LAM/MPI logo

LAM/MPI General User's Mailing List Archives

  |   Home   |   Download   |   Documentation   |   FAQ   |   all just in this list

From: Karl Wette (karl.wette_at_[hidden])
Date: 2005-04-28 00:20:19


Hi,

I am trying to get LAM/MPI 7.1.1 running under Cygwin 1.5.16-1 on a
Windows XP standalone laptop. My intention is to use it for testing
MPI programs on a single processor, i.e. using only localhost - I
assume this is possible?

I managed to compile fine using the --without-romio switch, and by
first commenting out the reference to inet_ntop in
share/ssi/boot/slurm/src/ssi_boot_slurm.c as suggested on the LAM/MPI
mailing list. However when I lamboot and try to mpirun
examples/hello/hello.exe I get:

$ mpirun -v -np 1 examples/hello/hello.exe
2252 examples/hello/hello.exe running on n0 (o)
Hello, world! I am 0 of 1
|°L|\

$ mpirun -v -np 2 examples/hello/hello.exe
3996 examples/hello/hello.exe running on n0 (o)
3484 examples/hello/hello.exe running on n0 (o)
-----------------------------------------------------------------------------
One of the processes started by mpirun has exited with a nonzero exit
code. This typically indicates that the process finished in error.
If your process did not finish in error, be sure to include a "return
0" or "exit(0)" in your C code before exiting the application.

PID 3996 failed on node n0 (127.0.0.1) due to signal 12.
-----------------------------------------------------------------------------

$ mpirun -v -np 3 examples/hello/hello.exe
2664 examples/hello/hello.exe running on n0 (o)
1916 examples/hello/hello.exe running on n0 (o)
3232 examples/hello/hello.exe running on n0 (o)
-----------------------------------------------------------------------------
One of the processes started by mpirun has exited with a nonzero exit
code. This typically indicates that the process finished in error.
If your process did not finish in error, be sure to include a "return
0" or "exit(0)" in your C code before exiting the application.

PID 2664 failed on node n0 (127.0.0.1) due to signal 12.
-----------------------------------------------------------------------------

In other words, it fails for -c > 1. I haven't managed to find this
problem in the LAM mailing list. Does anyone know how to fix this??

The exact commands I used to compile and boot LAM/MPI were:

./configure --without-romio 2>&1 | tee configure.log
make all 2>&1 | tee make_all.log
make install 2>&1 | tee make_install.log
make lamexamples 2>&1 | tee make_lamexamples.log
laminfo -all > laminfo.log
lamboot -d 2>&1 | tee lamboot.log

I also include the logfiles in .tar.gz format.

Many thanks!

Karl Wette
PhD Student, Department of Physics
The Australian National University
Canberra, Australia