# NVIDIA GeForce RTX 4070, 46 SMs, sm_89, iters=20000 reps=5
mode       best TF/s   all runs
f16/f16        132.6 123.5/132.6/132.6/132.6/132.6
f16/f32         66.3 66.3/66.3/66.3/66.3/66.3
bf16/f32        66.3 66.3/66.3/66.3/66.3/66.3
s8/s32         265.1 265.1/264.4/264.3/264.3/264.3
dp4a            65.8 65.7/65.7/65.7/65.8/65.8
ffma            31.7 31.7/31.7/31.7/31.7/31.7
