|
»
»
parallel Octave
|
View:
New views
11 Messages
—
Rating Filter:
Alert me
|
 |
parallel Octave
by Francesco Potortì
::
Rate this Message:
What is the current status of parallel Octave? In this moment the
<http://atc.ugr.es/javier-bin/mpitb> site on Octave MPITB does not respond, but the Google cache shows that the last news is from October 2008 and the last mentioned version of Octave is 2.9.12. Is that the way to go? Are there any other parallel Octave implementations? Anyone knows if MPITB can work with Octave 3? Am I completely out of line here? -- Francesco Potortì (ricercatore) Voice: +39 050 315 3058 (op.2111) ISTI - Area della ricerca CNR Fax: +39 050 315 2040 via G. Moruzzi 1, I-56124 Pisa Email: Potorti@... (entrance 20, 1st floor, room C71) Web: http://fly.isti.cnr.it/ _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: parallel Octave
by Jaroslav Hajek-2
::
Rate this Message:
On Sat, Mar 7, 2009 at 10:32 AM, Francesco Potorti` <Potorti@...> wrote:
> What is the current status of parallel Octave? In this moment the > <http://atc.ugr.es/javier-bin/mpitb> site on Octave MPITB does not > respond, but the Google cache shows that the last news is from October > 2008 and the last mentioned version of Octave is 2.9.12. > > Is that the way to go? Are there any other parallel Octave > implementations? Anyone knows if MPITB can work with Octave 3? Am I > completely out of line here? > If a simple SMP parallelism would suffice your needs, I have recently contributed the parcellfun (a parallel cellfun) function into OctaveForge/main/general. It is simple to use and quite efficient on systems implementing efficient process forking, such as GNU/Linux. cheers -- RNDr. Jaroslav Hajek computing expert & GNU Octave developer Aeronautical Research and Test Institute (VZLU) Prague, Czech Republic url: www.highegg.matfyz.cz _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: parallel Octave
by Jaroslav Hajek-2
::
Rate this Message:
On Sat, Mar 7, 2009 at 4:51 PM, Jaroslav Hajek <highegg@...> wrote:
> On Sat, Mar 7, 2009 at 10:32 AM, Francesco Potorti` <Potorti@...> wrote: >> What is the current status of parallel Octave? In this moment the >> <http://atc.ugr.es/javier-bin/mpitb> site on Octave MPITB does not >> respond, but the Google cache shows that the last news is from October >> 2008 and the last mentioned version of Octave is 2.9.12. >> >> Is that the way to go? Are there any other parallel Octave >> implementations? Anyone knows if MPITB can work with Octave 3? Am I >> completely out of line here? >> > > If a simple SMP parallelism would suffice your needs, I have recently > contributed the parcellfun (a parallel cellfun) function into > OctaveForge/main/general. > It is simple to use and quite efficient on systems implementing > efficient process forking, such as GNU/Linux. > > cheers > see also http://sourceforge.net/mailarchive/message.php?msg_name=69d8d540902270503u5921ec47k7285704190025d73%40mail.gmail.com RNDr. Jaroslav Hajek computing expert & GNU Octave developer Aeronautical Research and Test Institute (VZLU) Prague, Czech Republic url: www.highegg.matfyz.cz _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: parallel Octave
by Michael Creel
::
Rate this Message:
Francesco Potorti`-2 wrote: > > What is the current status of parallel Octave? In this moment the > <http://atc.ugr.es/javier-bin/mpitb> site on Octave MPITB does not > respond, but the Google cache shows that the last news is from October > 2008 and the last mentioned version of Octave is 2.9.12. > > Is that the way to go? Are there any other parallel Octave > implementations? Anyone knows if MPITB can work with Octave 3? Am I > completely out of line here? > > -- > Francesco Potortì (ricercatore) Voice: +39 050 315 3058 (op.2111) > ISTI - Area della ricerca CNR Fax: +39 050 315 2040 > via G. Moruzzi 1, I-56124 Pisa Email: Potorti@... > (entrance 20, 1st floor, room C71) Web: http://fly.isti.cnr.it/ > _______________________________________________ > Help-octave mailing list > Help-octave@... > https://www-old.cae.wisc.edu/mailman/listinfo/help-octave > > The last release of MPITB works fine with Octave 3.03. I haven't tried 3.04 yet. Compiling against Octave 3.5x a few weeks ago out of curiosity and ran into compilation problems. The MPITB web site is active, maybe you ran into a temporary down time. MIchael -- View this message in context: http://www.nabble.com/parallel-Octave-tp22385857p22409066.html Sent from the Octave - General mailing list archive at Nabble.com. _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: parallel Octave
by Michael Creel
::
Rate this Message:
The last release of MPITB works fine with Octave 3.03. I haven't tried 3.04 yet, but I would be surprised if there is any problem. I tried to use MPITB with Octave 3.1.5x a few weeks ago, and failed. The MPITB web site is active, maybe you ran into a temporary down time. Octave 3.01 and MPITB is available on the PelicanHPC live CD, with some example code, if you would like to try it out. Michael MIchael |
|
|
Re: parallel Octave
by Francesco Potortì
::
Rate this Message:
>If a simple SMP parallelism would suffice your needs, I have recently
>contributed the parcellfun (a parallel cellfun) function into >OctaveForge/main/general. >It is simple to use and quite efficient on systems implementing >efficient process forking, such as GNU/Linux. That's nice, thanks! I guess that its main usage is to exploit multicore and multicpu machines, right? Oh, and by the way, the documentations seems to imply the opposite of what you wrote above, that is, seems to say that Linux has not an efficient fork implementation. -- Francesco Potortì (ricercatore) Voice: +39 050 315 3058 (op.2111) ISTI - Area della ricerca CNR Fax: +39 050 315 2040 via G. Moruzzi 1, I-56124 Pisa Email: Potorti@... (entrance 20, 1st floor, room C71) Web: http://fly.isti.cnr.it/ _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: parallel Octave
by Jaroslav Hajek-2
::
Rate this Message:
On Mon, Mar 9, 2009 at 6:26 PM, Francesco Potorti` <Potorti@...> wrote:
>>If a simple SMP parallelism would suffice your needs, I have recently >>contributed the parcellfun (a parallel cellfun) function into >>OctaveForge/main/general. >>It is simple to use and quite efficient on systems implementing >>efficient process forking, such as GNU/Linux. > > That's nice, thanks! I guess that its main usage is to exploit > multicore and multicpu machines, right? Yes. > > Oh, and by the way, the documentations seems to imply the opposite of > what you wrote above, that is, seems to say that Linux has not an > efficient fork implementation. > Thanks, fixed. cheers -- RNDr. Jaroslav Hajek computing expert & GNU Octave developer Aeronautical Research and Test Institute (VZLU) Prague, Czech Republic url: www.highegg.matfyz.cz _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
paralell cellfun 'parcellfun'
by WMennerich
::
Rate this Message:
Thats exactly that what I was also searching for. Already the cellfun / arrayfun constructs can make your sources more readable (but often they are not faster than a for-loop). Does this function work with the 'standart-Octave' or are some multicore-subsystems needed? Does also a 'pararrayfun' exist? Maybe this function(s) should be core function(s) of octave since then you can use multiple cores in nearly each multithread situation (E.g. simulations with different parameter sets). Cheers, Wolfgang |
|
|
Re: paralell cellfun 'parcellfun'
by Jaroslav Hajek-2
::
Rate this Message:
On Wed, Mar 18, 2009 at 12:42 PM, WMennerich <W.Mennerich@...> wrote:
> > > Jaroslav Hajek-2 wrote: >> >> If a simple SMP parallelism would suffice your needs, I have recently >> contributed the parcellfun (a parallel cellfun) function into >> OctaveForge/main/general. >> It is simple to use and quite efficient on systems implementing >> efficient process forking, such as GNU/Linux. >> > > Thats exactly that what I was also searching for. Already the cellfun / > arrayfun constructs can make your sources more readable (but often they are > not faster than a for-loop). > Does this function work with the 'standart-Octave' or are some > multicore-subsystems needed? It should work in a normal Octave installation. I have only tested it with the development version; but it's likely it will work with 3.0.x as well. Note that it uses process forking, which is likely to be inefficient on Windows/Cygwin (windows provides no native support for the operation). On GNU/Linux, it scales great. > Does also a 'pararrayfun' exist? No, not yet. This carries some problems with optimally distributing the work. But eventually, I intend to implement pararrayfun using parcellfun. > Maybe this function(s) should be core function(s) of octave since then you > can use multiple cores in nearly each multithread situation (E.g. > simulations with different parameter sets). > I'm not that sure, given its limitations. But if people will want that to happen, I have no problem with it. -- RNDr. Jaroslav Hajek computing expert & GNU Octave developer Aeronautical Research and Test Institute (VZLU) Prague, Czech Republic url: www.highegg.matfyz.cz _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: paralell cellfun 'parcellfun'
by Francesco Potortì
::
Rate this Message:
>> Maybe this function(s) should be core function(s) of octave since then you
>> can use multiple cores in nearly each multithread situation (E.g. >> simulations with different parameter sets). > >I'm not that sure, given its limitations. But if people will want that >to happen, I have no problem with it. Maybe parcellfun could just be implemented inside cellfun, with an optional argument or an external global variable telling how many processors to use. -- Francesco Potortì (ricercatore) Voice: +39 050 315 3058 (op.2111) ISTI - Area della ricerca CNR Fax: +39 050 315 2040 via G. Moruzzi 1, I-56124 Pisa Email: Potorti@... (entrance 20, 1st floor, room C71) Web: http://fly.isti.cnr.it/ _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
|
|
Re: paralell cellfun 'parcellfun'
by Jaroslav Hajek-2
::
Rate this Message:
On Wed, Mar 18, 2009 at 9:58 PM, Francesco Potorti` <Potorti@...> wrote:
>>> Maybe this function(s) should be core function(s) of octave since then you >>> can use multiple cores in nearly each multithread situation (E.g. >>> simulations with different parameter sets). >> >>I'm not that sure, given its limitations. But if people will want that >>to happen, I have no problem with it. > > Maybe parcellfun could just be implemented inside cellfun, with an > optional argument or an external global variable telling how many > processors to use. > The practical problem is that parcellfun is m-file, while cellfun is compiled. Also, you still want a completely specialized code for uniprocess calls, so effectively you'd have two functions in one. But I'm not saying I'm completely against it, just it is premature now. -- RNDr. Jaroslav Hajek computing expert & GNU Octave developer Aeronautical Research and Test Institute (VZLU) Prague, Czech Republic url: www.highegg.matfyz.cz _______________________________________________ Help-octave mailing list Help-octave@... https://www-old.cae.wisc.edu/mailman/listinfo/help-octave |
| Free embeddable forum powered by Nabble | Forum Help |
