ASHBURN, Va.— The Defense Solutions division of Curtiss-Wright Corp. in Ashburn, Virginia, introduces the VPX3-4936 3U OpenVPX GPGPU processor module for deep learning, neural networks, Artificial Intelligence (AI)and machine learning.
The processor features the combination of the NVIDIA Ampere Graphics Processing Unit (GPU) and a configurable Gen4 PCI Express switch. The NVIDIA Ampere architecture increases performance and efficiency over the previous NVIDIA Turing generation, including more flexible concurrent execution of floating point and integer streams.
Application examples for the Embedded Computing Processor includes Intelligence, Surveillance and Reconnaissance (ISR); Electronic warfare (EW), high power radar; Signaling intelligence (SIGINT), sensor fusion and unmanned vehicles.
The Ampere device’s third-generation Tensor cores deliver four times the acceleration of AI and machine learning algorithms, and its -RT cores and CUDA core architecture offer twice the performance compared to the previous generation.
In addition to peaking at nearly 18 TFLOPS FP32 and 68 dense/136 sparse Tensor TOPS, NVIDIA Ampere also improves power efficiency, delivering 154 GFLOPS per watt. The module’s PCI Express Gen4 architecture also doubles host interface bandwidth, eliminating data throughput bottlenecks.
Pin-compatible with Curtiss-Wright’s VPX3-4935 Turing architecture, the VPX3-4936 enables system designers to improve computationally intensive processing algorithms without increasing size, weight, and power (SWaP). The board’s PCI-Express architecture also supports Non-Transparent Bridging (NTB) and daisy-chain options for system flexibility.
The rugged VPX-4936 module is designed in compliance with the US Army’s C5ISR/EW Modular Open Suite of Standards (CMOSS) and is based on the Sensor Open Systems Architecture (SOSA) technical standard to support computationally intensive ISR and EW systems.
For more information, contact Curtiss-Wright Defense Solutions online at www.curtisswrightds.com.