SAN JOSE, Calif. – A unit of electronics giant GE has released hardware and software products supporting Nvidia graphics chips for general-purpose computing at an Nvidia developer conference. It is one of several companies supporting the chips for high-performance applications across a variety of vertical markets.
GE Intelligent Platforms announced the 6U OpenVPX CUDA Starter Kit, an integrated, hardware and software development environment for general-purpose computing on Nvidia graphics processors. It also announced AxisLib-GPU, a software environment for development and debugging of CUDA applications.
The 6U CUDA Starter Kit includes a single-board computer with an Intel Core2 Duo processor and an Nvidia 96-core GT240 GPU. It also includes a dual Nvidia GT240 GPU card to support multi-GPU configurations and a four-slot chassis with disk drives running and CentOS Linux. A 3U version is also available.
AxisLib-GPU is a library of optimized math and DSP functions taking advantage of general-purpose GPU computing on Nvidia processors. GE already ships versions of the library for Power and Intel x86 processors.
The software is a set of libraries providing more than 500 digital signal processing and vector math functions optimized for Nvidia's GPUs. It is geared for applications including radar, sonar, image processing and signals intelligence.
“When compared to FPGA-based application development, CUDA has been demonstrated to be both faster and less expensive,” said Rob McKeel, vice president of military and aerospace embedded computing for the GE unit, speaking in a press statement.