[PATCH] Minor performance improvement for AMD64 assembly routines

[Ulrich Drepper]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Nicholas Miell wrote:

> The Intel optimization manual does say to avoid using prefixes where
> possible in order to increase decoder throughput. When tuning for
> nocona, gcc doesn't generate the prefixes.

Exactly.  Which is why adding this patch to blended code is a bad idea.
 The prefix decoding in P4 cores is slow.

- --
➧ Ulrich Drepper ➧ Red Hat, Inc. ➧ 444 Castro St ➧ Mountain View, CA ❖
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.6 (GNU/Linux)

iD8DBQFBtPnm2ijCOnn/RHQRAklaAKCJiVsA+HSbZURtv5L054HiRi15dACfcHM5
TzaDgTVRKEtWibyB2Sv76Zg=
=EKuD
-----END PGP SIGNATURE-----