Announcement

Collapse
No announcement yet.

Many Linux Desktop 2D Benchmarks Of NVIDIA vs. AMD Drivers

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    If those benches really matters, all are fine only if there is not some worse extremes that is what people should looking for, but yeah there wasn't nearly any.

    Not that i care about those benchmarks at all, it does not use my font setup and does not use my gtk theme which are all mostly faster then those numbers even on my Kabini APU both with radeon and with fglrx .

    Most of those benchs are probably unaccelerated cases and just use more CPU
    Last edited by dungeon; 17 January 2015, 08:05 PM.

    Comment


    • #12
      Originally posted by duby229 View Post
      Assuming your guess is correct, what can be done to force the GPU clock up that wouldn't interfere with benchmark results?
      Well, you could turn off DPM and force it to use the high power profile, if you wanted.

      But that would just be less realistic, as real desktop apps are going to result in the GPU being downclocked during normal use just like you're seeing here.

      I guess you could see if just running glxgears in the background helped. Again, that's probably just going to result in less realistic scores if it goes any higher.
      Last edited by smitty3268; 17 January 2015, 11:37 PM.

      Comment


      • #13
        Originally posted by smitty3268 View Post
        Well, you could turn off DPM and force it to use the high power profile, if you wanted.

        But that would just be less realistic, as real desktop apps are going to result in the GPU being downclocked during normal use just like you're seeing here.

        I guess you could see if just running glxgears in the background helped. Again, that's probably just going to result in less realistic scores if it goes any higher.
        Yeah, I guess you're right. Assuming the benches are supposed to represent actual usage. Which is what I prefer to see.

        On the other hand, assuming the benches are supposed to represent maximum performance, forcing the clock up with DPM might be interesting to see.

        Comment


        • #14
          Hmmm...

          GeForce GTX560, nvidia-drivers-346.22

          Code:
          GtkPerf 0.40 - Starting testing: Sun Jan 18 11:05:45 2015
          
          GtkEntry - time:  0.02
          GtkComboBox - time:  0.34
          GtkComboBoxEntry - time:  0.25
          GtkSpinButton - time:  0.03
          GtkProgressBar - time:  0.02
          GtkToggleButton - time:  0.03
          GtkCheckButton - time:  0.03
          GtkRadioButton - time:  0.04
          GtkTextView - Add text - time:  0.13
          GtkTextView - Scroll - time:  0.06
          GtkDrawingArea - Lines - time:  0.25
          GtkDrawingArea - Circles - time:  0.33
          GtkDrawingArea - Text - time:  0.10
          GtkDrawingArea - Pixbufs - time:  0.03
           --- 
          Total time:  1.65
          
          Quitting..

          Comment

          Working...
          X