<?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 Andrew,  please check how it in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034408#M20331</link>
    <description>&lt;P&gt;Andrew, &amp;nbsp;&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;please check how it works with the latest MKL 11.2 update 2 which has been released the last week.&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 09 Feb 2015 08:50:12 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2015-02-09T08:50:12Z</dc:date>
    <item>
      <title>MKL_DIRECT_CALL and zgemm3</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034402#M20325</link>
      <description>&lt;P&gt;It seems that MKL_DIRECT_CALL does not apply to zgemm3 and cgemm3, only zgemm and cgemm&lt;/P&gt;

&lt;P&gt;It seems slightly annoying that this is not the case as zgemm3 is significantly more numerically efficient for large matrices and is therefore a replacement for zgemm&amp;nbsp; and it would have been helpful for MKL_DIRECT_CALL to switch calls of zgemm3 as well as zgemm for small matrices&lt;/P&gt;</description>
      <pubDate>Thu, 28 Aug 2014 15:17:01 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034402#M20325</guid>
      <dc:creator>AndrewC</dc:creator>
      <dc:date>2014-08-28T15:17:01Z</dc:date>
    </item>
    <item>
      <title>you right, this optimization</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034403#M20326</link>
      <description>&lt;P&gt;you right, this optimization would &amp;nbsp;be added later into one of the next versions. We will update this record accordingly.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 28 Aug 2014 17:34:34 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034403#M20326</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2014-08-28T17:34:34Z</dc:date>
    </item>
    <item>
      <title>Great! At the moment I do my</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034404#M20327</link>
      <description>&lt;P&gt;Great! At the moment I do my own test of the sizes and switch to zgemm3 for N&amp;gt;128 (say)&lt;/P&gt;</description>
      <pubDate>Thu, 28 Aug 2014 19:21:37 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034404#M20327</guid>
      <dc:creator>AndrewC</dc:creator>
      <dc:date>2014-08-28T19:21:37Z</dc:date>
    </item>
    <item>
      <title>To make sure we understand</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034405#M20328</link>
      <description>&lt;P&gt;To make sure we understand your request correctly, you use zgemm instead of zgemm3m if the matrices are smaller than 128, right? And, you would like MKL_DIRECT_CALL feature to do a similar transformation if the matrices are small enough?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 28 Aug 2014 20:56:49 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034405#M20328</guid>
      <dc:creator>Murat_G_Intel</dc:creator>
      <dc:date>2014-08-28T20:56:49Z</dc:date>
    </item>
    <item>
      <title>In my existing code, I only</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034406#M20329</link>
      <description>&lt;P&gt;In my existing code, I only call zgemm3 - never zgemm&lt;/P&gt;

&lt;P&gt;I want to use MKL_DIRECT_CALL but since MKL_DIRECT_CALL does not support zgemm3, I have added wrapper code that calls zgemm3 for N&amp;gt;=128, and zgemm for N&amp;lt;128&lt;/P&gt;</description>
      <pubDate>Thu, 28 Aug 2014 21:59:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034406#M20329</guid>
      <dc:creator>AndrewC</dc:creator>
      <dc:date>2014-08-28T21:59:56Z</dc:date>
    </item>
    <item>
      <title>Thank you for the details! I</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034407#M20330</link>
      <description>&lt;P&gt;Thank you for the details! I got it know. Please let us know if there are other high priority routines that the MKL_DIRECT_CALL feature would help.&lt;/P&gt;</description>
      <pubDate>Fri, 29 Aug 2014 18:26:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034407#M20330</guid>
      <dc:creator>Murat_G_Intel</dc:creator>
      <dc:date>2014-08-29T18:26:04Z</dc:date>
    </item>
    <item>
      <title>Andrew,  please check how it</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034408#M20331</link>
      <description>&lt;P&gt;Andrew, &amp;nbsp;&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;please check how it works with the latest MKL 11.2 update 2 which has been released the last week.&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 09 Feb 2015 08:50:12 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034408#M20331</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2015-02-09T08:50:12Z</dc:date>
    </item>
    <item>
      <title>Yes, direct call to zgemm3</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034409#M20332</link>
      <description>&lt;P&gt;Yes, direct call to zgemm3/cgemm3 works &amp;nbsp;great in the latest update to MKL.&lt;/P&gt;

&lt;P&gt;thank you!&lt;/P&gt;</description>
      <pubDate>Wed, 11 Feb 2015 01:40:51 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034409#M20332</guid>
      <dc:creator>AndrewC</dc:creator>
      <dc:date>2015-02-11T01:40:51Z</dc:date>
    </item>
    <item>
      <title>Andrew, Thanks for nice words</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034410#M20333</link>
      <description>&lt;P&gt;Andrew, Thanks for nice words about Intel(R) MKL. Please don't hesitate report us any issues. regards, Gennady&lt;/P&gt;</description>
      <pubDate>Wed, 11 Feb 2015 09:57:47 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-DIRECT-CALL-and-zgemm3/m-p/1034410#M20333</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2015-02-11T09:57:47Z</dc:date>
    </item>
  </channel>
</rss>

