Path: utzoo!dciem!array!colin
From: colin@array.UUCP (Colin Plumb)
Newsgroups: comp.arch
Subject: Re: All those bits (SIMD micros)
Keywords: vectorizing byte processors
Message-ID: <489@array.UUCP>
Date: 12 Aug 90 05:11:21 GMT
References: <1990Aug11.203944.10478@nlm.nih.gov>
Distribution: na
Organization: Array Systems Computing, Inc., Toronto, Ontario, CANADA
Lines: 18

Look at the Am29000 (and 29050, soon).  They have a CPBYTES instruction
which does what you want, 32 bits at a time.  They return
v1.b0 = v2.b0 || v1.b1 == v2.b1 || v1.b2 == v2.b2 || v1.b3 == v2.b3
so you can write strcmp as:

loop:
	word1 = *pointer1++;
	if (word1 != word2)
		goto notequal;
	if (cpbytes(word1,0) == FALSE)
		goto loop;

	<check trailing bytes>

Perhaps someone from AMD could comment on the difference it's made
to their string instructions.
-- 
	-Colin