Intel® MPI Benchmarks User Guide and Methodology Description
Intel® MPI Benchmarks provides two types of benchmarks for nonblocking collective (NBC) routines that conform to the MPI-3 standard:
When you run the IMB-NBC component, only the overlap benchmarks are enabled by default. To measure pure communication time, specify the particular benchmark name or use the –include command-line parameter to run the _pure flavor of the benchmarks.
The following table lists all IMB-NBC benchmarks:
| Benchmarks Measuring Communication and Computation Overlap (Enabled by Default) | Benchmarks Measuring Pure Communication Time (Disabled by Default) |
|---|---|
|
Ibcast |
Ibcast_pure |
|
Iallgather |
Iallgather_pure |
|
Iallgatherv |
Iallgatherv_pure |
|
Igather |
Igather_pure |
|
Igatherv |
Igatherv_pure |
|
Iscatter |
Iscatter_pure |
|
Iscatterv |
Iscatterv_pure |
|
Ialltoall |
Ialltoall_pure |
|
Ialltoallv |
Ialltoallv_pure |
|
Ireduce |
Ireduce_pure |
|
Ireduce_scatter |
Ireduce_scatter_pure |
|
Iallreduce |
Iallreduce_pure |
|
Ibarrier |
Ibarrier_pure |
Measuring Communication and Computation Overlap
Measuring Pure Communication Time