ATI Radeon R600

R600 Technical Aspects

Techinical Aspects

Now onto the Technical bits that make up the r600. As I said earlier this is going to be a brief run-through and not a University dissertation on r600.

Unified Shader Architecture

The R600's design is similar to the xbox360's GPU as it is based on the Unified Superscalar shader architecture.

The Unified Shader Architecture coupled with Microsofts new DirectX 10 API allows the shaders to be 'unified'.
What this means is that instead of having a fixed number of shaders assigned to certain tasks, (eg x1900: 8 vertex shader processors & 48 pixel shader processors) they can be assigned depending on the job at hand meaning all of the shaders are used.

As a result, the GPU will be fully utilised and therefore performance will be enhanced, gaining up to 25% in performance.

Unified Superscalar Shader Architecture

  • 320 stream processing units
    • Dynamic load balancing and resource allocation for vertex, geometry, and pixel shaders
    • Common instruction set and texture unit access supported for all types of shaders
    • Dedicated branch execution units and texture address processors
  • 128-bit floating point precision for all operations
  • Command processor for reduced CPU overhead
  • Shader instruction and constant caches
  • Up to 80 texture fetches per clock cycle
  • Up to 128 textures per pixel
  • Fully associative multi-level texture cache design
  • DXTC and 3Dc+ texture compression
  • High resolution texture support (up to 8192 x 8192)
  • Fully associative texture Z/stencil cache designs
  • Double-sided hierarchical Z/stencil buffer
  • Early Z test, Re-Z, Z Range optimization, and Fast Z Clear
  • Lossless Z & stencil compression (up to 128:1)
  • Lossless color compression (up to 8:1)
  • 8 render targets (MRTs) with anti-aliasing support
  • Physics processing support

Now I don't need to say that the 2X00 series support DX10 fully with full SM 4.0 support. This is ATI's first card supporting the new Microsoft API and they've followed their Xenos Xbox 360 chip in making r600. In saying that, r600 has taken Xenos that bit futher and gone with a completely unified shader architecture, something nVidia have also done with G80.

The r600 consists of 320 independent stream processing units, made up of 64 superscaler shader processors, each a five-way unit. These all support FP32 bit precision in mathematical operations. Added in are 16 texture units (TMU's) and 16 ROPs (render backends). The 2900 XT has a 512mb ring-bus architecture, taken forward from r580, which can break through 100BG/sec; the same as the G80 can, but at a more interesting price-point.

ATI have also added a "programmable tessellation unit". This is notable as the current DX10 specification do not include this, although Microsoft is said to have plans in including it at a later stage.

Shader Units

ATI have gone a different router to nVidia in as far as their Shader Units are concerned. This isn't in so much as the actual number (though they do differ), more the approach to the way that each stream processor is layed out. r600 uses a 5-way superscaler shader processor, with 5 parts and 5 instructions per clock. These sit in clusters of 16 shaders (80 stream processing units each cluster altogether) and added to them is a branch execution unit. Added is a 64KB memory read/write cache which can be accessed by any shader cluster. This means that in DX10 architecture you can avoid going through the render backend and write straight to memory.

r600 shader

So that's the big difference in architecture of the stream processing units as I see it. ATI have added a lot of additional features, but as this is a brief article, I will leave you to click on the links I have provided below for a more in-depth analysis of the architecture. Now onto what some of this means.
«Prev 1 2 3 4 5 Next»

Most Recent Comments

15-05-2007, 13:36:20

Well you have the Apogee (very soon we hope) so I would go for a Laing D5 (reliability and flow), though some would say different :D

As it's your GPU too you want a PA 120.3 for a RAD, but your case is tiny so perhaps you could fit a 120.2 to the back of your case

GPU = MCW60 - would fit most newer cards too so you have options

For the res I reckon those tube res look very cool and you may just be able to squeeze one in. If not then Alphacool do a sweet mini-res :)

Tubing is your choice but myself I prefer 1/2" :D

wowo just saw hams post - bargain of the week!

15-05-2007, 14:04:43

Just measured up and there is no way I could fit a 24mm in the top of my case, only other solutions are a 24mm on the back or a 36mm on the top.

15-05-2007, 14:59:00

Ok this is what I have come up with so far, I am planning on mounting a 240mm rad on the back of my case and having a 120mm rad my free cd bays.

So I would need the following:

Not sure on a pump yet and if I should have a reservoir.

Comments welcome.

15-05-2007, 15:01:30

I second the MCW60 for GPU, very good block.

Also I wouldn't bother w/cing the NB.

You'll need a reservoir, I like the XPSC ones which fit in the 5.25" drive bays, have a blue LED as well.

15-05-2007, 18:08:52

For a res i recomend the alphacool cape coolex 25, check my rig gallery for pics.
It looks nice and hold a fair bit of liquid and i have it mounted on the roof of my case. :D
Theres my input for what its worth. lol.

15-05-2007, 18:25:39

It looks like something that women would play with :eek:

I am just looking for something small to sit inside my case ;)

15-05-2007, 18:31:43

Micro rez?

15-05-2007, 21:38:03

Swiftech MCres micro :)
BTW Kempez, Laing reports that 4.3% of DDCs are breaking. 4.3 is high statistically but chances are, if you buy a DDC you will be fine. D5s break as well, just a week ago on XS someone's D5 broke :) and the majority of people there use DDC. The only pumps I would call reliable are iwaki and panworld, and even then, they still have a chance of breaking. IanY, a crazy guy on XS, says "don't trust the pump" and sticks like 7 pumps into his computer...
Oh and try to get a thermochill if you can, they're most effective. A thermochill PA120.2 keeps water temps at almost the same temps as an MCR320 or Coolrad 32t, BUT has almost 1/2 the restriction. And of course, PA120.3 mops the floor.

15-05-2007, 21:45:23

GoldenTiger is what I'm looking at personally, I'm using an X-Qpack which is a small-form-factor... I modded it to use normal ATX boards, so while space is tight, I think I can fit it mostly inside :eek:, I think it's about as small as you'll get for a well-performing kit.

16-05-2007, 19:32:23

serialk11r is what I'm looking at personally, I'm using an X-Qpack which is a small-form-factor... I modded it to use normal ATX boards, so while space is tight, I think I can fit it mostly inside :eek:, I think it's about as small as you'll get for a well-performing kit.

That will not bring you good performance no matter how much you wish it will or how much you want to think it will. The radiator is simply too small.

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.