Building NVIDIA's GT200

Here's a Streaming Processor, NVIDIA calls it an SP:

NVIDIA calls an individual SP a single processing core, which is actually true. It is a fully pipelined, single-issue, in-order microprocessor complete with two ALUs and a FPU. An SP doesn't have any cache, so it's not particularly great at anything other than cranking through tons of mathematical operations. Since an SP spends most of its time working on pixel or vertex data, the fact that it doesn't have a cache doesn't really matter. Aside from name similarities, one NVIDIA SP is a lot like a very simplified version of a SPE in the Cell microprocessor (or maybe the SPE is like a really simple version of one of NVIDIA's SMs, which we'll get to in a minute). While a single SPE in Cell has seven execution units, a single NVIDIA SP only has three.

By itself a SP is fairly useless, but NVIDIA builds GPUs and if you add up enough of these little monsters you can start to get something productive given that graphics rendering is a highly parallelizable task.

Here's a Streaming Multiprocessor, which NVIDIA abbreviates as SM:

A SM is an array of SPs, eight to be specific, along with two more processors called Special Function Units (SFUs). Each SFU has four FP multiply units which are used for transcendental operations (e.g. sin, cosin) and interpolation, the latter being used in some of the calculations for things like anisotropic texture filtering. Although NVIDIA isn't specific in saying so, we assume that each SFU is also a fully pipelined, single-issue, in-order microprocessor. There's a MT issue unit that dispatches instructions to all of the SPs and SFUs in the group.

In addition to the processor cores in a SM, there's a very small instruction cache, a read only data cache and a 16KB read/write shared memory. These cache sizes are kept purposefully small because unlike a conventional desktop microprocessor, the datasets we're trying to cache here are small. Each SP ends up working on an individual pixel and despite the move to 32-bit floating point values, there's only so much data associated with a single pixel. The 16KB memory is akin to Cell's local stores in that it's not a cache, but a software-managed data store so that latency is always predictable. With this many cores in a single SM, control and predictability and very important to making the whole thing work efficiently.

Take one more step back and you've got a Texture/Processor Cluster (TPC):


The G80/G92 TPC (left) vs. the GT200 TPC (right)

NVIDIA purposefully designed its GPU architecture to be modular, so a single TPC can be made up of any number of SMs. In the G80 architecture it was made up of two SMs but with the GT200 architecture it now has three SMs.

The components of the TPC however haven't changed; a TPC is made up of SMs, some control logic and a texture block. Remember that a SM is a total of 8 SPs and 2 SFUs, so that brings the total up to 24 SPs and 6 SFUs (must...not...type...STFU) per cluster in GT200 (up from 16 SPs and 4 SFUs in G80). The texture block includes texture addressing and filtering logic as well as a L1 texture cache.

The modular theme continues with the Streaming Processor Array (SPA) that is composed of a number of TPCs:


The GT200 SPA, that's 240 SPs in there if you want to count them

In G80 the SPA was made up of 8 TPCs, but with GT200 we've moved up to 10. Note that each TPC now has 3 SMs vs. 2, so the overall processing power of GT200 has increased by 87.5% over G80.


And here's G80/G92, only 128 SPs thanks to two SMs per TPC and 8 TPCs

At the front end of the GPU we've got schedulers and control logic to distribute workloads to the entire array of processing cores. At the other end we've got L2 texture caches and rasterization processors that handle final filtering and output of data to the frame buffer.

The culmination of all of this is that the new GT200 GPU, the heart of the GeForce GTX 280 and 260, features 240 SPs, 160KB of local memory, an even smaller amount of cache and is built on TSMC's 65nm process using 1.4 billion transistors.


1.4 Billion Transistors.  It wants vertex data.  Really bad.


754 Million Transistors

There are more transistors in this chip than there are people in China, and it's the largest, most compute-dense chip we've ever reviewed.

Index Lots More Compute, a Leetle More Texturing
POST A COMMENT

108 Comments

View All Comments

  • epobirs - Monday, June 16, 2008 - link

    There is an important precedent that gives Nvidia good reason to not rush to a new smaller process level. Recall when ATI first became a serious player in gaming GPUs with the 9700. It was for its time a big chip pushing the limits of the process level, while Nvidia at the time was concentrating on bleeding edge technology. Nvidia's chips got stomped by ATI's in that generation, in large part because the ATI chip had far better optimization of its transistors. Reply
  • anartik - Monday, June 16, 2008 - link

    We can agree the pricing sucks. But the point that seems to be missing is that Nvidia promised a 50% performance improvement and they delivered. The 280 delivers 45FPS vs 32FPS for the 9800GT in Assassins creed. Thats just shy of 50% (48FPS) which is a huge performance increase compared to what we have been getting the past couple years for a new card. Slap 2x280 on a card and it vaporizes the 9800 GX2 or any SLI/Xfire solution. The 9800 GX2 scales ~63% over the 9800GTX. So if you do that for a 280GX2 (or SLI) you get roughly 73 frames per second. Plus the new cards have more memory to deal with bandwidth and large textures vs the nuetered 512 on the 96/9800's and 8800GT... the reason I have held onto my 8800 GTX with 768mb. Granted I won't be rushing out and buying one tomorrow but the 280 is the fastest GPU and a x2 will be faster than any other x2 card. It's a little rediculous to think the single 280 sucks becuase it's not faster than multiple GPU's like the 9800 GX2 (although when memory counts it is). Reply
  • araczynski - Monday, June 16, 2008 - link

    this is all they could spit out? all that noise and all those transistors and it gets its ass handed to it by the gx2 more often than not?

    talk about fizzle, perhaps at best it'll lower the price of the gx2 a bit.

    not to mention no built in hdmi, good lord, they must've had two seperate teams working on the gtx and gx2 at the same time and just wanted to see what they could come up with separately.
    Reply
  • Ananke - Monday, June 16, 2008 - link

    I don't think many people at this forum tread understand that nVidia target is the supercomputer market. I was totally impressed from one post a month ago, where a software engineer managed to put and use 3 SLI system for magnetoresonance rendering. Nvidia and AMD /that's why they acquired ATI/ have already significant experience in multiprocessor and parallel calculation. nVidia is ahead though, since they have CUDA becoming more popular for complex calculation. A year ago Intel realized parallel processing from Sun is their biggest danger, now nVidia and Ati come too. Imagine, supercomputers build with thousands of G200 chips, and only some Intels used for mapping, instead of thousands of Xeons. nVidia thinks way more ahead just for the mere visual/gaming market. I am very very impressed, and very eager to see what ATI can do. Also, I hope Ati and Havoc will be able to offer competition to CUDA, or uniformity? Anyway, from a scientific point of view, recent developments in the graphic market make foundamental science more affordable than anytime before. Reply
  • Reflex - Monday, June 16, 2008 - link

    Anand/Derek -

    I am not sure why you are comparing this chip to a Penryn or other general purpose CPU as the comparisons are meaningless. GPU's are designed very differently than CPU's, namely a high level descriptor language is used and the design is then created by a program, which is then hand tweaked by engineers. By contrast, a CPU may use a high level language, but the actual design is almost entirely done by hand, with large teams working on each sub component and literally years of tweaking. It takes Intel between five and ten years to bring a design to market, which is why there is such a push by them to keep adjusting the design and optimizing it to stretch its usefulness out as long as possible to maximize the initial investment. This simply does not happen with a GPU.

    GPU's are designed to last 18-24 months as a competitive solution. nVidia and Ati cannot afford to spend even five years designing them. As a result the level of hand optimization is greatly reduced, and inefficiencies with transistors are tolerated. Typically they are produced on equipment that is already paid for by the previous, more optimized products, or contracted out to third parties(TSMC). Since the products are sold for a premium, the wasted die space is not very relevant. It is a diametrically opposed process to what you see with CPU development.

    Despite how impressive it may seem to go on about 1.4 billion transisters, truthfully a modern CPU does more with far less than a modern GPU, and honestly neither nVidia nor Ati are in the same league as Intel and AMD, neither at the engineering level nor when comparing the products they put out. To an Intel engineer, this GPU is at least four times larger than it needs to be to get the performance you get out of it.

    The maturation of the industry, either due to reaching a point where GPU's can do 90% of what anyone needs, or simply because power budgets get more restrictive, will come when the level of optimization required for a CPU is required for a GPU, and product cycles stretch out to 3-5 years. Then you will have a more direct comparison between the two, since the design parameters will be much more similiar.

    I am not knocking nV here, btw, I'm simply calling into question why one would even compare a Penryn to a GPU, it makes no sense at all when they were designed from the ground up for different purposes, lifespans and with different transister budgets.
    Reply
  • 7Enigma - Tuesday, June 17, 2008 - link

    I think what this shows is there a brute force way of doing something that while not necessarily pretty can get you to a goal. Yes compared to Intel's latest and greatest it is a grotesque abomination of wasted energy/transistors/die size, but the bottom line is it is pretty darn impressive from a CPU/GPU standpoint.

    I think many of us long for the days of more than 2 major competetors for each race (CPU/GPU). We've been stuck in a rut with ATI and Nvidia, AMD and Intel. Yes you have some niche products by other companies, and budget pieces being made by a host of has-beens, but really tier 1 stuff is just not being fought over by more than 2 companies.

    What I want to see (complete dreamland here) is a start up from some very savvy disgruntled employees of say AMD/ATI, Intel, IBM, etc. (and don't forget possibly the most important segment, the marketing team) with some clout and a LOT of dough to say, "Screw this, we're going balls to the wall and throw the kitchen sink at the market."

    I mean let's be honest here, what's another 100 watts or a billion transistors anymore? I can guarantee you every geek out there would shell out more money for a product that devestates the current competition. I don't care if it's not as frugal with the power, or as small, or as pretty, I want the speed man, gimme the speed!
    Reply
  • Anand Lal Shimpi - Monday, June 16, 2008 - link

    While I'd normally agree with you, GPUs have been getting pretty complex to design. Much of the shader multiprocessors in G80 and GT200 were designed by hand, and remember that G80 (the original predecessor to GT200) was in development for four years before its launch.

    The transistor comparison is a valid one, while Penryn is a very impressive design, it is so for different reasons than GT200. The size of GT200 also helps illustrate fundamental differences in approach to CPU vs. GPU design and really highlights why Intel is building Larrabee.

    -A
    Reply
  • crimson117 - Monday, June 16, 2008 - link

    Because to non-engineers, they're two silicon computer chips, and 1.4 billion of anything is a lot!

    It also helps me to visually understand why this thing gets so hot, since it's got so much more surface area packed with transistors.

    You're right that CPUs and GPUs are designed for different tasks and shouldn't be considered pure apples to apples, but then you go against your own advice and start saying how CPUs are so much more advanced, and how Intel engineers could do that in 1/4 the size of a chip. So which is it - should they be compared, or should they not be compared?

    And the authors did mention how simple it could be for either company to slap the other type of chip right in with their usual type; make a Intel CPU with added GPU capabilities, or make a nVidia GPU with CPU capabilities. So there's another point where they recognize the differences but do try to illustrate the sameness.

    So I'm not really sure your criticisms hold water.
    Reply
  • Reflex - Monday, June 16, 2008 - link

    You are looking for contradictions where there are none. A chip is a chip, but that does not mean that they are all designed with the same goals, budgets and time constraints. *IF* Intel devoted the resources to a GPU that they devote to a CPU, yes they could produce a product like this in a fraction of the transisters. That said, the product would take 5-10 years to design, would cost hundreds of millions of dollars to develop, and would need a lifespan of at least 5 years in the market to be worth the effort. Obviously this is not a reasonable approach in a market with such fast product turnover.

    My post was not an attempt to diss nV or this product, it was pointing out that the comparison of a GPU to a CPU is inane as they have completely different design constraints. You may as well compare a CPU to cache memory, or RAM or a sound processor. All have transisters, right?

    It especially bothered me when they implied that nVidia has the transister budget to toss a general purpose CPU on the die. The fact is that they may have the transister budget, but they do not have the time or money available to do so, and the product would be obsolete before it ever hit the market as a result of such an attempt. It would be marrying two completely different design philosophies, and this is why the combined CPU/GPU products that are upcoming are not likely to be the strongest performers.
    Reply
  • paydirt - Monday, June 16, 2008 - link

    You all seem to be assuming that GPUs will only be used for games. If that's all you care about, then why do you whine when a GPU is made to perform well as a number cruncher (for science, for modeling/simulations)?

    It's the best single GPU gaming card.
    It's the best widely (?) available GPU number cruncher.
    For a whole system gaming GPU solution, it isn't the most cost effective.

    If you're all into numbers, then why are you assigning emotions to it. It simply is what it is.
    Reply

Log in

Don't have an account? Sign up now