Pentium chips have f.p.u. error -- rounding error on division
i love my VAX!
jcole at LSUVAX.SNCC.LSU.EDU
Mon Nov 28 11:04:00 EST 1994
In article <3b31b9$4he at netnews.upenn.edu>, tromp at sanger.bcm.tju.edu (Gerard Tromp) writes
> Intel made some lame statement that it would affect average users only 9
>times in a billion. The basis for such probability statement is unclear. _HOWEVER_
>they also indicated that they would be willing to "work with scientists and
>engineers if their applications were likely to be affected". The full implication
>of the statement is unclear -- presumably one can obtain a corrected chip if it
>is evident that one's results are likely...
> Just thought everyone should be aware of the potential problem. Perhaps
>this is the source of some of the recent inconsistancies on DOS machines.
First, sorry about the annoying format...I am just getting used to this editor.
Anyway, I am a dedicated IBM user only when I can not get my hands on a DEC
APX-series machine. Let's face it, Intel has demonstrated once again their
slipshod approach to engineering and pseudo-foxes. I realize the Alpha
machines cost a lot more, but maybe you get what you pay for...90 mHz with
errors in the important stuff (how do you miss such a significant thing as a
buggy fpu?!), or >200 mHz (with BIG buses!) and real engineering.
Sorry to ramble...I am kinda fond of the guys at DEC...
John B. Cole
Graduate Research Assistant
Department of Dairy Science
Louisiana State University
Baton Rpuge, LA 70803
(all opinions herein are mine in their entirety, not LSU's...}:) )
More information about the Gen-link