<?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 Bulent! in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/PARDISO-Phase-33/m-p/1039995#M20645</link>
    <description>&lt;P&gt;Bulent!&lt;/P&gt;

&lt;P&gt;yes, this is expected in the case if your case computes with iterative refinement. &amp;nbsp;there is way to estimate how much memory it will take but this is pretty roughly estimation.&lt;/P&gt;

&lt;P&gt;With regard to OOC mode -- please try to evaluate ( you promised to do that :) ) 11.2. This version helps you in the case of out-of -core.&lt;/P&gt;

&lt;P&gt;regards, Gennady&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Thu, 30 Oct 2014 11:21:00 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2014-10-30T11:21:00Z</dc:date>
    <item>
      <title>PARDISO - Phase 33</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/PARDISO-Phase-33/m-p/1039994#M20644</link>
      <description>&lt;P&gt;Hello&lt;/P&gt;

&lt;P&gt;I am solving (relatively) a big system with PARDISO (6810921 nonzero terms, 64080 equations, and 508 columns in load vector). I am calling Phase 11, 22 and 33.&lt;/P&gt;

&lt;P&gt;I just noticed that PARDISO tries to allocate significant amount of memory&amp;nbsp;when "Phase 33" is called, and then returns me memory allocation.&lt;/P&gt;

&lt;P&gt;I understand that Phase 11 and 22 needs to allocate memory for factorization, but I was not expecting&amp;nbsp;high memory demand for Phase 33 as well.&lt;/P&gt;

&lt;P&gt;Is this expected? Is there a way to know how much memory needed for Phase 33? Anyway to reduce this&amp;nbsp;memory demand&amp;nbsp;(out-of-core option is not helping me for this).&lt;/P&gt;

&lt;P&gt;Regards&lt;/P&gt;

&lt;P&gt;Bulent&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 29 Oct 2014 16:44:12 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/PARDISO-Phase-33/m-p/1039994#M20644</guid>
      <dc:creator>Alemdar__Bulent</dc:creator>
      <dc:date>2014-10-29T16:44:12Z</dc:date>
    </item>
    <item>
      <title>Bulent!</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/PARDISO-Phase-33/m-p/1039995#M20645</link>
      <description>&lt;P&gt;Bulent!&lt;/P&gt;

&lt;P&gt;yes, this is expected in the case if your case computes with iterative refinement. &amp;nbsp;there is way to estimate how much memory it will take but this is pretty roughly estimation.&lt;/P&gt;

&lt;P&gt;With regard to OOC mode -- please try to evaluate ( you promised to do that :) ) 11.2. This version helps you in the case of out-of -core.&lt;/P&gt;

&lt;P&gt;regards, Gennady&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 11:21:00 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/PARDISO-Phase-33/m-p/1039995#M20645</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2014-10-30T11:21:00Z</dc:date>
    </item>
  </channel>
</rss>

