<?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 Gennady, in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038729#M20592</link>
    <description>&lt;P&gt;Gennady,&lt;/P&gt;

&lt;P&gt;One more, are there any plans to make these multithreaded? Thanks!&lt;/P&gt;</description>
    <pubDate>Thu, 30 Oct 2014 16:56:56 GMT</pubDate>
    <dc:creator>Jen_B_</dc:creator>
    <dc:date>2014-10-30T16:56:56Z</dc:date>
    <item>
      <title>triangular solver</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038722#M20585</link>
      <description>&lt;P&gt;I am using the mkl_?coosv, specifically one with d,&amp;nbsp;and compiled the program with 'ifort -openmp -mkl'. I have set 'mkl_omp_num_threads', and also 'omp_proc_bind=true'. I have tested it for&amp;nbsp;three different thread numbers 4, 8, 16. I am getting the following timings: 0.36, 0.3, and 0.32. I am running it on a machine with 16 cores. are these timings reasonable? or are there anything else I should be doing before doing the runs. thanks.&lt;/P&gt;</description>
      <pubDate>Tue, 28 Oct 2014 17:33:22 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038722#M20585</guid>
      <dc:creator>Jen_B_</dc:creator>
      <dc:date>2014-10-28T17:33:22Z</dc:date>
    </item>
    <item>
      <title>all of triangle solvers</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038723#M20586</link>
      <description>&lt;P&gt;all of triangle solvers routines are&amp;nbsp;&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;not threaded for now.In the case if you call this routine many time into your application, we would recommend you to make the convertion from coo -&amp;gt; csr format and then call&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN class="option" style="color: rgb(8, 96, 168); font-family: 'Courier New', Courier, monospace; font-size: 13.6000003814697px; line-height: 15.9999980926514px;"&gt;&lt;A style="color: rgb(8, 96, 168); font-family: Verdana, Arial, sans-serif; font-size: 13.6000003814697px; line-height: 15.9999980926514px;"&gt;mkl_?csrsv&lt;/A&gt;. It would faster because of internally, we make conversion coo-&amp;gt;csr.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&lt;SPAN class="option" style="color: rgb(8, 96, 168); font-family: 'Courier New', Courier, monospace; font-size: 13.6000003814697px; line-height: 15.9999980926514px;"&gt;--Gennady&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 03:08:51 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038723#M20586</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2014-10-30T03:08:51Z</dc:date>
    </item>
    <item>
      <title>Thanks Gennady. Is mkl_?csrsv</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038724#M20587</link>
      <description>&lt;P&gt;Thanks Gennady. Is mkl_?csrsv multi threaded? I.e., would there be any effect if I set "mkl_num_threads"? Also, what are the minimal environmental settings needed before I call mkl functions? Thanks!&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 03:26:15 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038724#M20587</guid>
      <dc:creator>Jen_B_</dc:creator>
      <dc:date>2014-10-30T03:26:15Z</dc:date>
    </item>
    <item>
      <title>Jen, </title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038725#M20588</link>
      <description>&lt;P&gt;Jen,&amp;nbsp;&lt;/P&gt;

&lt;P&gt;Not! All sparse triangle solvers ( including CSR, DIA and BSR ) are not threaded, but when you call mkl_?coosv, internally we make the conversation from COO to CSR format ).&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 04:34:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038725#M20588</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2014-10-30T04:34:56Z</dc:date>
    </item>
    <item>
      <title>Gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038726#M20589</link>
      <description>&lt;P&gt;Gennady,&lt;/P&gt;

&lt;P&gt;1) Is it the same for MKL 11.2?&lt;/P&gt;

&lt;P&gt;2) So there is no use of playing with MKL_NUM_THREADS for all of mkl_?{csr/bsr/csc/coo}sv?&lt;/P&gt;

&lt;P&gt;3) Is 2) same for Xeon PHI too?&lt;/P&gt;

&lt;P&gt;Thanks!&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 13:02:15 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038726#M20589</guid>
      <dc:creator>Jen_B_</dc:creator>
      <dc:date>2014-10-30T13:02:15Z</dc:date>
    </item>
    <item>
      <title>yes, all of these statements</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038727#M20590</link>
      <description>&lt;P&gt;yes, all of these statements apply to version 11.2.&lt;/P&gt;

&lt;P&gt;All of these routines (&amp;nbsp;&lt;SPAN style="font-size: 12px; line-height: 14.3999996185303px;"&gt;mkl_?{csr/bsr/csc/coo}sv? ) &amp;nbsp;is single - threaded only&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 12px; line-height: 14.3999996185303px;"&gt;yes, this is the same for all IA including Xeon Phi.&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&lt;SPAN style="font-size: 12px; line-height: 14.3999996185303px;"&gt;Gennady&lt;/SPAN&gt;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 15:11:05 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038727#M20590</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2014-10-30T15:11:05Z</dc:date>
    </item>
    <item>
      <title>Gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038728#M20591</link>
      <description>&lt;P&gt;Gennady,&lt;/P&gt;

&lt;P&gt;Thanks! Last question does it really matter for the csrsv case, whether the row elements column indices are sorted or not in ascending order?&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 16:52:54 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038728#M20591</guid>
      <dc:creator>Jen_B_</dc:creator>
      <dc:date>2014-10-30T16:52:54Z</dc:date>
    </item>
    <item>
      <title>Gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038729#M20592</link>
      <description>&lt;P&gt;Gennady,&lt;/P&gt;

&lt;P&gt;One more, are there any plans to make these multithreaded? Thanks!&lt;/P&gt;</description>
      <pubDate>Thu, 30 Oct 2014 16:56:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/triangular-solver/m-p/1038729#M20592</guid>
      <dc:creator>Jen_B_</dc:creator>
      <dc:date>2014-10-30T16:56:56Z</dc:date>
    </item>
  </channel>
</rss>

