From owner-freebsd-hackers Mon Jul 23 14:25:45 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from sneakerz.org (sneakerz.org [216.33.66.254]) by hub.freebsd.org (Postfix) with ESMTP id 095CE37B403 for ; Mon, 23 Jul 2001 14:25:39 -0700 (PDT) (envelope-from bright@sneakerz.org) Received: by sneakerz.org (Postfix, from userid 1092) id 84D495D01F; Mon, 23 Jul 2001 16:25:28 -0500 (CDT) Date: Mon, 23 Jul 2001 16:25:28 -0500 From: Alfred Perlstein To: Leo Bicknell Cc: freebsd-hackers@freebsd.org Subject: Re: MPP and new processor designs. Message-ID: <20010723162528.C65796@sneakerz.org> References: <20010723165519.A33391@ussenterprise.ufp.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <20010723165519.A33391@ussenterprise.ufp.org>; from bicknell@ufp.org on Mon, Jul 23, 2001 at 04:55:19PM -0400 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG * Leo Bicknell [010723 15:58] wrote: > > A number of new chips have been released lately, along with some > enhancements to existing processors that all fall into the same > logic of parallelizing some operations. Why, just today I ran > across an article about http://www.theregister.co.uk/content/3/20576.html, > which bosts 128 ALU's on a single chip. > > This got me to thinking about an interesting way of using these > chips. Rather than letting the hardware parallelize instructions > from a single stream, what about feeding it multiple streams of > instructions. That is, treat it like multiple CPU's running two > (or more) processes at once. [snip] This is planned, the idea is to allow multple threads to execute at the same time, since they share the same TLB/VM state the logic units for execution can be duplicated without needing additional VM/TLB units. > > I'm sure the hardware isn't quite designed for this at the moment > and so it couldn't "just be done", but if you had say 128 ALU's > most single user systems could dedicate one ALU to a process > and never context switch, in the traditional sense. For systems > that run lots of processors the rate limiting on a single process > wouldn't be a big issue, and you could gain lots of effiencies > in the global aspect by not context-switching in the traditional > sense. You can't really do this, the other units, specifically the VMM unit would have to be duplicated as well. > Does anyone know of something like this being tried? Traditional > 2-8 way SMP systems probably don't have enough processors (I'm > thinking 64 is a minimum to make this interesting) and require > other glue to make multiple independant processors work together. > Has anyone tried this with them all in one package, all clocked > together, etc? I think IBM has or will be doing your method with thier processors, multiple processors on a single die. The method I mention is rumored to be in the works at Intel and possibly other companies. -- -Alfred Perlstein [alfred@freebsd.org] Ok, who wrote this damn function called '??'? And why do my programs keep crashing in it? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message