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

[Peng Liu via libcxx-commits]

================
@@ -0,0 +1,608 @@
+// -*- 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 <algorithm>
+#include <cstddef>
+#include <iterator>
+#include <ranges> // for std::from_range
+#include <string>
+#include <type_traits>
+#include <vector>
+
+#include "benchmark/benchmark.h"
+#include "test_iterators.h"
+#include "test_macros.h"
+#include "../GenerateInput.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);
+
+  for (auto _ : st) {
+    Container c(size); // we assume the destructor doesn't dominate the benchmark
+    DoNotOptimizeData(c);
+  }
+}
+
+template <class Container, class Generator>
+void BM_ctor_size_value(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  ValueType value = gen();
+  benchmark::DoNotOptimize(value);
+
+  for (auto _ : st) {
+    Container c(size, value); // we assume the destructor doesn't dominate the benchmark
+    DoNotOptimizeData(c);
+  }
+}
+
+template <class Container, class Generator>
+void BM_ctor_iter_iter(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  const auto begin = in.begin();
+  const auto end   = in.end();
+  benchmark::DoNotOptimize(in);
+
+  for (auto _ : st) {
+    Container c(begin, end); // we assume the destructor doesn't dominate the benchmark
+    DoNotOptimizeData(c);
+  }
+}
+
+#if TEST_STD_VER >= 23
+template <class Container, class Generator>
+void BM_ctor_from_range(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const auto size = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  benchmark::DoNotOptimize(in);
+
+  for (auto _ : st) {
+    Container c(std::from_range, in); // we assume the destructor doesn't dominate the benchmark
+    DoNotOptimizeData(c);
+  }
+}
+#endif
+
+template <class Container, class Generator>
+void BM_ctor_copy(benchmark::State& st, Generator gen) {
+  auto size = st.range(0);
+  Container in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+
+  for (auto _ : st) {
+    Container c(in); // we assume the destructor doesn't dominate the benchmark
+    DoNotOptimizeData(c);
+    DoNotOptimizeData(in);
+  }
+}
+
+template <class Container, class Generator>
+void BM_assignment(benchmark::State& st, Generator gen) {
+  auto size = st.range(0);
+  Container in1, in2;
+  std::generate_n(std::back_inserter(in1), size, gen);
+  std::generate_n(std::back_inserter(in2), size, gen);
+  DoNotOptimizeData(in1);
+  DoNotOptimizeData(in2);
+
+  // Assign from one of two containers in succession to avoid
+  // hitting a self-assignment corner-case
+  Container c(in1);
+  bool toggle = false;
+  for (auto _ : st) {
+    c      = toggle ? in1 : in2;
+    toggle = !toggle;
+    DoNotOptimizeData(c);
+    DoNotOptimizeData(in1);
+    DoNotOptimizeData(in2);
+  }
+}
+
+// Benchmark Container::assign(input-iter, input-iter) when the container already contains
+// the same number of elements that we're assigning. The intent is to check whether the
+// implementation basically creates a new container from scratch or manages to reuse the
+// pre-existing storage.
+template <typename Container, class Generator>
+void BM_assign_input_iter_full(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  auto size       = st.range(0);
+  std::vector<ValueType> in1, in2;
+  std::generate_n(std::back_inserter(in1), size, gen);
+  std::generate_n(std::back_inserter(in2), size, gen);
+  DoNotOptimizeData(in1);
+  DoNotOptimizeData(in2);
+
+  Container c(in1.begin(), in1.end());
+  bool toggle = false;
+  for (auto _ : st) {
+    std::vector<ValueType>& in = toggle ? in1 : in2;
+    auto first                 = in.data();
+    auto last                  = in.data() + in.size();
+    c.assign(cpp17_input_iterator(first), cpp17_input_iterator(last));
+    toggle = !toggle;
+    DoNotOptimizeData(c);
+  }
+}
+
+template <class Container, class Generator>
+void BM_insert_begin(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const int size  = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+
+  Container c(in.begin(), in.end());
+  DoNotOptimizeData(c);
+
+  ValueType value = gen();
+  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, class Generator>
+  requires std::random_access_iterator<typename Container::iterator>
+void BM_insert_middle(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const int size  = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+
+  Container c(in.begin(), in.end());
+  DoNotOptimizeData(c);
+
+  ValueType value = gen();
+  benchmark::DoNotOptimize(value);
+
+  for (auto _ : st) {
+    auto mid = c.begin() + (size / 2); // requires random-access iterators in order to make sense
+    c.insert(mid, value);
+    DoNotOptimizeData(c);
+
+    c.erase(c.end() - 1); // avoid growing indefinitely
+  }
+}
+
+// Insert at the start of a vector in a scenario where the vector already
+// has enough capacity to hold all the elements we are inserting.
+template <class Container, class Generator>
+void BM_insert_begin_input_iter_with_reserve_no_realloc(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const int size  = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+  auto first = in.data();
+  auto last  = in.data() + in.size();
+
+  const int small = 100; // arbitrary
+  Container c;
+  c.reserve(size + small); // ensure no reallocation
+  std::generate_n(std::back_inserter(c), small, gen);
+
+  for (auto _ : st) {
+    c.insert(c.begin(), cpp17_input_iterator(first), cpp17_input_iterator(last));
+    DoNotOptimizeData(c);
+
+    st.PauseTiming();
+    c.erase(c.begin() + small, c.end()); // avoid growing indefinitely
+    st.ResumeTiming();
+  }
+}
+
+// Insert at the start of a vector in a scenario where the vector already
+// has almost enough capacity to hold all the elements we are inserting,
+// but does need to reallocate.
+template <class Container, class Generator>
+void BM_insert_begin_input_iter_with_reserve_almost_no_realloc(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const int size  = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+  auto first = in.data();
+  auto last  = in.data() + in.size();
+
+  const int overflow = size / 10; // 10% of elements won't fit in the vector when we insert
+  Container c;
+  c.reserve(size);
+  std::generate_n(std::back_inserter(c), overflow, gen);
+
+  for (auto _ : st) {
+    c.insert(c.begin(), cpp17_input_iterator(first), cpp17_input_iterator(last));
+    DoNotOptimizeData(c);
+
+    st.PauseTiming();
+    c.erase(c.begin() + overflow, c.end()); // avoid growing indefinitely
+    st.ResumeTiming();
+  }
+}
+
+// Insert at the start of a vector in a scenario where the vector can fit a few
+// more elements, but needs to reallocate almost immediately to fit the remaining
+// elements.
+template <class Container, class Generator>
+void BM_insert_begin_input_iter_with_reserve_near_full(benchmark::State& st, Generator gen) {
+  using ValueType = typename Container::value_type;
+  const int size  = st.range(0);
+  std::vector<ValueType> in;
+  std::generate_n(std::back_inserter(in), size, gen);
+  DoNotOptimizeData(in);
+  auto first = in.data();
+  auto last  = in.data() + in.size();
+
+  const int overflow = 9 * (size / 10); // 90% of elements won't fit in the vector when we insert
+  Container c;
+  c.reserve(size);
+  std::generate_n(std::back_inserter(c), overflow, gen);
+
+  for (auto _ : st) {
+    c.insert(c.begin(), cpp17_input_iterator(first), cpp17_input_iterator(last));
+    DoNotOptimizeData(c);
+
+    st.PauseTiming();
+    c.erase(c.begin() + overflow, c.end()); // avoid growing indefinitely
+    st.ResumeTiming();
+  }
----------------
winner245 wrote:

Oops! You are correct. I mistakenly referred to the copy-assignment operator when it’s actually the move-assignment operator being used. Given this clarification, the current tests LGTM as is. Sorry for my confusion.

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