Date: 08/10/2009

GE Fanuc deploys NVIDIA graphics processing units (GPUs) on its new hardware products

GE Fanuc has announced that it had signed an agreement with NVIDIA to develop new hardware products using NVIDIA graphics processing units (GPUs) based on the CUDA architecture, for military and aerospace applications.

These new products deliver processing capability for applications and environments that require leading edge computing such as radar, signals intelligence and video surveillance and interpretation.

"There has long been interest in taking the processing performance inherent in state-of-the-art GPUs - such as their massively parallel computing capability - and applying that to problems that have historically been solved using complex DSP and FPGA processor architectures," said Peter Cavill, General Manager, Military & Aerospace Products at GE Fanuc Intelligent Platforms. "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. 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 new generations of powerful mobile military platforms."

NVIDIA's CUDA technology delivers up to 100x increase in speed and lend themselves to parallel computing.

"CUDA is becoming increasingly pervasive in a broad range of environments and applications, and has reached a tipping point," said Taner Ozcelik, General Manager, Embedded Business at NVIDIA. "We're delighted to help GE Fanuc revolutionize mission critical embedded computing with CUDA in demanding military and aerospace applications, which have been historically constrained by compute performance."

A family of 6U VPX products will feature combinations of Intel dual core processors and NVIDIA CUDA-enabled GPUs, to create powerful multi-board solutions. This family, and the new 3U VPX platform, will additionally support OpenCL.

The CUDA architecture enables programmers to write programs in conventional computing languages to access the parallel processing capabilities of the GPU.

For more details visit www.gefanuc.com