PATCH: powerpc/strchr.S for BPs

[Greg McGary]

Greg McGary <greg@mcgary.org> writes:

> OK, I benchmarked it, and the upshot is that the overhead is in the
> noise at approx 0.8%.

Oops.  Wrongo.  I was off by an order of magnitude.  The slowdown is 8%.

> I suspected this all along, but didn't feel
> like arguing, because it would just come across as whining. 8^)
> Let this be an instructive case regarding optimizing for micro-efficiencies.

Let this be a lesson hasty interpretation of results.

Greg