ATI Radeon HD 2900 XT: Calling a Spade a Spade
by Derek Wilson on May 14, 2007 12:04 PM EST- Posted in
- GPUs
Final Words
What a long, strange journey it has been to this point. We have a very delayed launch from AMD that features a part that consumes quite a bit of power and doesn't compete with the competition's high end offering. At face value, this sounds quite a bit like NVIDIA's NV30 launch, but thankfully we wouldn't go so far as to call this NV30 Part 2: the R600 Story.
Even though AMD has not built a high end part, they have built a part that runs very consistently at its performance target (which could not be said about NV30). AMD is also not trying to pass this card off as something it's not: rather than price this card out of its class, the R600 will find a good home at a reasonable price.
Despite the delays, despite the quirks, and despite the lack of performance leadership, AMD has built a good part. It might not be as exciting as an ultra high end card, and it certainly isn't as power efficient as an 8800 GTX or Ultra, but it has quite a few positives that make it an interesting product, and more competition is always a good thing. The worst thing that could happen now is for NVIDIA to get as complacent as ATI did after R300 wiped the floor with the competition.
Let's break it down with something akin to a pro/con list. Here's what AMD did right:
R600 features a tessellator which offers an interesting option to geeks and game developers even if it doesn't offer a lot of value to the average consumer. We've got full HD video decode acceleration for all the major codecs. There is a huge amount of processing power available for the code and data that fits the structure of the hardware. Audio is integrated into the video stream and sent out over HDMI with a special adapter allowing both DVI and HDMI to coexist and without the need of splitting the audio channel out from elsewhere. We like to see more options for antialiasing, and even if we don't necessarily like the tent filters the edge detect AA is a really cool concept that looks pretty good. And we absolutely love the architectural detail AMD has gone into with R600.
And here's what AMD did wrong:
First, they refuse to call a spade a spade: this part was absolutely delayed, and it works better to admit this rather than making excuses. Forcing MSAA resolve to run on the shader hardware is less than desirable and degrades both pixel throughput and shader horsepower as opposed to implementing dedicated resolve hardware in the render back ends. Not being able to follow through with high end hardware will hurt in more than just in lost margins. The thirst for wattage that the R600 displays is not what we'd like to see from an architecture that is supposed to be about efficiency. Finally, attempting to extract a high instruction level parallelism using a VLIW design when something much simpler could exploit the huge amount of thread level parallelism inherent in graphics was not the right move.
Maybe that's a lot to digest, but the bottom line is that R600 is not perfect nor is it a failure. The HD 2900 XT competes well with the 640MB 8800 GTS, though the 8800 GTS 320MB does have a price/performance advantage over both in all but the highest resolutions and AA settings under most current games. There are features we like about the hardware and we would love to see exploited. There is potential there, especially for Xbox 360 ports, to really shine... though console ports are often looked down upon in the PC market, particularly if they come late and offer little new to the platform.
Another bit question is that we still haven't seen how either G80 or R600 handle DX10 based games. This unknown will continue for just a little while longer, as next month we should start seeing some titles support DX10. The first titles may not be representative of later DX10 titles, however, so this is something we will only be able to properly assess with time.
For now, R600 is a good starting place for AMD's DX10 initiative, and with a bit of evolution to their unified shader hardware it could eventually rise to the top. We aren't as excited about this hardware as we were about G80, and there are some drawbacks to AMD's implementation, but we certainly won't count them out of the fight. Power efficiency on 65nm remains to be seen, and there is currently a huge performance gap NVIDIA has left between the 8600 GTS and the 8800 GTS 320MB. If AMD is able to capitalize here with the HD 2600 series, they will certainly still have a leg to stand on. We will have to wait to see those performance results though.
In the meantime, we are just happy that R600 is finally here after such a long wait. Let's hope for AMD's sake that the next revision of their hardware doesn't take quite so long to surface and manages to compete better with six month old competing products. We certainly hope we won't see a repeat of the R600 launch when Barcelona and Agena take on Core 2 Duo/Quad in a few months....
Facebook
Twitter
RSS
86 Comments
View All Comments
mostlyprudent - Monday, May 14, 2007 - link
Frankly, neither the NVIDIA nor the AMD part at this price point is all that impressive an upgrade from the prior generations. We keep hearing that we will have to wait for DX10 titles to know the real performance of these cards, but I suspect that by the time DX10 titles are on the shelves we will have at least product line refreshes by both companies. Does anyone else feel like the graphics card industry is jerking our chains?johnsonx - Monday, May 14, 2007 - link
It seems pretty obvious that AMD needs a Radeon HD2900Pro to fill in the gap between the 2900XT and 2600XT. Use R600 silicon, give it 256Mb RAM with a 256-bit memory bus. Lower the clocks 15% so that power consumption will be lower, and so that chips that don't bin at full XT speeds can be used. Price at $250-$300. It would own the upper-midrange segment over the 8600GTS, and eat into the 8800GTS 320's lunch as well.GlassHouse69 - Monday, May 14, 2007 - link
If I know this, and YOU know this.... wouldnt anandtech? I see money under the table or utter stupidity at work at anand. I mean, I know that the .01+ version does a lot better in benches as well as the higher res with aa/af on sometimes get BETTER framerates than lower res, no aa/af settings. This is a driver thing. If I know this, you know this, anand must. I would rather admit to being corrupt rather than that stupid.GlassHouse69 - Monday, May 14, 2007 - link
wrong section. dt is doing that today it seems to a few peoplexfiver - Monday, May 14, 2007 - link
Hi, thank you for a really in depth review. While reading other 'earlier' reviews I remember a site using Catalyst 8.38 and reported performance improvements upto 14% from 8.37. Look forward to Anandtech's view on this.xfiver - Monday, May 14, 2007 - link
My apologies it was VR zone and 8.36 to 8.37 (not 8.38)GlassHouse69 - Monday, May 14, 2007 - link
If I know this, and YOU know this.... wouldnt anandtech? I see money under the table or utter stupidity at work at anand. I mean, I know that the .01+ version does a lot better in benches as well as the higher res with aa/af on sometimes get BETTER framerates than lower res, no aa/af settings. This is a driver thing. If I know this, you know this, anand must. I would rather admit to being corrupt rather than that stupid.Gary Key - Tuesday, May 15, 2007 - link
I have worked extensively with four 8.37 releases and now the 8.38 release for the upcoming P35 release article. The 8.37.4.2 alpha driver had the top performance in SM3.0 heavy apps but was not very stable with numerous games, especially under Vista. The released 8.37.4.3 driver on AMD's website is the most stable driver to date and has decent performance but nothing near the alpha 8.37 or beta 8.38. The 8.38s offer great benchmark performance in the 3DMarks, several games, and a couple of DX10 benchmarks from AMD.
However, the 8.38s more or less broke CrossFire, OpenGL, and video acceleration in Vista depending upon the app and IQ is not always perfect. While there is a great deal of promise in their performance and we see the potential, they are still Beta drivers that have a long ways to go in certain areas before their final release date of 5/23 (internal target).
That said, would you rather see impressive results in 3DMarks or have someone tell you the truth about the development progress or lack of it with the drivers. As much as I would like to see this card's performance improve immediately, it is what it is at this time with the released drivers. AMD/ATI will improve the performance of the card with better drivers but until they are released our only choice is to go with what they sent. We said the same thing about NVIDIA's early driver issues with the G80 so there are not any fanboys or people taking money under the table around here. You can put all the lipstick on a pig you want, but in the end, you still have a pig. ;-)
Anand Lal Shimpi - Monday, May 14, 2007 - link
There's nothing sinister going on, ATI gave us 8.37 to test with and told us to use it. We got 8.38 today and are currently testing it for a follow-up.Take care,
Anand
GlassHouse69 - Monday, May 14, 2007 - link
wow dood. you replied!Yes, I have been wondering about the ethics of your group here for about a year now. I felt this sorta slick leaning towards and masking thing goign on. Nice to see there is not.
Thanks for the 1000's of articles and tests!
-Mr. Glass