<?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 Slow DSS solver in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947860#M15024</link>
    <description>&lt;DIV&gt;Hello everone!&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;I have two questions about DSS solver.&lt;/DIV&gt;
&lt;DIV&gt;1. Why is the first use of dss_reorder( ) VERY SLOW? For a matrix 1300x1300 with only 5000nnz I had to stop my program because it hunged (even for a matrix of size 7 it takes about a second or two to reorder) Is this normal, or I am doing some kind of a mistake....&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;2. What could possibly be a couse of an error "MKL-DSS-DSS-Error, An unclassifiable error occured"? I get it while using several time the routine for solving which is almost identical to an example program in dss_sym. It always crashes on reordering routine and it occures in unpredictable moments. This happens during solving the same system in each routine call.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thank you in advance for any answer&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Peter&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;</description>
    <pubDate>Tue, 20 Jul 2004 06:56:40 GMT</pubDate>
    <dc:creator>Deleted_U_Intel</dc:creator>
    <dc:date>2004-07-20T06:56:40Z</dc:date>
    <item>
      <title>Slow DSS solver</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947860#M15024</link>
      <description>&lt;DIV&gt;Hello everone!&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;I have two questions about DSS solver.&lt;/DIV&gt;
&lt;DIV&gt;1. Why is the first use of dss_reorder( ) VERY SLOW? For a matrix 1300x1300 with only 5000nnz I had to stop my program because it hunged (even for a matrix of size 7 it takes about a second or two to reorder) Is this normal, or I am doing some kind of a mistake....&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;2. What could possibly be a couse of an error "MKL-DSS-DSS-Error, An unclassifiable error occured"? I get it while using several time the routine for solving which is almost identical to an example program in dss_sym. It always crashes on reordering routine and it occures in unpredictable moments. This happens during solving the same system in each routine call.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thank you in advance for any answer&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Peter&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;</description>
      <pubDate>Tue, 20 Jul 2004 06:56:40 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947860#M15024</guid>
      <dc:creator>Deleted_U_Intel</dc:creator>
      <dc:date>2004-07-20T06:56:40Z</dc:date>
    </item>
    <item>
      <title>Re: Slow DSS solver</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947861#M15025</link>
      <description>&lt;DIV&gt;Peter,&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;First of all, thanks for trying out DSS. &lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;It is difficult to diagnose this issue with the information given. DSS should be fast and should reorder that matrix efficiently.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;I would suggest reporting this to Intel Premier support with a suitable example.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Bruce&lt;/DIV&gt;</description>
      <pubDate>Tue, 27 Jul 2004 01:21:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947861#M15025</guid>
      <dc:creator>Intel_C_Intel</dc:creator>
      <dc:date>2004-07-27T01:21:13Z</dc:date>
    </item>
    <item>
      <title>Re: Slow DSS solver</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947862#M15026</link>
      <description>&lt;DIV&gt;Hi Peter &lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;The DSS solver is based on PARDISO and I am one of the authors. Do you haveany dense rows or columns in the sparse systems. This might be a problem in theMKL Pardiso Version.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;I am interested in the problem. Could you please send me the system?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Olaf Schenk&lt;/DIV&gt;
&lt;DIV&gt;CS Department&lt;/DIV&gt;
&lt;DIV&gt;University of Basel&lt;/DIV&gt;
&lt;DIV&gt;Switzerland&lt;/DIV&gt;</description>
      <pubDate>Thu, 12 Aug 2004 22:52:57 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Slow-DSS-solver/m-p/947862#M15026</guid>
      <dc:creator>basel</dc:creator>
      <dc:date>2004-08-12T22:52:57Z</dc:date>
    </item>
  </channel>
</rss>

