Over the past couple of weeks, we spoke with multiple sources in the NVIDIA ecosystem, who are hearing that NVIDIA is ready to hit the silicon production with TSMC’s 28nm process.
"We have working silicon and, momentarily, about to go to production with 28-nanometer. And it’s looking really good, it’s looking much, much better than our experience with 40-nanometer. It’s just a comprehensive, across-the-board engagement between TSMC and ourselves, and making sure that we’re ready for production ramp when the time comes. So I feel really good about 28."
The quote above comes from the co-founder and CEO of NVIDIA, Jen-Hsun Huang from the the recent transcript of the 2Q FY 2012 conference call. There was one thing omitted though – those initial parts are not based on Kepler architecture.
According to our sources, the company will repeat the strategy from previous architectures (G80-G9x, GT200-GT21X) and introduce a limited number of die-shrunk Fermi-based parts which are to be used for process optimization.
As such, the low-numbered GeForce 600 parts will target OEM and SI vendors, but we expect some parts to appear in e-tail/retail as well, as the box-business (Add-In-Board Vendors) companies usually get their share of parts which are worth seeing in discrete end of business.
Does this mean that Kepler will skip the GeForce 600 naming and become GeForce 700 Series, as it happened with GeForce 300 and 400? Only time will tell.
The parts are planned for introduction for this years’ holiday season.