Takes me back... There was significant hype around those things when they first managed to build them at scale (~15 years ago), because they were promising for low power, high density persistent storage and are also academically interesting: The "concept" of memristors was explored over 50 years ago (they are passive components that couple electrical charge and magnetical flux, just like a resistor does with current/voltage, a capacitor with voltage/charge or an inductivity with current/flux).<p>But I think the main problem was that they never managed to scale up the clock speeds sufficiently, even though structure size (=> density) was already highly promising from the start.<p>Maybe in a slightly different history with some discoveries in different orders these could have replaced flash memory in SSDs completely.<p>But that whole episode thought me that betting on early technology is <i>hard</i>, and always a risky business, because no matter how promising an approach looks, if it turns out that you can not find the necessary improvements in only a single dimension, then the whole thing is kinda doomed and will probably never be competitive (=> a highly relevant insight especially when speculating about things like novel battery chemistries or the like).
The original pre-print is available at: <a href="https://www.researchsquare.com/article/rs-3647379/v1" rel="nofollow">https://www.researchsquare.com/article/rs-3647379/v1</a><p>which is probably a less spammy source than the ResearchGate link.
Just a bit of context: MRAM exists as an IP for long time, but their promise to execute code directly from it didnt really pan out because of speed. So it competes against flash to store the code that is booted into SRAM and it loses there too because of mostly larger area
This was later published in Nature:<p><a href="https://www.nature.com/articles/s41586-024-07902-2" rel="nofollow">https://www.nature.com/articles/s41586-024-07902-2</a>
> 460× less energy than digital computers<p>The brain is running on 20W of power and it has the best LLM, the best robotics control unit, very good sensor integration and all the other exciting stuff which we* want** AIs to have. I'd rather have that than nuclear powerplants feeding data centers.<p>* overreaching a bit<p>** also not really true for everyone