On Fri, Sep 11, 2009 at 10:48 AM, Ravi <span dir="ltr"><<a href="mailto:rxk@cfdrc.com">rxk@cfdrc.com</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div link="blue" vlink="purple" lang="EN-US">
<div>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);">Matt,</span></p>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);">I see your point: lots of interesting information is given by
log_summary. However I need to report the </span>total latency time and computation/communication
for some simulations. How do I get those? </p></div></div></blockquote><div><br>We have no way of getting that information. You can try the MPI profiling tools (like JUMPSHOT).<br><br> Matt<br> </div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div link="blue" vlink="purple" lang="EN-US"><div>
<p>Thanks</p>
<p>Ravi<span style="font-size: 11pt; color: rgb(31, 73, 125);"></span></p>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);"> </span></p>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);"> </span></p>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);"> </span></p>
<div style="border-style: solid none none; border-color: rgb(181, 196, 223) -moz-use-text-color -moz-use-text-color; border-width: 1pt medium medium; padding: 3pt 0in 0in;">
<p><b><span style="font-size: 10pt;">From:</span></b><span style="font-size: 10pt;">
<a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a> [mailto:<a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a>] <b>On
Behalf Of </b>Matthew Knepley<br>
<b>Sent:</b> Friday, September 11, 2009 10:12 AM<br>
<b>To:</b> PETSc users list<br>
<b>Cc:</b> <a href="mailto:pjd@cfdrc.com" target="_blank">pjd@cfdrc.com</a>; Vincent Harrand<br>
<b>Subject:</b> Re: parallel statistics.</span></p>
</div><div><div></div><div class="h5">
<p> </p>
<p>On Fri, Sep 11, 2009 at 10:09 AM, Ravi <<a href="mailto:rxk@cfdrc.com" target="_blank">rxk@cfdrc.com</a>> wrote:</p>
<div>
<blockquote style="border-style: none none none solid; border-color: -moz-use-text-color -moz-use-text-color -moz-use-text-color rgb(204, 204, 204); border-width: medium medium medium 1pt; padding: 0in 0in 0in 6pt; margin-left: 4.8pt; margin-right: 0in;">
<div>
<div>
<p><span style="font-size: 11pt;">Hi Matt, </span></p>
<p>log_summary does give information like time for barrier, zero size MPI_send.
However interesting statistics like total latency time,
computation/communication time ratio etc. This is needed by me to study the
effect of partitions and BCs.</p>
</div>
</div>
</blockquote>
<div>
<p><br>
It gives these numbers for individual functions, like VecDot(), which is what
is important for solvers. Maybe you can<br>
get generic things from JUMPSHOT, but the interpretation would be problematic.
What routine you you fix if total<br>
latency was high?<br>
<br>
Matt<br>
</p>
</div>
<blockquote style="border-style: none none none solid; border-color: -moz-use-text-color -moz-use-text-color -moz-use-text-color rgb(204, 204, 204); border-width: medium medium medium 1pt; padding: 0in 0in 0in 6pt; margin-left: 4.8pt; margin-right: 0in;">
<div>
<div>
<p>Thanks</p>
<p>Ravi<span style="font-size: 11pt; color: rgb(31, 73, 125);"> </span></p>
<p><span style="font-size: 11pt; color: rgb(31, 73, 125);">
</span></p>
<div style="border-style: solid none none; border-color: -moz-use-text-color; border-width: 1pt medium medium; padding: 3pt 0in 0in;">
<p><b><span style="font-size: 10pt;">From:</span></b><span style="font-size: 10pt;"> <a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a>
[mailto:<a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a>]
<b>On Behalf Of </b>Matthew Knepley<br>
<b>Sent:</b> Thursday, September 10, 2009 2:06 PM<br>
<b>To:</b> PETSc users list<br>
<b>Subject:</b> Re: parallel statistics.</span></p>
</div>
<div>
<div>
<p> </p>
<p>On Thu, Sep 10, 2009 at 1:22 PM, Ravi <<a href="mailto:rxk@cfdrc.com" target="_blank">rxk@cfdrc.com</a>> wrote:</p>
<div>
<blockquote style="border-style: none none none solid; border-color: -moz-use-text-color -moz-use-text-color -moz-use-text-color rgb(204, 204, 204); border-width: medium medium medium 1pt; margin: 5pt 0in 5pt 4.8pt; padding: 0in 0in 0in 6pt;">
<div>
<div>
<p>Hi all,</p>
<p>
This is Ravi Kannan from CFD Research Corporation. Are there readily available
or installable commands or chunks of code to get the parallel statistics
including important ones like time spent in waiting and latency, communication
time, available memory spent in each machine etc. when solving AX=B type
problem</p>
</div>
</div>
</blockquote>
<div>
<p><br>
In -log_summary.<br>
<br>
Matt<br>
</p>
</div>
<blockquote style="border-style: none none none solid; border-color: -moz-use-text-color -moz-use-text-color -moz-use-text-color rgb(204, 204, 204); border-width: medium medium medium 1pt; margin: 5pt 0in 5pt 4.8pt; padding: 0in 0in 0in 6pt;">
<div>
<div>
<p> </p>
<p>Thanks in advance</p>
<p>Ravi</p>
<p> </p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">Ravi Kannan, PhD</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">Research Engineer</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">CFD Research Corporation</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">215 Wynn Drive, Suite
501</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">Huntsville, AL
35805</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;">(256)726-4851</span></p>
<p><span style="font-size: 10.5pt; font-family: Consolas;"><a href="mailto:rxk@cfdrc.com" target="_blank">rxk@cfdrc.com</a></span></p>
<p> </p>
</div>
</div>
</blockquote>
</div>
<p><br>
<br clear="all">
<br>
-- <br>
What most experimenters take for granted before they begin their experiments is
infinitely more interesting than any results to which their experiments lead.<br>
-- Norbert Wiener</p>
</div>
</div>
</div>
</div>
</blockquote>
</div>
<p><br>
<br clear="all">
<br>
-- <br>
What most experimenters take for granted before they begin their experiments is
infinitely more interesting than any results to which their experiments lead.<br>
-- Norbert Wiener</p>
</div></div></div>
</div>
</blockquote></div><br><br clear="all"><br>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener<br>