Quoting: Guestmy 6900 xt :huh::happy:

Impressive! :D

:woot: that's sick :grin:

Quoting: Guest

External Media: You need to be logged in to view this.

edit:
my 6900 xt :huh::happy:

damn !

Really need to update this I guess .

Here's my 6800XT

I've built a second workstation using Ryzen 9 5950X and ASUS TUF Gaming 3080Ti OC.

With no overclocking, it produces this when running Ubuntu MATE 21.04



I had a tinker and applied a modest system-wide overclock.

Ryzen 9 [email protected] base all core and DDR4@3600Mhz CL16 with tuned sub memory timings

• +120 Mhz GPU Clock Offset (1935 Mhz - 1950 Mhz)
• +1000 Mhz Memory Transfer Rate Offset (10500 Mhz or 21000 Mhz @ double data rate)
• +25W Power Limit (375W target)
• 100% Fan duty (all GPU fans)

NVIDIA Settings tweaks

• Force Composition Pipeline - Disabled
• OpenGL Image Settings - High Performance
• PowerMizer Preferred Mode - Prefer Maximum Performance

Last edited by Wimpress on 1 Aug 2021 at 11:33 am UTC

So what am I supposed to think of those results:





Is running the benchmark in 2K bad because it's not the native resolution?
Or is 2K-Extreme more demanding than 4K?
And if it's about GPU performance, shouldn't those results be close to each other?

Oh, just seen, that I still have v1.0 while you guys are using v1.1 of the benchmark......... Why is the download so slow? And when will they add vulkan support?

Quoting: peta77Or is 2K-Extreme more demanding than 4K?

The 2K extreme profile is pretty much one of the most GPU heavy things available. You might be able to set up a custom 4k on extreme for nice single digit fps.

Quoting: Ehvis

Quoting: peta77Or is 2K-Extreme more demanding than 4K?

The 2K extreme profile is pretty much one of the most GPU heavy things available. You might be able to set up a custom 4k on extreme for nice single digit fps.

Well, not really. If these would be the settings:



Then it's pretty much a solid 11! :tongue:

Updated Google sheet too. Hopefully i got everything right.

Updated the the OP top 50 pic too!

I am now listed twice on positions 36 and 37 in the pic.

Quoting: Guesthello all :smile: here is a comparison of my 6900 xt on linux vs windows i did:

External Media: You need to be logged in to view this.

very competitive. if my math is correct, a 7.13% difference in score. i wonder how the results would be if it was a clean vulkan vs vulkan.

9.33% difference with my math. To get percentages, you divide the smaller number by the larger and then move the decimal.

It's nice to see the comparison side by side like that. Thanks for sharing.

The smaller number is around 93% of the bigger one, so the difference is around 7%.

It’s also different depending on whether you’re counting the increase relative to the smaller number, or the decrease relative to the bigger one.

Those on OSS drivers might want to do a rerun that aint on the dev branch, just tried 21.3!

A couple of points more than my last result but nothing extraordinary.

BIOS-switch is set to "normal" mode AFAIR.

Last edited by crt0mega on 4 Jan 2022 at 5:14 pm UTC

This is my 6700XT, a good little performer.

RTX 3080, first random run without any tweaks:

First run with new graphics card (RX 6900 XT) Not planning to tweak it before new PSU arrives, my current 550W is very underpowered for that card.

Quoting: woox2k550W

:dizzy:

Thats risky !

i just need to edit the recording I did and uploaded it on Youtube but you can see all my other Benchmarks here.
https://www.youtube.com/playlist?list=PLnIYWF-c4CDZvfWizXwZ_33nXc16sMgj5

Very minor improvement, but still an improvement. Just set the GPU into high perf mode and maxed out fans. Obvously i also replaced my old PSU and now have Crosair RM1000X, that will power this card just fine!