<?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 Hello Tang, Wei, in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Routine-to-compute-A-xy/m-p/1149523#M26989</link>
    <description>&lt;P&gt;Hello Tang, Wei,&lt;/P&gt;&lt;P&gt;MKL only provides&amp;nbsp;&amp;nbsp;A := alpha*x*y'+ A for cblas_?ger. Yes, you can set A=0 to meet your expectation of&amp;nbsp;A := alpha*x*y'. And&amp;nbsp;it has good performance without any performance&amp;nbsp;degradation.&lt;/P&gt;&lt;P&gt;Best Regards,&lt;/P&gt;&lt;P&gt;Ruqiu&lt;/P&gt;</description>
    <pubDate>Tue, 31 Mar 2020 05:44:39 GMT</pubDate>
    <dc:creator>Ruqiu_C_Intel</dc:creator>
    <dc:date>2020-03-31T05:44:39Z</dc:date>
    <item>
      <title>Routine to compute A=xy'?</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Routine-to-compute-A-xy/m-p/1149522#M26988</link>
      <description>&lt;P&gt;The BLAS Level 2 routine&amp;nbsp;cblas_?ger computes&amp;nbsp;A := alpha*x*y'+ A. Is there a simpler routine that just calculates&amp;nbsp;A := alpha*x*y'?&lt;/P&gt;&lt;P&gt;Setting A=0 offers the same results, but does it provide good&amp;nbsp;performance too? i.e. am I wasting computation in doing the additions?&lt;/P&gt;</description>
      <pubDate>Fri, 27 Mar 2020 17:23:09 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Routine-to-compute-A-xy/m-p/1149522#M26988</guid>
      <dc:creator>tang__wei</dc:creator>
      <dc:date>2020-03-27T17:23:09Z</dc:date>
    </item>
    <item>
      <title>Hello Tang, Wei,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Routine-to-compute-A-xy/m-p/1149523#M26989</link>
      <description>&lt;P&gt;Hello Tang, Wei,&lt;/P&gt;&lt;P&gt;MKL only provides&amp;nbsp;&amp;nbsp;A := alpha*x*y'+ A for cblas_?ger. Yes, you can set A=0 to meet your expectation of&amp;nbsp;A := alpha*x*y'. And&amp;nbsp;it has good performance without any performance&amp;nbsp;degradation.&lt;/P&gt;&lt;P&gt;Best Regards,&lt;/P&gt;&lt;P&gt;Ruqiu&lt;/P&gt;</description>
      <pubDate>Tue, 31 Mar 2020 05:44:39 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Routine-to-compute-A-xy/m-p/1149523#M26989</guid>
      <dc:creator>Ruqiu_C_Intel</dc:creator>
      <dc:date>2020-03-31T05:44:39Z</dc:date>
    </item>
  </channel>
</rss>

