Can anybody with experience in fabrication reveal more about this? Very exciting ideas, but hoping to learn more in real-world context

  • trolololol@lemmy.world
    link
    fedilink
    arrow-up
    2
    ·
    10 months ago

    Interesting, in this particular case it’s implementing a single operation, but I can imagine they can implement other single operation dedicated chips as well. So I’d expect ASICs but no CPUs

    https://actu.epfl.ch/news/redefining-energy-efficiency-in-data-processing/

    By setting the conductivity of each transistor, we can perform analog vector-matrix multiplication in a single step by applying voltages to our processor and measuring the output

    • weew@lemmy.ca
      link
      fedilink
      arrow-up
      4
      ·
      10 months ago

      Still, i don’t think it’ll need to get much more complex to be very useful for AI workloads.

      People have been discovering that more, and simpler, calculations seem to work better? the trend in AI workloads seems to have gone from FP32 -> FP16 -> INT16 -> INT8 and possibly even INT4?

      Seems like just having lots of simple calculations is more efficient/effective than more complex stuff.