Speed-up and refactor move-assignment operator for vector<bool>

Author: winner245

libcxx/include/__vector/vector_bool.h

@@ -398,6 +398,8 @@ class _LIBCPP_TEMPLATE_VIS vector<bool, _Allocator> {
     __guard.__complete();
   }
 
+  _LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI void __copy_by_words(const vector& __v);
+
   template <class _Iterator, class _Sentinel>
   _LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI void __assign_with_sentinel(_Iterator __first, _Sentinel __last);
 
@@ -695,18 +697,23 @@ _LIBCPP_CONSTEXPR_SINCE_CXX20 vector<bool, _Allocator>::vector(const vector& __v
   }
 }
 
+template <class _Allocator>
+_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI void vector<bool, _Allocator>::__copy_by_words(const vector& __v) {
+  if (__v.__size_) {
+    if (__v.__size_ > capacity()) {
+      __vdeallocate();
+      __vallocate(__v.__size_);
+    }
+    std::copy(__v.__begin_, __v.__begin_ + __external_cap_to_internal(__v.__size_), __begin_);
+  }
+  __size_ = __v.__size_;
+}
+
 template <class _Allocator>
 _LIBCPP_CONSTEXPR_SINCE_CXX20 vector<bool, _Allocator>& vector<bool, _Allocator>::operator=(const vector& __v) {
   if (this != std::addressof(__v)) {
     __copy_assign_alloc(__v);
-    if (__v.__size_) {
-      if (__v.__size_ > capacity()) {
-        __vdeallocate();
-        __vallocate(__v.__size_);
-      }
-      std::copy(__v.__begin_, __v.__begin_ + __external_cap_to_internal(__v.__size_), __begin_);
-    }
-    __size_ = __v.__size_;
+    __copy_by_words(__v);
   }
   return *this;
 }
@@ -754,7 +761,7 @@ vector<bool, _Allocator>::operator=(vector&& __v)
 template <class _Allocator>
 _LIBCPP_CONSTEXPR_SINCE_CXX20 void vector<bool, _Allocator>::__move_assign(vector& __c, false_type) {
   if (__alloc_ != __c.__alloc_)
-    assign(__c.begin(), __c.end());
+    __copy_by_words(__c);
   else
     __move_assign(__c, true_type());
 }

libcxx/test/benchmarks/containers/ContainerBenchmarks.h

@@ -51,6 +51,20 @@ void BM_Assignment(benchmark::State& st, Container) {
   }
 }
 
+template <class Container, class Allocator>
+void BM_Move_Assignment(benchmark::State& st, Container, Allocator) {
+  auto size = st.range(0);
+  Container c1(Allocator{1});
+  Container c2(Allocator{2});
+  c1.reserve(size);
+  c2.resize(size);
+  for (auto _ : st) {
+    c1 = std::move(c2);
+    DoNotOptimizeData(c1);
+    DoNotOptimizeData(c2);
+  }
+}
+
 template <std::size_t... sz, typename Container, typename GenInputs>
 void BM_AssignInputIterIter(benchmark::State& st, Container c, GenInputs gen) {
   auto v = gen(1, sz...);

libcxx/test/benchmarks/containers/vector_bool_operations.bench.cpp

@@ -0,0 +1,77 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++03, c++11
+
+#include <cstdint>
+#include <cstdlib>
+#include <cstring>
+#include <deque>
+#include <functional>
+#include <memory>
+#include <string>
+#include <vector>
+
+#include "benchmark/benchmark.h"
+#include "ContainerBenchmarks.h"
+#include "../GenerateInput.h"
+
+using namespace ContainerBenchmarks;
+
+template <typename T, typename SIZE_TYPE = std::size_t, typename DIFF_TYPE = std::ptrdiff_t>
+class CustomSizedAllocator {
+  template <typename U, typename Sz, typename Diff>
+  friend class CustomSizedAllocator;
+
+public:
+  using value_type                  = T;
+  using size_type                   = SIZE_TYPE;
+  using difference_type             = DIFF_TYPE;
+  using propagate_on_container_swap = std::true_type;
+
+  explicit CustomSizedAllocator(int i = 0) : data_(i) {}
+
+  template <typename U, typename Sz, typename Diff>
+  constexpr CustomSizedAllocator(const CustomSizedAllocator<U, Sz, Diff>& a) noexcept : data_(a.data_) {}
+
+  constexpr T* allocate(size_type n) {
+    if (n > max_size())
+      throw std::bad_array_new_length();
+    return std::allocator<T>().allocate(n);
+  }
+
+  constexpr void deallocate(T* p, size_type n) noexcept { std::allocator<T>().deallocate(p, n); }
+
+  constexpr size_type max_size() const noexcept { return std::numeric_limits<size_type>::max() / sizeof(value_type); }
+
+  int get() { return data_; }
+
+private:
+  int data_;
+
+  constexpr friend bool operator==(const CustomSizedAllocator& a, const CustomSizedAllocator& b) {
+    return a.data_ == b.data_;
+  }
+  constexpr friend bool operator!=(const CustomSizedAllocator& a, const CustomSizedAllocator& b) {
+    return a.data_ != b.data_;
+  }
+};
+
+BENCHMARK_CAPTURE(BM_Move_Assignment,
+                  vector_bool_uint32_t,
+                  std::vector<bool, CustomSizedAllocator<bool, std::uint32_t, std::int32_t>>{},
+                  CustomSizedAllocator<bool, std::uint32_t, std::int32_t>{})
+    ->Arg(5140480);
+
+BENCHMARK_CAPTURE(BM_Move_Assignment,
+                  vector_bool_uint64_t,
+                  std::vector<bool, CustomSizedAllocator<bool, std::uint64_t, std::int64_t>>{},
+                  CustomSizedAllocator<bool, std::uint64_t, std::int64_t>{})
+    ->Arg(5140480);
+
+BENCHMARK_MAIN();