|
|
|
|
HPM Counter Statistics | ||||
---|---|---|---|---|
Event | Ntasks | Avg | Min(rank) | Max(rank) |
PAPI_FP_OPS | * | 2734998999.03 | 2710500979 (56) | 2746996009 (1) |
PAPI_L1_DCA | * | 9838173799.80 | 8862399284 (5) | 13758259876 (63) |
PAPI_L1_DCM | * | 154911036.86 | 146734356 (54) | 166527891 (49) |
PAPI_TOT_INS | * | 20485667094.89 | 18534287420 (5) | 28572145975 (63) |
Communication Event Statistics (100.00% detail, -1.7287e-05 error) | |||||||
---|---|---|---|---|---|---|---|
Buffer Size | Ncalls | Total Time | Min Time | Max Time | %MPI | %Wall | |
MPI_Send | 8192 | 816368 | 39.956 | 2.861e-06 | 1.591e-02 | 27.61 | 4.46 |
MPI_Waitsome | 0 | 107060 | 20.114 | 0.000e+00 | 6.649e-02 | 13.90 | 2.24 |
MPI_Allreduce | 8 | 28002 | 11.304 | 0.000e+00 | 6.078e-02 | 7.81 | 1.26 |
MPI_Alltoall | 4 | 6912 | 6.518 | 6.509e-05 | 2.291e-02 | 4.50 | 0.73 |
MPI_Waitall | 32768 | 66168 | 5.426 | 0.000e+00 | 2.500e-03 | 3.75 | 0.61 |
MPI_Send | 32768 | 13880 | 5.423 | 1.693e-05 | 1.307e-02 | 3.75 | 0.60 |
MPI_Waitall | 40960 | 63816 | 3.594 | 0.000e+00 | 2.454e-03 | 2.48 | 0.40 |
MPI_Waitall | 64 | 8694 | 3.343 | 4.270e-04 | 1.512e-03 | 2.31 | 0.37 |
MPI_Waitall | 3072 | 36768 | 3.295 | 0.000e+00 | 2.174e-03 | 2.28 | 0.37 |
MPI_Send | 327680 | 2128 | 2.689 | 5.100e-04 | 7.351e-03 | 1.86 | 0.30 |
MPI_Allgather | 8 | 3904 | 2.638 | 1.180e-04 | 9.050e-03 | 1.82 | 0.29 |
MPI_Allreduce | 4 | 896 | 2.467 | 6.318e-05 | 3.441e-02 | 1.70 | 0.28 |
MPI_Waitall | 8192 | 34464 | 2.317 | 0.000e+00 | 1.627e-03 | 1.60 | 0.26 |
MPI_Waitall | 24576 | 21272 | 1.996 | 0.000e+00 | 2.562e-03 | 1.38 | 0.22 |
MPI_Send | 16384 | 15552 | 1.737 | 9.060e-06 | 3.966e-03 | 1.20 | 0.19 |
MPI_Send | 2048 | 419608 | 1.684 | 0.000e+00 | 7.060e-04 | 1.16 | 0.19 |
MPI_Send | 98304 | 6328 | 1.582 | 4.196e-05 | 4.982e-03 | 1.09 | 0.18 |
MPI_Waitall | 10240 | 33120 | 1.554 | 0.000e+00 | 1.285e-03 | 1.07 | 0.17 |
MPI_Waitall | 2560 | 39216 | 1.549 | 0.000e+00 | 1.953e-03 | 1.07 | 0.17 |
MPI_Send | 12288 | 8944 | 1.515 | 9.060e-06 | 6.376e-03 | 1.05 | 0.17 |
MPI_Send | 40960 | 2376 | 1.347 | 6.390e-05 | 6.734e-03 | 0.93 | 0.15 |
MPI_Waitall | 2048 | 33120 | 1.251 | 0.000e+00 | 6.101e-04 | 0.86 | 0.14 |
MPI_Send | 81920 | 3256 | 1.228 | 3.815e-05 | 3.318e-03 | 0.85 | 0.14 |
MPI_Send | 256 | 265492 | 1.172 | 0.000e+00 | 1.746e-03 | 0.81 | 0.13 |
MPI_Allgather | 4 | 1216 | 1.119 | 1.107e-03 | 9.377e-03 | 0.77 | 0.12 |
MPI_Waitall | 6144 | 12384 | 1.117 | 4.053e-06 | 1.726e-03 | 0.77 | 0.12 |
MPI_Waitall | 512 | 34512 | 1.100 | 0.000e+00 | 1.911e-03 | 0.76 | 0.12 |
MPI_Send | 512 | 436936 | 1.090 | 0.000e+00 | 1.814e-03 | 0.75 | 0.12 |
MPI_Alltoallv | 0 | 6912 | 1.043 | 9.775e-06 | 1.593e-03 | 0.72 | 0.12 |
MPI_Send | 8 | 209744 | 0.986 | 0.000e+00 | 1.721e-03 | 0.68 | 0.11 |
MPI_Waitall | 640 | 33120 | 0.978 | 0.000e+00 | 1.101e-03 | 0.68 | 0.11 |
MPI_Send | 128 | 457112 | 0.967 | 0.000e+00 | 6.130e-04 | 0.67 | 0.11 |
MPI_Send | 20480 | 2320 | 0.941 | 2.599e-05 | 3.541e-02 | 0.65 | 0.10 |
MPI_Irecv | 8192 | 816368 | 0.837 | 0.000e+00 | 1.583e-03 | 0.58 | 0.09 |
MPI_Waitall | 49152 | 21272 | 0.580 | 0.000e+00 | 2.344e-03 | 0.40 | 0.06 |
MPI_Waitall | 1536 | 11040 | 0.538 | 3.099e-06 | 5.782e-04 | 0.37 | 0.06 |
MPI_Allreduce | 24 | 1216 | 0.484 | 1.459e-04 | 3.015e-03 | 0.33 | 0.05 |
MPI_Waitall | 320 | 3312 | 0.464 | 9.537e-07 | 1.172e-03 | 0.32 | 0.05 |
MPI_Waitall | 384 | 9936 | 0.440 | 9.537e-07 | 1.193e-03 | 0.30 | 0.05 |
MPI_Send | 32 | 132288 | 0.428 | 0.000e+00 | 3.540e-04 | 0.30 | 0.05 |
MPI_Waitall | 224 | 3312 | 0.388 | 0.000e+00 | 1.203e-03 | 0.27 | 0.04 |
MPI_Send | 16 | 88608 | 0.356 | 0.000e+00 | 1.667e-03 | 0.25 | 0.04 |
MPI_Send | 64 | 83612 | 0.322 | 0.000e+00 | 9.079e-04 | 0.22 | 0.04 |
MPI_Waitall | 12288 | 11040 | 0.310 | 0.000e+00 | 1.181e-03 | 0.21 | 0.03 |
MPI_Waitall | 448 | 2208 | 0.253 | 1.099e-04 | 1.048e-03 | 0.18 | 0.03 |
MPI_Allreduce | 24576 | 64 | 0.217 | 3.863e-03 | 3.964e-03 | 0.15 | 0.02 |
MPI_Send | 393216 | 192 | 0.192 | 7.510e-04 | 2.515e-03 | 0.13 | 0.02 |
MPI_Irecv | 2048 | 419608 | 0.189 | 0.000e+00 | 2.890e-04 | 0.13 | 0.02 |
MPI_Waitall | 229376 | 1288 | 0.187 | 4.315e-05 | 3.142e-03 | 0.13 | 0.02 |
MPI_Send | 49152 | 280 | 0.179 | 3.149e-04 | 4.466e-03 | 0.12 | 0.02 |
MPI_Reduce | 8 | 1984 | 0.176 | 0.000e+00 | 6.408e-03 | 0.12 | 0.02 |
MPI_Waitall | 896 | 3312 | 0.169 | 2.980e-05 | 5.939e-04 | 0.12 | 0.02 |
MPI_Send | 2560 | 44160 | 0.159 | 0.000e+00 | 8.431e-04 | 0.11 | 0.02 |
MPI_Bcast | 8 | 384 | 0.158 | 4.506e-05 | 2.384e-03 | 0.11 | 0.02 |
MPI_Recv | 4 | 32 | 0.157 | 4.834e-03 | 9.759e-03 | 0.11 | 0.02 |
MPI_Waitall | 768 | 9936 | 0.143 | 0.000e+00 | 4.921e-04 | 0.10 | 0.02 |
MPI_Send | 57344 | 312 | 0.141 | 1.450e-04 | 3.251e-03 | 0.10 | 0.02 |
MPI_Irecv | 512 | 436936 | 0.139 | 0.000e+00 | 2.408e-05 | 0.10 | 0.02 |
MPI_Irecv | 256 | 265492 | 0.138 | 0.000e+00 | 1.581e-03 | 0.10 | 0.02 |
MPI_Irecv | 128 | 457112 | 0.124 | 0.000e+00 | 2.098e-05 | 0.09 | 0.01 |
MPI_Send | 65536 | 200 | 0.114 | 6.604e-05 | 3.615e-03 | 0.08 | 0.01 |
MPI_Send | 131072 | 344 | 0.114 | 1.431e-04 | 3.301e-03 | 0.08 | 0.01 |
MPI_Send | 524288 | 96 | 0.108 | 9.229e-04 | 2.525e-03 | 0.07 | 0.01 |
MPI_Irecv | 8 | 209744 | 0.103 | 0.000e+00 | 1.561e-03 | 0.07 | 0.01 |
MPI_Waitall | 128 | 1104 | 0.101 | 1.192e-06 | 1.208e-03 | 0.07 | 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 |
|
Switch Traffic (volume by node) |
|
Memory usage by node |
|