NVIDIA introduces high-performance platform for embedded systems
26 March 2014
NVIDIA launched a new platform to the support the development of a new generation of applications that employ computer vision, image processing and real-time data processing in a range of industries including automotive. The NVIDIA Jetson TK1 Developer Kit offers performance of 326 gigaflops—nearly three times more than any similar embedded platform.
The Jetson TK1 Developer Kit includes a full C/C++ toolkit based on NVIDIA CUDA architecture, the most pervasive parallel computing platform and programming model. The Jetson TK1 platform supports the NVIDIA VisionWorks toolkit, which provides a rich set of computer vision and image processing algorithms to create applications quickly. These include CUDA-powered capabilities in areas such as robotics, augmented reality, computational photography, human-computer interface and advanced driver assistance systems (ADAS).
| “Jetson TK1 fast tracks embedded computing into a future where machines interact and adapt to their environments in real time.” —Ian Buck, vice president of Accelerated Computing at NVIDIA |
At the heart of the Jetson TK1 Developer Kit is the Tegra K1 mobile processor, NVIDIA’s 192-core super chip built on the NVIDIA Kepler GPU architecture. Tegra K1’s 192 fully programmable cores deliver the most advanced graphics and compute performance in a mobile form factor.
The Tegra K1 processor is based on the same Kepler architecture that powers the US’s fastest supercomputer, the Titan supercomputer at Oak Ridge National Laboratories, as well the world’s 10 most efficient supercomputers. Designed from the ground up for CUDA—which has more than 100,000 developers at more than 8,000 institutions, and is taught at top universities in 62 countries—Jetson TK1 Developer Kit includes the programming tools required by software developers to quickly develop and deploy compute-intensive systems.
A range of developers and system builders in the industrial, robotics and medical fields have expressed support for the development platform.
GE Intelligent Platforms, for one, has signed an agreement with NVIDIA to bring products based on the NVIDIA Tegra K1 mobile processor to the embedded computing market. GE will be NVIDIA’s preferred provider of the new technology to serve applications in harsh environments, most notably to customers in the military/aerospace market.
Future mobile parallel computing machines, using 200+ low cost, low power consumption CPUs and GPUs, will make autonomous drive vehicles possible by 2020 or shortly thereafter.
A dual redundant system with appropriate sensors will eventually control autonomous drive vehicles much better than the average human driver. Up to 80% of current accidents could be avoided thereby reducing road fatalities in USA by 35,000 x .8 = 28,000/year to a low 7,000/year.
Will gun bullets fatalities increase at the same rate (or faster) than road fatalities decrease?
Posted by: HarveyD | 26 March 2014 at 05:55 AM