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">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">https://github.com/madaan/BVP-MPI-PROJECT/blob/master/SumNELe/Sigma%28N%29.png</a>) . <br>
<br>The setup is as follows : <br>
<style type="text/css">
<!--
@page { margin: 2cm }
P { margin-bottom: 0.21cm; direction: ltr; color: #000000; widows: 2; orphans: 2 }
P.western { font-family: "Times New Roman", serif; font-size: 9pt }
P.cjk { font-family: "MS Mincho"; font-size: 9pt; so-language: ar-SA }
P.ctl { font-family: "Times New Roman"; font-size: 9pt }
A:link { color: #0000ff; so-language: zxx }
-->
</style>
<p class="" 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 class="" 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 class="" style="margin-bottom:0cm"><br></p><p class="" 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 class="" style="margin-bottom:0cm">We call the project <b>Junk Computing</b>.</p><br>I request your thoughts /comments /criticism .<p class="" style="margin-bottom:0cm">I also request suggestions for some simple benchmarking programs that i can write. <br>
</p>
<p class="" style="margin-bottom:0cm"><br></p><p class="" style="margin-bottom:0cm">Thanks for the precious time. <br></p><p class="" style="margin-bottom:0cm">With regards</p><p class="" style="margin-bottom:0cm"><br> </p>
<div class="gmail_extra"><div class="gmail_quote">On Fri, Nov 9, 2012 at 11:30 PM, <span dir="ltr"><<a href="mailto:mpich2-dev-request@mcs.anl.gov" target="_blank">mpich2-dev-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 mpich2-dev mailing list submissions to<br>
<a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@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/mpich2-dev" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich2-dev</a><br>
or, via email, send a message with subject or body 'help' to<br>
<a href="mailto:mpich2-dev-request@mcs.anl.gov">mpich2-dev-request@mcs.anl.gov</a><br>
<br>
You can reach the person managing the list at<br>
<a href="mailto:mpich2-dev-owner@mcs.anl.gov">mpich2-dev-owner@mcs.anl.gov</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of mpich2-dev digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
1. Re: mpich2-dev Digest, Vol 47, Issue 3<br>
(Muhammad Zulfikar Handana)<br>
2. No Gain For calculating maximum of an array (Aman Madaan)<br>
3. Re: No Gain For calculating maximum of an array (Jeff Hammond)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Fri, 9 Nov 2012 14:28:04 +0700<br>
From: Muhammad Zulfikar Handana <<a href="mailto:zulfikarhandana@gmail.com">zulfikarhandana@gmail.com</a>><br>
To: <a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@mcs.anl.gov</a><br>
Subject: Re: [mpich2-dev] mpich2-dev Digest, Vol 47, Issue 3<br>
Message-ID:<br>
<CAN0Ct=3J9cmmDeXY96qcoJW+iLQvc705QuxWuW=<a href="mailto:rGYeSPv1%2BUg@mail.gmail.com">rGYeSPv1+Ug@mail.gmail.com</a>><br>
Content-Type: text/plain; charset="iso-8859-1"<br>
<br>
Thanks jeff for your answer and i have another question<br>
so thats mean, MPICH2 must be modified before we have setting manually<br>
that message protocol?<br>
<br>
Thanks<br>
<br>
Handana<br>
<br>
><br>
> Message: 4<br>
> Date: Mon, 5 Nov 2012 23:18:11 -0500<br>
> From: Jeff Hammond <<a href="mailto:jhammond@alcf.anl.gov">jhammond@alcf.anl.gov</a>><br>
> To: <a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@mcs.anl.gov</a><br>
> Subject: Re: [mpich2-dev] setting manually eager to rendezvous<br>
> Message-ID:<br>
> <CAGKz=uKP2D0mut=<br>
> <a href="mailto:P92SLR6D00A_9n6KcJWO8fqFppiotYfDz3g@mail.gmail.com">P92SLR6D00A_9n6KcJWO8fqFppiotYfDz3g@mail.gmail.com</a>><br>
> Content-Type: text/plain; charset=ISO-8859-1<br>
><br>
> Please post user questions to <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a>. This list is<br>
> for developers of MPICH2 and those who may be modifying the<br>
> implementation.<br>
><br>
> In this case, those environment variables are not relevant unless you<br>
> have Blue Gene/P, and in that case, MPICH2 1.4 will not work anyways.<br>
><br>
> If you want to know about eager vs. rendezvous, perhaps you can<br>
> re-post this question on the user list and someone will answer<br>
> regarding the settings for ch3.<br>
><br>
> Best,<br>
><br>
> Jeff<br>
><br>
> On Mon, Nov 5, 2012 at 10:46 PM, Muhammad Zulfikar Handana<br>
> <<a href="mailto:zulfikarhandana@gmail.com">zulfikarhandana@gmail.com</a>> wrote:<br>
> > Hi, iam Handana. this my first project using MPICH2, i have little<br>
> confused<br>
> > because i dont know how to setting manually eager to rendezvous at MPICH2<br>
> > 1.41p1. i have a read this using code<br>
> ><br>
> > DCMF_EAGER -<br>
> > DCMF_RZV -<br>
> ><br>
> > am i right? or there is another code? thank you very much for your<br>
> attention<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>
><br>
><br>
> ------------------------------<br>
><br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/dbfe8fca/attachment-0001.html" target="_blank">http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/dbfe8fca/attachment-0001.html</a>><br>
<br>
------------------------------<br>
<br>
Message: 2<br>
Date: Fri, 9 Nov 2012 13:17:14 +0530<br>
From: Aman Madaan <<a href="mailto:madaan.amanmadaan@gmail.com">madaan.amanmadaan@gmail.com</a>><br>
To: <a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@mcs.anl.gov</a><br>
Subject: [mpich2-dev] No Gain For calculating maximum of an array<br>
Message-ID:<br>
<<a href="mailto:CA%2Bh7vmBLxppUR88uahVrbxNeTQKbnOy%2BHC5qajGF127Xn9BPUw@mail.gmail.com">CA+h7vmBLxppUR88uahVrbxNeTQKbnOy+HC5qajGF127Xn9BPUw@mail.gmail.com</a>><br>
Content-Type: text/plain; charset="iso-8859-1"<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 to<br>
all the supporting nodes. Then MPI_REDUCE is used to get the global maximum<br>
.<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 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>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/95f933a2/attachment-0001.html" target="_blank">http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/95f933a2/attachment-0001.html</a>><br>
-------------- next part --------------<br>
A non-text attachment was scrubbed...<br>
Name: DistributedLargest.c<br>
Type: text/x-csrc<br>
Size: 2268 bytes<br>
Desc: not available<br>
URL: <<a href="http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/95f933a2/attachment-0001.c" target="_blank">http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20121109/95f933a2/attachment-0001.c</a>><br>
<br>
------------------------------<br>
<br>
Message: 3<br>
Date: Fri, 9 Nov 2012 08:42:07 -0600<br>
From: Jeff Hammond <<a href="mailto:jhammond@alcf.anl.gov">jhammond@alcf.anl.gov</a>><br>
To: <a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@mcs.anl.gov</a>, <a href="mailto:madaan.amanmadaan@gmail.com">madaan.amanmadaan@gmail.com</a><br>
Subject: Re: [mpich2-dev] No Gain For calculating maximum of an array<br>
Message-ID:<br>
<CAGKz=u+2aQytQvDum1ENYqqwXwsHSStFu=<a href="mailto:HceeqRfV3e5xSQqA@mail.gmail.com">HceeqRfV3e5xSQqA@mail.gmail.com</a>><br>
Content-Type: text/plain; charset=ISO-8859-1<br>
<br>
Please resend to <a href="mailto:mpich-discuss@mcs.anl.gov">mpich-discuss@mcs.anl.gov</a>.<br>
<br>
Jeff<br>
<br>
On Fri, Nov 9, 2012 at 1:47 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 to<br>
> all the supporting nodes. Then MPI_REDUCE is used to get the global maximum<br>
> .<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 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>
><br>
> Aman Madaan<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>
<br>
<br>
------------------------------<br>
<br>
_______________________________________________<br>
mpich2-dev mailing list<br>
<a href="mailto:mpich2-dev@mcs.anl.gov">mpich2-dev@mcs.anl.gov</a><br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/mpich2-dev" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/mpich2-dev</a><br>
<br>
<br>
End of mpich2-dev Digest, Vol 47, Issue 4<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>