*BSD News Article 79554


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!nntp.coast.net!news2.acs.oakland.edu!news.tacom.army.mil!news.webspan.net!www.nntp.primenet.com!nntp.primenet.com!cam-news-hub1.bbnplanet.com!news.mathworks.com!uunet!in1.uu.net!delphi.com!usenet
From: Jim Nelson <smartsignal@delphi.com>
Newsgroups: comp.unix.bsd.freebsd.misc
Subject: Re: Why one should buy parity memory for reliability?
Date: Mon, 30 Sep 96 09:48:35 -0500
Organization: Delphi (info@delphi.com email, 800-695-4005 voice)
Lines: 28
Message-ID: <xlDxUb7.smartsignal@delphi.com>
References: <32485B0D.41C6@austin.ibm.com> <52br3d$9s8@flash.noc.best.net>
NNTP-Posting-Host: bos1d.delphi.com
X-To: Matthew Dillon <dillon@best.com>

Matthew Dillon <dillon@best.com> writes:
 
>:>I was involve in designing one of the microcontroller for Motorola,
>:>one of the things we left out for the future controller was not
 
 
>:>I was involve in designing one of the microcontroller for Motorola,
>:>one of the things we left out for the future controller was not
>:>supporting parity (less pin count). The reasoning was, In the normal
 
The big difference between controllers and larger systems is in the amount of
RAM consumed.  A typical microcontroller can do its job with a 64KB address
space - and the RAM is normally static CMOS - which comprises 5 or 6 fets per
bit vs the single fets/bit in DRAM.  The difference in memory size - 64KB
vs 64MB - i.e., 1000 to 1, is the really big factor.  Even a vanishingly
small probability of corruption is made probable when multiplied by the number
of individual bits in a large array, say 64MB, or 2GB...
 
>    Having parity and the dram controller incorporated *into* the 
>    microcontroller or cpu is the way to go, removing the requirement for
>    external buffers or muxes and reducing the pin count while at the same
>    time supporting page mode, burst read, and interleaved dram 
>    subsystems... even wider data busses.  Couple that with I/O, a *real*
>    cpu core, and at *least* an instruction cache, and you have a hot product.
 
That's a different market from the microcontroller market.  Sounds great, but
microcontrollers aimed at low-power environments don't use DRAM because
of the refresh requirement.  Maybe what you need is a new name for the solution.