1st,I'm a newbie.
I've written a mpi program to realize the parallel computing and encounter many problems.
- When the computing scale is small, that means the communication time is short, just needs few minutes, such as 14 minutes or less. The program runs well and finished the jog.
But when the computing scale is bigger, that means need hours of running to finish,probelms come. After about half an hour's running,the program exsit with abnormal,the error message is that:p4_error: interrupt SIGx: 6
but the calculating result in the running time is correct.I don't understand the meaning of this error message. Any one can interpret it to me specifically? And if someone could give me the mpi error message list to chech each message's meaning , I'll appreciate it a lot.
- I'd like to set one rank as the master rank, and give it higher priority. But I still don't know how to se the priority in unix. Maybe someone could give me a way.
Thank you for all your help.