Mercury Takes High-Performance Graphics Processing to the Edge

Transformative technology enables sensors to synthesize situational awareness information in real time and detect threats faster

ANDOVER, Mass., June 11, 2020 (GLOBE NEWSWIRE) -- Mercury Systems, Inc., a leader in trusted, secure mission-critical technologies for aerospace and defense, today unveiled the new GSC6204 OpenVPX™ 6U NVIDIA® Turing™ architecture-based GPU co-processing engine, providing accelerated high-performance computing capabilities to commercial aerospace and defense applications.

“Our customers need real-time, data center-level performance in their platforms to process the unrelenting streams of data from high-resolution, long-range sensors,” said Joe Plunkett, Vice President and General Manager of Mercury’s Sensor Processing group. “As part of our commitment to Innovation That Matters, we’re leveraging NVIDIA GPU technology to embed the latest parallel processing capabilities into ruggedized solutions and bring supercomputing closer to the edge. By making commercial technology profoundly more accessible to aerospace and defense, we can more rapidly turn sensor data into actionable information.”

“Mercury Systems is doing great work in harnessing the power of NVIDIA GPUs in their solutions,” said Anthony Robbins, Vice President of Federal at NVIDIA. “The rapid advancements made in parallel processing and HPC have had a significant impact on the ways that companies like Mercury are applying AI to solve real-world problems across all industries.”

Compute-intensive AI, radar, electro-optical/infrared imagery, cognitive EW and sensor fusion applications require high-performance computing capabilities closer to the sensor for effectiveness. To address this need, Mercury’s purpose-built GSC6204 module incorporates the NVIDIA Turing GPU architecture to bring the latest advancements in processing and scale to the embedded domain. Powered by dual NVIDIA Quadro® TU104 processors and incorporating NVIDIA’s NVLink™ high-speed direct GPU-to-GPU interconnect technology, the module delivers the same massive parallel processing capability found in data centers. Combined with Mercury’s HDS6605 Intel® Xeon® Scalable server blade, SCM6010 fast storage, SFM6126 wideband PCIe switches, streaming IOM-400 I/O modules and ruggedized to withstand environmental extremes, these GPU co-processing engines are a critical component of a truly composable high-performance embedded edge compute (HPEEC) environment unmatched by competing solutions.

Source: Mercury Systems
Date: Jun 12, 2020