# nThread 1 nGpus 8 minBytes 1 maxBytes 8589934592 step: 2(factor) warmup iters: 5 iters: 20 validation: 0 # # Using devices # Rank 0 Pid 112580 on localhost device 0 [0x00] A100-SXM4-40GB # Rank 1 Pid 112580 on localhost device 1 [0x00] A100-SXM4-40GB # Rank 2 Pid 112580 on localhost device 2 [0x00] A100-SXM4-40GB # Rank 3 Pid 112580 on localhost device 3 [0x00] A100-SXM4-40GB # Rank 4 Pid 112580 on localhost device 4 [0x00] A100-SXM4-40GB # Rank 5 Pid 112580 on localhost device 5 [0x00] A100-SXM4-40GB # Rank 6 Pid 112580 on localhost device 6 [0x00] A100-SXM4-40GB # Rank 7 Pid 112580 on localhost device 7 [0x00] A100-SXM4-40GB # # out-of-place in-place # size count type redop time algbw busbw error time algbw busbw error # (B) (elements) (us) (GB/s) (GB/s) (us) (GB/s) (GB/s) hostname:3442:3442 [0] NCCL INFO Launch mode Parallel 0 0 float sum 34.88 0.00 0.00 N/A 33.65 0.00 0.00 N/A 0 0 float sum 33.54 0.00 0.00 N/A 33.72 0.00 0.00 N/A 0 0 float sum 33.45 0.00 0.00 N/A 33.44 0.00 0.00 N/A 0 0 float sum 34.07 0.00 0.00 N/A 33.44 0.00 0.00 N/A 0 0 float sum 33.55 0.00 0.00 N/A 33.43 0.00 0.00 N/A 32 1 float sum 35.06 0.00 0.00 N/A 35.14 0.00 0.00 N/A 64 2 float sum 34.82 0.00 0.00 N/A 34.76 0.00 0.00 N/A 128 4 float sum 34.38 0.00 0.00 N/A 34.52 0.00 0.00 N/A 256 8 float sum 34.75 0.01 0.01 N/A 34.32 0.01 0.01 N/A 512 16 float sum 34.71 0.01 0.01 N/A 35.43 0.01 0.01 N/A 1024 32 float sum 35.16 0.03 0.03 N/A 34.75 0.03 0.03 N/A 2048 64 float sum 35.43 0.06 0.05 N/A 35.29 0.06 0.05 N/A 4096 128 float sum 35.49 0.12 0.10 N/A 35.17 0.12 0.10 N/A 8192 256 float sum 35.18 0.23 0.20 N/A 35.77 0.23 0.20 N/A 16384 512 float sum 35.27 0.46 0.41 N/A 35.49 0.46 0.40 N/A 32768 1024 float sum 35.00 0.94 0.82 N/A 35.09 0.93 0.82 N/A 65536 2048 float sum 36.78 1.78 1.56 N/A 36.92 1.77 1.55 N/A 131072 4096 float sum 40.71 3.22 2.82 N/A 39.78 3.29 2.88 N/A 262144 8192 float sum 48.12 5.45 4.77 N/A 46.65 5.62 4.92 N/A 524288 16384 float sum 59.81 8.77 7.67 N/A 58.88 8.90 7.79 N/A 1048576 32768 float sum 72.37 14.49 12.68 N/A 74.95 13.99 12.24 N/A 2097152 65536 float sum 80.64 26.01 22.76 N/A 79.62 26.34 23.05 N/A 4194304 131072 float sum 108.9 38.53 33.72 N/A 109.3 38.37 33.57 N/A 8388608 262144 float sum 147.3 56.96 49.84 N/A 166.8 50.28 44.00 N/A 16777216 524288 float sum 152.4 110.11 96.34 N/A 152.8 109.82 96.09 N/A 33554432 1048576 float sum 240.5 139.50 122.06 N/A 240.8 139.33 121.91 N/A 67108864 2097152 float sum 356.1 188.45 164.89 N/A 352.1 190.57 166.75 N/A 134217728 4194304 float sum 618.1 217.15 190.01 N/A 615.2 218.18 190.90 N/A 268435456 8388608 float sum 1108.7 242.11 211.84 N/A 1112.6 241.27 211.11 N/A 536870912 16777216 float sum 2169.0 247.52 216.58 N/A 2181.8 246.07 215.31 N/A 1073741824 33554432 float sum 4203.0 255.47 223.54 N/A 4206.3 255.27 223.36 N/A 2147483648 67108864 float sum 8356.9 256.97 224.85 N/A 8323.5 258.00 225.75 N/A 4294967296 134217728 float sum 16400 261.89 229.15 N/A 16402 261.86 229.13 N/A 8589934592 268435456 float sum 32464 264.60 231.52 N/A 32502 264.29 231.25 N/A # Out of bounds values : 0 OK # Avg bus bandwidth : 60.168 #