From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mga05.intel.com ([192.55.52.89] helo=fmsmga101.fm.intel.com) by linuxtogo.org with esmtp (Exim 4.72) (envelope-from ) id 1Tt1fY-00063X-HB for openembedded-core@lists.openembedded.org; Wed, 09 Jan 2013 20:50:38 +0100 Received: from mail-ea0-f200.google.com ([209.85.215.200]) by mga01.intel.com with ESMTP/TLS/RC4-SHA; 09 Jan 2013 11:35:22 -0800 Received: by mail-ea0-f200.google.com with SMTP id j13so1824889eaa.11 for ; Wed, 09 Jan 2013 11:35:21 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=x-received:x-received:date:from:to:cc:message-id:in-reply-to :references:subject:x-mailer:mime-version:content-type :content-transfer-encoding:content-disposition:x-gm-message-state; bh=gGbi2fC3+QnOrhMMlkJ0Ge20BInnfEJSUi+t2c/5pYk=; b=RVFUS1gyq2OxKZubRe6QP+MMNaOez3/bQEq1O54T1NyikwF+Ir94BAxnjwhFgwfRrW q07pOr0YRHzAewWM+l61jsC882yBU737ImOLvga7z6ifkTZdYLLJJbR0Y49XVIfuCB63 bZg0IbuB8cwSvcg0HK0Kgu8ei7gGaLJNDJO869ECp1zxEtsnmMHKn1PCGFODUqVfyEQp a4vpNMR1RPkV4tCWQ+A1sO6ZXfQuLKXagMQEm0wq37sq/yKNcH6Wmn35Yt6/h3/aZxtY wJJ/KfKav46Fja/KP2uU8WeWw0ErLQh0xzX18Zw5zPJBXu77kwTvljGO+h8fGrLOhMKS I43w== X-Received: by 10.194.89.167 with SMTP id bp7mr109563880wjb.0.1357760121151; Wed, 09 Jan 2013 11:35:21 -0800 (PST) X-Received: by 10.194.89.167 with SMTP id bp7mr109563867wjb.0.1357760121022; Wed, 09 Jan 2013 11:35:21 -0800 (PST) Received: from [192.168.1.7] (35.106.2.81.in-addr.arpa. [81.2.106.35]) by mx.google.com with ESMTPS id dm3sm5210733wib.9.2013.01.09.11.35.19 (version=TLSv1 cipher=RC4-SHA bits=128/128); Wed, 09 Jan 2013 11:35:19 -0800 (PST) Date: Wed, 9 Jan 2013 19:35:24 +0000 From: Ross Burton To: =?utf-8?Q?Bj=C3=B8rn_Forsman?= Message-ID: <89ACB277BC7047D58E19B3BA98CE24F0@intel.com> In-Reply-To: References: X-Mailer: sparrow 1.6.4 (build 1178) MIME-Version: 1.0 X-Gm-Message-State: ALoCoQkedqvfNisyaIjdkAhYhQS+FxRxYASk3og5EfdwDauczEbB1RhOSPPDxNq05a0GC0iKHmfHTIeaMHrXGJMYYv6QVYTAIe/m4SFRDkVjGZrC93/vesuqYxtSLyEehk2YHK7O7F6WzBL3DS7xubaQx0eCxnPGeEJxdbRF6RNoIMCosu+u0sf21sabp/c8+igVVeIM/l0A Cc: OE Core mailing list Subject: Re: for a quad-core machine, shouldn't parallelism be set to 8? X-BeenThere: openembedded-core@lists.openembedded.org X-Mailman-Version: 2.1.11 Precedence: list List-Id: Patches and discussions about the oe-core layer List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Jan 2013 19:50:38 -0000 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline On Wednesday, 9 January 2013 at 18:42, Bj=C3=B8rn =46orsman wrote: > > =23 =46or a quad-core machine, BB=5FNUMBER=5FTHREADS =3D =224=22, PAR= ALLEL=5FMAKE =3D =22-j 4=22 would > > =23 be appropriate for example. > > =20 > > i thought the general rule was that parallelism should be *twice* > > the number of cores. that's certainly what's suggested in the yocto > > QS guide: > =20 > =20 > =20 > Some time ago I wrote a script to build the linux kernel 3 times at > each -jN level from 1 to 50. Then I averaged the build time on each > -jN level. I got the fastest build with -jNCPUS. Going above NCPUS > just added overhead, although very little. The overhead seemed to > build up quite linearly from above -jNCPUS. Because the overhead is so > little, having -jNCPUS*2 may not be noticeably slower than -jNCPUS. > =20 > I ran the same benchmark another machine and it showed the same trend > curve. Note that NCPUS must include the hyperthread cores. Of course if you set BB=5FNUM=5FTHREADS and PARALLEL=5FMAKE to NCPUS, the= n you're actually potentially running NCPUS*NCPUS compile threads. I'm n= ot convinced that NCPUS*2 is useful with that considered. Ross