<?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 Linking with ILP64 did fix in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115100#M24601</link>
    <description>&lt;P&gt;Linking with ILP64 did fix the problem. It had to be done manually, since Visual Studio plugin silently links to LP64&lt;/P&gt;</description>
    <pubDate>Fri, 12 Feb 2016 21:31:10 GMT</pubDate>
    <dc:creator>renorm2</dc:creator>
    <dc:date>2016-02-12T21:31:10Z</dc:date>
    <item>
      <title>Memory requirement of SVD drivers</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115098#M24599</link>
      <description>&lt;P&gt;I tried dgedd routines from &lt;A href="https://software.intel.com/en-us/node/521149"&gt;https://software.intel.com/en-us/node/521149&lt;/A&gt;&lt;/P&gt;

&lt;P&gt;My matrix is 100K by 30K, about 24 GB in size. I am using MKL 11.3 on a windows server with about 300 GB memory. The routines failed with error message "Not enough memory to allocate work array".&lt;/P&gt;

&lt;P&gt;On my desktop with 32 GB memory I am able to perform SVD of 100K by 13K matrix. In my case work array size should scales quadratically with number of colomns, so going from 13K to 30K should be possible.&lt;/P&gt;</description>
      <pubDate>Wed, 03 Feb 2016 02:50:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115098#M24599</guid>
      <dc:creator>renorm2</dc:creator>
      <dc:date>2016-02-03T02:50:02Z</dc:date>
    </item>
    <item>
      <title>have you linked the case with</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115099#M24600</link>
      <description>&lt;P&gt;have you linked the case with ILP64 libs?&lt;/P&gt;</description>
      <pubDate>Thu, 04 Feb 2016 05:47:48 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115099#M24600</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2016-02-04T05:47:48Z</dc:date>
    </item>
    <item>
      <title>Linking with ILP64 did fix</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115100#M24601</link>
      <description>&lt;P&gt;Linking with ILP64 did fix the problem. It had to be done manually, since Visual Studio plugin silently links to LP64&lt;/P&gt;</description>
      <pubDate>Fri, 12 Feb 2016 21:31:10 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115100#M24601</guid>
      <dc:creator>renorm2</dc:creator>
      <dc:date>2016-02-12T21:31:10Z</dc:date>
    </item>
    <item>
      <title>yes, by the default when you</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115101#M24602</link>
      <description>&lt;P&gt;yes, by the default when you choose linking with mkl from Visual Studio environment, lp64 libraries will be used.&lt;/P&gt;</description>
      <pubDate>Sat, 13 Feb 2016 04:54:59 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-requirement-of-SVD-drivers/m-p/1115101#M24602</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2016-02-13T04:54:59Z</dc:date>
    </item>
  </channel>
</rss>

