Honestly man I'm not looking for a fight, and that I'm so critical of AMD sometimes is because I know they can do better. I have an Nvidia GPU out of chance, speaking for myself I've always had a thing for Radeon cards - but so far AMD hasn't given me reasons to celebrate. Seems like they just keep self owning like that.
The statement towards AMD fans wasn't explicitly directed at you, sorry if it came out that way: but it's a general trend I see. AMD can do better. I know it, I've seen it first hand, trust me on this.
The easiest way to spot DLSS v. FSR is foliage and fire renditions. FSR will always be worse off. XeSS is still new. Cyberpunk is like the only implementation of XeSS 1.1 that I know of, but more are coming, and the criticisms leveled at FSR are consistent through a large variety of games. Good enough as it may be for some people, when options are available it's the last thing I'm looking at.
The way AMD does business right now, it's pretty clear AMD would likely be just as anti-consumer if they were in Nvidia's position. Given the state of the GPU market and how AMD and Nvidia keep prices high, it's not even guaranteed that a more competitive AMD would bring prices down or bring larger jumps in performance. It's a sad remark on the state of the GPU market, which is essentially a duopoly.
In regards to XeSS, here is an article on it's Death Stranding implementation:
https://www.techpowerup.com/review/...tor-s-cut-xess-vs-dlss-vs-fsr-2-0-comparison/
I should note, TechPowerUp did not use an Intel card and thus did not get XMX acceleration. I looked around to see if I could find one but only found TechSpot's article also testing the non-XMX as well.
From the above article:
"Speaking of XeSS, compared to DLSS and FSR 2.0, the XeSS render quality in terms of overall image detail is comparable to what DLSS and FSR 2.0 can output, but with some differences in temporal stability. One of the most noticeable differences in image quality between XeSS, DLSS and FSR 2.0 is how XeSS deals with ghosting. XeSS has noticeable ghosting issues and black trails on the flying chyral crystal particles and flying cryptobiotes similar to what DLSS 2.1 had in the past. On the DLSS side, this issue was fixed with the updates to the DLSS render pipeline, and no doubt, it can be fixed in Xess too. What's also important to note is that we are testing XeSS with an RTX GPU using the "standard" kernel instead of the Intel Arc GPU kernel, which uses the XMX engines and an advanced XeSS upscaling model, which may affect our image quality results.
Interestingly, when using XeSS, there are some major differences in performance gains, compared to DLSS or FSR 2.0, which essentially had equal or very similar performance gains in most games. As we are testing XeSS with an RTX 3060 GPU, which does not have the XMX instruction set, designed to accelerate XeSS workloads on Intel's Arc GPUs, the performance gains are less than what we can expect on Arc GPUs, so keep that in mind. That said, the actual performance increase difference between XeSS and DLSS or FSR 2.0 is about 13% at 4K Quality mode, in favor of DLSS or FSR 2.0. However, compared to native 4K resolution, XeSS manages to deliver up to 25% more performance while using the DP4a instruction set that's compatible with all GPU architectures, which is still a quite decent performance uplift. "
There's also a shadow of the tomb raider article on it as well, again non-XMX:
https://www.techpowerup.com/review/shadow-of-the-tomb-raider-xess-vs-dlss/
As you pointed out, these are not the latest versions of XeSS and in general there just isn't enough of a sample size to tell whether these are representative of the whole.
Not that Ultra and High, or even Medium are so much different these days anyway.
