Skip to navigation Skip to content

Issue
Ten

How it all started

According to EPCC director Professor Arthur Trew, EPCC was conceived over a period of six or seven years in the early 1980s’ by a small group of physics researchers who were interested in using “novel architectures” such as parallel computers to help in their projects – looking into esoteric subjects such as quarks and zero magnetism.  At that time, said Trew, the USA was far ahead with supercomputers such as the Cray XI, and the UK researchers “had to do something imaginative to compete&rd…

How it all started

Article by Peter Barr

According to EPCC director Professor Arthur Trew, EPCC was conceived over a period of six or seven years in the early 1980s’ by a small group of physics researchers who were interested in using “novel architectures” such as parallel computers to help in their projects – looking into esoteric subjects such as quarks and zero magnetism.  At that time, said Trew, the USA was far ahead with supercomputers such as the Cray XI, and the UK researchers “had to do something imaginative to compete” with their American rivals. 

Having got their hands on what was then the most advanced computer in the UK, ICL's Distributed Array Processor (DAP), the breakthrough arrived thanks to an “ingenious” bit of programming, and the researchers persuaded the University of Edinburgh's Department
of Computing Science to provide further funding. With backing from the Science and Engineering Research Council (SERC) and the Department of Trade and Industry (DTI), the researchers were able to buy one of the very first transputer-based computers from Meiko, which “gradually grew to be one of the largest such parallel computers in the world.”

In 1990, EPCC was founded “to accelerate the exploitation of parallel computing through industry, commerce and academia,” developing simulation software to run on parallel computers, as well as providing consultancy services and training. It was staffed primarily by physicists who wanted to advance their theoretical research and also embraced the idea that they had to work with industry partners – for example, Barclays Bank and British Gas, two of their earliest clients. Over the years, the centre graduated from its early machines to a CM-200, then in 1994 it bought a 256-processor Cray T3D – then Europe’s fastest supercomputer – soon followed by a Cray T3E, dedicated to particle physics. 

In 2002, EPCC became lead partner in the HPCx consortium, supporting the national supercomputing service for UK academic research, and in 2008 it became the host for HECToR, a similar service, funded to the tune of £115 million over six years, from 2007 to 2013.

According to Professor Richard Kenway, EPCC’s Chairman, the secret of EPCC's success was to “hire the brightest graduates and set them the hardest of problems – without telling them the problems were hard.” The birth of the organisation was also “a long gestation period involving many parents,” said Kenway, and today it has a staff of over 70 people. 

 

"How it all started". Science Scotland (Issue Ten)
Printed from http://www.sciencescotland.org/feature.php?id=90 on 23/06/17 01:03:59 PM

Science Scotland is a science & technology publication brought to you by The Royal Society of Edinburgh (www.rse.org.uk).