In a strategy shift, Nvidia plans to expand its business model by licensing its current and future GPU and modem technology to other silicon vendors. This includes the current Kepler GPU product family, as well as the modem technology acquired from Icera.
Nvidia has done it in past, when the company licensed an earlier GPU core to Sony for the Playstation 3. The company also receives more than $250 million a year from Intel as a license fee for its visual computing patents.
Now, the explosion of Android devices presents an unprecedented opportunity for Nvidia to accelerate this effort. The company will start by licensing the GPU core based on the NVIDIA Kepler architecture. Its DX11, OpenGL 4.3, and GPGPU capabilities, along with performance and efficiency, create a new class of licensable GPU cores. Nvidia claims that Kepler can operate in a half-watt power envelope, making it scalable from smartphones to supercomputers.
Kepler is the basis for currently shipping GeForce, Quadro and Tesla GPUs, as well as Nvidia's next-generation Tegra mobile processor codenamed Logan. Nvidia said it would offer licensees all necessary designs, collateral and support to integrate NVIDIA?s powerful graphics cores into their devices.
Nvidia will also offer licensing rights to its visual computing portfolio, enabling licensees to develop their own GPU functionality.
Admittedly, this opens up Nivida to competition for the company?s Tegra family of processors from silicon vendors using Nvidia technology. However, it will create opportunities for other silicon vendors to use the technology in targeting other markets and applications not targeted with Tegra.
Other GPU licensors are ARM, DMP, Imagination, and Vivante.
Nvidia's decision to enter the IP licensing business could be related to the lack of volume sales of Tegra, which has suffered from being a step behind companies like Qualcomm and MediaTek in integrating Wi-Fi and cellular modem technology, which is becoming a critical competitive factor in the mobile segment. Tegra has not secured any high-volume design wins, while emerging OEMs like Huawei and ZTE have not showed interest for Tegra as they develop their own processing solutions in-house or through subsidiaries.
New CUDA tools support ARM CPUs
Seperately, Nvidia released on Tuesday its CUDA 5.5 programming tools, which will for the first time support ARM CPUs.
CUDA parallel programming tools are iused by developers to write and manage applications that harness the combined processing power of GPUs, CPUs and other processors.
CUDA is offering performance boosts mainly in image processing, meaning that smartphones with cameras could see improved image processing and recognition. According to Nvidia, graphics processing is faster and more power-efficient through CUDA tools. The benefits of CUDA will also come to supercomputers running on ARM processors or Nvidia's graphics cards, Nvidia claims.
Since no CUDA 5.5 compatible chips are available so far, Nvidia is providing mobile developers a prototype Cuda 5.5 board - hardware that connects Tegra 3 chips with a CUDA-compatible GPU called Kayla through a PCI-Express slot.