Thanks to all who sent me results of the bcopy benchmark --- sorry I
didn't mention that it might take days to execute.

I was a bit surprised by the results.  The two optimized versions were
between 65 and 105% faster on the '020, '040, and '060.  But there was
barely any improvement on '030 systems.  I don't know why --- the
benchmarks should be large enough to eliminate (or at least make
visable) any data cache effects.

I've been running a profiled kernel on one of my Sun 3's for the last
few months.  I've determined that bcopy() and bzero() are two of the
most expensive functions during a "make build" (at 5 and 6% respect-
ively).  I think the new code is a worthwhile microoptimization.

Again thanks for all the results,

	--jtc