<?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 Potential bug in complex versions of mkl_?omatadd in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219380#M30174</link>
    <description>&lt;P class="p1"&gt;Hi all,&lt;/P&gt;
&lt;P class="p1"&gt;I think came upon a bug in the mkl_?omatadd routine, especially the complex versions. If both matrices A and B are conjugate transposed, the matrix A is only conjugated. I configured the zomatadd.c example file that intel provided in order to show that this is the case:&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Screenshot 2020-10-20 at 13.26.30.png" style="width: 999px;"&gt;&lt;img src="https://community.intel.com/t5/image/serverpage/image-id/13282i988AA95D6D32D23C/image-size/large/is-moderation-mode/true?v=v2&amp;amp;px=999&amp;amp;whitelist-exif-data=Orientation%2CResolution%2COriginalDefaultFinalSize%2CCopyright" role="button" title="Screenshot 2020-10-20 at 13.26.30.png" alt="Screenshot 2020-10-20 at 13.26.30.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Screenshot 2020-10-20 at 13.23.00.png" style="width: 999px;"&gt;&lt;img src="https://community.intel.com/t5/image/serverpage/image-id/13283i99CAA9955E671CB3/image-size/large/is-moderation-mode/true?v=v2&amp;amp;px=999&amp;amp;whitelist-exif-data=Orientation%2CResolution%2COriginalDefaultFinalSize%2CCopyright" role="button" title="Screenshot 2020-10-20 at 13.23.00.png" alt="Screenshot 2020-10-20 at 13.23.00.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P class="p1"&gt;As you can see the results are the same, which is incorrect. The second computation gives the wrong answer.&lt;/P&gt;
&lt;P class="p1"&gt;There are actually two more cases I found, where the result is wrong:&lt;/P&gt;
&lt;OL class="ol1"&gt;
&lt;LI class="li1"&gt;A transposed and B conjugated: This combination conjugate transposes A instead of just transposing it.&lt;/LI&gt;
&lt;LI class="li1"&gt;A conjugated and B transposed: This combination conjugate transposes B instead of just transposing it.&lt;/LI&gt;
&lt;/OL&gt;
&lt;P&gt;The example file is also attached for you to test it.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Best regards,&lt;/P&gt;
&lt;P&gt;Simon&lt;/P&gt;</description>
    <pubDate>Tue, 20 Oct 2020 11:45:13 GMT</pubDate>
    <dc:creator>AC_Simon33</dc:creator>
    <dc:date>2020-10-20T11:45:13Z</dc:date>
    <item>
      <title>Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219380#M30174</link>
      <description>&lt;P class="p1"&gt;Hi all,&lt;/P&gt;
&lt;P class="p1"&gt;I think came upon a bug in the mkl_?omatadd routine, especially the complex versions. If both matrices A and B are conjugate transposed, the matrix A is only conjugated. I configured the zomatadd.c example file that intel provided in order to show that this is the case:&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Screenshot 2020-10-20 at 13.26.30.png" style="width: 999px;"&gt;&lt;img src="https://community.intel.com/t5/image/serverpage/image-id/13282i988AA95D6D32D23C/image-size/large/is-moderation-mode/true?v=v2&amp;amp;px=999&amp;amp;whitelist-exif-data=Orientation%2CResolution%2COriginalDefaultFinalSize%2CCopyright" role="button" title="Screenshot 2020-10-20 at 13.26.30.png" alt="Screenshot 2020-10-20 at 13.26.30.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Screenshot 2020-10-20 at 13.23.00.png" style="width: 999px;"&gt;&lt;img src="https://community.intel.com/t5/image/serverpage/image-id/13283i99CAA9955E671CB3/image-size/large/is-moderation-mode/true?v=v2&amp;amp;px=999&amp;amp;whitelist-exif-data=Orientation%2CResolution%2COriginalDefaultFinalSize%2CCopyright" role="button" title="Screenshot 2020-10-20 at 13.23.00.png" alt="Screenshot 2020-10-20 at 13.23.00.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P class="p1"&gt;As you can see the results are the same, which is incorrect. The second computation gives the wrong answer.&lt;/P&gt;
&lt;P class="p1"&gt;There are actually two more cases I found, where the result is wrong:&lt;/P&gt;
&lt;OL class="ol1"&gt;
&lt;LI class="li1"&gt;A transposed and B conjugated: This combination conjugate transposes A instead of just transposing it.&lt;/LI&gt;
&lt;LI class="li1"&gt;A conjugated and B transposed: This combination conjugate transposes B instead of just transposing it.&lt;/LI&gt;
&lt;/OL&gt;
&lt;P&gt;The example file is also attached for you to test it.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Best regards,&lt;/P&gt;
&lt;P&gt;Simon&lt;/P&gt;</description>
      <pubDate>Tue, 20 Oct 2020 11:45:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219380#M30174</guid>
      <dc:creator>AC_Simon33</dc:creator>
      <dc:date>2020-10-20T11:45:13Z</dc:date>
    </item>
    <item>
      <title>Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219419#M30175</link>
      <description>&lt;P&gt;what version of mkl do you use?&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 20 Oct 2020 13:35:17 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219419#M30175</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2020-10-20T13:35:17Z</dc:date>
    </item>
    <item>
      <title>Re: Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219431#M30177</link>
      <description>&lt;P&gt;I'm using the mkl that comes with 2020 update 2 parallel studio. I'm on MacOS.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 20 Oct 2020 14:13:49 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219431#M30177</guid>
      <dc:creator>AC_Simon33</dc:creator>
      <dc:date>2020-10-20T14:13:49Z</dc:date>
    </item>
    <item>
      <title>Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219678#M30180</link>
      <description>&lt;P&gt;Yes, you are right, that's the issue. You may escalate the case to Intel Online Service Center against Intel MKL.&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Wed, 21 Oct 2020 07:15:06 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219678#M30180</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2020-10-21T07:15:06Z</dc:date>
    </item>
    <item>
      <title>Re: Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219754#M30183</link>
      <description>&lt;P&gt;Thanks for confirming the issue. There was already a ticket created by Khoros, is that enough?&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 21 Oct 2020 11:07:19 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1219754#M30183</guid>
      <dc:creator>AC_Simon33</dc:creator>
      <dc:date>2020-10-21T11:07:19Z</dc:date>
    </item>
    <item>
      <title>Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1270742#M31111</link>
      <description>&lt;P&gt;the fix of the issue has been released in the latest oneMKL 2021.2 which available for download.&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 05 Apr 2021 03:16:55 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1270742#M31111</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2021-04-05T03:16:55Z</dc:date>
    </item>
    <item>
      <title>Re:Potential bug in complex versions of mkl_?omatadd</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1270743#M31112</link>
      <description>&lt;P&gt;The issue is closing and we will no longer respond to this thread.&amp;nbsp;If you require additional assistance from Intel, please start a new thread.&amp;nbsp;Any further interaction in this thread will be considered community only.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 05 Apr 2021 03:17:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Potential-bug-in-complex-versions-of-mkl-omatadd/m-p/1270743#M31112</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2021-04-05T03:17:16Z</dc:date>
    </item>
  </channel>
</rss>

