[libc++] Backport segmented iterator optimization for std::for_each to C++11 (#134960)

Previously, the segmented iterator optimization for `std::for_each` was restricted to C++23 and later due to its dependency on `__movable_box`, which is not available in earlier standards. This patch eliminates that restriction, enabling consistent optimizations starting from C++11. 

By backporting this enhancement, we improve performance across older standards and create opportunities to extend similar optimizations to other algorithms by forwarding their calls to `std::for_each`.

Author: winner245

libcxx/docs/ReleaseNotes/21.rst

@@ -67,6 +67,9 @@ Improvements and New Features
 - The ``std::stable_sort`` algorithm uses radix sort for floating-point types now, which can improve the performance
   up to 10x, depending on type of sorted elements and the initial state of the sorted array.
 
+- The segmented iterator optimization for ``std::for_each`` has been backported to C++11. Previously it was only available
+  in C++23 and later.
+
 Deprecations and Removals
 -------------------------
 

libcxx/include/__algorithm/for_each.h

@@ -13,44 +13,40 @@
 #include <__algorithm/for_each_segment.h>
 #include <__config>
 #include <__iterator/segmented_iterator.h>
-#include <__ranges/movable_box.h>
-#include <__utility/in_place.h>
-#include <__utility/move.h>
+#include <__type_traits/enable_if.h>
 
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
 #  pragma GCC system_header
 #endif
 
-_LIBCPP_PUSH_MACROS
-#include <__undef_macros>
-
 _LIBCPP_BEGIN_NAMESPACE_STD
 
-template <class _InputIterator, class _Function>
-_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _Function
-for_each(_InputIterator __first, _InputIterator __last, _Function __f) {
+template <class _InputIterator, class _Sent, class _Func>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void __for_each(_InputIterator __first, _Sent __last, _Func& __f) {
   for (; __first != __last; ++__first)
     __f(*__first);
-  return __f;
 }
 
-// __movable_box is available in C++20, but is actually a copyable-box, so optimization is only correct in C++23
-#if _LIBCPP_STD_VER >= 23
-template <class _SegmentedIterator, class _Function>
-  requires __is_segmented_iterator<_SegmentedIterator>::value
-_LIBCPP_HIDE_FROM_ABI constexpr _Function
-for_each(_SegmentedIterator __first, _SegmentedIterator __last, _Function __func) {
-  ranges::__movable_box<_Function> __wrapped_func(in_place, std::move(__func));
-  std::__for_each_segment(__first, __last, [&](auto __lfirst, auto __llast) {
-    __wrapped_func =
-        ranges::__movable_box<_Function>(in_place, std::for_each(__lfirst, __llast, std::move(*__wrapped_func)));
+#ifndef _LIBCPP_CXX03_LANG
+template <class _SegmentedIterator,
+          class _Function,
+          __enable_if_t<__is_segmented_iterator<_SegmentedIterator>::value, int> = 0>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
+__for_each(_SegmentedIterator __first, _SegmentedIterator __last, _Function& __func) {
+  using __local_iterator_t = typename __segmented_iterator_traits<_SegmentedIterator>::__local_iterator;
+  std::__for_each_segment(__first, __last, [&](__local_iterator_t __lfirst, __local_iterator_t __llast) {
+    std::__for_each(__lfirst, __llast, __func);
   });
-  return std::move(*__wrapped_func);
 }
-#endif // _LIBCPP_STD_VER >= 23
+#endif // !_LIBCPP_CXX03_LANG
 
-_LIBCPP_END_NAMESPACE_STD
+template <class _InputIterator, class _Function>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _Function
+for_each(_InputIterator __first, _InputIterator __last, _Function __f) {
+  std::__for_each(__first, __last, __f);
+  return __f;
+}
 
-_LIBCPP_POP_MACROS
+_LIBCPP_END_NAMESPACE_STD
 
 #endif // _LIBCPP___ALGORITHM_FOR_EACH_H

libcxx/include/algorithm

@@ -2061,6 +2061,7 @@ template <class BidirectionalIterator, class Compare>
 #    include <cstring>
 #    include <iterator>
 #    include <memory>
+#    include <optional>
 #    include <stdexcept>
 #    include <type_traits>
 #    include <utility>

libcxx/include/array

@@ -566,6 +566,7 @@ _LIBCPP_POP_MACROS
 #    include <cstdlib>
 #    include <iterator>
 #    include <new>
+#    include <optional>
 #    include <type_traits>
 #    include <utility>
 #  endif

libcxx/include/bitset

@@ -973,6 +973,7 @@ _LIBCPP_POP_MACROS
 #  if !defined(_LIBCPP_REMOVE_TRANSITIVE_INCLUDES) && _LIBCPP_STD_VER <= 20
 #    include <concepts>
 #    include <cstdlib>
+#    include <optional>
 #    include <type_traits>
 #  endif
 #endif // __cplusplus < 201103L && defined(_LIBCPP_USE_FROZEN_CXX03_HEADERS)

libcxx/include/codecvt

@@ -596,6 +596,7 @@ _LIBCPP_END_NAMESPACE_STD
 #    include <limits>
 #    include <mutex>
 #    include <new>
+#    include <optional>
 #    include <stdexcept>
 #    include <type_traits>
 #    include <typeinfo>

libcxx/include/condition_variable

@@ -357,6 +357,7 @@ _LIBCPP_POP_MACROS
 #    include <initializer_list>
 #    include <iosfwd>
 #    include <new>
+#    include <optional>
 #    include <stdexcept>
 #    include <system_error>
 #    include <type_traits>

libcxx/include/ios

@@ -887,6 +887,7 @@ _LIBCPP_POP_MACROS
 #    include <limits>
 #    include <mutex>
 #    include <new>
+#    include <optional>
 #    include <stdexcept>
 #    include <system_error>
 #    include <type_traits>

libcxx/include/locale

@@ -3692,6 +3692,7 @@ _LIBCPP_POP_MACROS
 #    include <cstdarg>
 #    include <iterator>
 #    include <mutex>
+#    include <optional>
 #    include <stdexcept>
 #    include <type_traits>
 #    include <typeinfo>

libcxx/include/streambuf

@@ -386,6 +386,7 @@ _LIBCPP_POP_MACROS
 
 #  if !defined(_LIBCPP_REMOVE_TRANSITIVE_INCLUDES) && _LIBCPP_STD_VER <= 20
 #    include <cstdint>
+#    include <optional>
 #  endif
 #endif // __cplusplus < 201103L && defined(_LIBCPP_USE_FROZEN_CXX03_HEADERS)