device: NVIDIA GB200
shape: experts=8, tokens/expert=4096, M=32768, K=8192, N=4096
dtype: torch.bfloat16
torch: 2.12.0a0+5aff3928d8.nv26.05
transformer_engine: 2.15.0+42b84005
nvidia-cudnn-frontend: 1.23.0
nvidia-cutlass-dsl: 4.4.1

summary:
activation   cudnn_ms      te_ms   te/cudnn
swiglu          1.550      1.934      1.25x
dswiglu         0.870      1.734      1.99x
srelu           0.739      1.041      1.41x
dsrelu          0.781      1.341      1.72x
geglu           1.544      1.890      1.22x
dgeglu          0.889      1.820      2.05x