Function lattice_best_bf16_bench 

pub fn lattice_best_bf16_bench(
    m: usize,
    k: usize,
    n: usize,
    sm_arch: u32,
    gpu: &GpuLimits,
) -> String

The knob lattice’s own best bf16 rung for a shape, as a runnable benchmark: the kernel select_hmma_kernel picks (cp.async when its tile divides the shape and fits, else the basic WMMA kernel). This is the backend-native baseline a lowering measures itself against — the fair opponent is the best thing this lattice can already emit, not its worst.