AMAX BrainMax DL-E48A Re-Configurable PCIe Dual Root Complex Deep Learning Server

BrainMax® DL-E48A

4U 8x GPU Server

 

  • Deep Learning Training and Inference

Request a Quote

The BrainMax™ DL-E48A is Powered by 8x NVIDIA Tesla V100S PCIe GPU accelerators and 2x Intel® Xeon® Scalable Family Processors. Featuring the first-in-industry accelerated GPU computing solution to support a re-configurable single and dual root complex PCIe architecture. Configure hardware optimization on the fly for AI and DL training, inference, HPC compute, rendering and virtualization applications.

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 V100S PCIe

System Memory (Maximum)

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

Expansion Slots

  • 8 x PCI-E x16 (Gen3 x16 link), Full-length/Full-height

Half-length/Low-profile:

  • Rear: Dual root topology: 2 x PCI-E x16 (Gen3 x 16 link), LP, HL, or
    Single root topology: 1 X PCI-E x16 (Gen3 x16 link), LP, HL
  • Front: 1 x PCI-E x8 (Gen3 x8 link) , LP, HL

Connectivity

  • 1 x Dual Port Intel I350-AM2 Gigabit LAN controller
  • 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

  • 2+1 Redundant 1600W 80PLUS Platinum Power Supply

System Dimensions

  • 6.9”x 17.2” x 31.4” / 175.6mm x 439mm x 798mm (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.