<?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 Does the Intel MKL CSR  format imply a restriction on the spars in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782147#M1561</link>
    <description>it should works w/o problem, if I am not mistaken we should change the documentation.</description>
    <pubDate>Tue, 17 Jul 2012 17:08:06 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2012-07-17T17:08:06Z</dc:date>
    <item>
      <title>Does the Intel MKL CSR  format imply a restriction on the sparse matrix?</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782146#M1560</link>
      <description>Is it true that Intel MKL compressed sparse row (CSR)format requires that each and every row of the sparse matrix should have at least one none-zero element?&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;In page 2756 of the Intel MKL Reference Manual(2007), it is said that CSR format for sparse matrix A consists of four arrays,which are called the&lt;I&gt; values&lt;/I&gt;, &lt;I&gt;columns&lt;/I&gt;,&lt;I&gt; pointerB&lt;/I&gt;, and &lt;I&gt;pointerE&lt;/I&gt; arrays, and that the length of&lt;I&gt; pointerB&lt;/I&gt; array is equal to the number of rows in A. Besides, element j of &lt;I&gt;pointerB&lt;/I&gt; array gives the index into the values array that contains the first non-zero element in a row j of A.So we can deduce that every row of A must have at least one non-zero element.&lt;/DIV&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;The problem is, what would happen if some rows of A consist of all zeros?&lt;/DIV&gt;</description>
      <pubDate>Tue, 17 Jul 2012 13:13:27 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782146#M1560</guid>
      <dc:creator>euclid0413</dc:creator>
      <dc:date>2012-07-17T13:13:27Z</dc:date>
    </item>
    <item>
      <title>Does the Intel MKL CSR  format imply a restriction on the spars</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782147#M1561</link>
      <description>it should works w/o problem, if I am not mistaken we should change the documentation.</description>
      <pubDate>Tue, 17 Jul 2012 17:08:06 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782147#M1561</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2012-07-17T17:08:06Z</dc:date>
    </item>
    <item>
      <title>Does the Intel MKL CSR  format imply a restriction on the spars</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782148#M1562</link>
      <description>Yes, the missing information in the documentation can be really misleading and result in some bugs in appplications.</description>
      <pubDate>Thu, 19 Jul 2012 03:59:19 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Does-the-Intel-MKL-CSR-format-imply-a-restriction-on-the-sparse/m-p/782148#M1562</guid>
      <dc:creator>euclid0413</dc:creator>
      <dc:date>2012-07-19T03:59:19Z</dc:date>
    </item>
  </channel>
</rss>

