<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=Content-Type content="text/html; charset=us-ascii">
<meta name=Generator content="Microsoft Word 12 (filtered medium)">
<style>
<!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.gmailquote
{mso-style-name:gmail_quote;}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:"Calibri","sans-serif";
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;}
@page Section1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
{page:Section1;}
-->
</style>
<!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang=EN-US link=blue vlink=purple>
<div class=Section1>
<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'>Looking at your pong data, it looks to me like latency is your bottleneck
from a network perspective. You appear to be getting really good
bandwidth. One thing you can check is that your TCP windows are set to a
large enough value. Newer versions of linux do this automatically, but it
might be worth checking. <o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'><o:p> </o:p></span></p>
<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'>Another thought. Since you have great bandwidth, but not
great latency, try grouping the communications into larger messages, rather
than many small ones. <o:p></o:p></span></p>
<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'><o:p> </o:p></span></p>
<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'>The real issue, though, seems to be the boundary conditions. My
guess is that enforcing the boundary conditions results in a sync point where
the program has to wait until everything is caught up. Maybe you could
give us an idea of what new boundary conditions you are imposing?<o:p></o:p></span></p>
<p class=MsoNormal><a name="_MailEndCompose"><span style='font-size:11.0pt;
font-family:"Calibri","sans-serif";color:#1F497D'><o:p> </o:p></span></a></p>
<div style='border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in'>
<p class=MsoNormal><b><span style='font-size:10.0pt;font-family:"Tahoma","sans-serif"'>From:</span></b><span
style='font-size:10.0pt;font-family:"Tahoma","sans-serif"'> owner-mpich-discuss@mcs.anl.gov
[mailto:owner-mpich-discuss@mcs.anl.gov] <b>On Behalf Of </b>Hee Il Kim<br>
<b>Sent:</b> Saturday, March 29, 2008 5:15 AM<br>
<b>To:</b> mpich-discuss@mcs.anl.gov<br>
<b>Subject:</b> Re: [mpich-discuss] Scalability of Intel quad core (Harpertown)
cluster<o:p></o:p></span></p>
</div>
<p class=MsoNormal><o:p> </o:p></p>
<p class=MsoNormal style='margin-bottom:12.0pt'>Hi,<br>
<br>
mpi_pong test reuslts show that out gigabit network has <br>
<br>
Max rate = 115.335908 MB/sec Min latency = 49.948692 usec<br>
<br>
I ran it several times and got almost the same results. Unfortunately I could
not analyse more and the reuslt was attached to this mail.<br>
<br>
Hee Il<o:p></o:p></p>
<div>
<p class=MsoNormal><span class=gmailquote>2008/3/29, Elvedin Trnjanin <<a
href="mailto:trnja001@umn.edu">trnja001@umn.edu</a>>:</span><o:p></o:p></p>
<p class=MsoNormal style='margin-bottom:12.0pt'>You would do that within the
code. If you're trying to pass every<br>
element of an int array one at a time (message size is sizeof(int)), it<br>
will have much worse performance than sending the entire array (message<br>
size is sizeof(int)*arraydimensions.<br>
<br>
Example -<br>
<a href="http://www.scl.ameslab.gov/Projects/mpi_introduction/figs/mpi_pong.c">http://www.scl.ameslab.gov/Projects/mpi_introduction/figs/mpi_pong.c</a><br>
This is a start for a decent approximation of network bandwidth and<br>
latency for a certain message size. Although not accurate, it'll<br>
certainly give you an idea of your network's performance with various<br>
message sizes and transfer types. It only works on two nodes at a time<br>
however so other types of communication like AlltoAll are not tested.<br>
<br>
<br>
Hee Il Kim wrote:<br>
><br>
> I checked the bandwidth behavior mentioned by Elvedin. Could I change<br>
> or setup the message size and frequency in a runtime level or any<br>
> other steps?<br>
><o:p></o:p></p>
</div>
</div>
</body>
</html>