In
<[EMAIL PROTECTED]>,
on 07/18/2006
at 05:26 PM, SUBSCRIBE IBM-MAIN tdell <T'[EMAIL PROTECTED]>
said:
>To recap..
Much of that is wrong.
>Mainframes don't actually have a backplane that's governed by a bus
>arbitrator scheme as some implementation have done in the past.
Some do.
>That channel subsystem as it was called, was strictly a place for the
>more experienced coders so beware. It has it's own methodology when
>it came to writing code.
You don't write code for the channel. There is a very limited set of
opcodes for channel command words and there is no provision for even
simple computation.
>The channel subsystem is really a processor in it's own right.
On some mainfames, not on all. The channels on, e.g., the 360/40,
360/50, 370/145, 370/155, worked by cycle stealing.
> All throughout the architecture you'll find various processors that
>are part of the machine architectural composition,
No, that's implementation.
--
Shmuel (Seymour J.) Metz, SysProg and JOAT
ISO position; see <http://patriot.net/~shmuel/resume/brief.html>
We don't care. We don't have to care, we're Congress.
(S877: The Shut up and Eat Your spam act of 2003)
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
