Highlights:
  • Rack Height: 4U
  • Processor Supported: 2x Intel Xeon Scalable Family
  • Drive Bays: 24x 2.5" Hot-Swap
  • Supports up to 10x Double-Wide cards in a Single-Root complex
Contact sales for pricing

The TensorEX TS4-672702-DPN is a 4U rack mountable Deep Learning P2P Solution supporting 2x Intel Xeon Scalable processors and a maximum of 3 TB DDR4 memory. The TensorEX TS4-672702-DPN is a compute node designed and optimized for computing accelerators such as the NVIDIA® Tesla® GPUs. The TensorEX TS4-672702-DPN supports up to 10 double wide GPU cards on a single root complex PCIe bus to offer vast gains in processing time for the most supercomputing intensive applications, from cutting-edge rendering farms to the latest simulations in leading scientific research.

Features:

  • Supports two Intel Xeon processor scalable family (Skylake-SP)
  • Supports up to 3TB DDR4 System Memory
  • Full P2P communication between 10x PCIe devices
  • Supports 10x NVIDIA Tesla GPUs
  • 24 x 2.5" hot-swappable HDD bays
  • 2000W Redundant Titanium Level Power Supplies
  • 2x 10GBASE-T Network Adapter

NVIDIA Tesla GPU Options

ModelStandard MemoryMemory Bandwidth (GB/s)CUDA CoresTensor CoresSingle Precision (TFLOPS)Double Precision (TFLOPS)Power (W)Explore
Tesla V100S 32 GB32 GB HBM21134512064016.48.2250Specs
Tesla V100 32 GB32 GB HBM29005120640147250Specs
Tesla V100 16 GB16 GB HBM29005120640147250Specs
Tesla P100 16 GB16 GB HBM27323584-9.34.7250Specs
Tesla P100 12 GB12 GB HBM25493584-9.34.7250Specs
Tesla T416 GB GDDR632025603208.10.2475Specs
Tesla P48 GB GDDR51922560-5.50.1775Specs

Deep Learning Software Stack


Ubuntu Deep Learning Software Stack

NVIDIA CUDA
cuDNN
theano
Torch
Keras
Docker
NCCL
Caffe
Bidmach
OpenCV
RAPIDS
Caffe2
Anaconda
TensorFlow
MXNet

Exxact Docker NGC Ready Deep Learning Stack

Includes configuration and testing for the following NGC Ready Docker containers:

NVIDIA CUDA
NVIDIA Digits
Caffe
PyTorch
TensorFlow
RAPIDS

Additional Docker Images:

Portainer

Optional Software

SINGA
Singularity
Microsoft Cognitive Toolkit
Deep Learning NVIDIA GPU Solutions

Processor & Chipset
Number of Processors Supported
2
Processor Socket
LGA 3647
Processor Type
Xeon
Processor Supported
  • Bronze 31XX
  • Bronze 32XX
  • Silver 41XX
  • Silver 42XX
  • Gold 51XX
  • Gold 52XX
  • Gold 61XX
  • Gold 62XX
  • Platinum 81XX
  • Platinum 82XX
Number of UPI links
3
Thermal Design Power (TDP)
205 W
Chipset Manufacturer
Intel
Chipset Model
C622
Memory
Maximum Memory
1.5 TB
Memory Technology
DDR4 SDRAM
Memory Standard
DDR4-2666/PC4-21300
Number of Total Memory Slots
24
Controllers
SATA3
  • Via C622 chipset
Display & Graphics
Graphics Controller Manufacturer
ASPEED
Graphics Controller Model
AST2500 BMC
Network & Communication
Ethernet Technology
  • 10GBASE-T
I/O Expansions
PCI Express
  • 11x PCI-E 3.0 x16 slots (Supports 10x double-wide cards)
  • 1x PCI-E 3.0 x8 (in x16 slots)
  • Single root complex
Drive Bays
Hot-swap
  • 24x 2.5" Hot-swap drive bays
Interfaces/Ports
Total Number of USB Ports
4
Number of USB 3.0 Ports
4
Number of SATA Interfaces
10
LAN
  • 2x RJ45 10GBASE-T Ethernet LAN Ports
  • 1x RJ45 IPMI dedicated LAN Port
Onboard Video
1x VGA Connector
Power Description
Number of Power Supplies
4
Redundant Power Supplies
Yes (2+2)
Maximum Power Supply Wattage
2000 W
Certification
80 Plus Titanium
Physical Characteristics
Color
Black
Form Factor
Rack-mountable
Rack Height
4U
Height
7.0"
Width
17.2"
Depth
29"