NVIDIA DLSS 3.5, Featuring Ray Reconstruction (RR), Has Been Announced at GamesCom 2023 and Is Set to Arrive This Fall

DrezKill said:
I don't think so either, because only the RTX 4000 series has the Optical Flow Accelerators needed for Frame Generation.
Click to expand...

I think the 3000 series also has the optical flow Accelerators, except they don't perform fast enough to do frame generation.
 
Grimlakin said:
It's possible based on efficiency of code. Remember those Tensor cores or general compute cores on the Nvidia cards are in effect programmable processors able to do all sorts of code calls. One of the reasons these cards (well the 3000 series) were so good at mining. So Nvidia COULD... but I doubt they will. they tend to abandon their older generational cards pretty quick.
Click to expand...
I'm not aware of the tensor cores being used for mining.
 
Peter_Brosdahl said:
Brent mentioned this in his first RTX 4090 Founders Edition review, and a bit more detail in general regarding all the new stuff with the 40 series which I strongly recommend for a read or re-read as I've done on multiple occasions. The short end is even though Ampere is capable of it, Ada is optimized for it and it's unlikely even the best code could ever get even a 3090 Ti to compare to a 4090 and so on.

https://www.thefpsreview.com/2022/10/11/nvidia-geforce-rtx-4090-founders-edition-review/
Click to expand...
Brent_Justice said:
Negative, all RTX GPUs of every series have Optical Flow Accelerators via the Tensor Cores.

The difference is simply that the RTX 40 series is much faster and more accurate.
Click to expand...

Yeah it was a good idea to go back and re-read that, cuz I definitely didn't remember any of that. From the article:
Brent_Justice said:
This is very important to know, the Optical Flow Engine (OFA) was present in the last generation, Ampere, which is not what is new here. The ability to do Optical Flow Estimation was already present in the last generation hardware’s Tensor Cores. What’s new here, is the fact that Ada Lovelace is simply much faster at it, and more accurate. It is this performance boost of the Optical Flow Acceleration that is allowing Ada Lovelace to do Frame Generation. Technically, it could be done in the previous generation, it just might not lead to an actual improvement in the gameplay experience and bad image quality.
Click to expand...
 
" it just might not lead to an actual improvement in the gameplay experience and bad image quality."

This made me chuckle. I know it's understood to be.. "And introduce bad image quality" but as is... lol.
 
Stoly said:
If I'm not mistaken DLSS3=DLSS2+Framegeneration (only on RTX40), but DLSS3.5 = DLSS2+AI Denoising on pre RTX40 but also = DLSS2+Framegeneration+AI Denoising on RTX40 (and up?).

There have been rumors that frame generation could be coming to RTX30, but I don't think so.
Click to expand...
What a clusterf%@k
 
Brian_B said:
What a clusterf%@k
Click to expand...
I totally agree.

On one hand PC building is as simplistic as it's ever been. On the other hand, if they want the most graphical features for a gaming GPU the easiest way to explain it to a consumer is to tell them to shoot for a mid-high tier NV card (my apologies to AMD fans whom I do respect). I will say that Intel and AMD are making strides but despite being proprietary, NV is putting the extra hardware in their GPUs for added performance. I firmly believe that if Intel/AMD want to gain more, or even take the lead, with non-proprietary solutions they must continue to improve them but also beef up their hardware. It's the one way really.
 
You must log in or register to reply here.
Become a Patron!
Back
Top