HPC for industry

Work on the Edinburgh International Data Facility has passed three key milestones, bringing the infrastructure that will underpin the £600m Data-Driven Innovation Programme significantly closer to reality.

Firstly, and perhaps most importantly, EIDF’s home, Computer Room 4 (cr4) at the University’s Advanced Computing Facility, completed its main construction phase at the end of the third quarter of 2020 and cr4 has entered its commissioning and fit-out phase.  If everything goes to plan, we will start to build infrastructure in the room from January 2021.

EPCC continues to support industry in these challenging times, leveraging our three key foundations:

• The hosting, provision and management of high-performance computing (HPC) and data facilities for academia and business.
• Research and project support to optimise the computing activities of those organisations.
• Our unique project-based Applications Group, which provides bespoke novel and high-performance software solutions to academia, industry and commerce.

During the past year EPCC has increased its engagement with the Machine Intelligence Garage, a UK Government programme that supports innovative startups which make use of machine-learning techniques and artificial intelligence (AI).

Part of the Machine Intelligence Garage's remit is to enable technical support, such as HPC services, which is provided by various partners. For example, its industrial partners include AWS, Google Cloud, and NVIDIA. EPCC is a founding partner and we also offer support and potential collaboration for interested startups.

Cirrus is a Tier-2 state-of-the-art advanced computing facility available to industry and academia. Hosted and managed by EPCC, it provides an ideal platform for solving computational, simulation, modelling, and data science challenges. 

The system was recently upgraded via a £3.5m funding award from the UK's Engineering and Physical Sciences Research Council. This included the addition of 144 NVIDIA V100 GPUs and a 256TB high-performance storage layer for the most demanding data-streaming applications. 

In June, a unique collaboration between the University of Edinburgh, the Financial Data and Technology Association, and Fintech Scotland was awarded £22.5m from UK Government to harness financial data for societal and economic benefit. The Global Open Finance Centre of Excellence (GOFCoE) will be an independent collaboration between governments and regulators, the financial services, industry and academia. 

EPCC is a partner in the EXCELLERAT programme, which brings together key players from industry, research and HPC to provide services that will enable the European engineering industry to advance towards Exascale technologies.

There are great opportunities for engineering applications in exploiting Exascale computing. EXCELLERAT brings together expertise in HPC and engineering software to support the development of applications that can exploit computing capability at this level. 

EPCC has collaborated with Intel® and Illuminate Technologies to investigate innovative performance-enhancing, packet-processing approaches within the type of Cloud environment expected to be seen in 5G deployments. 

We support businesses across a wide range of industries and sectors. 

We recently completed a successful collaboration with Oil and Gas integrity management specialists, PIM Ltd, to investigate the benefits and opportunities for using novel automation and data analytics technologies to improve the effectiveness and productivity of asset integrity management services. Over the last eight years PIM has delivered risk-based inspection services to the Oil and Gas sector and has built up a considerable amount of data which can be leveraged to optimise future inspection services.

EPCC is a partner in the EXCELLERAT programme, which brings together key players from industry, research and HPC to provide services that will enable the European engineering industry to advance towards Exascale technologies. A Service Platform (including training, access to codes and software, and expert consultation) will be offered within EXCELLERAT where participants will be provided with the most suitable type of support, based on their own current needs.

The Met Office relies on some of the world’s most computationally intensive codes and works to very tight time constraints. It is important to explore and understand any technology that can potentially accelerate its codes, ultimately modelling the atmosphere and forecasting the weather more rapidly.

Field Programmable Gate Arrays (FPGAs) provide a large number of configurable logic blocks sitting within a sea of configurable interconnect. It has recently become easier for developers to convert their algorithms to configure these fundamental components and so execute their HPC codes in hardware rather than software. This has significant potential benefits for both performance and energy usage, but as FPGAs are so different from CPUs or GPUs, a key challenge is how we design our algorithms to leverage them.