Nvidia says DLSS 5 comes with a 50-60% performance hit, which makes me wonder what we're doing here
www.pcgamer.com
You thought ray tracing was bad...

cross-posted from: https://lemmy.world/post/51453544

The very bad news is, Nvidia says turning DLSS 5 on will currently reduce performance by 50-60%. And that’s across the board—no matter the game.

  • givesomefucks@lemmy.worldEnglish
    5·
    7 hours ago

    Genuinely asking:

    Is this the first time DLSS hurts fps instead of improving it?

    Like, I thought that was the entire point of it. It allowed you to turn up settings but still have useable frame rates.

    I don’t know who would pay for a card to support this, just to turn around and cut the fps in half.

    It seems like their target demo is people that pay for 5090s but for some reason still put on all the frame gen and scaling stuff to make their game look worse. This chops the frame in half, when they could just turn off frame gen and scaling and likely have better and steadier frames.

    • Dudewitbow@lemmy.zipEnglish
      6·
      7 hours ago

      Dlss was originally an anti aliasing technique (its in the name) so it has originally been a performance hit. It was casual change and marketing that decided that upscaling from a lower resolution was the norm.

      DLDSR is essentially what DLSS 1.0 was

      If youre upscaling from a lower resolution, thats no longer the SS in DLSS (super sampling)

      • urushitan 漆たん@kakera.kintsugi.moeEnglish
        1·
        3 hours ago

        DLAA is the anti aliasing only. DLSS was always ai upscaling with anti aliasing as a first pass, literally Deep Learning Super Sampling.

        DLSS 1

        The first iteration of DLSS is a predominantly spatial image upscaler with two stages, both relying on convolutional auto-encoder neural networks.[31] The first step is an image enhancement network which uses the current frame and motion vectors to perform edge enhancement, and spatial anti-aliasing. The second stage is an image upscaling step which uses the single raw, low-resolution frame to upscale the image to the desired output resolution. Using just a single frame for upscaling means the neural network itself must generate a large amount of new information to produce the high-resolution output, which can result in slight hallucinations such as leaves that differ in style to the source content.[13]

        https://en.wikipedia.org/wiki/Deep_Learning_Super_Sampling

      • givesomefucks@lemmy.worldEnglish
        1·
        6 hours ago

        Thanks!

        I’ve got a 4070 super now, but other than that I always had AMD. So just never really paid attention to it.

        Definitely seems like the my first Nvidia GPU is gonna be my last tho