<?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 Pardiso freezes occasionally when matrix is singular in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101140#M23895</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;I have an application which uses Pardiso (pardiso_64) for large sparse matrix solves.&lt;BR /&gt;
	&lt;BR /&gt;
	In running a series of tests for my application in parallel processes with different input, I have discovered that sometimes (but not always), when the matrix is singular (which in this application can happen and is OK), the application freezes. I have isolated the problem to the call to pardiso_64 by adding print statements before and after the call). If I rerun the failed test afterwards one by one (not in parallel with other tests), the execution of my application completes, and I can see the pardiso error code -4 (which I propagate to a text file through my application).&amp;nbsp;&lt;/P&gt;

&lt;P&gt;This issue is not isolated to a single input file, but happens randomly for some of the tests in every batch run. When I run each of the frozen tests one by one afterwards, they complete successfully I see the pardiso error code -4 in my application's output. So it only happens when the matrix is singular, and when my application is run in multiple processes at the same time. And only occasionally.&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 1em;"&gt;I'm running on a 2-core CPU (Intel i7). Pardiso uses 4 threads (up to a full core, I think). I have mkl 11.3 update 3.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 1em;"&gt;Also, note that if I use&amp;nbsp;&lt;/SPAN&gt;mkl_set_num_threads(1) prior to the call to pardiso_64, there are no issues.&lt;/P&gt;

&lt;P&gt;Also also, I use the parallel&amp;nbsp;&lt;SPAN style="font-size: 1em;"&gt;metis nested disection option, iparm(2) = 3. If I set iparm(2) = 0, there are no issues.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;Are there any known issues related to what I observe?&lt;/P&gt;

&lt;P&gt;Best,&lt;BR /&gt;
	Jens&lt;/P&gt;</description>
    <pubDate>Tue, 04 Oct 2016 14:29:42 GMT</pubDate>
    <dc:creator>Jens_E_</dc:creator>
    <dc:date>2016-10-04T14:29:42Z</dc:date>
    <item>
      <title>Pardiso freezes occasionally when matrix is singular</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101140#M23895</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;I have an application which uses Pardiso (pardiso_64) for large sparse matrix solves.&lt;BR /&gt;
	&lt;BR /&gt;
	In running a series of tests for my application in parallel processes with different input, I have discovered that sometimes (but not always), when the matrix is singular (which in this application can happen and is OK), the application freezes. I have isolated the problem to the call to pardiso_64 by adding print statements before and after the call). If I rerun the failed test afterwards one by one (not in parallel with other tests), the execution of my application completes, and I can see the pardiso error code -4 (which I propagate to a text file through my application).&amp;nbsp;&lt;/P&gt;

&lt;P&gt;This issue is not isolated to a single input file, but happens randomly for some of the tests in every batch run. When I run each of the frozen tests one by one afterwards, they complete successfully I see the pardiso error code -4 in my application's output. So it only happens when the matrix is singular, and when my application is run in multiple processes at the same time. And only occasionally.&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 1em;"&gt;I'm running on a 2-core CPU (Intel i7). Pardiso uses 4 threads (up to a full core, I think). I have mkl 11.3 update 3.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 1em;"&gt;Also, note that if I use&amp;nbsp;&lt;/SPAN&gt;mkl_set_num_threads(1) prior to the call to pardiso_64, there are no issues.&lt;/P&gt;

&lt;P&gt;Also also, I use the parallel&amp;nbsp;&lt;SPAN style="font-size: 1em;"&gt;metis nested disection option, iparm(2) = 3. If I set iparm(2) = 0, there are no issues.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;Are there any known issues related to what I observe?&lt;/P&gt;

&lt;P&gt;Best,&lt;BR /&gt;
	Jens&lt;/P&gt;</description>
      <pubDate>Tue, 04 Oct 2016 14:29:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101140#M23895</guid>
      <dc:creator>Jens_E_</dc:creator>
      <dc:date>2016-10-04T14:29:42Z</dc:date>
    </item>
    <item>
      <title>Jens, Could you please try</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101141#M23896</link>
      <description>&lt;P&gt;Jens, Could you please try the latest update 4 ( 11.3.4) where we fixed some regression problem with METIS reordering and keep us updated with the status. best, Gennady&lt;/P&gt;</description>
      <pubDate>Wed, 05 Oct 2016 10:47:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101141#M23896</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2016-10-05T10:47:41Z</dc:date>
    </item>
    <item>
      <title>Hi,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101142#M23897</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;Sure, I will do that. However, short term I am happy with using the minimum degree algorithm, so I might not get around to it until next week.&lt;BR /&gt;
	&lt;BR /&gt;
	Also, note that both METIS implementations (iparm(2) = 3 and iparm(2) = 2) causes the same behavior. So it's not exclusive to the parallel implementation.&lt;/P&gt;

&lt;P&gt;Jens&lt;/P&gt;</description>
      <pubDate>Wed, 05 Oct 2016 16:48:01 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Pardiso-freezes-occasionally-when-matrix-is-singular/m-p/1101142#M23897</guid>
      <dc:creator>Jens_E_</dc:creator>
      <dc:date>2016-10-05T16:48:01Z</dc:date>
    </item>
  </channel>
</rss>

