10-Way NVIDIA GeForce Linux Vulkan Performance For F1 2017

[kaprikawn]

I'm more interested in the AMD numbers, but this is promising stuff. I've recently purchased two full priced new releases, and the price is a little steep, so it'll really hit the wallet to get his. But I'm definitely going to do it if only to support Feral.

Another call for NOT doing Windows benchmarks. If you want Windows benchmarks :

http://lmgtfy.com/?q=F1+2017+PC+Benchmarks

[bug77]

So basically the recommended configuration can run this at 4k, ultra settings with AA. On the other hand, the recommended configuration does include a GTX 1070 which is anything but cheap.

[prazola]

Why do you think Nvidia underperform in Vulkan? They don't. AMD's Vulkan performance may be better in the well optimized windows driver but...

on Linux Nvidia Vulkan is easily faster than AMD. AMD are the ones who underperform on Linux Vulkan. It's something nobody expected after all the promotion regarding thinner driver layers, using mantle as a starting point etc... But sadly it happened.

Is it hard for you to realize that at 1080p there's no gain in performance from gtx1070 to gtx1080ti in linux? You can clearly spot the difference with guru3d benchs (DX11 ofc). Nvdia gets more performance with DX11 than with vulkan.

[prazola]

1920x1080 Ultra quality
GTX 1060 Linux: 117 fps, Windows: 76 fps
GTX 1070 Linux: 142 fps, Windows: 110 fps

What is the problem??

You already got answered, but look also at gtx1080ti.

[oooverclocker]

I'm so curious about the RADV-results, especially those of the Vega cards...

[bug77]

No CPU load graphs, no perf/W... I know day 1 reviews are a thing, but I hope those are still incoming.

[humbug]

GOL compared windows vs Linux and sadly it's looking really bad. On a 980ti Linux Vulkan performance is 30-40% lower than windows DX11
https://www.gamingonlinux.com/articl...t-report.10652

Ouch

Would be very interesting to get a Feral developer technical comment on the reason for the wide gap. Michael?
Would be a lot less work than bench-marking 34 GPUs

[md1032]

It would be interesting to see a comparison with 387.22 because it has "* Improved performance of fullscreen Vulkan applications using X11 swapchains."

[Michael]

It would be interesting to see a comparison with 387.22 because it has "* Improved performance of fullscreen Vulkan applications using X11 swapchains."

387 currently has regressions with this game, which is why it wasn't used.

[chimpy]

Usually feral games get better performance over time, so the performance for this game at launch is actually pretty good.