ATI Radeon HD 4890 vs. NVIDIA GeForce GTX 275
by Anand Lal Shimpi & Derek Wilson on April 2, 2009 12:00 AM EST- Posted in
- GPUs
Putting this PhysX Business to Rest
Let me put things in perspective. Remember our Radeon HD 4870/4850 article that went up last year? It was a straight crown-robbing on ATI’s part, NVIDIA had no competitively priced response at the time.
About two hours before the NDA lifted on the Radeon HD 4800 series we got an urgent call from NVIDIA. The purpose of the call? To attempt to persuade us to weigh PhysX and CUDA support as major benefits of GeForce GPUs. A performance win by ATI shouldn’t matter, ATI can’t accelerate PhysX in hardware and can’t run CUDA applications.
The argument NVIDIA gave us was preposterous. The global economy was weakening and NVIDIA cautioned us against recommending a card that in 12 months would not be the right choice because new titles supporting PhysX and new CUDA applications would be coming right around the corner.
The tactics didn’t work obviously, and history showed us that despite NVIDIA’s doomsday warnings - Radeon HD 4800 series owners didn’t live to regret their purchases. Yes, the global economy did take a turn for the worst, but no - NVIDIA’s PhysX and CUDA support hadn’t done anything to incite buyer’s remorse for anyone who has purchased a 4800 series card. The only thing those users got were higher frame rates. (Note that if you did buy a Radeon HD 4870/4850 and severely regretted your purchase due to a lack of PhysX/CUDA support, please post in the comments).
This wasn’t a one time thing. NVIDIA has delivered the same tired message at every single opportunity. NVIDIA’s latest attempt was to punish those reviewers who haven’t been sold on the PhysX/CUDA messages by not sending them GeForce GTS 250 cards for review. The plan seemed to backfire thanks to one vigilant Inquirer reporter.
More recently we had our briefing for the GeForce GTX 275. The presentation for the briefing was 53 slides long, now the length wasn’t bothersome, but let’s look at the content of the slides:
| Slides About... | Number of Slides in NVIDIA's GTX 275 Presentation |
| The GeForce GTX 275 | 8 |
| PhysX/CUDA | 34 |
| Miscellaneous (DX11, Title Slides, etc...) | 11 |
You could argue that NVIDIA truly believes that PhysX and CUDA support are the strongest features of its GPUs. You could also argue that NVIDIA is trying to justify a premium for its much larger GPUs rather than having to sell them as cheap as possible to stand up to an unusually competitive ATI.
NVIDIA’s stance is that when you buy a GeForce GPU, it’s more than just how well it runs games. It’s about everything else you can run on it, whether that means in-game GPU accelerated PhysX or CUDA applications.
Maybe we’ve been wrong this entire time. Maybe instead of just presenting you with bar charts of which GPU is faster we should be penalizing ATI GPUs for not being able to run CUDA code or accelerate PhysX. Self reflection is a very important human trait, let’s see if NVIDIA is truly right about the value of PhysX and CUDA today.
Facebook
Twitter
RSS
294 Comments
View All Comments
jeffrey - Thursday, April 2, 2009 - link
1) ATI driver - Was 8.12 really used? Why? 9.3 was released last month.2) Conclusion - The edge should have gone to the 4890 for being ahead of the 275 in most games at resolutions targeting the price point.
Gary Key - Thursday, April 2, 2009 - link
1. The 9.4 beta was used for the HD 4890 and the chart has been updated to reflect it. The 9.3 drivers are not any faster than the 8.12 HotFix for the other AMD cards in every test I have run but Crysis Warhead with a Core 2 Quad. A few improvements have been made for CF compatibility and video playback though.2. The conclusion has been updated to clarify our thoughts between the two cards.
can - Thursday, April 2, 2009 - link
An ATI gpu with and nvidia gpu doing physx? I'm curious to see results of this kind of arrangement. Not a dedicated PCI Physx card, but on a faster bus, with a more powerful processor, as a video card. I'm wondering about pitfalls and performance and the literal looks of the application.SiliconDoc - Monday, April 6, 2009 - link
Sorry bub, you're stuck with ati, and as far as curiosity for physx - uhh... don't worry, you're not missing much, anand only got addicted to it for a bit.If you want the driver hack for it, there's a thread at techpowerup.
Some genius figured something out on it- not sure which os.
Jamahl - Thursday, April 2, 2009 - link
The conclusion in this review is awful beyond anything I have read before.How can the reviewer say the 275 is winning this one when the benchmarks clearly show dominance for the 4890 at most resolutions?
Otherwise it was a good article but the conclusion leaves a sour taste in the mouth.
SiliconDoc - Monday, April 6, 2009 - link
He could say it because he said it for ati for 6 months when ati won the top resolution. So his brain is in a "fart mode" that lied for ati for so long, he said it this time for nvidia - either that or he realized if he didn't he would look like an exposed raging red rooster fanboy.Good thing the reds started screaming NOW, after loving it for 6 months when their card was on top using the false method - because anand came in and saved the day - and changed the conclusion - for ati.
LOL
When nvidia doesn't give them a card for review again, it will be "them towing the line of honesty" that causes, no doubt, right ?
BWAHAHAHAAAAAAA
( you all just tell yourselves that along with our dear leaders )
erikejw - Thursday, April 2, 2009 - link
"On the NVIDIA side, we received a reference version of the GTX 275."You wish.
"since there is no 275 ASIC, NV is telling OEMs that they can make it from either a 280 or 260 board. One costs much more, and one performs better, so guess what everyone is going to use?
That isn't necessarily bad, but how NV is seeding reviewers is. They are only going to be giving out a very special run of ONLY 280 based parts.
Quite special 280 based parts at that. Reviewers beware, what you are getting is not what you can buy."
http://www.theinquirer.net/inquirer/news/599/10515...">http://www.theinquirer.net/inquirer/new...ia-hoodw...
bill3 - Thursday, April 2, 2009 - link
A lot of people seem to be crying about lack of temp, power consumption, oc, and fan noise numbers..while I agree in a stand alone review these are glaring omissions, the fact is theres a dozen reviews around the web where you can get that info in triplicate. I would much rather have the insight on CUDA and PHysx!I mean, people act like the internet isnt free and we all arent a google search/mouse click away from that type of info! Geez.
That said, I suppose reviews must be treated as "stand alone", however artificial a construct it may be. However if theres anything thats easily forgivable to be left out it's simple data numbers that can be found at a thousand other places. Which is exactly what temp, oc, etc are. I already know those numbers from a ton of other reviews. These people whining in the comments act like Anand is the only hardware review site there is. I would think if anybody was truly interested in laying out 250 to purchase one of these theyd be looking at more than one review!
SkullOne - Thursday, April 2, 2009 - link
I second the question about why did you use Catalyst 8.12 Hotfix? Other sites are using what appears to be an Beta Catalyst 9.4 driver so is your listing of Catalyst 8.12 a misprint?Also why do you care if AMD sent you an overclocked version? The HD4890 is directly targeted at the overclocking enthusiasts which is a realm that AMD has ignored up until now while NV embraced it.
The HD4890 has already been taken to 1+GHz on it's GPU and up to 4.8GHz on it's memory on other sites. That by far makes it the better buy.
SkullOne - Thursday, April 2, 2009 - link
Forgot to mention that by having this extremely overclockable card AMD has opened up another entire SKU for themselves by selling "OC" cards with the 4890.