[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Octave versus matlab performances on linux platform 64 bits
From: |
Sergei Steshenko |
Subject: |
Re: Octave versus matlab performances on linux platform 64 bits |
Date: |
Thu, 30 Oct 2008 10:52:53 -0700 (PDT) |
--- On Thu, 10/30/08, Peter Cloetens <address@hidden> wrote:
> From: Peter Cloetens <address@hidden>
> Subject: Re: Octave versus matlab performances on linux platform 64 bits
> To: address@hidden
> Cc: "Luca Tagliacozzo" <address@hidden>, "Jaroslav Hajek" <address@hidden>,
> address@hidden
[snip]
> This seems indeed very dependent on the BLAS library:
> On 3.0.1 with standard blas and lapack we get (with the
> m-code):
> tic;a=matpow(rand(1000),10);toc
> Elapsed time is 20.3305 seconds.
>
> and for the large problem
> tic;a=matpow(rand(3000),10);toc
> Elapsed time is 547.43 seconds.
>
> On 2.1.73 where we had mkl from intel (with the m-code and
> using 1 cpu):
> tic;a=matpow(rand(1000),10);toc
> ans = 3.7134
>
> and for the large problem
> tic;a=matpow(rand(3000),10);toc
> ans = 89.689
>
> This makes a factor of 6 for the same code.
> Peter
My result:
octave:6> tic;a=matpow(rand(3000),10);toc
Elapsed time is 76.59 seconds.
.
Which just proves that one should use custom-built ATLAS or faster
alternative.
Regards,
Sergei.