54 строки
4.3 KiB
Plaintext
54 строки
4.3 KiB
Plaintext
# nThread 1 nGpus 8 minBytes 1 maxBytes 8589934592 step: 2(factor) warmup iters: 5 iters: 20 validation: 0
|
|
#
|
|
# Using devices
|
|
# Rank 0 Pid 112372 on localhost device 0 [0x00] A100-SXM4-40GB
|
|
# Rank 1 Pid 112372 on localhost device 1 [0x00] A100-SXM4-40GB
|
|
# Rank 2 Pid 112372 on localhost device 2 [0x00] A100-SXM4-40GB
|
|
# Rank 3 Pid 112372 on localhost device 3 [0x00] A100-SXM4-40GB
|
|
# Rank 4 Pid 112372 on localhost device 4 [0x00] A100-SXM4-40GB
|
|
# Rank 5 Pid 112372 on localhost device 5 [0x00] A100-SXM4-40GB
|
|
# Rank 6 Pid 112372 on localhost device 6 [0x00] A100-SXM4-40GB
|
|
# Rank 7 Pid 112372 on localhost device 7 [0x00] A100-SXM4-40GB
|
|
#
|
|
# out-of-place in-place
|
|
# size count type 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 34.27 0.00 0.00 N/A 33.57 0.00 0.00 N/A
|
|
0 0 float 33.41 0.00 0.00 N/A 33.62 0.00 0.00 N/A
|
|
0 0 float 33.94 0.00 0.00 N/A 33.48 0.00 0.00 N/A
|
|
0 0 float 33.83 0.00 0.00 N/A 33.62 0.00 0.00 N/A
|
|
0 0 float 33.82 0.00 0.00 N/A 33.57 0.00 0.00 N/A
|
|
32 1 float 35.03 0.00 0.00 N/A 34.15 0.00 0.00 N/A
|
|
64 2 float 34.36 0.00 0.00 N/A 33.83 0.00 0.00 N/A
|
|
128 4 float 33.94 0.00 0.00 N/A 35.22 0.00 0.00 N/A
|
|
256 8 float 34.44 0.01 0.01 N/A 34.82 0.01 0.01 N/A
|
|
512 16 float 34.84 0.01 0.01 N/A 34.76 0.01 0.01 N/A
|
|
1024 32 float 35.38 0.03 0.03 N/A 34.53 0.03 0.03 N/A
|
|
2048 64 float 34.67 0.06 0.05 N/A 34.91 0.06 0.05 N/A
|
|
4096 128 float 34.62 0.12 0.10 N/A 34.81 0.12 0.10 N/A
|
|
8192 256 float 34.76 0.24 0.21 N/A 35.03 0.23 0.20 N/A
|
|
16384 512 float 34.80 0.47 0.41 N/A 34.90 0.47 0.41 N/A
|
|
32768 1024 float 34.54 0.95 0.83 N/A 35.23 0.93 0.81 N/A
|
|
65536 2048 float 36.34 1.80 1.58 N/A 36.01 1.82 1.59 N/A
|
|
131072 4096 float 40.18 3.26 2.85 N/A 39.43 3.32 2.91 N/A
|
|
262144 8192 float 46.45 5.64 4.94 N/A 46.27 5.67 4.96 N/A
|
|
524288 16384 float 58.48 8.96 7.84 N/A 60.40 8.68 7.60 N/A
|
|
1048576 32768 float 72.95 14.37 12.58 N/A 73.07 14.35 12.56 N/A
|
|
2097152 65536 float 77.28 27.14 23.75 N/A 75.84 27.65 24.20 N/A
|
|
4194304 131072 float 100.7 41.64 36.43 N/A 99.56 42.13 36.86 N/A
|
|
8388608 262144 float 123.5 67.94 59.44 N/A 120.7 69.51 60.82 N/A
|
|
16777216 524288 float 167.7 100.03 87.52 N/A 164.6 101.94 89.20 N/A
|
|
33554432 1048576 float 265.8 126.24 110.46 N/A 257.5 130.33 114.04 N/A
|
|
67108864 2097152 float 379.7 176.74 154.65 N/A 367.6 182.57 159.75 N/A
|
|
134217728 4194304 float 698.6 192.13 168.12 N/A 657.3 204.20 178.67 N/A
|
|
268435456 8388608 float 1192.2 225.16 197.01 N/A 1136.0 236.29 206.76 N/A
|
|
536870912 16777216 float 2304.1 233.01 203.88 N/A 2227.9 240.98 210.85 N/A
|
|
1073741824 33554432 float 4413.4 243.29 212.88 N/A 4258.8 252.12 220.61 N/A
|
|
2147483648 67108864 float 8658.8 248.01 217.01 N/A 8389.4 255.98 223.98 N/A
|
|
4294967296 134217728 float 17016 252.40 220.85 N/A 16474 260.71 228.12 N/A
|
|
8589934592 268435456 float 33646 255.31 223.39 N/A 32669 262.94 230.07 N/A
|
|
# Out of bounds values : 0 OK
|
|
# Avg bus bandwidth : 58.2651
|
|
#
|