<html> <head> <base href="https://bugs.freedesktop.org/"> </head> <body> <div> <a class="bz_bug_link bz_status_NEW " title="NEW - Radeon: heavy r300 performance drop regression between 11.x and 19.x" href="https://bugs.freedesktop.org/show_bug.cgi?id=110781#c46">Comment # 46</a> on <a class="bz_bug_link bz_status_NEW " title="NEW - Radeon: heavy r300 performance drop regression between 11.x and 19.x" href="https://bugs.freedesktop.org/show_bug.cgi?id=110781">bug 110781</a> from <a class="email" href="mailto:u9vata@gmail.com" title="Richard Thier <u9vata@gmail.com>"> Richard Thier</a> <pre>In comparison this is the unpatched 19.x originally (10 sec): -> 12466 (any) ioctl calls -> 3111 DRM_IOCTL_RADEON_GEM_CREATE -> 3112 DRM_IOCTL_GEM_CLOSE ^^Sorry these values were bad, it is not this much and I don't know how I measured this back then but I cannot do it anymore. Actually it is not that easy to find the "more minor" issue, but I still feel it is there. The only way for finding it is to bisect in this way: -> bisect ... -> apply patches of Marek -> See if result has 7-8 CREATE calls or a bit more -> stash away patches -> bisect ... Only this way it is properly measurable because "measuring" without the patch in place is much harder to do by naked eye.</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are the assignee for the bug.</li> </ul> </body> </html>