Scalable Configurations

The CS500 cluster supercomputer can be customized for multi-

ple uses — from an all-purpose, massively parallel HPC system

to a cluster optimized for hybrid compute- and data-intensive

workloads.

Each system has compute nodes, which run parallel MPI and

OpenMP tasks with maximum efficiency, and management nodes,

which provide I/O connectivity, function as login nodes, and

can be configured for unique workloads requiring large memory

configurations.

Cray rackmount servers are highly configurable in an HPC-

optimized, industry-standard package. Each configuration can be

replicated to create a reliable and powerful large-scale system.

Comprehensive HPC & Deep Learning

Environment

Our complete software environment lets you develop and optimize

applications and efficiently monitor system resources.

The CS500 system’s customizable software stack is compatible

with most open-source and commercial applications. It includes

key Cray-authored components, popular open-source software,

and industry-leading applications from Cray partners.

The software stack includes:

•

•

The Cray Programming Environment, a complete, fully

integrated suite of HPC-optimized compilers, libraries and

tools for programming, debugging, performance analysis,

workload management, environment setup and more

•

Your choice of Bright Cluster Manager for HPC or Cray’s

Advanced Cluster Engine (ACE) for system management

•

Bright for Deep Learning, a comprehensive deep learning

environment that includes a choice of machine learning

frameworks including Caffe, Torch, Tensorflow, and Theano;

and machine learning libraries including MLPython, NVIDIA

CUDA Deep Neural Network library (cuDNN), Deep

Learning GPU Training System (DIGITS), and CaffeOnSpark

AMD EPYC™ Balanced Architecture for Optimum Performance

the AMD EPYC SoC have the flexibility, performance and security to efficiently support the most

demanding workloads.