RES AI XR6 3U, 8 Drive 21 Inch Rugged GPU Server
Dual Intel® Xeon® Scalable processors, 4 double-wide NVIDIA GPUs, 4TB memory and 8 disk drives
Compact 21 Inch Deep, Rear I/O Supercomputing Server
Built from the ground up to provide edge computing capability previously reserved for the data center, Mercury’s RES AI 3U supercomputing server packs dual Intel® Xeon® Scalable processors, four double-wide NVIDIA Tesla GPUs, 4TB DDR4 ECC memory and 8 drives of storage in a 45lb server form factor.
This product is not recommended for new designs. Visit our RES X07 or RES X08 servers for new-design applications.
Specifications
- Dual Intel® Xeon® Scalable CPUs with up to 28 cores per processor
- Up to 4 double-wide NVIDIA Tesla or Quadro GPU accelerators
- Up to 4TB memory with 16 DIMM slots, 2933MHz RDIMM/LRDIMM
Management and Operating System
- Windows®, Linux®, VMware® and other hypervisors
- IPMI v2.0, Redfish option available
- TPM 2.0 support
- Optional RAID Controller for SAS3/SATA3
Expansion and Modular Maintainability
- 2 Disk on Module (up to 128GB per DOM)
- 7 PCIe 3.0 cards
- 4 PCIe x16 GPU (double-width, FHFL) slots
- 3 PCIe single-width, FHHL slots: 2 PCIe x16 + 1 PCIe x4 (in x8 slot)
Power Supply Options
- Single or Redundant 100/240V VAC (47/63Hz, 400Hz)
- Single or Redundant 10-36 VDC, 32 Amps
- Single or Redundant 36-72 VDC, 18 Amps
- MIL-STD 461
Input/Output Versatility
Front Access
- 8 removable, hot pluggable drives, 2.5” SATA/SAS3, U.2 NVME option available
- 1 power switch
Rear Access
- 2 10GBaseT Ethernet Ports (RJ45)
- 2 USB 3.0
- 2 USB 2.0
- 1 IPMI 2.0
- 1 VGA graphic port
- 1 COM port
Additional Options
- Shock pins
- Front door filter
- Slide rails
Maximize Throughput with Parallel Computing
Powered by four of the the latest NVIDIA® Volta architecture GPUs, RES AI 3U harnesses parallel processing to maximize throughput, boost productivity and push the boundaries of compute-heavy mission-critical applications such as signal intelligence (SIGINT), cryptography, deep learning, artificial intelligence (AI), surveillance, sensor fusion, visualization, image processing, tracking and big data analytics. Other GPU options are available.
Scale Supercomputing Applications from the Cloud to the Edge
Compatible with multiple operating systems, applications and software, RES AI adheres to open standards and integrates the latest commercial technologies to support supercomputing from the cloud to the edge.
Application Highlight:
Broadcasting the Superbowl
Traveling to and from sporting events in a vehicle, our supercomputing servers support real-time media broadcasting at the NFL Superbowl. Employing advanced data center NVIDIA GPUs to accelerate performance, they prevent lag time by processing imagery and video feeds right on the field, so you see every touchdown as it happens.
Thank you! We have received your message and will be in touch with you shortly.