[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: NaN slowdown with some processors
From: |
David Bateman |
Subject: |
Re: NaN slowdown with some processors |
Date: |
Wed, 04 Jun 2008 11:24:11 +0200 |
User-agent: |
Thunderbird 2.0.0.12 (X11/20080306) |
David Bateman wrote:
>
> With a Core2 Duo 2.2GHz T7500 processor
>
> octave:3> a=zeros(300,300);tic;b=(1.0+a)*a;toc
> Elapsed time is 0.00938201 seconds.
> octave:4> a=zeros(300,300);tic;b=(NaN+a)*a;toc
> Elapsed time is 0.00932693 seconds.
>
Sorry this is also with Atlas 3.8.1 64bit SSE3 linked in. Not sure what
would be the result if I was using a 32bit build..
D.
--
David Bateman address@hidden
Motorola Labs - Paris +33 1 69 35 48 04 (Ph)
Parc Les Algorithmes, Commune de St Aubin +33 6 72 01 06 33 (Mob)
91193 Gif-Sur-Yvette FRANCE +33 1 69 35 77 01 (Fax)
The information contained in this communication has been classified as:
[x] General Business Information
[ ] Motorola Internal Use Only
[ ] Motorola Confidential Proprietary
- NaN slowdown with some processors, Olli Saarela, 2008/06/04
- Re: NaN slowdown with some processors, Marc Normandin, 2008/06/04
- Re: NaN slowdown with some processors, Michael Goffioul, 2008/06/04
- Re: NaN slowdown with some processors, David Bateman, 2008/06/04
- Re: NaN slowdown with some processors,
David Bateman <=
- Re: NaN slowdown with some processors, Fredrik Lingvall, 2008/06/04
- Re: NaN slowdown with some processors, Thomas Ilnseher, 2008/06/04
- Re: NaN slowdown with some processors, Olli Saarela, 2008/06/04
- Re: NaN slowdown with some processors, Dmitri A. Sergatskov, 2008/06/05