<?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 Re:pardiso factorization speed in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1389397#M33219</link>
    <description>&lt;P&gt;Hi Karl,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;I just want to let you know that the team is still investigating this issue.&lt;/P&gt;&lt;P&gt;We will let you know once we find out the issue.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;Khang&lt;/P&gt;&lt;BR /&gt;</description>
    <pubDate>Thu, 02 Jun 2022 00:22:13 GMT</pubDate>
    <dc:creator>Khang_N_Intel</dc:creator>
    <dc:date>2022-06-02T00:22:13Z</dc:date>
    <item>
      <title>pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363340#M32786</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;when using pardiso on an upper triangular symmetric matrix of dimension 130,00 x 130,000 with 1,000,000 non-zeros it needs about 15 sec for a factorization, which is very slow compared to cholmod(suitesparse) 0.3 sec.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Further on large matrices, say &amp;gt;1,000,000 x &amp;gt;1,000,000 pardiso is so unbearable slow that it becomes unusable, whereas cholmod(suitesparse) can easily cope with the problem.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Is there any way to speed up pardiso? I figured that it gets stuck at the analysis stage.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I am using oneapi version 2021.2.0 on linux, kernel version 5.16.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks&lt;/P&gt;</description>
      <pubDate>Thu, 24 Feb 2022 12:34:00 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363340#M32786</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-02-24T12:34:00Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363632#M32789</link>
      <description>&lt;P&gt;The only way to speed up the reordering stage is by trying the OpenMP version of Metis (iparm[1]=3). &lt;/P&gt;&lt;P&gt;wrt to factorization performance against cholmod -- here make sense to share the case to check the behavior on our end.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 25 Feb 2022 05:37:57 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363632#M32789</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2022-02-25T05:37:57Z</dc:date>
    </item>
    <item>
      <title>Re: pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363975#M32800</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;I'll make an example.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Question is how I can get he matrix to Intel? My current best example matrix with 12M rows/columns and 500M elements needs 11GB on disk!&lt;/P&gt;</description>
      <pubDate>Fri, 25 Feb 2022 23:50:37 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1363975#M32800</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-02-25T23:50:37Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1364000#M32803</link>
      <description>&lt;P&gt;You could upload the case anywhere ( google drive as an example) and give us the link by the private channel into this forum or directly via email ( Gennady.Fedorov@intel.com). And please add the driver which will write this matrix and run the solver with your parameters. It will essentially save the reproducing time.&lt;/P&gt;&lt;P&gt;-Gennady&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Sat, 26 Feb 2022 04:45:49 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1364000#M32803</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2022-02-26T04:45:49Z</dc:date>
    </item>
    <item>
      <title>Re: Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1364096#M32805</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I have emailed you a link for downloading an archive with matrix and driver.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The example also reproduces the observation from this thread &lt;A href="https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/omp-warning-when-using-pardiso-and-metis-threaded-version/td-p/1363562" target="_self"&gt;https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/omp-warning-when-using-pardiso-and-metis-threaded-version/td-p/1363562&lt;/A&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks for looking into this.&lt;/P&gt;</description>
      <pubDate>Sun, 27 Feb 2022 00:24:23 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1364096#M32805</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-02-27T00:24:23Z</dc:date>
    </item>
    <item>
      <title>Re: pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1368485#M32909</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&lt;a href="https://community.intel.com/t5/user/viewprofilepage/user-id/41889"&gt;@Gennady_F_Intel&lt;/a&gt; wondering whether you had the time yet to look into the example provided?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I just installed oneapi 2022.0.2, and all the described problems remain, even the omp_nested warning from this &lt;A href="https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/omp-warning-when-using-pardiso-and-metis-threaded-version/td-p/1363562" target="_self"&gt;thread&lt;/A&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 14 Mar 2022 08:34:14 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1368485#M32909</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-03-14T08:34:14Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1368829#M32915</link>
      <description>&lt;P&gt;I am very sorry, Karl. I missed this thread and will do it asap.&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 15 Mar 2022 04:35:18 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1368829#M32915</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2022-03-15T04:35:18Z</dc:date>
    </item>
    <item>
      <title>Re: Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1373913#M32960</link>
      <description>&lt;P&gt;Hi Gennady,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I responded to your email some time ago pointing out that there must be an issue at your side reading the sparse array in binary.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Is there any update on this?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Best&lt;/P&gt;</description>
      <pubDate>Mon, 04 Apr 2022 00:15:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1373913#M32960</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-04-04T00:15:16Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1373929#M32961</link>
      <description>&lt;P&gt;Hi Karl,&lt;/P&gt;&lt;P&gt;I responded by email to you on this matter.&lt;/P&gt;&lt;P&gt;The reordering performance problem has been reproduced on our end and escalated against the Sparse Solver Team.&lt;/P&gt;&lt;P&gt;We will keep this thread updated in case of any updates.&lt;/P&gt;&lt;P&gt;thanks,&lt;/P&gt;&lt;P&gt;Gennady&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 04 Apr 2022 01:38:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1373929#M32961</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2022-04-04T01:38:42Z</dc:date>
    </item>
    <item>
      <title>Re: Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1376645#M33013</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I had contacted the pardiso team about this problem as well, and according to their test and a test library they provided to me the problem does not affect the most recent pardiso version.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Does Intel have any plans for updating pardiso?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks.&lt;/P&gt;</description>
      <pubDate>Tue, 12 Apr 2022 23:18:29 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1376645#M33013</guid>
      <dc:creator>may_ka</dc:creator>
      <dc:date>2022-04-12T23:18:29Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1389397#M33219</link>
      <description>&lt;P&gt;Hi Karl,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;I just want to let you know that the team is still investigating this issue.&lt;/P&gt;&lt;P&gt;We will let you know once we find out the issue.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;Khang&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 02 Jun 2022 00:22:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1389397#M33219</guid>
      <dc:creator>Khang_N_Intel</dc:creator>
      <dc:date>2022-06-02T00:22:13Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1410254#M33562</link>
      <description>&lt;P&gt;Hi Karl,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;The issue has already been escalated to the mkl team.&lt;/P&gt;&lt;P&gt;Due to many changes, we might not have a solution at this time.&lt;/P&gt;&lt;P&gt;I will consult with the mkl team and will get back to with an estimated timelione.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;Khang&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 23 Aug 2022 21:47:47 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1410254#M33562</guid>
      <dc:creator>Khang_N_Intel</dc:creator>
      <dc:date>2022-08-23T21:47:47Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1411017#M33574</link>
      <description>&lt;P&gt;Hi Karl,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;The latest I received from the mkl team is that the solution might not be available until, to the earliest, the second half of next year.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;Khang&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 26 Aug 2022 17:21:43 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1411017#M33574</guid>
      <dc:creator>Khang_N_Intel</dc:creator>
      <dc:date>2022-08-26T17:21:43Z</dc:date>
    </item>
    <item>
      <title>Re:pardiso factorization speed</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1630859#M36427</link>
      <description>&lt;P&gt;Hi Karl.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;This issue will be fixed in the upcoming oneAPI 2025.0 release.&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 13 Sep 2024 02:17:58 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/pardiso-factorization-speed/m-p/1630859#M36427</guid>
      <dc:creator>Mahan</dc:creator>
      <dc:date>2024-09-13T02:17:58Z</dc:date>
    </item>
  </channel>
</rss>

