Mobile GPU clustering enables quick & pertinent Big Data

By connecting clusters of low-power NVIDIA Tegra K1 mobile processors with IDT’s RapidIO interconnect and timing technology, the platform can deliver real-time data that network operators can use to provide consumers a more responsive and interactive experience.

Designed for high-performance computing, IoT appliances and wireless access networks handling 4G and higher traffic, the platform features cutting-edge deep learning and pattern recognition computing capabilities. By installing the hardware at multiple, geographically dispersed base stations along the edge of the network, the Big Data problem is solved by distributing the computing capacity and delivering  lightning-quick analysis of locally generated data, such as social media content.

Sailesh Chittipeddi, Vice President, Global Operations, and Chief Technology Officer, IDT, commented: “For example, if you tweet that you’ve just seen a movie and are headed out to dinner, some nearby dining options could pop up on your screen. Or the technology can be used for mass transit; if you’re standing at a bus stop, you can check your phone for the precise location of your bus. The possibilities are virtually endless.”

Chittipeddi refers to the platform as 'supercomputing at the edge' because the technology is deployed and analysis conducted at local base stations - at the edge of the wireless network - rather than in a central location, removing the bottleneck between the base station and the core of the network. “The solution was developed with an architecture designed to handle the emerging market for geographically distributed analytics, deep learning and pattern recognition in real time,” he said.

"By taking mobile low-power GPU technology and connecting it with 100ns latency RapidIO interconnect, this modular cluster can be deployed to distribute high-performance compute functionality to the edge of the wireless network, where it is most geographically sensitive," said Jag Bolaria of the Linley Group. "The innovation paves the path for co-locating real-time deployable analytics in the approximately 2m base stations deployed annually in wireless networks."

The 'Supercomputing at the Edge' platform uses IDT’s 20Gb/s interconnect technology to connect a low-latency cluster of NVIDIA Tegra K1 mobile processors. It’s suitable for micro base station deployment along with larger computing clusters in the C-RAN, a new cellular network architecture. Each computing card is based on connecting up to four GPU units per processing card connected with RapidIO low-latency NIC and switching products on board.

The platform, which can support up to 12 teraflops per IU RapidIO server blade, is based on servers from Prodrive Technologies and computing cards from Concurrent Technologies. Each computing card contains four NVIDIA mobile processors. The processors deliver 192 fully programmable CUDA cores for advanced graphics and compute performance. Each card in the system matches computing cores with 20Gb/s interconnect to each GPU, with over 140Gb/s of built-in switching at each node with IDT’s best-in-class timing solutions.

IDT will present the 'Supercomputing at the Edge' platform at the Linley Data Center Conference and Mobile World Congress.