We already know that 16nm FinFET manufacturing process has been heavily delayed but, during its earnings call held few days ago, Nvidia teased its upcoming next-gen GPU, the GM200, and was quite keen to express its excitement.


Considering that the Maxwell GPU architecture is quite efficient, and since 16nm FinFET manufacturing process is heavily delayed by TSMC, Nvidia might have decided to launch the big GM200 on 28nm manufacturing process, and later re-release it on 16nm, when it is ready in late 2015 or early 2016.

When asked if the company is going to skip 20 nanometer and go straight to FinFET, Nvidia CEO, Jen-Hsun Huang, noted that "We haven’t announced our next generation products yet. And so we’ve got lot of great surprises for you guys and I’m excited about our next generation GPU. But right now we’re enjoying ramping Maxwell. ….. And so Maxwell is unquestionably at this point a home run and we’re just savoring the moment and ramping the living daylights out of it."

Since AMD is not skipping the 20nm manufacturing process, this could help Nvidia to keep the competition at bay, despite the fact that the GPU will be based on 28nm manufacturing process.

According to early rumors, the GM200 GPU could bring up to 50 percent better performance when compared to the GM204 GPU-based GTX 980, which certainly sounds like a neat performance boost.



Source: via Wccftech.com.