[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20160617195754.GP3912@pd.tnic>
Date: Fri, 17 Jun 2016 21:57:54 +0200
From: Borislav Petkov <bp@...en8.de>
To: Vince Weaver <vincent.weaver@...ne.edu>
Cc: Huang Rui <ray.huang@....com>, linux-kernel@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Subject: Re: [patch] events/amd/power add support for fam16h model30h
On Fri, Jun 17, 2016 at 03:41:38PM -0400, Vince Weaver wrote:
> FWIW on the trinity machine (F15hM13h) with your patch applied I get the
> following:
>
> vince@a10:~$ sensors
> k10temp-pci-00c3
> Adapter: PCI adapter
> temp1: +0.0°C (high = +70.0°C)
> (crit = +70.0°C, hyst = +69.0°C)
>
> fam15h_power-pci-00c4
> Adapter: PCI adapter
> power1: N/A (crit = 100.04 W)
Yeah, I didn't expect to be that easy.
Provided hw support on TN is present, someone needs to sit down and
audit the algorithm in show_power() and sanity-check all those values
coming from the PCI regs.
But I'd wait for Rui first to confirm whether it is even worth to chase
this or whether TN is a lost cause because this TDP mechanism is not
supported there or whatever other reason there might be...
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
Powered by blists - more mailing lists