Re: Multithreaded Atlas can be used by GCC-4.3.3-sjlj-mingw-TDM (Was Re: Sjlj vs dwarf2 on mingw for octave)

[Tatsuro MATSUOKA]

Hello

I have now preparing external libraries for mingw build. 
But it takes sometimes because new class will begin from April in my university.

If you would like to challenge for Msys+mingw build, it will be help the 
following

http://www.tatsuromatsuoka.com/octave/Eng/Win/

0001 ReadmeMingwOct3.0.2.txt, 24,267 bytes, 2008-09-22, md5 
9abc713c9eb45356fe84c4f09bd884f7, You 
must read before install.

0002 octave-3.0.2.mingw.tar.bz2, 66,465,129 bytes, 2008-09-22, md5 
ff626e21fe205d7a1930cf7d4545f410f,
Octave-3.0.2+octave-forge 20080831 (by Tatsuro Matsuoka Not Benjamin) for 
Mingw(Octave-Forge Partly
supportted but supported Forge).


You can use the libraries in the package for mingw build.
Some information in ReadmeMingwOct3.0.2.txt is old. Some urls are changed. In 
the case, you can find
new information by Google.

Regards

Tatsuro   

--- Tatsuro MATSUOKA  wrote:

> Hello
> 
> 
> 
> > If I use dw2 version of gcc-4.3.3, griddata3.m cannot be executed due to 
> > the error of pthread
> > mutex.
> > （I do not remember in detail.）
> 
> I found the comment on Octave thread in Japan.
> 
> assertion !pthread_mutex_lock ( &(ROOT->mutex) ) failed, line 74 of file
> /home/atlas/atlas3.8.2-gcc4.3.3-2/../ATLAS3.8.2 
> //src/pthreads/misc/ATL_signal_tree.c 
> 
> At that time I used ATLAS3.8.2 but the same error happens at the case of 
> ATLAS3.8.3.
> 
> This is perhaps because pthread-win32 is made for gcc witb sjlj-EH but I do 
> not have any
> evidence 
> for that.
> 
> Regards
> 
> Tatsuro
> 
> 
>  
> --- Tatsuro MATSUOKA  wrote:
> 
> > Hello
> > 
> > I wrote prevously
> > > Sjlj octave-3.0.4RC7
> > > octave.exe:2> testOregoB
> > > ans =  1.5469
> > > 
> > > Dwarfs octave-3.0.4RC5
> > > octave:3> testOregoB
> > > ans =  1.1875
> > 
> > The speed of octave interpreter that built by dw2-eH is 25-30% faster than 
> > that by sjlj-EH on
> > mingw-GCC-4.3.3-TDM.
> > 
> > However I found that the merit of sjlj EH on the view point of 
> > multithreaded ATLAS. 
> > 
> > By gcc-4.3.3 mingw (sjlj), I found that multithreaded atlas can be used, 
> > without error by
> > configured
> > with the following
> >  
> > ../../octave-3.0.4RC7/configure --prefix=/c/Programs/octave-3.0.4RC7s
> > --with-blas=--with-blas='-lptf77blas -latlas -lpthread'
> > 
> >  
> > d:\usr\Tatsu\mingwhome\octaves\octave-3.0.4RC7\scripts/geometry\griddata3.m 
> >  PASS    2/2
> > 
> > If I use dw2 version of gcc-4.3.3, griddata3.m cannot be executed due to 
> > the error of pthread
> > mutex.
> > （I do not remember in detail.）
> > 
> > The speed check by 
> > n=2000; A=randn(n); B=randn(n);tic; C=A*B; t=toc, MFLOPS=2*n^3/t*1e-6
> > 
> > MFLOPS =  4970.9 (Ht-Pentium-4 prescott 3.4GHz)
> > 
> > On the other hand single thread ATLAS by GCC-4.3.3-dw2 on the same 
> > computer, 
> > n=2000; A=randn(n); B=randn(n);tic; C=A*B; t=toc, MFLOPS=2*n^3/t*1e-6
> > 
> > MFLOPS = 4830.2 
> > 
> > The multithreaded atlas is a little bit faster than the single thread atlas 
> > even though 
> > one physical core with hyper-threading.
> > (On GotoBLAS with smp on for my computer is slower than that by single 
> > thread.)
> > 
> > If the multi-thread atlas to Core2Duo and so on, the merit of sjlj EH may 
> > exist.
> > 
> > Of course, the data should be accumulated for other computers.
> > I will distribute the dependency library kit for mingw in thre near future 
> > on my web.
> > 
> > Similar kind of experiments on Unix are also to be useful for users who 
> > would like to carry
> out
> > fast
> > Matrix calculation of large n (n x n).
> > 
> > Regards
> > 
> > Tatsuro 
> > 
> 
> 
> --------------------------------------
> Power up the Internet with Yahoo! Toolbar.
> http://pr.mail.yahoo.co.jp/toolbar/
> 


--------------------------------------
Power up the Internet with Yahoo! Toolbar.
http://pr.mail.yahoo.co.jp/toolbar/