<?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 Parallel Studio Crashes after Profiling  in Software Archive</title>
    <link>https://community.intel.com/t5/Software-Archive/Parallel-Studio-Crashes-after-Profiling/m-p/745405#M1942</link>
    <description>Initially my application was not multithreaded, using parallel studio we found the hotspots and threaded few modules. After parllelizing the O/P is fine but when we profile again we find the parallel studio lists the hotspots and immediately crashes throwing the following error&lt;BR /&gt;&lt;BR /&gt;[Exception]&lt;BR /&gt;Address: 0x7C90EDDC&lt;BR /&gt;Code: 0xc00000fd&lt;BR /&gt;Description: EXCEPTION_STACK_OVERFLOW&lt;BR /&gt;Module: ntdll.dll &lt;BR /&gt;&lt;BR /&gt;Find the attached file for the dump.&lt;BR /&gt;&lt;BR /&gt;This happens in few configurations only. The part of module that was threaded was low level functions which is invoked nearly 10,000 times (depending upon the configuration). &lt;BR /&gt;&lt;BR /&gt;Every time the function is called, Threads are invoked using QueueUserWorkItem() that are finally suspended on a events using WaitForMultipleObjects() . &lt;BR /&gt;&lt;BR /&gt;We get the correct O/P and expected performance too but profiling leads to a crash.&lt;BR /&gt;&lt;BR /&gt;Can any one give some suggestions for the issue.&lt;BR /&gt;&lt;BR /&gt;Regards&lt;BR /&gt;Venkat&lt;BR /&gt;</description>
    <pubDate>Wed, 10 Nov 2010 10:31:05 GMT</pubDate>
    <dc:creator>Venkatachalam_Vr</dc:creator>
    <dc:date>2010-11-10T10:31:05Z</dc:date>
    <item>
      <title>Parallel Studio Crashes after Profiling</title>
      <link>https://community.intel.com/t5/Software-Archive/Parallel-Studio-Crashes-after-Profiling/m-p/745405#M1942</link>
      <description>Initially my application was not multithreaded, using parallel studio we found the hotspots and threaded few modules. After parllelizing the O/P is fine but when we profile again we find the parallel studio lists the hotspots and immediately crashes throwing the following error&lt;BR /&gt;&lt;BR /&gt;[Exception]&lt;BR /&gt;Address: 0x7C90EDDC&lt;BR /&gt;Code: 0xc00000fd&lt;BR /&gt;Description: EXCEPTION_STACK_OVERFLOW&lt;BR /&gt;Module: ntdll.dll &lt;BR /&gt;&lt;BR /&gt;Find the attached file for the dump.&lt;BR /&gt;&lt;BR /&gt;This happens in few configurations only. The part of module that was threaded was low level functions which is invoked nearly 10,000 times (depending upon the configuration). &lt;BR /&gt;&lt;BR /&gt;Every time the function is called, Threads are invoked using QueueUserWorkItem() that are finally suspended on a events using WaitForMultipleObjects() . &lt;BR /&gt;&lt;BR /&gt;We get the correct O/P and expected performance too but profiling leads to a crash.&lt;BR /&gt;&lt;BR /&gt;Can any one give some suggestions for the issue.&lt;BR /&gt;&lt;BR /&gt;Regards&lt;BR /&gt;Venkat&lt;BR /&gt;</description>
      <pubDate>Wed, 10 Nov 2010 10:31:05 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Parallel-Studio-Crashes-after-Profiling/m-p/745405#M1942</guid>
      <dc:creator>Venkatachalam_Vr</dc:creator>
      <dc:date>2010-11-10T10:31:05Z</dc:date>
    </item>
    <item>
      <title>Parallel Studio Crashes after Profiling</title>
      <link>https://community.intel.com/t5/Software-Archive/Parallel-Studio-Crashes-after-Profiling/m-p/745406#M1943</link>
      <description>Would that be possible to send a test case that we can use to reproduce the crash?&lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;--mark</description>
      <pubDate>Fri, 12 Nov 2010 20:13:39 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Parallel-Studio-Crashes-after-Profiling/m-p/745406#M1943</guid>
      <dc:creator>Mark_S_Intel1</dc:creator>
      <dc:date>2010-11-12T20:13:39Z</dc:date>
    </item>
  </channel>
</rss>

