On Wed, 20 Apr 2005 10:06:15 -0700 (PDT)
Linus Torvalds [off-list ref] wrote:

I bet your SHA1 implementation is done with hand-optimized and scheduled
x86 MMX code or something, while my poor G5 is probably using some slow
generic routine. As a result, it only improved by 33% for me since the
compression was just part of the picture, but with your cheap SHA1 the
compression costs really dominated, and so it's almost four times faster
for you.

The openssl tree has a i586 optimized SHA1 implementation.
A quick scan of the 0.9.7e tree I happen to have lying around
shows there aren't optimized for other cpus in there, just i586.