Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uunet!tut.cis.ohio-state.edu!pacific.mps.ohio-state.edu!linac!att!news.cs.indiana.edu!news.nd.edu!mentor.cc.purdue.edu!pop.stat.purdue.edu!hrubin
From: hrubin@pop.stat.purdue.edu (Herman Rubin)
Newsgroups: comp.arch
Subject: Re: new word order?
Message-ID: <7235@mentor.cc.purdue.edu>
Date: 2 Mar 91 14:22:43 GMT
References: <606@mtndew.Tustin.CA.US> <1991Mar1.095745.13399@siesoft.co.uk> <1255@TALOS.UUCP>
Sender: news@mentor.cc.purdue.edu
Lines: 33

In article <1255@TALOS.UUCP>, jerry@TALOS.UUCP (Jerry Gitomer) writes:
> imw@siesoft.co.uk (Ian Wild) writes:
> 
> |friedl@mtndew.Tustin.CA.US (Stephen J. Friedl) says:
 
			...................

> |68xxx:               1 2 3 4
> |80x86 (normally):    4 3 2 1
> |80x86 (+ cc -Mb):    2 1 4 3
> 
> |My question is WHY?

I am familiar with the order on the VAXen, and I can give some answer to
the WHY.  First to clarify the notation; the order listed is the order of
bytes in memory by address, and the byte number is from most significant
to least significant.  The 68xxx is big-endian; the most significant byte
comes first in memory.  The 80x86 and VAX are little-endian; the least
significant byte comes first in memory.  If an object is likely to have
its information in the least significant end, this is an advantage in
that the memory address of the lowest order byte is that of the {short
word, long word, double word}.

But for floating point, they had the most significant short word first.
For double on the VAX, the order is 21436587, so truncating to single
was done by using the same address.

I do not think that either way is the right way to do things; I am 
merely reporting.
--
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
Phone: (317)494-6054
hrubin@l.cc.purdue.edu (Internet, bitnet)   {purdue,pur-ee}!l.cc!hrubin(UUCP)