Re: Evidence of an insidious Pentium Bug?

Subject: Re: Evidence of an insidious Pentium Bug?
From: Erik Naggum <erik@naggum.no>
Date: 1999/09/03
Newsgroups: comp.lang.lisp
Message-ID: <3145341043550221@naggum.no>

* "David McClain" <dmcclain@azstarnet.com>
| The code snippet below compiles to a harmless and correct sequence of
| Pentium instructions, yet the version that negates by subtraction from
| zero works correctly while the direct negation with "FCHS" fails, in the
| routines "catanh" and "catanhx".

  why post this in ML when you're really trying to show a problem in the
  Pentium?  I'd appreciate the assembly listing and discussion about that.

| My confidence in the Pentium architecture has now been quite badly shaken!

  wow, it took you this long?  ;)

#:Erik
-- 
  save the children: just say NO to sex with pro-lifers