From owner-freebsd-smp Fri Mar 14 23: 3:25 2003 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5E7F337B404 for ; Fri, 14 Mar 2003 23:03:24 -0800 (PST) Received: from pirx.hexapodia.org (pirx.hexapodia.org [208.42.114.113]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1D07843F3F for ; Fri, 14 Mar 2003 23:03:23 -0800 (PST) (envelope-from adi@hexapodia.org) Received: by pirx.hexapodia.org (Postfix, from userid 22448) id AC3D3B404; Sat, 15 Mar 2003 01:03:21 -0600 (CST) Date: Sat, 15 Mar 2003 01:03:21 -0600 From: Andy Isaacson To: Brooks Davis Cc: smp@freebsd.org Subject: Re: weird power usage on dual Xeon Message-ID: <20030315010321.A12293@hexapodia.org> References: <20030314174113.A16583@Odin.AC.HMC.Edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <20030314174113.A16583@Odin.AC.HMC.Edu>; from brooks@one-eyed-alien.net on Fri, Mar 14, 2003 at 05:41:13PM -0800 X-PGP-Fingerprint: 48 01 21 E2 D4 E4 68 D1 B8 DF 39 B2 AF A3 16 B9 X-PGP-Key-URL: http://web.hexapodia.org/~adi/pgp.txt X-Domestic-Surveillance: money launder bomb tax evasion Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Fri, Mar 14, 2003 at 05:41:13PM -0800, Brooks Davis wrote: > Is it expected that the Idle loop would consume more power > then a FPU intensive application like SETI@Home? The only thing I can > think of is that the Idle loop stays in the cache and doesn't have the > kinds of stalls an appliction with 15MB of data to process does. > > no HTT HTT > idle+hlt 94W 94W > idle 170W 183W > seti 160W 172W > seti+hlt 159W 171W > > idle: idle > htl: sysctl machdep.cpu_idle_hlt=1 > seti: all CPUs (real or logical) running linux-setiathome-i686 FWIW, I've measured about 45 W per processor (2.4 GHz Xeon 512k). Do you get a different answer if you run only two copies of SETI? I can't imagine that their FFT routine takes kindly to having to share L1 cache, perhaps it's spending all its time waiting for the L2... and do you actually process more work units per hour with 4 SETI processes running on HT as opposed to 2 SETIs without HT? I kinda doubt it, but would welcome real information. -andy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message