[0] DAPL startup(): trying to open default DAPL provider from dat registry: ibnic0v2 [1] DAPL startup(): trying to open default DAPL provider from dat registry: ibnic0v2 [0] MPI startup(): DAPL provider ibnic0v2 [1] MPI startup(): DAPL provider ibnic0v2 [0] MPI startup(): dapl data transfer mode [1] MPI startup(): dapl data transfer mode [0] MPI startup(): Internal info: pinning initialization was done [0] MPI startup(): Rank Pid Node name Pin cpu [0] MPI startup(): 0 3700 CN01 {0,1,2,3,4,5,6,7} [0] MPI startup(): 1 2632 CN02 {0,1,2,3,4,5,6,7} [1] MPI startup(): Internal info: pinning initialization was done [0] MPI startup(): I_MPI_DEBUG=5 [0] MPI startup(): I_MPI_PIN_MAPPING=1:0 0 #--------------------------------------------------- # Intel (R) MPI Benchmark Suite V3.2.3, MPI-1 part #--------------------------------------------------- # Date : Thu Jan 17 08:56:05 2013 # Machine : Intel(R) 64 Family 6 Model 26 Stepping 5, GenuineIntel # Release : 6.1.7601 # Version : Service Pack 1 # MPI Version : 2.2 # MPI Thread Environment: MPI_THREAD_MULTIPLE # New default behavior from Version 3.2 on: # the number of iterations per message size is cut down # dynamically when a certain run time (per message size sample) # is expected to be exceeded. Time limit is defined by variable # "SECS_PER_SAMPLE" (=> IMB_settings.h) # or through the flag => -time # Calling sequence was: # C:\Users\sg\Desktop\imb_3.2.3\WINDOWS\IMB-MPI1_VS_2010\x64\Release\IMB-MPI1.exe # Minimum message length in bytes: 0 # Maximum message length in bytes: 4194304 # # MPI_Datatype : MPI_BYTE # MPI_Datatype for reductions : MPI_FLOAT # MPI_Op : MPI_SUM # # # List of Benchmarks to run: # PingPong # PingPing # Sendrecv # Exchange # Allreduce # Reduce # Reduce_scatter # Allgather # Allgatherv # Gather # Gatherv # Scatter # Scatterv # Alltoall # Alltoallv # Bcast # Barrier #--------------------------------------------------- # Benchmarking PingPong # #processes = 2 #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 3.99 0.00 1 1000 3.99 0.24 2 1000 3.76 0.51 4 1000 3.77 1.01 8 1000 3.78 2.02 16 1000 3.81 4.01 32 1000 3.93 7.77 64 1000 3.93 15.52 128 1000 4.05 30.12 256 1000 4.10 59.57 512 1000 4.41 110.62 1024 1000 4.99 195.63 2048 1000 6.22 314.13 4096 1000 8.30 470.55 8192 1000 10.63 735.28 16384 1000 15.31 1020.76 32768 1000 21.21 1473.49 65536 640 31.53 1982.50 131072 320 52.39 2385.87 262144 160 94.76 2638.22 524288 80 185.22 2699.49 1048576 40 356.92 2801.73 2097152 20 699.45 2859.38 4194304 10 1393.73 2870.00 ... #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.05 0.46 0.26 1 1000 3.41 3.41 3.41 2 1000 3.42 3.42 3.42 4 1000 3.42 3.42 3.42 8 1000 3.42 3.42 3.42 16 1000 3.43 3.44 3.43 32 1000 3.50 3.51 3.50 64 1000 3.55 3.55 3.55 128 1000 3.57 3.58 3.57 256 1000 3.79 3.80 3.80 512 1000 4.08 4.08 4.08 1024 1000 4.74 4.75 4.74 2048 1000 5.89 5.90 5.89 4096 1000 8.12 8.13 8.13 8192 1000 10.31 10.32 10.31 16384 1000 14.74 14.75 14.74 32768 1000 20.05 20.05 20.05 Fatal error in PMPI_Bcast: Other MPI error, error stack: PMPI_Bcast(2112)........: MPI_Bcast(buf=00000000030C0040, count=65536, MPI_BYTE, root=0, comm=0x84000000) failed MPIR_Bcast_impl(1670)...: I_MPIR_Bcast_intra(1887): Failure during collective MPIR_Bcast_intra(1461)..: MPIR_Bcast_binomial(156): message sizes do not match across processes in the collective [0:CN01.****.*****] unexpected disconnect completion event from [1:CN02.****.*****] Assertion failed in file .\dapl_conn_rc.c at line 1128: 0 internal ABORT - process 0 job aborted: rank: node: exit code[: error message] 0: CN01.****.*****: 1: process 0 exited without calling finalize 1: CN02: 1: process 1 exited without calling finalize