[libcxx-commits] [libcxx] [libc++] Add benchmarks for copy algorithms (PR #127328)

[Nikolas Klauser via libcxx-commits]

================
@@ -0,0 +1,87 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+
+#include <algorithm>
+#include <deque>
+#include <iterator>
+#include <list>
+#include <string>
+#include <vector>
+
+#include "benchmark/benchmark.h"
+#include "../../GenerateInput.h"
+#include "test_macros.h"
+
+template <class Container, class Operation>
+void bm_general(std::string operation_name, Operation copy) {
+  auto bench = [copy](auto& st) {
+    auto const size = st.range(0);
+    using ValueType = typename Container::value_type;
+    Container c;
+    std::generate_n(std::back_inserter(c), size, [] { return Generate<ValueType>::random(); });
+
+    std::vector<ValueType> out(size);
+
+    for ([[maybe_unused]] auto _ : st) {
+      auto result = copy(c.begin(), c.end(), out.begin());
+      benchmark::DoNotOptimize(result);
+      benchmark::DoNotOptimize(out);
+      benchmark::DoNotOptimize(c);
+      benchmark::ClobberMemory();
+    }
+  };
+  benchmark::RegisterBenchmark(operation_name, bench)->Range(8, 1 << 20);
+}
+
+template <bool Aligned, class Operation>
+static void bm_vector_bool(std::string operation_name, Operation copy) {
+  auto bench = [copy](auto& st) {
+    auto n = st.range();
+    std::vector<bool> in(n, true);
+    std::vector<bool> out(Aligned ? n : n + 8);
+    benchmark::DoNotOptimize(&in);
+    auto first = in.begin();
+    auto last  = in.end();
+    auto dst   = Aligned ? out.begin() : out.begin() + 4;
+    for ([[maybe_unused]] auto _ : st) {
+      auto result = copy(first, last, dst);
+      benchmark::DoNotOptimize(result);
+      benchmark::DoNotOptimize(out);
+      benchmark::ClobberMemory();
+    }
+  };
+  benchmark::RegisterBenchmark(operation_name, bench)->Range(64, 1 << 20);
+}
+
+int main(int argc, char** argv) {
+  auto std_copy    = [](auto first, auto last, auto out) { return std::copy(first, last, out); };
+  auto ranges_copy = [](auto first, auto last, auto out) { return std::ranges::copy(first, last, out); };
+
+  // std::copy
+  bm_general<std::vector<int>>("std::copy(vector<int>)", std_copy);
+  bm_general<std::deque<int>>("std::copy(deque<int>)", std_copy);
+  bm_general<std::list<int>>("std::copy(list<int>)", std_copy);
+  bm_vector_bool<true>("std::copy(vector<bool>) (aligned)", std_copy);
+  bm_vector_bool<false>("std::copy(vector<bool>) (unaligned)", std_copy);
+
+  // ranges::copy
+  bm_general<std::vector<int>>("ranges::copy(vector<int>)", ranges_copy);
+  bm_general<std::deque<int>>("ranges::copy(deque<int>)", ranges_copy);
+  bm_general<std::list<int>>("ranges::copy(list<int>)", ranges_copy);
+#if TEST_STD_VER >= 23 // vector<bool>::iterator is not an output_iterator before C++23
+  bm_vector_bool<true>("ranges::copy(vector<bool>) (aligned)", ranges_copy);
+  bm_vector_bool<false>("ranges::copy(vector<bool>) (unaligned)", ranges_copy);
+#endif
+
+  benchmark::Initialize(&argc, argv);
+  benchmark::RunSpecifiedBenchmarks();
+  benchmark::Shutdown();
----------------
philnik777 wrote:

Looking at this more, I think the main problem is actually that registering the benchmarks isn't close to their definition, making it hard to understand what stuff runs which benchmarks. I think it would be way better if we could refactor it to something like
```c++
void run_benchmarks() {
  register_benchmark("BenchmarkName", [](benchmark::State& state) { ... });

  auto some_generic_benchmark = []<class T>(benchmark::State& state) { ... };
  register_benchmark("BenchmarkName", template_args<int>{}, some_generic_benchmark);

  <more benchmarks>
}
```

I think we could do that by having some header with a bit of boilerplate stuff, e.g.

```c++

template <class Func>
auto register_benchmark(std::string_view name, Func benchmark) {
  return benchmark::RegisterBenchmark(name, benchmark);
}

template <class... Args>
struct template_args {};

template <class Func, class... Args>
auto register_benchmark(std::string_view name, template_args<Args...>, Func benchmark) {
  return register_benchmark(name, [](benchmark::State& state) { benchmark::operator()<Args...>(state); });
}

// There are probably more useful tools we could add here

void run_benchmarks();

int main() {
  <whatever>
  run_benchmarks();
  <whatever>
}

```
I don't know whether that actually works (probably not, since I wrote this down without checking anything), but something similar would be a nice readability improvement I think.

https://github.com/llvm/llvm-project/pull/127328