Electrons are fleeting. Magnets remember. That’s the reason your computer stores data permanently in a magnetic hard drive, but uses semiconductor electronics for the random-access memory (RAM) that runs software. Problem is, once you cut the juice, the data in this short-term memory disappears. That’s why Windows has to re-boot every time-your PC is transferring the program from the hard drive onto the RAM chips.
So it’s not surprising that some of the world’s largest microelectronics makers are racing to develop magnetic RAM that could provide computers with a fast and cheap “instant on.” Scientists at IBM’s Almaden Research Center say they have now fabricated a crude magnetic RAM prototype containing 500 working memory cells (each cell represents a bit of memory) by sandwiching aluminum between ultrathin layers of a ferromagnetic metal alloy. The prototype has storage density as good as DRAM (dynamic random access memory), the most common type of semiconductor memory, but reads and writes information 20 times faster while consuming less than than one hundredth the energy.
Although it’s still a few years from the market, says Stuart Parkin, an Almaden researcher who helped pioneer recent IBM advances in hard disk technology, magnetic RAM’s speed and power efficiency should initially prove “incredibly useful” in battery-operated electronics used for applications such as digital cameras and cell phones.
Turning on Magnetic RAM Organization Status IBM Research
(San Jose, Calif.) Built a 500-cell prototype based on magnetic tunneling junction technology Hewlett-Packard
(Palo Alto, Calif.) Demonstrated a working test device proving design and materials Honeywell
(Plymouth, Minn.) Has shown a 1-Mbit chip; promises a product for specialized defense applications by next year Intregrated Magnetoelectronics
(Berkeley, Calif.) Built a 8-Kbit prototype; plans to complete a 1-Mbit all-magnetic RAM device next year Motorola
(Phoenix, Ariz.) Demonstrated a 512-bit working prototype; predicts a commercial product within five years
Capitalizing on machine learning with collaborative, structured enterprise tooling teams
Machine learning advances require an evolution of processes, tooling, and operations.
The Download: how to fight pandemics, and a top scientist turned-advisor
Plus: Humane's Ai Pin has been unveiled
The race to destroy PFAS, the forever chemicals
Scientists are showing these damaging compounds can be beat.
How scientists are being squeezed to take sides in the conflict between Israel and Palestine
Tensions over the war are flaring on social media—with real-life ramifications.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.