Newsgroups: comp.arch
Path: utzoo!henry
From: henry@utzoo.uucp (Henry Spencer)
Subject: Re: 1Meg DRAM supply voltage
Message-ID: <1989Oct17.154651.16073@utzoo.uucp>
Organization: U of Toronto Zoology
References: <6797@hubcap.clemson.edu>
Date: Tue, 17 Oct 89 15:46:51 GMT

In article <6797@hubcap.clemson.edu> rchampe@hubcap.clemson.edu (Richard Champeaux) writes:
>I remember a while ago when they were developing 1 Meg DRAMS, they said
>that they had to be run off of 3.3v supplies to reduce power dissapation...

This is one of these "gonna have to make big changes real soon now" claims
that keeps running around, and keeps getting shot down when people discover
that it's cost-effective to work *really hard* to avoid the pain of making
such changes.  Other such claims are "gonna have to drop silicon and go to
gallium arsenide real soon now", "gonna have to go to highly-parallel
machines to get any further speed increase real soon now", and "gonna have
to drop optical lithography and go to electron beams or X-rays real soon now".
(One of the gems of my collection is an unintentionally-hilarious paper
from an IEEE conference proceedings that proves, in some detail, that it
is impossible to build 64Kb DRAMs with optical lithography.)

"Gonna have to go to 3.3V for the next generation of memories" has been
around for fifteen years or so.
-- 
A bit of tolerance is worth a  |     Henry Spencer at U of Toronto Zoology
megabyte of flaming.           | uunet!attcan!utzoo!henry henry@zoo.toronto.edu
