54 строки
4.6 KiB
Plaintext
54 строки
4.6 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 112424 on localhost device 0 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 1 Pid 112424 on localhost device 1 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 2 Pid 112424 on localhost device 2 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 3 Pid 112424 on localhost device 3 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 4 Pid 112424 on localhost device 4 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 5 Pid 112424 on localhost device 5 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 6 Pid 112424 on localhost device 6 [0x00] A100-SXM4-40GB
|
||
|
|
# Rank 7 Pid 112424 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 35.20 0.00 0.00 N/A 34.05 0.00 0.00 N/A
|
||
|
|
0 0 float sum 34.18 0.00 0.00 N/A 33.50 0.00 0.00 N/A
|
||
|
|
4 1 float sum 34.73 0.00 0.00 N/A 35.30 0.00 0.00 N/A
|
||
|
|
8 2 float sum 34.66 0.00 0.00 N/A 34.84 0.00 0.00 N/A
|
||
|
|
16 4 float sum 35.00 0.00 0.00 N/A 35.61 0.00 0.00 N/A
|
||
|
|
32 8 float sum 35.60 0.00 0.00 N/A 35.27 0.00 0.00 N/A
|
||
|
|
64 16 float sum 34.83 0.00 0.00 N/A 34.61 0.00 0.00 N/A
|
||
|
|
128 32 float sum 34.53 0.00 0.01 N/A 43.78 0.00 0.01 N/A
|
||
|
|
256 64 float sum 34.56 0.01 0.01 N/A 34.95 0.01 0.01 N/A
|
||
|
|
512 128 float sum 34.94 0.01 0.03 N/A 35.20 0.01 0.03 N/A
|
||
|
|
1024 256 float sum 36.07 0.03 0.05 N/A 35.77 0.03 0.05 N/A
|
||
|
|
2048 512 float sum 35.42 0.06 0.10 N/A 35.89 0.06 0.10 N/A
|
||
|
|
4096 1024 float sum 35.92 0.11 0.20 N/A 36.11 0.11 0.20 N/A
|
||
|
|
8192 2048 float sum 35.91 0.23 0.40 N/A 36.07 0.23 0.40 N/A
|
||
|
|
16384 4096 float sum 36.18 0.45 0.79 N/A 35.87 0.46 0.80 N/A
|
||
|
|
32768 8192 float sum 36.65 0.89 1.56 N/A 35.73 0.92 1.60 N/A
|
||
|
|
65536 16384 float sum 37.82 1.73 3.03 N/A 37.25 1.76 3.08 N/A
|
||
|
|
131072 32768 float sum 41.19 3.18 5.57 N/A 41.11 3.19 5.58 N/A
|
||
|
|
262144 65536 float sum 47.53 5.52 9.65 N/A 47.94 5.47 9.57 N/A
|
||
|
|
524288 131072 float sum 60.32 8.69 15.21 N/A 60.52 8.66 15.16 N/A
|
||
|
|
1048576 262144 float sum 74.78 14.02 24.54 N/A 76.17 13.77 24.09 N/A
|
||
|
|
2097152 524288 float sum 93.48 22.43 39.26 N/A 96.10 21.82 38.19 N/A
|
||
|
|
4194304 1048576 float sum 112.0 37.44 65.52 N/A 110.2 38.06 66.60 N/A
|
||
|
|
8388608 2097152 float sum 162.0 51.79 90.63 N/A 160.0 52.44 91.77 N/A
|
||
|
|
16777216 4194304 float sum 226.0 74.23 129.90 N/A 225.0 74.57 130.49 N/A
|
||
|
|
33554432 8388608 float sum 374.3 89.65 156.89 N/A 372.8 90.00 157.50 N/A
|
||
|
|
67108864 16777216 float sum 584.5 114.81 200.91 N/A 581.9 115.33 201.82 N/A
|
||
|
|
134217728 33554432 float sum 1162.2 115.49 202.11 N/A 1162.5 115.46 202.05 N/A
|
||
|
|
268435456 67108864 float sum 2112.2 127.09 222.40 N/A 2111.8 127.11 222.45 N/A
|
||
|
|
536870912 134217728 float sum 4200.3 127.82 223.68 N/A 4184.0 128.32 224.55 N/A
|
||
|
|
1073741824 268435456 float sum 8159.5 131.59 230.29 N/A 8176.5 131.32 229.81 N/A
|
||
|
|
2147483648 536870912 float sum 16215 132.44 231.76 N/A 16203 132.53 231.93 N/A
|
||
|
|
4294967296 1073741824 float sum 32070 133.92 234.37 N/A 32052 134.00 234.50 N/A
|
||
|
|
8589934592 2147483648 float sum 63896 134.44 235.26 N/A 63959 134.30 235.03 N/A
|
||
|
|
# Out of bounds values : 0 OK
|
||
|
|
# Avg bus bandwidth : 68.4048
|
||
|
|
#
|