From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 109955] amdgpu [RX Vega 64] system freeze while gaming Date: Sun, 17 Nov 2019 17:13:10 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1074173369==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [131.252.210.165]) by gabe.freedesktop.org (Postfix) with ESMTP id 4CAE76E2DC for ; Sun, 17 Nov 2019 17:13:11 +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 --===============1074173369== Content-Type: multipart/alternative; boundary="15740107913.1D47AD9.24932" Content-Transfer-Encoding: 7bit --15740107913.1D47AD9.24932 Date: Sun, 17 Nov 2019 17:13:11 +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=3D109955 --- Comment #136 from haro41@gmx.de --- Thank you for testing and reporting back. I think the crashes are caused by voltage drops, followed by a hardware failure. That would explain the many different kernel logs too, because from the dri= vers pow, it is randomly. If vsync is enabled, mclk level is switched at least twice per frame (down/= up). And in some cases i have seen more switches inside a frame.=20 I am not sure, if this fast memory clock level switching, multiple times du= ring a frame really useful? It saves not much power, but makes the system instab= le, apparently. I don't think this is wanted behavior, it looks more like a firmware bug, i= mo. Maybe an opensource driver developer can help us to understand? --=20 You are receiving this mail because: You are the assignee for the bug.= --15740107913.1D47AD9.24932 Date: Sun, 17 Nov 2019 17:13:11 +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

Comm= ent # 136 on bug 10995= 5 from haro41@gmx.de 
Thank you for testing and reporting back.

I think the crashes are caused by voltage drops, followed by a hardware
failure.
That would explain the many different kernel logs too, because from the dri=
vers
pow, it is randomly.

If vsync is enabled, mclk level is switched at least twice per frame (down/=
up).
And in some cases i have seen more switches inside a frame.=20

I am not sure, if this fast memory clock level switching, multiple times du=
ring
a frame really useful? It saves not much power, but makes the system instab=
le,
apparently.

I don't think this is wanted behavior, it looks more like a firmware bug, i=
mo.

Maybe an opensource driver developer can help us to understand?

You are receiving this mail because:
  • You are the assignee for the bug.
= --15740107913.1D47AD9.24932-- --===============1074173369== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVs --===============1074173369==--