See ya later flash drives, hello Phase Change Memory?

[Handruin]

This time it's a new kind of phase change memory (PCM) that reads and writes 100 times faster than flash, stays reliable for millions of write-cycles (as opposed to just thousands with flash), and is cheap enough to be used in anything from enterprise-level servers all the way down to mobile phones. PCM is based on a special alloy that can be nudged into different physical states, or phases, by controlled bursts of electricity. In the past, the technology suffered from the tendency of one of the states to relax and increase its electrical resistance over time, leading to read errors.

http://www.engadget.com/2011/06/30/embargo-ibm-develops-instantaneous-memory-100x-faster-than-fl/

Sounds too good to be true. Hopefully we'll see these replace flash drives in the next couple years if it makes it out of their lab and the cost can be kept down.

 

[Mercutio]

They call it cheap now, but watch when they're released and 10x as expensive as equivalent flash modules.

 

[BingBangBop]

New prospective tech is always promoted as the best thing since Wonder Bread and much cheaper. The true test is not what they say early but rather if it ever gets released as a product and what the price and capabilities are like when mass produced.

As an example, I'm still waiting for 3d holographic memory ...

 

[Will Rickards]

This kind of stuff has been in the news before. Glad to hear they seem to have the bugs worked out. But when will we see a drive for sale? 5 years?

 

[Handruin]

I see a huge need for this kind of replacement to flash memory. How many long posts have we had in the forum related to people complaining about the reliability and performance inconsistencies of flash-based SSDs? If this can make it to market as-claimed, then why deal with funky algorithms that deal with compression or wear-leveling, etc? Make the product simple, and let it perform. They claim millions of write cycles vs thousands. That's a big difference even in broad terms.

I'm excited that there is even news of something else being worked on to enhance/replace flash-based storage. The entire market for these drives seems so dull lately. Hell, the big rage seems to be PCIe cards for the performance-minded folk, but they are very specific and expensive.

 

[BingBangBop]

I won't disagree that there isn't a need. My point is that it is just vaporware. Until there is a product where's the value?

 

[LunarMist]

They will just make it 5 bits per cell or something so that it will be 99% unreliable crap and perhaps a small amount will be produced at premium prices for the high end.

 

[LiamC]

IBM. 'nuff said. They have a history of promoting tech like this but have a history of not delivering.

I'm not saying that research like this not good. It is. But there are large rewards a few promising technologies being trumpeted by competing companies. Whoever gets to market first stands to make a fortune—even if they have an inferior tech. Look at x86

Until I see some working tech, I'll just give it a golf clap.

 

[Handruin]

I won't disagree that there isn't a need. My point is that it is just vaporware. Until there is a product where's the value?

I know a lot of this stuff can and will be vaporware, but I was excited for a possible change. The value could be that a news article/discovery like this might open flash-based vendors eyes that maybe they need to investigate this or become obsolete.

 

[Bozo]

In this Computerworld article, phase change memory is already being used.

 

[Handruin]

Thanks for the link Bozo, it had more data than the link I posted.