Case Studies > National Centre for Nuclear Research

National Centre for Nuclear Research

Company Size
1,000+
Region
  • Europe
Country
  • United Kingdom
Product
  • Arista 7508E
  • Arista EOS
  • SGI Ice X
Tech Stack
  • 40GbE
  • MLAG
  • ECMP
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Customer Satisfaction
  • Digital Expertise
  • Productivity Improvements
Technology Category
  • Infrastructure as a Service (IaaS) - Cloud Storage Services
  • Networks & Connectivity - Ethernet
  • Networks & Connectivity - Network Management & Analysis Software
Applicable Industries
  • National Security & Defense
Applicable Functions
  • Business Operation
  • Facility Management
Services
  • Hardware Design & Engineering Services
  • Software Design & Engineering Services
  • System Integration
About The Customer
The Atomic Weapons Establishment (AWE) is located on a 750-acre site in Aldermaston, Berkshire, and plays a crucial role in the UK's defense. It is responsible for the design, build, maintenance, and decommissioning of the UK's Trident warheads. Managed by a consortium of Serco Group plc, Lockheed Martin Corporation, and Jacobs Engineering Group since 2000, AWE employs around 4,500 staff and 2,000 contractors. The site and facilities are owned by the government, but the day-to-day management of Britain's nuclear stockpile is contracted out. AWE has been central to the UK's nuclear defense for over 60 years.
The Challenge
Following the UK's agreement in 1996 to sign the Comprehensive Nuclear Test-Ban Treaty, AWE's work must be completed without actual test firing of weapons. This poses enormous technical and engineering challenges, necessitating high performance computing (HPC) systems for simulation, modeling, design, plasma physics, materials science, and hydrodynamics. AWE has invested significantly in its HPC capability, operating several supercomputing platforms. The demands on networking are significant, requiring cutting-edge technology to manage the high volume of calculations and data generated.
The Solution
AWE decided to separate its HPC and corporate networks, building a new dedicated HPC network managed by the HPC team. They installed nine Arista 7508E modular data center switches, along with 400 short and long-range 40GbE optics. This made AWE one of the first organizations in Europe to deploy 40GbE Arista switch technology on such a scale. The Arista EOS operating system allowed AWE to write custom scripts and applications for security and monitoring. The new network guarantees a 'lossless' Ethernet environment, crucial for AWE's IBM-based multi-petabyte storage platform. The flexibility and openness of Arista's EOS were key factors in their selection.
Operational Impact
  • The new HPC network has removed bottlenecks and improved throughput and performance fourfold.
  • Reliability has been enhanced, allowing AWE to use its key platforms, including IBM storage, to the maximum.
  • The new network has made AWE's team of scientists and engineers more efficient and productive.
  • The project has provided a clear growth path for future upgrades to 100GbE capability.
  • The separation of HPC and corporate networks has allowed each to focus on their specific priorities.
Quantitative Benefit
  • AWE's new HPC network supports 400 short and long-range 40GbE optics.
  • The new network has improved performance fourfold compared to the previous setup.
  • The HPC network can aggregate ten 40GbE connections to create a bandwidth of 400 gigabits.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.