High Performance Embedded Computing
High Performance Computing has now come to the world of embedded systems – and, especially, to the systems being developed and deployed by the world's armed forces. To address the most demanding and sophisticated applications, such as ISR and electronic warfare, high performance embedded computing – HPEC – uses the power, not just of multiple single board computers working together, but also of multi-core and many-core processors.
| HPEC Brochure | rugged 6U OpenVPX InfiniBand | (HPEC) Center of Excellence | (HPEC) Lab Development System | |||
|
GE brings the performance of supercomputers to the harsh environments of the military and aerospace domains. By using designs based on standard architectures and interconnects, and applying our unrivaled expertise in packaging, compute power that was previously restricted to air-conditioned machine rooms can now be brought to bear on the toughest problems in the toughest environments. GE's HPEC product family includes our DSP280 dual 2nd Generation Intel Quad Core i7 platform which is capable of more than 260 Gigaflops peak performance, our SBC625 3rd Generation Core i7 6U OpenVPX SBC, our latest NPN240 dual NVIDIA CUDA GPGPUs and switch fabric modules (SFMs) such as the GBX460 10GE card. These COTS OpenVPX modules harness mainstream LINUX and Windows™ platforms along with open middlewares to deliver world class performance at a fraction of the cost of proprietary solutions. |
AXIS Advanced Multiprocessor Integrated SoftwareAXISLIB-AVX is GE's comprehensive DSP and math function library providing the full VSIPL Core 1.0 profile with hand optimized AVX support to extract game changing levels of performance from Intel's brand new 256bit wide SIMD AVX unit. The VSIPL API ensures code portability across multiple processor generations in support of planned technology refresh during the entire program life cycle. AXISPRO includes a high-performance IPC middleware and GUI for task-level programming and fast prototyping to reduce development cost and shorten time to solution of even the most complex signal processing applications. |
|||||















REQUEST MORE INFO