This chapter will look at how the Internet has enabled large numbers of computers to be connected together in such a way that they can be used to attack wicked problems – that is, problems that are computationally very difficult to solve. The chapter starts by briefly looking at one application area: genome sequencing. I then describe a concept known as grid computing where very large numbers of computers are connected together in such a way that their spare capacity can be used to attack such hard problems. The chapter concludes by very briefly looking ahead to the seventh chapter and describes how the grid concept has become commercialized into something known as cloud computing. This involves regarding the Internet as just one huge computer with almost infinite computing power and data-storage facilities. You may think that this is just a technical issue, but it also has some important social and philosophical issues and questions; some of these are explored in Chapter 8.
There is a path from the early single processor computer, via closely coupled supercomputers, to loosely coupled supercomputers and then to the Internet where PCs and other computers collaborate on tasks. This chapter represents a half way house in the path towards cloud computing – one of the key ideas in this book.
- An introduction to the Human Genome project. The project has finished but the results are of immense utility.
- The travelling salesman problem is the problem to solve by computer scientists. This site is extensive and some of it is technical. It is worth looking at the history of the problem and its applications.
- The Jaguar system by Cray.
- This page from the European Centre for Medium Range Weather Forecasting shows how one organisation utilised supercomputers.
- The Beowulf system developed by Joel Adams and Tim Brom.
- A good introduction to the DNS system.
- An example of ant simulations being used to solve a software problem.
- Expert systems are a form of artificial intelligence (AI). This page details many of the applications of AI.
- This is a good Wikipedia entry on supercomputers. Its worth keeping an eye on this page: as time goes on more and more powerful supercomputers will be added.
- An introduction to grid computing that also includes some scientific applications and some business applications.
- This is Nicholas Carr’s first book Does IT Matter, his second book The Big Switch carries on from this and looks at computing as a utility comparing its growth with that of the electricity industry. I highly recommend both.
Speed Disparity and Multitasking
In Chapter 2 I describe the disparity in speeds between the hardware processor of a computer and file storage technology: the former operates in microseconds, while the latter operates in milliseconds. There is potentially a major waste of processor hardware when a processor makes a request for some file storage data and has to wait for a long time to receive it. One option is for the processor to idle: effectively doing nothing. The other option is for the operating system of the computer, for example Windows, to ask the processor to carry out some other task; this is a process known as multi-tasking. Later you will meet a concept known as grid computing in Chapter 4. This is a technology that connects a number of processors together in such a way that they take advantage of this slack resource. This article describes another use for slack resources on a home PC: running computational programs that help into biomedical research. Your home computer will use slack processor resource to carry out computations while you are, for example, retrieving word-processed files.
The Super Chip
Intel, this week, announced a supercomputer on a chip. It could possible bring high power computation to the desktop. Looks like the Beowulf computer I describe in this chapter will be superseded. Here’s the story from the Daily Telegraph.
Making Money from the Weather
In the book I describe how researchers have been able to plot the incidence of flu and other health problems by looking at the geographical spread of queries to the Google search engine. Here’s another example of how extra information can be used; this time in order to make money.