NVIDIA's Fermi: Architected for Tesla, 3 Billion Transistors in 2010
by Anand Lal Shimpi on September 30, 2009 12:00 AM EST- Posted in
- GPUs
Final Words
Today's launch is strange. I tried to convince NVIDIA to release more information about Fermi but was met with staunch resistance from the company. NVIDIA claims that by pre-announcing Fermi's performance levels it would seriously hurt its existing business. It's up to you whether or not you want to believe that.
Last quarter the Tesla business unit made $10M. That's not a whole lot of money for a company that, at its peak, grossed $1B in a single quarter. NVIDIA believes that Fermi is when that will all change. To borrow a horrendously overused phrase, Fermi is the inflection point for NVIDIA's Tesla sales.
By adding support for ECC, enabling C++ and easier Visual Studio integration, NVIDIA believes that Fermi will open its Tesla business up to a group of clients that would previously not so much as speak to NVIDIA. ECC is the killer feature there.
While the bulk of NVIDIA's revenue today comes from 3D graphics, NVIDIA believes that Tegra (mobile) and Tesla are the future growth segments for the company. This hints at a very troubling future for GPU makers - are we soon approaching the Atom-ization of graphics cards?
Will 2010 be the beginning of good enough performance in PC games? Display resolutions have pretty much stagnated, PC games are first developed on consoles which have inferior hardware and thus don't have as high the GPU requirements. The fact that NVIDIA is looking to Tegra and Tesla to grow the company is very telling. Then again, perhaps a brand new approach to graphics is what we'll need for the re-invigoration of PC game development. Larrabee.
If the TAM for GPUs in HPC is so big, why did NVIDIA only make $10M last quarter? If you ask NVIDIA it has to do with focus and sales.
According to NVIDIA, over the past couple of years NVIDIA's Tesla sales efforts have been scattered. The focus was on selling to any customers that could potentially see a speedup, trying to gain some traction for the Tesla business.
Jen-Hsun did some yelling and now NVIDIA is a bit more focused in that department. If Tesla revenues increase linearly from this point, that's simply not going to be enough. I asked NVIDIA if exponential growth for Tesla was in the cards and if so, when would it happen. The answer was yes and with Fermi.
We'll see how that plays out, but if Fermi doesn't significantly increase Tesla revenues then we know that NVIDIA is in serious trouble.
The architecture looks good, Fermi just needs to be priced right. Oh and the chip needs to hurry up and come out.
Facebook
Twitter
RSS
415 Comments
View All Comments
hazarama - Saturday, October 3, 2009 - link
"Do you see any sign of commercial software support? Anybody Nvidia can point to and say "they are porting $important_app to openCL"? I haven't heard a mention. That pretty much puts Nvidia's GPU computing schemes solely in the realm of academia"Maybe you should check out Snow Leopard ..
samspqr - Friday, October 2, 2009 - link
Well, I do HPC for a living, and I think it's too early to push GPU computing so hard because I've tried to use it, and gave up because it required too much effort (and I didn't know exactly how much I would gain in my particular applications).I've also tried to promote GPU computing among some peers who are even more hardcore HPC users, and they didn't pick it up either.
If even your typical physicist is scared by the complexity of the tool, it's too early.
(as I'm told, there was a time when similar efforts were needed in order to use the mathematical coprocessor...)
Yojimbo - Sunday, October 4, 2009 - link
>>If even your typical physicist is scared by the complexity of the >>tool, it's too early.This sounds good but it's not accurate. Physicists are interested in physics and most are not too keen on learning some new programing technique unless it is obvious that it will make a big difference for them. Even then, adoption is likely to be slow due to inertia. Nvidia is trying to break that inertia by pushing gpu computing. First they need to put the hardware in place and then they need to convince people to use it and put the software in place. They don't expect it to work like a switch. If they think the tools are in place to make it viable, then how is the time to push, because it will ALWAYS require a lot of effort when making the switch.
jessicafae - Saturday, October 3, 2009 - link
Fantastic article.I do bioinformatics / HPC and in our field too we have had several good GPU ports for a handful for algorithms, but nothing so great to drive us to add massive amounts of GPU racks to our clusters. With OpenCL coming available this year, the programming model is dramatically improved and we will see a lot more research and prototypes of code being ported to OpenCL.
I feel we are still in the research phase of GPU computing for HPC (workstations, a few GPU racks, lots of software development work). I am guessing it will be 2+ years till GPU/stream/OpenCL algorithms warrant wide-spread adoption of GPUs in clusters. I think a telling example is the RIKEN 12petaflop supercomputer which is switching to a complete scalar processor approach (100,000 Sparc64 VIIIfx chips with 800,000 cores)
http://www.fujitsu.com/global/news/pr/archives/mon...">http://www.fujitsu.com/global/news/pr/archives/mon...
Thatguy97 - Thursday, May 28, 2015 - link
oh fermi how i miss ya hot underperforming ass