CHARLOTTESVILLE, Va., 9 Oct. 2009. GE Fanuc Intelligent Platforms in Charlottesville, Va., plans to develop VPX-based embedded computing products using NVIDIA embedded graphics processing units in its embedded systems products intended for applications in radar systems, signals intelligence, and video surveillance.
These graphics processing units (GPUs) from NVIDIA Corp. in Bedford, Mass., are based on CUDA architecture, which delivers as much as 100x increase in speed in a broad range of applications that lend themselves to parallel computing.
Early tests at GE Fanuc have shown that military applications will benefit from similar increases in speed. A major prime contractor in the military/aerospace industry has evaluated the CUDA architecture in a radar system, and found that performance improvement of 15x is achievable with minimal reprogramming effort. Other prime contractors are expressing substantial interest in the technology.
"The CUDA architecture allows us to offer our customers a level of processing performance that surpasses anything else in the industry by a significant margin," explains Peter Cavill, general manager of military and aerospace products at GE Fanuc.
"NVIDIA GPUs, in effect, bring the power of supercomputing and parallel processing to applications that are size-, weight- and power-constrained, and will enable us to create generations of powerful mobile military platforms," Cavill says.
In addition to having potential applications in radar, signals intelligence, and video surveillance and interpretation, GPUs based on the CUDA architecture represent outstanding potential in other application areas including target tracking, image stabilization, synthetic aperture radar simulation, pattern recognition, video encoding/decoding, graphics rendering, object recognition, in-crowd behavioral monitoring and analysis, cryptography, sensor processing and software defined radio. Traditional graphics applications will also benefit greatly from high performance NVIDIA GPUs.
GE Fanuc hardware products with CUDA-based GPUs will be announced before the end of this year, company officials say. The first board will be 3U VPX-based. A family of 6U VPX products will have combinations of Intel dual core processors and NVIDIA CUDA-enabled graphics.
The CUDA architecture enables programmers to write programs in conventional computing languages to access the massively parallel processing capabilities of the GPU. This architecture, in tandem with the CUDA C language -- the same as conventional C with minor extensions -- allows developers to achieve transformative increases in performance.
For more information contact GE Fanuc online at www.gefanuc.com.
