IBM is operating on both super-fast and super-dense memory media that should reach enterprises earlier the finish of this decade, and demand in few industries appears probably to keep pace with the progresses.

The amount of information that initiatives have to dispense with is growing so quick that they are coming up against power and area finxed and grappling with how to handle the data, according to analysts, users and IBM officials at a press event that the company hosted in San Francisco on Wednesday.

IBM highlighted two futurist techs that researchers are exploring now to address distinguish challenges: how to make elementary information present quicker and how to pack archived data into a littler space. For the former, the company is formulating so-called "racetrack" storage, in which information is preserved in unlike magnetic regions that travel over short, nano-scale wires when accessed. It may arrive on sale in five to seven years, according to Bruce Hillsberg, IBM's director of storage systems research. For the latter, researchers are apply an unspecified magnetic tech that could preserved a petabyte of information in a standard 1U rack unit.

IBM conceives "racetrack" tech will pave the way for Storage Class Memory, which will be almost as quick as today's memory but be able to scale up to enterprise save capacity. It's so dense that it could permit a portable music player to hold 500,000 songs.

With Storage Class Memory, the amount of area and power necessitated to store prominent enterprise information sets could shrink dramatically by 2020. What would take 1,250 racks of hard disk reple today could be preserved in one rack, with less than one-third the energy. The medium will also last longer than the flash SSDs (solid-state drives) now apply for fast storage, he said.

The other twist IBM is operating on, which it called easy the "petabyte storage twist," would be planned to store information for as long as 50 years minus the require for migration to another medium. Moving message from one twist to a newer generation of hardware costs money and time and can insert record-keeping faults, he said.

Minus giving more particulars about the twist, Hillsberg said it would have few proceeding parts but not as many as a tape library, the distinctive solution for long-term archiving today. He envisions it being apply not as a substitute for tape but in conjugation with it, possibly to give access to archived information above a cloud infrastructure.