Continuing our SC12 related coverage today, while AMD was the first GPU announcement of the day they are not the only one. NVIDIA is also using the venue to launch their major GPU compute product for the year: Tesla K20.

We first saw Tesla K20 at NVIDIA’s 2012 GPU Technology Conference, where NVIDIA first announced the K20 along with the already shipping K10. At the time NVIDIA was still bringing up the GPU behind K20 – GK110 – with the early announcement at GTC offering an early look at the functionality it would offer in order to prime the pump for developers. At the time we knew quite a bit about its functionality, but not its pricing, configuration, or performance.

More recently, upon completion of K20 NVIDIA has dedicated most of the initial allocation to Oak Ridge National Laboratory’s Titan supercomputer, completing delivery on a contract years in the making. As it turned out K20 was quite powerful indeed, and with K20 providing some 90% of the computational throughput of the supercomputer, Titan has taken the #1 spot on the fall Top500 supercomputer list.

This brings us to today. With Titan complete NVIDIA can now focus their attention and their GPU allocations towards making the Tesla K20 family available to the public at large. With SC12 and the announcement of the new Top500 list as their backdrop, today NVIDIA will be officially launching the Tesla K20 family of compute GPUs.

NVIDIA Tesla Family Specification Comparison
  Tesla K20X Tesla K20 Tesla M2090 Tesla M2070Q
Stream Processors 2688 2496 512 448
Core Clock 732MHz 706MHz 650MHz 575MHz
Shader Clock N/A N/A 1300MHz 1150MHz
Memory Clock 5.2GHz GDDR5 5.2GHz GDDR5 3.7GHz GDDR5 3.13GHz GDDR5
Memory Bus Width 384-bit 320-bit 384-bit 384-bit
Single Precision 3.95 TFLOPS 3.52 TFLOPS 1.33 TFLOPS 1.03 TFLOPS
Double Precision 1.31 TFLOPS (1/3) 1.17 TFLOPS (1/3) 655 GFLOPS (1/2) 515 GFLOPS (1/2)
Transistor Count 7.1B 7.1B 3B 3B
TDP 235W 225W 250W 225W
Manufacturing Process TSMC 28nm TSMC 28nm TSMC 40nm TSMC 40nm
Architecture Kepler Kepler Fermi Fermi
Launch Price >$3199 $3199? N/A N/A

When NVIDIA first announced K20 back in May we were given a number of details about the GK110 GPU that would power it, but because they were still in the process of bringing up the final silicon for GK110 we knew little about the shipping configuration for K20. What we could say for sure is that GK110 was being built with 15 SMXes, 6 memory controllers, 1.5MB of L2 cache, and that it would offer double precision (FP64) performance that was 1/3rd its single precision (FP32 rate). Now with the launch of the K20 we finally have details on what the shipping configurations will be for K20.

First and foremost, K20 will not be a single GPU but rather it will be a family of GPUs. NVIDIA has split up what was previously announced as a single GPU into two GPUs: K20 and K20X. K20X is the more powerful of these GPUs, featuring 14 active SMXes along with all 6 memory controllers and 1.5MB of L2 cache, attached to 6GB of GDDR5. It will be clocked at 732MHz for the core clock and 5.2GHz for the memory clock. This sets a very high bar for theoretical performance, with FP32 performance at 3.95 TFLOPS, FP64 performance at 1.31 TFLOPS, and fed by some 250GB/sec of memory bandwidth. For those of you who have kept an eye on Titan, these are the same specs as the GPUs Titan, and though NVIDIA would not name it at the time we can now confirm that Titan is in fact composed of K20X GPUs and not K20.

Below K20X will be the regular K20. K20 gives up 1 SMX and 1 memory controller, giving it 13 SMXes, 5 memory controllers, 1.25MB of L2 cache, and 5GB of GDDR5. It will also be clocked slightly lower than K20X, with a shipping core clock of 706MHz while the memory clock is held at 5.2GHz. This will give K20 theoretical performance numbers around 3.52 TFLOPS for FP32, 1.17 TFLOPS for FP64, fed by 208GB/sec of memory bandwidth.

This split ends up being very similar to what NVIDIA eventually did with the Fermi generation of Tesla products such as the M2090 and M2075, spacing their products not only by performance and pricing, but also by power consumption. K20X will be NVIDIA’s leading Tesla K20 product, offering the best performance at the highest power consumption (235W). K20 meanwhile will be cheaper, a bit slower, and perhaps most importantly lower power at 225W. On that note, despite the fact that the difference is all of 10W, 225W is a very important cutoff in the HPC space – many servers and chasses are designed around that being their maximum TDP for PCIe cards – so it was important for NVIDIA to offer as fast a card as possible at this TDP, alongside the more powerful but more power hungry K20X. This tiered approach also enables the usual binning tricks, allowing NVIDIA to do something with chips that won’t hit the mark for K20X.

Moving on, at the moment NVIDIA is showing off the passively cooled K20 family design, confirming in the process that both K20 and K20X can be passively cooled as is the standard for servers. NVIDIA’s initial wave of focus for the Telsa K20 is going to be on servers (it is SC12 after all), but with K20 also being an integral part of NVIDIA’s next-generation Maximus strategy we’re sure to see actively cooled workstation models soon enough.

NVIDIA Launches Tesla K20, Cont


View All Comments

  • CeriseCogburn - Thursday, November 29, 2012 - link

    Maybe he's the hacker that gives the -20 to every post on every gpu article at Tom's that is not 100% amd fanboy lie plus up based, or even hints at liking any nVidia card, ever.
    I'm so SICK of having to hit the show post crap at Tom's in order to read any comments that aren't radeon rager amd favor boys
  • nutgirdle - Monday, November 12, 2012 - link

    I've heard through back channels that nVidia may be moving away from supporting OpenCL. Can you confirm any of this? Reply
  • Ryan Smith - Monday, November 12, 2012 - link

    There's always going to be that nagging concern since NVIDIA has CUDA, but I haven't heard anything so substantiate that rumor. Reply
  • CeriseCogburn - Thursday, November 29, 2012 - link

    You mean you're worried and still sore over how pathetic AMD has been in it's lack and severey long time lacking suport for OpenCL compared to nVidia's far ahead forever and a long time great job in actually supporting it and breaking all the new ground, while amd fanboys whine OpenCl is the way and amd PR propaganda liar freaks paid by amd squeal OpenCL should be the only way forward ?
    Yeah, that's what you really meant, or rather should have said.
    Hey, cheer up, amd finally got the checkmark in GPU-Z for OpenCL support. Like YEARS after nVidia.
    Thanks, I love the attacks on nVidia, while amd is crap.
    It's one of the major reasons why amd is now nearly dead. The amd fanboys focus on hating the rich, prosperous, and profitable competition 100%, instead of directing their efforts at kicking the loser, amd, in the head or groin, or at all, let alone hard enough, for their failures to become apparent and self evident, so that they actually do something about them, fix them, and perform.
    Most famous Catalyst Maker quote: " I didn't know we had a problem. "
    That's amd professionalism for you.
  • Casper42 - Wednesday, May 15, 2013 - link

    CeriseCogburn, how are you not banned from here?

    I'm an Nvidia fan, but 90% of what comes out of your keyboard is just hate and vitriol.

    Tone it down a little man!
  • Jorange - Monday, November 12, 2012 - link

    So the GK110 will form the basis of the GTX 680's replacement? Reply
  • thebluephoenix - Monday, November 12, 2012 - link

    Yes. Reply
  • suryad - Friday, November 16, 2012 - link

    That's pretty much what I needed to hear. My Geforce 285 GTX OC editions in SLI are getting a bit long in the tooth! Reply
  • Ryan Smith - Monday, November 12, 2012 - link

    Frankly we have no idea. It is a GPU, so NVIDIA could absolutely do that if they wanted to. But right now the entire allocation is going to Tesla. And after that I would expect to see a Quadro GK110 card before we ever saw a consumer card. Reply
  • mayankleoboy1 - Monday, November 12, 2012 - link

    Probably no. Why should it ? With HPC, they can sell it at $4000, making atleast $2000 in profit.

    With a consumer gaming card, thay would have to sell it at $ 600 max, making $150-200 max.

Log in

Don't have an account? Sign up now