ramblings of an aimless mind

Just another Wordpress.com weblog

The LHC computer system.

leave a comment »

One of the most well publicised events in the scientific community in the recent past has been the opening of the Large Hadron Collider. The world reacted with great incredulity and amazement when they heard of the 27km tunnel built across the borders of two nations, the collaboration of 10000 scientists, the bunch of detectors all hoping to find the “Higgs boson” and of course, the idea that went around suggesting that the LHC would create a black hole that will swallow up the earth. The project cost around 4-6 billion euros, a figure which some people thought would have been better spent on solving more relevant issues. After all, knowing which particle the universe originated from is not so important as solving the global warming crisis right?

While the LHC was getting so much attention and the odd bit of controversy, there were huge technical developments in the computing systems which have received no mention at all, but are quite ground breaking in their own right. Not surprising, since the computers were not the focus of the project, but it is interesting to realise that the computing infrastructure would have created a new paradigm out of one of the “secondary” requirements of the project.

The LHC is expected to produce about 5-6 gigabytes of data every second, all of which has to be filtered, processed and stored. The computer infrastructure to accomplish this is a multi-tiered structure of different locations connected by fibre optic links. This distributed structure, along with the algorithms etc. formed the basis for what is now known as high throughput computing, which has a slightly different focus compared to high performance computing and could probably be used for some of the heavy number crunching applications that turn up in the future (climate modelling?). Details of the computing infrastructure can be found in the link, so I will not dwell upon it. What I want to point out is that this is not the first time CERN has innovated in the field of computer science. Way back in 1990, their computer science division tried out something called the HTTP protocol, designed to make it easier for researchers to share their results. The protocol went on to form the foundation of the world wide web and the rest, as is often said, is history.

This goes to underline some of the indirect benefits of pure research to the more “useful” technical fields. I initially used to feel that research should be all about something that has a tangible benefit to society and something esoteric like finding the Higgs boson or colliding neutrons is a waste of resources. I have now come to realise that while the main focus of  any high cost pure research project (low cost projects are easy to handle anyway) may not have an obvious tangible benefit, there will always be other practical difficulties which need to be solved and which may/will produce innovative solutions. Scientists working on these problems are also a funny bunch, probably the paragon of the breed that does things purely for the fun of it and not for monetary gain. Forcing these people to work on applied problems may be as horrifying to them as licking stamps for customers in the local post office and will probably make them give up their aspirations and settle down in a routine job and study their fields of interest as a hobby. It is probably better to allow them pursue their dreams, develop the technologies for the pursuit and then have another bunch of people more interested in the applied side of things to try and apply the offshoots of their work to other worldly issues. Unless the research organisation desires to make money from it, it does not even have to employ a large staff to do such work. Just having someone who is knowledgeable enough to document the results well will do the job.

In other words, it is important not to judge research only by the perceived utility of its focus. The evaluation should also include the secondary aims, something that ties in nicely with my earlier post on science being about the journey and not the destination


Written by clueso

November 14, 2008 at 9:04 am

Posted in Uncategorized

Tagged with

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: