|
|
|
|
HPM Counter Statistics | ||||
---|---|---|---|---|
Event | Ntasks | Avg | Min(rank) | Max(rank) |
Communication Event Statistics (0.00% detail, 2.4309e+06 error) | |||||||
---|---|---|---|---|---|---|---|
Buffer Size | Ncalls | Total Time | Min Time | Max Time | %MPI | %Wall | |
MPI_Alltoallv | 20480 | 3376960 | 352826.480 | 8.974e-03 | 9.610e-01 | 14.51 | 4.98 |
MPI_Barrier | 0 | 40110780 | 294302.345 | 1.979e-05 | 6.077e+01 | 12.11 | 4.15 |
MPI_Alltoallv | 114688 | 2531336 | 56499.071 | 2.212e-03 | 1.010e+00 | 2.32 | 0.80 |
MPI_Bcast | 4096 | 16592250 | 50749.650 | 0.000e+00 | 1.044e-01 | 2.09 | 0.72 |
MPI_Bcast | 786432 | 3150000 | 16890.797 | 5.469e-04 | 2.033e-01 | 0.69 | 0.24 |
MPI_Bcast | 2048 | 639450 | 33888.503 | 0.000e+00 | 2.488e+01 | 1.39 | 0.48 |
MPI_Reduce | 786432 | 6426000 | 6677.614 | 2.630e-04 | 1.867e-01 | 0.27 | 0.09 |
MPI_Alltoallv | 131072 | 956344 | 20928.648 | 2.316e-03 | 8.513e-01 | 0.86 | 0.30 |
MPI_Bcast | 393216 | 3024000 | 17767.812 | 4.430e-04 | 2.103e-01 | 0.73 | 0.25 |
MPI_Reduce | 393216 | 6426000 | 30210.954 | 4.470e-04 | 1.958e-01 | 1.24 | 0.43 |
MPI_Allreduce | 786432 | 2406600 | 17873.251 | 2.502e-03 | 1.849e-01 | 0.74 | 0.25 |
MPI_Recv | 4096 | 49225104 | 18694.422 | 0.000e+00 | 3.146e-01 | 0.77 | 0.26 |
MPI_Alltoallv | 14336 | 110720 | 11583.740 | 9.067e-03 | 9.582e-01 | 0.48 | 0.16 |
MPI_Allreduce | 8 | 145160 | 1745.757 | 2.313e-05 | 3.464e-01 | 0.07 | 0.02 |
MPI_Recv | 4 | 122500 | 1057.383 | 0.000e+00 | 6.447e-02 | 0.04 | 0.01 |
MPI_Recv | 65536 | 5093588 | 4007.809 | 5.007e-06 | 1.342e+00 | 0.16 | 0.06 |
MPI_Bcast | 1048576 | 122450 | 3837.154 | 1.108e-03 | 6.666e-02 | 0.16 | 0.05 |
MPI_Bcast | 131072 | 528750 | 3537.996 | 1.883e-05 | 2.481e+00 | 0.15 | 0.05 |
MPI_Bcast | 3584 | 1070600 | 2413.065 | 0.000e+00 | 8.990e-02 | 0.10 | 0.03 |
MPI_Recv | 1048576 | 424635 | 2650.560 | 9.489e-05 | 8.390e-02 | 0.11 | 0.04 |
MPI_Send | 65536 | 5092423 | 2257.346 | 5.960e-06 | 2.687e+00 | 0.09 | 0.03 |
MPI_Reduce | 131072 | 528750 | 2648.681 | 2.694e-05 | 2.968e+00 | 0.11 | 0.04 |
MPI_Bcast | 24576 | 14850 | 2948.968 | 3.815e-06 | 1.652e+00 | 0.12 | 0.04 |
MPI_Allreduce | 4096 | 678650 | 1441.478 | 2.098e-05 | 4.913e-02 | 0.06 | 0.02 |
MPI_Bcast | 12288 | 37500 | 768.075 | 1.907e-06 | 9.274e-02 | 0.03 | 0.01 |
MPI_Sendrecv_replace | 1048576 | 750000 | 1253.583 | 2.070e-04 | 1.361e-02 | 0.05 | 0.02 |
MPI_Bcast | 49152 | 5000 | 925.222 | 6.914e-06 | 5.954e-01 | 0.04 | 0.01 |
MPI_Recv | 3584 | 2413048 | 1118.509 | 0.000e+00 | 3.335e-01 | 0.05 | 0.02 |
MPI_Bcast | 1024 | 8947960 | 1669.162 | 0.000e+00 | 8.970e-02 | 0.07 | 0.02 |
MPI_Bcast | 4 | 17791180 | 1669.231 | 0.000e+00 | 5.448e-02 | 0.07 | 0.02 |
MPI_Alltoall | 4 | 2520 | 953.168 | 2.736e-03 | 1.117e+00 | 0.04 | 0.01 |
Load balance by task: HPM counters |
---|
by MPI rank, by MPI time |
Load balance by task: memory, flops, timings |
by MPI rank, by MPI time |
Communication balance by task (sorted by MPI time) |
by MPI rank , time detail by MPI time , time detail by rank , call list |
Message Buffer Size Distributions: time |
|
Message Buffer Size Distributions: Ncalls |
|
Communication Topology : point to point data flow |
|