From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Mon, 7 Jul 2008 10:17:32 -0700 From: Eric Blossom To: Arnd Bergmann Subject: Re: [Cbe-oss-dev] powerpc/cell/cpufreq: add spu aware cpufreq governor Message-ID: <20080707171732.GC26603@comsec.com> References: <200807071702.31240.arnd@arndb.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <200807071702.31240.arnd@arndb.de> Cc: Dave Jones , Stephen Rothwell , cpufreq@lists.linux.org.uk, linuxppc-dev@ozlabs.org, Jeremy Kerr , cbe-oss-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Mon, Jul 07, 2008 at 05:02:30PM +0200, Arnd Bergmann wrote: > From: Christian Krafft > > This patch adds a cpufreq governor that takes the number of running spus > into account. It's very similar to the ondemand governor, but not as complex. > Instead of hacking spu load into the ondemand governor it might be easier to > have cpufreq accepting multiple governors per cpu in future. > Don't know if this is the right way, but it would keep the governors simple. I've got a basic question about this idea: Does it throttle only idle spus or is there a single control for the entire PPE + SPE complex? I can think of many situations in our code where at certain times we may only be able to keep N out of M spes occupied (because of how we've expressed our task-specific parallelism), but we're counting on the ones we're using running at full speed so that we can maintain our real-time throughput. (Our application does real-time signal processing of continuously streaming data) Is there a way to disable the "throttling SPEs" feature short of configuring it out of the kernel? Eric