Skip to main content

Stanford finds that phase change memory could be 1,000 times faster than DRAM

stanford phase change memory breakthrough pcm
IBM Research
There’s new evidence that phase change memory could be a viable successor to the DRAM that we use today. A research project undertaken by Stanford University has demonstrated that the technology could facilitate memory that is thousands of times faster than the current crop.

Phase change memory takes advantage of materials that can inhabit two separate states; an amorphous state without a clearly defined structure, and a crystalline state with an organized, rigid structure.

Research into the usage of phase change memory has been promising, but there are still questions about the technology’s capacity for scaling, according to a report from Extreme Tech. Chip designers want to be sure that shifting to a new type of memory would provide benefits for many years, rather than just a few.

To that end, a team led by Aaron Lindenberg embarked on a research project to find out the speed at which phase change memory changes from one state to another, and how that pace could be harnessed.

The study found that exposing phase change memory cells to a 0.5THz pulse of electricity for just picoseconds can form crystallized filaments that could potentially be used to store data, while the large part of the cell remains in an amorphous state.

The key here is that the memory can change states on a picosecond timescale, whereas today’s DRAM operates on a nanosecond timescale. This means that phase change memory could potentially perform certain operations up to a thousand times quicker, while offering other benefits like reduced energy consumption and the ability to store data permanently even without power.

Aside from the speed, researchers also found that the crystallized filaments can be reliably measured. Because of that, it would be possible to store memory in the phase change material. The measurement of filaments might be used as a means of storing dead.

“This work is fundamental but promising,” said Lindenberg in a statement regarding the research that was released by Stanford. “A thousandfold increase in speed coupled with lower energy use suggests a path toward future memory technologies that could far outperform anything previously demonstrated.”

Editors' Recommendations

Brad Jones
Former Digital Trends Contributor
Brad is an English-born writer currently splitting his time between Edinburgh and Pennsylvania. You can find him on Twitter…
How to customize mouse gestures on Mac
Apple Magic Mouse on a desk.

Did you know that you can still pull off gestures and haptic tricks with a Mac computer, even without a touchscreen? Such feats are possible, just as long as you own an Apple Magic Mouse. Far more than a sleek-looking desk accessory, the Magic Mouse functions much like a MacBook trackpad. Taps, long presses, swipes, and pinches (among other actions) deliver a number of results, and you’ll be able to customize these commands, too.

Read more
How to delete or hide chats in Microsoft Teams
Running Microsoft Teams on the Galaxy Tab S8.

Microsoft Teams is a terrific workplace platform for keeping the camaraderie strong. Featuring collaborative messaging, video conferencing, and file-sharing tools, it’s your one-stop-shop for in-office, hybrid and at-home workers alike. But anyone with a long history of using Teams will tell you how clogged up your message stockpile can get. Fortunately, deleting and hiding these exchanges is relatively easy to do, and we’ve put together this guide to help.

Read more
Why Llama 3 is changing everything in the world of AI
Meta AI on mobile and desktop web interface.

In the world of AI, you've no doubt heard about what OpenAI and Google have been up to. And now, Meta's Llama LLM (large language model) is becoming an increasingly important player in the game, especially with its open-source nature. Meta recently made a big splash with the launch of its Llama 3 AI model, and it's shaken up the field dramatically.

The reasons why are multiple and varied. It's free to use, it has a wide user base, and yes, it's open source, to name but a few. Here's why Llama 3 is taking the AI industry by storm and may shape its future for some time to come.
Llama 3 is really good
We can debate until the cows come home about how useful AIs like ChatGPT and Llama 3 are in the real world -- they're not bad at teaching you board game rules -- but the few benchmarks we have for how capable these AI are give Llama 3 a distinct advantage.

Read more