<?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 Optimization of ABINIT 6.0.2 using Intel Compilers/MKL on a Lin in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimization-of-ABINIT-6-0-2-using-Intel-Compilers-MKL-on-a/m-p/835137#M6021</link>
    <description>Hello Martin,&lt;DIV&gt;guote:"&lt;SPAN style="font-family: Verdana, Arial, Helvetica, sans-serif; white-space: pre;"&gt;We are interested in &lt;B&gt;further optimizations using Intel MKL libraries&lt;/B&gt; or &lt;B&gt;different compiler options/flags"&lt;/B&gt;&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/DIV&gt;&lt;DIV&gt;Based on our registration center data, LRZ uses the valid version of the latest MKL versions ( bundled with Intel Fortran Compiler ).Do you have the concrete suggestions for the further improving of MKL?Can you provide more details for that?&lt;/DIV&gt;&lt;DIV&gt;--Gennady&lt;/DIV&gt;</description>
    <pubDate>Fri, 23 Apr 2010 05:50:17 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2010-04-23T05:50:17Z</dc:date>
    <item>
      <title>Optimization of ABINIT 6.0.2 using Intel Compilers/MKL on a Linux/SGI Altix/Itanium platform</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimization-of-ABINIT-6-0-2-using-Intel-Compilers-MKL-on-a/m-p/835136#M6020</link>
      <description>&lt;DIV align="justify"&gt;
&lt;PRE class="sectionBodyText"&gt;Dear Sir or Madam,&lt;BR /&gt;&lt;/PRE&gt;
&lt;PRE class="sectionBodyText"&gt;&lt;BR /&gt;at the &lt;I&gt;LRZ computing center Garching, Munich &lt;/I&gt;(&lt;A class="moz-txt-link-abbreviated" href="http://www.lrz.de/"&gt;www.lrz.de&lt;/A&gt;) we are currently trying to &lt;B&gt;optimize the ABINIT software&lt;/B&gt; (&lt;A class="moz-txt-link-abbreviated" href="http://www.abinit.org/"&gt;www.abinit.org&lt;/A&gt;) version &lt;B&gt;6.0.2&lt;/B&gt; on various platforms using Intel compilers and libraries for scientific use at the Technical University Munich and at Munich University of Applied Sciences.&lt;BR /&gt;&lt;BR /&gt;We managed to get a working parallel built using the Intel Fortran compiler version 10.1. We are interested in &lt;B&gt;further optimizations using Intel MKL libraries&lt;/B&gt; or &lt;B&gt;different compiler options/flags&lt;/B&gt;. The current configuration is documented in an ABINIT forum thread at &lt;A class="moz-txt-link-freetext" href="http://forum.abinit.org/viewtopic.php?f=3&amp;amp;t=221"&gt;http://forum.abinit.org/viewtopic.php?f=3&amp;amp;t=221&lt;/A&gt;&lt;BR /&gt;&lt;/PRE&gt;
&lt;/DIV&gt;

&lt;DIV align="justify"&gt;
&lt;PRE class="sectionBodyText"&gt;&lt;BR /&gt;We would appreciate any help on how to achieve a &lt;B&gt;maximum optimized production version&lt;/B&gt; for following platforms:&lt;BR /&gt;&lt;BR /&gt;i.   &lt;B&gt;Linux/SGI Altix/Itanium&lt;/B&gt;&lt;BR /&gt;ii.  Linux/x86_64/Opteron&lt;BR /&gt;iii. Linux/ia64&lt;BR /&gt;&lt;BR /&gt;We intend to use the first platform intensively, as the &lt;B&gt;HLRBII-supercomputer&lt;/B&gt; consists of SGI Altix nodes. For further information please see &lt;BR /&gt;  &lt;A class="moz-txt-link-freetext" href="http://www.lrz-muenchen.de/services/compute/hlrb/hardware/index.html"&gt;http://www.lrz-muenchen.de/services/compute/hlrb/hardware/index.html&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;If you need any additional information, please do not hesitate to contact me or Momme Allalen (&lt;A class="moz-txt-link-abbreviated" href="mailto:Momme.Allalen@lrz.de"&gt;Momme.Allalen@lrz.de&lt;/A&gt;). &lt;BR /&gt;&lt;BR /&gt;Kind regards,&lt;BR /&gt;Martin Haeufel&lt;BR /&gt;&lt;BR /&gt;TU Munich, WSI (T33)&lt;BR /&gt;&lt;A class="moz-txt-link-abbreviated" href="http://www.wsi.tum.de/"&gt;www.wsi.tum.de&lt;/A&gt;&lt;BR /&gt;&lt;/PRE&gt;
&lt;/DIV&gt;

&lt;DIV&gt;&lt;/DIV&gt;</description>
      <pubDate>Thu, 22 Apr 2010 15:53:19 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimization-of-ABINIT-6-0-2-using-Intel-Compilers-MKL-on-a/m-p/835136#M6020</guid>
      <dc:creator>Martin_H</dc:creator>
      <dc:date>2010-04-22T15:53:19Z</dc:date>
    </item>
    <item>
      <title>Optimization of ABINIT 6.0.2 using Intel Compilers/MKL on a Lin</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimization-of-ABINIT-6-0-2-using-Intel-Compilers-MKL-on-a/m-p/835137#M6021</link>
      <description>Hello Martin,&lt;DIV&gt;guote:"&lt;SPAN style="font-family: Verdana, Arial, Helvetica, sans-serif; white-space: pre;"&gt;We are interested in &lt;B&gt;further optimizations using Intel MKL libraries&lt;/B&gt; or &lt;B&gt;different compiler options/flags"&lt;/B&gt;&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/DIV&gt;&lt;DIV&gt;Based on our registration center data, LRZ uses the valid version of the latest MKL versions ( bundled with Intel Fortran Compiler ).Do you have the concrete suggestions for the further improving of MKL?Can you provide more details for that?&lt;/DIV&gt;&lt;DIV&gt;--Gennady&lt;/DIV&gt;</description>
      <pubDate>Fri, 23 Apr 2010 05:50:17 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimization-of-ABINIT-6-0-2-using-Intel-Compilers-MKL-on-a/m-p/835137#M6021</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2010-04-23T05:50:17Z</dc:date>
    </item>
  </channel>
</rss>

