From mboxrd@z Thu Jan  1 00:00:00 1970
X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me
X-Spam-Level: 
X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00 autolearn=ham
	autolearn_force=no version=3.4.4
X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: 107f24,6f568a2e6507575
X-Google-Attributes: gid107f24,public
X-Google-Thread: f891f,6f568a2e6507575
X-Google-Attributes: gidf891f,public
X-Google-Thread: 103376,6f568a2e6507575
X-Google-Attributes: gid103376,public
X-Google-ArrivalTime: 2001-04-25 05:12:32 PST
Path: 
 newsfeed.google.com!newsfeed.stanford.edu!news.ems.psu.edu!news.litech.org!not-for-mail
From: jmv16@cornell.edu (Jeffrey M. Vinocur)
Newsgroups: comp.lang.ada,comp.lang.functional,comp.lang.misc
Subject: Re: Thoughts and Opinions or something like that
Date: Wed, 25 Apr 2001 12:12:32 +0000 (UTC)
Organization: Cornell University
Sender: jeff@litech.org
Message-ID: <9c6evg$em1$1@marduk.litech.org>
References: <HtiF6.5582$Tv2.757613@news6-win.server.ntlworld.com>
 <9c642e$of323@news.kvaerner.com>
NNTP-Posting-Host: marduk.litech.org
X-Trace: marduk.litech.org 988200752 15041 128.84.154.54 (25 Apr 2001 12:12:32
 GMT)
X-Complaints-To: usenet@litech.org
NNTP-Posting-Date: Wed, 25 Apr 2001 12:12:32 +0000 (UTC)
X-Newsreader: trn 4.0-test76 (Apr 2, 2001)
Originator: jeff@litech.org (Jeffrey M. Vinocur)
Xref: newsfeed.google.com comp.lang.ada:6919 comp.lang.functional:5286
 comp.lang.misc:1128
Date: 2001-04-25T12:12:32+00:00
List-Id: <comp.lang.ada>

In article <9c642e$of323@news.kvaerner.com>,
Tarjei T. Jensen <tarjei.jensen@kvaerner.com> wrote:
>
>As far as instructions are concerned I always fancied deviding branch
>instructions into two groups: Those who branch most of the time and those
>who seldom branch. The idea was that one could skimp on branch prediction on
>the CPU. For a while or for loop one would use the former type of
>instructions. Since I have heard of nobody who have done this I assume that
>the idea is not particularly good.

Well, the goal isn't to lessen branch prediction -- the silicon
is there either way -- but rather to reduce mispredicted
branches.  The most basic approach, I guess, is assume all
backwards branches will be taken -- this gets loops.  One
not-very-complicated approach is to cache whether a branch was
taken last time through and predict the same.  This approach,
however, does exactly what you suggest; it gets loop iterations
2,3,4,...,n-1 all correct.