<?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 Problem with ScaLapack PCLAPRNT (RH Linux, ifort 11.1, openmpi 1.2.4, mkl 10.2.x.x) in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Problem-with-ScaLapack-PCLAPRNT-RH-Linux-ifort-11-1-openmpi-1-2/m-p/817547#M4431</link>
    <description>I have run into a problem with a fortran code when calling scalapack routine PCLAPRNT. As soon as this subroutine is called the code will die on a seg fault. If I use a hand built scalapack and blacs (using source from netlib.org) library with the same code then it will run correctly. It only seg faults when I link the MKL scalapack.&lt;BR /&gt;&lt;BR /&gt;My machine is Linux running RH5 and I trie several flavors of MKL 10.2 including 10.2.6.038. I also use MKL for the blacs and blas. The compiler is ifort 11.1 and the mpi library I am using is a hand-compiler ifort based openmpi v1.2.4.&lt;BR /&gt;&lt;BR /&gt;A code that demonstrates this can be downloaded from &lt;A href="http://www.netlib.org/scalapack/examples/sample_pcheevx_call.f" target="_blank"&gt;http://www.netlib.org/scalapack/examples/sample_pcheevx_call.f&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;here is a copy of my makefile:&lt;BR /&gt;&lt;BR /&gt;EXE = sample_pcheevx.intel.mkl&lt;BR /&gt;F90 = mpif90&lt;BR /&gt;&lt;BR /&gt;MKL_HOME = /usr/global/intel/mkl/10.2.6.038/lib/em64t&lt;BR /&gt;&lt;BR /&gt;SCALAPACKLIB = -lmkl_scalapack_lp64&lt;BR /&gt;LIBBLACS = -lmkl_blacs_openmpi_lp64&lt;BR /&gt;BLASLIB = -lmkl_intel_lp64 -lmkl_sequential -lmkl_core&lt;BR /&gt;&lt;BR /&gt;F90FLAGS = -O3&lt;BR /&gt;LDFLAGS = -L$(MKL_HOME) $(SCALAPACKLIB) $(LIBBLACS) $(BLASLIB) -Wl,-R$(MKL_HOME)&lt;BR /&gt;&lt;BR /&gt;$EXE:sample_pcheevx.f&lt;BR /&gt; $(F90) sample_pcheevx.f -o $(EXE) $(F90FLAGS) $(LDFLAGS)&lt;BR /&gt;&lt;BR /&gt;clean:&lt;BR /&gt; /bin/rm *.o $(EXE)&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;any advice appreciaed.&lt;BR /&gt;&lt;BR /&gt;thanks,&lt;BR /&gt;&lt;BR /&gt;--Jeff</description>
    <pubDate>Fri, 24 Sep 2010 19:01:02 GMT</pubDate>
    <dc:creator>nucci</dc:creator>
    <dc:date>2010-09-24T19:01:02Z</dc:date>
    <item>
      <title>Problem with ScaLapack PCLAPRNT (RH Linux, ifort 11.1, openmpi 1.2.4, mkl 10.2.x.x)</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Problem-with-ScaLapack-PCLAPRNT-RH-Linux-ifort-11-1-openmpi-1-2/m-p/817547#M4431</link>
      <description>I have run into a problem with a fortran code when calling scalapack routine PCLAPRNT. As soon as this subroutine is called the code will die on a seg fault. If I use a hand built scalapack and blacs (using source from netlib.org) library with the same code then it will run correctly. It only seg faults when I link the MKL scalapack.&lt;BR /&gt;&lt;BR /&gt;My machine is Linux running RH5 and I trie several flavors of MKL 10.2 including 10.2.6.038. I also use MKL for the blacs and blas. The compiler is ifort 11.1 and the mpi library I am using is a hand-compiler ifort based openmpi v1.2.4.&lt;BR /&gt;&lt;BR /&gt;A code that demonstrates this can be downloaded from &lt;A href="http://www.netlib.org/scalapack/examples/sample_pcheevx_call.f" target="_blank"&gt;http://www.netlib.org/scalapack/examples/sample_pcheevx_call.f&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;here is a copy of my makefile:&lt;BR /&gt;&lt;BR /&gt;EXE = sample_pcheevx.intel.mkl&lt;BR /&gt;F90 = mpif90&lt;BR /&gt;&lt;BR /&gt;MKL_HOME = /usr/global/intel/mkl/10.2.6.038/lib/em64t&lt;BR /&gt;&lt;BR /&gt;SCALAPACKLIB = -lmkl_scalapack_lp64&lt;BR /&gt;LIBBLACS = -lmkl_blacs_openmpi_lp64&lt;BR /&gt;BLASLIB = -lmkl_intel_lp64 -lmkl_sequential -lmkl_core&lt;BR /&gt;&lt;BR /&gt;F90FLAGS = -O3&lt;BR /&gt;LDFLAGS = -L$(MKL_HOME) $(SCALAPACKLIB) $(LIBBLACS) $(BLASLIB) -Wl,-R$(MKL_HOME)&lt;BR /&gt;&lt;BR /&gt;$EXE:sample_pcheevx.f&lt;BR /&gt; $(F90) sample_pcheevx.f -o $(EXE) $(F90FLAGS) $(LDFLAGS)&lt;BR /&gt;&lt;BR /&gt;clean:&lt;BR /&gt; /bin/rm *.o $(EXE)&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;any advice appreciaed.&lt;BR /&gt;&lt;BR /&gt;thanks,&lt;BR /&gt;&lt;BR /&gt;--Jeff</description>
      <pubDate>Fri, 24 Sep 2010 19:01:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Problem-with-ScaLapack-PCLAPRNT-RH-Linux-ifort-11-1-openmpi-1-2/m-p/817547#M4431</guid>
      <dc:creator>nucci</dc:creator>
      <dc:date>2010-09-24T19:01:02Z</dc:date>
    </item>
    <item>
      <title>Problem with ScaLapack PCLAPRNT (RH Linux, ifort 11.1, openmpi</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Problem-with-ScaLapack-PCLAPRNT-RH-Linux-ifort-11-1-openmpi-1-2/m-p/817548#M4432</link>
      <description>I could not reproduce your error, but that is understandable because you are using a number of custom-built components.&lt;BR /&gt;&lt;BR /&gt;The example uses a couple of big arrays which are allocated on the stack. That could cause problems. You may try reducing LWORK and LRWORK to, say, 10000; you could make sure that you have raised the stack limit adequately; you could use the -heap-arrays compiler option; you could declare some/all of RWORK, WORK, A, Z with the SAVE attribute.&lt;BR /&gt;&lt;BR /&gt;If none of these suggestions work, you may need to replace your custom-built libraries one at a time by a standard version and try running.</description>
      <pubDate>Fri, 24 Sep 2010 21:14:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Problem-with-ScaLapack-PCLAPRNT-RH-Linux-ifort-11-1-openmpi-1-2/m-p/817548#M4432</guid>
      <dc:creator>mecej4</dc:creator>
      <dc:date>2010-09-24T21:14:13Z</dc:date>
    </item>
  </channel>
</rss>

