[libcxx-commits] [libcxx] [libc++] Optimize ranges::move{, _backward} for vector<bool>::iterator (PR #121109)

via libcxx-commits libcxx-commits at lists.llvm.org
Mon Feb 3 07:57:05 PST 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-libcxx

Author: Peng Liu (winner245)

<details>
<summary>Changes</summary>

As a follow-up to #<!-- -->121013 (which optimized `ranges::copy`) and #<!-- -->121026 (which optimized `ranges::copy_backward`), this PR enhances the performance of `std::ranges::{move, move_backward}` for `vector<bool>::iterator`, addressing a subtask outlined in issue #<!-- -->64038. 

The optimizations bring performance improvements analogous to those achieved for the `{copy, copy_backward}` algorithms: up to **2000x** for aligned moves and **60x** for unaligned moves. Moreover, comprehensive tests covering up to 4 storage words (256 bytes) with odd and even bit sizes are provided, which validate the proposed optimizations in this patch. 

### Benchmarks 

 #### Aligned move (up to 2406x)

```
-----------------------------------------------------------------------------
Benchmark                                  Before         After   Improvement
-----------------------------------------------------------------------------
bm_ranges_move_vb_aligned/8               11.3 ns       4.80 ns          2.4x
bm_ranges_move_vb_aligned/64              89.5 ns       5.33 ns         16.8x
bm_ranges_move_vb_aligned/512              716 ns       5.05 ns          142x
bm_ranges_move_vb_aligned/4096            5662 ns       9.84 ns          575x
bm_ranges_move_vb_aligned/32768          44880 ns       46.1 ns          973x
bm_ranges_move_vb_aligned/65536          90616 ns       79.3 ns         1143x
bm_ranges_move_vb_aligned/102400        144683 ns       67.0 ns         2159x
bm_ranges_move_vb_aligned/106496        150643 ns       68.5 ns         2199x
bm_ranges_move_vb_aligned/110592        158098 ns       70.3 ns         2249x
bm_ranges_move_vb_aligned/114688        168557 ns       74.9 ns         2250x
bm_ranges_move_vb_aligned/118784        169404 ns       77.6 ns         2183x
bm_ranges_move_vb_aligned/122880        173890 ns       80.0 ns         2174x
bm_ranges_move_vb_aligned/126976        179472 ns       81.2 ns         2210x
bm_ranges_move_vb_aligned/131072        182714 ns       86.5 ns         2112x
bm_ranges_move_vb_aligned/135168        190121 ns       87.8 ns         2165x
bm_ranges_move_vb_aligned/139264        197667 ns       90.1 ns         2193x
bm_ranges_move_vb_aligned/143360        211083 ns       87.7 ns         2406x
bm_ranges_move_vb_aligned/147456        225014 ns       89.6 ns         2511x
bm_ranges_move_vb_aligned/151552        219499 ns       91.4 ns         2402x
bm_ranges_move_vb_aligned/155648        224825 ns       99.0 ns         2271x
bm_ranges_move_vb_aligned/159744        227261 ns        103 ns         2206x
bm_ranges_move_vb_aligned/163840        229928 ns        182 ns         1263x
bm_ranges_move_vb_aligned/167936        226347 ns        212 ns         1068x
bm_ranges_move_vb_aligned/172032        238817 ns        142 ns         1682x
bm_ranges_move_vb_aligned/176128        257062 ns        121 ns         2124x
bm_ranges_move_vb_aligned/180224        262250 ns        122 ns         2150x
bm_ranges_move_vb_aligned/184320        261486 ns        118 ns         2216x
bm_ranges_move_vb_aligned/188416        269745 ns        127 ns         2124x
bm_ranges_move_vb_aligned/192512        271024 ns        128 ns         2117x
bm_ranges_move_vb_aligned/196608        275733 ns        228 ns         1209x
bm_ranges_move_vb_aligned/200704        278653 ns        285 ns          978x
bm_ranges_move_vb_aligned/204800        286797 ns        243 ns         1180x
```

#### Aligned move_backward (up to 2226x)

```
-------------------------------------------------------------------------------------
Benchmark                                           Before        After   Improvement
-------------------------------------------------------------------------------------
bm_ranges_move_backward_vb_aligned/8               9.72 ns       5.03 ns         1.9x
bm_ranges_move_backward_vb_aligned/64              89.8 ns       5.23 ns        17.2x
bm_ranges_move_backward_vb_aligned/512              643 ns       5.18 ns         124x
bm_ranges_move_backward_vb_aligned/4096            5037 ns       10.1 ns         499x
bm_ranges_move_backward_vb_aligned/32768          40126 ns       44.9 ns         894x
bm_ranges_move_backward_vb_aligned/65536          80262 ns       77.5 ns        1036x
bm_ranges_move_backward_vb_aligned/102400        125445 ns       64.0 ns        1960x
bm_ranges_move_backward_vb_aligned/106496        131869 ns       69.0 ns        1911x
bm_ranges_move_backward_vb_aligned/110592        142678 ns       64.1 ns        2226x
bm_ranges_move_backward_vb_aligned/114688        141358 ns       65.1 ns        2171x
bm_ranges_move_backward_vb_aligned/118784        148357 ns       66.5 ns        2231x
bm_ranges_move_backward_vb_aligned/122880        151052 ns       68.8 ns        2196x
bm_ranges_move_backward_vb_aligned/126976        158514 ns       71.4 ns        2220x
bm_ranges_move_backward_vb_aligned/131072        163450 ns       73.5 ns        2224x
bm_ranges_move_backward_vb_aligned/135168        170184 ns        158 ns        1077x
bm_ranges_move_backward_vb_aligned/139264        172592 ns        103 ns        1676x
bm_ranges_move_backward_vb_aligned/143360        179955 ns       93.9 ns        1916x
bm_ranges_move_backward_vb_aligned/147456        185436 ns       95.1 ns        1950x
bm_ranges_move_backward_vb_aligned/151552        194811 ns       94.4 ns        2064x
bm_ranges_move_backward_vb_aligned/155648        195126 ns       96.3 ns        2026x
bm_ranges_move_backward_vb_aligned/159744        203279 ns       99.6 ns        2041x
bm_ranges_move_backward_vb_aligned/163840        208438 ns        174 ns        1198x
bm_ranges_move_backward_vb_aligned/167936        211036 ns        209 ns        1010x
bm_ranges_move_backward_vb_aligned/172032        217071 ns        139 ns        1562x
bm_ranges_move_backward_vb_aligned/176128        226155 ns        117 ns        1933x
bm_ranges_move_backward_vb_aligned/180224        232424 ns        117 ns        1987x
bm_ranges_move_backward_vb_aligned/184320        236457 ns        117 ns        2021x
bm_ranges_move_backward_vb_aligned/188416        240821 ns        127 ns        1896x
bm_ranges_move_backward_vb_aligned/192512        247794 ns        127 ns        1951x
bm_ranges_move_backward_vb_aligned/196608        243881 ns        217 ns        1124x
bm_ranges_move_backward_vb_aligned/200704        255730 ns        286 ns         894x
bm_ranges_move_backward_vb_aligned/204800        245215 ns        237 ns        1035x
```


 #### Unaligned move_backward (up to 62x)

```
-----------------------------------------------------------------------------
Benchmark                                  Before         After   Improvement
-----------------------------------------------------------------------------
bm_ranges_move_vb_unaligned/8             11.4 ns       8.64 ns          1.3x
bm_ranges_move_vb_unaligned/64            96.5 ns       8.18 ns           12x
bm_ranges_move_vb_unaligned/512            755 ns       17.9 ns           42x
bm_ranges_move_vb_unaligned/4096          6013 ns       97.7 ns           62x
bm_ranges_move_vb_unaligned/32768        47906 ns        781 ns           61x
bm_ranges_move_vb_unaligned/262144      384167 ns       6201 ns           62x
bm_ranges_move_vb_unaligned/1048576    1521607 ns      25520 ns           60x
```

 #### Unaligned move_backward (up to 64x)

```
-------------------------------------------------------------------------------------
Benchmark                                           Before        After   Improvement
-------------------------------------------------------------------------------------
bm_ranges_move_backward_vb_unaligned/8            10.00 ns       9.61 ns         1.0x
bm_ranges_move_backward_vb_unaligned/64            88.4 ns       8.53 ns          10x
bm_ranges_move_backward_vb_unaligned/512            656 ns       17.8 ns          37x
bm_ranges_move_backward_vb_unaligned/4096          5238 ns        102 ns          51x
bm_ranges_move_backward_vb_unaligned/32768        42843 ns        706 ns          61x
bm_ranges_move_backward_vb_unaligned/262144      339261 ns       5803 ns          58x
bm_ranges_move_backward_vb_unaligned/1048576    1484360 ns      23332 ns          64x
```



---

Patch is 35.53 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/121109.diff


10 Files Affected:

- (modified) libcxx/docs/ReleaseNotes/21.rst (+2-3) 
- (modified) libcxx/include/__algorithm/move.h (+10) 
- (modified) libcxx/include/__algorithm/move_backward.h (+10) 
- (modified) libcxx/include/__bit_reference (-16) 
- (added) libcxx/test/benchmarks/algorithms/move.bench.cpp (+55) 
- (added) libcxx/test/benchmarks/algorithms/move_backward.bench.cpp (+55) 
- (modified) libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move.pass.cpp (+42-11) 
- (modified) libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move_backward.pass.cpp (+44-16) 
- (modified) libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move.pass.cpp (+74-33) 
- (modified) libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move_backward.pass.cpp (+84-34) 


``````````diff
diff --git a/libcxx/docs/ReleaseNotes/21.rst b/libcxx/docs/ReleaseNotes/21.rst
index 82f1de6bad3942..9b3e120e4bfd64 100644
--- a/libcxx/docs/ReleaseNotes/21.rst
+++ b/libcxx/docs/ReleaseNotes/21.rst
@@ -43,9 +43,8 @@ Implemented Papers
 Improvements and New Features
 -----------------------------
 
-- The ``std::ranges::{copy, copy_n, copy_backward}`` algorithms have been optimized for ``std::vector<bool>::iterator``\s,
-  resulting in a performance improvement of up to 2000x.
-
+- The ``std::ranges::{copy, copy_n, copy_backward, move, move_backward}`` algorithms have been optimized for
+  ``std::vector<bool>::iterator``, resulting in a performance improvement of up to 2000x.
 
 Deprecations and Removals
 -------------------------
diff --git a/libcxx/include/__algorithm/move.h b/libcxx/include/__algorithm/move.h
index 6f3b0eb5d2927c..a3320e9f1985d0 100644
--- a/libcxx/include/__algorithm/move.h
+++ b/libcxx/include/__algorithm/move.h
@@ -9,11 +9,13 @@
 #ifndef _LIBCPP___ALGORITHM_MOVE_H
 #define _LIBCPP___ALGORITHM_MOVE_H
 
+#include <__algorithm/copy.h>
 #include <__algorithm/copy_move_common.h>
 #include <__algorithm/for_each_segment.h>
 #include <__algorithm/iterator_operations.h>
 #include <__algorithm/min.h>
 #include <__config>
+#include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
 #include <__iterator/segmented_iterator.h>
 #include <__type_traits/common_type.h>
@@ -98,6 +100,14 @@ struct __move_impl {
     }
   }
 
+  template <class _Cp, bool _IsConst>
+  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<__bit_iterator<_Cp, _IsConst>, __bit_iterator<_Cp, false> >
+  operator()(__bit_iterator<_Cp, _IsConst> __first,
+             __bit_iterator<_Cp, _IsConst> __last,
+             __bit_iterator<_Cp, false> __result) {
+    return std::__copy(__first, __last, __result);
+  }
+
   // At this point, the iterators have been unwrapped so any `contiguous_iterator` has been unwrapped to a pointer.
   template <class _In, class _Out, __enable_if_t<__can_lower_move_assignment_to_memmove<_In, _Out>::value, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_In*, _Out*>
diff --git a/libcxx/include/__algorithm/move_backward.h b/libcxx/include/__algorithm/move_backward.h
index 24a8d9b24527a7..14482fee181147 100644
--- a/libcxx/include/__algorithm/move_backward.h
+++ b/libcxx/include/__algorithm/move_backward.h
@@ -9,10 +9,12 @@
 #ifndef _LIBCPP___ALGORITHM_MOVE_BACKWARD_H
 #define _LIBCPP___ALGORITHM_MOVE_BACKWARD_H
 
+#include <__algorithm/copy_backward.h>
 #include <__algorithm/copy_move_common.h>
 #include <__algorithm/iterator_operations.h>
 #include <__algorithm/min.h>
 #include <__config>
+#include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
 #include <__iterator/segmented_iterator.h>
 #include <__type_traits/common_type.h>
@@ -107,6 +109,14 @@ struct __move_backward_impl {
     }
   }
 
+  template <class _Cp, bool _IsConst>
+  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<__bit_iterator<_Cp, _IsConst>, __bit_iterator<_Cp, false> >
+  operator()(__bit_iterator<_Cp, _IsConst> __first,
+             __bit_iterator<_Cp, _IsConst> __last,
+             __bit_iterator<_Cp, false> __result) {
+    return std::__copy_backward<_ClassicAlgPolicy>(__first, __last, __result);
+  }
+
   // At this point, the iterators have been unwrapped so any `contiguous_iterator` has been unwrapped to a pointer.
   template <class _In, class _Out, __enable_if_t<__can_lower_move_assignment_to_memmove<_In, _Out>::value, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_In*, _Out*>
diff --git a/libcxx/include/__bit_reference b/libcxx/include/__bit_reference
index bb8d4725c39805..c4e00769715479 100644
--- a/libcxx/include/__bit_reference
+++ b/libcxx/include/__bit_reference
@@ -186,22 +186,6 @@ private:
         __mask_(__m) {}
 };
 
-// move
-
-template <class _Cp, bool _IsConst>
-inline _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false>
-move(__bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
-  return std::copy(__first, __last, __result);
-}
-
-// move_backward
-
-template <class _Cp, bool _IsConst>
-inline _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> move_backward(
-    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
-  return std::copy_backward(__first, __last, __result);
-}
-
 // swap_ranges
 
 template <class _Cl, class _Cr>
diff --git a/libcxx/test/benchmarks/algorithms/move.bench.cpp b/libcxx/test/benchmarks/algorithms/move.bench.cpp
new file mode 100644
index 00000000000000..909c0c4f1b4c58
--- /dev/null
+++ b/libcxx/test/benchmarks/algorithms/move.bench.cpp
@@ -0,0 +1,55 @@
+//===----------------------------------------------------------------------===//
+//
+// 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, c++14, c++17, c++20
+
+#include <algorithm>
+#include <benchmark/benchmark.h>
+#include <vector>
+
+static void bm_ranges_move_vb(benchmark::State& state, bool aligned) {
+  auto n = state.range();
+  std::vector<bool> in(n, true);
+  std::vector<bool> out(aligned ? n : n + 8);
+  benchmark::DoNotOptimize(&in);
+  auto dst = aligned ? out.begin() : out.begin() + 4;
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(std::ranges::move(in, dst));
+    benchmark::DoNotOptimize(&out);
+  }
+}
+
+static void bm_move_vb(benchmark::State& state, bool aligned) {
+  auto n = state.range();
+  std::vector<bool> in(n, true);
+  std::vector<bool> out(aligned ? n : n + 8);
+  benchmark::DoNotOptimize(&in);
+  auto beg = in.begin();
+  auto end = in.end();
+  auto dst = aligned ? out.begin() : out.begin() + 4;
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(std::move(beg, end, dst));
+    benchmark::DoNotOptimize(&out);
+  }
+}
+
+static void bm_ranges_move_vb_aligned(benchmark::State& state) { bm_ranges_move_vb(state, true); }
+static void bm_ranges_move_vb_unaligned(benchmark::State& state) { bm_ranges_move_vb(state, false); }
+
+static void bm_move_vb_aligned(benchmark::State& state) { bm_move_vb(state, true); }
+static void bm_move_vb_unaligned(benchmark::State& state) { bm_move_vb(state, false); }
+
+// Test std::ranges::move for vector<bool>::iterator
+BENCHMARK(bm_ranges_move_vb_aligned)->Range(8, 1 << 16)->DenseRange(102400, 204800, 4096);
+BENCHMARK(bm_ranges_move_vb_unaligned)->Range(8, 1 << 20);
+
+// Test std::move for vector<bool>::iterator
+BENCHMARK(bm_move_vb_aligned)->Range(8, 1 << 20);
+BENCHMARK(bm_move_vb_unaligned)->Range(8, 1 << 20);
+
+BENCHMARK_MAIN();
diff --git a/libcxx/test/benchmarks/algorithms/move_backward.bench.cpp b/libcxx/test/benchmarks/algorithms/move_backward.bench.cpp
new file mode 100644
index 00000000000000..48b1a776bf4dd9
--- /dev/null
+++ b/libcxx/test/benchmarks/algorithms/move_backward.bench.cpp
@@ -0,0 +1,55 @@
+//===----------------------------------------------------------------------===//
+//
+// 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, c++14, c++17, c++20
+
+#include <algorithm>
+#include <benchmark/benchmark.h>
+#include <vector>
+
+static void bm_ranges_move_backward_vb(benchmark::State& state, bool aligned) {
+  auto n = state.range();
+  std::vector<bool> in(n, true);
+  std::vector<bool> out(aligned ? n : n + 8);
+  benchmark::DoNotOptimize(&in);
+  auto dst = aligned ? out.end() : out.end() - 4;
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(std::ranges::move_backward(in, dst));
+    benchmark::DoNotOptimize(&out);
+  }
+}
+
+static void bm_move_backward(benchmark::State& state, bool aligned) {
+  auto n = state.range();
+  std::vector<bool> in(n, true);
+  std::vector<bool> out(aligned ? n : n + 8);
+  benchmark::DoNotOptimize(&in);
+  auto beg = in.begin();
+  auto end = in.end();
+  auto dst = aligned ? out.end() : out.end() - 4;
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(std::move_backward(beg, end, dst));
+    benchmark::DoNotOptimize(&out);
+  }
+}
+
+static void bm_ranges_move_backward_vb_aligned(benchmark::State& state) { bm_ranges_move_backward_vb(state, true); }
+static void bm_ranges_move_backward_vb_unaligned(benchmark::State& state) { bm_ranges_move_backward_vb(state, false); }
+
+static void bm_move_backward_vb_aligned(benchmark::State& state) { bm_move_backward(state, true); }
+static void bm_move_backward_vb_unaligned(benchmark::State& state) { bm_move_backward(state, false); }
+
+// Test std::ranges::move_backward for vector<bool>::iterator
+BENCHMARK(bm_ranges_move_backward_vb_aligned)->Range(8, 1 << 16)->DenseRange(102400, 204800, 4096);
+BENCHMARK(bm_ranges_move_backward_vb_unaligned)->Range(8, 1 << 20);
+
+// Test std::move_backward for vector<bool>::iterator
+BENCHMARK(bm_move_backward_vb_aligned)->Range(8, 1 << 20);
+BENCHMARK(bm_move_backward_vb_unaligned)->Range(8, 1 << 20);
+
+BENCHMARK_MAIN();
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move.pass.cpp
index b1ad6873bc5e5a..8b414b061105f2 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move.pass.cpp
@@ -20,6 +20,7 @@
 #include <cassert>
 #include <iterator>
 #include <memory>
+#include <vector>
 
 #include "MoveOnly.h"
 #include "test_iterators.h"
@@ -45,15 +46,15 @@ struct Test {
   template <class OutIter>
   TEST_CONSTEXPR_CXX20 void operator()() {
     const unsigned N = 1000;
-    int ia[N] = {};
+    int ia[N]        = {};
     for (unsigned i = 0; i < N; ++i)
-        ia[i] = i;
+      ia[i] = i;
     int ib[N] = {0};
 
-    OutIter r = std::move(InIter(ia), InIter(ia+N), OutIter(ib));
-    assert(base(r) == ib+N);
+    OutIter r = std::move(InIter(ia), InIter(ia + N), OutIter(ib));
+    assert(base(r) == ib + N);
     for (unsigned i = 0; i < N; ++i)
-        assert(ia[i] == ib[i]);
+      assert(ia[i] == ib[i]);
   }
 };
 
@@ -73,13 +74,13 @@ struct Test1 {
     const unsigned N = 100;
     std::unique_ptr<int> ia[N];
     for (unsigned i = 0; i < N; ++i)
-        ia[i].reset(new int(i));
+      ia[i].reset(new int(i));
     std::unique_ptr<int> ib[N];
 
-    OutIter r = std::move(InIter(ia), InIter(ia+N), OutIter(ib));
-    assert(base(r) == ib+N);
+    OutIter r = std::move(InIter(ia), InIter(ia + N), OutIter(ib));
+    assert(base(r) == ib + N);
     for (unsigned i = 0; i < N; ++i)
-        assert(*ib[i] == static_cast<int>(i));
+      assert(*ib[i] == static_cast<int>(i));
   }
 };
 
@@ -92,6 +93,26 @@ struct Test1OutIters {
   }
 };
 
+TEST_CONSTEXPR_CXX20 bool test_vector_bool(std::size_t N) {
+  std::vector<bool> in(N, false);
+  for (std::size_t i = 0; i < N; i += 2)
+    in[i] = true;
+
+  { // Test move with aligned bytes
+    std::vector<bool> out(N);
+    std::move(in.begin(), in.end(), out.begin());
+    assert(in == out);
+  }
+  { // Test move with unaligned bytes
+    std::vector<bool> out(N + 8);
+    std::move(in.begin(), in.end(), out.begin() + 4);
+    for (std::size_t i = 0; i < N; ++i)
+      assert(out[i + 4] == in[i]);
+  }
+
+  return true;
+}
+
 TEST_CONSTEXPR_CXX20 bool test() {
   types::for_each(types::cpp17_input_iterator_list<int*>(), TestOutIters());
   if (TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED)
@@ -118,7 +139,7 @@ TEST_CONSTEXPR_CXX20 bool test() {
     // When non-trivial
     {
       MoveOnly from[3] = {1, 2, 3};
-      MoveOnly to[3] = {};
+      MoveOnly to[3]   = {};
       std::move(std::begin(from), std::end(from), std::begin(to));
       assert(to[0] == MoveOnly(1));
       assert(to[1] == MoveOnly(2));
@@ -127,7 +148,7 @@ TEST_CONSTEXPR_CXX20 bool test() {
     // When trivial
     {
       TrivialMoveOnly from[3] = {1, 2, 3};
-      TrivialMoveOnly to[3] = {};
+      TrivialMoveOnly to[3]   = {};
       std::move(std::begin(from), std::end(from), std::begin(to));
       assert(to[0] == TrivialMoveOnly(1));
       assert(to[1] == TrivialMoveOnly(2));
@@ -135,6 +156,16 @@ TEST_CONSTEXPR_CXX20 bool test() {
     }
   }
 
+  { // Test vector<bool>::iterator optimization
+    assert(test_vector_bool(8));
+    assert(test_vector_bool(19));
+    assert(test_vector_bool(32));
+    assert(test_vector_bool(49));
+    assert(test_vector_bool(64));
+    assert(test_vector_bool(199));
+    assert(test_vector_bool(256));
+  }
+
   return true;
 }
 
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move_backward.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move_backward.pass.cpp
index 61dea47b510716..dfee9de2fa7687 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move_backward.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/move_backward.pass.cpp
@@ -19,6 +19,7 @@
 #include <cassert>
 #include <iterator>
 #include <memory>
+#include <vector>
 
 #include "MoveOnly.h"
 #include "test_iterators.h"
@@ -44,24 +45,22 @@ struct Test {
   template <class OutIter>
   TEST_CONSTEXPR_CXX20 void operator()() {
     const unsigned N = 1000;
-    int ia[N] = {};
+    int ia[N]        = {};
     for (unsigned i = 0; i < N; ++i)
-        ia[i] = i;
+      ia[i] = i;
     int ib[N] = {0};
 
-    OutIter r = std::move_backward(InIter(ia), InIter(ia+N), OutIter(ib+N));
+    OutIter r = std::move_backward(InIter(ia), InIter(ia + N), OutIter(ib + N));
     assert(base(r) == ib);
     for (unsigned i = 0; i < N; ++i)
-        assert(ia[i] == ib[i]);
+      assert(ia[i] == ib[i]);
   }
 };
 
 struct TestOutIters {
   template <class InIter>
   TEST_CONSTEXPR_CXX20 void operator()() {
-    types::for_each(
-        types::concatenate_t<types::bidirectional_iterator_list<int*> >(),
-        Test<InIter>());
+    types::for_each(types::concatenate_t<types::bidirectional_iterator_list<int*> >(), Test<InIter>());
   }
 };
 
@@ -72,24 +71,44 @@ struct Test1 {
     const unsigned N = 100;
     std::unique_ptr<int> ia[N];
     for (unsigned i = 0; i < N; ++i)
-        ia[i].reset(new int(i));
+      ia[i].reset(new int(i));
     std::unique_ptr<int> ib[N];
 
-    OutIter r = std::move_backward(InIter(ia), InIter(ia+N), OutIter(ib+N));
+    OutIter r = std::move_backward(InIter(ia), InIter(ia + N), OutIter(ib + N));
     assert(base(r) == ib);
     for (unsigned i = 0; i < N; ++i)
-        assert(*ib[i] == static_cast<int>(i));
+      assert(*ib[i] == static_cast<int>(i));
   }
 };
 
 struct Test1OutIters {
   template <class InIter>
   TEST_CONSTEXPR_CXX23 void operator()() {
-    types::for_each(types::concatenate_t<types::bidirectional_iterator_list<std::unique_ptr<int>*> >(),
-                    Test1<InIter>());
+    types::for_each(
+        types::concatenate_t<types::bidirectional_iterator_list<std::unique_ptr<int>*> >(), Test1<InIter>());
   }
 };
 
+TEST_CONSTEXPR_CXX20 bool test_vector_bool(std::size_t N) {
+  std::vector<bool> in(N, false);
+  for (std::size_t i = 0; i < N; i += 2)
+    in[i] = true;
+
+  { // Test move_backward with aligned bytes
+    std::vector<bool> out(N);
+    std::move_backward(in.begin(), in.end(), out.end());
+    assert(in == out);
+  }
+  { // Test move_backward with unaligned bytes
+    std::vector<bool> out(N + 8);
+    std::move_backward(in.begin(), in.end(), out.end() - 4);
+    for (std::size_t i = 0; i < N; ++i)
+      assert(out[i + 4] == in[i]);
+  }
+
+  return true;
+}
+
 TEST_CONSTEXPR_CXX20 bool test() {
   types::for_each(types::bidirectional_iterator_list<int*>(), TestOutIters());
   if (TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED)
@@ -117,7 +136,7 @@ TEST_CONSTEXPR_CXX20 bool test() {
     // When non-trivial
     {
       MoveOnly from[3] = {1, 2, 3};
-      MoveOnly to[3] = {};
+      MoveOnly to[3]   = {};
       std::move_backward(std::begin(from), std::end(from), std::end(to));
       assert(to[0] == MoveOnly(1));
       assert(to[1] == MoveOnly(2));
@@ -126,7 +145,7 @@ TEST_CONSTEXPR_CXX20 bool test() {
     // When trivial
     {
       TrivialMoveOnly from[3] = {1, 2, 3};
-      TrivialMoveOnly to[3] = {};
+      TrivialMoveOnly to[3]   = {};
       std::move_backward(std::begin(from), std::end(from), std::end(to));
       assert(to[0] == TrivialMoveOnly(1));
       assert(to[1] == TrivialMoveOnly(2));
@@ -134,11 +153,20 @@ TEST_CONSTEXPR_CXX20 bool test() {
     }
   }
 
+  { // Test vector<bool>::iterator optimization
+    assert(test_vector_bool(8));
+    assert(test_vector_bool(19));
+    assert(test_vector_bool(32));
+    assert(test_vector_bool(49));
+    assert(test_vector_bool(64));
+    assert(test_vector_bool(199));
+    assert(test_vector_bool(256));
+  }
+
   return true;
 }
 
-int main(int, char**)
-{
+int main(int, char**) {
   test();
 #if TEST_STD_VER >= 20
   static_assert(test());
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move.pass.cpp
index a0d1473360a14e..664631aea826b1 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.move/ranges.move.pass.cpp
@@ -31,6 +31,7 @@
 #include "almost_satisfies_types.h"
 #include "MoveOnly.h"
 #include "test_iterators.h"
+#include "test_macros.h"
 
 template <class In, class Out = In, class Sent = sentinel_wrapper<In>>
 concept HasMoveIt = requires(In in, Sent sent, Out out) { std::ranges::move(in, sent, out); };
@@ -65,7 +66,7 @@ constexpr void test(std::array<int, N> in) {
   {
     std::array<int, N> out;
     std::same_as<std::ranges::in_out_result<In, Out>> decltype(auto) ret =
-      std::ranges::move(In(in.data()), Sent(In(in.data() + in.size())), Out(out.data()));
+        std::ranges::move(In(in.data()), Sent(In(in.data() + in.size())), Out(out.data()));
     assert(in == out);
     assert(base(ret.in) == in.data() + in.size());
     assert(base(ret.out) == out.data() + out.size());
@@ -73,8 +74,7 @@ constexpr void test(std::array<int, N> in) {
   {
     std::array<int, N> out;
     auto range = std::ranges::subrange(In(in.data()), Sent(In(in.data() + in.size())));
-    std::same_as<std::ranges::in_out_result<In, Out>> decltype(auto) ret =
-        std::ranges::move(range, Out(out.data()));
+    std::same_as<std::ranges::in_out_result<In, Out>> decltype(auto) ret = std::ranges::move(range, Out(out.data()));
     assert(in == out);
     assert(base(ret.in) == in.data() + in.size());
     assert(base(ret.out) == out.data() + out.size());
@@ -84,16 +84,16 @@ constexpr void test(std::array<int, N> in) {
 template <class InContainer, class OutContainer, class In, class Out, class Sent = In>
 constexpr void test_containers() {
   {
-    InContainer in {1, 2, 3, 4};
+    InContainer in{1, 2, 3, 4};
     OutContainer out(4);
     std::same_as<std::ranges::in_out_result<In, Out>> auto ret =
-      std::ranges::move(In(in.begin()), Sent(In(in.end())), Out(out.begin()));
+        std::ranges::move(In(in.begin()), Sent(In(in.end())), Out(out.begin()));
     assert(std::ranges::equal(in, out));
     assert(base(ret.in) == in.end());
     assert(base(ret.out) == out.end());
   }
   {
-    InContainer in {1, 2, 3, 4};
+    InContainer in{1, 2, 3, 4};
     OutContainer out(4);
     auto range = std::ranges::subrange(In(in.begin()), Sent(In(in.end())));
     std::same_as<std::ranges::in_out_result<In, Out>> auto ret = std::ranges::move(range, Out(out.begin()));
@@ -165,22 +165,51 @@ constexpr void test_proxy_in_iterators() {
 }
 
 struct IteratorWithMoveIter {
-  using value_type = int;
-  using difference_type = int;
+  using value_type                = int;
+  using difference_type           = int;
   explicit IteratorWithMoveIter() = default;
   int* ptr;
   constexpr IteratorWithMoveIter(int* ptr_) : ptr(ptr_) {}
 
   constexpr int& operator*() const; // iterator with iter_move should not be dereferenced
 
-  constexpr Iterato...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/121109


More information about the libcxx-commits mailing list