<?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 New test in Intel® Moderncode for Parallel Architectures</title>
    <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/New-test/m-p/977778#M5645</link>
    <description>&lt;DIV&gt;I ran the program you sent and the output was:&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Hello from thread 0&lt;/DIV&gt;
&lt;DIV&gt;0 0&lt;/DIV&gt;
&lt;DIV&gt;1 0&lt;/DIV&gt;
&lt;DIV&gt;2 0&lt;/DIV&gt;
&lt;DIV&gt;3 0&lt;/DIV&gt;
&lt;DIV&gt;4 0&lt;/DIV&gt;
&lt;DIV&gt;5 0&lt;/DIV&gt;
&lt;DIV&gt;6 0&lt;/DIV&gt;
&lt;DIV&gt;7 0&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;At this point it hung, so once again the second thread simply never got started. When I set OMP_NUM_THREADS to 1 the program ran fine with one thread outputting all the numbers correctly. When I set it to 2 the program hung at the point I indicated.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Even more strangely, it worked once. I tried it and it hung. Then I tried it again (this time redirecting the output to a file) and it worked, correctly printing hello from both threads and printing all 16 outputs. I then tried it several times more, sometimes outputting to the console and sometimes redirecting the output to a file, and I could never get it to work again.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;You asked if it works with hyperthreading disabled. How do I disable hyperthreading under Linux?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;If you'd like I'd be happy to give you access to a user account on the machine I'm doing this on. We would just have to figure out a secure way for me to send you the username and password. (Phone?)&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks again for your help,&lt;/DIV&gt;
&lt;DIV&gt;Gary&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;P.S. - My Internet connectivity will be spotty over the holidays, but I'll be checking the board at least once a week and I'll be back in more regular contact shortly after New Year's.&lt;/DIV&gt;</description>
    <pubDate>Sat, 20 Dec 2003 07:27:43 GMT</pubDate>
    <dc:creator>gfelder</dc:creator>
    <dc:date>2003-12-20T07:27:43Z</dc:date>
    <item>
      <title>New test</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/New-test/m-p/977778#M5645</link>
      <description>&lt;DIV&gt;I ran the program you sent and the output was:&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Hello from thread 0&lt;/DIV&gt;
&lt;DIV&gt;0 0&lt;/DIV&gt;
&lt;DIV&gt;1 0&lt;/DIV&gt;
&lt;DIV&gt;2 0&lt;/DIV&gt;
&lt;DIV&gt;3 0&lt;/DIV&gt;
&lt;DIV&gt;4 0&lt;/DIV&gt;
&lt;DIV&gt;5 0&lt;/DIV&gt;
&lt;DIV&gt;6 0&lt;/DIV&gt;
&lt;DIV&gt;7 0&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;At this point it hung, so once again the second thread simply never got started. When I set OMP_NUM_THREADS to 1 the program ran fine with one thread outputting all the numbers correctly. When I set it to 2 the program hung at the point I indicated.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Even more strangely, it worked once. I tried it and it hung. Then I tried it again (this time redirecting the output to a file) and it worked, correctly printing hello from both threads and printing all 16 outputs. I then tried it several times more, sometimes outputting to the console and sometimes redirecting the output to a file, and I could never get it to work again.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;You asked if it works with hyperthreading disabled. How do I disable hyperthreading under Linux?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;If you'd like I'd be happy to give you access to a user account on the machine I'm doing this on. We would just have to figure out a secure way for me to send you the username and password. (Phone?)&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks again for your help,&lt;/DIV&gt;
&lt;DIV&gt;Gary&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;P.S. - My Internet connectivity will be spotty over the holidays, but I'll be checking the board at least once a week and I'll be back in more regular contact shortly after New Year's.&lt;/DIV&gt;</description>
      <pubDate>Sat, 20 Dec 2003 07:27:43 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/New-test/m-p/977778#M5645</guid>
      <dc:creator>gfelder</dc:creator>
      <dc:date>2003-12-20T07:27:43Z</dc:date>
    </item>
    <item>
      <title>Re: New test</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/New-test/m-p/977779#M5646</link>
      <description>&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks for running the test program. It's pretty clear that the second thread either isn't created or the program somehow exits before the second thread starts. I'm at a loss as to how either of these possibilities could occur. I can't reproduce the problem on any of my lab systems.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;We need to involve the compiler team at this point. I can think of a few more things for you to try but they won't getyou any closer to a solution. Please submit this issue to &lt;A href="http://www.intel.com/software/products/support/#premier" target="_blank"&gt;Premier Support&lt;/A&gt;. Their support engineers are better suited to working this issue with the compiler developers.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Best regards,&lt;/DIV&gt;
&lt;DIV&gt;Henry&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;PS You can &lt;EM&gt;usually &lt;/EM&gt;enable or disable Hyper-Threading in the BIOS.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;</description>
      <pubDate>Sat, 20 Dec 2003 08:01:45 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/New-test/m-p/977779#M5646</guid>
      <dc:creator>Henry_G_Intel</dc:creator>
      <dc:date>2003-12-20T08:01:45Z</dc:date>
    </item>
  </channel>
</rss>

