Hundreds of video gamers eagerly convened in SanJose, Calif., last November to celebrate the arrivalof
Since then, it's been Nvidia hitting the road, striving to convince a different group of computer users of the merits of a chip that the company hopes will bring a big boost to its business.
In June, Nvidia will launch a new brand dedicated to selling the G80 -- not as a graphics accelerator for PCs and workstations, but as a chipintended to take on data-crunching computing chores currently handled by microprocessors.
Nvidia calls the concept "GPU computing" and contends that the 128 individual "stream" processors packed into the G80 chip make it ideally suited for such computational heavy lifting.
According to CEO Jen-Hsun Huang, the G80 boasts 10 times the floatingpoint computational muscle of today's top-of-the-linePC microprocessor.
"We believe GPU computing will usher in an era ofthe personal supercomputer, and will dramaticallyaccelerate the adoption of new methods fromcomputational chemistry to computational finance tocomputational genomics," Huang said in a Februaryconference call with financial analysts.
The effort is being spearheaded by Andy Keane, whojoined Nvidia last year and has worked atmicroprocessor outfits like
Last year, speculation grew that Nvidia was secretly developing a PC microprocessor based on the x86 instruction set to better compete with the recently merged
Advanced Micro Devices
and ATI Tech, which fields both graphicschips and microprocessors, as well as Intel, whichalready has both capabilities.
For now, though, Nvidia appears to be approaching thecomputing market from another angle.
Nvidia says the GPU computing businesswill focus on high-performance computing, a market inwhich multimillion-dollar supercomputers and banks ofinterconnected servers plow through massive amounts ofdata to simulate nuclear blasts, uncover oil and gasdeposits and run complex financial models.
All those applications require parallel computing, somethingwhich graphics processors are inherently good at doing.
Compared to current hardware requirements, thepotential to use mass-produced Nvidia graphics chipsto do these jobs offers customers a lot of bang forthe buck.
"Because the graphics guys are turning out thesechips that have a very high inherent floating pointcapability, and doing it in much higher volumes thanany supercomputer could ever think about ... theeconomics are very compelling," says Nathan Brookwood,a microprocessor analyst with research firm Insight64.
"If you have a problem that lends itself to lotsof computation in parallel, then this is a very cost-effective approach," Brookwood says.
But Wall Street is taking a wait-and-see attitude tothe graphics processor's alter-ego.
"It's an intriguing avenue of development," saysStifel Nicolaus analyst Blake Fischer. "The issue is,what is its applicability into the real world? Fromwhat we're seeing at this point, we view it as more ofa niche product."
Mainstream PC users don't really need parallelprocessing capabilities, nor is the software that runson standard PCs optimized to take advantage ofparallel processing.
That leaves Nvidia's GPU computing group fishing in a small, albeit lucrativepond, say analysts.
The Cell processor, jointly developed by
, also boastsparallel processing prowess. But besides beingfeatured in Sony's own PlayStation 3 game console andcertain medical imaging products from
, thechip has yet to gain much mass appeal.
However, Nvidia isn't dissuaded by fears of a limitedaddressable market, and believes the new GPU computingbusiness will help its professional group grow to a $1billion business in the next couple of years, says Michael Hara, vice president of investor relations.
Of course, the company's professional group, which currentlyprovides traditional graphics accelerators forworkstations, is already a $500 million businessesgrowing at 30% a year. So, the $1 billion mark would beattainable in a few years anyway at current growthrates.
However, GPU computing adds another engine to Nvidia'sprofessional group, giving investors confidence thatthat business will be able to keep growing, saysStifel Nicolaus' Fischer.
"But I don't think many people have started tobake that into their estimates," Fischer says. StifelNicolaus makes a market in Nvidia shares.
That said, any contribution from the new GPUcomputing effort can only help the bottom line.Nvidia's current crop of professional products carryprofit margins in the 60% range, well above thecorporate average of 44%. And the forthcoming GPUcomputing products promise similar margin advantages,since they leverage the investments Nvidia has alreadymade in its mainstream graphics processors.
The expectation on the Street is that Nvidia willraise its corporate gross margin target from itscurrent level of 45% sometime in the next fewquarters.
If the GPU computing business lends a handin hoisting the margin, it will already have earnedits keep.