Code covered by the BSD License  

Highlights from
Multicore - Parallel processing on multiple cores

4.74074

4.7 | 64 ratings Rate this file 123 Downloads (last 30 days) File Size: 44.7 KB File ID: #13775

Multicore - Parallel processing on multiple cores

by

 

26 Jan 2007 (Updated )

This package provides parallel processing on multiple cores/machines.

| Watch this File

File Information
Description

This package provides parallel processing on multiple cores on a single machine or on multiple machines that have access to a common directory.

If you have multiple function calls that are independent of each other, and you can reformulate your code as

for k = 1:numel(parameterCell)
  resultCell{k} = myfun(parameterCell{k});
end

then, replacing the loop by

resultCell = startmulticoremaster(@myfun, parameterCell);

allows you to evaluate your loop in parallel. All you need to do is to start as many additional Matlab sessions/processes as you want slaves to work, and to run

startmulticoreslave

in those additional Matlab sessions.

Everything is programmed in plain and platform-independent Matlab - no toolboxes are used, no compilation of mex-files is necessary.

Please get started with 1. the documentation in file multicore.html, 2. the help lines of function startmulticoremaster.m and 3. the demo function multicoredemo.m.

Discuss with other users here: http://groups.yahoo.com/group/multicore_for_matlab

I have spent many hours to develop this package. If you would like to let me know that you appreciate my work, you can do so by leaving a donation: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=GPUZTN4K63NRY

Keywords: Parallel processing, distributed computing, multiple cores.

Acknowledgements

This file inspired Batch Job and Distributed Batch Job.

Required Products MATLAB
MATLAB release MATLAB 7.5 (R2007b)
Tags for This File   Please login to tag files.
Please login to add a comment or rating.
Comments and Ratings (76)
26 Mar 2014 David

I added this bit of code to startmulticoremaster so that it automatically starts the appropriate amount of slaves (make sure your path is setup properly so that it can find startmulticoreslave.m upon startup):

% Start slaves:
max_instances = 4;
[status,result] = system('tasklist /FI "imagename eq matlab.exe" /fo table /nh');
currently_running = length(strfind(result,'MATLAB.exe'));

for i = 1:(max_instances-currently_running)
!"C:\Program Files\MATLAB\R2013b\bin\matlab.exe" -nodisplay -nosplash -nodesktop -r "run('startmulticoreslave.m');exit;"
end

20 Jan 2014 Erd

Package is quite useful. If it was not using variable transfer based on files but direct memory, then it would have been much more useful. Currently it takes a while for the parallel processes to start, since there is a large overhead

30 Apr 2013 David Trebing  
21 Dec 2012 Yulin

I test this code and compared with parfor

Elapsed time running STARTMULTICOREMASTER: 4.80 seconds.
Elapsed time running STARTMULTICOREMASTER: 4.72 seconds.
Elapsed time running STARTMULTICOREMASTER: 4.70 seconds.
Elapsed time running STARTMULTICOREMASTER: 4.69 seconds.
Elapsed time running STARTMULTICOREMASTER: 4.70 seconds.
Elapsed time without slave support: 20.84 seconds.

and with parfor only
Elapsed time running TESTFUN with parfor only: 3.21 seconds.

it seems that parfor is more powerful and simple to use.

06 Dec 2012 Alan Mackay

Very useful tool for running parallel sessions. With a few minor tweaks to code, primiarly additional 'set up' and 'clean up' functions to handle opening and closing minimalist slave sessions, I have run this across multiple cores on the same machine and across multiple machines too.

Currently running this quite happily with ~23/24 sessions.

06 Dec 2012 Alan Mackay  
25 Nov 2012 Tim

Great, works exactly as described! It's a bit ridiculous that this functionality isn't included natively in Matlab considering how much we pay for the software.

04 Oct 2012 haidi

Hi, has anyone been successful using this package for a larger scale. In my case, it actually does not work very well when running on 100 cores. For some reasons the slave got stuck in a loop with the message "Ignoring old semaphore of file"???

28 Sep 2012 haidi

Great work!!
Is there a way to use this package without having to manually starting Matlab?
The reason I ask the question is as follows. I use Torque to submit to a cluster of 16 nodes, each node having 64 cores. However, I cannot start multiple matlab instances in a single node (even it has 64 cores). Your help is greatly appreciated!!! Many thanks.

23 Aug 2012 Pink_panther

I activated only 3 slaves. Demo works great on my 8 core laptop! Be sure each session has path set to see the multicore folder.

>> multicoredemo
Elapsed time running STARTMULTICOREMASTER: 7.04 seconds.
Elapsed time running STARTMULTICOREMASTER: 7.39 seconds.
Elapsed time running STARTMULTICOREMASTER: 7.35 seconds.
Elapsed time running STARTMULTICOREMASTER: 6.74 seconds.
Elapsed time running STARTMULTICOREMASTER: 6.77 seconds.
Elapsed time without slave support: 20.86 seconds.
Elapsed time running TESTFUN directly: 19.84 seconds.

23 Aug 2012 Pink_panther  
23 Aug 2012 Pink_panther  
26 Jul 2012 Phil Corbishley

Works very well, thanks

28 Nov 2011 Rohit Verma

I tried running my function simultaneously with 3 different datasets together, but the slave processes doesnt do anything and the time is the same as if I am running without it.

28 Nov 2011 Rohit Verma

Can I use it for running multiple processes accessing the same function using different parameter cell. Please note that the function takes in image input in each call. Will that be a problem ?

Thanks very nice code

28 Nov 2011 Zhanhong

Great Package! Definitely useful for multicore CPUs. I have a 6 core AMD. It's such a pain if MATLAB can't run parallel.
I have a demo tip for newbies:
If you want to see the effect, make sure your function have to run at least several times on the input cell. If your function only has one input, all the slave sessions will be doing nothing because the function is already running on master. You'd probably want to make your input into segments to make all the slaves run simultaneously.

19 Nov 2011 laoya

The tool is really powerful. I want to know if we can develop a similar tool by Fortran or C language. There are two reasons:
1) since every master and slave program need a matlab window, it is too expensive to buy multiple licenses of Matlab to run on different machines;
2) the slave program is launched by matlab, which will also need more than 100 MB memory, however, maybe the slave program only need to launch another external execute program with different parameters. Write a pure master/pure program will decrease the memory usage greatly.

Thanks,
Zhanhgong Tang

31 Oct 2011 Jason D  
29 Jul 2011 Christopher Carr  
29 Jul 2011 Christopher Carr  
29 Jul 2011 Christopher Carr  
16 Jun 2011 Giovanni Bracco

Simply wonderful!
I have an optimization problem -including several launches of a Simulink model- running on a single core in a little more than 30 hours. By reformulating the problem as required by the Marcus' scripts (half a day work) I'm currently using five Windows PCs with a total of 14 cores and carrying out the simulation in 3.1 hours.
Thank you!!!

16 Jun 2011 Giovanni Bracco  
12 Jun 2011 Xinghua Lou

Hi Markus,

Great work!

I may have one suggestion: the file I/O becomes a bottleneck in my application since saving the meta-data of a task (large image sequences) costs almost as much time as processing the task. Maybe it helps a lot if the file I/O can be replace by shared memory functions and there is a new Matlab library for use: http://www.mathworks.com/matlabcentral/fileexchange/28572-sharedmatrix. I think it is a perfect complement to your library.

Best,
Xinghua

25 Feb 2011 Darin McCoy

nevermind my previous comment.....i didnt read the instructions :)

5 stars for the m file and 6 stars for customer service. Thanks Markus!

23 Feb 2011 Darin McCoy

No improvement running the multicoredemo.m file

Elapsed time running STARTMULTICOREMASTER: 21.53 seconds.
Elapsed time running STARTMULTICOREMASTER: 21.67 seconds.
Elapsed time running STARTMULTICOREMASTER: 21.31 seconds.
Elapsed time running STARTMULTICOREMASTER: 21.31 seconds.
Elapsed time running STARTMULTICOREMASTER: 21.30 seconds.
Elapsed time without slave support: 21.14 seconds.
Elapsed time running TESTFUN directly: 20.00 seconds.

11 Dec 2010 Johnny Ta

awesome. you're my savior. the code works like charm!

04 Oct 2010 Torfinn

Thank you for these tools, they are vastly useful and will save me much time.

26 Sep 2010 Hamid Badi

Great

26 Sep 2010 Hamid Badi  
11 Dec 2009 Robert Stead

I'm having problems with the lasterror function in this code. There appear to be several instances where the lasterror function is passed a string 'reset' as an input argument, but the function lasterror is only defined for inputs of structure type. This causes errors at several points in the code, and I am unable to run the multicoredemo routine. I'm sure this is something I'm doing wrong, but I'd be grateful if someone could help me!

04 Nov 2009 Karl

Hi Markus,

first of all -- you've developed a great tool that helps me a lot with my simulations in the field of audio signal processing. Seeing my dual quad core at 100% (instead of 13%) load warms my heart :).

Well, I'm not sure whether I'm getting something wrong here, but I had some problems when the function that is executed by the multicoremaster() (and the slaves) has more than one return value. It seems that in this case all but the first return values get lost. I applied a little trick that I found out about some time ago to solve this problem:
Everytime that feval() is called (in startmulticoremaster() and startmulticoreslave() ) I added something like this:

N_returnValues = nargout(functionHandleCell{k});
clear('returnValue'); % this is dirty! The next call doesn't work
% without clearing "returnValue" beforehand if
% N_returnValues==1. If it's greater->no
% problem (even without clearing
% "returnValue")
[returnValue{1:N_returnValues}] = feval(functionHandleCell{k}, parameterCell{k}{:}); % ha!
resultCell{k} = returnValue;

Doing so, the resultsCell that is returned from startmulticoremaster() is always a cell -- even if the called function has only one return value...

I hope this is of any value to anybody and that I'm not causing trouble by posting this hack :). I'm always open to learn a better solution....

Cheers, and thanks again for Multicore!

Karl

04 Nov 2009 Karl  
24 Oct 2009 DAdler

Thank you very much for this great tool! I started using your code a few of months ago, and I must say it saved me lots of hours of work.

28 Sep 2009 Johannes Wunsch

Awesome tool, I use it for fitting a computationally expensive financial model and it works just great. Thanks a lot for publishing it!! Johannes

16 Sep 2009 Amir

I have little bit of problem running the master and slave processes over the network. I am not sure how to share the folder over a linux network!
Anybody can help?

25 Aug 2009 German

sorry just missed to start a second matlab session with "startmulticoreslave".
Great code.

24 Aug 2009 German

Hello, when i am running the multicoredemo, only the master is working, but not the slave. What am i doing wrong?
multithreading unabled/ is set to one core.
I use a duo core processor with windows vista and Matlab 7.8.0 R2009a 64-bit.
Thank you very much.

23 Jul 2009 Nir

Great Work !
Speeds up my work more than twice on a quad computer. Not much change had to be done in order to use it.
Thanks
Nir

03 Jun 2009 Thomas

Great tool!

02 Jun 2009 dpb10  
02 Apr 2009 Richard

Brilliant tool! Great being able to sit back and watch a progress bar sliding along as a room full of computers gets to work doing your simulation.

I have a question though - what dimensions are typically used for parameterCell? I've tried doing some large multidimensional runs (e.g. 4x150x10) and things seemed to grind to a halt - I'm still looking into it, just wondered if the dimensions I'm using are typical or too large.

Cheers. Great work,
Richard.

18 Feb 2009 Richard Crozier

Fantastic program, and particularly suited to my work with genetic algorithms. There is one mnor error I've noticed though. In startmulticoreslave, if you activate debug mode you reach the following line (77):

fileNr = str2double(regexptokens(parameterFileName,...
'parameters_\d+_(\d+)\.mat'));

But there is no regexptokens function, at least there isn't in R2007a or R2007b or R2008a. My solution is to replace this with the following lines (although I'm sure someone could come up with something more robust and/or elegent).

fileNrCell = regexp(parameterFileName,'parameters_\d+_(\d+)\.mat', 'tokens');

fileNr = str2double(fileNrCell{1});

The program is excellent though, thanks again!

10 Feb 2009 Markus Buehren

I have opened a discussion group for the Multicore package on Yahoo. Please join and discuss with other users!

http://groups.yahoo.com/group/multicore_for_matlab/

05 Feb 2009 Moody

I've been using multicore for a while now and its absolutely excellent. I'm running on 5 dual xeon x5460 as well as a couple of quad core boxes.

I was wondering if anyone compared performance of this toolbox with the parfor parallel computing matlab toolbox. Are they comparable?

I believe I'm bottlenecked now due to the hard disk I/O, so I was looking at the in memory possibilities of this or potentially upgrading my hd's to solid state to reduce the overhead.

BTW, I also tried precreating all the mat files once instead of doing multiple loops to reduce the I/O. Unfortunately, that didn't help as much as I hoped.

Don't get me wrong though, this is much, much, much faster than single threading, but as always we need to keep pushing :).

30 Jan 2009 Andrew Scott  
25 Jan 2009 Jordi Arnabat

Thanks for this great contribution, it's very useful.

Correction:
I've used in under a grid of computers running different OS: GNU/Linux, Mac and Windows (XP). When the shared folder is on a network computer (not mapped to a local drive, for example: \\servername\sharedfolder); Windows systems fail trying to delete the semaphores, causing the master process run forever.

The solution I found is to slightly modify compsep.m and concatpath.m as follows:

_______________________________________________________
function str = chompsep(str)
unix_sep = '/';
pc_sep = '\';

if isunix && str(1)==pc_sep
str = strrep(str, pc_sep, unix_sep);
elseif ispc && str(1)==unix_sep
str = strrep(str, unix_sep, pc_sep);
end

if ~isempty(str) && (str(end) == unix_sep || str(end) == pc_sep)
str(end) = '';
end

_______________________________________________________
function str = concatpath(varargin)
unix_sep = '/';
pc_sep = '\';

str = '';
for n=1:nargin
curStr = varargin{n};
str = fullfile(str, chompsep(curStr));
end

if isunix && str(1)==pc_sep
str = strrep(str, pc_sep, unix_sep);
elseif ispc && str(1)==unix_sep
str = strrep(str, unix_sep, pc_sep);
end

24 Jan 2009 Vasilis Kapetanidis

Thank you! This works just fine and now I have 100% CPU usage on all 4 cores! By measuring the elapsed time it seems that it runs about 3.4 times faster than with a single matlab doing all the work, so that's about 85% efficient on my quad-core

now, if only this could run on a single multi-core machine with only one matlab instance running

12 Jan 2009 Arturo Serrano  
07 Jan 2009 Arturo Serrano

I got the same problem as Rohaly. When master ends the computation, and there is a slave still working, the master computes the remaining job again, yielding an extra iteration.
The solution is to set MAXMASTEREVALUATIONS, with all its drawbacks, since i understand that this isn't a bug rather than a problem not knowing if the slave got interrupted.

BTW, it works like a charm.

21 Dec 2008 Marcio Sales

I tested the functions on two dual core machines. I had great gain when paralellizing processing between the processors of dual core machine or between the two machines using a single processor in each. However, I had no significant gain when trying to using both processors on both machines. Is that because the gain of using more processors is being reduced by increased load of data recording when you add more processors/machines? Also, there are times when I get an error in which one of the workers can't delete the temporary files and this seems to happen more frequently when you increase the number of workers. Is anyone having the same issues? My two machines run Vista 64bits.

19 Dec 2008 Janos Rohaly

It seems there is the possibility for master and slave to simultaneously evaluate the same set of parameters. For example, if slave starts evaluating a slow process, master can catch up, and there is nothing to prevent it to start the very same computation since slave hasn't generated the result file yet. There is also a bug in setfilesemaphore.m. dirStruct(k).datenum in line 78 should be datenum(dirStruct(k).date).

15 Sep 2008 Bruno Cordani

Great!!!

03 Sep 2008 M H

Its absolutely excellent. Am using it now on my quad core machine and am probably going to buy another quad core just to see my models run so quickly. :)

14 Jul 2008 Robert Turner

Brilliant library. Works like a charm

30 Jun 2008 uju jbl  
25 May 2008 Jun Kim

This process works very well. For my model estimation, I was able to cut the execution time in a drastic manner. Also Markus was kind and was very responsive to my question.

08 Feb 2008 Markus Buehren

> An option for avoiding the use of the
> master core is desirable

The option is already existing: You can use the input parameter MAXMASTEREVALUATIONS and set it to zero.

04 Feb 2008 Igor S

An option for avoiding the use of the master core is desirable
Indeed if one slave process terminates or crushes the entiere process continues but if by chance the iteration that crushes is on the master core all the process is compromised

14 Jan 2008 igor scardanzan

great , just some difficulties to kill the slave : the process persists and CNTR C does not work . one should await the execution end

18 Dec 2007 A. S.

Thanks, very useful. Synchronization is not optimal (for example, the master shouldn't start working on a task if a slave is already working on it), but still a great program.

07 Dec 2007 Andrea Soldan

very useful and it works excellently.
much more than the distribuited computing toolbox provided by Matlab (which is very hard to use).
my SO is Linux, and i'm working with 4 workers ( 2 dual-core processors)

21 Oct 2007 David Brown

Works excellently. It would be nice to see this turned into a fully-guided setup to use this.

05 Oct 2007 Huy Bui

Multicore works quite well overall. I got a bug though. I make a mistake in parameterCell. The slave processes all die because of that. When I tried to exit all slave processes & start again, the same error causing slave processes dead appears again & again.

27 Aug 2007 Kevin Thom

Awesome program ... I have run it successfully using anywhere from 4 processors on one machine to 10 processors on 5 machines ... it makes a whole range of computationally expensive projects feasible in MATLAB.

26 Aug 2007 happy matlabuser

Ran it with 8 processors across 6 machines, and it works beautifully. Unfortunately, if you kill one or more processors, the master processor MUST do that job. Since the jobs are long for my problem, it's better to kill everything in that situation and finish everything at the command line. The master starts at the top of the list, and the slaves start at the bottom. When they meet somewhere in the middle, the master will always redo one of the jobs. I don't think the code will be efficient for a very large number of very small jobs (correct me if I'm wrong); so, I recommend making jobs medium length, (total run time)/(10*(# of processors)) for example. For my problem, these are fairly minor concerns. The author did a great job with this code -- easily saving me hours of work -- thank you!

14 Jun 2007 Markus Buehren

Yes and no: The slave process should create the directory if it is not existing (I have updated that). However, you can start the slave processes whenever you like! You can also interrupt and restart them while the master is running.

21 May 2007 Darren 3M

Brilliant use of the filesystem to share the load. It's not quite 2x increase but on a quick cluster test I got an increase of 4x with 5CPU's so 80% efficient.

02 Mar 2007 schena gianni

on dual-processor Intel Xeon based machines it halfs calculation time i.e. it cuts by a factor 2 !

30 Jan 2007 Michal Kvasnicka

Wow!!! After the few hours of hard experimentation with MULTICORE I finally learned how to use this code for parallel running on my four core PC. This is realy good and useful tool for distributed computing!!!

1. Informational text in the demo must be extended to detailed description how to run "tesfun" in parallel regime.
2. Some work must be done to minimize interprocess communication overhead, which may be very itensive (25% of the overall load) in some cases.

Good work!!!

30 Jan 2007 Michal Kvasnicka

I am not able to reproduce any improvment from sequential to parallel (multicore) realization of the testing demo code.

I would go as far as to say, that parallel (multi-core) realization is slower then sequential in some cases.

29 Jan 2007 William Renaud

Would it be possible to make this compatible with Octave? Due to licensing restrictions it is difficult for many people to have numerous Matlab instances available.

29 Jan 2007 Zhijun Wang

Corrections:

I tested the programn to see whether this program can improve parallel processing in a single machine with the following code:

______________________
N=20;
for m = 1:10
tic
for z = 1:N
testfun(z)
end
toc
end
__________________________

Results show the program do not improve anything comparing with my code in a single machine!

So I rate again

28 Jan 2007 Zhijun Wang

Parallel processing on multiple cores in a single machine is very useful!

28 Jan 2007 lucia Come

long due as standard matlab capability
does it work also with scrits or only with functions ?

28 Jan 2007 Michal Kvasnicka

The demo should be more selfdescriptive. Comparison with single core demo running is very important for parallelization impact evaluation.

Updates
26 Jan 2007

bad line breaks in description...

29 Jan 2007

Informational text added to demo, improvements in file access organization.

21 May 2007

Updated info due to new Matlab multicore functionality.

29 May 2007

Another note about multithreading

30 May 2007

Update of documentation contained in zip file, no changes to source code.

15 Jun 2007

Slave process will now create the temporary directory if it is not existing.

22 Jun 2007

There was a subfunction missing (which is only executed after a write error).

22 Jun 2007

Yet another small update.

25 Sep 2007

Improved support for small numbers of very long function evaluations.

12 Oct 2007

A file was missing - sorry.

14 Nov 2007

Update of contact information in documentation.

14 Nov 2007

Old e-mail address removed from help comments of m-files.

03 Nov 2008

Subfunction datenum2 was not needed.

15 Dec 2008

Semaphore stuff improved.

17 Dec 2008

Forgot to include file chompsep.m

21 Dec 2008

Semaphore mechanism improved.

07 Jan 2009

Introduced parameter EVALSATONCE which causes the multicore package to do several function evaluations after each other before saving/loading and thus reducing the communication overhead. Demo function MULTICOREDEMO heavily commented.

18 Jan 2009

I have nearly re-written both master and slave in order to make the package even more robust and to reduce the overhead for inter-process communication.

27 Jan 2009

Another change to the semaphore mechanism.

22 Feb 2009

File regexptokens.m added.
Dicussion group created: http://groups.yahoo.com/group/multicore_for_matlab

09 Mar 2009

If a slave is killed during working on a job, the master will now generate the parameter file of that job again instead of working on the file himself. This will increase performance in certain situations.

17 Mar 2009

Added an optional waitbar.

20 Mar 2009

Added estimation of time left in waitbar.

05 Apr 2009

Using system-dependent file separators in paths again. Waitbar shows progress during parameter file generation now.

07 Apr 2009

Two bugs fixed, one regarding the waitbar, one regarding the semaphore mechanism.

10 Apr 2009

In each multicore run, "clear functions" is now called once to ensure that changes to m-files take effect.

12 Apr 2009

Call to "clear functions" now in master and slaves, bug fixed.

13 Apr 2009

File displayerrorstruct.m was missing.

15 Apr 2009

Bug fixed.

17 Jun 2009

Estimation of time left changed, post-processing function introduced.

19 Jun 2009

Structure being passed to post-processing function changed (still undocumented feature)

25 Aug 2009

Small changes to documentation and gethostname.m

10 Mar 2010

Bugfix.

11 Apr 2011

Only E-mail changed in html document.

04 Jul 2011

Description modified to make it more concise.

04 Jul 2011

Links in help lines corrected.

05 Jul 2011

Description changed again.

29 Aug 2011

Overhead resulting from expanding the function handle cell reduced.

29 Aug 2011

Typo fixed.

30 Aug 2011

Typo fixed.

12 Sep 2011

Bugfix: calling startmulticoremaster.m without settings works now.

18 Sep 2011

New features:
1. Slave settings can be set via command line argument.
2. Slave Matlab process can be quit after a given time in seconds.

14 Jan 2013

Performance improvement - especially when using a large number of slaves

16 Jan 2013

Added parfor-loop to demo.

Contact us