warpReduceMin

[lns]

/// Finds the minimum `val` across the warp
template <typename T>
__device__ __forceinline__ T warpReduceMin(T val) {
  return warpReduce<T, Max<T> >(val, Min<T>());
}

should be

  return warpReduce<T, Min<T> >(val, Min<T>());

right?