# NVIDIA GeForce RTX 4060 Ti, 34 SMs, sm_89, iters=20000 reps=5
mode       best TF/s   all runs
f16/f16         92.9 92.9/92.8/92.7/92.7/92.7
f16/f32         46.4 46.4/46.3/46.4/46.4/46.4
bf16/f32        46.4 46.4/46.4/46.4/46.4/46.4
s8/s32         185.4 185.4/185.3/185.3/185.2/184.5
dp4a            46.0 45.9/46.0/45.9/45.9/45.9
ffma            22.2 22.2/22.1/22.2/22.2/22.2
