OpenVPX embedded computing modules for intelligence and surveillance uses introduced by Curtiss-Wright

These applications include high-performance radar, SIGINT, EO/IR, data fusion ingest, processing and display, and autonomous vehicles.
Jan. 6, 2020
2 min read

ASHBURN, Va. – The Curtiss-Wright Corp. Defense Solutions division in Ashburn, Va., is introducing three NVIDIA Quadro Turing (TU104/6) GPU/inference engine-based OpenVPX embedded computing modules for demanding applications in intelligence, reconnaissance, and surveillance (ISR).

Curtiss-Wright is announcing these open-architecture high-performance embedded computing (HPEC) processors through the company's reseller agreement with WOLF Advanced Technology in Whitchurch-Stouffville, Ontario.

Curtiss-Wright also announced the availability of a AMD Radeon (E9171)-based XMC graphics engine card to support compute-intensive ISR and electronic warfare (EW) systems.

The rugged VPX3-4925, VPX3-4935, and VPX6-4955 modules have Tensor Cores (288, 384, and 768 respectively) for accelerating tensor/matrix computation in deep learning neural network training and inference used in artificial intelligence (AI) applications requiring teraFLOPs of accelerated processing.

These applications include high-performance radar, SIGINT, EO/IR, data fusion ingest, processing and display, and autonomous vehicles.

Related: SOSA open-systems standard for embedded computing, sensor processing could be in final form by this summer

The size, weight, and power (SWaP)-optimized VPX3-4925 3U OpenVPX GPGPU processor has an NVIDIA Quadro Turing TU106 (RTX3000E) GPU that delivers 6.4 TFLOPS/TIPS performance.

It provides 2304 CUDA cores, 288 Tensor Cores, and 36 ray-tracing (RT) cores. For higher performance in SWaP-constrained applications, the 3U VPX3-4935 module, has a NVIDIA Quadro Turing TU104 (RTX5000E) GPU that delivers 11.2 TFLOPS/TIPS.

The VPX3-4935’s higher core count includes 3072 CUDA Cores, 384 Tensor Cores, and 48 RT Cores. For more demanding applications, the 6U form factor VPX6-4955 (6144 CUDA cores, 768 Tensor Cores, 96 RT Cores) hosts dual TU104 GPUs for 22 TFLOPS/TIPS performance.

Designed to work with NVIDIA TensorRT, CUDA, the Turing Tensor Cores of the modules add INT8 and INT4 matrix operation while continuing support for high-precision workloads.

For more information contact Curtiss-Wright Defense Solutions online at www.curtisswrightds.com.

Sign up for our eNewsletters
Get the latest news and updates

Voice Your Opinion!

To join the conversation, and become an exclusive member of Military Aerospace, create an account today!