# NVIDIA GeForce RTX 4090, 128 SMs, sm_89, iters=20000 reps=5
mode       best TF/s   all runs
f16/f16        330.8 302.7/325.0/330.8/330.8/330.8
f16/f32        164.9 164.8/164.9/164.9/164.9/164.9
bf16/f32       164.8 164.8/164.8/164.8/164.8/164.8
s8/s32         659.4 659.4/659.4/659.4/659.4/659.4
dp4a           164.0 164.0/164.0/164.0/163.5/163.1
ffma            78.5 78.5/78.5/78.5/78.5/78.5
