Slashdot Mirror
Hands On With Nvidia's New GTX 280 Card
notdagreatbrain writes "Maximum PC magazine has early benchmarks on Nvidia's newest GPU architecture — the GTX 200 series. Benchmarks on the smokin' fast processor reveal a graphics card that can finally tame Crysis at 1900x1200.
'The GTX 280 delivered real-world benchmark numbers nearly 50 percent faster than a single GeForce 9800 GTX running on Windows XP, and it was 23 percent faster than that card running on Vista. In fact, it looks as though a single GTX 280 will be comparable to — and in some cases beat — two 9800 GTX cards running in SLI, a fact that explains why Nvidia expects the 9800 GX2 to fade from the scene rather quickly.'"
http://anandtech.com/video/showdoc.aspx?i=3334
http://techreport.com/articles.x/14934
Conclusion: 9800GX2 is faster and cheaper
In most reviews, the 9800GX2 is faster, and it's also $200 cheaper. As a multi-GPU card it has some problems with scaling, and micro-stutter makes it very jumpy like all existing SLI setups.
I'm not well versed in the cause of micro-stutter, but the results are that frames aren't spaced evenly from each other. In a 30 fps situation, a single card will give you a frame at 0 ms, 33 ms, 67 ms, 100 ms, etc. Add a new SLI card and let's say you have 100% scaling, which is overly optimistic. Frames now render at 0 ms, 8 ms, 33 ms, 41 ms, 67 ms, 75 ms, 100ms, and 108ms. You get twice the frames per second, but they're not evenly spaced. In this case, which uses realistic numbers, you're getting 60 fps might say that the output looks about the same as 40 fps, since the delay between every other frame is 25 ms.
It would probably look a bit better than 40 fps, since between each 25 ms delay you get an 8 ms delay, but beyond the reduced effective fps there are other complications as well. For instance, the jitter is very distracting to some people. Also, most LCD monitors, even those rated at 2-5 ms response times, will have issues showing the 33 ms frame completely free of ghosting from the 8 ms frame before the 41 ms frame shows up.
Most people only look at fps, though, which makes the 9800 GX2 a very attractive choice. Because I'm aware of micro-stutter, I won't buy a multi-GPU card or SLI setup unless it's more than 50% faster than a single-GPU card, and that's still ignoring price. That said, I'm sort of surprised to find myself now looking mostly to AMD's 4870 release next week instead of going to Newegg for a GTX280, since the 280 results, while not bad, weren't quite what I was hoping for in a $650 card.
"I zero-index my hamsters" - Willtor (147206)
Because graphics operations are embarrassingly parallel whereas regular programs arn't.
Full Tilt
Only you can prevent FUD!
You may be wondering, with a chip this large, about power consumptionâ"as in: Will the lights flicker when I fire up Call of Duty 4? The chip's max thermal design power, or TDP, is 236W, which is considerable. However, Nvidia claims idle power draw for the GT200 of only 25W, down from 64W in the G80. They even say GT200's idle power draw is similar to AMD's righteously frugal RV670 GPU. We shall see about that, but how did they accomplish such a thing? GeForce GPUs have many clock domains, as evidenced by the fact that the GPU core and shader clock speeds diverge. Tamasi said Nvidia implemented dynamic power and frequency scaling throughout the chip, with multiple units able to scale independently. He characterized G80 as an "on or off" affair, whereas GT200's power use scales more linearly with demand. Even in a 3D game or application, he hinted, the GT200 might use much less power than its TDP maximum. Much like a CPU, GT200 has multiple power states with algorithmic determination of the proper state, and those P-states include a new, presumably relatively low-power state for video decoding and playback. Also, GT200-based cards will be compatible with Nvidia's HybridPower scheme, so they can be deactivated entirely in favor of a chipset-based GPU when they're not needed.
I think one huge thing is that graphics is a hugely parallelizable task. The operations aren't very complex, so they can just keep cramming more and more processing units onto the chip.
Intel and AMD are having issues getting over 4 cores per die right now, while this card "... packs 240 tiny processing cores into this space, plus 32 raster-operation processors".
If I have nothing to hide, don't search me
8000gts were much louder than their 3870 counterparts too.
i dont get why people fall for that - push a chip to limits, put a noisy fan on it, and sell it as high performance card.
at least with ati 3870 you can decide whether you gonna overclock the card and endure the noise or not.
Read radical news here
This is how graphics cards used to work. You would plug a VGA cable from your standard 2D graphics card to your, for example, Voodoo II card, and the Voodoo II card would go out to the monitor. You could just have the 3D card working in passthrough mode when not doing 3D stuff. Something like this could work on a single board though. There's no reason you couldn't power down entire sections of the graphics card that you aren't using. Most video cards support changing the clock speed on the card. I'm wondering if this is a problem at all, with any real effects, or whether it's just speculation based on the poster assuming what might happen. Anybody have any real numbers for wattage drained based on idle/full workload for these large cards?
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
When run under Vista, it features tons of additional effects. Those are the reasons why the speed improvement in Crysis aren't that much impressive under Vista.
PS: And for the record, Radeon HD3870X2 uses the exact same GDDR3, not GDDR4 as TFA's review says. ATI choose to go for GDDR3 to cut the costs of the dual GPU setup. (Only a few non standard boards by 3rd party manufacturer use GDDR4 and a PCI-express 2.0 bridge).
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
Nvidia has made great strides in reducing its GPUs' power consumption, and the GeForce 200 series promises to be no exception. In addition to supporting Hybrid Power (a feature that can shut down a relatively power-thirsty add-in GPU when a more economical integrated GPU can handle the workload instead), these new chips will have performance modes optimized for times when Vista is idle or the host PC is running a 2D application, when the user is watching a movie on Blu-ray or DVD, and when full 3D performance is called for. Nvidia promises the GeForce device driver will switch between these modes based on GPU utilization in a fashion that's entirely transparent to the user. So, yes, they hear you, and are making improvements in this area.
today is spelling optional day.
Pet peeve: Profane people propagating perfunctory pedantry.
However, not all that power is needed for running the 3D desktops. I can run Compiz (linux 3D desktop) on my Intel GMA 950 without a single slowdown. With all the standard 3D eyecandy turned on. So you wouldn't need to run an nVidia 8800 at full clock speed to render the desktop effects. Also, Windows Vista and Linux both support turning off the 3D effects and running in full 2D mode. I'm sure Mac OS supports the same, although I've never looked into it, so it's hard to say for sure. Especially since MacOS has such a limited number of computers that it is supported on.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
Actually, NVidia's pretty good about getting Linux drivers for new cards out relatively quickly.
Remember, open source is free as in speech, not free as in bear.
Also, graphics processors are evolving quickly, where as CPUs have had basically the same instruction set for 30 years now.
For example, with the 8000 series pixel shaders had become very important in modern games, so the cards were optimised for pixel shading performance much more than the 7000 series was. There is simply no equivalent for CPUs - even stuff like SSE extensions is really just trying to do the same stuff in a more parallel way, it isn't a radically new way of doing things.
const int one = 65536; (Silvermoon, Texture.cs)
SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
Precisely. This is something that can be solved by simply throwing more transistors in. Their biggest challenge is probably power and heat, not architecture.
Not to mention that "programs" on GPUs are ridiculously simple compared to something on a general purpose CPU. Next time you write a shader, try branching (i.e. if, else), your shader will slow to a relative crawl.
Maybe your eyes are better than mine, but I don't think we're even getting that.
Texture size and number of objects in a scene on Crysis would be the best examples, there is a difference. Games are moving to levels (especially for HD or 1920x1200&up players) that the texture limitations of DX9.0c can't bring the detail needed, and this is just one 'tiny' aspect of DX10.
http://www.tomsgames.com/us/2007/09/18/dx10_part3/page3.html
Bundling it into Vista is bad, for a slew of reasons, and the shit they've pulled with several 'Vista only' titles,
DX10 has specific reasons why it only runs on Vista. Go ask the people hacking the libraries for XP. They will run, but it expects the OS to be handling aspects of the GPU that XP isn't doing.
http://arstechnica.com/journals/microsoft.ars/2007/2/14/7060
DX10 is designed around Vista because it expects GPU RAM Virtualization to be available from the OS. (Only Vista can do this) DX10 expects even 'in-game' threads/processes to be prioritized and handled by the OS, and only Vista can do this because it has a pre-emptive scheduler for the GPU, XP don't (in fact no other OS has one). To put these things in XP would be to make a full WDDM for XP, and that is not quite so easy.
The DX10 stuff like this is a tie over from the XBox360 development team, and DX10 is what MS and Robbie learned to take gaming forward on the PC.
As for the 'Vista Only' titles, there were reasons for them at the time. For example Halo 2, as its online play is Games for Windows Live, and at the time used Vista's communication framework, and Live for Windows (the Gaming connection) was a Vista only technology. So the Halo 2 development went forward with these considerations, and other internal optimizations in the game just exepcted the Vista WDDM to be there, etc. Microsoft went back and wrote Live Games for Windows for XP from the ground up. (Hence some of the new networking features in XP SP3, just to support it.)
So it may have seemed nefarious, but was not a con, just a platform specific feature and optimization design, pure and simple... Sadly MS was counting on NVidia and ATI to have their WDDM drivers at XP levels at release of VIsta, and this didn't happen. When MS jumped in with NVidia and ATI and 'helped' their driver development the fruit of this was seen around June 07, as Vista was catching to XP in gaming performance, and by Sept 07, had equaled it.
I see absolutely nothing to recommend Vista over XP, at this time or in the near future.
This is where Microsoft's marketing sucks. They should do like Apple and list every tiny feature.(Remember the 300 list about Leopard?) If Microsoft did a list like this for Vista, it would be around 10,000 items in their list.
If I had time this morning, I could take your circumstances and make a very credible case for Vista. I also understand where you are coming from as Vista is a plumbing and architecture shift, they burned their time to build more features based on these changes with the iniitial dump of Longhorn. Windows 7 is basically going to be a showcase of what is already in Vista, since it doesn't have any major architecture changes planned.
Hardly a year out of date. The figures you post are one month old, and involve Vista SP1 final, vs SP3 of XP. I admit I am impressed by the evening out that Vista has managed to achieve, in those tests.
Ok, year was a bit of tongue in cheek.
A lot of people didn't realize that NVidia and ATI had to write the Vista WDDM drivers from scratch, as it is a dramatic different model than XPDM. From letting Vista do scheduling to RAM virtualization and handing over more to the OS from core driver level to even Aero Composer.
And even though I think NVidia and ATI could have done better at launch, as they didn't provide drivers to beta testers