Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 17 Apr 2008 17:35:16 -0700
From:      "David O'Brien" <obrien@freebsd.org>
To:        David Malone <dwmalone@maths.tcd.ie>
Cc:        gnn@freebsd.org, freebsd-current@freebsd.org, Jeff Roberson <jroberson@jroberson.net>, Andrew Gallatin <gallatin@cs.duke.edu>
Subject:   Re: TSC Timecounter and multi-core/SMP
Message-ID:  <20080418003516.GD11705@dragon.NUXI.org>
In-Reply-To: <20080415084602.GA44129@walton.maths.tcd.ie>
References:  <m2d4oy8n30.wl%gnn@neville-neil.com> <18431.23276.913397.188219@grasshopper.cs.duke.edu> <m27iezwonx.wl%gnn@neville-neil.com> <20080414215057.B959@desktop> <20080415084602.GA44129@walton.maths.tcd.ie>

next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Apr 15, 2008 at 09:46:02AM +0100, David Malone wrote:
> On Mon, Apr 14, 2008 at 09:51:42PM -1000, Jeff Roberson wrote:
> > I think we should confirm whether this is the case with earlier opterson. 
> > I have seen two processors on the same die out of sync.
> 
> This can definitely happen according to this note from AMD, which
> someone posted a link to earlier in the thread:
> 
> 	http://lkml.org/lkml/2005/11/4/173
> 
> it can happen when you hlt one core, but don't hlt the other on
> some processors.

Actually that is something slightly different.  Even without HLT, RDTSC
on the two cores of a dual-core processor can be out of sync.  HLT can
affect the delta between the two cores.

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



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080418003516.GD11705>