AMD has released the source code for FSR 2.0 (FidelityFX Super Resolution), which means that any developer can now use the frame rate boosting technology in their games.
AMD's FSR 2.0 is the company's rival to Nvidia's DLSS, and that's clearly good news for running more games with the technology. The small caveat here is that Team Red has released all the materials (opens in a new tab) needed to work with DX12 and Vulkan games, but not DX11 (if you want to go that route, you'll need to contact AMD directly, as reported by Tom's Hardware(Opens in a new tab).
Also, support for Unreal Engine 4.26/4.27 (and UE5, for that matter) is coming very soon as a plug-in, promises AMD.
AMD also gave us an idea of how long it would take for developers to get FSR 2.0 into their games, this time varies obviously, but if a title already supports DLSS 2.0 it might only take a few days to roll out. worked. Similarly, it will be a quick process for those using the Unreal Engine plugin, unsurprisingly.
For some games, FSR 2.0 support could be a considerably longer (and windier) road, and AMD put the longest delay in its estimates at four weeks or more.
Analysis: The proof is in the premium pudding
Interestingly, along with this source code release, AMD took the opportunity to throw some criticism at Nvidia (and Intel XeSS, which, like DLSS, is powered by AI).
As you may know, with version 2.0, FSR is now very similar to DLSS, mainly because AMD decided to use time scaling, which is how Nvidia weaves its magic out of increased frame rates.
FSR 1.0 used spatial scaling, and there's a big difference in going temporal with FSR 2.0, as the former only accesses data related to the current frame in play, whereas with space, earlier frames are brought into play. . And this gives better quality results when it comes to the upscaled image (upscaling is how these technologies improve frame rates - in a nutshell, letting the GPU run at a lower resolution and then adjusting it to a higher resolution). target resolution, instead of running in that native resolution).
Now, Nvidia will indicate that its machine learning (AI) skills are in the mix with the timeline to achieve even better results, but AMD claims in its GPUOpen article that the introduction of AI is simply not necessary to get an improved picture. of good quality. . In fact, AMD says that machine learning is often just used to combine previous frames to get the scaled image, rather than recognizing objects in the actual scene, so Team Red is basically downplaying the importance of adding the power of AI.
We certainly can't take that argument at face value, and Nvidia claims that its AI routines do a lot more work in terms of producing a better, improved final image.
Either way, and what goes on under the hood with this technology is a very complex question, it's pretty telling to see AMD go on the offensive like this. And also, when you look at the results of FSR 2.0 compared to DLSS 2.0, the image quality is very similar. The proof is in the pudding, as they say, and the scaling built into supported games so far shows that FSR 2.0 is giving Nvidia a good run for its money (certainly going past Deathloop and God of War, as tested by Tom's Hardware).
Note that FSR 1.0 and 2.0 can be used together in a game if the developer wishes, giving the player a choice of one or the other, and this is important if the player in question does not have a good enough GPU for FSR 2.0 (which has more stringent hardware requirements). This comes with the obvious caveat that the quality of FSR 1.0 results is lower, but it's still nice to have an option. Hitman 3 is an example of a game that supports FSR 1.0 and 2.0.
AMD's openness around FSR and coverage of a wider range of base and different graphics cards, including Nvidia models, is one of the biggest strengths of its frame rate boost solution compared to DLSS, which requires specifically an Nvidia RTX graphics card.
Today's best graphics card deals