From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Bonniot Subject: Centrino: undervolting and further reducing heat Date: Wed, 18 May 2005 13:36:04 +0200 Message-ID: Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=gmane.org@lists.linux.org.uk Content-Type: text/plain; charset="iso-8859-1"; format="flowed" To: cpufreq@lists.linux.org.uk Hi, I have a dothan 1.6 GHz processor, and i've been investigating how to reduc= e=20 heat to minimize fan usage. One very promising avenue is undervolting.=20 According to several online articles, there is a large potential for=20 undervolting. I ended up modifying speedstep-centrino.c to test it out.=20 Results are very positive: it can run under heavy load at 1.6Ghz with only = 972mV (down from 1340mV). This decreased temperature by 10=B0C! At 600MHz, = the=20 minimum 700mV was sufficient. I understand that the driver needs to be conservative by default, but given= =20 the huge benefits, it would make a lot of sense to offer a way to specify=20 lower voltages to those who want to. Has anybody investigated this=20 possibility, or already started working on it? What would be a good interfa= ce=20 to specify the voltages? Independently of this feature, I wonder how it's possible to further reduce= =20 consumption when the system is mostly ideal, and even 600MHz is more than=20 needed. The idea being to let the system cool down even more in that case. = Is=20 there any existing way to achive this on linux? One possibility I found in = the=20 intel docs is the IA32_THERM_CONTROL MSR, which can reduce clock speed by=20 12.5% to 87.5%. Am I right in thinking that it could be combined with=20 speedstep to achieve even lower power consumption states? Are there other=20 possibilities? Cheers, Daniel