Hi Ken, I just wanted to let you know that the problem has been fixed. There is an option to the nagfor compiler (-C=undefined) that we used and we should not have. Here’s what the nagfor man page says about this option: The -C=undefined option is subject to a number of limitations and is not binary-compatible with code compiled without that option; see the Undefined Variable Detection section for further details. Kevin Olson HPC Software Developer Numerical Algorithms Group, Inc 801 Warrenville Road, Suite 185 Lisle, Illinois 60532-4332 T 267-664-9913 F 630-971-2706 www.nag.com On 3/10/16, 2:10 PM, "Kenneth Raffenetti" <[email protected]> wrote:
Do you have a small reproducer program we could try on our systems? Also your config.log file would be useful.
We do test this compiler combination on Ubuntu in our nightly builds without issue.
Ken
On 03/10/2016 09:34 AM, Kevin Olson wrote:
Hello,
I am having trouble running a fortran code sung the NAG fortran compiler and various versions of mpich. All fail in the same way: First the error I’ getting:
Fatal error in PMPI_Comm_rank: Invalid argument, error stack: PMPI_Comm_rank(110): MPI_Comm_rank(MPI_COMM_WORLD, rank=(nil)) failed PMPI_Comm_rank(82).: Null pointer in parameter rank Makefile.spicer:414: recipe for target 'initial0' failed make: *** [initial0] Error 1
This comes from the first call to an MPI function after MPI_INIT().
I am attempting to run the code on a Linux (Ubuntu) machine with AMD processor. The code does run successfully on other systems with the same combination of compilers (A Mac for instance). Here are the specs for the compilers used.
NAG Fortran Compiler Release 6.0(Hibiya) Build 1064 Product NPL6A60NA for x86-64 Linux Copyright 1990-2015 The Numerical Algorithms Group Ltd., Oxford, U.K.
Using built-in specs. COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/4.9/lto-wrapper Target: x86_64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Ubuntu 4.9.2-10ubuntu13' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --disable-werror --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu Thread model: posix gcc version 4.9.2 (Ubuntu 4.9.2-10ubuntu13)
Is there an inconsistency with the compilers on such a system? Do you have any other suggestions? Thanks!
Kevin Olson HPC Software Developer Numerical Algorithms Group, Inc 801 Warrenville Road, Suite 185 Lisle, Illinois 60532-4332 T 267-664-9913 F 630-971-2706 www.nag.com Kevin Olson HPC Software Developer Numerical Algorithms Group, Inc 801 Warrenville Road, Suite 185 Lisle, Illinois 60532-4332 T 267-664-9913 F 630-971-2706 www.nag.com
_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss