I am going to test the difference between mpirun and mpiexec on LSF.
The following manual says that mpirun is related to LSF.
1. I would like to see what physical process mpirun and mpiexec use when working through LSF.
Can the "-trace" command confirm which physical processes are being used?
2. Since there is a case where mpiexec is faster, I want to use mpiexec instead of mpirun.
Is there a disadvantage of not being recognized by job scheduler?
- Cluster Computing
- General Support
- Intel® Cluster Ready
- Message Passing Interface (MPI)
- Parallel Computing
What do you mean by physical processes? Anyway, mpirun is just a wrapper for mpiexec to automatically detect job schedulers. Since Intel MPI 2019, mpiexec can also automatically detect job schedulers. In Intel MPI 2018 only mpirun could do this. So, now you can use just mpiexec.
Best regards, Anatoliy
Please use "export I_MPI_DEBUG=5" in your LSF script to see which processors are used per node.
The flag "-trace" is used to create trace files for the Intel Trace Analyzer and Collector, see https://software.intel.com/en-us/trace-analyzer, i.e. to profile the MPI communication in your code.