# NVIDIA GeForce RTX 4070 SUPER, 56 SMs, sm_89, iters=20000 reps=5
mode       best TF/s   all runs
f16/f16        153.4 143.4/149.0/153.4/153.4/153.4
f16/f32         76.7 76.7/76.7/76.7/76.7/76.7
bf16/f32        76.7 76.7/76.7/76.7/76.7/76.7
s8/s32         306.9 306.9/306.9/306.9/306.9/306.9
dp4a            76.4 76.4/76.4/76.4/76.4/76.4
ffma            36.6 36.6/36.6/36.6/36.6/36.6
