Re: FC3 x86_64 math functions slowdown

• To: For users of Fedora Core releases <fedora-list@xxxxxxxxxx>
• Subject: Re: FC3 x86_64 math functions slowdown
• From: Ulrich Drepper <drepper@xxxxxxxxxx>
• Date: Sat, 09 Jul 2005 21:53:39 -0700
• In-reply-to: <[email protected]>
• List-archive: <https://www.redhat.com/archives/fedora-list>
• List-help: <mailto:[email protected]?subject=help>
• List-id: For users of Fedora Core releases <fedora-list.redhat.com>
• List-post: <mailto:[email protected]>
• List-subscribe: <http://www.redhat.com/mailman/listinfo/fedora-list>, <mailto:[email protected]?subject=subscribe>
• List-unsubscribe: <http://www.redhat.com/mailman/listinfo/fedora-list>, <mailto:[email protected]?subject=unsubscribe>
• Organization: Red Hat, Inc.
• References: <[email protected]>
• Reply-to: For users of Fedora Core releases <fedora-list@xxxxxxxxxx>
• User-agent: Mozilla Thunderbird 1.0.2-7 (X11/20050623)

D. Angelis wrote:
> I have noticed a significant (up to 5 times !!!) slowdown of some math
> functions in /lib64/libm.so.6 (glibc-2.3-5) shipped with FC3
> compared to the version (glibc-2.3.3) shipped with SuSe 9.1.

Very simple explanation: the other code uses non-standard math functions
which are optimized for the processor but don't produce the same
results.  Remember, I can arbitrarily fast compute wrong results.

-- 
➧ Ulrich Drepper ➧ Red Hat, Inc. ➧ 444 Castro St ➧ Mountain View, CA ❖

• Follow-Ups:
  • Re: FC3 x86_64 math functions slowdown
    • From: Tony Nelson

• References:
  • FC3 x86_64 math functions slowdown
    • From: D. Angelis

• Prev by Date: Re: Can't Configure System Settings Anymore
• Next by Date: Bluetooth USB devices
• Previous by thread: FC3 x86_64 math functions slowdown
• Next by thread: Re: FC3 x86_64 math functions slowdown
• Index(es):
  • Date
  • Thread