Feature Overview

There are quite a few exciting new features being introduced with ATI's new X1000 series. Of course, we have a new line of hardware based on a more refined architecture. But at the end of the day, it's not the way that a company implements a dot product or manages memory latency that sells product; it's what consumers can do with the hardware that counts. ATI will not disappoint with the number of new features thtat they have included in their new top to bottom family of graphics hardware.

To provide a quick overview of the new lineup from ATI, here are the key featuers of the X1000 series.
  • Fabbed on TSMC's 90nm process
  • Shader Model 3.0 support
  • Fulltime/fullspeed fp32 processing for floating point pixel formats
  • New "Ring Bus" memory architecture with support for GDDR4
  • Antialiasing supported on MRT and fp16 output
  • High quality angle independent Anisotropic Filtering
  • AVIVO and advanced decode/encode support
Shader Model 3.0 has been covered quite a bit over the past year and a half. To quickly summarize the differences, Shader Model 3.0 requires hardware to support dynamic flow control in both the vertex and fragment pipeline. This means that if/else statements and looping are possible. Rather than unrolling loops in programs, SM3.0 can keep instruction counts lower for complex operations. Also, conditional rendering allows unified shaders to run on large areas and do different things on different pixels. Other features such as two-sided lighting and vertex textures are also possible. The real advantages of SM3.0 come in the form of number of registers, branching, relaxed instruction limits, efficiency and accuracy (fp32 support is required). And all these features are now supported top to bottom on both NVIDIA and ATI hardware.

Running on a 90nm TSMC process has given ATI the ability to push clock speeds quite high. With die sizes small and transistor counts high, ATI is able to pack a lot of performance in their new architecture. As the feature list indicates, ATI hasn't just waited idly by. But the real measure of what will be enough to put ATI back on top will be how much performance customers get for their money. To start answering that question, we first need to look at the parts launching and their prices.

ATI X1000 Series Features
Radeon X1300 Pro
Radeon X1600
Radeon X1800 XL
Radeon X1800 XT
Vertex Pipelines
2
5
8
8
Pixel Pipelines
4
12
16
16
Core Clock
600
590
500
625
Memory Size
256MB
256MB
256MB
512MB
Memory Data Rate
800MHz
1.38GHz
1GHz
1.5GHz
Texture Units
4
4
16
16
Render Backends
4
4
16
16
Z Compare Units
4
8
16
16
Maximum Threads
128
128
512
512
Avaialbility
This Week
11/30/2005
This Week
11/5/2005
MSRP
$149
$249
$449
$549

Along with all these features, CrossFire cards for the new X1000 series will be following in a few months. While we don't have anything to test, we can expect quite a few improvements from the next generation of ATI's multi-GPU solution. First and foremost, master cards will include a dual-link TMDS receiver to allow resolutions greater than 1600x1200 to run. This alone will make CrossFire on the X1000 series infinitely more useful than the current incarnation. We can also expect a better compositing engine built on a faster/larger FPGA. We look forward to checking out ATI's first viable multi-GPU solution as soon as it becomes available to us.

Rather than include AVIVO coverage in this article, we have published a separate article on ATI's X1000 series display hardware. The high points are a 10-bit gamma engine, H.264 accelerated decoding and hardware assisted transcoding. While we won't see transcoding support until the end of the year, we have H.264 decode support today. For more details, please check out our Avivo image quality comparison and technology overview.

Index Pipeline Layout and Details
Comments Locked

103 Comments

View All Comments

  • mlittl3 - Wednesday, October 5, 2005 - link

    I'll tell you how it is a win. Take a 8 less pipeline architecture, put it onto a brand new 0.90nm die shrink, clock the hell out of the thing, consume just a little more power and add all the new features like sm3.0 and you equal the competition's fastest card. This is a win. So when ATI releases 1,2,3 etc. more quad pipes, they will be even faster.

    I don't see anything bob. Anandtech's review was a very bad one. ALL the other sites said this was is good architecture and is on par with and a little faster than nvidia. None of those conclusions can be drawn from the confusing graphs here.

    Read the comments here and you will see others agree. Good job, ATI and Nvidia for bringing us competition and equal performing cards. Now bob, go to some other sites, get a good feel for which card suits your needs, and then go buy one. :)
  • bob661 - Wednesday, October 5, 2005 - link

    I read the other sites as well as AT. Quite frankly, I trust AT before any of the other sites because their methodology and consistancy is top notch. HardOCP didn't even test a X1800XT and if I was an avid reader of their site I'd be wondering where that review was. I guess I don't see it your way because I only look for bang for the buck not which could be better if it had this or had that. BTW, I just got some free money (no, I didn't steal it!) today so I'm going to pick up a 7800GT. :)
  • Houdani - Wednesday, October 5, 2005 - link

    One of the reasons for the card selections is due to the price of the cards -- and was stated as such. Just because ATI is calling the card "low-end" doesn't mean it should be compared with other low-end cards. If ATI prices their "low-end" card in the same range as a mid-range card, then it should rightfully be compared to those other cards which are at/near the price.

    But your point is well taken. I'd like to see a few more cards tossed in there.
  • Madellga - Wednesday, October 5, 2005 - link

    Derek, I don't know if you have the time for this, but a review at other website showed a huge difference in performance at the Fear Demo. Ati was in the lead with substantial advantage for the maximum framerates, but near at minimum.

    http://techreport.com/reviews/2005q4/radeon-x1000/...">http://techreport.com/reviews/2005q4/radeon-x1000/...

    As Fear points towards the new generation of engines, it might be worth running some numbers on it.

    Also useful would be to report minimum framerates at the higher resolutions, as this relates to good gameplay experience if all goodies are cranked up.
  • Houdani - Wednesday, October 5, 2005 - link

    Well, the review does state that the FEAR Demo greatly favors ATI, but that the actual shipping game is expected to not show such bias. Derek purposefully omitted the FEAR Demo in order to use the shipping game instead.
  • allnighter - Wednesday, October 5, 2005 - link

    Is it safe to assume that you guys might not have had enough time with these cards to do your usuall in-depth review? I'm sure you'll update for us to be able to get the full picture. I also must say that I'm missing the oc part of the review. I wanted to see how true it is taht these chips can go sky hig.> Given the fact that they had 3 re-spins it may as well be true.
  • TinyTeeth - Wednesday, October 5, 2005 - link

    ...an Anandtech review.

    But it's a bit thin, I must say. I'm still missing overclocking results and Half-Life 2 and Battlefield 2 results. How come no hardware site has tested the cards in Battlefield 2 yet?

    From my point of view, Doom III, Splinter Cell, Everquest II and Far Cry are the least interesting games out there.

    Overall it's a good review as you can expect from the absolutely best hardware site there is, but I hope and expect there will be another, much larger review.
  • Houdani - Wednesday, October 5, 2005 - link

    The best reason to continue benchmarking games which have been out for a while is because those are the games which the older GPUs were previously benched. When review sites stop using the old benchmarks, they effectively lose the history for all of the older GPU's, and therefore we lose those GPUs in the comparison.

    Granted, the review is welcome to re-benchmark the old GPUs using the new games ... but that would be a significant undertaking and frankly I don't see many (if any) review sites doing that.

    But I will throw you this bone: While I think it's quite appropriate to use benchmarks for two years (maybe even three years), it would also be a good thing to very slowly introduce new games at a pace of one per year, and likewise drop one game per year.
  • mongoosesRawesome - Wednesday, October 5, 2005 - link

    they have to retest whenever they use a different driver/CPU/motherboard, which is quite often. I bet they have to retest every other article or so. Its a pain in the butt, but thats why we visit and don't do the tests ourselves.
  • Madellga - Wednesday, October 5, 2005 - link

    Techreport has Battlefield 2 benchmarks, as Fear, Guild Wars and others. I liked the article, recommend that you read also.

Log in

Don't have an account? Sign up now