How to Buy 60 Day Free Trial

SUSE Linux Enterprise High Performance Computing

A highly scalable, high performance open source operating system designed to utilize the power of parallel computing for modeling, simulation and advanced analytics applications

SUSE Linux Enterprise High Performance Computing (HPC) provides a parallel computing platform for high performance data analytics workloads such as artificial intelligence and machine learning. Fueled by the need for more compute power and scale, businesses around the world today are recognizing that a high performance computing infrastructure is vital to supporting the analytics applications of tomorrow. This product is built for easy adoption across lower-cost Arm-based hardware all the way up to the largest supercomputers in the world – with a focus on flexibility and providing SUSE-supported capabilities (i.e., Slurm for workload management) for today’s HPC environments.

Find out what's new in the latest release notes for SLES 15 GA.

Key Features

Easier management and monitoring of your parallel computing environment with an updated and supported set of popular HPC tools and utilities, including tools for workload and cluster management

Expands your x86-64 and Arm-based HPC cluster environment to the full range of hardware being used today for HPC – from low-cost to high-end supercomputers

Increases resource efficiency and extreme scaling by enabling offload of HPC processing to public and hybrid cloud, with updated SLE HPC images for both Microsoft Azure and AWS

Accelerates innovation with a broad ecosystem of hardware and software partners, delivering cohesive HPC stacks for the latest supercomputers

High scalability, efficiency and performance by utilizing Linux clustering and the power of parallel computing running on a wide range of hardware

SUSE-supported HPC module for x86-64 and ARM64, providing simple and reliable access to high-demand HPC capabilities such as Slurm for workload management

Reference Architecture:

SUSE Linux Enterprise High Performance Computing includes support for the following HPC services and capabilities:

Workload management (Slurm)
Remote and parallel shells
Performance monitoring and measuring tools
Serial console monitoring tool
Cluster power management tool
Tool to discover the machine hardware topology
Tool to monitor memory errors
Scalable profiling library for MPI applications (Message Passing Interface in parallel computing)
Tool to determine CPU model on capabilities (x86-64 only)
User extensible heap manager capable of distinguishing between different kinds of memory (x86-64 only)

Environment modules that simplify customizing the users’ shell environment
File format libraries for storing and organizing large amounts of numerical and scientific data
Authentication service and credential validation in HPC clusters
High performance Message Passing Library
High performance MPI over Infiniband
Scientific and mathematical computing libraries for parallel computing
Console access and management

Tech Specs

HPC Module

SUSE makes adopting HPC easier to implement by adding packages to the HPC module. This module is intended to simplify deployment and management of HPC environments by providing a number of fully supported HPC packages to SUSE Linux Enterprise HPC customers.

These packages were built and tested by SUSE and are provided at no additional cost with the SUSE Linux Enterprise High Performance Computing support subscription. All of the packages are open source and many are based on packages from OpenHPC. The HPC module is provided for customers using X86-64 and Arm AArch64 platforms and is available to customers with SLE HPC subscriptions.

The module structure allows SUSE to deliver additions and enhancements to HPC packages more frequently than is possible via Service Packs. Here is the list of packages and release numbers available in the HPC module currently:

conman 0.2.9
clustduct 0.0.2-1.4
cpuid 20170122 (x86 only)
fftw 3.3.6
ganglia 3.7.2
ganglia-web 3.7.2
genders 1.2.2
GCC 7.3.1
gsl 2.4
hdf5 1.10.1
hwloc 1.11.8
hypre 2.15.1
imb 2019.1

lua-lmod 7.6.1
memkind 1.6.0 (x86 only)
metis 5.1.0
mpip 3.4.1
mrsh 2.12
mumps 5.1.2
munge 0.5.13
mvapich2 2.2.13
netcdf 4.6.1
netcdf-cxx 4.3.0
netcdf-fortran 4.4.4
numpy 1.14.0
ocr 1.0.1
openblas 0.2.20
openmpi 2.1.6
papi 5.6.0
pdsh 2.33
petsc 3.8.3
phdf5 1.10.1
powerman in base OS
prun 1.0
rasdaemon in base OS
ScaLAPACK 2.0.2
scipy 1.2.0
scotch 6.0.6
slurm 18.08.05
superlu 5.2.1
trilinos 12.10.1

Minimum Hardware Requirements

SUSE Linux Enterprise High Performance Computing is fully supported on any x-86-64-based or Arm64-based SUSE YES Certified server platform that is certified for the SUSE Linux Enterprise Server versions listed in the Minimum System Requirements section of our documentation:

SUSE Linux Enterprise Server 15 Quick Start

SUSE Linux Enterprise Server 12 Quick Start

SUSE Linux Enterprise Server for Arm 12 SP3 Installation Guide

Architectures Supported

x86-64

Arm64 (Aarch64)

Take an In-depth Look at the Product

Success Stories

Leibniz Supercomputing Centre Success Story

Boosted overall performance by a factor of 50, making SuperMUC the fastest supercomputer in Europe and the fourth fastest worldwide when it went into production
Simplified system configuration with leading automation tools such as AutoYaST
Improved energy efficiency with advanced power saving features, providing 20 times more performance per watt than the previous environment
Enables smooth migration from Itanium 2 to x86 processor architecture

Zentralanstalt für Meteorologie und Geodynamik (ZAMG)

Delivers maximum performance for the available budget on 7,000 cores
Enables flexible collaboration and easy exchange of applications between different research groups
Facilitates system administration across HPC and non-HPC systems

Tokyo Institute of Technology Success Story

Supports peak performance of 5.7 petaflops (PFlops), the best of any cluster-type supercomputer in Japan
Provides interconnectivity with consumer IT equipment as well as support for high-end environments
Helped Tsubame become one of the world’s top-ranked large-scale cluster-type supercomputers
Offers excellent management capabilities

Total Success Story

Raised computational performance, enabling faster simulations
Enabled 10-times increase in computing capacity
Optimized price-performance, keeping TCO as low as possible

Irish Centre for High-End Computing Success Story

Boosted stability, performance and computational power
Enabled users to perform more complex and demanding research and development activities
Contributed to optimal price-performance through small OS footprint

Gregor Mendel Institute of Molecular Plant Biology Success Story

Supports cutting-edge scientific research in plant biology, helping to foster innovation
Gives scientists quicker and easier access to the latest computational tools and high-performance computing resources
Enables deployment of virtual machines in a private cloud in just 10 minutes
Reduces time spent on provisioning and managing IT services