> You are right of course conceptually. But I'm pretty sure
> now that KA620 was the only implementation of the rtVAX architecture.
I *think* that the KA620 was the only VAX chip that was
deliberately hobbled. There were, however, other machines
called rtVAX <some-number>. I forget the exact details
but at least one of them was based on the CVAX chip. I
expect that there was something at the board-level that
would have prevented them running OpenVMS but the chip
was (I'm pretty sure) a standard CVAX.
> early VARMs, the EK-VAXAR-RM ones, are
> lovely: 100% pure ASCII, except for boldface section headers
> the book is line printer output.
One of the standard questions I recall within DEC was
"can I have an electronic copy of STD 032" to which the
standard answer was "No, there's no such thing". Obviously
there *was* such a thing, it just never got released that
way. It only came out (AFAIK) in hardcopy. Same with the
Alpha SRM.
> From the appearance seems
> to be very close to the DEC internal VAX spec, DEC STD 032
> (though not having a copy of the latter it's an educated
> guess). But then they stopped issuing VARMs in that format,
> and published it as a book (with ISBN and all, rather than an
> EK part #).
The books were slightly sanitised copies of DEC STD 032 but
professionally printed. If that V6.1 EK-VAXAR-RM is the
one I'm thinking of (but just cannot lay my hands on right
now) then it too is a sanitised DEC STD 032 that eventually
turned into the first edition of the book.
There's not a huge difference between STD 032 and the books.
There are a few paragraphs missing here and there but I don't
remember anything hugely significant (and I'm no longer
in a position to check). The sanitised bits are quite obvious -
I recall some kind of markup (either "/" or "\" at the start
of the not-for-publication lines). Lists of DEC contacts with
phone numbers and the revision history probably got dropped too.
The only major omission is the Virtual VAX stuff (which was
done for some three letter agency but never became a product
- I heard that it just ran way too slowly to be useful).
It has its own SID (09 IIRC, I guess(0)07 was already taken :-)).
Much more interesting was the list of VAX bugs (i.e. the list
of which chips had waivers for which particularly obscure
issues). But even these would not help you understand the
architecture any better. All the ones that were relevant
to what I was doing were called out in system specific
documentation anyway.
> (I'm designing a new VAX CPU chip, so I have to have a very
> solid picture of the spec requirements and options and their
> evolution.)
I think I've said before, what you really want is not STD 032
but AXE, the tool that runs on your new VAX and checks for
correct operation of instructions.
> Since the MMU is internal to the CPU chip, the difference
> between KA630 and KA620 is in the silicon (78032 vs. 78R32)
> rather than board-level.
Yes. KA620 was a mangled chip and not a mangled board.
Antonio
--
---------------
Antonio Carlini arcarlini_at_iee.org
Received on Fri Mar 19 2004 - 14:27:31 GMT