From owner-freebsd-amd64@FreeBSD.ORG Sat Feb 21 00:55:57 2009 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4CC69106564A for ; Sat, 21 Feb 2009 00:55:57 +0000 (UTC) (envelope-from yanefbsd@gmail.com) Received: from yw-out-2324.google.com (yw-out-2324.google.com [74.125.46.31]) by mx1.freebsd.org (Postfix) with ESMTP id 0366C8FC13 for ; Sat, 21 Feb 2009 00:55:56 +0000 (UTC) (envelope-from yanefbsd@gmail.com) Received: by yw-out-2324.google.com with SMTP id 2so450609ywt.13 for ; Fri, 20 Feb 2009 16:55:56 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=QsevqtBjYoQ+PDYGB73hfBQqc5fEhyBF5XlTOfVlASk=; b=fKxRC2ZcRx5X8H8wfKD/Zfg70WvgS1GMhpi5y48Nf588Nm7QRv/EYjYPra2GNpQZxh Dh2O2zqnvabPJCFzZviCYXCoU8jDD39F5oVuTssSIhFV1d93pb8aErDwHT7vHrTaMQKl km+Khp8PuDh2Y/YM3MeZl2T/DJOvXodd6GYF4= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=qgJQ3hz7XYV5t1uIqf32medu4lBkxtLLMgPk5VhWlx1geYu+ZQH27SPVwyIlKX3bYV 8wG7skFaRof8OH9x+196/t9Y4iIgtiAxxNoqAd9ULNBKPkrw812TycS0gDh17DYLZ51r dVB/Ffr0cQsMH22CMm8p+UUtAFMkbRQ3FttLQ= MIME-Version: 1.0 Received: by 10.90.35.15 with SMTP id i15mr105092agi.83.1235177755995; Fri, 20 Feb 2009 16:55:55 -0800 (PST) In-Reply-To: <01b401c993b5$525b7960$f7126c20$@net> References: <9D0C41D6-5EDB-4D17-8258-352FE8ADAFBD@chesterdkat.com> <499DAAF8.4030005@dir.bg> <6101e8c40902191108w2234b13k84466dfd9f1fe4ee@mail.gmail.com> <013f01c99364$5689e4a0$039dade0$@net> <20090220185928.GB7314@slackbox.xs4all.nl> <01b401c993b5$525b7960$f7126c20$@net> Date: Fri, 20 Feb 2009 16:55:55 -0800 Message-ID: <7d6fde3d0902201655r5a69985cubd8f21fb38b0771@mail.gmail.com> From: Garrett Cooper To: Howard Leadmon Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-amd64@freebsd.org Subject: Re: Intel Xeon Processor kernel compile CPU type. X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 21 Feb 2009 00:55:57 -0000 On Fri, Feb 20, 2009 at 3:45 PM, Howard Leadmon wrote: > Good, so nocona is really the right one to specify. Good to know I have > been doing it correctly on my x64 machines, and heck nice document/defines > there, I'll keep that in my notes so I know how to find stuff like that in > the future.. > > > --- > Howard Leadmon > > >> -----Original Message----- >> From: Roland Smith [mailto:rsmith@xs4all.nl] >> Sent: Friday, February 20, 2009 1:59 PM >> To: Howard Leadmon >> Cc: 'Oliver Pinter'; freebsd-amd64@freebsd.org >> Subject: Re: Intel Xeon Processor kernel compile CPU type. >> >> On Fri, Feb 20, 2009 at 09:05:46AM -0500, Howard Leadmon wrote: >> > I knew HAMMER was the only type for making your kernel, but what >> CPUTYPE's >> > are OK for 64bit? >> >> > CPU: Intel(R) Xeon(TM) CPU 2.80GHz (2793.20-MHz K8-class CPU) >> > Origin = "GenuineIntel" Id = 0xf48 Stepping = 8 >> > >> > >> Features=0xbfebfbff> CA >> > ,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE> >> > Features2=0x649d >> > AMD Features=0x20100800 >> > AMD Features2=0x1 >> > Cores per package: 2 >> > Logical CPUs per core: 2 >> > FreeBSD/SMP: Multiprocessor System Detected: 8 CPUs >> > >> > So should this stuff be set to nocona, core2, or what?? >> >> Have a look at /usr/share/mk/bsd.cpu.mk. If you are using the amd64 >> architecture, you can use CPUTYPE=prescott or CPUTYPE=core2, but both >> will be converted to CPUTYPE=nocona. That's probably because that is the >> latest variant that the gcc in base understands. I know it's already been said, but Intel recommends (with the compiler version that we have) to use prescott for i686 and nocona for amd64 because it best matches the caching / instruction scheduling for the Core 2 CPU's. If we actually move to gcc 4.3+ they have improved support for -march=core2. HTH, -Garrett