From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 110781] Radeon: heavy r300 performance drop regression between 11.x and 19.x Date: Fri, 07 Jun 2019 06:36:47 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0323557509==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [131.252.210.165]) by gabe.freedesktop.org (Postfix) with ESMTP id 25DE989A1A for ; Fri, 7 Jun 2019 06:36:47 +0000 (UTC) In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============0323557509== Content-Type: multipart/alternative; boundary="15598894072.610446.21680" Content-Transfer-Encoding: 7bit --15598894072.610446.21680 Date: Fri, 7 Jun 2019 06:36:47 +0000 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated https://bugs.freedesktop.org/show_bug.cgi?id=3D110781 --- Comment #46 from Richard Thier --- 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 fe= el 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 pat= ch in place is much harder to do by naked eye. --=20 You are receiving this mail because: You are the assignee for the bug.= --15598894072.610446.21680 Date: Fri, 7 Jun 2019 06:36:47 +0000 MIME-Version: 1.0 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated

Comme= nt # 46 on bug 11078= 1 from = Richard Thier 
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" witho=
ut the patch
in place is much harder to do by naked eye.

You are receiving this mail because:
  • You are the assignee for the bug.
= --15598894072.610446.21680-- --===============0323557509== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVs --===============0323557509==--