Address reviewer comments

Author: winner245

libcxx/docs/ReleaseNotes/21.rst

@@ -76,6 +76,10 @@ Improvements and New Features
 - The ``bitset::to_string`` function has been optimized, resulting in a performance improvement of up to 8.3x for bitsets
   with uniformly distributed zeros and ones, and up to 13.5x and 16.1x for sparse and dense bitsets, respectively.
 
+- The ``std::distance`` and ``std::ranges::distance`` algorithms have been optimized for segmented iterators (e.g.,
+  ``std::join_view`` iterators), reducing the complexity from ``O(n)`` to ``O(n / segment_size)``. Benchmarks show
+  performance improvements of over 1600x in favorable cases with large segment sizes (e.g., 1024).
+
 Deprecations and Removals
 -------------------------
 

libcxx/include/__iterator/distance.h

@@ -33,54 +33,35 @@ _LIBCPP_PUSH_MACROS
 
 _LIBCPP_BEGIN_NAMESPACE_STD
 
-#if _LIBCPP_STD_VER >= 20
-template <class _Iter>
-using __iter_distance_t _LIBCPP_NODEBUG = std::iter_difference_t<_Iter>;
-#else
-template <class _Iter>
-using __iter_distance_t _LIBCPP_NODEBUG = typename iterator_traits<_Iter>::difference_type;
-#endif
-
 template <class _InputIter, class _Sent>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 __iter_distance_t<_InputIter>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 typename iterator_traits<_InputIter>::difference_type
 __distance(_InputIter __first, _Sent __last) {
-  __iter_distance_t<_InputIter> __r(0);
+  typename iterator_traits<_InputIter>::difference_type __r(0);
   for (; __first != __last; ++__first)
     ++__r;
   return __r;
 }
 
 template <class _RandIter, __enable_if_t<__has_random_access_iterator_category<_RandIter>::value, int> = 0>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 __iter_distance_t<_RandIter>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 typename iterator_traits<_RandIter>::difference_type
 __distance(_RandIter __first, _RandIter __last) {
   return __last - __first;
 }
 
-template <class _SegmentedIter, class _Difference>
-struct __segment_distance {
-  using _Traits _LIBCPP_NODEBUG = __segmented_iterator_traits<_SegmentedIter>;
-
-  _Difference& __r_;
-
-  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 explicit __segment_distance(_Difference& __r) : __r_(__r) {}
-
-  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 void
-  operator()(typename _Traits::__local_iterator __lfirst, typename _Traits::__local_iterator __llast) {
-    __r_ += std::__distance(__lfirst, __llast);
-  }
-};
-
+#if _LIBCPP_STD_VER >= 20
 template <class _SegmentedIter,
           __enable_if_t<!__has_random_access_iterator_category<_SegmentedIter>::value &&
                             __is_segmented_iterator<_SegmentedIter>::value,
                         int> = 0>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 __iter_distance_t<_SegmentedIter>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 typename iterator_traits<_SegmentedIter>::difference_type
 __distance(_SegmentedIter __first, _SegmentedIter __last) {
-  using __difference_type = __iter_distance_t<_SegmentedIter>;
-  __difference_type __r(0);
-  std::__for_each_segment(__first, __last, std::__segment_distance<_SegmentedIter, __difference_type>(__r));
+  typename iterator_traits<_SegmentedIter>::difference_type __r(0);
+  std::__for_each_segment(__first, __last, [&__r](auto __lfirst, auto __llast) {
+    __r += std::__distance(__lfirst, __llast);
+  });
   return __r;
 }
+#endif // _LIBCPP_STD_VER >= 20
 
 template <class _InputIter>
 inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX17 typename iterator_traits<_InputIter>::difference_type
@@ -97,7 +78,7 @@ struct __distance {
   template <class _Ip, sentinel_for<_Ip> _Sp>
     requires(!sized_sentinel_for<_Sp, _Ip>)
   _LIBCPP_HIDE_FROM_ABI constexpr iter_difference_t<_Ip> operator()(_Ip __first, _Sp __last) const {
-    return std::__distance(std::move(__first), std::move(__last));
+    return static_cast<iter_difference_t<_Ip>>(std::__distance(std::move(__first), std::move(__last)));
   }
 
   template <class _Ip, sized_sentinel_for<decay_t<_Ip>> _Sp>

libcxx/test/benchmarks/iterators/distance.bench.cpp

@@ -46,10 +46,6 @@ int main(int argc, char** argv) {
           ->Arg(1024)
           ->Arg(4096)
           ->Arg(8192);
-      // ->Arg(1 << 14)
-      // ->Arg(1 << 16)
-      // ->Arg(1 << 18)
-      // ->Arg(1 << 20);
     };
     bm.operator()<std::vector<std::vector<int>>>("std::distance(join_view(vector<vector<int>>))", std_distance, 256);
     bm.operator()<std::deque<std::deque<int>>>("std::distance(join_view(deque<deque<int>>))", std_distance, 256);