I am using PGI 9.0-1 to compile OpenMPI 1.3.3. I use the following
command to configure OpenMPI:
./configure CC=pgcc CXX=pgCC FC=pgf90 F90=pgf90 --prefix=/shared/ben/
openmpi-1.3.3
The PGI compilers are in the path. The make and make install complete
successfully. The problem that I am hav
I'm attempting to compile OpenMPI version 1.3.3 with Intel C/C++/Fortran
version 11.1.046. Others have reported success using these compilers (
http://software.intel.com/en-us/forums/intel-c-compiler/topic/68111/). The
line where compilation fails is included at the end of this message. I have
a
I have received two private emails saying to check my PATH and
LD_LIBRARY_PATH.
The path is OK and I am using the full pathname to make sure I get the
right exe. I also checked the LD_LIBRARY_PATH and that appears to be OK.
On Sep 4, 2009, at 7:28 AM, Ben Mayer wrote:
I am using PGI 9.0-
Hi Ben
Is it a possible problem with your PATH?
Very often Linux distributions (I suppose it is Linux, but maybe not)
have several MPI versions, plus others that may come with compilers,
etc, and their order on your path may not be what you want.
What do "which mpif90" and "which mpiexec" tell?
Hi Ben
My recollection is that similar problems were reported here
when there was some residual of a previous build
(perhaps with gfortran), which was not completely
cleaned up, when the current build was compiled.
Have you tried to start fresh from the tarball using PGI only?
Gus Correa
--
Good idea. I have tried it twice.
On Sep 4, 2009, at 9:33 AM, Gus Correa wrote:
Hi Ben
My recollection is that similar problems were reported here
when there was some residual of a previous build
(perhaps with gfortran), which was not completely
cleaned up, when the current build was compiled
Can you clarify what icpc11.1 is? Is it a sym link to the icpc 11.1
compiler, or is it a shell script that ends up invoking the icpc v11.1
compiler?
I ask because the compile line in question ends up with a complex
quoting scheme that includes a token with spaces in it:
-DOMPI_CONFIG
On Sep 2, 2009, at 5:27 PM, Greg Fischer wrote:
OK, I've found the offending code and gotten rid of the fork()
warning. I'm still left with this:
Sorry for the delay -- I was in Helsinki this past week at the MPI
Forum meeting; that was consuming most of my bandwidth.
[bl302:26556] ***
