<?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 John in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134278#M25857</link>
    <description>&lt;P&gt;John&lt;/P&gt;&lt;P&gt;you may also submit this issue via &lt;A href="https://supporttickets.intel.com/"&gt;Intel Online Service Center&lt;/A&gt; where you could share the reproducer and all needed details in the case if all of your data are private.&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Wed, 04 Mar 2020 01:29:56 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2020-03-04T01:29:56Z</dc:date>
    <item>
      <title>MKL Sparse BLAS executor slower than deprecated routines</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134276#M25855</link>
      <description>&lt;P&gt;I have several sparse iterative solvers that use the deprecated&amp;nbsp;MKL sparse Blas procedures.&amp;nbsp;After converting the solvers to use the latest sparse BLAS executor functions they all run slower than before. Has anyone else noticed this difference?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; Typical times (seconds):&lt;BR /&gt;Equations&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; threads Old_MKL&amp;nbsp; Executor_MKL&lt;BR /&gt;2e5&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 1&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 13&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 17&lt;BR /&gt;2e5&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 6&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 6&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;10&lt;BR /&gt;3e6&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 1&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 170&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;250&lt;/P&gt;&lt;P&gt;The solvers used mkl_dcsrtrsv and mkl_dcsrsymv, they were updated to use mkl_sparse_d_trsv and mkl_sparse_d_mv. Double precision and double complex show similar time comparisons.&lt;/P&gt;&lt;P&gt;The&amp;nbsp;comparisons&amp;nbsp;were performed&amp;nbsp;on a windows 10 computer with a Xeon E5 1650 processor,&amp;nbsp;software built using&amp;nbsp;Parallel XE 2019 with&amp;nbsp;intel fortran and C++ compilers.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Sun, 01 Mar 2020 15:51:20 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134276#M25855</guid>
      <dc:creator>SIMKIN__John</dc:creator>
      <dc:date>2020-03-01T15:51:20Z</dc:date>
    </item>
    <item>
      <title>Hello,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134277#M25856</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;&lt;P&gt;We haven't heard of this issue. Could you share your workload (matrix) with us so that we can check? Also, which threading did you use (I assume, OpenMP), was it Intel OpenMP or GNU?&lt;/P&gt;&lt;P&gt;Also, did you call mkl_sparse_optimize with appropriate hints before the actual calls to the computational routines?&lt;/P&gt;&lt;P&gt;In other words, if you can give us a simple example (just showing the way you call old SpBLAS and IE SpBLAS), it would speed up our investigation.&lt;/P&gt;&lt;P&gt;Thanks,&lt;BR /&gt;Kirill&lt;/P&gt;</description>
      <pubDate>Tue, 03 Mar 2020 21:53:28 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134277#M25856</guid>
      <dc:creator>Kirill_V_Intel</dc:creator>
      <dc:date>2020-03-03T21:53:28Z</dc:date>
    </item>
    <item>
      <title>John</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134278#M25857</link>
      <description>&lt;P&gt;John&lt;/P&gt;&lt;P&gt;you may also submit this issue via &lt;A href="https://supporttickets.intel.com/"&gt;Intel Online Service Center&lt;/A&gt; where you could share the reproducer and all needed details in the case if all of your data are private.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 04 Mar 2020 01:29:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134278#M25857</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2020-03-04T01:29:56Z</dc:date>
    </item>
    <item>
      <title>I have now created a small</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134279#M25858</link>
      <description>&lt;P&gt;I have now created a small program to demonstrate the problem and submitted it as an issue to the support centre as recommended by F. Gennady.&lt;/P&gt;&lt;P&gt;I will report progress.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 20 Mar 2020 14:14:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1134279#M25858</guid>
      <dc:creator>SIMKIN__John</dc:creator>
      <dc:date>2020-03-20T14:14:41Z</dc:date>
    </item>
    <item>
      <title>Re: MKL Sparse BLAS executor slower than deprecated routines</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1372668#M32949</link>
      <description>&lt;P&gt;Hi,&lt;BR /&gt;Is there any update on the topic? I believe the problem can still be observed.&lt;BR /&gt;Regards,&lt;BR /&gt;Jeremiasz&lt;/P&gt;</description>
      <pubDate>Tue, 29 Mar 2022 09:57:47 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/MKL-Sparse-BLAS-executor-slower-than-deprecated-routines/m-p/1372668#M32949</guid>
      <dc:creator>jwolosiuk</dc:creator>
      <dc:date>2022-03-29T09:57:47Z</dc:date>
    </item>
  </channel>
</rss>

