<br><div class="gmail_extra">Thanks a lot for the answers!<br><br>I have calculated the maximum element of an array that has around 5*10^7 elements, but there were still no gains!<br>Is the code correct? <br>I have reattached the program file for your kind reference. <br>
<br>I would like to request some more guidance on the results. <br><br>As i mentioned, the results that i get from embarrassingly parallel problems are not at all surprising . <br>The plots are (<a href="https://github.com/madaan/BVP-MPI-PROJECT/blob/master/PI/PI.png" target="_blank">https://github.com/madaan/BVP-MPI-PROJECT/blob/master/PI/PI.png</a>) and (<a href="https://github.com/madaan/BVP-MPI-PROJECT/blob/master/SumNELe/Sigma%28N%29.png" target="_blank">https://github.com/madaan/BVP-MPI-PROJECT/blob/master/SumNELe/Sigma%28N%29.png</a>) . <br>
<br>The setup is as follows : <br>
<p style="margin-bottom:0cm"><b>Node
configuration</b><font face="Times, serif"><font style="font-size:13pt" size="4"><br></font></font>There
are 3 similar nodes, each consisting of an Intel(R) Pentium(R) 4 CPU,
2.60GHz with 512 MB of memory. Each processor has 512 KB cache.<font face="Times, serif"><font style="font-size:13pt" size="4"><br></font></font><br>
</p>
<p style="margin-bottom:0cm">Another node has an
Intel Core i3-330M, 2.13GHz with 3GB of memory. It is termed <b>FOX</b> for
reference . All the nodes runs Ubuntu 12.04 Long term
support version.<font face="Times, serif"><font style="font-size:13pt" size="4"><br><br></font></font><b>Network
setup:</b> <font face="Times, serif"><font style="font-size:13pt" size="4"><br></font></font>Nodes
are interconnected via a fast Ethernet switch (10 MB/s). The network
configuration is essentially meshed. For all tests the MPI/Pro
library from MPI Software Technology (MPI/Pro distribution version
1.6.3). </p><p style="margin-bottom:0cm"><br></p><p style="margin-bottom:0cm">The
aim of the project is to compare the computing power of a group of
dumped machines with a state of the art ( or so i say ) computer,
called the fox for reference. <br>
</p><p style="margin-bottom:0cm">We call the project <b>Junk Computing</b>.</p><br>I request your thoughts /comments /criticism .<p style="margin-bottom:0cm">I also request suggestions for some simple benchmarking programs that i can write. <br>
</p>
<p style="margin-bottom:0cm"><br></p>Thanks for the precious time. <br><br><div class="gmail_quote">On Fri, Nov 9, 2012 at 11:30 PM, <span dir="ltr"><<a href="mailto:mpich-discuss-request@mcs.anl.gov" target="_blank">mpich-discuss-request@mcs.anl.gov</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Send mpich-discuss mailing list submissions to<br>
<a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss</a><br>
or, via email, send a message with subject or body 'help' to<br>
<a href="mailto:mpich-discuss-request@mcs.anl.gov">mpich-discuss-request@mcs.anl.gov</a><br>
<br>
You can reach the person managing the list at<br>
<a href="mailto:mpich-discuss-owner@mcs.anl.gov">mpich-discuss-owner@mcs.anl.gov</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of mpich-discuss digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
1. Re: No gain for calculating maximum element of an array<br>
(Jeff Hammond)<br>
2. Re: No gain for calculating maximum element of an array<br>
(Darius Buntinas)<br>
3. Re: do not get mpif90 after building mpich2 in linux (Gus Correa)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Fri, 9 Nov 2012 09:07:28 -0600<br>
From: Jeff Hammond <<a href="mailto:jhammond@alcf.anl.gov">jhammond@alcf.anl.gov</a>><br>
To: <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
Subject: Re: [mpich-discuss] No gain for calculating maximum element<br>
of an array<br>
Message-ID:<br>
<CAGKz=<a href="mailto:uL6NzyxqF_cKMhAsR3dyoXsEOcX0r40TC1EKtuRwPqD-A@mail.gmail.com">uL6NzyxqF_cKMhAsR3dyoXsEOcX0r40TC1EKtuRwPqD-A@mail.gmail.com</a>><br>
Content-Type: text/plain; charset="iso-8859-1"<br>
<br>
It is not surprising at all that shared memory is 20x faster than<br>
distributed memory using MPI, particularly on the machines you are using,<br>
which I assume are running GigE.<br>
<br>
Jeff<br>
<br>
On Fri, Nov 9, 2012 at 8:59 AM, Aman Madaan <<a href="mailto:madaan.amanmadaan@gmail.com">madaan.amanmadaan@gmail.com</a>>wrote:<br>
<br>
> Hello<br>
><br>
> I am pretty new to MPI programming and i was doing some research on<br>
> performance of dumped computers in our college.<br>
> Although my cluster is giving the expected gain for many embarrassingly<br>
> parallel problems,but the attached simple program for calculating maximum<br>
> number in an array is unexpectedly slow.<br>
><br>
> The file of numbers is first read at the root and the array is scattered<br>
> to all the supporting nodes. Everyone calculates their local maximum abd<br>
> the MPI_REDUCE is used to get the global maximum<br>
><br>
> The result of running the program are as follows :<br>
><br>
> *Using 2 nodes : *<br>
><br>
> axiom@node1:~/Programs/largest$ mpiexec -f f ./a.out numbers/num10000.txt<br>
> 10000<br>
><br>
> Maximum = 3999213<br>
><br>
> wall clock time = 0.002819<br>
><br>
> *Using single node : *<br>
><br>
> axiom@node1:~/Programs/largest$ mpiexec ./a.out numbers/num10000.txt<br>
> 10000<br>
><br>
> Maximum = 3999213<br>
><br>
> wall clock time = 0.000168<br>
><br>
> ..........<br>
><br>
> The situation remains same even after increasing the number of elements.<br>
><br>
> I request your suggestions.<br>
><br>
> Thanks a lot for your time.<br>
><br>
><br>
> With regards<br>
><br>
><br>
> --<br>
><br>
> Aman Madaan<br>
><br>
><br>
><br>
> _______________________________________________<br>
> mpich-discuss mailing list <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
> To manage subscription options or unsubscribe:<br>
> <a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss</a><br>
><br>
><br>
<br>
<br>
--<br>
Jeff Hammond<br>
Argonne Leadership Computing Facility<br>
University of Chicago Computation Institute<br>
<a href="mailto:jhammond@alcf.anl.gov">jhammond@alcf.anl.gov</a> / (630) 252-5381<br>
<a href="http://www.linkedin.com/in/jeffhammond" target="_blank">http://www.linkedin.com/in/jeffhammond</a><br>
<a href="https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond" target="_blank">https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond</a><br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20121109/9b42f09d/attachment-0001.html" target="_blank">http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20121109/9b42f09d/attachment-0001.html</a>><br>
<br>
------------------------------<br>
<br>
Message: 2<br>
Date: Fri, 9 Nov 2012 09:38:38 -0600<br>
From: Darius Buntinas <<a href="mailto:buntinas@mcs.anl.gov">buntinas@mcs.anl.gov</a>><br>
To: <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
Subject: Re: [mpich-discuss] No gain for calculating maximum element<br>
of an array<br>
Message-ID: <<a href="mailto:9E5094A9-A819-4982-A5EC-3E7BBAF8CFBE@mcs.anl.gov">9E5094A9-A819-4982-A5EC-3E7BBAF8CFBE@mcs.anl.gov</a>><br>
Content-Type: text/plain; charset=iso-8859-1<br>
<br>
<br>
It looks like your problem size is way too small to see a significant difference. Try increasing the problem size until the run time is 10 or so minutes.<br>
<br>
-d<br>
<br>
<br>
On Nov 9, 2012, at 8:59 AM, Aman Madaan wrote:<br>
<br>
> wall clock time = 0.000168<br>
><br>
><br>
<br>
<br>
<br>
------------------------------<br>
<br>
Message: 3<br>
Date: Fri, 09 Nov 2012 12:59:29 -0500<br>
From: Gus Correa <<a href="mailto:gus@ldeo.columbia.edu">gus@ldeo.columbia.edu</a>><br>
To: Mpich Discuss <<a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a>><br>
Subject: Re: [mpich-discuss] do not get mpif90 after building mpich2<br>
in linux<br>
Message-ID: <<a href="mailto:509D4481.5050801@ldeo.columbia.edu">509D4481.5050801@ldeo.columbia.edu</a>><br>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed<br>
<br>
On 11/09/2012 08:25 AM, Michael Seman wrote:<br>
> In reply to various posts, the Intel compiler is set up using the<br>
> ifortvars and iccvars scripts. I have compiled FFTW package without a<br>
> hitch. I did see in one of the release notes that there is a problem<br>
> with version 13 of Intel compilers, so I used version 11.1 which I<br>
> already had.<br>
> Well anyway, I noticed in the mpich2 config.log the following message:<br>
><br>
> ld: /opt/intel/Compiler/11.1/080/bin/lib/for_main.o: No such file: No<br>
> such file or directory<br>
><br>
> That path is obviously wrong - I haven't figured out yet where that gets<br>
> screwed up. Now if a create a lib subdirectory under bin and copy all<br>
> the *.o files from the lib/intel64 directory, and then try building<br>
> mpich2, I do get the mpif90 wrapper. I think that's like plugging fuel<br>
> leaks with chewing gum, so I need to locate the origin of the defective<br>
> ld path.<br>
> _______________________________________________<br>
> mpich-discuss mailing list <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
> To manage subscription options or unsubscribe:<br>
> <a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss</a><br>
Hi Michael<br>
Still sounds as a flaw in the compiler environment.<br>
'printenv | grep LIB' may give some clue.<br>
Hope it helps,<br>
Gus Correa<br>
<br>
<br>
------------------------------<br>
<br>
_______________________________________________<br>
mpich-discuss mailing list<br>
<a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a><br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss</a><br>
<br>
<br>
End of mpich-discuss Digest, Vol 50, Issue 12<br>
*********************************************<br>
</blockquote></div><br><br clear="all"><br>-- <br><blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><font style="background-color:rgb(204,204,255)">Aman Madaan<br>+91-9958725963</font><br>
</blockquote><br>
</div>