From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754739AbaIPQqd (ORCPT ); Tue, 16 Sep 2014 12:46:33 -0400 Received: from www.sr71.net ([198.145.64.142]:50410 "EHLO blackbird.sr71.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754462AbaIPQqc (ORCPT ); Tue, 16 Sep 2014 12:46:32 -0400 Message-ID: <54186966.3010901@sr71.net> Date: Tue, 16 Sep 2014 09:46:30 -0700 From: Dave Hansen User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Peter Zijlstra , Chuck Ebbert CC: Ingo Molnar , linux-kernel@vger.kernel.org, borislav.petkov@amd.com, andreas.herrmann3@amd.com, hpa@linux.intel.com, ak@linux.intel.com Subject: Re: [PATCH] x86: Consider multiple nodes in a single socket to be "sane" References: <20140915222641.D640BD8A@viggo.jf.intel.com> <20140916032920.GH2840@worktop.localdomain> <20140916013845.390833b9@as> <20140916064403.GC14807@gmail.com> <20140916020300.5013b8f0@as> <20140916160134.GB2848@worktop.localdomain> In-Reply-To: <20140916160134.GB2848@worktop.localdomain> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/16/2014 09:01 AM, Peter Zijlstra wrote: > On Tue, Sep 16, 2014 at 02:03:00AM -0500, Chuck Ebbert wrote: >> Hmm, looking closer at the diagram, each ring has its own memory controller, so >> it really is NUMA if you break the interconnect between that caches. > > How does it do that? Does it split the DIMM slots in two as well, with > half for the one node and the other half for the other? Or will both > 'nodes' share the same local memory? I the diagrams in here are accurate in describing the rings: http://www.enterprisetech.com/2014/09/08/intel-ups-performance-ante-haswell-xeon-chips/ The "nodes" each get their own memory controller and exclusive set of DIMMs.