Merge branch 'main' into users/chapuni/cov/single/unifyusers/chapuni/cov/single/unify

11 files changed, 54 insertions, 77 deletions

diff --git a/libcxx/include/__algorithm/comp_ref_type.h b/libcxx/include/__algorithm/comp_ref_type.h
index c367fbb..6a9d5ce 100644
--- a/libcxx/include/__algorithm/comp_ref_type.h
+++ b/libcxx/include/__algorithm/comp_ref_type.h
@@ -56,10 +56,10 @@ struct __debug_less {
 // Pass the comparator by lvalue reference. Or in the debug mode, using a debugging wrapper that stores a reference.
 #if _LIBCPP_HARDENING_MODE == _LIBCPP_HARDENING_MODE_DEBUG
 template <class _Comp>
-using __comp_ref_type = __debug_less<_Comp>;
+using __comp_ref_type _LIBCPP_NODEBUG = __debug_less<_Comp>;
 #else
 template <class _Comp>
-using __comp_ref_type = _Comp&;
+using __comp_ref_type _LIBCPP_NODEBUG = _Comp&;
 #endif
 
 _LIBCPP_END_NAMESPACE_STD
diff --git a/libcxx/include/__algorithm/copy.h b/libcxx/include/__algorithm/copy.h
index 4f30b20..962aa90 100644
--- a/libcxx/include/__algorithm/copy.h
+++ b/libcxx/include/__algorithm/copy.h
@@ -47,7 +47,7 @@ struct __copy_impl {
 
   template <class _InIter, class _OutIter>
   struct _CopySegment {
-    using _Traits = __segmented_iterator_traits<_InIter>;
+    using _Traits _LIBCPP_NODEBUG = __segmented_iterator_traits<_InIter>;
 
     _OutIter& __result_;
 
diff --git a/libcxx/include/__algorithm/iterator_operations.h b/libcxx/include/__algorithm/iterator_operations.h
index 6cdb0ae..e5c89c1 100644
--- a/libcxx/include/__algorithm/iterator_operations.h
+++ b/libcxx/include/__algorithm/iterator_operations.h
@@ -48,13 +48,13 @@ struct _RangeAlgPolicy {};
 template <>
 struct _IterOps<_RangeAlgPolicy> {
   template <class _Iter>
-  using __value_type = iter_value_t<_Iter>;
+  using __value_type _LIBCPP_NODEBUG = iter_value_t<_Iter>;
 
   template <class _Iter>
-  using __iterator_category = ranges::__iterator_concept<_Iter>;
+  using __iterator_category _LIBCPP_NODEBUG = ranges::__iterator_concept<_Iter>;
 
   template <class _Iter>
-  using __difference_type = iter_difference_t<_Iter>;
+  using __difference_type _LIBCPP_NODEBUG = iter_difference_t<_Iter>;
 
   static constexpr auto advance      = ranges::advance;
   static constexpr auto distance     = ranges::distance;
@@ -72,13 +72,13 @@ struct _ClassicAlgPolicy {};
 template <>
 struct _IterOps<_ClassicAlgPolicy> {
   template <class _Iter>
-  using __value_type = typename iterator_traits<_Iter>::value_type;
+  using __value_type _LIBCPP_NODEBUG = typename iterator_traits<_Iter>::value_type;
 
   template <class _Iter>
-  using __iterator_category = typename iterator_traits<_Iter>::iterator_category;
+  using __iterator_category _LIBCPP_NODEBUG = typename iterator_traits<_Iter>::iterator_category;
 
   template <class _Iter>
-  using __difference_type = typename iterator_traits<_Iter>::difference_type;
+  using __difference_type _LIBCPP_NODEBUG = typename iterator_traits<_Iter>::difference_type;
 
   // advance
   template <class _Iter, class _Distance>
@@ -94,10 +94,10 @@ struct _IterOps<_ClassicAlgPolicy> {
   }
 
   template <class _Iter>
-  using __deref_t = decltype(*std::declval<_Iter&>());
+  using __deref_t _LIBCPP_NODEBUG = decltype(*std::declval<_Iter&>());
 
   template <class _Iter>
-  using __move_t = decltype(std::move(*std::declval<_Iter&>()));
+  using __move_t _LIBCPP_NODEBUG = decltype(std::move(*std::declval<_Iter&>()));
 
   template <class _Iter>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 static void __validate_iter_reference() {
@@ -217,7 +217,7 @@ private:
 };
 
 template <class _AlgPolicy, class _Iter>
-using __policy_iter_diff_t = typename _IterOps<_AlgPolicy>::template __difference_type<_Iter>;
+using __policy_iter_diff_t _LIBCPP_NODEBUG = typename _IterOps<_AlgPolicy>::template __difference_type<_Iter>;
 
 _LIBCPP_END_NAMESPACE_STD
 
diff --git a/libcxx/include/__algorithm/mismatch.h b/libcxx/include/__algorithm/mismatch.h
index f585537..a683679 100644
--- a/libcxx/include/__algorithm/mismatch.h
+++ b/libcxx/include/__algorithm/mismatch.h
@@ -78,7 +78,7 @@ __mismatch_vectorized(_Iter __first1, _Iter __last1, _Iter __first2) {
       }
 
       for (size_t __i = 0; __i != __unroll_count; ++__i) {
-        if (auto __cmp_res = std::__as_mask(__lhs[__i] == __rhs[__i]); !std::__all_of(__cmp_res)) {
+        if (auto __cmp_res = __lhs[__i] == __rhs[__i]; !std::__all_of(__cmp_res)) {
           auto __offset = __i * __vec_size + std::__find_first_not_set(__cmp_res);
           return {__first1 + __offset, __first2 + __offset};
         }
@@ -90,7 +90,7 @@ __mismatch_vectorized(_Iter __first1, _Iter __last1, _Iter __first2) {
 
     // check the remaining 0-3 vectors
     while (static_cast<size_t>(__last1 - __first1) >= __vec_size) {
-      if (auto __cmp_res = std::__as_mask(std::__load_vector<__vec>(__first1) == std::__load_vector<__vec>(__first2));
+      if (auto __cmp_res = std::__load_vector<__vec>(__first1) == std::__load_vector<__vec>(__first2);
           !std::__all_of(__cmp_res)) {
         auto __offset = std::__find_first_not_set(__cmp_res);
         return {__first1 + __offset, __first2 + __offset};
@@ -107,8 +107,8 @@ __mismatch_vectorized(_Iter __first1, _Iter __last1, _Iter __first2) {
     if (static_cast<size_t>(__first1 - __orig_first1) >= __vec_size) {
       __first1 = __last1 - __vec_size;
       __first2 = __last2 - __vec_size;
-      auto __offset = std::__find_first_not_set(
-          std::__as_mask(std::__load_vector<__vec>(__first1) == std::__load_vector<__vec>(__first2)));
+      auto __offset =
+          std::__find_first_not_set(std::__load_vector<__vec>(__first1) == std::__load_vector<__vec>(__first2));
       return {__first1 + __offset, __first2 + __offset};
     } // else loop over the elements individually
   }
diff --git a/libcxx/include/__algorithm/move.h b/libcxx/include/__algorithm/move.h
index 005099d..6f3b0eb 100644
--- a/libcxx/include/__algorithm/move.h
+++ b/libcxx/include/__algorithm/move.h
@@ -50,7 +50,7 @@ struct __move_impl {
 
   template <class _InIter, class _OutIter>
   struct _MoveSegment {
-    using _Traits = __segmented_iterator_traits<_InIter>;
+    using _Traits _LIBCPP_NODEBUG = __segmented_iterator_traits<_InIter>;
 
     _OutIter& __result_;
 
diff --git a/libcxx/include/__algorithm/ranges_iterator_concept.h b/libcxx/include/__algorithm/ranges_iterator_concept.h
index 2af891d..58790e9 100644
--- a/libcxx/include/__algorithm/ranges_iterator_concept.h
+++ b/libcxx/include/__algorithm/ranges_iterator_concept.h
@@ -44,7 +44,7 @@ consteval auto __get_iterator_concept() {
 }
 
 template <class _Iter>
-using __iterator_concept = decltype(__get_iterator_concept<_Iter>());
+using __iterator_concept _LIBCPP_NODEBUG = decltype(__get_iterator_concept<_Iter>());
 
 } // namespace ranges
 _LIBCPP_END_NAMESPACE_STD
diff --git a/libcxx/include/__algorithm/ranges_unique_copy.h b/libcxx/include/__algorithm/ranges_unique_copy.h
index 3b4a64e..ee7f0a0 100644
--- a/libcxx/include/__algorithm/ranges_unique_copy.h
+++ b/libcxx/include/__algorithm/ranges_unique_copy.h
@@ -60,7 +60,7 @@ struct __unique_copy {
   }
 
   template <class _InIter, class _OutIter>
-  using __algo_tag_t = decltype(__get_algo_tag<_InIter, _OutIter>());
+  using __algo_tag_t _LIBCPP_NODEBUG = decltype(__get_algo_tag<_InIter, _OutIter>());
 
   template <input_iterator _InIter,
             sentinel_for<_InIter> _Sent,
diff --git a/libcxx/include/__algorithm/simd_utils.h b/libcxx/include/__algorithm/simd_utils.h
index 3ca7924..4e03723 100644
--- a/libcxx/include/__algorithm/simd_utils.h
+++ b/libcxx/include/__algorithm/simd_utils.h
@@ -70,7 +70,7 @@ struct __get_as_integer_type_impl<8> {
 };
 
 template <class _Tp>
-using __get_as_integer_type_t = typename __get_as_integer_type_impl<sizeof(_Tp)>::type;
+using __get_as_integer_type_t _LIBCPP_NODEBUG = typename __get_as_integer_type_impl<sizeof(_Tp)>::type;
 
 // This isn't specialized for 64 byte vectors on purpose. They have the potential to significantly reduce performance
 // in mixed simd/non-simd workloads and don't provide any performance improvement for currently vectorized algorithms
@@ -90,7 +90,7 @@ inline constexpr size_t __native_vector_size = 1;
 #  endif
 
 template <class _ArithmeticT, size_t _Np>
-using __simd_vector __attribute__((__ext_vector_type__(_Np))) = _ArithmeticT;
+using __simd_vector __attribute__((__ext_vector_type__(_Np))) _LIBCPP_NODEBUG = _ArithmeticT;
 
 template <class _VecT>
 inline constexpr size_t __simd_vector_size_v = []<bool _False = false>() -> size_t {
@@ -106,7 +106,7 @@ _LIBCPP_HIDE_FROM_ABI _Tp __simd_vector_underlying_type_impl(__simd_vector<_Tp,
 }
 
 template <class _VecT>
-using __simd_vector_underlying_type_t = decltype(std::__simd_vector_underlying_type_impl(_VecT{}));
+using __simd_vector_underlying_type_t _LIBCPP_NODEBUG = decltype(std::__simd_vector_underlying_type_impl(_VecT{}));
 
 // This isn't inlined without always_inline when loading chars.
 template <class _VecT, class _Iter>
@@ -116,65 +116,42 @@ template <class _VecT, class _Iter>
   }(make_index_sequence<__simd_vector_size_v<_VecT>>{});
 }
 
-template <size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI bool __all_of(__simd_vector<bool, _Np> __vec) noexcept {
-  return __builtin_reduce_and(__vec);
-}
-
 template <class _Tp, size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI auto __as_mask(__simd_vector<_Tp, _Np> __vec) noexcept {
-  static_assert(!is_same<_Tp, bool>::value, "vector type should not be a bool!");
-  return __builtin_convertvector(__vec, __simd_vector<bool, _Np>);
-}
-
-// This uses __builtin_convertvector around the __builtin_shufflevector to work around #107981.
-template <size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI __simd_vector<bool, 8>
-__extend_vector(__simd_vector<bool, _Np> __vec) noexcept {
-  using _VecT = __simd_vector<bool, _Np>;
-  if constexpr (_Np == 4) {
-    return __builtin_convertvector(
-        __builtin_shufflevector(__vec, _VecT{}, 0, 1, 2, 3, 4, 5, 6, 7), __simd_vector<bool, 8>);
-  } else if constexpr (_Np == 2) {
-    return std::__extend_vector(
-        __builtin_convertvector(__builtin_shufflevector(__vec, _VecT{}, 0, 1, 2, 3), __simd_vector<bool, 4>));
-  } else if constexpr (_Np == 1) {
-    return std::__extend_vector(
-        __builtin_convertvector(__builtin_shufflevector(__vec, _VecT{}, 0, 1), __simd_vector<bool, 2>));
-  } else {
-    static_assert(sizeof(_VecT) == 0, "Unexpected vector size");
-  }
+[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI bool __all_of(__simd_vector<_Tp, _Np> __vec) noexcept {
+  return __builtin_reduce_and(__builtin_convertvector(__vec, __simd_vector<bool, _Np>));
 }
 
-template <size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI auto __to_int_mask(__simd_vector<bool, _Np> __vec) {
-  if constexpr (_Np < 8) {
-    return std::__bit_cast<uint8_t>(std::__extend_vector(__vec));
-  } else if constexpr (_Np == 8) {
-    return std::__bit_cast<uint8_t>(__vec);
-  } else if constexpr (_Np == 16) {
-    return std::__bit_cast<uint16_t>(__vec);
-  } else if constexpr (_Np == 32) {
-    return std::__bit_cast<uint32_t>(__vec);
-  } else if constexpr (_Np == 64) {
-    return std::__bit_cast<uint64_t>(__vec);
-  } else {
-    static_assert(sizeof(__simd_vector<bool, _Np>) == 0, "Unexpected vector size");
-    return 0;
-  }
-}
+template <class _Tp, size_t _Np>
+[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI size_t __find_first_set(__simd_vector<_Tp, _Np> __vec) noexcept {
+  using __mask_vec = __simd_vector<bool, _Np>;
 
-template <size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI size_t __find_first_set(__simd_vector<bool, _Np> __vec) noexcept {
+  // This has MSan disabled du to https://github.com/llvm/llvm-project/issues/85876
+  auto __impl = [&]<class _MaskT>(_MaskT) _LIBCPP_NO_SANITIZE("memory") noexcept {
 #  if defined(_LIBCPP_BIG_ENDIAN)
-  return std::min<size_t>(_Np, std::__countl_zero(std::__to_int_mask(__vec)));
+    return std::min<size_t>(
+        _Np, std::__countl_zero(__builtin_bit_cast(_MaskT, __builtin_convertvector(__vec, __mask_vec))));
 #  else
-  return std::min<size_t>(_Np, std::__countr_zero(std::__to_int_mask(__vec)));
+    return std::min<size_t>(
+        _Np, std::__countr_zero(__builtin_bit_cast(_MaskT, __builtin_convertvector(__vec, __mask_vec))));
 #  endif
+  };
+
+  if constexpr (sizeof(__mask_vec) == sizeof(uint8_t)) {
+    return __impl(uint8_t{});
+  } else if constexpr (sizeof(__mask_vec) == sizeof(uint16_t)) {
+    return __impl(uint16_t{});
+  } else if constexpr (sizeof(__mask_vec) == sizeof(uint32_t)) {
+    return __impl(uint32_t{});
+  } else if constexpr (sizeof(__mask_vec) == sizeof(uint64_t)) {
+    return __impl(uint64_t{});
+  } else {
+    static_assert(sizeof(__mask_vec) == 0, "unexpected required size for mask integer type");
+    return 0;
+  }
 }
 
-template <size_t _Np>
-[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI size_t __find_first_not_set(__simd_vector<bool, _Np> __vec) noexcept {
+template <class _Tp, size_t _Np>
+[[__nodiscard__]] _LIBCPP_HIDE_FROM_ABI size_t __find_first_not_set(__simd_vector<_Tp, _Np> __vec) noexcept {
   return std::__find_first_set(~__vec);
 }
 
diff --git a/libcxx/include/__algorithm/sort.h b/libcxx/include/__algorithm/sort.h
index ed828b6..5c60b23 100644
--- a/libcxx/include/__algorithm/sort.h
+++ b/libcxx/include/__algorithm/sort.h
@@ -890,10 +890,10 @@ __sort_dispatch(_RandomAccessIterator __first, _RandomAccessIterator __last, _Co
 }
 
 template <class _Type, class... _Options>
-using __is_any_of = _Or<is_same<_Type, _Options>...>;
+using __is_any_of _LIBCPP_NODEBUG = _Or<is_same<_Type, _Options>...>;
 
 template <class _Type>
-using __sort_is_specialized_in_library = __is_any_of<
+using __sort_is_specialized_in_library _LIBCPP_NODEBUG = __is_any_of<
     _Type,
     char,
 #if _LIBCPP_HAS_WIDE_CHARACTERS
diff --git a/libcxx/include/__algorithm/three_way_comp_ref_type.h b/libcxx/include/__algorithm/three_way_comp_ref_type.h
index 5702a1f..f6f7645 100644
--- a/libcxx/include/__algorithm/three_way_comp_ref_type.h
+++ b/libcxx/include/__algorithm/three_way_comp_ref_type.h
@@ -61,10 +61,10 @@ struct __debug_three_way_comp {
 // Pass the comparator by lvalue reference. Or in the debug mode, using a debugging wrapper that stores a reference.
 #  if _LIBCPP_HARDENING_MODE == _LIBCPP_HARDENING_MODE_DEBUG
 template <class _Comp>
-using __three_way_comp_ref_type = __debug_three_way_comp<_Comp>;
+using __three_way_comp_ref_type _LIBCPP_NODEBUG = __debug_three_way_comp<_Comp>;
 #  else
 template <class _Comp>
-using __three_way_comp_ref_type = _Comp&;
+using __three_way_comp_ref_type _LIBCPP_NODEBUG = _Comp&;
 #  endif
 
 #endif // _LIBCPP_STD_VER >= 20
diff --git a/libcxx/include/__algorithm/unwrap_iter.h b/libcxx/include/__algorithm/unwrap_iter.h
index 8cc0d22..b66a682 100644
--- a/libcxx/include/__algorithm/unwrap_iter.h
+++ b/libcxx/include/__algorithm/unwrap_iter.h
@@ -46,7 +46,7 @@ struct __unwrap_iter_impl {
 // It's a contiguous iterator, so we can use a raw pointer instead
 template <class _Iter>
 struct __unwrap_iter_impl<_Iter, true> {
-  using _ToAddressT = decltype(std::__to_address(std::declval<_Iter>()));
+  using _ToAddressT _LIBCPP_NODEBUG = decltype(std::__to_address(std::declval<_Iter>()));
 
   static _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR _Iter __rewrap(_Iter __orig_iter, _ToAddressT __unwrapped_iter) {
     return __orig_iter + (__unwrapped_iter - std::__to_address(__orig_iter));