From owner-freebsd-hackers Thu Dec 11 10:59:23 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id KAA05127 for hackers-outgoing; Thu, 11 Dec 1997 10:59:23 -0800 (PST) (envelope-from owner-freebsd-hackers) Received: from misery.sdf.com (misery.sdf.com [204.244.210.193]) by hub.freebsd.org (8.8.7/8.8.7) with SMTP id KAA05095 for ; Thu, 11 Dec 1997 10:59:06 -0800 (PST) (envelope-from tom@sdf.com) Received: from tom by misery.sdf.com with smtp (Exim 1.73 #1) id 0xgDfd-0004av-00; Thu, 11 Dec 1997 10:49:13 -0800 Date: Thu, 11 Dec 1997 10:49:12 -0800 (PST) From: Tom To: Tom Bartol cc: hackers@freebsd.org Subject: Re: This IS relevant, you'll realize why later. In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Thu, 11 Dec 1997, Tom Bartol wrote: > On Thu, 11 Dec 1997, Jonathan Lemon wrote: > > > Hmm. One of my professors was claiming that with 128 bits, you would have > > an address space of 2^128, which would be large enough that you could do > > away with virtual memory altogether. > > > > Just give each piece of data it's own unique address, (ala Multics) and > > then never relocate it for the lifetime of the system. She pointed out > > that even the human genome database project is smaller than this. > > > > Somehow, I don't quite buy the argument. > > -- > > Jonathan > > > > I'd buy it for $5.00 -- > If the logic for each bit fit in a cube 0.14 picometer on a side you could > fit 2^128 bits in 1 cubic meter. Never mind that 0.14 picometer is > ~1/700th the diameter of a hydrogen atom and is only about 100 times > bigger than an atomic nucleus! So if we could fit the logic for one bit > in the space of a hydrogen atom, 2^128 bits would fill a cube ~700 meters > on a side! Or if one bit fit in a cube 0.25 microns on a side then 2^128 > bits would fill a cube ~1750 kilometers on a side (i.e. about 1/4th the > volume of the Moon)!!!! I think you are missing the point. The point is about address space, not physical RAM. The mapping of address space to physical RAM is flexible. Many current CPUs have a 4GB address space, but most systems have less than 4GB of RAM. Tom