Am I seeing things or does my AMD card run significantly more efficient on Linux?
I switched from Windows to Fedora last week and I'm monitoring the stats with Mangohud when playing games. I used to run HWinfo on 2nd monitor when using Windows 11.
I have 6800X ( default voltage) . The card maintains higher clocks at lower power most of the time. I've set the same OC as on Windows with a 2700MHz max clock and in games I'm sitting pinned at 2670MHz-2700MHz almost all the time in Linux when I don't hit power limit (312W) while on Windows the actual clock barely went over 2600MHz and card was almost always bouncing off of power limit resulting in massive clock drops to 2300-2400MHz. On Linux the drops go down just by like 100MHz-130MHz at most in the same scenarios.
Unfortunately I'd need to install Windows again and do proper testing to compare but I wonder if anyone else can confirm/deny this to me.
At least on idle I can confirm for a fact that the card uses less power, usually around 30-35W while on W11 was like 40-50W.
Need to confirm the fps, it could be using less power because it's receiving less work to do.
I agree, that's why I said I'd need to retest on W11 to confirm. I'm really going based on the clock vs power used behavior. The card consistently clocks higher within the same power budget on Linux.
I don't know how accurate the reported clock speeds from Mangohud are though.
IDK how big the performance vs Windows is exactly... FPS wise. All games seem to run really well and roughly in the same ball park.
The frame pacing on Linux is immaculate though. At least in the games I play and tried.
You need the number over time, and to confirm the same features are used, ie whatever Ray tracing or other effects.
This is hard to measure and confirm, could be more efficient, could be lower settings.
I applaud you investigating though!
It's really bumming me, I'll try to throw W11 back on a spare SSD if I'll get some more free time and test this.
I've spent quite a while benching and tinkering with the card and monitoring on Windows so seeing the monitoring results on Linux deviate this much from what I expected is interesting to me.
I need to think of some good games to try this on, games that offer results which don't deviate too much for simpler testing.