Researchers from Peking University say their resistive random-access memory chip may be capable of speeds 1,000 faster than the Nvidia H100 and AMD Vega 20 GPUs.

“The new device is built from arrays of resistive random-access memory (RRAM) cells… The team was able to combine the speed of analog computation with the accuracy normally associated with digital processing. Crucially, the chip was manufactured using a commercial production process, meaning it could potentially be mass-produced.”

Article is based on this paper: https://www.nature.com/articles/s41928-025-01477-0

  • Alexstarfire@lemmy.worldEnglish
    1815·
    15 hours ago

    It uses 1% of the energy but is still 1000x faster than our current fastest cards? Yea, I’m calling bullshit. It’s either a one off, bullshit, or the next industrial revolution.

    EDIT: Also, why do articles insist on using ##x less? You can just say it uses 1% of the energy. It’s so much easier to understand.

    • CosmoNova@lemmy.worldEnglish
      471·
      12 hours ago

      I mean it‘s like the 10th time I‘m reading about THE breakthrough in Chinese chip production on Lemmy so lets just say I‘m not holding my breath LoL.

      • 4am@lemmy.zipEnglish
        211·
        10 hours ago

        Yeah it’s like reading about North American battery science. Like yeah ok cool, see you in 30 years when you’re maybe production ready

    • Snot Flickerman@lemmy.blahaj.zoneEnglish
      173·
      12 hours ago

      https://www.nature.com/articles/s41928-025-01477-0

      Here’s the paper published in Nature.

      However, it’s worth noting that Nature has had to retract studies before:

      https://en.wikipedia.org/wiki/Nature_(journal)#Retractions

      From 2000 to 2001, a series of five fraudulent papers by Jan Hendrik Schön was published in Nature. The papers, about semiconductors, were revealed to contain falsified data and other scientific fraud. In 2003, Nature retracted the papers. The Schön scandal was not limited to Nature; other prominent journals, such as Science and Physical Review, also retracted papers by Schön.

      Not saying that we shouldn’t trust anything published in scientific journals, but yes, we should wait until more studies that replicate these results exist before jumping to conclusions.

        • TheBlackLounge@lemmy.zipEnglish
          2·
          3 hours ago

          To a billion parameter matrix inverter? Probably not too hard, maybe not at those speeds.

          To a GPU, or even just the functions used in GenAI? We don’t even know if those are possible with analog computers to begin with.