[libcxx-commits] [libcxx] [libc++] Refactor the sequence container benchmarks (PR #119763)

[Louis Dionne via libcxx-commits]

================
@@ -0,0 +1,510 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef TEST_BENCHMARKS_CONTAINERS_CONTAINER_BENCHMARKS_H
+#define TEST_BENCHMARKS_CONTAINERS_CONTAINER_BENCHMARKS_H
+
+#include <cstddef>
+#include <iterator>
+#include <ranges> // for std::from_range
+#include <string>
+#include <vector>
+
+#include "benchmark/benchmark.h"
+#include "test_iterators.h"
+#include "test_macros.h"
+
+namespace ContainerBenchmarks {
+
+template <class Container>
+void DoNotOptimizeData(Container& c) {
+  if constexpr (requires { c.data(); }) {
+    benchmark::DoNotOptimize(c.data());
+  } else {
+    benchmark::DoNotOptimize(&c);
+  }
+}
+
+//
+// Sequence container operations
+//
+template <class Container>
+void BM_ctor_size(benchmark::State& st) {
+  auto size = st.range(0);
+  char buffer[sizeof(Container)];
+  for (auto _ : st) {
+    std::construct_at(reinterpret_cast<Container*>(buffer), size);
+    benchmark::DoNotOptimize(buffer);
+    st.PauseTiming();
+    std::destroy_at(reinterpret_cast<Container*>(buffer));
+    st.ResumeTiming();
+  }
+}
+
+template <class Container>
+void BM_ctor_size_value(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  ValueType value{};
+  benchmark::DoNotOptimize(value);
+  char buffer[sizeof(Container)];
+  for (auto _ : st) {
+    std::construct_at(reinterpret_cast<Container*>(buffer), size, value);
+    benchmark::DoNotOptimize(buffer);
+    st.PauseTiming();
+    std::destroy_at(reinterpret_cast<Container*>(buffer));
+    st.ResumeTiming();
+  }
+}
+
+template <class Container>
+void BM_ctor_iter_iter(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  std::vector<ValueType> in(size);
+  const auto begin = in.begin();
+  const auto end   = in.end();
+  benchmark::DoNotOptimize(in);
+  char buffer[sizeof(Container)];
+  for (auto _ : st) {
+    std::construct_at(reinterpret_cast<Container*>(buffer), begin, end);
+    benchmark::DoNotOptimize(buffer);
+    st.PauseTiming();
+    std::destroy_at(reinterpret_cast<Container*>(buffer));
+    st.ResumeTiming();
+  }
+}
+
+#if TEST_STD_VER >= 23
+template <class Container>
+void BM_ctor_from_range(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  std::vector<ValueType> in(size);
+  benchmark::DoNotOptimize(in);
+  char buffer[sizeof(Container)];
+  for (auto _ : st) {
+    std::construct_at(reinterpret_cast<Container*>(buffer), std::from_range, in);
+    benchmark::DoNotOptimize(buffer);
+    st.PauseTiming();
+    std::destroy_at(reinterpret_cast<Container*>(buffer));
+    st.ResumeTiming();
+  }
+}
+#endif
+
+template <class Container>
+void BM_ctor_copy(benchmark::State& st) {
+  auto size = st.range(0);
+  Container c(size);
+  char buffer[sizeof(Container)];
+  for (auto _ : st) {
+    std::construct_at(reinterpret_cast<Container*>(buffer), c);
+    benchmark::DoNotOptimize(buffer);
+    st.PauseTiming();
+    std::destroy_at(reinterpret_cast<Container*>(buffer));
+    st.ResumeTiming();
+  }
+}
+
+template <class Container>
+void BM_assignment(benchmark::State& st) {
+  auto size = st.range(0);
+  Container c1;
+  Container c2(size);
+  for (auto _ : st) {
+    c1 = c2;
+    DoNotOptimizeData(c1);
+    DoNotOptimizeData(c2);
+  }
+}
+
+template <typename Container>
+void BM_assign_inputiter(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  auto size       = st.range(0);
+  std::vector<ValueType> inputs(size);
+  Container c(inputs.begin(), inputs.end());
+  DoNotOptimizeData(c);
+  DoNotOptimizeData(inputs);
+  ValueType* first = inputs.data();
+  ValueType* last  = inputs.data() + inputs.size();
+
+  for (auto _ : st) {
+    c.assign(cpp17_input_iterator(first), cpp17_input_iterator(last));
+    benchmark::ClobberMemory();
+  }
+}
+
+template <class Container>
+void BM_insert_start(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const int count = st.range(0);
+  std::vector<ValueType> inputs(count);
+  Container c(inputs.begin(), inputs.end());
+  DoNotOptimizeData(c);
+
+  ValueType value{};
+  benchmark::DoNotOptimize(value);
+
+  for (auto _ : st) {
+    c.insert(c.begin(), value);
+    DoNotOptimizeData(c);
+
+    c.erase(std::prev(c.end())); // avoid growing indefinitely
+  }
+}
+
+template <class Container>
+  requires std::random_access_iterator<typename Container::iterator>
+void BM_insert_middle(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const int count = st.range(0);
+  std::vector<ValueType> inputs(count);
+  Container c(inputs.begin(), inputs.end());
+  DoNotOptimizeData(c);
+
+  ValueType value{};
+  benchmark::DoNotOptimize(value);
+
+  for (auto _ : st) {
+    auto mid = c.begin() + (count / 2); // requires random-access iterators in order to make sense
+    c.insert(mid, value);
+    DoNotOptimizeData(c);
+
+    c.erase(c.end() - 1); // avoid growing indefinitely
+  }
+}
+
+template <class Container>
+void BM_insert_input_iter_with_reserve_no_realloc(benchmark::State& st) {
+  using ValueType = typename Container::value_type;
+  const int count = st.range(0);
+  std::vector<ValueType> inputs(count);
+  const auto beg = cpp17_input_iterator(inputs.begin());
+  const auto end = cpp17_input_iterator(inputs.end());
+
+  auto size = 100; // arbitrary
+  Container c(size);
+  c.reserve(size + inputs.size()); // ensure no reallocation
+  for (auto _ : st) {
+    c.insert(c.begin(), beg, end);
+    DoNotOptimizeData(c);
+
+    st.PauseTiming();
+    c.erase(c.begin() + size, c.end()); // avoid growing indefinitely
+    st.ResumeTiming();
+  }
+}
+
+template <class Container>
+void BM_insert_input_iter_with_reserve_half_filled(benchmark::State& st) {
----------------
ldionne wrote:

My version of the benchmark does insert `count / 2` elements when it constructs the vector in the first place:

```c++
Container c(count / 2);
```

I then reserve space for `count` elements, which ensures the vector has `count / 2` elements at the front but enough capacity for `count` elements total. That is, unless I've made a big mistake.

In contrast, your benchmark was reserving and then assigning, which will not take advantage of the additional capacity. That is because assignment will replace the underlying buffer, in this case effectively shrinking the vector. Do you agree?

If that's the case, then I think perhaps this version of the benchmark is more correct than the previous one, but I'd like to know your thoughts on this.

https://github.com/llvm/llvm-project/pull/119763