String Functions for x86-64

[Menezes, Evandro]

Ulrich, 

> Where is the (reproducible) data to support that claim?  I 
> have no reason to believe you.

Using the string/test-* programs and comparing the data for the proposed routines and the current ones, I compared their performance on an Athlon 64 system (2.2GHz, DDR PC3200) and on a P4 one (3.2GHz, DDR2 PC2-3200).  As the case requires, I'll also send the performance using a home-grown test.

I'll send a report on each routine separately, hopefully with enough data to demonstrate their performance.

Thanks,

-- 
_______________________________________________________
Evandro Menezes               AMD            Austin, TX