C:\Program Files (x86)\Intel\oneAPI\mpi\latest\benchmarks\imb\WINDOWS\IMB-MPI1_VS_2017\x64\Debug> IMB-MPI1.exe #---------------------------------------------------------------- # Intel(R) MPI Benchmarks 2021.5, MPI-1 part #---------------------------------------------------------------- # Date : Fri Oct 27 15:28:06 2023 # Machine : Intel(R) 64 Family 6 Model 142 Stepping 12, GenuineIntel # Release : 6.2.9200 # Version : # MPI Version : 3.1 # MPI Thread Environment: # Calling sequence was: # C:\Program Files (x86)\Intel\oneAPI\mpi\latest\env\..\bin\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_local # Reduce_scatter # Reduce_scatter_block # Allgather # Allgatherv # Gather # Gatherv # Scatter # Scatterv # Alltoall # Alltoallv # Bcast # Barrier # !! Benchmark PingPong invalid for 1 processes !! # !! Benchmark PingPing invalid for 1 processes !! #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 1 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 27.77 27.77 27.77 0.00 1 1000 27.11 27.11 27.11 0.07 2 1000 29.22 29.22 29.22 0.14 4 1000 28.83 28.83 28.83 0.28 8 1000 29.07 29.07 29.07 0.55 16 1000 37.51 37.51 37.51 0.85 32 1000 32.27 32.27 32.27 1.98 64 1000 30.79 30.79 30.79 4.16 128 1000 34.46 34.46 34.46 7.43 256 1000 45.54 45.54 45.54 11.24 512 1000 44.51 44.51 44.51 23.00 1024 1000 45.87 45.87 45.87 44.65 2048 1000 45.00 45.00 45.00 91.02 4096 1000 46.28 46.28 46.28 177.01 8192 1000 47.09 47.09 47.09 347.93 16384 1000 61.52 61.52 61.52 532.68 32768 1000 66.50 66.50 66.50 985.43 65536 640 77.61 77.61 77.61 1688.80 131072 320 116.86 116.86 116.86 2243.27 262144 160 300.44 300.44 300.44 1745.08 524288 80 1840.03 1840.03 1840.03 569.87 1048576 40 1275.58 1275.58 1275.58 1644.07 2097152 20 1667.11 1667.11 1667.11 2515.92 4194304 10 4364.01 4364.01 4364.01 1922.22 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 1 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 55.83 55.83 55.83 0.00 1 1000 49.71 49.71 49.71 0.08 2 1000 44.82 44.82 44.82 0.18 4 1000 38.73 38.73 38.73 0.41 8 1000 38.97 38.97 38.97 0.82 16 1000 38.98 38.98 38.98 1.64 32 1000 40.18 40.18 40.18 3.19 64 1000 40.26 40.26 40.26 6.36 128 1000 50.15 50.15 50.15 10.21 256 1000 70.81 70.81 70.81 14.46 512 1000 71.46 71.46 71.46 28.66 1024 1000 73.17 73.17 73.17 55.98 2048 1000 96.30 96.30 96.30 85.06 4096 1000 101.13 101.13 101.13 162.01 8192 1000 109.42 109.42 109.42 299.48 16384 1000 92.21 92.21 92.21 710.75 32768 1000 96.52 96.52 96.52 1358.00 65536 640 134.28 134.28 134.28 1952.23 131072 320 207.61 207.61 207.61 2525.31 262144 160 467.77 467.77 467.77 2241.65 524288 80 2553.52 2553.52 2553.52 821.28 1048576 40 3273.67 3273.67 3273.67 1281.22 2097152 20 5307.71 5307.71 5307.71 1580.46 4194304 10 6032.82 6032.82 6032.82 2780.99 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 4 1000 0.04 0.04 0.04 8 1000 0.06 0.06 0.06 16 1000 0.06 0.06 0.06 32 1000 0.05 0.05 0.05 64 1000 0.06 0.06 0.06 128 1000 0.05 0.05 0.05 256 1000 0.05 0.05 0.05 512 1000 0.06 0.06 0.06 1024 1000 0.07 0.07 0.07 2048 1000 0.10 0.10 0.10 4096 1000 0.13 0.13 0.13 8192 1000 0.14 0.14 0.14 16384 1000 0.29 0.29 0.29 32768 1000 1.06 1.06 1.06 65536 640 1.68 1.68 1.68 131072 320 3.05 3.05 3.05 262144 160 10.13 10.13 10.13 524288 80 23.95 23.95 23.95 1048576 40 45.37 45.37 45.37 2097152 20 83.11 83.11 83.11 4194304 10 195.65 195.65 195.65 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.06 0.06 0.06 4 1000 0.05 0.05 0.05 8 1000 0.09 0.09 0.09 16 1000 0.08 0.08 0.08 32 1000 0.05 0.05 0.05 64 1000 0.05 0.05 0.05 128 1000 0.05 0.05 0.05 256 1000 0.05 0.05 0.05 512 1000 0.06 0.06 0.06 1024 1000 0.06 0.06 0.06 2048 1000 0.06 0.06 0.06 4096 1000 0.15 0.15 0.15 8192 1000 0.26 0.26 0.26 16384 1000 0.43 0.43 0.43 32768 1000 0.94 0.94 0.94 65536 640 1.56 1.56 1.56 131072 320 3.17 3.17 3.17 262144 160 9.48 9.48 9.48 524288 80 20.10 20.10 20.10 1048576 40 32.77 32.77 32.77 2097152 20 75.85 75.85 75.85 4194304 10 188.00 188.00 188.00 #---------------------------------------------------------------- # Benchmarking Reduce_local # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 0.04 0.04 0.04 8 1000 0.04 0.04 0.04 16 1000 0.04 0.04 0.04 32 1000 0.04 0.04 0.04 64 1000 0.04 0.04 0.04 128 1000 0.05 0.05 0.05 256 1000 0.05 0.05 0.05 512 1000 0.05 0.05 0.05 1024 1000 0.07 0.07 0.07 2048 1000 0.09 0.09 0.09 4096 1000 0.15 0.15 0.15 8192 1000 0.24 0.24 0.24 16384 1000 0.66 0.66 0.66 32768 1000 1.55 1.55 1.55 65536 640 2.46 2.46 2.46 131072 320 6.41 6.41 6.41 262144 160 14.83 14.83 14.83 524288 80 24.04 24.04 24.04 1048576 40 63.13 63.13 63.13 2097152 20 104.22 104.22 104.22 4194304 10 312.60 312.60 312.60 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.18 0.18 0.18 4 1000 0.48 0.48 0.48 8 1000 0.57 0.57 0.57 16 1000 0.56 0.56 0.56 32 1000 0.45 0.45 0.45 64 1000 0.47 0.47 0.47 128 1000 0.27 0.27 0.27 256 1000 0.30 0.30 0.30 512 1000 0.38 0.38 0.38 1024 1000 0.40 0.40 0.40 2048 1000 0.56 0.56 0.56 4096 1000 0.35 0.35 0.35 8192 1000 0.37 0.37 0.37 16384 1000 1.33 1.33 1.33 32768 1000 1.37 1.37 1.37 65536 640 2.41 2.41 2.41 131072 320 3.85 3.85 3.85 262144 160 9.30 9.30 9.30 524288 80 20.67 20.67 20.67 1048576 40 43.59 43.59 43.59 2097152 20 228.00 228.00 228.00 4194304 10 169.12 169.12 169.12 #---------------------------------------------------------------- # Benchmarking Reduce_scatter_block # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 4 1000 0.05 0.05 0.05 8 1000 0.05 0.05 0.05 16 1000 0.05 0.05 0.05 32 1000 0.04 0.04 0.04 64 1000 0.04 0.04 0.04 128 1000 0.05 0.05 0.05 256 1000 0.08 0.08 0.08 512 1000 0.05 0.05 0.05 1024 1000 0.08 0.08 0.08 2048 1000 0.08 0.08 0.08 4096 1000 0.09 0.09 0.09 8192 1000 0.13 0.13 0.13 16384 1000 0.32 0.32 0.32 32768 1000 0.84 0.84 0.84 65536 640 1.78 1.78 1.78 131072 320 3.40 3.40 3.40 262144 160 9.05 9.05 9.05 524288 80 18.47 18.47 18.47 1048576 40 38.27 38.27 38.27 2097152 20 73.57 73.57 73.57 4194304 10 275.88 275.88 275.88 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 1 1000 0.12 0.12 0.12 2 1000 0.14 0.14 0.14 4 1000 0.14 0.14 0.14 8 1000 0.14 0.14 0.14 16 1000 0.13 0.13 0.13 32 1000 0.21 0.21 0.21 64 1000 0.12 0.12 0.12 128 1000 0.13 0.13 0.13 256 1000 0.14 0.14 0.14 512 1000 0.14 0.14 0.14 1024 1000 0.14 0.14 0.14 2048 1000 0.14 0.14 0.14 4096 1000 0.29 0.29 0.29 8192 1000 0.21 0.21 0.21 16384 1000 0.50 0.50 0.50 32768 1000 0.96 0.96 0.96 65536 640 1.59 1.59 1.59 131072 320 3.84 3.84 3.84 262144 160 9.02 9.02 9.02 524288 80 18.25 18.25 18.25 1048576 40 39.69 39.69 39.69 2097152 20 76.82 76.82 76.82 4194304 10 165.18 165.18 165.18 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.11 0.11 0.11 1 1000 0.20 0.20 0.20 2 1000 0.23 0.23 0.23 4 1000 0.22 0.22 0.22 8 1000 0.22 0.22 0.22 16 1000 0.13 0.13 0.13 32 1000 0.21 0.21 0.21 64 1000 0.13 0.13 0.13 128 1000 0.13 0.13 0.13 256 1000 0.13 0.13 0.13 512 1000 0.17 0.17 0.17 1024 1000 0.17 0.17 0.17 2048 1000 0.34 0.34 0.34 4096 1000 0.23 0.23 0.23 8192 1000 0.23 0.23 0.23 16384 1000 1.19 1.19 1.19 32768 1000 1.24 1.24 1.24 65536 640 1.99 1.99 1.99 131072 320 3.20 3.20 3.20 262144 160 10.71 10.71 10.71 524288 80 22.83 22.83 22.83 1048576 40 35.68 35.68 35.68 2097152 20 82.05 82.05 82.05 4194304 10 349.72 349.72 349.72 #---------------------------------------------------------------- # Benchmarking Gather # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 1 1000 0.12 0.12 0.12 2 1000 0.13 0.13 0.13 4 1000 0.13 0.13 0.13 8 1000 0.14 0.14 0.14 16 1000 0.27 0.27 0.27 32 1000 0.14 0.14 0.14 64 1000 0.13 0.13 0.13 128 1000 0.23 0.23 0.23 256 1000 0.15 0.15 0.15 512 1000 0.14 0.14 0.14 1024 1000 0.16 0.16 0.16 2048 1000 0.15 0.15 0.15 4096 1000 0.19 0.19 0.19 8192 1000 0.23 0.23 0.23 16384 1000 0.96 0.96 0.96 32768 1000 1.16 1.16 1.16 65536 640 2.42 2.42 2.42 131072 320 3.82 3.82 3.82 262144 160 9.22 9.22 9.22 524288 80 17.13 17.13 17.13 1048576 40 44.85 44.85 44.85 2097152 20 71.23 71.23 71.23 4194304 10 165.99 165.99 165.99 #---------------------------------------------------------------- # Benchmarking Gatherv # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 1 1000 0.33 0.33 0.33 2 1000 0.40 0.40 0.40 4 1000 0.39 0.39 0.39 8 1000 0.38 0.38 0.38 16 1000 0.37 0.37 0.37 32 1000 0.54 0.54 0.54 64 1000 0.59 0.59 0.59 128 1000 0.41 0.41 0.41 256 1000 0.28 0.28 0.28 512 1000 0.30 0.30 0.30 1024 1000 0.35 0.35 0.35 2048 1000 0.38 0.38 0.38 4096 1000 0.38 0.38 0.38 8192 1000 0.43 0.43 0.43 16384 1000 1.20 1.20 1.20 32768 1000 1.28 1.28 1.28 65536 640 1.77 1.77 1.77 131072 320 3.53 3.53 3.53 262144 160 12.94 12.94 12.94 524288 80 20.07 20.07 20.07 1048576 40 51.17 51.17 51.17 2097152 20 89.18 89.18 89.18 4194304 10 172.64 172.64 172.64 #---------------------------------------------------------------- # Benchmarking Scatter # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.09 0.09 1 1000 0.25 0.25 0.25 2 1000 0.14 0.14 0.14 4 1000 0.14 0.14 0.14 8 1000 0.13 0.13 0.13 16 1000 0.11 0.11 0.11 32 1000 0.12 0.12 0.12 64 1000 0.13 0.13 0.13 128 1000 0.14 0.14 0.14 256 1000 0.16 0.16 0.16 512 1000 0.18 0.18 0.18 1024 1000 0.17 0.17 0.17 2048 1000 0.19 0.19 0.19 4096 1000 0.21 0.21 0.21 8192 1000 0.37 0.37 0.37 16384 1000 0.83 0.83 0.83 32768 1000 1.21 1.21 1.21 65536 640 1.98 1.98 1.98 131072 320 4.45 4.45 4.45 262144 160 9.23 9.23 9.23 524288 80 20.55 20.55 20.55 1048576 40 42.97 42.97 42.97 2097152 20 73.87 73.87 73.87 4194304 10 434.79 434.79 434.79 #---------------------------------------------------------------- # Benchmarking Scatterv # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.22 0.22 0.22 1 1000 0.23 0.23 0.23 2 1000 0.21 0.21 0.21 4 1000 0.23 0.23 0.23 8 1000 0.21 0.21 0.21 16 1000 0.20 0.20 0.20 32 1000 0.21 0.21 0.21 64 1000 0.25 0.25 0.25 128 1000 0.25 0.25 0.25 256 1000 0.28 0.28 0.28 512 1000 0.28 0.28 0.28 1024 1000 0.31 0.31 0.31 2048 1000 0.31 0.31 0.31 4096 1000 0.30 0.30 0.30 8192 1000 0.31 0.31 0.31 16384 1000 0.72 0.72 0.72 32768 1000 1.17 1.17 1.17 65536 640 2.86 2.86 2.86 131072 320 3.69 3.69 3.69 262144 160 9.15 9.15 9.15 524288 80 17.42 17.42 17.42 1048576 40 42.06 42.06 42.06 2097152 20 252.79 252.79 252.79 4194304 10 305.71 305.71 305.71 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 1 1000 0.12 0.12 0.12 2 1000 0.14 0.14 0.14 4 1000 0.13 0.13 0.13 8 1000 0.14 0.14 0.14 16 1000 0.12 0.12 0.12 32 1000 0.12 0.12 0.12 64 1000 0.12 0.12 0.12 128 1000 0.12 0.12 0.12 256 1000 0.12 0.12 0.12 512 1000 0.12 0.12 0.12 1024 1000 0.17 0.17 0.17 2048 1000 0.16 0.16 0.16 4096 1000 0.16 0.16 0.16 8192 1000 0.24 0.24 0.24 16384 1000 0.53 0.53 0.53 32768 1000 0.96 0.96 0.96 65536 640 1.97 1.97 1.97 131072 320 3.66 3.66 3.66 262144 160 10.60 10.60 10.60 524288 80 18.46 18.46 18.46 1048576 40 42.02 42.02 42.02 2097152 20 78.82 78.82 78.82 4194304 10 227.34 227.34 227.34 #---------------------------------------------------------------- # Benchmarking Alltoallv # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.55 0.55 0.55 1 1000 27.76 27.76 27.76 2 1000 28.12 28.12 28.12 4 1000 26.65 26.65 26.65 8 1000 26.33 26.33 26.33 16 1000 25.94 25.94 25.94 32 1000 27.06 27.06 27.06 64 1000 31.44 31.44 31.44 128 1000 30.88 30.88 30.88 256 1000 44.04 44.04 44.04 512 1000 44.02 44.02 44.02 1024 1000 43.92 43.92 43.92 2048 1000 59.99 59.99 59.99 4096 1000 50.73 50.73 50.73 8192 1000 47.67 47.67 47.67 16384 1000 59.84 59.84 59.84 32768 1000 60.35 60.35 60.35 65536 640 80.87 80.87 80.87 131072 320 94.27 94.27 94.27 262144 160 234.08 234.08 234.08 524288 80 578.39 578.39 578.39 1048576 40 1001.11 1001.11 1001.11 2097152 20 1431.11 1431.11 1431.11 4194304 10 3068.76 3068.76 3068.76 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 1 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.06 0.06 0.06 1 1000 0.06 0.06 0.06 2 1000 0.04 0.04 0.04 4 1000 0.06 0.06 0.06 8 1000 0.05 0.05 0.05 16 1000 0.07 0.07 0.07 32 1000 0.06 0.06 0.06 64 1000 0.06 0.06 0.06 128 1000 0.05 0.05 0.05 256 1000 0.05 0.05 0.05 512 1000 0.06 0.06 0.06 1024 1000 0.06 0.06 0.06 2048 1000 0.05 0.05 0.05 4096 1000 0.04 0.04 0.04 8192 1000 0.05 0.05 0.05 16384 1000 0.04 0.04 0.04 32768 1000 0.04 0.04 0.04 65536 640 0.04 0.04 0.04 131072 320 0.04 0.04 0.04 262144 160 0.04 0.04 0.04 524288 80 0.04 0.04 0.04 1048576 40 0.03 0.03 0.03 2097152 20 0.03 0.03 0.03 4194304 10 0.04 0.04 0.04 #--------------------------------------------------- # Benchmarking Barrier # #processes = 1 #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 0.02 0.02 0.02 # All processes entering MPI_Finalize C:\Program Files (x86)\Intel\oneAPI\mpi\latest\benchmarks\imb\WINDOWS\IMB-MPI1_VS_2017\x64\Debug> mpiexec --version Intel(R) MPI Library for Windows* OS, Version 2021.9 Build 20230308 Copyright 2003-2023, Intel Corporation.