• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Ryzen's poor performance with Nvidia GPU's. Foul play? Did Nvidia know?

Page 9 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Did Nvidia know about the Ryzen performance issue and choose not to fix it?

  • Yes, Nvidia has guilt regarding this issue. They wanted to damage AMD.

    Votes: 45 38.8%
  • No, Nvidia is innocent regarding this issue. They simply didn't know or its out of their hands.

    Votes: 71 61.2%

  • Total voters
    116
So I had to push 2732x1536 DSR to really choke the GPU for CPU utilization to drop.
PB7Ecyd.jpg
So, after correcting my initial position, I think it is reasonable to conclude that unless you are absolutely choking your GPU with crazy high resolutions, it won't affect CPU utilization that much when you change between different resolutions.

Yeah, same as in CS:GO.
 
Yeah, same as in CS:GO.
Though I must say that this particular result is mostly academic as unless you're standing still, CPU usage goes up to 100% anyway. And as you said before, if there is little variance in frame times, and not much frame to frame difference, draw calls are reduced and hence CPU utilization would fall as well, which is what this shows, in line with what is expected.
 
No, it isn't. Maybe in DX9 mode but not in DX11. It was always a mix between 60:40 to 70:30 during the times I took the screenshots, roughly speaking.

Which both add up to 100% of a single core. You're witnessing thread migration, not a multi-threaded game.
 
Which both add up to 100% of a single core. You're witnessing thread migration, not a multi-threaded game.
It added up to a little over 100% in that particular scene, and it definitely goes up to more than that when I'm in more graphically demanding scenes. So yeah, no thread migration. The game is multi-threaded, at least on two cores.
 
No, it isn't. Maybe in DX9 mode but not in DX11. It was always a mix between 60:40 to 70:30 during the times I took the screenshots, roughly speaking.
You do understand that with Windows beautiful scheduling, it means that it was actually loading a single thread to a limit but was shuffling that load between 2 cores in the process? And yes, it adds up a little over 100% but aux threads are aux.
 
You do understand that with Windows beautiful scheduling, it means that it was actually loading a single thread to a limit but was shuffling that load between 2 cores in the process? And yes, it adds up a little over 100% but aux threads are aux.
You do understand that I chose this particular scene because it was the least taxing on both the CPU and GPU so that I could push the resolution to see its effect on the utilizations, right? Like how testing at 800x600 shows that the GPU has room to spare and can actually go to higher utilization when I increased the resolution to 1280x960?

And I said that the the game is multi-threaded - the moment I go to the next area which is an outdoors and hence more graphically demanding, both the CPU and GPU utilizations shoot up and I get better CPU utilization across both cores.
 
You do understand that I chose this particular scene because it was the least taxing on both the CPU and GPU so that I could push the resolution to see its effect on the utilizations, right?
I guess i do, but i also had interpret it as your argument that CPU utilization is not actually decreasing with resolution.
 
Back
Top