BigDog Architecture

Main Content

BIGDOG ARCHITECTURE

What is a High Performance Computing Cluster?

A High Performance Computing Cluster (HPCC) most generally refers to the practice of aggregating computing power in a way that delivers much higher performance than one may get out of a typical desktop computer or workstation to solve large problems in science, engineering, or business.

A helpful way to help understand what high performance computers are is to think about what's in them. You have all of the elements you'd find on your desktop (processors, memory, disk, operating system) just more of them. High performance computers of interest to small and medium-sized businesses today are really clusters of computers. Each individual computer in a commonly configured small cluster has one to four processors, and today's processors typically have from two to four cores. HPC people often refer to the individual computer in a cluster as nodes.

The point of having a high performance computer is so that the individual nodes can work together to solve a problem larger than any one computer may easily solve. And, just like people, the nodes need to be able to talk to one another to work together. Of course computers talk to each other over networks, and there are variety of interconnect options available. (Reference: InsideHPC)

BigDog is an HPCC system acquired in 2015. The BigDog HPCC is based on a Cisco Unified Computing System (UCS) solution and includes 40 C-Series nodes and a Nexus 9000 series switch.

BigDog Configuration

The BigDog Hardware Configuration is as follows:

Hardware Node Intel XEON E-5 
Processor
Per Node
Core
Per Node
RAM
Per Node
TDD
Per Node
NVIDIA
K40 GPU
CUDA Core
Per Node
GDDR5 Memory
Per Node
Ports and Connections

Nexus 9300

1

48 port 10G & 6 port 40G
SFP+ Twinax Copper Coonection

UCS C-220

36

2

20

64GB

1TB

UCS C-220

2

2

20

768GB

4TB

UCS C-240

2

2

20

64GB

1TB

2

2880

12GB

TOTAL

40

80

800

4TB

46TB

2

5760

24GB

48 port 10G & 6 port 40