AMD FSR 2.0 source code is out – and so are the knives for Nvidia DLSS
AMD has made the source code of FSR 2.0 (FidelityFX Super Resolution) public, which means any developer can now use the frame rate boosting technology in their games.
AMD’s FSR 2.0 is the firm’s rival to Nvidia DLSS, and it’s clearly good news in terms of getting more games up and running with the technology. The little caveat here is that Team Red has taken out all the ingredients. (opens in new tab) Needs 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 Tom’s Hardware) (opens in new tab) Report).
Also, support for Unreal Engine 4.26/4.27 (and UE5, for that matter) is coming soon as a plug-in, as AMD promises.
AMD also told us that the amount of time it may take for developers to incorporate FSR 2.0 into their games varies — obviously — but if a title already supports DLSS 2.0, it should be implemented. It may only take a few days to do. Likewise, for those using the Unreal Engine plug-in, this will be a quick process, as you might expect.
For some games, bringing in support for FSR 2.0 could be quite a long (and winding) road, with AMD putting the longest time frame in its estimates at more than four weeks.
Analysis: The proof is in the advanced pudding
Interestingly, with this source code release, AMD took the opportunity to fire up some flak at Nvidia (and Intel XESS, for that matter, which is DLSS AI-powered).
As you may know, with version 2.0, FSR is now a good deal similar to DLSS, mainly because AMD has made the move to use temporary upscaling, which is how Nvidia weaves its frame rate boosting magic.
FSR 1.0 employed spatial upscaling, and with FSR 2.0 there is a major difference in switching to temporal, as the former only accesses data related to the current frame in-game – whereas with spatial, the previous frame is accessed in-game. is brought. And it makes for better quality results when it comes to the upscaled image (upscaling is how these technologies improve frame rates – in simple words, by allowing the GPU to run a lower resolution, and then running it instead of up to the target resolution. in that native res).
Now, Nvidia will point to temporary upscaling as well as having its machine learning (AI) chops in the mix to get better results, but AMD claims in its GPUOpen article that the introduction of AI is just to get a good one. did not need to. Enhanced image quality. In fact, AMD argues that machine learning is often employed in conjunction with just the previous frame to obtain an enhanced image, as opposed to actually recognizing objects in the actual scene, and so Team Red is basically a team of AI. Undermining the importance of adding to power.
We certainly can’t take that argument at face value, and Nvidia claims its AI routines are doing a lot of the heavy lifting in terms of producing a better final enhanced image.
Whatever the case – and what’s happening under the bonnet with this technology is a very complex matter – to see AMD getting aggressive like this is saying a lot. And besides, when you look at the results for FSR 2.0 compared to DLSS 2.0, it’s a very close call for image quality. The proof is in the pudding, as they say, and the upscaling baked into the supported games so far gives FSR 2.0 a decent run for its money to Nvidia (certainly by Deathloop and God of War, as in Tom’s). hardware has been tested).
Note that both FSR 1.0 and 2.0 can be used together in a game if the developer wishes, giving the player the option of either – and this is important if the gamer in question does not have a sufficient GPU for FSR 2.0 ( which has more stringent hardware requirements). This comes with the clear caveat that the quality of the FSR 1.0 results is inferior, but it is a good choice nonetheless. Hitman 3 is an example of a game that is supporting both FSR 1.0 and 2.0.
AMD’s openness around FSR and ensuring that it covers a wide range of bases and different graphics cards – including Nvidia models – are the biggest strengths of its frame rate boosting solution compared to DLSS, for which Specifically requires an Nvidia RTX graphics card.