Since 1986 - Covering the Fastest Computers in the World and the People Who Run Them

Language Flags
May 1, 2014

NVIDIA Enables Device-Level Supercomputing

Tiffany Trader
TK1_Dev_Kit-6350-GREEN-V4_280

The Jetson TK1 development kit is now shipping. Order what GPU maker NVIDIA calls the “first mobile embedded supercomputer” and you’ll get a board with the same core technology that’s in use by many of the world’s fastest supercomputers, including the top US system, Titan. You’ll also receive an AC adapter with power cord, a USB cable for flashing, and NVIDIA’s quick start guide.

NVIDIA sums up the Jetson TK1 as “a tiny but full-featured computer designed for the development of embedded and mobile applications.” The $192 kit offers 192 programmable Tegra K1 cores, perfect for tasks like feature-detection and tracking, object recognition, and 3D scene analysis.

Notably, the project is the first to meld CUDA with mobile GPUs. The TK1 – which combines a Kepler GPU with a NVIDIA 4-plus-1 quad-core ARM Cortex-A15 CPU – is “the only mobile processor today that supports CUDA 6 for computing and full desktop OpenGL 4.4 and DirectX 11 for graphics,” according to NVIDIA.

The board employs the same Kepler architecture and CUDA core technology as NVIDIA supplies to leading labs and universities to accelerate computational workloads.

What this means, according to NVIDIA blogger Will Park, is that “the applications for Tegra K1 are already here.”

“The result: Jetson TK1 is a great development platform for computer vision and CUDA applications for robotics, medicine, security, automotive, and defense applications, among others,” continues Park.

Each 5″ wide by 5″ long board comes with the Tegra K1 processor, 2 GB of RAM, 16 GB 4.51 eMMC memory, and a long list of peripherals and ports. CUDA-support in a compact, low-power platform “makes development as simple as developing on a PC,” says the GPU maker.

The kit offers an opportunity for developers, professional, student or hobbyist, to unleash their inner Edison. With so many possible applications, and a potential 300 Gigaflops of computing power per board, the really cool part will be seeing what kind of creative visions will be enabled.

NVIDIA is also targeting the Jetson TK1 at OEMs – robotics, avionics, and medical device companies – who can use Tegra K1 SoCs to develop new products, and can employ Jetson to make the process easier. When they’re ready to enter production, they can customize the compute elements by working with one of NVIDIA’s board partners.

The technology is available now for $1 per core, sold in increments of 192.

Tags: , , ,

SC14 Virtual Booth Tours

AMD SC14 video AMD Virtual Booth Tour @ SC14
Click to Play Video
Cray SC14 video Cray Virtual Booth Tour @ SC14
Click to Play Video
Datasite SC14 video DataSite and RedLine @ SC14
Click to Play Video
HP SC14 video HP Virtual Booth Tour @ SC14
Click to Play Video
IBM DCS3860 and Elastic Storage @ SC14 video IBM DCS3860 and Elastic Storage @ SC14
Click to Play Video
IBM Flash Storage
@ SC14 video IBM Flash Storage @ SC14  
Click to Play Video
IBM Platform @ SC14 video IBM Platform @ SC14
Click to Play Video
IBM Power Big Data SC14 video IBM Power Big Data @ SC14
Click to Play Video
Intel SC14 video Intel Virtual Booth Tour @ SC14
Click to Play Video
Lenovo SC14 video Lenovo Virtual Booth Tour @ SC14
Click to Play Video
Mellanox SC14 video Mellanox Virtual Booth Tour @ SC14
Click to Play Video
Panasas SC14 video Panasas Virtual Booth Tour @ SC14
Click to Play Video
Quanta SC14 video Quanta Virtual Booth Tour @ SC14
Click to Play Video
Seagate SC14 video Seagate Virtual Booth Tour @ SC14
Click to Play Video
Supermicro SC14 video Supermicro Virtual Booth Tour @ SC14
Click to Play Video