<?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 Can clbas_dcopy support overlapping regions for source and dest in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Can-clbas-dcopy-support-overlapping-regions-for-source-and/m-p/785446#M1827</link>
    <description>Underlying code works the same as public source versions. According to Fortran rules, overlap isn't permitted, as if the prototypes were defined with *restrict. In practice, it will likely work OK with overlap, if copying toward smaller addresses with positive increment parameters, or toward larger addresses with negative increments.&lt;BR /&gt;memmove() is fairly efficient in most current implementations (maybe better than ?copy for the case of both increments negative), so it may not make sense to use ?copy in such cases.</description>
    <pubDate>Tue, 16 Nov 2010 04:15:20 GMT</pubDate>
    <dc:creator>TimP</dc:creator>
    <dc:date>2010-11-16T04:15:20Z</dc:date>
    <item>
      <title>Can clbas_dcopy support overlapping regions for source and destination?</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Can-clbas-dcopy-support-overlapping-regions-for-source-and/m-p/785445#M1826</link>
      <description>I couldn't seem to find this in the docs, though I'm sure it's specified somewhere.&lt;DIV&gt;&lt;SPAN style="font-family: Verdana, Arial, Helvetica, sans-serif;"&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;Can cblas_?copy support overlapping regions for the source and destinations vectors?&lt;/DIV&gt;&lt;/DIV&gt;</description>
      <pubDate>Mon, 15 Nov 2010 22:54:57 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Can-clbas-dcopy-support-overlapping-regions-for-source-and/m-p/785445#M1826</guid>
      <dc:creator>chollida01</dc:creator>
      <dc:date>2010-11-15T22:54:57Z</dc:date>
    </item>
    <item>
      <title>Can clbas_dcopy support overlapping regions for source and dest</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Can-clbas-dcopy-support-overlapping-regions-for-source-and/m-p/785446#M1827</link>
      <description>Underlying code works the same as public source versions. According to Fortran rules, overlap isn't permitted, as if the prototypes were defined with *restrict. In practice, it will likely work OK with overlap, if copying toward smaller addresses with positive increment parameters, or toward larger addresses with negative increments.&lt;BR /&gt;memmove() is fairly efficient in most current implementations (maybe better than ?copy for the case of both increments negative), so it may not make sense to use ?copy in such cases.</description>
      <pubDate>Tue, 16 Nov 2010 04:15:20 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Can-clbas-dcopy-support-overlapping-regions-for-source-and/m-p/785446#M1827</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2010-11-16T04:15:20Z</dc:date>
    </item>
  </channel>
</rss>

