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
The Widespread Support Fallacy
NVIDIA acquired Ageia, they were the guys who wanted to sell you another card to put in your system to accelerate game physics - the PPU. That idea didn’t go over too well. For starters, no one wanted another *PU in their machine. And secondly, there were no compelling titles that required it. At best we saw mediocre games with mildly interesting physics support, or decent games with uninteresting physics enhancements.
Ageia’s true strength wasn’t in its PPU chip design, many companies could do that. What Ageia did that was quite smart was it acquired an up and coming game physics API, polished it up, and gave it away for free to developers. The physics engine was called PhysX.
Developers can use PhysX, for free, in their games. There are no strings attached, no licensing fees, nothing. Now if the developer wants support, there are fees of course but it’s a great way of cutting down development costs. The physics engine in a game is responsible for all modeling of newtonian forces within the game; the engine determines how objects collide, how gravity works, etc...
If developers wanted to, they could enable PPU accelerated physics in their games and do some cool effects. Very few developers wanted to because there was no real install base of Ageia cards and Ageia wasn’t large enough to convince the major players to do anything.
PhysX, being free, was of course widely adopted. When NVIDIA purchased Ageia what they really bought was the PhysX business.
NVIDIA continued offering PhysX for free, but it killed off the PPU business. Instead, NVIDIA worked to port PhysX to CUDA so that it could run on its GPUs. The same catch 22 from before existed: developers didn’t have to include GPU accelerated physics and most don’t because they don’t like alienating their non-NVIDIA users. It’s all about hitting the largest audience and not everyone can run GPU accelerated PhysX, so most developers don’t use that aspect of the engine.
Then we have NVIDIA publishing slides like this:
Indeed, PhysX is one of the world’s most popular physics APIs - but that does not mean that developers choose to accelerate PhysX on the GPU. Most don’t. The next slide paints a clearer picture:
These are the biggest titles NVIDIA has with GPU accelerated PhysX support today. That’s 12 titles, three of which are big ones, most of the rest, well, I won’t go there.
A free physics API is great, and all indicators point to PhysX being liked by developers.
The next several slides in NVIDIA’s presentation go into detail about how GPU accelerated PhysX is used in these titles and how poorly ATI performs when GPU accelerated PhysX is enabled (because ATI can’t run CUDA code on its GPUs, the GPU-friendly code must run on the CPU instead).
We normally hold manufacturers accountable to their performance claims, well it was about time we did something about these other claims - shall we?
Our goal was simple: we wanted to know if GPU accelerated PhysX effects in these titles was useful. And if it was, would it be enough to make us pick a NVIDIA GPU over an ATI one if the ATI GPU was faster.
To accomplish this I had to bring in an outsider. Someone who hadn’t been subjected to the same NVIDIA marketing that Derek and I had. I wanted someone impartial.
Meet Ben:
I met Ben in middle school and we’ve been friends ever since. He’s a gamer of the truest form. He generally just wants to come over to my office and game while I work. The relationship is rarely harmful; I have access to lots of hardware (both PC and console) and games, and he likes to play them. He plays while I work and isn't very distracting (except when he's hungry).
These past few weeks I’ve been far too busy for even Ben’s quiet gaming in the office. First there were SSDs, then GDC and then this article. But when I needed someone to play a bunch of games and tell me if he noticed GPU accelerated PhysX, Ben was the right guy for the job.
I grabbed a Dell Studio XPS I’d been working on for a while. It’s a good little system, the first sub-$1000 Core i7 machine in fact ($799 gets you a Core i7-920 and 3GB of memory). It performs similarly to my Core i7 testbeds so if you’re looking to jump on the i7 bandwagon but don’t feel like building a machine, the Dell is an alternative.
I also setup its bigger brother, the Studio XPS 435. Personally I prefer this machine, it’s larger than the regular Studio XPS, albeit more expensive. The larger chassis makes working inside the case and upgrading the graphics card a bit more pleasant.
My machine of choice, I couldn't let Ben have the faster computer.
Both of these systems shipped with ATI graphics, obviously that wasn’t going to work. I decided to pick midrange cards to work with: a GeForce GTS 250 and a GeForce GTX 260.
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.