80386 32-Bit Multiply Problems?

80386 32-Bit Multiply Problems?

Post by trim.. » Mon, 02 Apr 1990 22:49:00



The San Jose Mercury News today reported on "errors in the intel
32-bit chip when doingg a multiply of  32-bit value with another
32-bit value".

The article inferred that the greatest impact would be on the Compac
company who is shipping the largest number of 80386-based equipment
currently. It was inferred that intel would replace the current part
over the next n monthss (years).

A few questions:

        1) What IS the result of this operation? can someone post
        a result (pure intellectual curiosity).

        2) Has Intel posted this to the field with a position
        statement on part replacement?

This is meant to have no bearing on Intel as a parts producer and
supplier.  Merely my (personal) interest.

I'd type in the whole article but I'm not sure if it's legal.

Gary M. Trimble - Lockheed Advanced Marine Systems
UUCP: {(ucbvax!dual!sun) (ihnp4!qubix)}!sunncal!leadsv!trimble
      {{allegra ihnp4 dual}!fortune!decvax!decwrl}!amdcad!cae780!leadsv!trimble

--
Gary M. Trimble - Lockheed Advanced Marine Systems
UUCP: {(ucbvax!dual!sun) (ihnp4!qubix)}!sunncal!leadsv!trimble
      {{allegra ihnp4 dual}!fortune!decvax!decwrl}!amdcad!cae780!leadsv!trimble

 
 
 

80386 32-Bit Multiply Problems?

Post by g.. » Mon, 02 Apr 1990 21:34:00



>The San Jose Mercury News today reported on "errors in the intel
>32-bit chip when doingg a multiply of  32-bit value with another
>32-bit value".

>The article inferred that the greatest impact would be on the Compaq
>company who is shipping the largest number of 80386-based equipment
>currently.
[..]
>    1) What IS the result of this operation? can someone post
>    a result (pure intellectual curiosity).

[..]
        3) can it be easily worked-around in a compiler  0.25 * :-)

[ I can see it now 'the startup routine does a multiply and sees if
the result is right. If so, it arranges for the multiply emulation
trap to replace the INT ops with real multiply ops, and restart them..]
--
----------------------------------------------------------------------
Greg Smith     University of Toronto      UUCP: ..utzoo!utcsri!greg
Have vAX, will hack...

 
 
 

1. Japanese 32-bit micro can be a 68020 or 80386

There is an article in this week's "PC Week" magazine about a 32-bit micro
developed in Japan by a joint venture of a couple of major players there
(sorry, I don't have the article at hand) that has a writable control store
and thus can have different microprograms loaded into it to emulate the 80386,
68020 and others, apparently as a means of getting around microcode copyright
issues that have prevented Japanese manafacturers from cloning those processors.
It's called VM, for Virtual Microprocessor.

Even the immediate implications are stunning, I think.  One thing is that
those of us who have always wanted to diddle microcode may soon be able to,
tho' there won't be much software or software compatibility for those who
do (the Microprogramming Construction Set?).  It would be a boon to
researchers and others trying to implement oddball language architectures
and get them to execute efficiently on a CISC-type machine (Smalltalk, LISP,
etc.)

Another thing is that it could be more desirable to have a microprogrammable
machine than not, for the wider compatibility it could offer (a lot of work
required to implement that range of compatibility, though.)  

Imagine a version of the microprogrammable chip in which the operating system
could context switch among trusted sets of microprograms.  Weird.

Imagine a virtual personal computer which, on exactly the same hardware,
could be a DOS-compatible 80386 workstation or a 68020 workstation, with
microcode and software being the only differences.  How about a
Forth machine?  A Vax?

If tangible benefits beyond end-running microcode copyright issues are
provided, reasonably soon, American uP manafacturers will need to develop
their own microprogrammable machines, unless they're certain of their RISC
architectures, because people will buy them.  If the processor is only
used as a means of getting around the copyright problem, it's no big deal
to us as microprocessor consumers which we would use other than price,
performance and reliability, although I imagine it is regarded as a
very big deal by Motorola and Intel and any other manafacturers selling
processors that this processor can emulate.
--
"Now here's something you're really going to like!" -- Rocket J. Squirrel
..!{bellcore!tness1,uunet!nuchat}!sugar!karl, Unix BBS (713) 438-5018

2. Cannot install kernel debug DLLs for Win98

3. 32-bit architecture & 32-bit program

4. Trouble with Schema/TransformNode()

5. 80386 Multiply: quote from Intel

6. memory problems

7. Help! Seagate 32-bit Windows Driver Problems

8. I wonder if someone can help me please

9. 24-bit to 32-bit float

10. padding leading/trailing bytes to a crc-32/32-bit parallel generator for any byte length

11. WANTED: algorithm to perform 64-bit / 32-bit signed & unsigned divide

12. bring 32-bit executable to 64-bit processor (intel processor)