[libc++] Optimize std::find for segmented iterators (#67224)

```
--------------------------------------------------------------------------
Benchmark                                              old             new
--------------------------------------------------------------------------
bm_find<std::deque<char>>/1                        6.06 ns         10.6 ns
bm_find<std::deque<char>>/2                        15.5 ns         10.6 ns
bm_find<std::deque<char>>/3                        19.0 ns         10.6 ns
bm_find<std::deque<char>>/4                        20.8 ns         10.6 ns
bm_find<std::deque<char>>/5                        22.0 ns         10.6 ns
bm_find<std::deque<char>>/6                        23.0 ns         10.5 ns
bm_find<std::deque<char>>/7                        24.8 ns         10.7 ns
bm_find<std::deque<char>>/8                        25.7 ns         10.6 ns
bm_find<std::deque<char>>/16                       28.3 ns         10.6 ns
bm_find<std::deque<char>>/64                       44.2 ns         27.0 ns
bm_find<std::deque<char>>/512                       133 ns         37.6 ns
bm_find<std::deque<char>>/4096                      867 ns         53.1 ns
bm_find<std::deque<char>>/32768                    6838 ns          160 ns
bm_find<std::deque<char>>/262144                  52897 ns         1495 ns
bm_find<std::deque<char>>/1048576                215621 ns         6077 ns
bm_find<std::deque<short>>/1                       6.03 ns         6.28 ns
bm_find<std::deque<short>>/2                       15.8 ns         15.8 ns
bm_find<std::deque<short>>/3                       20.5 ns         20.3 ns
bm_find<std::deque<short>>/4                       21.0 ns         21.0 ns
bm_find<std::deque<short>>/5                       23.0 ns         22.1 ns
bm_find<std::deque<short>>/6                       22.6 ns         23.0 ns
bm_find<std::deque<short>>/7                       23.4 ns         23.7 ns
bm_find<std::deque<short>>/8                       24.4 ns         24.9 ns
bm_find<std::deque<short>>/16                      26.6 ns         27.2 ns
bm_find<std::deque<short>>/64                      43.2 ns         40.9 ns
bm_find<std::deque<short>>/512                      124 ns         90.7 ns
bm_find<std::deque<short>>/4096                     845 ns          525 ns
bm_find<std::deque<short>>/32768                   7273 ns         3194 ns
bm_find<std::deque<short>>/262144                 53710 ns        24385 ns
bm_find<std::deque<short>>/1048576               216086 ns        96195 ns
bm_find<std::deque<int>>/1                         6.03 ns         10.3 ns
bm_find<std::deque<int>>/2                         15.6 ns         10.3 ns
bm_find<std::deque<int>>/3                         19.1 ns         10.3 ns
bm_find<std::deque<int>>/4                         22.3 ns         10.3 ns
bm_find<std::deque<int>>/5                         23.5 ns         10.4 ns
bm_find<std::deque<int>>/6                         23.1 ns         10.3 ns
bm_find<std::deque<int>>/7                         23.7 ns         10.2 ns
bm_find<std::deque<int>>/8                         24.5 ns         10.2 ns
bm_find<std::deque<int>>/16                        27.9 ns         26.6 ns
bm_find<std::deque<int>>/64                        42.6 ns         32.2 ns
bm_find<std::deque<int>>/512                        123 ns         43.0 ns
bm_find<std::deque<int>>/4096                       874 ns         93.5 ns
bm_find<std::deque<int>>/32768                     7031 ns          751 ns
bm_find<std::deque<int>>/262144                   57723 ns         6169 ns
bm_find<std::deque<int>>/1048576                 230867 ns        35851 ns
bm_ranges_find<std::deque<char>>/1                 5.97 ns         10.6 ns
bm_ranges_find<std::deque<char>>/2                 16.0 ns         10.5 ns
bm_ranges_find<std::deque<char>>/3                 19.5 ns         10.5 ns
bm_ranges_find<std::deque<char>>/4                 21.1 ns         10.6 ns
bm_ranges_find<std::deque<char>>/5                 22.8 ns         10.5 ns
bm_ranges_find<std::deque<char>>/6                 22.8 ns         10.6 ns
bm_ranges_find<std::deque<char>>/7                 23.4 ns         10.8 ns
bm_ranges_find<std::deque<char>>/8                 24.1 ns         10.5 ns
bm_ranges_find<std::deque<char>>/16                26.9 ns         10.6 ns
bm_ranges_find<std::deque<char>>/64                50.2 ns         27.2 ns
bm_ranges_find<std::deque<char>>/512                126 ns         38.3 ns
bm_ranges_find<std::deque<char>>/4096               868 ns         53.8 ns
bm_ranges_find<std::deque<char>>/32768             6695 ns          161 ns
bm_ranges_find<std::deque<char>>/262144           54411 ns         1497 ns
bm_ranges_find<std::deque<char>>/1048576         241699 ns         6042 ns
bm_ranges_find<std::deque<short>>/1                6.39 ns         6.31 ns
bm_ranges_find<std::deque<short>>/2                15.8 ns         15.9 ns
bm_ranges_find<std::deque<short>>/3                19.0 ns         19.8 ns
bm_ranges_find<std::deque<short>>/4                20.8 ns         20.9 ns
bm_ranges_find<std::deque<short>>/5                21.8 ns         22.1 ns
bm_ranges_find<std::deque<short>>/6                23.0 ns         23.0 ns
bm_ranges_find<std::deque<short>>/7                23.2 ns         23.9 ns
bm_ranges_find<std::deque<short>>/8                23.7 ns         24.4 ns
bm_ranges_find<std::deque<short>>/16               26.6 ns         26.8 ns
bm_ranges_find<std::deque<short>>/64               43.4 ns         39.7 ns
bm_ranges_find<std::deque<short>>/512               131 ns         90.5 ns
bm_ranges_find<std::deque<short>>/4096              851 ns          523 ns
bm_ranges_find<std::deque<short>>/32768            7370 ns         3166 ns
bm_ranges_find<std::deque<short>>/262144          60778 ns        24814 ns
bm_ranges_find<std::deque<short>>/1048576        229288 ns        99273 ns
bm_ranges_find<std::deque<int>>/1                  6.43 ns         10.2 ns
bm_ranges_find<std::deque<int>>/2                  16.6 ns         10.2 ns
bm_ranges_find<std::deque<int>>/3                  19.6 ns         10.2 ns
bm_ranges_find<std::deque<int>>/4                  21.0 ns         10.2 ns
bm_ranges_find<std::deque<int>>/5                  21.9 ns         10.4 ns
bm_ranges_find<std::deque<int>>/6                  22.7 ns         10.2 ns
bm_ranges_find<std::deque<int>>/7                  23.9 ns         10.2 ns
bm_ranges_find<std::deque<int>>/8                  23.8 ns         10.2 ns
bm_ranges_find<std::deque<int>>/16                 27.2 ns         27.1 ns
bm_ranges_find<std::deque<int>>/64                 42.4 ns         32.4 ns
bm_ranges_find<std::deque<int>>/512                 122 ns         43.0 ns
bm_ranges_find<std::deque<int>>/4096                895 ns         93.7 ns
bm_ranges_find<std::deque<int>>/32768              6890 ns          756 ns
bm_ranges_find<std::deque<int>>/262144            54025 ns         6102 ns
bm_ranges_find<std::deque<int>>/1048576          221558 ns        32783 ns
```

2 files changed, 120 insertions, 0 deletions

diff --git a/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/find.pass.cpp b/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/find.pass.cpp
index 3141f14..0afc573 100644
--- a/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/find.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/find.pass.cpp
@@ -19,6 +19,7 @@
 
 #include <algorithm>
 #include <cassert>
+#include <deque>
 #include <vector>
 #include <type_traits>
 
@@ -115,6 +116,52 @@ struct TestTypes {
   }
 };
 
+void test_deque() {
+  { // empty deque
+    std::deque<int> data;
+    assert(std::find(data.begin(), data.end(), 4) == data.end());
+  }
+
+  { // single element - match
+    std::deque<int> data;
+    data.push_back(4);
+    assert(std::find(data.begin(), data.end(), 4) == data.begin());
+  }
+
+  { // single element - no match
+    std::deque<int> data;
+    data.push_back(3);
+    assert(std::find(data.begin(), data.end(), 4) == data.end());
+  }
+
+  // many elements
+  int sizes[] = {2, 3, 1023, 1024, 1025, 2047, 2048, 2049};
+  for (auto size : sizes) {
+    { // last element match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      data[size - 1] = 4;
+      assert(std::find(data.begin(), data.end(), 4) == data.end() - 1);
+    }
+
+    { // second-last element match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      data[size - 2] = 4;
+      assert(std::find(data.begin(), data.end(), 4) == data.end() - 2);
+    }
+
+    { // no match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      assert(std::find(data.begin(), data.end(), 4) == data.end());
+    }
+  }
+}
+
 TEST_CONSTEXPR_CXX20 bool test() {
   types::for_each(types::integer_types(), TestTypes<char>());
   types::for_each(types::integer_types(), TestTypes<int>());
@@ -124,10 +171,21 @@ TEST_CONSTEXPR_CXX20 bool test() {
   Test<TriviallyComparable<wchar_t>, TriviallyComparable<wchar_t>>().operator()<TriviallyComparable<wchar_t>*>();
 #endif
 
+  // TODO: Remove the `_LIBCPP_ENABLE_EXPERIMENTAL` check once we have the FTM guarded or views::join isn't
+  // experimental anymore
+#if TEST_STD_VER >= 20 && (!defined(_LIBCPP_VERSION) || defined(_LIBCPP_ENABLE_EXPERIMENTAL))
+  {
+    std::vector<std::vector<int>> vec = {{1, 2, 3}, {4, 5, 6}, {7, 8, 9}};
+    auto view                         = vec | std::views::join;
+    assert(std::find(view.begin(), view.end(), 4) == std::next(view.begin(), 3));
+  }
+#endif
+
   return true;
 }
 
 int main(int, char**) {
+  test_deque();
   test();
 #if TEST_STD_VER >= 20
   static_assert(test());
diff --git a/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/ranges.find.pass.cpp b/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/ranges.find.pass.cpp
index dbb5874..4ae049c 100644
--- a/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/ranges.find.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.nonmodifying/alg.find/ranges.find.pass.cpp
@@ -26,6 +26,7 @@
 #include <algorithm>
 #include <array>
 #include <cassert>
+#include <deque>
 #include <ranges>
 #include <vector>
 
@@ -130,6 +131,17 @@ constexpr bool test() {
                     });
                   });
 
+  // TODO: Remove the `_LIBCPP_ENABLE_EXPERIMENTAL` check once we have the FTM guarded or views::join isn't
+  // experimental anymore
+#if TEST_STD_VER >= 20 && (!defined(_LIBCPP_VERSION) || defined(_LIBCPP_ENABLE_EXPERIMENTAL))
+  {
+    std::vector<std::vector<int>> vec = {{1, 2, 3}, {4, 5, 6}, {7, 8, 9}};
+    auto view                         = vec | std::views::join;
+    assert(std::ranges::find(view.begin(), view.end(), 4) == std::next(view.begin(), 3));
+    assert(std::ranges::find(view, 4) == std::next(view.begin(), 3));
+  }
+#endif
+
   { // check that the first element is returned
     {
       struct S {
@@ -205,7 +217,57 @@ public:
   friend bool operator==(const Comparable& lhs, long long rhs) { return comparable_data[lhs.index_] == rhs; }
 };
 
+void test_deque() {
+  { // empty deque
+    std::deque<int> data;
+    assert(std::ranges::find(data, 4) == data.end());
+    assert(std::ranges::find(data.begin(), data.end(), 4) == data.end());
+  }
+
+  { // single element - match
+    std::deque<int> data = {4};
+    assert(std::ranges::find(data, 4) == data.begin());
+    assert(std::ranges::find(data.begin(), data.end(), 4) == data.begin());
+  }
+
+  { // single element - no match
+    std::deque<int> data = {3};
+    assert(std::ranges::find(data, 4) == data.end());
+    assert(std::ranges::find(data.begin(), data.end(), 4) == data.end());
+  }
+
+  // many elements
+  for (auto size : {2, 3, 1023, 1024, 1025, 2047, 2048, 2049}) {
+    { // last element match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      data[size - 1] = 4;
+      assert(std::ranges::find(data, 4) == data.end() - 1);
+      assert(std::ranges::find(data.begin(), data.end(), 4) == data.end() - 1);
+    }
+
+    { // second-last element match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      data[size - 2] = 4;
+      assert(std::ranges::find(data, 4) == data.end() - 2);
+      assert(std::ranges::find(data.begin(), data.end(), 4) == data.end() - 2);
+    }
+
+    { // no match
+      std::deque<int> data;
+      data.resize(size);
+      std::fill(data.begin(), data.end(), 3);
+      assert(std::ranges::find(data, 4) == data.end());
+      assert(std::ranges::find(data.begin(), data.end(), 4) == data.end());
+    }
+  }
+}
+
 int main(int, char**) {
+  test_deque();
   test();
   static_assert(test());