Latest field-deployable parallel computing subsystems optimize big data workloads for mission-critical platforms
Mercury Systems, Inc. unveiled the EnterpriseSeries™ RES AI rugged rackmount server line, bringing High Performance Computing (HPC) capabilities to aerospace, defense and other mission-critical applications at the edge.
“The proliferation of sensors, ever-growing data loads and the evolution of complex deep learning neural networks continues to increase computational demands, driving the need for supercomputing infrastructure closer to the edge.” said Scott Orton, Vice President and General Manager of Mercury’s Trusted Mission Solutions group. “Through close collaboration with technology leaders such as NVIDIA and Intel, we’ve developed reliable parallel computing systems that accelerate demanding artificial intelligence (AI), signal intelligence (SIGINT), and sensor fusion applications where it’s needed the most.”
Why it Matters: Evolving compute-intensive AI, virtualization, big data analytics, SIGINT, autonomous vehicle, Electronic Warfare (EW) and sensor fusion applications require data center supercomputing capabilities closer to the source of data origin. Delivering HPC capabilities to the edge presents challenges as every application has its own security, performance, footprint, budget and reliability requirements. To address this need, Mercury partners with technology leaders to align technology roadmaps and deliver cutting-edge computing in scalable, field-deployable form-factors that are fully configurable to each unique workload.
What it delivers: Mercury’s rugged HPC servers leverage the latest data center processing and co-processing technologies to accelerate the most demanding workloads. Customer benefits include:
- The ability to scale supercomputing applications from the cloud to the edge with rugged subsystems that adhere to open standards and integrate the latest commercial technologies.
- Maximized throughput through contemporary NVIDIA® graphics processing units (GPUs), Intel® server-class processors, field-programmable gate array (FPGA) accelerators, and high-speed networking.
- Optimized performance for almost any mission-critical platform with multiple form-factors that withstand a broad range of field environments
- Advanced security options that deliver trusted performance and safeguard critical data
- Extended system longevity and product lifecycles to support the needs of aerospace, defense and other mission critical operations.
Engineered to handle massive workloads anywhere, Mercury’s supercomputing servers integrate the latest NVIDIA® GPUs and Intel® Xeon® Scalable processors in environmentally resilient, rugged, expandable form-factors. To optimize performance in a small footprint, RES AI servers densely pack multiple processors and expansion slots in a range of compact chassis to support the unique application and deployment requirements of customers.
Powered by NVIDIA Volta, Pascal™ and Turing™ architecture GPUs, Mercury’s subsystems harness parallel processing to maximize throughput, boost productivity and push the boundaries of compute-intensive applications. A single RES AI 4U server supports up to eight NVIDIA V100 Tensor Core GPUs.
Optimized performance in extreme conditions:
Built from the ground up to provide edge computing capability previously reserved for the datacenter, field-deployable RES AI servers incorporate innovative patented technologies and design features to withstand shock, vibration, dust, sand, and temperature extremes. To ensure uptime, availability, and sustained optimal performance in almost any environment, RES AI servers are certified to multiple military (MIL-STD) and commercial (IEC) environmental specifications.
Trusted and Secure:
For security-imperative applications, Mercury’s servers can be customized with U.S. designed and manufactured motherboards and unique hardware and software protection layers that safeguard critical IP. When configured with Mercury’s self-encrypting, defense-grade solid state drives (SSD), RES AI delivers data-at-rest protection. A multi-platform compatible, secure hypervisor option that guards against cyberattacks, is also available.