Peter,
IBM defines a bytes as the least addressable amount of storage. However,
once we are talking about wide bytes usually the storage is addressed as
words even though the storage in the word can not be further sub-addressed.
This seems to have started with the IBM 360 series. For example the 360-50
physically fetches memory in words 32 bits but can address 8 bits (byte).
On the other hand this machine's microcode is in 90 bit words. It can not
be subaddressed but it is not referred to as bytes.
These 90 bit words (should be called bytes) are the largest that I have
actually worked with.
Carl
-----Original Message-----
From: unicode-bounce@unicode.org [mailto:unicode-bounce@unicode.org]On
Behalf Of Peter_Constable@sil.org
Sent: Thursday, May 17, 2001 1:39 PM
To: unicode@unicode.org
Subject: [OT] bits and bytes
I seem to recall not long ago hearing of some machine architechtures that
have used large bytes, i.e. high number of bits per byte. I think at some
point I heard mention of a 36-bit byte, but one of my colleagues questioned
that (he once worked with a 36-bit architecture, but says it was actually
using 9-bit bytes).
Can anyone clarify for me how big a byte has ever been? (If you could
identify the particular hardware, that would be helpful.)
- Peter
---------------------------------------------------------------------------
Peter Constable
Non-Roman Script Initiative, SIL International
7500 W. Camp Wisdom Rd., Dallas, TX 75236, USA
Tel: +1 972 708 7485
E-mail: <peter_constable@sil.org>
This archive was generated by hypermail 2.1.2 : Fri Jul 06 2001 - 00:18:17 EDT