I suspect the error was something else. `real.exe: error: _get_addr: No such file or directory` does look like a MPICH error. In fact, I suspect mpirun probably is from other package by not hydra, then there is probably some mis-matched assumptions. — Hui Zhou T: 630-252-3430 On Nov 17, 2018, at 12:31 PM, William Gropp <[email protected]<mailto:[email protected]>> wrote: I’m also at a loss to understand why "mpirun ./real.exe” would fail - if a -np xx argument is required, then mpirun should issue the error; if not, then a rational choice of default would be 1 process, and should behave as “mpirun -np 1 ./real.exe”. Of course, it should be mpiexec instead of mpirun, but that shouldn’t matter. Bill William Gropp Director and Chief Scientist, NCSA Thomas M. Siebel Chair in Computer Science University of Illinois Urbana-Champaign On Nov 15, 2018, at 1:01 PM, Gropp, William D via discuss <[email protected]<mailto:[email protected]>> wrote: Yes, singleton is the ./real.exe below. At least that version should have worked. Bill On Nov 14, 2018 2:00 PM, "Zhou, Hui" <[email protected]<mailto:[email protected]>> wrote: Hi Bill, To clarify, a singleton refers to a process started directly — such as ./real.exe, right? For the case of `mpirun ./real.exe`, or even `mpirun -np 1 ./real.exe`, is not technically a singleton, correct? — Hui Zhou On Nov 13, 2018, at 9:30 PM, William Gropp via discuss <[email protected]<mailto:[email protected]>> wrote: This is not quite true. From the MPI standard: 10.5.2 Singleton MPI_INIT A high-quality implementation will allow any process (including those not started with a “parallel application” mechanism) to become an MPI process by calling MPI_INIT. There was a time when MPICH could do this, and there were features in the original PMI to support this. Bill William Gropp Director and Chief Scientist, NCSA Thomas M. Siebel Chair in Computer Science University of Illinois Urbana-Champaign On Nov 13, 2018, at 10:27 AM, Si, Min via discuss <[email protected]<mailto:[email protected]>> wrote: Hi Zhifeng, You have to always execute the MPI program by using mpirun or mpiexec with -np <number of processes>. At MPI_Init, the process tries to read information (e.g., MPI rank, number of processes) from the PMI server which is another process launched by the mpiexec command. This information is necessary for MPI library to initialize communication (e.g., connecting two processes). Best regards, Min On 2018/11/04 10:27, Zhifeng Yang via discuss wrote: Hi After I installed mpich and used it in a FORTRAN code. There is an error while running this FORTRAN code called real.exe by using the following command $./real.exe or $mpirun ./real.exe real.exe: error: _get_addr: No such file or directory real.exe: error: _get_addr: No such file or directory real.exe: error: _get_addr: No such file or directory Fatal error in MPI_Init: Other MPI error, error stack: MPIR_Init_thread(784).....: MPID_Init(1323)...........: channel initialization failed MPIDI_CH3_Init(120).......: MPID_nem_init_ckpt(852)...: MPIDI_CH3I_Seg_commit(364): PMI_Barrier returned -1 But while using mpirun with specifying number of processors. as follows $mpirun -np 1 ./real.exe There is no error any more. I am not sure why? do you have any explanation? Thank you very much Best regards Zhifeng _______________________________________________ discuss mailing list [email protected]<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list [email protected]<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list [email protected]<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss _______________________________________________ discuss mailing list [email protected]<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss