Curtiss-Wright Controls Embedded Computing (CWCEC) has introduced the VPX6-490 OpenVPX GPU Application Accelerator that provides two Nvidia Fermi architecture GPU devices on a 6U VPX board.
Based on industry-standard MXM modules, the VPX6-490 is fitted with a pair of 240 core GPU devices each with 2GB of GDDR5 memory. The VPX6-490 leverages new OpenVPX profile standards to deploy the bandwidth of two 16-lane Gen2 PCI Express interfaces which is critical to maximizing the performance that can be extracted from the GPUs.
Integrated into a High Performance Embedded Computing (HPEC) subsystem, VPX6-490 functions as a co-processor attached to a host Intel-processor board and takes advantage of the new PCIe Expansion Plane definitions in the VITA 65 OpenVPX standard to provide off the shelf backplane support for high-speed interconnection between pairs of SBC/GPU.
The combination of 2nd Generation Intel processors, gen2 PCI Express interconnect and 480 NVIDIA CUDA cores raises the performance bar for embedded High Performance Embedded Computing (HPEC) systems for demanding military digital signal processing (DSP) applications such as C4ISR, EO/IR, and SatCom.
The VPX6-490 is designed to work with Intel processor- based SBCs, such as the Curtiss-Wright VPX6-1956 2nd Generation Intel Core i7 and the CHAMP-AV8 dual 2nd Generation Intel Core i7 multiprocessor card.
• 6U OpenVPX form factor
• One or two Nvidia® Fermi architecture GPUs
o 2 Gbytes GDDR5 memory
o 256-bit wide memory bus
o 80 Gbyte/s memory bandwidth
o 16-lane Gen2 PCIe interface
• Dual DVI graphics outputs
• Temperature sensors
• Voltage sensor
• Current sensor
• Intelligent Platform Management Interface (IPMI) support