<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Hi John, in Intel® MPI Library</title>
    <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927973#M2495</link>
    <description>&lt;P&gt;Hi John,&lt;/P&gt;
&lt;P&gt;Is there a particular reason you need to use 4.0.2?&amp;nbsp; If not, I'd recommend using 4.1.0.&lt;/P&gt;
&lt;P&gt;Sincerely,&lt;BR /&gt; James Tullos&lt;BR /&gt; Technical Consulting Engineer&lt;BR /&gt; Intel® Cluster Tools&lt;/P&gt;</description>
    <pubDate>Thu, 18 Apr 2013 14:46:24 GMT</pubDate>
    <dc:creator>James_T_Intel</dc:creator>
    <dc:date>2013-04-18T14:46:24Z</dc:date>
    <item>
      <title>Segmentation Fault in MPI_Finalize()</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927969#M2491</link>
      <description>&lt;P&gt;I've run into a problem using Intel MPI 4.0.2.003.&amp;nbsp; I'm running the "Hello world" program that comes with MPI over OFA on two nodes.&amp;nbsp; The IB Verbs layer is provided by a library we've developed at Cray.&amp;nbsp; It presents an IB verbs interface to MPI and uses Cray's proprietary high-speed network to do the data transfer within the cluster.&amp;nbsp; If I use DAPL, it works fine, but it crashes when I try to use OFA.&lt;/P&gt;
&lt;P&gt;The backtrace for the crash is:&lt;BR /&gt;&amp;gt; (gdb) bt&lt;BR /&gt;&amp;gt; #0&amp;nbsp; 0x00002aaaab49d6c1 in MPID_OFA_module_Finalize_CM ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #1&amp;nbsp; 0x00002aaaab4870d3 in MPID_nem_gen2_module_finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #2&amp;nbsp; 0x00002aaaab46a31b in MPID_nem_finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #3&amp;nbsp; 0x00002aaaab37928b in MPIDI_CH3_Finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #4&amp;nbsp; 0x00002aaaab46624e in MPID_Finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #5&amp;nbsp; 0x00002aaaab420afa in PMPI_Finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /cray/css/iaa/mpi_images/impi/4.0.2.003/intel64/lib/libmpi.so.4&lt;BR /&gt;&amp;gt; #6&amp;nbsp; 0x00002aaaaaccf229 in MPI_Finalize ()&lt;BR /&gt;&amp;gt;&amp;nbsp;&amp;nbsp;&amp;nbsp; from /lus/scratch/jdc/795857/lib/libpibgni.so.1.0.0&lt;BR /&gt;&amp;gt; #7&amp;nbsp; 0x0000000000400be4 in main ()&lt;/P&gt;
&lt;P&gt;I looked at MPID_OFA_module_Finalize_CM() with gdb.&amp;nbsp; It looks like it's picking up cm_pending_head, which has a value of zero, and using it as a pointer.&lt;/P&gt;
&lt;P&gt;This is speculation, but I wonder whether "CM" stands for Connection Manager.&amp;nbsp; Our software doesn't provide a connection manager, and I wonder whether this is the root of the problem.&lt;/P&gt;
&lt;P&gt;Is this a known problem in 4.1.2?&lt;/P&gt;
&lt;P&gt;Thanks.&lt;/P&gt;</description>
      <pubDate>Thu, 11 Apr 2013 18:58:01 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927969#M2491</guid>
      <dc:creator>John_Cavanaugh</dc:creator>
      <dc:date>2013-04-11T18:58:01Z</dc:date>
    </item>
    <item>
      <title>Hi John,</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927970#M2492</link>
      <description>&lt;P&gt;Hi John,&lt;/P&gt;
&lt;P&gt;Looking through our reports, I have only found one error that could be related.&amp;nbsp; However, the solution there was to increase the locked memory limit, which you have already done.&amp;nbsp; I'll check with our developers to see if they have any better ideas.&lt;/P&gt;
&lt;P&gt;Also, I would recommend that for specific&amp;nbsp;or complex issues, you submit them through Intel® Premier Support instead of through the forums.&lt;/P&gt;
&lt;P&gt;Sincerely,&lt;BR /&gt; James Tullos&lt;BR /&gt; Technical Consulting Engineer&lt;BR /&gt; Intel® Cluster Tools&lt;/P&gt;</description>
      <pubDate>Fri, 12 Apr 2013 15:39:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927970#M2492</guid>
      <dc:creator>James_T_Intel</dc:creator>
      <dc:date>2013-04-12T15:39:24Z</dc:date>
    </item>
    <item>
      <title>Hi John,</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927971#M2493</link>
      <description>&lt;P&gt;Hi John,&lt;/P&gt;
&lt;P&gt;Have you tried this with Version 4.1 yet?&amp;nbsp; We have not released a Version 4.1.2 at this time.&lt;/P&gt;
&lt;P&gt;Sincerely,&lt;BR /&gt; James Tullos&lt;BR /&gt; Technical Consulting Engineer&lt;BR /&gt; Intel® Cluster Tools&lt;/P&gt;</description>
      <pubDate>Fri, 12 Apr 2013 18:00:09 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927971#M2493</guid>
      <dc:creator>James_T_Intel</dc:creator>
      <dc:date>2013-04-12T18:00:09Z</dc:date>
    </item>
    <item>
      <title>Sorry, I had a typo in my</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927972#M2494</link>
      <description>&lt;P&gt;Sorry, I had a typo in my original message.&amp;nbsp; I meant 4.0.2.003.&lt;/P&gt;
&lt;P&gt;I have run with 4.1.0.024.&amp;nbsp; I don't hit the problem there.&amp;nbsp; I get farther down in MPID_OFA_module_Finalize_CM() and hang because of a bug in my code.&lt;/P&gt;
&lt;P&gt;Thanks for the information about Premier Support.&amp;nbsp; I'll be sure to use it in the future when it seems appropriate.&lt;/P&gt;</description>
      <pubDate>Fri, 12 Apr 2013 18:08:45 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927972#M2494</guid>
      <dc:creator>John_Cavanaugh</dc:creator>
      <dc:date>2013-04-12T18:08:45Z</dc:date>
    </item>
    <item>
      <title>Hi John,</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927973#M2495</link>
      <description>&lt;P&gt;Hi John,&lt;/P&gt;
&lt;P&gt;Is there a particular reason you need to use 4.0.2?&amp;nbsp; If not, I'd recommend using 4.1.0.&lt;/P&gt;
&lt;P&gt;Sincerely,&lt;BR /&gt; James Tullos&lt;BR /&gt; Technical Consulting Engineer&lt;BR /&gt; Intel® Cluster Tools&lt;/P&gt;</description>
      <pubDate>Thu, 18 Apr 2013 14:46:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927973#M2495</guid>
      <dc:creator>James_T_Intel</dc:creator>
      <dc:date>2013-04-18T14:46:24Z</dc:date>
    </item>
    <item>
      <title>My goal is to understand the</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927974#M2496</link>
      <description>&lt;P&gt;My goal is to understand the cause of the problem (and to fix it, if it's in my code).&amp;nbsp; If we have customers who run into this, we need to be able to explain to them why there's a problem and what to do about it.&lt;/P&gt;
&lt;P&gt;I found the problem that was causing the hang in 4.1.0, so using it is an option.&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 18 Apr 2013 16:28:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927974#M2496</guid>
      <dc:creator>John_Cavanaugh</dc:creator>
      <dc:date>2013-04-18T16:28:42Z</dc:date>
    </item>
    <item>
      <title>Hi John,</title>
      <link>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927975#M2497</link>
      <description>&lt;P&gt;Hi John,&lt;/P&gt;
&lt;P&gt;Understood.&amp;nbsp; I'll see what can be done to find a root cause for this.&amp;nbsp; But the simple answer if you have a customer running into the issue is to ask them to try with the latest version of the Intel® MPI Library.&lt;/P&gt;
&lt;P&gt;Sincerely,&lt;BR /&gt; James Tullos&lt;BR /&gt; Technical Consulting Engineer&lt;BR /&gt; Intel® Cluster Tools&lt;/P&gt;</description>
      <pubDate>Thu, 18 Apr 2013 18:23:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-MPI-Library/Segmentation-Fault-in-MPI-Finalize/m-p/927975#M2497</guid>
      <dc:creator>James_T_Intel</dc:creator>
      <dc:date>2013-04-18T18:23:41Z</dc:date>
    </item>
  </channel>
</rss>

