Xref: utzoo comp.sys.intel:1083 comp.arch:13092
Path: utzoo!utgpu!jarvis.csri.toronto.edu!cs.utexas.edu!usc!apple!voder!pyramid!weitek!jetsun!goss
From: goss@jetsun.WEITEK.COM (Richard Goss)
Newsgroups: comp.sys.intel,comp.arch
Subject: 386 pipelined addressing mode
Message-ID: <858@jetsun.WEITEK.COM>
Date: 10 Jan 90 17:50:30 GMT
Reply-To: goss@jetsun.WEITEK.COM (Richard Goss)
Distribution: comp.sys.intel
Organization: WEITEK, Sunnyvale CA
Lines: 9

I have heard in the past that running the 386 in pipelined addressing mode
degrades performance compared to running in non-pipelined mode with the 
appropriate wait states.  I heard it had something to do with the bus
interface unit starting a bus cycle when the execution unit needs to take a 
branch, jump, etc. and having to wait for this useless bus cycle to complete 
and then be flushed. Someone said the degradation was around 12% on average.
Could someone please confirm this.

Thank you.