<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body><table border="1" cellspacing="0" cellpadding="8">
        <tr>
          <th>Bug ID</th>
          <td><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - Low performance after suspend on RX 480"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=97362">97362</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Low performance after suspend on RX 480
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>DRI
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>unspecified
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>Other
          </td>
        </tr>

        <tr>
          <th>OS</th>
          <td>All
          </td>
        </tr>

        <tr>
          <th>Status</th>
          <td>NEW
          </td>
        </tr>

        <tr>
          <th>Severity</th>
          <td>normal
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>medium
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>DRM/AMDgpu
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>dri-devel@lists.freedesktop.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>haagch@frickel.club
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Created <span class=""><a href="attachment.cgi?id=125811" name="attach_125811" title="dmesg">attachment 125811</a> <a href="attachment.cgi?id=125811&action=edit" title="dmesg">[details]</a></span>
dmesg

01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI]
Ellesmere [Polaris10] (rev c7)

Tried on vanilla Linux 4.7 and 4.8-rc2 with the async pageflip commit reverted.

I'm testing with a very simple directx9 application (without nine) because the
impact is extremely obvious with wine:
<a href="http://www.codesampler.com/dx9src/dx9src_1.htm#dx9_initialization">http://www.codesampler.com/dx9src/dx9src_1.htm#dx9_initialization</a>

Before suspending it runs with 5000+ FPS, after suspending it runs with <1000.
Also, if you keep the mouse pointer over the window moving, it will have a very
small performance drop before suspending and a huuuge performance drop after
suspending.

I looked at the powerplay values in sysfs while that application is running in
wine and before suspend,
pcie is
0: 2.5GB, x8 
1: 8.0GB, x16 *
and sclk is
0: 300Mhz 
1: 608Mhz 
2: 910Mhz 
3: 1077Mhz 
4: 1145Mhz 
5: 1191Mhz 
6: 1236Mhz 
7: 1288Mhz *

after suspend it's
pcie
0: 2.5GB, x8 *
1: 8.0GB, x16 
and sclk
0: 300Mhz 
1: 608Mhz *
2: 910Mhz 
3: 1077Mhz 
4: 1145Mhz 
5: 1191Mhz 
6: 1236Mhz 
7: 1288Mhz 


mclk is
0: 300Mhz 
1: 2000Mhz *
in both cases.

I then tried
echo high > /sys/class/drm/card0/device/power_dpm_force_performance_level
and the sclk clock goes to max and pcie goes to 16x again, but the performance
of the application does NOT increase so it looks like the low clocks are a
symptom of whatever causes low performance.

dmesg from 4.8-rc2 attached, shows some errors:

[  574.369317] 
                failed to send message 5e ret is 0 


[  574.369317] [drm:amdgpu_vce_ring_test_ring [amdgpu]] *ERROR* amdgpu: ring 12
test failed
[  574.369317] [drm:amdgpu_resume [amdgpu]] *ERROR* resume of IP block
<vce_v3_0> failed -110
[  574.369317] [drm:amdgpu_resume_kms [amdgpu]] *ERROR* amdgpu_resume failed
(-110).</pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are the assignee for the bug.</li>
      </ul>
    </body>
</html>