login
Header Space

 
 

Re: Pentium

Score:
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Subject: Re: Pentium
Date: Monday, April 26, 1993 - 4:34 pm

In article <1r3rvs$omf@nz12.rz.uni-karlsruhe.de> s_titz@ira.uka.de (Olaf Titz) writes:

I won't say anything about your final statement; I've already seen the
flame-out over a similar sentiment expressed here.

I disagree with you on another point, however.  For Intel to withold
information on their P5 architecture in order to give microshaft (and
other companies willing to agree to whatever Intel's nondisclosure
requires) an advantage in writing an optimizing compiler is much worse
than anything Diamond or other hardware suppliers can do.  There are
a multitude of vendor choices when it comes to VGA cards; just how many
choices do you have when it comes to the CPU?

And why can Intel get away with it?  Because there are so many ignorant
people out there who will follow the crowd and listen to the salespeople
who pushes the P5.  Ninety-nine percent of the people who buy computers
don't care about the architecture of the CPU, as long as it runs the software
they want.  Even those users who develop applications typically purchase
a compiler for their work, so they don't really care about the machine
architecture.  It's only the very few: compiler writers, kernel hackers,
and others, who could benefit from the chip architecture being fully
disclosed.

So the burning question in my mind is, what is Intel gaining by not
disclosing the P5 architecture?  Or perhaps a more appropriate question
might be, what is Intel not losing? :-)

-- 
Kevin Sanders, KN6FQ                 NCR Torrey Pines
kevin.sanders@torreypinesca.ncr.com    (619) 597-3602
kevin%beacons@cyber.net
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: Pentium, Kevin Sanders, (Mon Apr 26, 4:34 pm)
speck-geostationary