Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!usc!snorkelwacker.mit.edu!bloom-beacon!eru!hagbard!sunic!mcsun!hp4nl!charon!dik
From: dik@cwi.nl (Dik T. Winter)
Newsgroups: comp.arch
Subject: Re: RISC integer multiply/divide (was Re: Snake)
Message-ID: <3237@charon.cwi.nl>
Date: 1 Apr 91 00:28:14 GMT
References: <32580004@hpcuhe.cup.hp.com> <1991Mar26.221120.6725@webo.dg.com> <6920@auspex.auspex.com>
Sender: news@cwi.nl
Organization: CWI, Amsterdam
Lines: 28

In article <6920@auspex.auspex.com> guy@auspex.auspex.com (Guy Harris) writes:
 > I saw something that indicated that integer multiply and divide
 > instructions have been added to HP-PA, and that the chips in the new
 > machine, I think, implement them.
Right.
 > 
 > I think the IBM ROMP had no integer multiply or divide instructions;
 > the POWER architecture does.
Also correct.
 > 
You may also mention the move in AMD 29k to the 29050.

 > Are there any remaining RISC holdouts that originally didn't have
 > integer multiply and divide, and that haven't added those instructions
 > to their architectures?

Now this is a bit slippery (checking the 32*32->64 bit multiply and
64/32->32,32 bit divide; this may be old hat, and, what is RISC?):
i860:	no integer multiply/divide, uses FP (slight support for multiply)
m88k:	full support (no remainder & no 64 bit res/src, uses FP)
amd29k:	full support (from 29050)
sparc:	full support (no remainder (from version 8))
mips:	full support (no 64 bit src for div/rem)
power:	full support (it appears when trying)
hppa:	full support (uses FP, might limit res/src to 32 bits, I am not sure)
--
dik t. winter, cwi, amsterdam, nederland
dik@cwi.nl