Bookmark and Share


While particular approaches in graphics processing units design have been pretty different for leading computer visual companies ATI Technologies and NVIDIA Corp., in future the architecture of GPUs from the firms may be fundamentally different, as executives from both companies proclaim different approaches for chip internal architectures.

NVIDIA Disagrees with ATI Technologies

ATI Technologies’ developer relations manager Richard Huddy said last month during a conference in London, UK, that the company’s future visual processing units will feature unified pixel and shader processing. While he declined to elaborate on the timeframes for such chips, he said unified pixel and vertex data processing is a required capability for Windows Graphics Foundation 2.0 that comes out together with Microsoft’s next-generation operating system called Windows Longhorn. On of the benefits the unified approach brings is ability to dynamically allocate chip resources depending on the demand for pixel and vertex processing, Mr. Huddy said. Another one is simplified software development.

NVIDIA Corp.’s chief architect David Kirk called the unified graphics engines as an implementation detail, not a feature, but admitted the unified architecture would be nice for programmers, who would have one instruction set for vertex and pixel shaders.

“It’s not clear to me that an architecture for a good, efficient, and fast vertex shader is the same as the architecture for a good and fast pixel shader. A pixel shader would need far, far more texture math1 performance and read bandwidth than an optimized vertex shader. So, if you used that pixel shader to do vertex shading, most of the hardware would be idle, most of the time. Which is better – a lean and mean optimized vertex shader and a lean and mean optimized pixel shader or two less-efficient hybrid shaders? There is an old saying: ‘Jack of all trades, master of none’,” Mr. Kirk said in an interview with ExtremeTech web-site.

ATI: Bridging Today and Tomorrow

Not much is known about the architecture and capabilities of the code-named R520 product scheduled for release in Q2 2005 that was initially referred as the R500. What is clear now is that the new graphics chip will sport Shader Model 3.0 – pixel shaders 3.0 and vertex shaders 3.0 – bringing additional programming capabilities to ATI’s future graphics processors as well as some other innovations.

ATI’s R5xx architecture will not resemble that of the previous generation products and NVIDIA’s GeForce 6 architecture known as NV4x, particularly ATI will implement efficient flow-control, a crucial feature for pixel shaders 3.0, that will not bring speed penalty it does on existing SM3.0 hardware, according to sources. The future of the graphics hardware lies in higher number of ALUs ops per texture ops, unified pixel and vertex shaders as well as some other requirements of Microsoft Windows Longhorn operating system, such as virtualisation and context switches. While ATI agrees on the long-term goals for its roadmap, it does not name feature-set of actual products and says all the architectural changes will be implemented gradually, not at once.

Some sources claim that the R500 is a code-name of ATI’s graphics processor that will be submitted for Microsoft’s next Xbox console. The shader core of the R500 was reported to have 48 Arithmetic Logic Units (ALUs) that can execute 64 simultaneous threads on groups of 64 vertices or pixels. ALUs are automatically and dynamically assigned to either pixel or vertex processing depending on load. The ALUs can each perform one vector and one scalar operation per clock cycle, for a total of 96 shader operations per clock cycle. Texture loads can be done in parallel to ALU operations. At peak performance, the GPU can issue 48 billion shader operations per second, it was said.

The R520 is also expected to feature advanced memory interface, presumably supporting GDDR4 memory.

NVIDIA: Plans Unclear

While NVIDIA remains extremely tight-lipped over its future products, it is known that the company is readying its code-named NV47 visual processing unit, a massively revamped GeForce 6 architecture with 24 pixel pipelines. The NV47 is expected to be released sometime in Spring, 2005, but it is unknown whether NVIDIA is ahead, or behind ATI’s R520 product. NVIDIA also reportedly plans to release a chip called NV48 in Q2 2005.

The status of NVIDIA’s future architecture code-named NV50 is also uncertain: some reported recently that the chip had been cancelled, but officials decline to confirm or deny the information.


Comments currently: 17
Discussion started: 12/23/04 08:15:52 AM
Latest comment: 01/03/07 05:06:56 PM
Expand all threads | Collapse all threads


Hey, nice bias to the article numbnuts:

Shader unification is NOT an ATI thing, it's a Microsoft thing! :(
0 0 [Posted by:  | Date: 12/23/04 08:15:52 AM]
- collapse thread

Exactly like Mr. Huddy commented.
"he said unified pixel and vertex data processing is a required capability for Windows Graphics Foundation 2.0 that comes our together with Microsoft’s next-generation operating system called Windows Longhorn"
0 0 [Posted by:  | Date: 12/23/04 09:05:11 AM]
And MY point is that X-Bit is spinning it by saying, "NVIDIA Disagrees with ATI Technologies" and "ATI Says Unified Rendering Engine – the Way to Go, NVIDIA Disagrees". On top of that, David Kirk was pointing out the different needs of the pixel and vertex shading beasts - his point was not directed at DirectX Next, WGF2.0 or ATI or putting that down. He was pointing out an obvious hurdle, not trying to dissuade something that nVidia themselves have had direct input on (in DirectX technology) with Microsoft.

It's just not good journalism. Leave this type of piecemeal stuff to The Inquirer please.
0 0 [Posted by:  | Date: 12/23/04 09:33:03 AM]
Sorry, but I will disagree.

There is an architecture approach. ATI has one, NVIDIA has another - that's a fact. NVIDIA disagrees with ATI's approach at this point - that is also a fact. But ATI claims its approach complies to a standard - that is a yet another fact. Hence, I believe it is a normal way to say that ATI disagrees with NVIDIA on certain architecture approaches and otherwise. It is definitely not "spinning".
0 0 [Posted by:  | Date: 12/23/04 11:17:40 AM]
Wow. The fact is both ATI and nVidia have direct input on DirectX. If nVidia didn't like how that unfolded it's not exclusively ATI's fault/problem. I don't see that it is a matter of agreement or opinion - this is how the DirectX relationship is amongst these three players, is it not?

Additionally the question posed to David Kirk was not in reference to ATI exclusively but a concept introduced by DirectX Next and/or WGF 2.0...and even if it weren't referencing DXNext or WGF 2.0, it's simply referencing the ongoing question of "When is the GPU going to turn into a CPU, if ever?". ATI and nVidia are players within that scenario, not a creator of that scenario. Therefore David Kirk was not directly disagreeing with ATI. This is how XBit is spinning the scenario - you are creating a disagreement by association and that is is making more out of the situation than what exists. had a nice primer on DirectXNext many months ago w/a link on the frontpage for those who are unaware.

The single most-compelling proof of XBit's spin, is conveniently omitting this quote from David Kirk, "For sure, the distinction between the programming models and instruction sets of vertex shaders and pixel shaders should go away." THUS nVidia does NOT disagree with a unified shading technology as he DID agree with it.

Bad X-Bit. Shame on you!

0 0 [Posted by:  | Date: 12/23/04 12:25:35 PM]
I really am sorry, but now I don't understand your concern.

You would like to see our article entitled "NVIDIA does not agree with Microsoft", or what?

It is natural that NVIDIA and ATI have different design approaches. I understand both and publish both concepts. So, what's wrong?
0 0 [Posted by:  | Date: 12/23/04 01:03:17 PM]
Like I said before, "NVIDIA Disagrees with ATI Technologies" and "ATI Says Unified Rendering Engine – the Way to Go, NVIDIA Disagrees" - these are inaccurate and misleading.

I think a more-appropriate heading would be something like "ATI and nVidia's thoughts on a unified shader". There is no clashing of the titans going on here, no juicy trolling/flaming comments coming from either camp's marketing departments or anything fun like that. There are people that get confused-enough w/o a major site like X-Bit contributing to their confusion - I guarentee you right now there's going to be some knucklehead nVidia fanboy using this article as proof ATI is "wrong" or some birdbrained ATI fanboy using this article as proof that nVidia "can't do it".

I'm sensitive to this stuff - especially after THG calls the Gigabyte 3D1 the world's first dual-GPU card (as if they haven't been around the see the numerous other dual-GPU cards before the 3D1!?) - and previously I really hadn't noticed X-Bit making such a headline.

With all the fanboyism and spinning going on I'd rather make a fuss and hope to hold you up to a higher level.

0 0 [Posted by:  | Date: 12/23/04 01:31:42 PM]


Add your Comment

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture