Address ldionne's comments

Author: winner245

libcxx/docs/ReleaseNotes/21.rst

@@ -70,16 +70,13 @@ Improvements and New Features
 - The segmented iterator optimization for ``std::for_each`` has been backported to C++11. Previously it was only available
   in C++23 and later.
 
-- The ``std::for_each_n`` algorithm has been optimized for segmented iterators, resulting in a performance improvement of
-  up to 17.7x for ``std::deque<short>`` iterators, and up to 13.9x for ``std::join_view<vector<vector<short>>>`` iterators.
+- The ``std::for_each_n``, ``std::ranges::for_each`` and ``std::ranges::for_each_n`` algorithms have been optimized for
+  segmented iterators, resulting in a performance improvement of up to 17.7x for ``std::deque<short>`` iterators, and up
+  to 13.9x for ``std::join_view<vector<vector<short>>>`` iterators.
 
 - 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::ranges::for_each`` and ``std::ranges::for_each_n`` algorithms have been optimized for segmented iterators,
-  resulting in performance improvements of up to 21.3x for ``std::deque::iterator`` and 24.9x for ``join_view`` of
-  ``vector<vector<char>>``.
-
 Deprecations and Removals
 -------------------------
 

libcxx/include/__algorithm/ranges_for_each.h

@@ -43,7 +43,10 @@ struct __for_each {
   template <class _Iter, class _Sent, class _Proj, class _Func>
   _LIBCPP_HIDE_FROM_ABI constexpr static for_each_result<_Iter, _Func>
   __for_each_impl(_Iter __first, _Sent __last, _Func& __func, _Proj& __proj) {
-    if constexpr (!std::assignable_from<_Iter&, _Sent> && sized_sentinel_for<_Sent, _Iter>) {
+    // In the case where we have different iterator and sentinel types, the segmented iterator optimization
+    // in std::for_each will not kick in. Therefore, we prefer std::for_each_n in that case (whenever we can
+    // obtain the `n`).
+    if constexpr (!std::assignable_from<_Iter&, _Sent> && std::sized_sentinel_for<_Sent, _Iter>) {
       auto __n   = __last - __first;
       auto __end = std::__for_each_n(std::move(__first), __n, __func, __proj);
       return {std::move(__end), std::move(__func)};

libcxx/test/benchmarks/algorithms/nonmodifying/for_each.bench.cpp

@@ -42,12 +42,7 @@ int main(int argc, char** argv) {
           ->Arg(8)
           ->Arg(32)
           ->Arg(50) // non power-of-two
-          ->Arg(1024)
-          ->Arg(4096)
-          ->Arg(8192)
-          ->Arg(1 << 14)
-          ->Arg(1 << 16)
-          ->Arg(1 << 18);
+          ->Arg(8192);
     };
     bm.operator()<std::vector<int>>("std::for_each(vector<int>)", std_for_each);
     bm.operator()<std::deque<int>>("std::for_each(deque<int>)", std_for_each);
@@ -87,12 +82,7 @@ int main(int argc, char** argv) {
           ->Arg(8)
           ->Arg(32)
           ->Arg(50) // non power-of-two
-          ->Arg(1024)
-          ->Arg(4096)
-          ->Arg(8192)
-          ->Arg(1 << 14)
-          ->Arg(1 << 16)
-          ->Arg(1 << 18);
+          ->Arg(8192);
     };
     bm.operator()<std::vector<std::vector<int>>>("std::for_each(join_view(vector<vector<int>>))", std_for_each);
     bm.operator()<std::vector<std::vector<int>>>("rng::for_each(join_view(vector<vector<int>>)", std::ranges::for_each);

libcxx/test/benchmarks/algorithms/nonmodifying/for_each_n.bench.cpp

@@ -41,12 +41,7 @@ int main(int argc, char** argv) {
           ->Arg(8)
           ->Arg(32)
           ->Arg(50) // non power-of-two
-          ->Arg(1024)
-          ->Arg(4096)
-          ->Arg(8192)
-          ->Arg(1 << 14)
-          ->Arg(1 << 16)
-          ->Arg(1 << 18);
+          ->Arg(8192);
     };
     bm.operator()<std::vector<int>>("std::for_each_n(vector<int>)", std_for_each_n);
     bm.operator()<std::deque<int>>("std::for_each_n(deque<int>)", std_for_each_n);
@@ -84,12 +79,7 @@ int main(int argc, char** argv) {
           ->Arg(8)
           ->Arg(32)
           ->Arg(50) // non power-of-two
-          ->Arg(1024)
-          ->Arg(4096)
-          ->Arg(8192)
-          ->Arg(1 << 14)
-          ->Arg(1 << 16)
-          ->Arg(1 << 18);
+          ->Arg(8192);
     };
     bm.operator()<std::vector<std::vector<int>>>("std::for_each_n(join_view(vector<vector<int>>))", std_for_each_n);
     bm.operator()<std::vector<std::vector<int>>>(