Path: csiph.com!x330-a1.tempe.blueboxinc.net!newsfeed.hal-mli.net!feeder3.hal-mli.net!newsfeed.hal-mli.net!feeder1.hal-mli.net!border3.nntp.dca.giganews.com!Xl.tags.giganews.com!border1.nntp.dca.giganews.com!nntp.giganews.com!local2.nntp.dca.giganews.com!news.giganews.com.POSTED!not-for-mail
NNTP-Posting-Date: Wed, 22 Feb 2012 10:23:35 -0600
Message-ID: <4F451687.2080101@SPAM.comp-arch.net>
Date: Wed, 22 Feb 2012 08:23:35 -0800
From: "Andy (Super) Glew" <andy@SPAM.comp-arch.net>
Reply-To: andy@SPAM.comp-arch.net
Organization: comp-arch.net
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2) Gecko/20120216 Thunderbird/10.0.2
MIME-Version: 1.0
Newsgroups: comp.arch
Subject: Re: M68k add to memory is not a mistake any more
References: <ggtgp-8D1AEA.03180231012012@netnews.mchsi.com> <jhvm1i$q80$1@gosset.csi.cam.ac.uk> <o07c19-v832.ln1@ntp6.tmsw.no> <ji0qbu$154$1@speranza.aioe.org> <ji0sn5$75f$1@gosset.csi.cam.ac.uk>
In-Reply-To: <ji0sn5$75f$1@gosset.csi.cam.ac.uk>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Lines: 21
X-Usenet-Provider: http://www.giganews.com
X-Trace: sv3-CBHByKaZRxLPoPbjaUcEwY+ekBbh7/y+oyFcEURQmjrqim9hRo6r9649EkqePf1pbEI3TXIFMmeNrGr!eHn9sZF+QvL7cJT+PJKfC4G/LHJu8QUWjWQJnTLV7lO/0VTt7J7siLD+EvgtMII=
X-Complaints-To: abuse@giganews.com
X-DMCA-Notifications: http://www.giganews.com/info/dmca.html
X-Abuse-and-DMCA-Info: Please be sure to forward a copy of ALL headers
X-Abuse-and-DMCA-Info: Otherwise we will be unable to process your complaint properly
X-Postfilter: 1.3.40
X-Original-Bytes: 2256
Xref: x330-a1.tempe.blueboxinc.net comp.arch:6034

On 2/21/2012 11:53 AM, nmm1@cam.ac.uk wrote:

> And just why is it so impossible to have a core for each interface,
> and a few over?
>
> You seem to have misunderstood this thread.  It was and is not about
> what is usually done, but what could be done with a different, but
> easily deliverable, hardware and software design - i.e. computer
> architecture.

There was an article in some embedded magazine last year about how they 
were seeing a trend in automotive to fewer bigger CPUs, rather than 
more, smaller.

Mainly for load balancing.  If you have 16 CPUs of performance level 1, 
and you have 3 tasks that require performance level 2 and 12 that 
require performance level 0.5, you are out of luck.  But if you have 4 
CPUs each of performance level, say, 8, it all fits. Heck, even parity, 
performance level 4x4.

Parallelism is good. Load balancing is hard.