Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 9 Nov 1997 20:02:14 +0100
From:      j@uriah.heep.sax.de (J Wunsch)
To:        freebsd-chat@freebsd.org (FreeBSD chat list)
Cc:        perlsta@cs.sunyit.edu (Alfred Perlstein), rivers@dignus.com (Thomas David Rivers)
Subject:   Re: IDT processors?
Message-ID:  <19971109200214.ZJ19808@uriah.heep.sax.de>
In-Reply-To: <Pine.BSF.3.96.971109122904.18731A-100000@server.local.sunyit.edu>; from Alfred Perlstein on Nov 9, 1997 12:35:42 -0500
References:  <Pine.BSF.3.91.971108225631.5031B-100000@dot.ishiboo.com> <Pine.BSF.3.96.971109122904.18731A-100000@server.local.sunyit.edu>

next in thread | previous in thread | raw e-mail | index | archive | help
(Moved to chat.)

As Alfred Perlstein wrote:

> sorry for the rant, anyone know where  can get a bug free chip? someone
> has to be making them... :)

You're overly optimistic.  CPU bugs aren't anything new, and Intel
doesn't have a copyright on them either. :-)

When i started doing Unix, this was with Data General's DG/UX,
somewhere in 1991.  After some time, i was trying to debug a program
that constantly behaved differently under the debugger than straight-
through.  With quite a lot of effort, i had to find that the Motorola
MC88000 CPU simply botched some flags when doing hardware (instruc-
tion-level) tracing.  The result of some comparision has been marked
`less than', `equal', and `greater then' at the same time. :-O

Motorola has fixed the bug in later revisions of their CPU.

Data General had even a builtin ``silicon filter'' in their compiler,
to work around CPU bugs.  Maybe Thomas Rivers can tell us more about
it...  i know he's been one of the principal gcc hackers with DG back
in those days.

-- 
cheers, J"org

joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE
Never trust an operating system you don't have sources for. ;-)



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19971109200214.ZJ19808>