Comment Re:More anti-features from nvidia? (Score 1) 131
Though I think most of these AI-enhanced 'features' are indeed marketing fluff, I have to disagree that they impact game responsiveness.
Yes, DLSS3 does fudge actual frame rates by faking/upscaling in-between, but the vast majority of frames have to do with eye-candy anyway, and not responsiveness or input in any way. Professional games (and game-engines) have separate display and input systems, and often distinct physics-frames as well, that update at wildly different rates.
For example a RTS (so generally not reaction-based at all) will have logic-states (building queues, unit orders, mission objectives, etc) updating very infrequently, along with input, because those are essentially not time-sensitive relative to the rendering time-budget. Then you'll have physics frames at maybe 10-30 fps, just to make sure any collision and destruction animations have solid data, and then everything else is pure rendering - interpolating movement and explosion animations and superfluous things like that. Often these rendering frames have no access to game-state at all, being on separate threads or co-routines, to optimise everything. So they have nothing to do with player responsiveness. And if there is some nifty trick to interpolate them quicker or fake half of it, sure, whatever. The only impact here is whether the end results looks prettier or smoother.
Even on an FPS, where reaction-time is everything, physics frames will not exceed 60 fps. Even that much would is already unnecessary and quite wasteful. The only job of the rest of the frames is looking pretty when you reload, and making sure that graphics-heavy effects don't spike too much and steal time from the physics calculations whose accuracy is mechanically-essential. So again, whatever you do with your animation cycles has nothing to do with your input events or with your game-logic and world-states, so no impact on responsiveness at all.