[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: How to speed up Octave
From: |
Dmitri A Sergatskov |
Subject: |
Re: How to speed up Octave |
Date: |
Wed, 20 Jun 2001 20:24:41 -0600 (MDT) |
On 20 Jun 2001, Trond Eivind Glomsrod wrote:
>
> Yes, but I made 10 runs of each (and apart from the first run of each
> function, the
> results were very similar on different runs)
>
I do not quite understand how did you do 10 runs. Did you run 'rand'
once and the other function 10 times, or did you run rand + function
10 times?
Even though, on my pathetic AMD K6-III:
octave:1> tic;A=rand(20,20000);toc
ans = 0.63333
octave:2> tic;B=svd(A);toc
ans = 1.1776
octave:3> tic;A=rand(2000,2000);toc
ans = 5.9938
octave:4> tic;B=prod(A);toc
ans = 0.37541
octave:5> tic;A=rand(1000,1000);toc
ans = 1.5800
octave:6> tic;B=inv(A);toc
ans = 58.933
So as you can see except the 3d test 'rand' does take a significant portion
of the time. So for 'prod' test even if ATLAS speed things up 1000 times
it will show slightly less then 50% improvement :)
Dmitri.
-------------------------------------------------------------
Octave is freely available under the terms of the GNU GPL.
Octave's home on the web: http://www.octave.org
How to fund new projects: http://www.octave.org/funding.html
Subscription information: http://www.octave.org/archive.html
-------------------------------------------------------------
- Octave / Win 2000 memory limitations, Chris Mellen, 2001/06/15
- Re: How to speed up Octave, Dmitri A. Sergatskov, 2001/06/19
- Re: How to speed up Octave, Aaron Brick, 2001/06/19
- Re: How to speed up Octave, Francesco Potorti`, 2001/06/20
- Re: How to speed up Octave, Jonathan Drews, 2001/06/21