Function cmp_u32_to 

pub fn cmp_u32_to(
    lhs: &[u32],
    rhs: &[u32],
    mask: Option<&Bitmask>,
    op: ComparisonOperator,
    output: &mut Bitmask,
) -> Result<(), KernelError>

Zero-allocation variant: writes directly to caller’s output buffer.

Type-specific SIMD-accelerated comparison function with vectorised operations. Panics if output capacity < lhs.len().