Telephone: 0114 2572 200

Supermicro Supercomputer and Compute-on-Demand

Hosted cluster saves Engys in excess of £30k per annum on operational costs

Engys, a developer of computer-aided engineering software and services, is using a new high performance server cluster and Compute-on-Demand facility from OCF. Engys’ staff, based in five Worldwide locations, can now access significant processing power via a new server cluster to support their Computational Fluid Dynamic [CFD], Multi-Disciplinary Optimisation [MDO] and Adjoint CFD custom software development, design optimisation and project consultancy work. Engys also uses OCF’s Compute-on-Demand facility, enCORE, both for extra processing power when required and to host engineering software, which it provides as a service to its own customers.

Engys’ customers range from large OEMs to SMEs across the world. Example work includes consultancy projects, custom software development and delivery of technical support across multiple industries, including: automotive, aerospace, marine architecture, built environments, oil & gas, consumer products, and others.

Uniquely, Engys’ new server cluster is hosted and managed by OCF and is not based on the Engys site. Engys’ staff access the cluster remotely over the internet. Francisco Campos, Director of Operations at Engys says: “Having our own cluster, but hosted and managed by OCF, gives us freedom. We do not have to waste our own time and effort maintaining the cluster; we don’t need cluster skills. We also don’t need to provide energy to run and cool the cluster or space to house it. We don’t have to worry about its administration or security. There are significant economic advantages to having OCF run this for us. It will save us in the region of £30k per annum on staff and operational costs.”

All Engys’ staff – based in the UK, Germany, Italy, Australia and US – have workstations and a dedicated fibre optic internet line in order to access the cluster. Irrespective of location, staff can access the cluster day or night. Engys can also create ‘guest accounts’ enabling customers to log-in and test their own software on the cluster.

Server cluster technology
The server cluster purchased by Engys and hosted by OCF is built using Super Micro server technology and uses Intel’s latest Sandy Bridge CPU processors. It delivers 144 cores of processing power and 14Tbs of storage.

Compute on Demand
Engys also uses OCF’s recently upgraded enCORE Compute-on-Demand service. enCORE, which uses compute power from a cluster at the Science and Technology Facilities Council’s (STFC) Hartree Centre and can deliver up to 8,000 cores of vital processing power to businesses. Engys uses this service in a ‘burst’ fashion – either because its own cluster is busy or if it needs to handle very large jobs. Use of this service replaces Engys’ previous use of two similar European services. It boosts Engys’ available processing power by 8000 cores, meaning that Engys can accept both more projects and much larger cases.

Francisco adds: “We wanted to access a service based in the UK, closer to our international headquarters. Using enCORE enables us to deliver very large HPC simulation projects at a fraction of the cost and time it would take to realise these capabilities in-house. As a result, we can take on board new business with reduced scheduling concerns as enCORE provides the ideal platform for dealing with peak load demands.”

Software as a service
Lastly, Engys is using the enCORE facility to host its engineering software for customers that lack suitable compute facilities of their own. The enCORE facility is also enabling Engys to offer its software to customers in a service delivery model, for example Engys’ own adjoint CFD optimisation solver.

Read More »

OCF expands HPC-on-Demand service enCORE

We have expanded our HPC On-Demand service, enCORE. It can now deliver up to 8,000 cores of vital processing power to a wide range of business sectors in the UK and beyond.

The expansion of the service follows a newly signed agreement between OCF and the Science and Technology Facilities Council’s (STFC) Hartree Centre. The Centre is a research collaboratory in association with IBM launched in 2012, which was formed as a result of a £37.5 million investment by the UK government.

The enCORE service will use additional processing power from The Hartree Centre’s “Blue Wonder”, a new IBM System x iDataPlex cluster comprising 8,000 Intel Xeon E5-2670 processor cores. Tests show that the Blue Wonder iDataPlex cluster can achieve 206.3 teraFLOPS. Its 48 TB shared memory capacity also makes it the largest shared memory cluster in the UK. BlueWonder was installed and configured by OCF in partnership with IBM.

First launched in November 2010, the enCORE service was the first in the UK to operate with a commercial organisation harnessing available processing power from academic and research-based high performance server clusters. The service has since been used successfully by firms such as Engys, Actiflow, CVIS, BHR and Renuda to meet on-going and temporary “burst” requirements for additional processing power.

“enCORE has enabled our clients to re-evaluate their HPC computing strategy. Ease of use, exceptional technical support, scalability and price / performance have been key factors in them deciding to use an off-premise HPC cluster. We’ve seen this service directly lead to firms winning contracts they could not otherwise have delivered,” says Jerry Dixon, HPC on Demand business development manager, OCF plc. “Our expansion of the enCORE service will now enable larger businesses with significant and complex HPC workloads to utilise this flexible facility, and to deliver tangible business benefits.”

Dr David Kelsall, senior consultant at fluid engineering consultancy, BHR Group comments: “OCF’s enCORE service has enabled us to cope with peaks in demand for capacity when we are undertaking simultaneous consultancy and research projects. It is a very easy service to use, with an uncomplicated and simple structure that doesn’t require any previous HPC knowledge to operate.”

He adds: “The enCORE service allows us to tackle much larger calculations, up to four times greater than we can manage in-house.”

The enCORE service

• As part of the HPC on Demand service, OCF is responsible for pre-sales qualification with customers to discover required volumes of processing power and benchmarks to demonstrate that enCORE can run specific HPC applications efficiently

• The service is scalable and suitable for SMEs through to major corporate and academic / research users

• By working with OCF, customers receive an SLA-driven service, commercial terms and commercial account management, strong technical resource, and first class technical support and assistance for maximum efficiency

• OCF also holds a number of pre-installed and optimised application codes ready for use with the service; it can work with Independent Software Vendors to get application licensing for the term of a contract with customers, or it can potentially access the end users licences directly, thus ensuring adherence to the ISV’s licensing terms

• enCORE uses the latest Intel and NVIDIA GPU processor hardware for maximum performance

• Data transfer between the customer and enCORE is handled by enCORE’s simple secure web interface or, in the case of extremely large files, by secure shuttle service

• Contracts with OCF are flexible, and use of enCORE involves a small annual subscription plus a cost per core hour used; interested parties should contact OCF for pricing.

Read More »

Warwick’s £1.3m Cluster Supports Hundreds of Research Projects

A new server and storage cluster based at University of Warwick’s Centre for Scientific Computing (CSC) will support the simulation requirements of literally hundreds of new and existing research projects. It will enable researchers to create finer scale and more realistic simulation models, create more test scenarios and get better, more accurate predictions into areas such as Magneto Hydro Dynamics, Computational Fluid Dynamics and the simulation of air turbulence. The processing power of the new server and storage cluster will reach peak performance of 35.75 TeraFlops and is 3.5 times more powerful than the University’s existing 3-year old cluster. It will include 120TB’s of shared storage which will enable researchers to store data more easily and securely.

Live and operational since 1st July 2011, the server and storage cluster already supports researchers from the Chemistry, Physics, Engineering, Mathematics, Statistics, Computer Science and Systems Biology Departments. Research using the server cluster includes:

• Magneto Hydro Dynamics (MHD) research, the study of how magnetic fluids behave, which can itself support studies into nuclear fusion and astronomical events, such as sunspot movement;
• The simulation of molecules and material properties of living systems, to understand how bone, teeth, egg shells and other bio minerals grow. This will enable researchers to mimic their unique properties and learn to create more functional materials for human use;
• Computational Fluid Dynamic modelling including airflow in the lungs to better understand inhaled medicines, particulate environmental hazards and their effects on breathing; and simulation of noise turbulence to support the design of more aerodynamic vehicles and quieter jet engines.

The University is planning to expand access to the cluster to additional departments including: Manufacturing, Life Sciences and the Business School. Researchers can access the machine on a fair usage policy using software freely available on their own workstations and desktop PCs.

The server and storage cluster’s design, integration and configuration was supplied by data processing, data management and data storage provider, OCF plc. It is part funded by the Engineering and Physical Sciences Research Council (EPSRC) and from research grants and activity in Warwick.
The server and storage cluster is built using IBM hardware including the IBM System x iDataPlex server. The server and storage cluster uses 274 IBM System x iDataPlex dx360 M3 servers each with two Intel Xeon X5650 2.66 GHz 6 Core Processors (a total core count of 3288). There are an additional six IBM iDataPlex servers with 12 Nvidia GPU processors, which will enable the University to test the benefits of using some applications on the processor. The storage solution consists of two IBM System Storage DS3512 Arrays presented to the cluster over Infiniband by two IBM System x3650 M3 Servers using IBM’s General Parallel File System.

“We started high performance computing around 10 years ago to support and progress our research,” says Mark Rodger, Director of the Centre for Scientific Computing (CSC), University of Warwick. “Our new server cluster will allow us to continue support for our researchers and ensure the University remains at the forefront of research with some of the latest technology available, including IBM iDataPlex servers, GPU processors and 120TB of central, shared storage.”

The University of Warwick is also working with OCF on plans to re-sell any excess capacity on the server and storage cluster to UK small and medium businesses using OCF’s enCORE Infrastructure on Demand service. This will enable the University to earn revenue towards the development of a new server and storage cluster.


Read More »

Recent Comments

    Contact Us

    OCF plc
    Unit 5 Rotunda, Business Centre,
    Thorncliffe Park, Chapeltown,
    Sheffield, S35 2PG

    Tel: +44 (0)114 257 2200
    Fax: +44 (0)114 257 0022

    OCF Hotline: 0845 702 3829

    The Innovation Centre, Sci-Tech Daresbury,
    Keckwick Lane, Daresbury,
    Cheshire, WA4 4FS

    Tel: +44 (0)1925 607 360
    Fax: +44 (0)114 257 0022

    OCF plc is a company registered in England and Wales. Registered number 4132533. Registered office address: OCF plc, 5 Rotunda Business Centre, Thorncliffe Park, Chapeltown, Sheffield, S35 2PG

    Website Designed & Built by Grey Matter | web design sheffield