|
Neohapsis is currently accepting applications for employment. For more information, please visit our website www.neohapsis.com or email hr@neohapsis.com |
Re: ... is dead too -- Isn't segmentation removed in x86-64 "Long" mode?
From: Bryan J. Smith (b.j.smith
ieee.org)
Date: Sun May 25 2003 - 23:44:28 CDT
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Mon, 2003-05-26 at 00:36, Maurice Hilarius wrote:
> And, to help you with that nasty cough, they DO accept and execute SSE AND
> SSE2 SIMD instructions as well. And do them quite efficiently.
Yes, I'm vastly impressed how AMD has approached its 64/128-bit MMX/XMM
SIMD/vector implementation in general on even its 32-bit processors by
adding microcode to leverage its powerful 3-issue FPU in the Athlon.
Then again, and I do not mean to offend any distinguished former Intel
employees here (especially since they have more knowledge of their
programs than I), but I feel Intel's "slap on something new" approach to
SIMD/vector, while continuing to neglect their 32-bit FPU designs, have
been rather "marketing-driven" to this point.
--
Bryan J. Smith, E.I. mailto:b.j.smithieee.org http://thebs.org
CCDA/CCNA CIWSA/MCIWA LPIC2/RHCE MCSA http://thebs.org/certs.pdf
-----------------------------------------------------------------
** May the naive Windows mob never rule over UNIX common-sense **
_______________________________________________
Axp-list mailing list
Axp-listredhat.com
https://www.redhat.com/mailman/listinfo/axp-list
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]