From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.169]) by ozlabs.org (Postfix) with ESMTP id 7132DDE00F for ; Mon, 7 Jul 2008 21:48:11 +1000 (EST) Received: by ug-out-1314.google.com with SMTP id k3so925078ugf.0 for ; Mon, 07 Jul 2008 04:48:08 -0700 (PDT) Message-ID: <48720279.6010904@genesi-usa.com> Date: Mon, 07 Jul 2008 12:48:09 +0100 From: Matt Sealey MIME-Version: 1.0 To: ppc-dev Subject: e600 core power management Content-Type: text/plain; charset=UTF-8; format=flowed Sender: Matt Sealey List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hi guys, Quick question, am I right (and looking at idle_6xx.S, I think I am) in thinking that during the idle process, by default, an e600 core such as the 7448 or MPC8610 will automatically transition to a NAP state, thus being as low power as possible? Has anyone done any benchmarking of the power consumption of the processor when this transition is disabled (remove CPU_FTR_MAYBE_CAN_NAP) or have a rough idea what the benefits might be? Is there a performance reason for removing the feature or disabling naps altogether? The powersave-nap sysctl controls whether DOZE or NAP is entered on processors that support a seperate HID0[DOZE], however is it possible to extend it such that nap is never entered? -- Matt Sealey Genesi, Manager, Developer Relations