So here in Germany the NVIDIA editors day just ended. The media has been briefed on the latest tech. While most of this all is still under embargo, there are some things we can share. First off, after the announcements last Monday, a lot of people have been curious about the actual ‘normal’ game perf increases over last gen.
NVIDIA just released some slides on that which we want to share with you.
“Powered by Turing’s Tensor Cores, which perform lightning-fast deep neural network processing, GeForce RTX GPUs also support Deep Learning Super-Sampling (DLSS), a technology that applies deep learning and AI to rendering techniques, resulting in crisp, smooth edges on rendered objects in games.”
Basically, from what we have seen – if you compare 1:1 say a GTX 1080 to RTX 2080 and so forwards, you may expect 1.2x to 1.5x performance increases from generation to generation thanks to the new architectural changes made in the rendering pipeline. Of course, the final results as measured by editors and reviewers in the end matter. But for now, this is what NVIDIA released, also look a bit closer at the lower chart for some FPS numbers for the GTX 2080:
Deep Learning Super Sampling
Performance measurements will be a bit different this round though as NVIDIA is introducing DLSS, a supersampling antialiasing methodology that runs in AI directly over the Tensor cores after the image frame has been finished. The new technology looks promising and will offer great performance increases as you will not apply to say TAA over the rendering engine, DLSS was running over the tensor cores, AI AA.
We’ve seen some game demos of the same game running on a 1080 Ti and the other on the 2080 Ti, the performance was often doubled with close to the same image quality. DLSS is short for High-Quality Motion Image generation, Deep Learning Super Sampling. And it looked quite impressive. DLSS is not game specific, and in the future should work on most game titles.
