TL;DW:

  • FSR 3 is frame generation, similar to DLSS 3. It can greatly increase FPS to 2-3x.

  • FSR 3 can run on any GPU, including consoles. They made a point about how it would be dumb to limit it to only the newest generation of cards.

  • Every DX11 & DX12 game can take advantage of this tech via HYPR-RX, which is AMD’s software for boosting frames and decreasing latency.

  • Games will start using it by early fall, public launch will be by Q1 2024

It’s left to be seen how good or noticeable FSR3 will be, but if it actually runs well I think we can expect tons of games (especially on console) to make use of it.

    • Hypx@kbin.social
      link
      fedilink
      arrow-up
      5
      arrow-down
      3
      ·
      edit-2
      1 year ago

      You aren’t going to use these features on extremely old GPUs anyways. Most newer GPUs will have spare shader compute capacity that can be used for this purpose.

      Also, all performance is based on compromise. It is often better to render at a lower resolution with all of the rendering features turned on, then use upscaling & frame generation to get back to the same resolution and FPS, than it is to render natively at the intended resolution and FPS. This is often a better use of existing resources even if you don’t have extra power to spare.

    • Dudewitbow@lemmy.ml
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 year ago

      because I think the post assumes that the GPU is always using all of its resources during computation when it isn’t. There’s a reason why benchmarks can make a GPU hotter than a game can, as well as the fact that not all games pin the gpu performance at 100%. If a GPU is not pinned at 100%, there is a bottleneck in the presentation chain somewhere. (which means unused resources on the GPU)

      • kadu@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        1 year ago

        You’re correct, and if AMD is announcing the feature this does mean there’s is enough shader compute available for this to work.

        However, this does mean the algorithm must be light enough to generate the frame in that very limited resource usage. This is already what we see with FSR, that works well, but can’t fix some of the issues DLSS can because DLSS can use way more complex algorithms as it isn’t fighting for resources.

        • Dudewitbow@lemmy.ml
          link
          fedilink
          English
          arrow-up
          2
          arrow-down
          1
          ·
          1 year ago

          I still think it’s a matter of waiting for the results to show up later. AMD for RDNA3 does have an AI engine on it, and the gains it might have in FSR3 might be different in the same way XeSS does with branching logic. Too early to tell given that all the test suite tests are RDNA3, and that it doesn’t officially launch til 2 weeks from now.

          • kadu@lemmy.world
            link
            fedilink
            English
            arrow-up
            1
            ·
            1 year ago

            Yep, looking forward to the results, if it works well enough it could be huge for portable devices, for instance.