Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!ll-xn!ames!oliveb!pyramid!csg
From: csg@pyramid.UUCP (Carl S. Gutekunst)
Newsgroups: comp.arch
Subject: Re: Branch prediction in the 532
Message-ID: <2366@pyramid.UUCP>
Date: Sun, 10-May-87 04:20:42 EDT
Article-I.D.: pyramid.2366
Posted: Sun May 10 04:20:42 1987
Date-Received: Sun, 10-May-87 11:35:51 EDT
References: <324@dumbo.UUCP> <809@killer.UUCP> <2417@homxa.UUCP>
Reply-To: csg@pyramid.UUCP (Carl S. Gutekunst)
Organization: Pyramid Technology Corp., Mountain View, CA
Lines: 13

>> Has anyone bothered to think about adding branch instructions that tell
>> the CPU explicitly whether or not they expect to be taken?  For example,
>> Compilers would be able to pick the instructions they wanted.
>
>The CRISP Microprocessor has a single flag bit (call it True/False), and four
>conditional branch instructions: 

The Pyramid CPU uses a similar arrangement, with two instructions: "Branch on
False Condition" and "Branch on True Condition." Each has the usual assortment
of condition code tests. I never remember which assumes branch taken and which
assumes it's not; fortunately the compilers don't get similarly confused. :-)

<csg>