<?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 Hi, in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945450#M14840</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;Thanks a lot for testcase, we will investigate the problem.&lt;/P&gt;
&lt;P&gt;With best regards,&lt;/P&gt;
&lt;P&gt;Alexander Kalinkin&lt;/P&gt;</description>
    <pubDate>Fri, 15 Feb 2013 14:51:24 GMT</pubDate>
    <dc:creator>Alexander_K_Intel2</dc:creator>
    <dc:date>2013-02-15T14:51:24Z</dc:date>
    <item>
      <title>Memory leak happened in PARDISO when phase = 33?</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945448#M14838</link>
      <description>&lt;P&gt;Dear administrator,&lt;/P&gt;
&lt;P&gt;I used PARDISO to solve large sparse matrix with phase = 33 many times, I found that the memory usage increased everytime the PARDISO is called with phase=33. So I checked the sample program 'pardiso_sym_c.c' with Intel Inspector. The conculsion is as follows:&lt;/P&gt;
&lt;P&gt;1) When call the PARDISO 100 times with phase = 33, the object size by memory leak is 28800;&lt;/P&gt;
&lt;P&gt;2) When call the PARDISO 1000 times with phase = 33, the object size by memory leak is 288000.&lt;/P&gt;
&lt;P&gt;I also attached the whole solution for you to reproduce the problem.&lt;/P&gt;
&lt;P&gt;Could you please help me to take a look at it?&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Zhanghong Tang&lt;/P&gt;</description>
      <pubDate>Fri, 15 Feb 2013 13:40:19 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945448#M14838</guid>
      <dc:creator>Zhanghong_T_</dc:creator>
      <dc:date>2013-02-15T13:40:19Z</dc:date>
    </item>
    <item>
      <title>I also noticed the funciton</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945449#M14839</link>
      <description>&lt;P&gt;I also noticed the funciton 'mkl_free_buffers' and tried to add it after the PARDISO, however, the results are the same.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Zhanghong Tang&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 15 Feb 2013 13:48:55 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945449#M14839</guid>
      <dc:creator>Zhanghong_T_</dc:creator>
      <dc:date>2013-02-15T13:48:55Z</dc:date>
    </item>
    <item>
      <title>Hi,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945450#M14840</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;Thanks a lot for testcase, we will investigate the problem.&lt;/P&gt;
&lt;P&gt;With best regards,&lt;/P&gt;
&lt;P&gt;Alexander Kalinkin&lt;/P&gt;</description>
      <pubDate>Fri, 15 Feb 2013 14:51:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945450#M14840</guid>
      <dc:creator>Alexander_K_Intel2</dc:creator>
      <dc:date>2013-02-15T14:51:24Z</dc:date>
    </item>
    <item>
      <title>Tang,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945451#M14841</link>
      <description>&lt;P&gt;Tang,&lt;/P&gt;
&lt;P&gt;I noticed you use mkl from composer 2011 ( this is mkl version 10.3 ). I detected the memory leakage with the latest &amp;nbsp;MKL 11.0 ( bundled with Composer 2013 ) and I don't see the leakage. Would you check it on your side? yoг can give the eval version of mkl.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;--Gennady&lt;/P&gt;</description>
      <pubDate>Sat, 16 Feb 2013 04:36:14 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945451#M14841</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2013-02-16T04:36:14Z</dc:date>
    </item>
    <item>
      <title>Hi Gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945452#M14842</link>
      <description>&lt;P&gt;Hi Gennady,&lt;/P&gt;
&lt;P&gt;Thank you very much for your information. Is it really true that MKL 11.0 doesn't have the memory leakage problem? I will try it latter.&lt;/P&gt;
&lt;P&gt;On the other hand, some time ago I gave a post to complain that static link with the new version of MKL will generate too large static library (more than 300 MB) so that I still use version 10.3 (in 10.3 there is a file 'mkl_solver_lp64.lib' and I link with this one instead of 'mkl_core.lib' so that the size of generated library is reasonable). I don't know whether this problem is solved or not, or in your side you don't think it is a problem. However, if the latest version solved the memory leakage problem, I have to use latest version.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Zhanghong Tang&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;</description>
      <pubDate>Sat, 16 Feb 2013 08:33:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945452#M14842</guid>
      <dc:creator>Zhanghong_T_</dc:creator>
      <dc:date>2013-02-16T08:33:41Z</dc:date>
    </item>
    <item>
      <title>Hi Gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945453#M14843</link>
      <description>&lt;P&gt;Hi Gennady,&lt;/P&gt;
&lt;P&gt;Thank you very much for your information. I tested 11.0 and found that the memory leakage problem is really fixed.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Zhanghong Tang&lt;/P&gt;</description>
      <pubDate>Mon, 18 Feb 2013 14:20:46 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-happened-in-PARDISO-when-phase-33/m-p/945453#M14843</guid>
      <dc:creator>Zhanghong_T_</dc:creator>
      <dc:date>2013-02-18T14:20:46Z</dc:date>
    </item>
  </channel>
</rss>

