Invalid Instruction Sequences on i486 Query

Article View: comp.sys.intel

Article #45

#45

From: David C. Barber
Date: Sun, 01 Nov 1992 06:56

23 lines
1258 bytes

I have heard on several occasions that some instruction SEQUENCES don't
execute properly on the Intel 486DX.  This is reported to have caused
some programs that used certain sequences to fail on 486's.

While I can understand how a single instruction can fail to execute
properly (remember the 32-bit multiplies on early versions of the 80386)
I can see how (apparently) individual instructions worked ok on the 486,
yet some instruction sequences failed.

If anybody knows any details of these instruction sequence failures,
I'd be interested to hear the story.

I recommend contacting me by e-mail unless a lot of followup's to this
message are also asking for the same information.

Thanks.


Without change,                         *David Barber*
   nothing can ever get better.            @}-->----

UUCP: ucsd!crash!dbarber
INET: dbarber@crash.cts.com

Technical Details

Message-ID: <dbarber.720600998@crash.cts.com>

Path: arc1-ca.pugleaf.net!sparky!uunet!usc!sdd.hp.com!spool.mu.edu!agate!dog.ee.lbl.gov!news!nosc!crash!dbarber

Show Full Headers

Complete Article Headers

Newsgroups: comp.sys.intel
Path: arc1-ca.pugleaf.net!sparky!uunet!usc!sdd.hp.com!spool.mu.edu!agate!dog.ee.lbl.gov!news!nosc!crash!dbarber
From: dbarber@crash.cts.com (David C. Barber)
Subject: Invalid Instruction Sequences on i486 Query
Organization: CTS Network Services (crash, ctsnet), El Cajon, CA
Date: 1 Nov 92 06:56:38 GMT
Message-ID: <dbarber.720600998@crash.cts.com>
Lines: 23