Grid computing 'overhyped'
A leading figure in the European grid research community has criticised the technology industry for exaggerating the current capabilities of their grid computing products.
Mark Parsons, the commercial director of the Edinburgh Parallel Computing Centre (EPCC) and the National e-Science Centre, said at an EPCC seminar in London on Wednesday that grid computing — where computing power and data storage capacity can be shared between loosely coupled machines over a private network or the Internet — is still far from achieving its full potential.
"It's clear that grid has a lot to offer, but it's still early days," said Parsons. "There's been far too much hype about it."
Parsons said there is a lot of confusion over what grid computing is, partly caused by the number of words used to different companies to describe their grid computing strategies.
"Autonomic computing, adaptable computing, cluster computing, on-demand computing, utility computing, agile IT — all of us see these terms, which are different names for the same thing," said Parsons. "One of the problems in this area is that there are far too many marketing departments involved."
Parsons said that many companies market clustering products — where a series of machines are tightly linked together to provide load-balancing and resiliency when working on massive tasks — as grid technologies.
For example, he claimed that the "grid" computing products of companies such as Oracle, Platform and Gridsystems are merely a "new spin on clustering".
Colin Upstill, the managing director of the IT Innovation Centre, which researches grid technologies, agreed that there is a lot of PR noise around grid computing, but said the industry was further ahead than Parsons implied.
"There are a lot of serious and valuable things going on under that hype," said Upstill.
He claimed that a number of companies are using grids to increase competitive advantage, but are unwilling to talk about it so they can retain the upper hand over their competitors.