<?xml version="1.0" encoding="UTF-8"?>
<!-- Generated on Wed, 25 Nov 2009 15:04:13 -0800 -->
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <atom:link href="http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/feed" rel="self" type="application/rss+xml" />
    <title>Intel Software Network - <![CDATA[ Intel Fortran debugger and MPICH ]]> feed</title>
    <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512</link>
    <description></description>
    <language>en-us</language>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;"></div>
There was a thread several years ago about idb (now named idbc) and mpich:<br /><a href="http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/50526/">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/50526/</a><br />Is there nothing about updates to this on the mpich2 support sites?  Did it change that much?<br />Your command line appears to invoke debugging of mpiexec, not of your program.<br /><br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Thu, 29 Oct 2009 15:48:50 -0700</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/367365">tim18</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em> There was a thread several years ago about idb (now named idbc) and mpich:<br /><a href="http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/50526/">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/50526/</a><br />Is there nothing about updates to this on the mpich2 support sites?  Did it change that much?<br />Your command line appears to invoke debugging of mpiexec, not of your program.<br /><br /></em></div>
</div>
</div>
I guess there have been some changes. I have tried out what was suggested in that thread and it didn't work either:<br />neither mpirun nor the now recommended mpiexec recognize -dbg=idb as a valid option, whereas invoking it as<br />mpiexec -machinefile machines -n 1 idb stagyympi <br />yields:<br />problem with execution of idb  on  compute-0-0.local:  [Errno 2] No such file or directory <br />So, no luck there. Any other ideas?<br />Thomas<br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Thu, 29 Oct 2009 20:08:48 -0700</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/449851">truedas</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em>Hi,<br /><br />$ idb -parallel mpiexec -machinefile machines -n 4 ./stagyympi <br /><br />Any ideas what may be wrong here?<br />Thomas</em></div>
</div>
</div>
<br />Hi Thomas,<br /><br />Thank you for the interest to Intel products.<br /><br />The command line looks very strange. It should look like:<br />"xterm -e idb -pid &lt;pid_of_mpiexec&gt; -mpi2 -parallel /usr/bin/python"<br /><br />Also you should set environment variables:<br />IDB_HOME=&lt;where_idb_is_located&gt;<br />LD_LIBRARY_PATH=&lt;where_idb_libraries_are_located&gt;<br />IDB_PARALLEL_SHELL=&lt;full_path_to_ssh&gt; - you don't need this var if you use rsh connection.<br />Probably, MPIEXEC_DEBUG=1<br /><br />I hope this helps.<br /><br />Best wishes,<br /> Dmitry<br /><br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Thu, 29 Oct 2009 22:57:50 -0700</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/423452">Dmitry Kuzmin (Intel)</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em>
<div style="margin:0px;"></div>
<br />Hi Thomas,<br /><br />Thank you for the interest to Intel products.<br /><br />The command line looks very strange. It should look like:<br />"xterm -e idb -pid &lt;pid_of_mpiexec&gt; -mpi2 -parallel /usr/bin/python"<br /><br />Also you should set environment variables:<br />IDB_HOME=&lt;where_idb_is_located&gt;<br />LD_LIBRARY_PATH=&lt;where_idb_libraries_are_located&gt;<br />IDB_PARALLEL_SHELL=&lt;full_path_to_ssh&gt; - you don't need this var if you use rsh connection.<br />Probably, MPIEXEC_DEBUG=1<br /><br />I hope this helps.<br /><br />Best wishes,<br /> Dmitry<br /><br /></em></div>
</div>
</div>
Hi Dmitry,<br />I finally got to trying that out, but setting the IDB_PARALLEL_SHELL and MPIEXEC_DEBUG as you said made things hang. When I have only IDB_HOME and LD_LIBRARY_PATH set, I can somehow start the debugger and it seems to try to attach somehow to the process (although I don't understand why the last argument is the python executable and not the actual program executable), but then it says:<br />Intel(R) Debugger for applications running on IA-32, Version 9.1-28, Build 20070305<br />Reading symbolic information from /opt/rocks/bin/python2.4...No debugging symbols found<br />Attached to process id 27609  ....<br />stopped at [&lt;opaque&gt; _dl_sysinfo_int80(...) 0x008ca7a2]    <br />Symbol "MPIR_being_debugged" is not defined.<br />Symbol "MPIR_Breakpoint" is not defined.<br />Symbol "MPIR_Breakpoint" is not defined.<br />::MPIR_Breakpoint has no valid breakpoint address<br />Make breakpoint pending on future shared library load? (y or [n]) <br />Warning: Breakpoint not set<br /><br />and hangs, no matter whether I have chosen y or n in the breakpoint question.<br /><br />So, as that failed, I was prompted to look back into my MPICH installation again and notice that for some reason, it says in the configure log:<br />configure: WARNING: unrecognized options: --enable-debuginfo<br /><br />although according to the installation guide, this is the option I should give to "provide access to the message queues for debuggers". In the configure log, it also says later:<br />checking debugging support... no<br />although I'm not sure whether that refers to this kind of debugging or rather to the debugging options for MPICH2 developpers themselves (which would not be of interest for me).<br />So basically, I'm rather confused about the error messages and wonder if I have to build MPICH2 in a different way to make the Intel debugger work (and if so, how).<br />May the problem lie here already, and how do you build MPICH2 then?<br />Thomas<br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Fri, 30 Oct 2009 15:45:45 -0700</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/449851">truedas</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em>
<div style="margin:0px;"></div>
Hi Dmitry,<br />I finally got to trying that out, but setting the IDB_PARALLEL_SHELL and MPIEXEC_DEBUG as you said made things hang. When I have only IDB_HOME and LD_LIBRARY_PATH set, I can somehow start the debugger and it seems to try to attach somehow to the process (although I don't understand why the last argument is the python executable and not the actual program executable), but then it says:<br />Intel(R) Debugger for applications running on IA-32, Version 9.1-28, Build 20070305<br />Reading symbolic information from /opt/rocks/bin/python2.4...No debugging symbols found<br />Attached to process id 27609  ....<br />stopped at [&lt;opaque&gt; _dl_sysinfo_int80(...) 0x008ca7a2]    <br />Symbol "MPIR_being_debugged" is not defined.<br />Symbol "MPIR_Breakpoint" is not defined.<br />Symbol "MPIR_Breakpoint" is not defined.<br />::MPIR_Breakpoint has no valid breakpoint address<br />Make breakpoint pending on future shared library load? (y or [n]) <br />Warning: Breakpoint not set<br /><br />and hangs, no matter whether I have chosen y or n in the breakpoint question.<br /><br />So, as that failed, I was prompted to look back into my MPICH installation again and notice that for some reason, it says in the configure log:<br />configure: WARNING: unrecognized options: --enable-debuginfo<br /><br />although according to the installation guide, this is the option I should give to "provide access to the message queues for debuggers". In the configure log, it also says later:<br />checking debugging support... no<br />although I'm not sure whether that refers to this kind of debugging or rather to the debugging options for MPICH2 developpers themselves (which would not be of interest for me).<br />So basically, I'm rather confused about the error messages and wonder if I have to build MPICH2 in a different way to make the Intel debugger work (and if so, how).<br />May the problem lie here already, and how do you build MPICH2 then?<br />Thomas<br /></em></div>
</div>
</div>
<br />Hi Thomas,<br /><br />I was talking about Intel MPI Library and IDB.<br />I don't know how MPICH supports IDB, but invocation looked incorrectly. Probably MPICH was configured incorrecly during installation.<br />An application hangs because of MPIEXEC_DEBUG variable.<br /><br />IDB attaches to a python script first to get information about running processes from mtv.so. Mpiexec should wait for a debugger.<br /><br />BTW: your IDB is very old... March 2007 - I'm not sure that IDB could work correctly with MPI-2 applications at that time. Could you get idb 10.1 somehow?<br /><br />Regards!<br /> Dmitry<br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Sun, 01 Nov 2009 23:04:59 -0800</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ Some clarifications about idb 9.1 usage with mpich:<br /><br />The correct start up command is:<br />mpirun -dbg=idb -np &lt;number of processes&gt; &lt;binary name&gt;<br /><br />Two pre-requisites:<br />1. The environment variable IDB_HOME needs to be set to the directory where IDB resides.<br />2. The file mpirun_dbg.idb, which is included in the IDB 9.1 distribution, needs to be put in the "bin" directory of the MPICH installation.<br /><br />Please try this out and let me know if this helps.<br /><br />Best wishes,<br /> Dmitry<br /><br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Mon, 02 Nov 2009 22:03:55 -0800</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/423452">Dmitry Kuzmin (Intel)</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em>Some clarifications about idb 9.1 usage with mpich:<br /><br />The correct start up command is:<br />mpirun -dbg=idb -np &lt;number of processes&gt; &lt;binary name&gt;<br /><br />Two pre-requisites:<br />1. The environment variable IDB_HOME needs to be set to the directory where IDB resides.<br />2. The file mpirun_dbg.idb, which is included in the IDB 9.1 distribution, needs to be put in the "bin" directory of the MPICH installation.<br /><br />Please try this out and let me know if this helps.<br /><br />Best wishes,<br /> Dmitry<br /><br /></em></div>
</div>
</div>
Hi Dmitry,<br />thanks for the info, and sorry for being slow with the response.<br /><br />I guess it will be difficult to get my hands on a more recent version of the compiler on that architecture, but I tried it now with the version, and it still doesn't work.<br />$ echo $IDB_HOME<br /> /opt/intel/idb/9.1.045/<br />I also copied mpirun_dbg.idb into the bin directory where the MPICH executables live, but neither mpirun nor mpiexec recognize the option -gdb:<br />$ mpirun -gdb=idb -np 4 stagyympi<br /> invalid "local" arg: -gdb=idb<br /><br />I have looked in the installation guide if there is a way to "teach" MPICH the use of compilers other than gdb, but have found none.<br /><br />Thomas<br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Thu, 05 Nov 2009 21:54:53 -0800</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
    <item>
      <title>Re: Intel Fortran debugger and MPICH</title>
      <description><![CDATA[ <div style="margin:0px;">
<div id="quote_reply" style="width: 100%; margin-top: 5px;">
<div style="margin-left:2px;margin-right:2px;">Quoting - <a href="/en-us/profile/449851">truedas</a></div>
<div style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"><em>
<div style="margin:0px;"></div>
I have looked in the installation guide if there is a way to "teach" MPICH the use of compilers other than gdb, but have found none.<br /><br />Thomas<br /></em></div>
</div>
</div>
<br />I've looked into the MPICH2 mpiexec.py script and seems they support only GDB (-gdb) and TV (-tv) debuggers. -gdb option doesn't have parameters.<br />Unfortunately it's not so easy to modify mpiexec.py so that it would work with idb. If you wanna use IDB you probably need to install Intel MPI Library.<br /><br />Regards!<br /> Dmitry<br /><br /> ]]></description>
      <link>http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</link>
      <pubDate>Fri, 06 Nov 2009 06:42:11 -0800</pubDate>
      <guid isPermaLink="true">http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology/topic/69512/</guid>
      <category>Intel® Cluster Ready</category>
      <category>Tools</category>
    </item>
  </channel></rss>