During today’s Nvidia (NASDAQ:NVDA) earnings call for Q3 with very good numbers, Nvidia’s CEO Jen-Hsun Huang indicated that the company was already actively discussing licensing its GPU technologies in the mobile space to certain partners.
While Huang did not say how many partners they were working with or at what stage they were in the discussions, he did say the following, “Our licensing discussions are very active. And we have many in important stages.”
That statement was a response to an analyst question about the success of Maxwell and if it was bringing any potential progress on the licensing front. Currently, Nvidia is the sole user of its mobile GPUs and mobile GPU IP, however, with the success of Maxwell in desktop, there is a very good chance that some companies would become interested in utilizing it for their SoCs. Afterall, if you look at some of our Maxwell reviews, you can see that Nvidia is getting much more performance out of their GPUs while using the same process (28nm) as the previous generation and simultaneously reducing power. These advancements eventually trickle down to Nvidia’s mobile products as the company’s product roadmaps have indicated in the past.
Currently, the Tegra K1 utilizes Nvidia’s Kepler architecture, which was originally launched in desktop and laptop GPUs back in 2012 and then perfected in 2013 with the GTX Titan. Following the Kepler release in 2012, Nvidia announced the Tegra K1 (formerly known as Tegra 5) with Kepler in the beginning of this year and has been shipping Tegra K1 SoCs since the summer. So, a realistic timeframe to see Maxwell GPU IP in mobile is very likely going to be towards the tail end of 2015 or the beginning of 2016, so that isn’t necessarily going to be as quick as the mobile refresh cycle usually is. However, with each generation of SoC Nvidia has vastly improved the speed of GPU architecture implementation so there’s no knowing exactly how soon we could see an Nvidia GPU in something like a MediaTek.
It will be interesting to see how Nvidia will balance their GPU IP licensing with customers if they are also simultaneously competing with them. After all, ARM and IMG license both CPUs and GPUs, but neither of them actually produce their own products that compete with their licensees. There is also a chance that Nvidia may be trying to muscle weaker companies into licensing their technology because of the strength of their patents, which may be why Nvidia recently sued Samsung and Qualcomm.