<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body>
      <p>
        <div>
            <b><a class="bz_bug_link 
          bz_status_REOPENED "
   title="REOPENED - performance regression (3x slower) running glamor with PutImage workload (radeonsi)"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=105171#c19">Comment # 19</a>
              on <a class="bz_bug_link 
          bz_status_REOPENED "
   title="REOPENED - performance regression (3x slower) running glamor with PutImage workload (radeonsi)"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=105171">bug 105171</a>
              from <span class="vcard"><a class="email" href="mailto:u9vata@gmail.com" title="Richard Thier <u9vata@gmail.com>"> <span class="fn">Richard Thier</span></a>
</span></b>
        <pre>Possibly related problem on r300 code paths:

<a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - Radeon: heavy r300 performance drop regression between 11.x and 19.x"
   href="show_bug.cgi?id=110781">https://bugs.freedesktop.org/show_bug.cgi?id=110781</a>
<a href="https://www.phoronix.com/forums/forum/linux-graphics-x-org-drivers/open-source-amd-linux/1099745-how-to-tell-if-a-driver-is-gallium-or-just-mesa-slow-renderng-with-radeon/page10">https://www.phoronix.com/forums/forum/linux-graphics-x-org-drivers/open-source-amd-linux/1099745-how-to-tell-if-a-driver-is-gallium-or-just-mesa-slow-renderng-with-radeon/page10</a>
<a href="https://bbs.archlinux32.org/viewtopic.php?pid=5973#p5973">https://bbs.archlinux32.org/viewtopic.php?pid=5973#p5973</a>

It took me a whole lot of time to analyse the source of the problem and this is
the commit that causes slowdown for me too.

For me it was really useful to do an strace before and after this commit and I
find the GEM_CREATE numbers rise from around 7-11 to about thousands when just
doing 10 seconds of glxgears which is clearly wrong and causes my slowdown.

Maybe would be useful to test if the problem is also related to GEM/TTL in this
case? Just informing you because I have found this earlier issue when googling
the commit hash...

prenex</pre>
        </div>
      </p>


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

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