AMD FidelityFX Super Resolution 2.0 Debuts

[phoronix]

Phoronix: AMD FidelityFX Super Resolution 2.0 Debuts

Last year AMD announced FidelityFX Super Resolution for high performance, spatial upscaling for video games across platforms. Today ahead of GDC week AMD announced FidelityFX Super Resolution 2.0...

https://www.phoronix.com/scan.php?page=news_item&px=AMD-FidelityFX-Super-Res-2.0

[TNZfr]

Hi,
Around FSR, I have a little thing to say about RSR :

• I run a KDE Neon distro on a Ryzen 9 5950x / Radeon rx5700xt with Linux 5.16.15 & Mesa 22.0
• My desktop session is under wayland.
• I level up the desktop zoom to 125%. The resolution used by apps is now 3072x1720 instead of 4K.

This « zoomed » resolution is used by Vulkan and OpenGL games ... and output image are in 4K (monitor OSD 3840x2160@60 Hz). The most impressive are the FPS on my RX5700XT. With « Shadow of the tomb raider » benchmark (Steam linux native), I have a 44 - 45 FPS in 4K resolution ... and 66 FPS with the « zoomed » resolution.

I'm using this setting since KDE Plasma 5.24.0

So I wonder about RSR in GNU/Linux distros because what I describe seems to be similar ... maybe a subject for a phoronix test ?

[jeoshua]

But when is RSR going to find its way into the amdgpu driver stack? This is what I personally want to know.

[aufkrawall]

Remember oiaohm stating here that temporal approaches had no future? Just mentioning it for the lulz...
If this is can compete with good TAA(U) solutions found in some games, it would be nice progress to have this in a growing number of titles. Unlike FSR 1.0, which was just a step backwards. Really hope AMD can deliver this time.

[Jabberwocky]

I'm really happy that AMD is using GPU compute and not AI in runtime. I am not against the use of AI cores but seeking a vendor neutral implementation.

Here's a video preview by AMD: https://www.youtube.com/watch?v=oKD98lTqilQ

𝙰̷𝚌̷𝚌̷𝚘̷𝚛̷𝚍̷𝚒̷𝚗̷𝚐̷ ̷𝚝̷𝚘̷ ̷𝚑̷𝚊̷𝚛̷𝚍̷𝚠̷𝚊̷𝚛̷𝚎̷ ̷𝚞̷𝚗̷𝚋̷𝚘̷𝚡̷𝚎̷𝚍̷ ̷𝙵̷𝚂̷𝚁̷ ̷𝟸̷.̷𝟶̷ ̷𝚒̷𝚜̷ ̷𝚕̷𝚒̷𝚖̷𝚒̷𝚝̷𝚎̷𝚍̷ ̷𝚝̷𝚘̷ ̷𝙽̷𝚊̷𝚟̷𝚒̷ ̷𝙶̷𝙿̷𝚄̷𝚜̷ https://www.youtube.com/watch?v=ErfOEj4CVi0

[aufkrawall]

According to hardware unboxed FSR 2.0 is limited to Navi GPUs: https://www.youtube.com/watch?v=ErfOEj4CVi0

I didn't watch the video, but I don't think that statement is correct for FSR 2.0, but is for new "RSR" feature of new AMD Windows driver (which is just dull FSR 1.0 integrated in to the driver like Nvidia did with dull NIS).

[Jabberwocky]

I didn't watch the video, but I don't think that statement is correct for FSR 2.0, but is for new "RSR" feature of new AMD Windows driver (which is just dull FSR 1.0 integrated in to the driver like Nvidia did with dull NIS).

You are correct. It's about RSR not FSR. I mixed that up.

[linuxgeex]

Sadly if you watch the linked demo on Youtube you can see there's a 1 frame input lag on the FSR 2.0 side of the image, which equates to an extra 16ms input lag when you're playing games. That will be OK for RPG games but it will be terrible for platformers, shmups and FPS.

[aufkrawall]

Sadly if you watch the linked demo on Youtube you can see there's a 1 frame input lag on the FSR 2.0 side of the image, which equates to an extra 16ms input lag when you're playing games. That will be OK for RPG games but it will be terrible for platformers, shmups and FPS.

You really can't make that assumption by noticing a slight delay in a video. FSR 2.0 is normal post processing like any other TAA, it shouldn't introduce lag.

[jeoshua]

Sadly if you watch the linked demo on Youtube you can see there's a 1 frame input lag on the FSR 2.0 side of the image, which equates to an extra 16ms input lag when you're playing games. That will be OK for RPG games but it will be terrible for platformers, shmups and FPS.

That's not a given. There's no mechanical reason that should be the case, as information can be taken from last frame, and also frame rates vary so if you're running 105 fps that would only translate to 1/105 sec or ~9.5 ms.

Also, in that video there were more differences than just a frame, head bobbing up and down at different rates. The two images weren't mathematically the same so you can't draw any conclusions from them of this nature.