Subject: Re: Performance of various memcpy()'s
To: David Laight <david@l8s.co.uk>
From: Bang Jun-Young <junyoung@mogua.com>
List: port-i386
Date: 10/23/2002 02:16:40 
On Wed, Oct 16, 2002 at 12:58:52PM +0100, David Laight wrote:
>       rep movsw                                          1.619813 s
>       asm loop                                           1.190194 s
>       MMX memcpy using MOVQ                              1.024688 s
> 
> where the 'rep movsl' and 'asm loop' are:
> 
> 
> #include <machine/asm.h>
> 
> ENTRY(memcpy_rep_movsl)

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

Jun-Young

-- 
Bang Jun-Young <junyoung@mogua.com>