> BTW, where's 'rep movsw'? memcpy_rep_movsl is pretty much the same as
> libc memcpy.

Indeed - however there is a significant saving in not using
rep movsb to move the odd bytes.
The setup cost for movsb is quite significant, on my athlon (IIRC)
the cost for rep movsl is such that it is only worth using
for moderate length copies - indeed using word copies for short
transfers and MMX for long transfers could easily be a win over
rep movsl.

However this is all cpu type dependant.
You need some figures from P3 and P4.

	David

-- 
David Laight: david@l8s.co.uk