A query about hardware emulator on a Unix system
mark edwards
edwards at uwmacc.UUCP
Wed Sep 24 23:53:58 AEST 1986
In article <3922 at brl-smoke.ARPA> prindle at nadc.arpa writes:
>Greetings,
>I would like to enlist the aid of this net-newsgroup community in exploring
>a potential hardware approach to upgrading a programming support enviroment.
>We are also looking at strictly software approaches, but these currently
>appear to have a high risk.
>
First I would like to state my experience with the CP901, I worked at
an ASWOC as a Data System Technician (computer repairman), I have fixed
several problems in it and used it to locate problems in other devices.
In short I beleive I know exactly what and how it is used . The CP901 is
also used on some Navy planes while the CP-642B is used on ships.
Lets talk insides of these computers, can you say transistors ??
then you can say what the main logic components of the gates are for
the 642B. Now can you say flat pack ?, You've got it the CP901 is uses
these components to replace the transistors. Supposedly the same machine
though.
I am now a systems programmer/administrator for 780 based 4.2 machine.
>Requirements for the hardware approach:
>
....
> This board would be capable of emulating the instruction set architecture
> of a fairly primitive 30 bit militarized computer, specifically a Sperry
> (Univac) model CP-901/CP-642B. I/O channel instructions within this ISA
> would be converted, by the board, into interrupt requests to be honored by
> the main processor and the Unix system. The board would directly access
> a block of host computer virtual memory space (allocated by the Unix system)
> as the emulated computer's memory. The emulator could be multiprogrammed
> under control of the main processor and the Unix system: i.e. it could be
> stopped or started at any time by the main processor, any and all of it's
> registers would be readable or writable by the main processor, and the DMA
> memory mapping may be altered by the main processor.
>
It seems this might cause problems, mainly because I/O is done
differently on th CP901. It might seem to work fine in testing, but
when it is ported to the CP901 problems may develop when it used in
real situations.
> - or -
>
>b. A high speed, state-of-the-art, dual or multi-processor computer, running
> Unix as above, in which one or more of the processors could be micro-
> programmed to emulate the CP-901/CP-642B ISA as above, and dedicated to
> that task, with the remaining processor(s) running the Unix system.
>
I would probably go this route as long as the CP901/CP-642B were actually
replaced with this machine doing the emulation of these precious dears.
>..... as well as
>any thoughts about the feasibility or potential efficiency of such a system.
>
Thoughts ? Yes plenty!
The CP901/642B should be replaced, the computers along with all the
antiquated periperial devices. Why beat a dead horse ?? The initial
cost of replacing them will be high. But if cost are taken over a long
run for maintaining the existing systems, you might even break even
the first year !!!!!????
Examples
The tape drives break down constantly ( have they been replaced ?).
The high speed printer blows hammers about 3 a year (for the site
I was at), they were $400 a crack (Gee I could've had an epson).
They use Large Screen Projectors for the system, the site I was
at blew at least of the projection tubes in the two years I was
there, ~ $1,500 a crack. Seems like Sony or somebody makes a
better one, for less.
The new planes are being built all the time, and it seems the
cost of building these computers will be outrageously high. The
power of these machines can't be more than a 68020 chip.
The cost of training programmers to write programs for these
machines seems like it would be high.
There are better ways of making hardware, (and cheaper).
Sorry, this probably didn't belong here, but some idea of what the
system does and what it actually was, wasn't apparent.
mark
--
{allegra, ihnp4, seismo}!uwvax!uwmacc!edwards
UW-Madison, 1210 West Dayton St., Madison WI 53706
More information about the Comp.unix
mailing list