<?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 Limit problem with mkl in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990355#M17969</link>
    <description>Hi,&lt;BR /&gt;&lt;BR /&gt;I'm using mkl to get the inverse of a general matrix&lt;BR /&gt;with lapack in Fortran. I can't get this to work&lt;BR /&gt;for a 20x20 matrix, even if everything seems fine&lt;BR /&gt;for a 15x15 matrix. I got a seg fault when reaching 20x20.&lt;BR /&gt;I don't understand.&lt;BR /&gt;&lt;BR /&gt;Any clue ?&lt;BR /&gt;&lt;BR /&gt;thanks,&lt;BR /&gt;&lt;BR /&gt;Antoine.</description>
    <pubDate>Thu, 26 May 2005 21:58:30 GMT</pubDate>
    <dc:creator>amical</dc:creator>
    <dc:date>2005-05-26T21:58:30Z</dc:date>
    <item>
      <title>Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990355#M17969</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;I'm using mkl to get the inverse of a general matrix&lt;BR /&gt;with lapack in Fortran. I can't get this to work&lt;BR /&gt;for a 20x20 matrix, even if everything seems fine&lt;BR /&gt;for a 15x15 matrix. I got a seg fault when reaching 20x20.&lt;BR /&gt;I don't understand.&lt;BR /&gt;&lt;BR /&gt;Any clue ?&lt;BR /&gt;&lt;BR /&gt;thanks,&lt;BR /&gt;&lt;BR /&gt;Antoine.</description>
      <pubDate>Thu, 26 May 2005 21:58:30 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990355#M17969</guid>
      <dc:creator>amical</dc:creator>
      <dc:date>2005-05-26T21:58:30Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990356#M17970</link>
      <description>I may have problems linking everything.&lt;BR /&gt;&lt;BR /&gt;When I use &lt;BR /&gt;ifort -L/opt/intel/mkl721/lib/32/ -lmkl_ia32 -lguide -lpthread&lt;BR /&gt;&lt;BR /&gt;it can't find the routines for double precision.&lt;BR /&gt;&lt;BR /&gt;With the -static flag, then -lpthread can't be found.&lt;BR /&gt;&lt;BR /&gt;The compilation is successfull only with &lt;BR /&gt;-lmkl -lmkl_lapack64 -lguide -lpthread &lt;BR /&gt;&lt;BR /&gt;But then, I can't have the inverse of a matrix greater than&lt;BR /&gt;16x16&lt;BR /&gt;&lt;BR /&gt;I usually succeed in solving my problems alone, but this time...&lt;BR /&gt;&lt;BR /&gt;Antoine.</description>
      <pubDate>Thu, 26 May 2005 22:20:38 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990356#M17970</guid>
      <dc:creator>amical</dc:creator>
      <dc:date>2005-05-26T22:20:38Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990357#M17971</link>
      <description>You didn't specify enough information to comment effectively.  If you are running Red Hat 9, the static pthreads libraries are provided only in a patch, not in the full release.  If you are running a supported version of linux, those libraries should be present in the distribution, and would normally be installed as part of the gcc development section.</description>
      <pubDate>Fri, 27 May 2005 00:12:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990357#M17971</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2005-05-27T00:12:41Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990358#M17972</link>
      <description>In fact, I'm using a Mandrake Linux Distribution, and&lt;BR /&gt;now I guess this may be the source of the problem.&lt;BR /&gt;I can't verify now, cause I don't have access to my&lt;BR /&gt;computer. Since  what is really required is not clear in the requirements I thought that the libpthread was the one&lt;BR /&gt;in the convenient lib directory. If I get it right, the lib&lt;BR /&gt;is provided with gcc ? What is there in the patch exactly,&lt;BR /&gt;in case where I would need one too ? Is there a more detailled&lt;BR /&gt;documentation on the subject anywhere to help me fix this&lt;BR /&gt;problem ?&lt;BR /&gt;&lt;BR /&gt;Many questions as you see. Anyway, thanks for your answer...</description>
      <pubDate>Fri, 27 May 2005 03:45:07 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990358#M17972</guid>
      <dc:creator>amical</dc:creator>
      <dc:date>2005-05-27T03:45:07Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990359#M17973</link>
      <description>Still, there is something that puzzles me.&lt;BR /&gt;&lt;BR /&gt;Even if I don't have the correct pthread librairy to link&lt;BR /&gt;statically, why is there this limit when I use dynamic&lt;BR /&gt;librairies ? I don't get it.</description>
      <pubDate>Mon, 30 May 2005 15:26:54 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990359#M17973</guid>
      <dc:creator>amical</dc:creator>
      <dc:date>2005-05-30T15:26:54Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990360#M17974</link>
      <description>You didn't make it clear whether you have read up on the shell commands for increasing stack limit. I'm not prepared to research the historical reasons for defaults being set as low as they are.</description>
      <pubDate>Mon, 30 May 2005 19:59:26 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990360#M17974</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2005-05-30T19:59:26Z</dc:date>
    </item>
    <item>
      <title>Re: Limit problem with mkl</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990361#M17975</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;Thanks for your patience.&lt;BR /&gt;&lt;BR /&gt;First, everything works fine now. I found the libpthread.a&lt;BR /&gt;library in a rpm named "glibc-static-devel" everything&lt;BR /&gt;is ok now.&lt;BR /&gt;&lt;BR /&gt;But for the dynamic libraries I still have the same problem,&lt;BR /&gt;which may be due to my programs eventually, but not to a stack&lt;BR /&gt;size limit : ulimit returns "unlimited".&lt;BR /&gt;&lt;BR /&gt;I'll use the static libraries, and everything will be ok.&lt;BR /&gt;I have a friend which has the same problems with my programs,&lt;BR /&gt;I'll tell you if we find anything which could explain this.</description>
      <pubDate>Mon, 30 May 2005 22:44:11 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Limit-problem-with-mkl/m-p/990361#M17975</guid>
      <dc:creator>amical</dc:creator>
      <dc:date>2005-05-30T22:44:11Z</dc:date>
    </item>
  </channel>
</rss>

