The dawn of next generation storage is only three years away, IBM claimed last week, as holographic technology advances.
IBM told PC Week that it expects to have storage products based on holographic storage in 2002, which is three years earlier than industry pundits had been predicting.
Holographic storage promises to dramatically reduce the physical size of storage devices and increase the speed at which data can be stored, so that the same amount of data that now takes milliseconds would take microseconds to write to disk. Data is written to optical media using lasers and stored in a compact three-dimensional form that could potentially be as small as an atom.
There is no need for mechanical moving parts in such a system, and all the information in each page is accessed simultaneously, speeding up access times remarkably.
E-commerce is increasing the demand for storing larger quantities of data, and enabling it to be accessed more quickly, while complex multimedia data is increasing the size of the data to be stored.
Despite its pioneering efforts in holographic storage, IBM does not expect the market to mature for a few years after the first products appear, explained Christoph von Gamm, communications manager at the IBM Technology Group. That is why IBM continues to invest in current technology, such as digital tape and RAID controllers, that will be redundant if holographic storage takes off.
Last week, the company bought low-end RAID controller maker Mylex for $240 million (£152 million). "RAID controllers will dominate for at least ten years and digital tape is having a great revival - it will be the standard for permanent storage for the next ten or 20 years," claimed von Gamm.
IBM also launched a new cross-platform disk storage system last week, which it called Shark (see p13). "(Shark) is good news for IBM: it gives (the company) a product to compete with EMC, but it would have been better if (IBM) had it two years ago," said Claus Egge, senior storage analyst at research firm IDC.
A smartphone maker fiddling its benchmarking scores? That's unusual, isn't it?
'We are making good progress on 10nm,' claims Intel
Engineer calculates that Chengdu's plan to replace streetlights with artificial moonlight would cost $100bn
Research could also apply to other 'space weather' events involving hot, fast-moving plasma