“The fundamental building blocks of all computing devices could be about to undergo a dramatic change that would allow faster, more efficient machines. Researchers at computer firm Hewlett Packard have shown off working devices built using memristors – often described as electronics’ missing link. These tiny devices were proposed 40 years ago but only fabricated in 2008. HP says it has now shown that they can be used to crunch data, meaning they could be used to build advanced chips.”
The link has a %22 after it. Correct link is http://news.bbc.co.uk/2/hi/technology/8609885.stm
40 year old *proposal*.
“Despite being proposed by Professor Chua in 1971, it took almost forty years for a working memristor to be built”
Edited 2010-04-12 14:49 UTC
Seriously… fast like RAM, and non-volatile like hard drives… sign me up. 5 years from now it’ll be between memristors and SSD like its between SSD and hard drives today.
Personally I read the article to mean CPUs with on-chip cache so large that it negates the need for RAM and non-volatile so it’s instant power ups for devices / computers.
I wouldn’t be surprised if dedicated storage devices would still be needed as storage requirements continue to grow exponentially – at least for those of use that work a lot with high quality media, (eg audiophiles / record producers / engineers / DJs, movie editors / VJs, gamers, professional photographers / graphic designers, etc).
That said, maybe by the time this technology hits, the majority of average users will be using iPad-like devices for most of their computing and future “internet tablets” will only need high capacity non-volatile on-chip cache rather than the plethora of SSDs, memory cards (SD et al) and “retro” storage devices such as optical drives and magnetic readers (removable diskettes and HDDs).
However, by then we’ll all be living on the moon and driving hovercars. </bad joke>
Jaaaaaane! Stop this crazy thing!
Don’t hold your breath, I’m still waiting on the delivery of my MRAM pre-order. I think I can expect it to arrive just before my other order of protein-based, light controlled memory. And who knows, by that time I might be powering my computer with my very own nuclear fusion reactor.
In other words: I’ll believe it is a viable product when it’s there, in mass production.
Are the patents expired? Any tech company can use this technology?
A working memristor was produced in 2008. That should mean that the patents on the specific implementation of that thing should expire around 2028 (+/- 2 years)?