From: Andi Kleen <ak@suse.de>
To: "Nakajima, Jun" <jun.nakajima@intel.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Intel vs AMD x86-64
Date: 25 Feb 2004 00:49:19 +0100 [thread overview]
Message-ID: <p73n078598g.fsf@verdi.suse.de> (raw)
In-Reply-To: <7F740D512C7C1046AB53446D37200173EA2684@scsmsx402.sc.intel.com.suse.lists.linux.kernel>
"Nakajima, Jun" <jun.nakajima@intel.com> writes:
> Other than the standard IA-32 differences (eg. HT, SSE3, Intel Enhanced
> SpeedStep, etc.), there are few differences between the implementations
> of
> IA-32e and AMD64. The software visible ones are:
Thanks for the detailed list.
> BSF/BSR when source is 0 & operand size is 32:
> In 64-bit mode, the processor sets ZF, and the upper 32 bits of
> the destination are undefined. Should always check the ZF or do not
> use
> 32-bit operand size.
This one sounds a bit scary. I think it could hurt the
asm-x86_64/bitops.h:find_first_zero_bit if there is a race that
changes the value in memory between the last scasl and the bsfl
and the inliner assumes the edx output argument is zero extended.
Hopefully that case should be unlikely enough. I guess best would
be to change the function to use 64bit accesses to avoid this completely.
-Andi
next parent reply other threads:[~2004-02-24 23:49 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <7F740D512C7C1046AB53446D37200173EA2684@scsmsx402.sc.intel.com.suse.lists.linux.kernel>
2004-02-24 23:49 ` Andi Kleen [this message]
2004-03-02 23:22 Intel vs AMD x86-64 Nakajima, Jun
-- strict thread matches above, loose matches on Subject: below --
2004-02-26 1:19 Nakajima, Jun
2004-02-26 16:04 ` Timothy Miller
2004-02-27 3:16 ` Bill Davidsen
2004-02-25 20:07 Nakajima, Jun
2004-02-25 23:44 ` Timothy Miller
2004-02-26 0:13 ` H. Peter Anvin
[not found] <1sRYA-1uZ-23@gated-at.bofh.it>
[not found] ` <1sSi2-1NC-5@gated-at.bofh.it>
[not found] ` <1sT4l-2CW-17@gated-at.bofh.it>
2004-02-25 15:41 ` Bill Davidsen
2004-02-25 16:08 ` Moritz Muehlenhoff
2004-02-25 3:24 Nakajima, Jun
2004-02-25 16:22 ` Timothy Miller
2004-02-25 16:17 ` H. Peter Anvin
2004-02-25 17:18 ` Timothy Miller
2004-02-25 17:16 ` H. Peter Anvin
2004-02-25 19:05 ` Timothy Miller
2004-02-25 3:07 Nakajima, Jun
2004-02-24 23:15 Nakajima, Jun
2004-02-25 1:52 ` Chris Wedgwood
2004-02-24 21:01 Sean Fao
2004-02-24 21:26 ` Linus Torvalds
2004-02-24 22:21 ` Timothy Miller
2004-02-25 22:30 ` Davide Rossetti
2004-02-24 21:31 ` Timothy Miller
2004-02-24 21:31 ` Linus Torvalds
2004-02-24 21:28 ` Dave Jones
2004-02-26 21:39 ` Kai Henningsen
2004-02-24 2:42 Albert Cahalan
2004-02-24 16:44 ` Dave Jones
2004-02-24 15:11 ` Albert Cahalan
2004-02-24 17:34 ` Dave Jones
2004-02-24 15:29 ` Albert Cahalan
2004-02-24 18:07 ` Dave Jones
2004-02-23 19:59 Xose Vazquez Perez
2004-02-23 18:10 Nakajima, Jun
2004-02-24 13:25 ` Pavel Machek
2004-02-18 21:28 Peter Maas
2004-02-18 21:26 Peter Maas
2004-02-18 1:44 Linus Torvalds
2004-02-18 9:56 ` Mikael Pettersson
2004-02-18 14:31 ` Diego Calleja García
2004-02-18 18:17 ` Bryan O'Sullivan
2004-02-18 14:54 ` Stefan Smietanowski
2004-02-18 15:47 ` Linus Torvalds
2004-02-22 2:59 ` Herbert Poetzl
2004-02-22 3:12 ` Linus Torvalds
2004-02-22 3:39 ` Tomasz Rola
2004-02-22 3:47 ` Mike Fedyk
2004-02-22 4:12 ` Scott Robert Ladd
2004-02-23 0:38 ` Timothy Miller
2004-02-23 2:17 ` Tom Vier
2004-02-22 8:38 ` Geert Uytterhoeven
2004-02-22 10:00 ` Vojtech Pavlik
2004-02-23 15:51 ` Clay Haapala
2004-02-23 17:03 ` Adrian Bunk
2004-02-23 17:31 ` Linus Torvalds
2004-02-24 9:47 ` Kees Bakker
2004-02-24 9:59 ` viro
2004-02-24 10:59 ` Andrew Walrond
2004-02-23 18:56 ` Christoph Hellwig
2004-02-23 21:25 ` Rik van Riel
2004-02-23 21:36 ` Linus Torvalds
2004-02-23 21:48 ` David S. Miller
2004-02-23 22:08 ` Linus Torvalds
2004-02-23 22:06 ` David S. Miller
2004-02-23 22:56 ` H. Peter Anvin
2004-02-24 1:01 ` Thomas Zehetbauer
2004-02-24 1:11 ` John Heil
2004-02-24 13:32 ` Timothy Miller
2004-02-24 14:39 ` Scott Robert Ladd
2004-02-24 19:43 ` Rogier Wolff
2004-02-24 19:49 ` John Heil
2004-02-24 20:03 ` Mike Fedyk
2004-02-24 20:03 ` John Heil
2004-02-24 21:20 ` Timothy Miller
2004-02-25 18:40 ` Matt Seitz
2004-02-18 19:13 ` Aaron Lehmann
2004-02-19 6:02 ` Mikael Pettersson
2004-02-19 9:15 ` Terje Eggestad
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=p73n078598g.fsf@verdi.suse.de \
--to=ak@suse.de \
--cc=jun.nakajima@intel.com \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox