[libcxx-commits] [libcxx] [libc++][test] add benchmarks for `std::atomic::wait` (PR #70571)

[Louis Dionne via libcxx-commits]

================
@@ -0,0 +1,163 @@
+//===----------------------------------------------------------------------===//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include <atomic>
+#include <numeric>
+#include <thread>
+
+#include "benchmark/benchmark.h"
+#include "make_test_thread.h"
+
+#include <iostream>
+
+using namespace std::chrono_literals;
+
+void BM_atomic_wait_one_thread_one_atomic_wait(benchmark::State& state) {
+  std::atomic<std::uint64_t> a;
+  auto thread_func = [&](std::stop_token st) {
+    while (!st.stop_requested()) {
+      a.fetch_add(1, std::memory_order_relaxed);
+      a.notify_all();
+    }
+  };
+
+  std::uint64_t total_loop_test_param = state.range(0);
+
+  auto thread = support::make_test_jthread(thread_func);
+
+  for (auto _ : state) {
+    for (std::uint64_t i = 0; i < total_loop_test_param; ++i) {
+      auto old = a.load(std::memory_order_relaxed);
+      a.wait(old);
+    }
+  }
+}
+BENCHMARK(BM_atomic_wait_one_thread_one_atomic_wait)->RangeMultiplier(2)->Range(1 << 10, 1 << 24);
+
+void BM_atomic_wait_multi_thread_one_atomic_wait(benchmark::State& state) {
+  std::atomic<std::uint64_t> a;
+  auto notify_func = [&](std::stop_token st) {
+    while (!st.stop_requested()) {
+      a.fetch_add(1, std::memory_order_relaxed);
+      a.notify_all();
+    }
+  };
+
+  std::uint64_t total_loop_test_param = state.range(0);
+  constexpr auto num_waiting_threads  = 15;
+  std::vector<std::jthread> wait_threads;
+  wait_threads.reserve(num_waiting_threads);
+
+  auto notify_thread = support::make_test_jthread(notify_func);
+
+  std::atomic<std::uint64_t> start_flag = 0;
+  std::atomic<std::uint64_t> done_count = 0;
+  auto wait_func                        = [&a, &start_flag, &done_count, total_loop_test_param](std::stop_token st) {
+    auto old_start = 0;
+    while (!st.stop_requested()) {
+      start_flag.wait(old_start);
+      old_start = start_flag.load();
+      for (std::uint64_t i = 0; i < total_loop_test_param; ++i) {
+        auto old = a.load(std::memory_order_relaxed);
+        a.wait(old);
+      }
+      done_count.fetch_add(1);
+    }
+  };
+
+  for (size_t i = 0; i < num_waiting_threads; ++i) {
+    wait_threads.emplace_back(support::make_test_jthread(wait_func));
+  }
+
+  for (auto _ : state) {
+    done_count = 0;
+    start_flag.fetch_add(1);
+    start_flag.notify_all();
+    while (done_count < num_waiting_threads) {
+      std::this_thread::yield();
+    }
+  }
+  for (auto& t : wait_threads) {
+    t.request_stop();
+  }
+  start_flag.fetch_add(1);
+  start_flag.notify_all();
+  for (auto& t : wait_threads) {
+    t.join();
+  }
+}
+BENCHMARK(BM_atomic_wait_multi_thread_one_atomic_wait)->RangeMultiplier(2)->Range(1 << 10, 1 << 20);
+
+// hardware_destructive_interference_size not implemented yet for clang
+// alignas 128 to cover the cases for x86 and apple arm to prevent false sharing
+// from the test itself
+struct alignas(128) Atomic {
+  std::atomic<std::uint64_t> at{0};
+};
----------------
ldionne wrote:

I think this was a temporary test, it probably shouldn't be in the base benchmark.

https://github.com/llvm/llvm-project/pull/70571