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
I'm not really sure why we have NDAs on these products anymore. Before we even got our Radeon HD 4890, before we were even briefed on it, NVIDIA contacted us and told us that if we were working on a review to wait. NVIDIA wanted to send us something special.
Then in the middle of our Radeon HD 4890 briefing what do we see but a reference to a GeForce GTX 275 in the slides. We hadn't even laid hands on the 275, but AMD knew what it was and where it was going to be priced.
If you asked NVIDIA what the Radeon HD 4890 was, you'd probably hear something like "an overclocked 4870". If you asked AMD what the GeForce GTX 275 was, you'd probably get "half of a GTX 295".
The truth of the matter is that neither one of these cards is particularly new, they are both a balance of processors, memory, and clock speeds at a new price point.
As the prices on the cards that already offered a very good value fell, higher end and dual GPU cards remained priced significantly higher. This created a gap in pricing between about $190 and $300. AMD and NVIDIA saw this as an opportunity to release cards that fell within this spectrum, and they are battling intensely over price. Both companies withheld final pricing information until the very last minute. In fact, when I started writing this intro (Wednesday morning) I still had no idea what the prices for these parts would actually be.
Now we know that both the Radeon HD 4890 and the GeForce GTX 275 will be priced at $250. This has historically been a pricing sweet spot, offering a very good balance of performance and cost before we start to see hugely diminishing returns on our investments. What we hope for here is a significant performance bump from the GTX 260 core 216 and Radeon HD 4870 1GB class of performance. We'll wait till we get to the benchmarks to reveal if that's what we actually get and whether we should just stick with what's good enough.
At a high level, here's what we're looking at:
| GTX 285 | GTX 275 | GTX 260 Core 216 | GTS 250 / 9800 GTX+ | |
| Stream Processors | 240 | 240 | 216 | 128 |
| Texture Address / Filtering | 80 / 80 | 80 / 80 | 72/72 | 64 / 64 |
| ROPs | 32 | 28 | 28 | 16 |
| Core Clock | 648MHz | 633MHz | 576MHz | 738MHz |
| Shader Clock | 1476MHz | 1404MHz | 1242MHz | 1836MHz |
| Memory Clock | 1242MHz | 1134MHz | 999MHz | 1100MHz |
| Memory Bus Width | 512-bit | 448-bit | 448-bit | 256-bit |
| Frame Buffer | 1GB | 896MB | 896MB | 512MB |
| Transistor Count | 1.4B | 1.4B | 1.4B | 754M |
| Manufacturing Process | TSMC 55nm | TSMC 55nm | TSMC 65nm | TSMC 55nm |
| Price Point | $360 | ~$250 | $205 | $140 |
| ATI Radeon HD 4890 | ATI Radeon HD 4870 | ATI Radeon HD 4850 | |
| Stream Processors | 800 | 800 | 800 |
| Texture Units | 40 | 40 | 40 |
| ROPs | 16 | 16 | 16 |
| Core Clock | 850MHz | 750MHz | 625MHz |
| Memory Clock | 975MHz (3900MHz data rate) GDDR5 | 900MHz (3600MHz data rate) GDDR5 | 993MHz (1986MHz data rate) GDDR3 |
| Memory Bus Width | 256-bit | 256-bit | 256-bit |
| Frame Buffer | 1GB | 1GB | 512MB |
| Transistor Count | 959M | 956M | 956M |
| Manufacturing Process | TSMC 55nm | TSMC 55nm | TSMC 55nm |
| Price Point | ~$250 | ~$200 | $150 |
We suspect that this will be quite an interesting battle and we might have some surprises on our hands. NVIDIA has been talking about their new drivers which will be released to the public early Thursday morning. These new drivers offer some performance improvements across the board as well as some cool new features. Because it's been a while since we talked about it, we will also explore PhysX and CUDA in a bit more depth than we usually do in GPU reviews.
We do want to bring up availability. This will be a hard launch for AMD but not for NVIDIA (though some European retailers should have the GTX 275 on sale this week). As for AMD, we've seen plenty of retail samples from AMD partners and we expect good availability starting today. If this ends up not being the case, we will certainly update the article to reflect that later. NVIDIA won't have availability until the middle of the month (we are hearing April 14th).
NVIDIA hasn't been hitting their launches as hard lately, and we've gotten on them about that in past reviews. This time, we're not going to be as hard on them for it. The fact of the matter is that they've got a competitive part coming out in a time frame that is very near the launch of an AMD part at the same price point. We are very interested in not getting back to the "old days" where we had paper launched parts that only ended up being seen in the pages of hardware review sites, but we certainly understand the need for companies to get their side of the story out there when launches are sufficiently close to one another. And we're certainly not going to fault anyone for that. Not being available for purchase is it's own problem.
From the summer of 2008 to today we've seen one of most heated and exciting battles in the history of the GPU. NVIDIA and AMD have been pushing back and forth with differing features, good baseline performance with strengths in different areas, and incredible pricing battles in the most popular market segments. While AMD and NVIDIA fight with all their strength to win customers, the real beneficiary has consistently been the end user. And we certainly feel this launch is no exception. If you've got $250 to spend on graphics and were wondering whether you should save up for the GTX 285 or save money and grab a sub-$200 part, your worries are over. There is now a card for you. And it is good.
Facebook
Twitter
RSS
294 Comments
View All Comments
7Enigma - Thursday, April 2, 2009 - link
Deja vu again, and again, and again. I've posted in no less than 3 other articles how bad some of the conclusions have been. There is NO possible way you could conclude the 275 is the better card at anything other than the 30" display resolution. Not only that, but it appears with the latest Nvidia drivers they are making things worse.Honestly, does anyone else see the parallel between the original OCZ SSD firmware and these new Nvidia drivers? Seems like they were willing to sacrifice 99% of their customers for the 1% that have 30" displays (which probably wouldn't even be looking at the $250 price point). Nvidia, take a note from OCZ's situation; lower performance at 30" to give better performance at 22-24" resolutions would do you much better in the $250 price segment. You shot yourselves in the foot on this one...
Gary Key - Thursday, April 2, 2009 - link
The conclusion has been clarified to reflect the resolution results. It falls right into line with your thoughts and others as well as our original thoughts that did not make it through the edits correctly.7Enigma - Thursday, April 2, 2009 - link
Yup, I responded to Anand's post with a thank you. We readers just like to argue, and when something doesn't make sense, we're quick to go on the attack. But also quick to understand and appreciate a correction.duploxxx - Thursday, April 2, 2009 - link
Just some thoughts:There is only 1 single benchmark out of 7 where the 275 has better frame rates for 1680 and 1920 resolution against the 4890 and yet your final words are that you favor the 275???? Only in 2560 the 275 is clearly the better choice. Are you already in the year 2012 where 2560 might be the standard resolution of the sales, it is only very recent that the 1680 became standard and even then this resolution is high for global OEM market sales. Your 2560 is not even few % of the market.
I think you have to clarify your final words a bit more with your choice.... Perhaps if we see power consumption, fan noice etc that would be added value to the choice, but for now, TWIMTBP is really not enough push to prefer the card, I am sure the red team will improve there drivers as usual also.
anything else i missed in your review that could counter my thoughts?
SiliconDoc - Monday, April 6, 2009 - link
Derek has been caught in the 2560 wins it all no matter what with the months on end of ati taking that cake since the 4870 releasse. No lower resolutions mattered for squat since the ati lost there - so you'll have to excuse his months long brainwashing.Thankfully anand checked in and smacked it out of his review just in time for the red fanboy to start enjoying lower resolution wins while nvidia takes the high resolution crown, which is- well.. not a win here anymore.
Congratulations, red roosters.
duploxxx - Thursday, April 2, 2009 - link
just as addon, I also checked some other reviews (yes i always read anandtech first as main source of info) and i saw that it is cooler then a 4870 and actually consumes 10% less then a 4870 so this can't be the reason either while the 275 stays at the same 280 power consumption. Also OC parts are already shown GPU above 1000....cyriene - Thursday, April 2, 2009 - link
I would have liked to see some information on heat output and the temperatures of the cards while gaming.Otherwise, nice article.
7Enigma - Thursday, April 2, 2009 - link
This is an extreme omission. The fact that the 4890 is essentially an overclocked 4870 means with virtually nothing changed you HAVE to show the temps. I still stick by my earlier comment that the Vapo-chill model of the Sapphire 4870 is possibly a better card since it's temps are significantly lower than the stock 4870, while already being overclocked. I could easily imagine that for $50-60 less you could have the performance of the 4890 at cooler temps (by OC'ing the vapochill further).Comon guys, you have to give thought to this!
SiliconDoc - Monday, April 6, 2009 - link
Umm, they - you know the AT bosses, don't like the implications of that. So many months, even years, spent on screeching like women about nvidia rebranding has them in a very difficult position.Besides, they have to keep the illusion of superior red power useage, so only after demand will they put up the power chart.
They tried to get away with not, but they couldn't do it.
initialised - Thursday, April 2, 2009 - link
GPU-z lists the R790 as having a surface area of 282mm2 while the R770 has 256mm2 but both are listed as having the same transistor count.