I'm not sure what point your trying to make. The level of realism offered by DLSS 5 is not currently doable using native GPU compute which is why we are doing it with AI.
Also dont forget that its an option. You can turn it off if you want.
But what I said about Moores law being dead is a fact.
If we weren't going down this road of AI, graphics would be stagnating along side the slow progress that GPU hardware is making.
Even now we have to rely on DLSS for upscaling just to play games at 4k as the hardware is not there to run it natively.
With out DLSS we wouldn't have RT or PT at all as it just wouldn't be feasible to run.
Remember that this technology will advance performance wise very quickly.
NVIDIA already claims to have improved DLSS 5 performance by over five times (5X or 500%) over a six-month period and I imagine the next gen of cards will probably have some sort of hardware level improvements to drive this sort of thing even faster.
So the balance of progress has shifted more in to the realms of software advancements rather than hardware. We are still seeing hardware advancement, but it is just slower and will probably keep getting slower until there is some sort of big break through in hardware technology that changes the game.
Progress is going to be in the software side. I.e AI.
---
Also to take your example
"5080 4k dlss performance with RT Reflections in NBA 2027 is 102 fps vs dlls 5 with 43fps... Basically you're left with 42% of the initial performance"
OK, that may be so but what about if in 6 months time its only 25% reduction in fps?
Its like enabling RT. It kills your fps. Yes it does. But it also enhances the image quality.
I guarantee you DLSS 5.5 will be even faster with better IQ.
---
I also regard DLSS 5 as still preview technology with the NBA game just a tech demo of the technology Nvidia have clearly sponsored to show it off and get some real world performance metrics to measure.
I don't have a problem with AI, I'm just saying to use it wisely. Raster + DLSS 5 is a no go for me since it means you're going back to screen space effects.
DLSS 5 is just a filter, it doesn't have a holistic understanding of the scene, it can't do lighting and shadows better than PT and never will be able to in its current form. That is why nVIDIA says it works best with PT as it lays the foundation for that work on. Now... good luck with PT + DLSS 5 running real time at decent frame rates outside of some very expensive and limited hw.
OTOH, PT alone can give proper lighting and shadows at a similar or lower cost. You have the
TW4 demo were a 4070 was basically 60fps @1440p quality with a smart approach. Fatekeeper early access runs for me (rtx 4080, 5080x3d), at 4k DLSS Performance with Mega Lights at 60-70 fps
before frame gen and looks stunning.
Moreover on the characters side, developers should allow their "cinematic assets" to be rendered real time. I mean... you
already render them real time in cinematics with certain games and work real good, but they choose
purposely to handicap their visual presentation by not allowing them to be rendered in game. Not the least, look at the example shown here, where hair either renders shadows just as badly as raster or doesn't render them at all.
Performance gains can be made also by lower the end quality. Right now DLSS 5 uses the full image, but if you put it with DLSS in mind so it renders the image at lower resolution you do get better performance, but lower quality.
Let's not forget newer models of DLSS were heavier on older cards, so while presets like L and M improve IQ, that doesn't come freely. To get to that "just 25%", it will need to improve by around 4.1x:
Without DLSS 5 you already have:
1000/102=9,80 ms - for that 102fps
For 76,5 FPS, you'll need most:
1000/76,5=13,07 ms
Extra time available to DLSS 5:
13,07−9,80=3,27 ms
Now, the effective time cost is:
23,26−9,80=13,46 ms - for that 43fps
Ergo, you'll need
13,46/3,27≈4,1 times improvement for performance alone without other IQ improvements!
Is this an early stage to get that much improvement? I don't think so. Also, to be faster, it will need to run faster on current hardware, not on future hw. That doesn't make it faster per se.
To be fair that screenshot looks better as the lighting is very different and it does show.
Also, reading back my own nobile-induced typos in your quote of my post was horrendous
. Edited it now!
You need to have a high quality lighting system for best results, without that it can't have the best results.
Are you insinuating then that Nvidia are purposely holding back hardware advancement to push this AI narrative?
Because I will remind you that it not just Nvidia that has to use AI upscalers to get acceptable frame rates. AMD, Intel and Sony all have their own AI upscalers so what does that tell you about the state of pc hardware if the hardware is there to do all the graphics processing natively?
I asked AI this question:
Is the use of technology such as DLSS 5 a way to get further enhancement in the GPU space despite moores law being dead?
Answer:
Yes, technologies like
DLSS 5 are the
exact definition of how the industry is bypassing the death of traditional Moore's Law. However,
DLSS 5 shifts the paradigm entirely compared to previous versions. [
1]
While older iterations of DLSS were designed to save hardware resources, DLSS 5 is an aggressive pivot into
Neural Rendering. It replaces raw brute-force computing with advanced AI algorithms to achieve next-generation visuals. [
1,
2,
3]
How DLSS 5 Outsmarts Moore's Law
Instead of relying on the physical shrinking of transistors to squeeze out more performance, Nvidia is leaning into software and hardware co-design: [
1,
2]
- 3D-Guided Neural Rendering: Traditional rendering requires calculating millions of complex light bounces (ray tracing), which is incredibly heavy on standard silicon. DLSS 5 bypasses this by using an AI diffusion model. It takes a single rendered frame, reads the motion vectors, and dynamically "repaints" photorealistic lighting, subsurface skin scattering, and material textures onto the scene in real time. [1, 2, 3, 4]
- Algorithmic Efficiency over Transistor Count: By letting dedicated Tensor cores handle the heavy lifting of visual reconstruction, the primary graphics pipeline can focus on basic geometry. The AI fills in the cinematic gaps that hardware can no longer cheapen. [1, 2, 3]
The Twist: The "Moore's Law" Tax is Still Lurking
While DLSS 5 successfully unlocks movie-quality graphics that traditional silicon couldn't natively render, its launch has exposed a new bottleneck:
it is exceptionally heavy to run. [
1,
2,
3,
4]
- A Heavy Performance Penalty: Unlike previous DLSS versions that acted as a performance "cheat code" to boost frame rates, DLSS 5 causes a massive 50% to 70% drop in frame rates when turned on. It requires so much compute power that early tech demos required two flagship graphics cards to run smoothly. [1, 2, 3]
- The Need for Architecture Innovations: Because it is so resource-intensive, Nvidia and modders are already rushing to optimize it. They are attempting to port the model to the RTX 50-series' new 4-bit floating-point format (NVFP4), which reduces the memory and compute footprint on Blackwell architecture. [1]
The Bottom Line
DLSS 5 proves that enhancement in the GPU space is no longer just about adding more transistors to a chip. It is about using
generative AI as a tool to bridge the physical limits of hardware. However, because Moore's Law is dead, optimizing these heavy AI models to run efficiently on a single consumer GPU has become the new engineering battleground. [
1,
2,
3,
4]
---
Note this part:
While DLSS 5 successfully unlocks movie-quality graphics that traditional silicon couldn't natively render.
For Neural Rendering to be better and faster than PT it will need to have access to the whole scene and do the render itself. Right now is a screen space filter, it can't do any better.
DLSS 5 can't unlock movie quality graphics, that's BS. You also can't say what hw can do just based on what is done in general. You don't really have PC only titles pushing rendering technologies at their limit.
Right now is a "cheap" technic from a developer side to get better IQ, but is hardly the right way to do it, but rather is a step back.
