mirror of
https://github.com/paboyle/Grid.git
synced 2026-06-04 11:14:38 +01:00
42cd9eda71
and also some staggered hdcg type work
92 lines
2.1 KiB
CSV
92 lines
2.1 KiB
CSV
Per node summary table
|
|
|
|
L , Wilson, DWF4, Staggered, NaiveStag
|
|
|
|
8 , 90, 933, 38, 23
|
|
12 , 403, 1688, 178, 113
|
|
16 , 188, 1647, 449, 295
|
|
24 , 947, 1574, 674, 553
|
|
32 , 931, 1371, 718, 643
|
|
|
|
Memory Bandwidth
|
|
|
|
Bytes, GB/s per node
|
|
786432, 40.271620
|
|
12582912, 433.611792
|
|
63700992, 905.374321
|
|
201326592, 1114.979152
|
|
491520000, 1180.241898
|
|
|
|
|
|
Communications
|
|
|
|
Packet bytes, direction, GB/s per node
|
|
|
|
|
|
GEMM
|
|
|
|
M, N, K, BATCH, GF/s per rank fp64
|
|
16, 8, 16, 4096, 693.316363
|
|
16, 12, 16, 4096, 657.277058
|
|
16, 16, 16, 4096, 711.992616
|
|
32, 8, 32, 4096, 821.084324
|
|
32, 12, 32, 4096, 1279.852719
|
|
32, 16, 32, 4096, 2647.096674
|
|
64, 8, 64, 4096, 2630.192325
|
|
64, 12, 64, 4096, 3338.071321
|
|
64, 16, 64, 4096, 3950.899281
|
|
16, 8, 256, 4096, 1638.362501
|
|
16, 12, 256, 4096, 2377.502234
|
|
16, 16, 256, 4096, 3048.328833
|
|
32, 8, 256, 4096, 2917.384276
|
|
32, 12, 256, 4096, 4103.085151
|
|
32, 16, 256, 4096, 5102.971860
|
|
64, 8, 256, 4096, 3222.258206
|
|
64, 12, 256, 4096, 4619.456391
|
|
64, 16, 256, 4096, 5847.916650
|
|
8, 256, 16, 4096, 1728.073337
|
|
12, 256, 16, 4096, 2356.653970
|
|
16, 256, 16, 4096, 2676.876038
|
|
8, 256, 32, 4096, 2611.531990
|
|
12, 256, 32, 4096, 3451.573106
|
|
16, 256, 32, 4096, 3966.915301
|
|
8, 256, 64, 4096, 3436.248737
|
|
12, 256, 64, 4096, 4539.497945
|
|
16, 256, 64, 4096, 5307.992323
|
|
|
|
|
|
|
|
GEMM
|
|
|
|
M, N, K, BATCH, GF/s per rank fp32
|
|
16, 8, 16, 4096, 499.017445
|
|
16, 12, 16, 4096, 731.543385
|
|
16, 16, 16, 4096, 958.800786
|
|
32, 8, 32, 4096, 1549.813550
|
|
32, 12, 32, 4096, 2147.907502
|
|
32, 16, 32, 4096, 2601.698596
|
|
64, 8, 64, 4096, 3785.446233
|
|
64, 12, 64, 4096, 5116.694843
|
|
64, 16, 64, 4096, 6109.345016
|
|
16, 8, 256, 4096, 1206.627737
|
|
16, 12, 256, 4096, 1809.699599
|
|
16, 16, 256, 4096, 2412.014053
|
|
32, 8, 256, 4096, 2406.114488
|
|
32, 12, 256, 4096, 3605.531907
|
|
32, 16, 256, 4096, 4798.444037
|
|
64, 8, 256, 4096, 4688.711196
|
|
64, 12, 256, 4096, 6990.696301
|
|
64, 16, 256, 4096, 9214.749925
|
|
8, 256, 16, 4096, 2596.307289
|
|
12, 256, 16, 4096, 3439.892562
|
|
16, 256, 16, 4096, 3907.201036
|
|
8, 256, 32, 4096, 3012.752067
|
|
12, 256, 32, 4096, 3904.217583
|
|
16, 256, 32, 4096, 4599.047092
|
|
8, 256, 64, 4096, 3721.999042
|
|
12, 256, 64, 4096, 5098.573927
|
|
16, 256, 64, 4096, 6159.080872
|
|
|
|
|
|
|