<?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 Inaccurate Pardiso solutions after rebuild in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1615011#M36277</link>
    <description>&lt;P&gt;I rebuilt an old project with MKL 2024.2 and latest Visual Studio build tools and Windows SDK. Now some of the solutions from Pardiso have strange large errors in them. I think I was previously using MKL 10.2 or 11.1 and it worked properly. Has something changed since then that I need to alter my program for? Or is there any incompatibility with recent Visual C++?&lt;/P&gt;&lt;P&gt;Is it possible to still download MKL 10.2 or 11.1 to check?&lt;/P&gt;&lt;P&gt;Thanks&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 15 Jul 2024 09:25:52 GMT</pubDate>
    <dc:creator>sfdgsgsd</dc:creator>
    <dc:date>2024-07-15T09:25:52Z</dc:date>
    <item>
      <title>Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1615011#M36277</link>
      <description>&lt;P&gt;I rebuilt an old project with MKL 2024.2 and latest Visual Studio build tools and Windows SDK. Now some of the solutions from Pardiso have strange large errors in them. I think I was previously using MKL 10.2 or 11.1 and it worked properly. Has something changed since then that I need to alter my program for? Or is there any incompatibility with recent Visual C++?&lt;/P&gt;&lt;P&gt;Is it possible to still download MKL 10.2 or 11.1 to check?&lt;/P&gt;&lt;P&gt;Thanks&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 15 Jul 2024 09:25:52 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1615011#M36277</guid>
      <dc:creator>sfdgsgsd</dc:creator>
      <dc:date>2024-07-15T09:25:52Z</dc:date>
    </item>
    <item>
      <title>Re: Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1616196#M36288</link>
      <description>&lt;P&gt;You need to give reproducer (PARDISO settings and input data) if possible as your question is too vague to get a diagnosis.&lt;/P&gt;</description>
      <pubDate>Thu, 18 Jul 2024 17:28:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1616196#M36288</guid>
      <dc:creator>Andrew_Smith</dc:creator>
      <dc:date>2024-07-18T17:28:04Z</dc:date>
    </item>
    <item>
      <title>Re: Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1616200#M36289</link>
      <description>&lt;P&gt;&lt;a href="https://community.intel.com/t5/user/viewprofilepage/user-id/304648"&gt;@sfdgsgsd&lt;/a&gt;, yes please provide a reproducer.&amp;nbsp;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 18 Jul 2024 18:06:40 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1616200#M36289</guid>
      <dc:creator>Mark_L_Intel</dc:creator>
      <dc:date>2024-07-18T18:06:40Z</dc:date>
    </item>
    <item>
      <title>Re: Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629018#M36387</link>
      <description>&lt;P&gt;Hello&amp;nbsp;&lt;a href="https://community.intel.com/t5/user/viewprofilepage/user-id/304648"&gt;@sfdgsgsd&lt;/a&gt;,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp; &amp;nbsp; Do you have any updates regarding a reproducer? MKL 10.2 was released in 2009 and is no longer available. Obviously, a lot has changed since then.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 05 Sep 2024 21:45:14 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629018#M36387</guid>
      <dc:creator>Mark_L_Intel</dc:creator>
      <dc:date>2024-09-05T21:45:14Z</dc:date>
    </item>
    <item>
      <title>Re: Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629113#M36390</link>
      <description>&lt;P&gt;I haven't revisited this yet because I found a workaround to avoid recompiling it. But when I do, I'll first try using the same old version which I luckily kept a copy of.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;It's possible I've got some memory allocation bug which was just hidden by chance and got exposed with the newer version.&lt;/P&gt;</description>
      <pubDate>Fri, 06 Sep 2024 02:43:48 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629113#M36390</guid>
      <dc:creator>sfdgsgsd</dc:creator>
      <dc:date>2024-09-06T02:43:48Z</dc:date>
    </item>
    <item>
      <title>Re: Inaccurate Pardiso solutions after rebuild</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629348#M36397</link>
      <description>&lt;P&gt;Hello&amp;nbsp;&lt;a href="https://community.intel.com/t5/user/viewprofilepage/user-id/304648"&gt;@sfdgsgsd&lt;/a&gt;,&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp; &amp;nbsp;In your last comment, you mentioned&amp;nbsp;"found a workaround to avoid recompiling it"&amp;nbsp; and "It's possible I've got some memory allocation bug which was just hidden by chance."&amp;nbsp;This does sound like something we can reproduce on our side. Intel will no longer monitor this issue. Thank you for posting at the oneMKL Community Forum.&lt;/P&gt;</description>
      <pubDate>Fri, 06 Sep 2024 15:43:34 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Inaccurate-Pardiso-solutions-after-rebuild/m-p/1629348#M36397</guid>
      <dc:creator>Mark_L_Intel</dc:creator>
      <dc:date>2024-09-06T15:43:34Z</dc:date>
    </item>
  </channel>
</rss>

