Problem:main function starts with different addresses (ie. stack space is shifted). This causes replication and checkpointing to incorrectly place the stack data and generates seg fault
This problem is random. Most of the time stack starts from same address in all the MPI programs.
Reason: Not sure, but could be because mpirun inserts some env var during execution of the program.
Problem:
main
function starts with different addresses (ie. stack space is shifted). This causes replication and checkpointing to incorrectly place the stack data and generatesseg fault
This problem is random. Most of the time stack starts from same address in all the
MPI
programs.Reason: Not sure, but could be because
mpirun
inserts someenv
var during execution of the program.