• Subscribe

Wee ARCHIE: The bite-sized supercomputer

Speed read
  • University of Edinburgh micro-supercomputer is a big hit.
  • Schoolchildren get hands-on experience with parallel processing.
  • Scaled-down components make supercomputing concepts accessible.

A mini supercomputer is powering virtual dinosaur races and showing how the world’s most powerful computers work.

The compact machine — called Wee ARCHIE — takes its name from the £43M ($62M) ARCHER supercomputer at the University of Edinburgh's Advanced Computing Facility. ARCHER provides high performance computing support for research and industry projects in the UK.

<strong>Cute computer.</strong> Wee Archie is a pint-sized version of the world's fastest parallel processors. This tiny technological marvel is no toy, though: It is inspiring schoolchildren to try their hand at computing and making familiar the powerful world of high-performance computing. And it's cute, too. Courtesy University of Edinburgh/Maverick Photography.

Researchers use supercomputers for tasks requiring huge amounts of processing power, such as weather forecasting and molecular modeling of biological compounds, and often occupy several thousand square feet. Wee ARCHIE, however, replicates high performance computing techniques in miniature, taking up about a suitcase worth of space. One person can transport Wee Archie in its travel case and set it up in less than five minutes.

The machine simulates races between on-screen dinosaurs, letting users modify the structure of dinosaurs’ muscles and joints and alter their ability to run. Wee ARCHIE tests each of the configurations quickly, and presents the results as an on-screen race. It has already proven popular with school pupils at outreach events designed to shed light on the complexities of supercomputing.

“We use Wee ARCHIE to engage schoolchildren with supercomputing, and show them the huge benefits that the technology can bring to scientific research,” says Lorna Smith, of the ARCHER outreach group at EPCC. “We hope to inspire some of them to take up programming for themselves.” 

FUSION, the university’s science outreach group, designed and built Wee ARCHIE in collaboration with EPCC (formerly the Edinburgh Parallel Computing Center). “Designing Wee ARCHIE was highly enjoyable — from concept to building and using it,” says Archer application consultant, Alistair Grant. “Putting together a portable cluster which is safe, light, and easy to set up  — that was a challenging prospect.”

<strong>Big things in small packages.</strong> With 72 cores and 144GB of RAM, this small supercomputer can be set up in about five minutes. Students are thrilled by the ability to design dinosaurs on the fly and see parallel processing in person. Courtesy University of Edinburgh/Maverick Photography.

Wee ARCHIE contains 18 credit card-sized processors housed in a custom-made Perspex case. The machine has 72 cores across 18 Raspberry Pi processors with one gigabyte of RAM each. Each node has eight gigabytes of storage — which, depending on application, can be shared to give a total of 144 gigabytes. 

The portable system displays the types of hardware found inside the world’s fastest, most powerful supercomputers. LED displays on each of the processors light up when they are in use, showing how multiple parts of a parallel computing system work together to perform complex tasks.

“It is a tangible example of how parallel machines can be demonstrated,” says Grant. “Its recognizable components give familiarity to the general user while how it’s used and put together is likely a bit out of their comfort zones. It’s a functioning system at a scale people can understand without losing the big picture.”

Join the conversation

Do you have story ideas or something to contribute?
Let us know!

Copyright © 2017 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.