<?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: Memory leak when calling DFT from secondary thread in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854716#M6871</link>
    <description>Here is a minimal example, that reproduces the behavior. Notice the difference in dumped memory when running with/without the RUN_IN_PRIMARY_THREAD define.&lt;BR /&gt;&lt;BR /&gt;I'm using Compuware DevPartner for Visual C++ (Version 8.2) for error detection.&lt;BR /&gt;&lt;BR /&gt;Daniel&lt;BR /&gt;&lt;BR /&gt;P.S. I'm linking to the dll version of the C standard library.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
    <pubDate>Fri, 18 Jul 2008 13:06:08 GMT</pubDate>
    <dc:creator>daniel_flassig</dc:creator>
    <dc:date>2008-07-18T13:06:08Z</dc:date>
    <item>
      <title>Memory leak when calling DFT from secondary thread</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854714#M6869</link>
      <description>Hello,&lt;BR /&gt;I'm suffering from a little memory leak here:&lt;BR /&gt;&lt;BR /&gt;I'm using Intel MKL 10.0.3,&lt;BR /&gt;MSVC++ 2005 (Microsoft Compiler).&lt;BR /&gt;&lt;BR /&gt;I link statically to&lt;BR /&gt;mkl_intel_thread.lib,&lt;BR /&gt;libiomp5mt.lib&lt;BR /&gt;&lt;BR /&gt;I do not use OpenMP in the rest of the project. I do not manually set the number of threads to use.&lt;BR /&gt;&lt;BR /&gt;The startup thread is responsible for the user interface. One worker thread (created with _beginthreadex) calls &lt;BR /&gt;DftiCreateDescriptor(...)&lt;BR /&gt;DftiSetValue(...)&lt;BR /&gt;...&lt;BR /&gt;DftiCommitDescriptor(...)&lt;BR /&gt;and then executes a the fourier transforms many times. &lt;BR /&gt;&lt;BR /&gt;In the end I get memory leaks, most of them originating from&lt;BR /&gt;__kmp_allocate_team &amp;gt;&amp;gt; __kmp_print_storage_map_gtid (typically are 148 or 160 bytes each)&lt;BR /&gt;&lt;BR /&gt;For testing purposes I called the fourier transform code directly from within the startup thread and didn't get any memory leaks.&lt;BR /&gt;&lt;BR /&gt;I appreciate any helpful hints&lt;BR /&gt;Best regards&lt;BR /&gt;Daniel&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 17 Jul 2008 15:57:55 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854714#M6869</guid>
      <dc:creator>daniel_flassig</dc:creator>
      <dc:date>2008-07-17T15:57:55Z</dc:date>
    </item>
    <item>
      <title>Re: Memory leak when calling DFT from secondary thread</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854715#M6870</link>
      <description>Hello,&lt;BR /&gt;Thanks Ben. &lt;BR /&gt;I actually knew about the buffers that were not freed. When I said there were no leaks when the DFT was called from the primary thread, that meant none except for the lazily freed buffers. &lt;BR /&gt;It was because there were significantly more leaks (and leaks with a different allocation path), when the DFT was called from a secondary thread, that I posted this topic. The amount of additional leakage is however constant in a sense that it seems not to depend on how often the DFT is called from the secondary thread. &lt;BR /&gt;Best regards&lt;BR /&gt;Daniel&lt;BR /&gt;</description>
      <pubDate>Thu, 17 Jul 2008 17:31:30 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854715#M6870</guid>
      <dc:creator>daniel_flassig</dc:creator>
      <dc:date>2008-07-17T17:31:30Z</dc:date>
    </item>
    <item>
      <title>Re: Memory leak when calling DFT from secondary thread</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854716#M6871</link>
      <description>Here is a minimal example, that reproduces the behavior. Notice the difference in dumped memory when running with/without the RUN_IN_PRIMARY_THREAD define.&lt;BR /&gt;&lt;BR /&gt;I'm using Compuware DevPartner for Visual C++ (Version 8.2) for error detection.&lt;BR /&gt;&lt;BR /&gt;Daniel&lt;BR /&gt;&lt;BR /&gt;P.S. I'm linking to the dll version of the C standard library.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 18 Jul 2008 13:06:08 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Memory-leak-when-calling-DFT-from-secondary-thread/m-p/854716#M6871</guid>
      <dc:creator>daniel_flassig</dc:creator>
      <dc:date>2008-07-18T13:06:08Z</dc:date>
    </item>
  </channel>
</rss>

