Intel Releases XeSS 1.3, Improves FPS Across Presets with New Resolution Scaling, Improved Upscalers

[btarunr]

Intel on Wednesday released the XeSS 1.3 performance enhancement, which works with Intel Arc "Alchemist" discrete GPUs, and Intel Arc iGPUs powering the Core Ultra "Meteor Lake" processors. The new super sampling technology brings several under-the-hood improvements to the upscaler, which improves image quality at a given resolution. Intel leveraged this improved upscaler to rework the resolution-scale of each performance preset, thereby improving performance per preset; while also introducing new presets at both ends of the resolution scale. The company released the XeSS 1.3 SDK on GitHub, so developers can begin exploring the tech and implementing it on their games.

The XeSS 1.3 update is predicated on an improved upscaler. Intel says that it has updated the AI models with new optimizations, and additional pre-training, particularly with difficult to upscale elements (such as meshes, as in textures with a lot of alpha pixels). The updated upscaler offers better reconstruction of detail, better AA, less ghosting, and improved temporal stability. Intel then used this up change the resolution scale across all its presets as detailed in the table below. It introduced the new Ultra Performance preset that does a 3.0x resolution scale, something that didn't exist in the previous versions of XeSS. On the other end of the spectrum is Native AA, a mode that has zero upscaling, but just the full application of the upscaler as a varnish—this is essentially Intel's take on DLAA.



An increase in resolution scale implies that the game is being rendered at an even lower resolution, for the upscaler to work its magic with. The lower render resolution translates to performance improvements, which Intel presented in the tables above, for an Arc A750 discrete GPU, and a Core Ultra 7 155H mobile processor iGPU. Intel has internally tested XeSS 1.3 with a number of popular titles, at a given preset; and all its new presets (new resolution scales) with Cyberpunk 2077.



View at TechPowerUp Main Site

 

[claster17]

Intel must be really confident in their improved image quality to deviate from the somewhat standardized upscaling factor naming convention.
Looking forward to comparisons.

 

[vbq7qK68eyYAH4iR]

Going by Intel's own media material, the new XeSS 1.3 is slower than 1.2. The only way they got extra performance was by decreasing render resolution even further. When comparing old to new, at the same scaling factor, you get the below comparison. It's only XeSS 1.3's new 2.3x and 3.0x scaling that provides more performance.

1.2 Ultra Quality got 42 FPS, but 1.3 Ultra Quality Plus got 41 FPS
1.2 Quality got 50 FPS, but 1.3 Ultra Quality got 49 FPS
1.2 Balanced got 58 FPS, but 1.3 Quality got 57 FPS
1.2 Performance got 66 FPS, but 1.3 Balanced got 65 FPS.

 

[GoldenX]

Going by Intel's own media material, the new XeSS 1.3 is slower than 1.2. The only way they got extra performance was by decreasing render resolution even further. When comparing old to new, at the same scaling factor, you get the below comparison. It's only XeSS 1.3's new 2.3x and 3.0x scaling that provides more performance.

1.2 Ultra Quality got 42 FPS, but 1.3 Ultra Quality Plus got 41 FPS
1.2 Quality got 50 FPS, but 1.3 Ultra Quality got 49 FPS
1.2 Balanced got 58 FPS, but 1.3 Quality got 57 FPS
1.2 Performance got 66 FPS, but 1.3 Balanced got 65 FPS.

Meh, worth it for the quality improvement.
On hardware that can't run DLSS, it's a race to see what gets more adoption, FSR3.1 or this. Either would fix the distracting artifacts of their implementations.

Doing some testing for fun, running Cyberpunk on an i5 1240p laptop, no dGPU. You have to go down to 1280x720 + Performance/Ultra Performance to get 30 FPS, that's 240p gaming. Both FSR 3.0 (mod) and XeSS 1.2 look terrible that low

 

[arbiter]

Going by Intel's own media material, the new XeSS 1.3 is slower than 1.2. The only way they got extra performance was by decreasing render resolution even further. When comparing old to new, at the same scaling factor, you get the below comparison. It's only XeSS 1.3's new 2.3x and 3.0x scaling that provides more performance.

1.2 Ultra Quality got 42 FPS, but 1.3 Ultra Quality Plus got 41 FPS
1.2 Quality got 50 FPS, but 1.3 Ultra Quality got 49 FPS
1.2 Balanced got 58 FPS, but 1.3 Quality got 57 FPS
1.2 Performance got 66 FPS, but 1.3 Balanced got 65 FPS.

You are claiming slower when comparing a higher quality preset with a more performance preset?
"1.2 Ultra Quality got 42 FPS, but 1.3 Ultra Quality Plus got 41 FPS" you should compare Ultra Quality 1.2 to Ultra Quality 1.3 which is 42fps vs 49fps but you went with plus. same goes for every other comparison you made.

 

[HOkay]

This sounds like one good news, especially a native res XeSS AA mode! DLAA is by far my preferred of all these upscalers, at the worst performance of course, but it can look great in some games. I look forward to some in depth articles & comparisons!

 

[claster17]

You are claiming slower when comparing a higher quality preset with a more performance preset?

Is it really a higher quality preset if it's the same render resolution under a new name?

 

[roberto888]

You are claiming slower when comparing a higher quality preset with a more performance preset?
"1.2 Ultra Quality got 42 FPS, but 1.3 Ultra Quality Plus got 41 FPS" you should compare Ultra Quality 1.2 to Ultra Quality 1.3 which is 42fps vs 49fps but you went with plus. same goes for every other comparison you made.

You are exactly the people Intel try to fool with the new namings. 1.2 Ultra Quality scale is 1.3X while 1.3 Ultra Quality scale is 1.5X.

 

[MekiFoxx]

You are exactly the people Intel try to fool with the new namings. 1.2 Ultra Quality scale is 1.3X while 1.3 Ultra Quality scale is 1.5X.

The new super sampling technology brings several under-the-hood improvements to the upscaler, which improves image quality at a given resolution. Intel leveraged this improved upscaler to rework the resolution-scale of each performance preset, thereby improving performance per preset; while also introducing new presets at both ends of the resolution scale.

You either didn't read the article, or chose not to read this part specifically.

 

[bug]

You are exactly the people Intel try to fool with the new namings. 1.2 Ultra Quality scale is 1.3X while 1.3 Ultra Quality scale is 1.5X.

I think what Intel is trying to convey is the results of 1.2 using 1:1.3 scale can be matched by 1.3 using 1:1.5 scale.
That screenshot seems to hint it does even better. But it's a sample size of 1 so...

 

[Beginner Macro Device]

Okay, will test if this new 1.3 works on AMD. And how if yes.

 

[Denver]

They just changed the scale resolution factor to confuse and show greater gains. Intel acting according to what I expect from them... LoL

 

[Beginner Macro Device]

Okay, will test if this new 1.3 works on AMD. And how if yes.

No upscaling.

50% internal resolution, XeSS 1.2.

50% internal resolution, XeSS 1.3.

Overall, feels like a dozen minor improvements here and there with virtually zero performance penalty compared to older SDK. You WILL NOT be able to catch these differences on my screenshots, recordings, or whatnot, they're too subtle for it. Yet, no denying, it became better. Better enough for 50% internal resolution (1.3) to be at least on par with 58% internal resolution (1.2) in the Cyberpunk 2077 but still feel less jittery and shimmery. Not by much though.

Cool, I guess.

 

[AusWolf]

Why can't we just use the resolution multipliers instead of the stupid "ultra this" and "ultra that" naming?

 

[Beginner Macro Device]

Why can't we just use the resolution multipliers instead of the stupid "ultra this" and "ultra that" naming?

Average Joes resemble orcs from the WH40K: numbers greater than 3 are the forbidden knowledge for them. "57 percent? How much is this in actual gaming experience?"

 

[ShogoXT]

@ W1zzard Would you consider testing out this version of Xess using the FSR bridge mod? You can put it into various games that way.

I'm curious about it's "AI" claims that perhaps it would use NPU or AVX VNNI instruction assistance to aid with speed, but nothing in the documentation points to that. It seems similar to motion estimation tech that was GPU accelerated in video encoding tech years ago, PRE AI. Who knows though I can't seem to find much.

It would be nice to test it on CPUs fps that support VNNI with and without. Also Arc GPUs vs non using it. I have a lowly 3950x with a rx 6800 XT so I can't test AVX VNNI.

Ryzen 7000 and Alder Lake and newer vs older ones.

Edit: It would be disappointing if they simply labeled it AI for the tone mapping and motion estimation feature. That's pre AI tech. They were the ones who pushed for performance optimized ai if they don't include it, just change the scales this is doesn't look great.

 

[bug]

Why can't we just use the resolution multipliers instead of the stupid "ultra this" and "ultra that" naming?

Because, as you can see, what requires today 1:1.3 pixels, tomorrow can be done using just 1:1.5. Regardless, they can label setting anyway they want, at the end of the day you're still going to choose the one that looks good enough for your eyes. And it's probably not going to be the same one for all titles.

 

[AusWolf]

Average Joes resemble orcs from the WH40K: numbers greater than 3 are the forbidden knowledge for them. "57 percent? How much is this in actual gaming experience?"

Average Joes also think that enabling upscaling in Ultra Quality mode gives them better visuals than not enabling it. That's how deceptive modern gaming tech is.

Because, as you can see, what requires today 1:1.3 pixels, tomorrow can be done using just 1:1.5. Regardless, they can label setting anyway they want, at the end of the day you're still going to choose the one that looks good enough for your eyes. And it's probably not going to be the same one for all titles.

I'd rather not use any of it, if possible. When I do, I'd rather see the upscaling factor instead of some dumb, arbitrary name that Intel/Nvidia/AMD came up with. I'm a technical person, I like calling things what they are.

 

[Beginner Macro Device]

enabling upscaling in Ultra Quality mode gives them better visuals than not enabling it

In some games, it's true because native TAA works like hot garbage. It's a fairly limited list of titles though.

 

[AusWolf]

In some games, it's true because native TAA works like hot garbage. It's a fairly limited list of titles though.

That's not because upscaling gives you a better picture, but because in those games, enabling upscaling turns off TAA.

 

[HOkay]

That's not because upscaling gives you a better picture, but because in those games, enabling upscaling turns off TAA.

Agreed, but in those games, upscaling is the best visual experience, so it's better than the "native" presentation. It's just semantics though, & I rush you could just disable the built-in TAA!

 

[Nalga]

On My rig for some reason i have much more Shimmering on Ultra Quality than on performance. I check at 1440p and 4k with same result. Testing on Cyberpunk on 6800XT.