Product References

Product Brief: RES Server NVIDIA GPU Options

Aerospace and Defense Technology Product Guides, Tech Briefs, and Technical Content

Issue link:

Contents of this Issue


Page 0 of 1

PRODUCT BRIEF Mercury Systems, Inc. Engineered to Tackle Challenging Workloads Anywhere Mercury's rugged servers harness parallel processing to maximize throughput, boost productivity and push the boundaries of compute- heavy mission-critical applications. Our servers support unique application and deployment requirements by densely packing multiple processors and expansion slots in a range of compact chassis. Benefits • Maximized throughput with contemporary NVIDIA GPUs, Intel® processors and high-speed networking. • Ability to scale supercomputing applications from the data center to the edge with rugged subsystems that adhere to open standards and integrate the latest commercial technologies. • Optimized performance for almost any mission-critical platform with multiple form-factors that withstand a broad range of field environments. • Trusted performance and safeguarded critical data through our advanced secuirty options. • Extended system longevity and product lifecycles to support the needs of aerospace, defense and other mission critical operations. Applications • Artificial intelligence (AI) • Big data analytics • Sensor fusion • Cryptography • Image processing • Signal intelligence (SIGINT) • Electronic warfare • Other high-performance computing (HPC) applications A Trusted Platform Provider • Mercury servers are designed in the U.S. and manufactured in AS9100D and ISO9001 facilities to maintain stringent quality standards. • Compliance with DFARS 252.204-7012 and NIST SP 800-171A to protect information and safeguard against potential cyberattacks. Maximize Throughput with the Latest NVIDIA GPUs Offering up to 20x higher performance over the prior generation, the NVIDIA A100 Tensor Core GPU delivers unprecendented acceleration at every scale for AI, data analytics, and HPC to tackle the world's toughest computing challenges and enable real-time insights. By harnessing A100 parallel processing capabilities, applications can drastically reduce their computing footprint. The energy-efficient NVIDIA T4 GPU supports new INT4 and INT8 precision modes, utilizes high-bandwidth GDDR6 memory, and features 320 multi-precision Tensor cores and 2,560 CUDA cores. When utilized for AI applications, it delivers up to 9.3x higher performance than CPUs on training and up to 36x on inference. The NVIDIA T4 plugs into multiple RES server form factors. Supercomputing for the Edge Engineered to handle massive workloads anywhere, Mercury's RES AI supercomputing servers integrate the latest dual-width NVIDIA T4 and A100 GPUs in environmentally resilient, rugged, expandable form- factors. A single RES AI 4U server supports eight NVIDIA A100 data center GPUs. Minimize Your Parallel Computing Footprint Figure 1: Available in various form factors that support the latest GPUs, RES servers maximize performance in a small footprint. RES Server NVIDIA® GPU Options 2U 3U 4U 1U RES HD 2U other RES servers HDslim 4U RESmini multiple NVIDIA A100 NVIDIA T4

Articles in this issue

Links on this page

view archives of Product References - Product Brief: RES Server NVIDIA GPU Options