• @oyzmo
    link
    English
    222 days ago

    Life advise: If something sounds too good to be true, it most likely is…

  • @[email protected]
    link
    fedilink
    English
    122 days ago

    10x Faster!*

    *10x faster when thrown off the side of a building compared to stationary Nvidia 5090, actual clock speeds comparable.

  • @alphabethunter
    link
    English
    372 days ago

    Watch their announcement video on youtube, it screams VC funding scam. The whole announcement is basically just the CEO sitting on a couch and making outrageous claims, while all the supporting data and graphs carry the disclaimer “pre-silicon simulated benchmarks”. They say they’re going to have a live demo this month and in the following months, but they don’t even have real silicon, while also claiming they’re going to be shipping cards by Q4 2026.

  • @AdrianTheFrog
    link
    English
    7
    edit-2
    1 day ago

    Rasterization could be simulated in software with some driver trickery, but apparently it has less fp32 performance than the 5090 so it would be significantly slower

    Still, a RISC-V based GPU is very weird, normally I hear RISC-V being slower and less power efficient than even a CPU.

    I expect it to be bottlenecked by complex brdfs and shaders in actual path tracing workloads, but I guess we’ll see what happens.

      • @AdrianTheFrog
        link
        English
        5
        edit-2
        1 day ago

        In theory it should be able to be more power efficient. In practice, less development has been put into RISC-V CPU designs so they are still less power efficient than Arm (and maybe x86 even)

        • @[email protected]
          link
          fedilink
          English
          31 day ago

          Arm are RISC processors, I’m lead to believe x86-64 might even be something similar under the microcode.

          • @AdrianTheFrog
            link
            English
            21 day ago

            Yea I edited to say RISC-V specifically, thx

  • @[email protected]
    link
    fedilink
    English
    482 days ago

    There is one major catch: Zeus can only beat the RTX 5090 GPU in path tracing and FP64 compute workloads because it does not support traditional rendering techniques. This means it has little of no chance to become one of the best graphics cards.

    Still nice to see some competition.

    • @Cort
      link
      English
      192 days ago

      Would be kinda neat to have it as a dedicated ray tracing card, like the phys-x cards of yore

  • @0li0li
    link
    English
    72 days ago

    Well, until GPUs can be used as CPUs, ganes will not benefit from cardes that are that much more powerful. I mean, whether my games look fine, good or great, when there’s a drop in performance that impacts my enjoyment, it’s always CPU load (or memory leaks); never the GPU.

    • @[email protected]
      link
      fedilink
      English
      21 day ago

      You generally want to balance towards a GPU bottleneck, cause like you said the impact of CPU bottlenecks are real jittery and affect enjoyability more than a GPU one.

      • @0li0li
        link
        English
        01 day ago

        Can recall the last game where the GPU was the bottleneck tbh lol. Maybe back on console…

    • @AdrianTheFrog
      link
      English
      0
      edit-2
      1 day ago

      Still, a fully path traced game without the loss in detail that comes from heavy spatial and temporal resampling would be great

      And with enough performance, we could have that in VR too. According to my calculations in another comment a while ago that I can’t be bothered to find, if this company’s claims are to be believed (unlikely) this card should be fast enough for nearly flawless VR path tracing.

      It’s less exciting for gamers than it is for graphics devs, because no existing games are designed to take advantage of this high of rt performance