BrainMax DL E140 GPU Accelerated Server

BrainMax™ DL-E140

1U DP Xeon 4x Tesla PCIe GPU Server

 

  • Supports Four Double-Width Tesla V100/V100S PCIe GPU Cards in a 1U Chassis
  • Delivers up to 2,560 Tensor cores, 20,480 CUDA Cores, 8 Teraflops DP, 65.6 Teraflops SP, and 520 Teraflops Tensor performance
  • Delivers ~25% increase in memory bandwidth and higher FLOPS
  • Two 2nd Generation Intel® Xeon® Scalable Family Processors
  • 2x 2.5″ Hot-swap and 2x 2.5″ Internal Drive Bays

Request a Quote

  • Supports two Intel Xeon® Scalable Family processors.
  • Supports four Tesla V100/V100S PCIe GPU cards in a 1U chassis.
  • Delivers ~25% increase in memory bandwidth and higher FLOPS.
  • Powered by the latest Nvidia Tesla V100S GPU accelerator, the world’s fastest, most advanced, and most efficient data center GPUs ever built, delivering performance of up to 100 CPUs in a single Tesla V100 GPU, enabling data scientists, researchers, and engineers to tackle challenges that were once thought impossible.

Processor

  • Supports two 2nd Generation Intel® Xeon® Processor Scalable Family series, LGA 3647 Socket P0, TDP up to 165W

Motherboard Chipset

  • Intel® C621 series chipset

Memory

  • 12 DDR4 DIMM slots up to 2933/2666/2400/2133 MHz
  • Up to 3TB 3DS ECC DDR4-2933MHz RDIMM/LRDIMM
  • Supports Intel® Optane™ DCPMM

Graphics Processing Unit (GPU)

  • Supports four Tesla V100/V100S PCIe GPU cards in a 1U chassis
  • Delivers up to 2,560 Tensor cores, 20,480 CUDA Cores, 32.8 Teraflops double precision, 65.6 Teraflops single precision, and 520 Teraflops Tensor performance
  • Up to 128GB dedicated GDDR5 GPU memory (organized as 32GB per V100/V100S PCIe GPU)

Graphics & LAN

  • Onboard graphics controller
  • Intel® X540 Dual Port 10GBase-T
  • Virtual Machine Device Queues reduce I/O overhead
  • Supports 10GBASE-T, 100BASE-TX, and 1000BASE-T, RJ45 output

Expansion Slots

  • 4x PCI-E 3.0 x16 slots for 4x GPU cards
  • 2x PCI-E 3.0 x8 (in x16) low-profile slots

Server Management

  • Support for Intelligent Platform Management Interface v.2.0
  • IPMI 2.0 with virtual media over LAN and KVM-over-LAN support

Drive Bays

  • 2 x Hot-swap 2.5″ SAS/SATA drive bays
  • 2 x internal 2.5″ drive bays
  • Supports 1x M.2 2242/2260/2280 slot, with M.2 SATA and NVMe support

Chassis

  • 1U rack-optimized chassis
  • 2x 2.5″ hot-swap drive bays and 2x 2.5″ internal drive bays, optional NVME SSD support
  • Power supply: 2000W Redundant Power Supplies with PMBus

System Dimensions

  • 1.7″ x 17.2″ x 35.2” / 43mm x 437mm x 894mm (H x W x D)

Warranty

  • Optional on-site warranty

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.