The rift between Intel and Nvidia is about to get much, much bigger.
For years, many have speculated that Nvidia would eventually release its own x86-based processor. While rumors can come and go, one is hard pressed to ignore Nvidia CPU talk when it's coming from an executive inside the Santa Clara, CA company.
While taking questions at a Morgan Stanley conference in San Francisco yesterday, Nvidia's Michael Hara (Senior VP of investor relations) said an Nvidia-branded x86 CPU is a certainly within the next several years. “The question is not so much I think if; I think the question is when," said Hara. “I think some time down the road it makes sense to take the same level of integration that we’ve done with Tegra."
Nvidia's ARM-based Tegra CPU combines all computing functions (general purpose, video, etc.) onto one piece of silicon, and is expected to make a splash in the smartphone market, and may even find its way into other mobile devices. "Tegra is by any definition a complete computer on a chip, and the requirements of that market are such that you have to be very low power, very small, but highly efficient," said Hara. "So in that particular state it made a lot of sense to take that approach, and someday it’s going to make sense to take the same approach in the x86 market as well.”
While seeing an Nvidia x86 CPU would certainly shake up the marketplace, Hara says it wouldn't necessarily be for high demand machines. Instead, he believes that keeping high performance computing discrete will allow for the best performance. He proposes an Nvidia x86 chip for low power computing, like netbooks and MIDs. Sure, an Nvidia "Extreme Edition" CPU would be killer, but an offering from Nvidia in the mobile computing market would still give Intel and the Atom processor a run for their money.
With Nvidia and Intel already butting heads on discrete graphics, embedded graphics, chipsets and licensing, adding CPU design and manufacturing to the list just fuels what seems like an eternal technology rivalry.