“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.world
    link
    fedilink
    English
    arrow-up
    124
    arrow-down
    5
    ·
    9 months 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.world
      link
      fedilink
      English
      arrow-up
      38
      ·
      9 months 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.

    • yoyoyopo5@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      9 months ago

      They’re real, but they aren’t general purpose and lack precision. It’s just analog.

    • Treczoks@lemmy.world
      link
      fedilink
      English
      arrow-up
      17
      ·
      9 months ago

      Same here. I wait to see real life calculations done by such circuits. They won’t be able to e.g. do a simple float addition without losing/mangling a bunch of digits.

      But maybe the analog precision is sufficient for AI, which is an imprecise matter from the start.

  • NutWrench@lemmy.world
    link
    fedilink
    English
    arrow-up
    44
    arrow-down
    7
    ·
    9 months ago

    Look, It’s one of those articles again. The bi-monthly “China invents earth-shattering technology breakthrough that we never hear about again.”

    “1000x faster?” Learn to lie better. Real technological improvements are almost always incremental, like “10-20% faster, bigger, stronger.” Not 1000 freaking times faster. You lie like a child. Or like Trump.

  • Quazatron@lemmy.world
    link
    fedilink
    English
    arrow-up
    30
    arrow-down
    1
    ·
    9 months ago

    This was bound to happen. Neural networks are inherently analog processes, simulating them digitally is massively expensive in terms of hardware and power.

    Digital domain is good for exact computation, analog is better for approximate computation, as required by neural networks.

    • bulwark@lemmy.world
      link
      fedilink
      English
      arrow-up
      8
      ·
      9 months ago

      That’s a good point. The model weights could be voltage levels instead of digital representations. Lots of audio tech uses analog for better fidelity.I also read that there’s a startup using particle beams for lithography. Exciting times.