promised we'll give you an update on the performance and other features of the AMD systems that we reported on yesterday. Naturally AMD wasn't very keen on disclosing clockspeed or detailed system configurations of the demo systems they had running, but we took advantage of a few fellow journalists entering the room and keeping the AMD PR people busy to run a few quick benchmarks on the Athlon-64 system. The Athlon-64 demo system we already reported on yesterday had a 2GHz clockspeed and used the SuSe 64-bit Linux operating system and was running the 64-bit version of Unreal Tournament 2003 as a demo.
(pic of monitor playing UT2k3, FPS = 42)
Fig 1. The Athlon-64 system running SuSe 64-bit Linux and the 64-bits version of Unreal Tournament 2003.
Naturally we're intimately familiar with the workings of Unreal Tournament 2003 engine and after a quick look at the display settings, which were set at a 1024x768x32bit resolution with all other features at default, we measured a mere average 42fps and maximum fps around the 55...60fps mark. Considering the fact that this is a 2GHz Athlon-64 processor teamed up with a GeForce Ti 4600 we honestly expected a whole lot better. A 1.6GHz Pentium 4 with that very same GeForce Ti 4600 videocard would have no problems clocking in a similar score while running under Windows XP.
(pic of a white laptop with the terminal showing)
Fig 3. The Athlon-64 notebook running CyberLink's PowerDVD actually showing the first Harry Potter movie.
But there's more, we managed to take a closer look at the notebook too and quickly found out that this indeed is a proof of concept. It plays DVDs very well, mostly courtesy of the ATi M9-series graphics card, and unfortunately all our questions about whether we could do something else with it were answered with a resounding 'no'. We did however manage to find out what was inside in terms of chipset, memory and graphics card. The notebook apparently used a Via K8T400M chipset teamed up with an ATi M9-series graphics adapter and was using PC2100, DDR266, memory. The screen was a standard 14.1 inch running at a 1024x768 resolution and the DVD software they used was none other than CyberLink's PowerDVD.
(naked pizza-box style case)
Fig 2. The quad Opteron server with the top cover removed, the PCI-X slots in the back and a the four CPUs hidden underneath the huge heatsinks.
(two white LCDs next to each other, left showing a web browser and right showing UT2k3.)
Fig 3. The quad Opteron with the SuSe 64-bit Linux operating system running some sort of a database benchmark, right next to the UT2003 demo machine.
We naturally also took a closer look at the quad Opteron as that's definitely something AMD is currently pushing hard. They're putting all their weight behind the launch of their server products and have postponed the launch of the desktop version of the Opteron, the Athlon-64, back to September. The server parts, including completely pre-configured two-way Opteron systems, should be available in late April, right after the April 26th launch of the Opteron server CPU family. Clockspeeds will initially range up to 1.6 or 1.8GHz and performance is expected to be similar to Intel's Xeon offerings. But as always, we'll reserve judgement until we can actually evaluate two similarly configured servers side by side, for now all they have given us are SpecInt-2000 and SpecFP-2000 scores without disclosing the system configurations, so that doesn't tell us anything.
Nevertheless it looks like AMD is indeed trying to get some new and innovative products out of the door. Whether they'll be able to make a lasting impression, both in terms of features and performance, with their new 64-bit products remains to be seen though, we'll be sure to keep a close eye on any future developments.
Sander Sassen.
Ok, wait.
I'm the developer that did the 64-bit port of UT2003 (and the Linux port, and the Mac port...).
You need to keep two things in mind:
1) The OpenGL renderer is not as fast as the Direct3D renderer at this time. This is not the Athlon64's fault. You can see this on 32-bit Windows, since it can use both renderers. Since this is a Linux port of the game, we're using the GL renderer on the Athlon64 at this time.
2) The "stat fps" command isn't really a good benchmarking method.
3) This is a prerelease version of the game running on a prerelease version of SuSE running on prerelease drivers running on prerelease hardware. Please don't consider this "benchmark" to be representative!
--ryan.
Don't say, "don't quote me," because if no one quotes you, you probably haven't said a thing worth saying.
The site, with just a few comments on /., is already showing signs of slashdotting. I'll quote the most important parts about the UT 2003 benchmark, just in case:
"The Athlon-64 demo system we already reported on yesterday had a 2GHz clockspeed and used the SuSe 64-bit Linux operating system and was running the 64-bit version of Unreal Tournament 2003 as a demo."
-snip-
(at 1024x768x32...) "we measured a mere average 42fps and maximum fps around the 55...60fps mark. Considering the fact that this is a 2GHz Athlon-64 processor teamed up with a GeForce Ti 4600 we honestly expected a whole lot better."
Beware: In C++, your friends can see your privates!
http://www.nvidia.com/view.asp?IO=linux_amd64_disp lay_archive
And to be honest about it, Back five years it would take you DAYS to render the same amount of video. So give it a while longer, you'll be alright.
I really think that the 4-way system niche is so small that even AMD went to try to fill it, it would not be worth their investment.
On the other hand, I would like to see more selections of dual platforms. But as you may see even the demand for those are few and far between.
Back to the original thing: you can do "fast previews" on most 3D programs now if you got a good video card; I don't see how you can gripe that much about it; for long runs just leave it running overnight. or hell, maybe cheap render-farm out of Xboxes =)
My life in the land of the rising sun.
It depends on what you're doing.
I do video, and I work using HDTV 1080i/p 30fps (1920x1080) 16bit float (4x16bit R/G/B/A).
If you work with mattes and do a little compositing, you need a hell of a workstation to do this work, and rendering even a single frame can take up to 15min or even more...
So there may be a market for 4 CPU workstations. Take a look at www.quantel.com, even for video/ film work there are dedicated workstations.
...which you would expect if you'd never actually looked at any of the UT2K3 benchmarks on the net that show frame rate scaling linearly with CPU speed.
3 &p =13
for example - with a Radeon 9700:
botmatch:
Intel Pentium 4 1.5GHz = 35.5 FPS
Intel Pentium 4 3.06GHz = 69.6 FPS
flyby:
Intel Pentium 4 1.5GHz = 114.5 FPS
Intel Pentium 4 3.06GHz = 205.5 FPS
http://www.anandtech.com/cpu/showdoc.html?i=178
I'm not saying the original article made a fair comparison, but the game really does rely on the CPU a lot more than you seem to think.
And here another thing people don't realize: making everything 64 bits doesn't necessarily make programs go faster. With 64 bits, you have more pressure on the cache, on the bus, on the memory, etc...
erm. not true.
EVERYBODY (I am serious) went to win2k pretty much as soon as it came out. and that supports SMP out of box.
If you don't believe me, just think how many people exactly uses their parallel "home OS?" This would be windowsME, btw.
People who didn't want to shell out the dough generally sticked with win98; the ones who saw the need generally went with win2k - and that's a lot of people.
besides - dual CPU really wasn't a big deal until about that time when win2k was *just* about to come out anyhow. They were big for a while - especially when the celerons could be hacked into dualie systems, but now their demand seems to have waned, especially in a large part due to the fact that you have to shell out xeon dollars do get an intel dual setup.
It's definitely not because of the OS(s); linux and BSD had SMP support even before win2k was there - in the stable builds.
My life in the land of the rising sun.
There have been some disappointed posters, wondering why it isn't faster. Stop and think about it: Why would a 64-bit CPU be faster than a 32-bit CPU? It's not bus width, because Pentiums have always had 64-bit busses. It's not FPU width, because x86 FPUs have always been 80 bits internally. It's not 64-bit integer registers, because it's very rare indeed to need to do 64-bit integer math. It's not 64-bit pointers, because this is a machine with less than 4GB of memory. What it comes down to is that this processor is using slightly newer tech than AMD's previous chips, including a larger cache. But it has nothing whatsoever to do with being 64 bits, and hence the results are not mindblowing.
There's a persistant myth that a 64-bit processor is twice as fast as a 32-bit processor, which is completely incorrect.
Naturally we're intimately familiar with the workings of Unreal Tournament 2003 engine and after a quick look at the display settings, which were set at a 1024x768x32bit resolution with all other features at default, we measured a mere average 42fps and maximum fps around the 55...60fps mark. Considering the fact that this is a 2GHz Athlon-64 processor teamed up with a GeForce Ti 4600 we honestly expected a whole lot better. A 1.6GHz Pentium 4 with that very same GeForce Ti 4600 videocard would have no problems clocking in a similar score while running under Windows XP.
"Intimately familar"? Hardly. If they were intimately familiar with the engine, they would have known that it is not optimized for OpenGL, and that comparing Direct3D to OpenGL under Windows OR Linux is not a good or fair comparison.
Neither the Windows OpenGL renderer nor the Linux OpenGL renderer score the same as the D3D one.
You can see a real comparison of OpenGL and Direct3D here
Why do I keep typing pythong?
Which might indicate that vsync is enabled, effectively capping the the max fps while lowering the average. Whenever I run a benchmark and it tops out at 60 fps and I suspect, as these guys did, that the machine should be faster, I always double check the refresh rate settings and vsync.
-dameron