[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: False alarm (Re: reshape slowdown?)
From: |
Dmitri A. Sergatskov |
Subject: |
Re: False alarm (Re: reshape slowdown?) |
Date: |
Tue, 22 Feb 2005 12:18:52 -0700 |
User-agent: |
Mozilla Thunderbird 0.9 (X11/20041127) |
John W. Eaton wrote:
...
Transpose is not implemented with lapack or blas functions. I suppose
it could be due to changing from 2-d to N-d arrays, but I don't see
anything obvious that would account for a slowdown.
On Athlon MP 2000 MHz:
octave:3> s=rand(3000);
octave:4> tic; a=s'; toc
ans = 1.9846
On Athlon XP 1666 MHz -> 0.9 second.
The only difference between those machines
is lapack library...
Also on MP computer the time was almost 1/2 of that
back in June (octave.2.1.57)...
I am still looking at it, but I am really puzzled.
jwe
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
-------------------------------------------------------------
- reshape slowdown?, Dmitri A. Sergatskov, 2005/02/21
- Re: reshape slowdown?, David Bateman, 2005/02/22
- Re: reshape slowdown?, John W. Eaton, 2005/02/22
- False alarm (Re: reshape slowdown?), Dmitri A. Sergatskov, 2005/02/22
- False alarm (Re: reshape slowdown?), John W. Eaton, 2005/02/22
- Re: False alarm (Re: reshape slowdown?),
Dmitri A. Sergatskov <=
- Re: False alarm (Re: reshape slowdown?), Francesco Potorti`, 2005/02/23
- Re: False alarm (Re: reshape slowdown?), mavram, 2005/02/23
- Re: False alarm (Re: reshape slowdown?), Paul Kienzle, 2005/02/23
- Re: False alarm (Re: reshape slowdown?), Dmitri A. Sergatskov, 2005/02/25
- Re: False alarm (Re: reshape slowdown?), John W. Eaton, 2005/02/23