AMAX DGS1 8x Tesla NVLink Optimized Deep Learning Server

BrainMax® DGS-1

4U 8x Tesla SXM2 GPU Server

 

  • Deep Learning Training and Inference

Request a Quote

  • Hyperscale Datacenters, Supercomputing Centers, Consumer Internet Companies, Higher Ed Research, Government, Healthcare, Financial Services, Retail, Manufacturing

Processor

  • Dual Socket P (LGA 3647)
  • 2nd Gen. Intel® Xeon® Scalable Processors (Cascade Lake/Skylake), 3 UPI up to 10.4GT/s
  • Supports CPU TDP up to 205W

Chipset

  • Intel® C621 chipset

GPU Support & Quantity

  • 8 x Tesla V100 SXM2

System Memory (Maximum)

  • 24 DDR4 DIMM slots up to 2933/2666/2400/2133 MHz
  • Supports up to 6TB ECC RDIMM

Expansion Slots

  • 8 x SXM2 sockets (Gen3 x8 bus) for NVIDIA Tesla® V100 SXM2 modules
  • Rear Side: 4 x PCIe x16 (Gen3 x16 bus) Half-length low-profile slots, 1 x OCP mezzanine slot
  • Front Side: 1 x PCIe x16 (Gen3 x8 bus) Half-length low-profile slot

Connectivity

  • 2 x 1Gb/s BASE-T LAN ports (Intel® I350-AM2)
  • 1 x RJ45 Dedicated IPMI LAN port

VGA

  • Aspeed AST2500 BMC

Management

  • On board BMC (Baseboard Management Controllers)
  • Supports IPMI2.0, media/KVM over LAN with dedicated LAN for system management

Drive Bays

  • 8 x Hot-swap 2.5″ HDD Bays

Power Supply

  • 4 x 2200W redundant PSUs
  • 80 PLUS Platinum

System Dimensions

  • 7” x 17.6” x 34.6” / 176mm x 448mm x 880mm (H x W x D)

Optimized for Turnkey Solutions

Enable powerful design, training, and visualization with built-in software tools including TensorFlow, Caffe, Torch, Theano, BIDMach cuDNN, NVIDIA CUDA Toolkit and NVIDIA DIGITS.