Charm++ problem on EM64T/Myrinet cluster

From: Chona S. Guiang (chona_at_tacc.utexas.edu)
Date: Thu Mar 31 2005 - 16:08:38 CST

   I'm trying to build NAMD on our Myrinet cluster based on
dual-processor EM64T nodes. Had to edit some files as well to prevent
building shared libs. I did a

build charm++ mpi-linux icc smp --no-shared

but the test program pgm aborted:

test 0: initiated [groupring (milind)]
test 0: completed (16.39 sec)
test 1: initiated [nodering (milind)]
test 1: completed (11.92 sec)
test 2: initiated [varsize (mjlang)]
test 2: completed (0.10 sec)
test 3: initiated [varraystest (milind)]
test 3: completed (0.11 sec)
test 4: initiated [groupcast (mjlang)]
test 4: completed (0.29 sec)
test 5: initiated [nodecast (milind)]
test 5: completed (0.31 sec)
test 6: initiated [synctest (mjlang)]
Killed by signal 15.
Killed by signal 15.
Killed by signal 15.
Killed by signal 15.
Mar 31 15:51:21 2005 2596 3 6.0 Rtasks fail:
Rtask(s) 2 : exited with signal <11>
Rtask(s) 1 3 4 : exited with signal <15>

   Has anybody built Charm++ successfully with Intel compilers on a
similarly configured system?

Thanks,
Chona

This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:39:17 CST