Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 20 May 2005 09:55:26 -0700
From:      "David O'Brien" <obrien@freebsd.org>
To:        Attila Nagy <bra@fsn.hu>
Cc:        freebsd-amd64@freebsd.org
Subject:   Re: FreeBSD on dual core Opterons - stupid buildworld test
Message-ID:  <20050520165526.GE6982@dragon.NUXI.org>
In-Reply-To: <428CC309.5040306@fsn.hu>
References:  <428B6FC1.3000907@fsn.hu> <1116437340.69035.0.camel@hood.oook.cz> <20050518180521.GB9719@odin.ac.hmc.edu> <20050519010828.GA64608@dragon.NUXI.org> <428CC309.5040306@fsn.hu>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, May 19, 2005 at 06:47:05PM +0200, Attila Nagy wrote:
> David O'Brien wrote:
> >I'm taking care of this.  Please no one commit any AMD Dual-core related
> >patches (especially WRT HTT) with out passing them by me.
> Do you have any preliminary patches? Access to hardware?

Yes I have hardware - since March.

Everyone should note that difference of dual-core vs. single core doesn't
matter one bit for FreeBSD.  We don't have NUMA support, which is what is
required to care about the difference between 1x dual-core & 2x
single-core (or 2x dual-core & 4x single-core) Opteron.

For 6.0-RELEASE (which branches June 1, 2005), I'm going to just have the
kernel ignore that dual-core Opteron sets the HTT feature flag.

-- 
-- David  (obrien@FreeBSD.org)



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050520165526.GE6982>