Radeon Windows 10 vs. Linux RadeonSI/RADV Gaming Performance

[Exordium01]

Well we need more minimal FPS charts, because if is Windows performance average 100FPS and Linux 60fps its is still good, but not if minimal FPS value is under 30 FPS => games is stuttering.

Yep. My experience with an RX 470 is that you can't pick settings based on average frame rate because many if not most games I've tried frequently drop down to around 10 fps even if it averages 60+ fps. Unfortunately, average framerate is much more heavily impacted by graphical settings than minimum framerate, so you're stuck turning settings way down.

Until whatever causes that is addressed, gaming on Linux with an AMD GPU isn't going to be a very pleasant experience.

[Creak]

Only if the software is all fully-automated for PTS and/or there is a bunch of new subscribers.... so far this round of Windows 10 vs. Linux testing has proven to be a waste with minimal donations/new-subscribers not offsetting all the time spent on this round of testing, rather disappointed.

I understand that you need more subscribers, but what about the subscribers that are actually paying (like me) and would like to see this kind of benchmarks.
I've seen a lot of website going down because they were only aiming at newcomers only and not at their core members. It's your website after all, but I would advise you to be careful about this hunt for new subscribers, you might lose more that you think.

[Michael]

I understand that you need more subscribers, but what about the subscribers that are actually paying (like me) and would like to see this kind of benchmarks.
I've seen a lot of website going down because they were only aiming at newcomers only and not at their core members. It's your website after all, but I would advise you to be careful about this hunt for new subscribers, you might lose more that you think.

If there are like several premium members interested expressing interest in said test, I am more than happy as always to run said tests.

[oooverclocker]

My experience with an RX 470 is that you can't pick settings based on average frame rate because many if not most games I've tried frequently drop down to around 10 fps even if it averages 60+ fps.

From my experience with an RX 480 with Padoka PPA it already should have been fixed. Even Rocket League doesn't stutter during matches anymore. In which titles do you have issues?

[Exordium01]

From my experience with an RX 480 with Padoka PPA it already should have been fixed. Even Rocket League doesn't stutter during matches anymore. In which titles do you have issues?

Bioshock Infinite and XCOM 2. I don't have any other demanding games to try until the HITMAN port comes out (it came with the card). I'm using Padoka PPA with Ubuntu 16.10 kernel 4.8. It's not extended periods of poor performance, just a few slow frames pretty frequently.

[franglais125]

If there are like several premium members interested expressing interest in said test, I am more than happy as always to run said tests.

I'm definitely interested in the AMD graphics (closed or open source) Windows/Linux comparison. Nvidia, not so much.
So thanks a lot for this post!

[PadreAdamo]

I am not interested in nvidia tests at all. Zero. In addition I would like to see some AMD APU and FX tests.

[Aiua]

I understand that you need more subscribers, but what about the subscribers that are actually paying (like me) and would like to see this kind of benchmarks.
I've seen a lot of website going down because they were only aiming at newcomers only and not at their core members. It's your website after all, but I would advise you to be careful about this hunt for new subscribers, you might lose more that you think.

I share the sentiment. I'm sad for Michael if that didn't bring him a lot of new revenues, but as a subscriber I appreciate those articles, and that will positively influence my decision to renew when the time comes

[humbug]

Looking at these benchmarks we see games like civilization and Warhammer. Where the devs have written a DX12 backend, and then maintaining a separate openGL one for Linux, whether they do it themselves or outsource it. Why not go with vulkan and kill two birds with one stone? I'm sure they would prefer the codebases to be as similar as possible from windows to Linux.

[duby229]

Looking at these benchmarks we see games like civilization and Warhammer. Where the devs have written a DX12 backend, and then maintaining a separate openGL one for Linux, whether they do it themselves or outsource it. Why not go with vulkan and kill two birds with one stone? I'm sure they would prefer the codebases to be as similar as possible from windows to Linux.

That is the ideal situation that I think alot of us gamers are hoping for. I have the suspicion in the know devs already intuit what AMD's plans for open sourcing their Vulkan code is. I have to assume that Radv's very existence is evidence of that. Public understanding of it has been slower to get out then I would have liked though. A timeline would be cool. I assume porting companies already know through their contacts at AMD what the Vulkan plans for linux are too.

It's just a matter of time, but how much time I think is still not public knowledge yet.