Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!columbia!topaz!husc6!panda!genrad!decvax!decwrl!glacier!Shasta!andy
From: andy@Shasta.UUCP
Newsgroups: net.arch
Subject: Very Long Addresses
Message-ID: <831@Shasta.STANFORD.EDU>
Date: Tue, 9-Sep-86 15:48:23 EDT
Article-I.D.: Shasta.831
Posted: Tue Sep  9 15:48:23 1986
Date-Received: Wed, 10-Sep-86 20:15:36 EDT
References: <15505@ucbvax.BERKELEY.EDU> <5100121@ccvaxa> <588@mecc.UUCP>
Reply-To: andy@Shasta.UUCP (Andy Freeman)
Organization: Stanford University
Lines: 15
Keywords: Large addresses, fast comparators, big crocodiles
Summary: I'll tell you when I have too much


Most of us already use systems whose addresses are 100's of bits
long.*  Freedom in naming, especially if it results in sparse use
of the name space, can be quite important.

BTW - The delay of comparators that use precharging (see the Manchester
carry-chain adder in Mead-Conway) seems to be independent of the size
of the addresses being compared, at least through several tens of bits.

-andy
*How long is your name?  What about your address?
-- 
UUCP:  ...!decwrl!glacier!shasta!andy forwards to
ARPA:  andy@sushi.stanford.edu
(415) 329-1718/723-3088 home/cubicle