[libcxx-commits] [libcxx] [libc++][ranges] optimize the performance of `ranges::starts_with` (PR #84570)

[Konstantin Varlamov via libcxx-commits]

================
@@ -0,0 +1,106 @@
+//===----------------------------------------------------------------------===//
+//
+// 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 <algorithm>
+#include <benchmark/benchmark.h>
+#include <vector>
+
+#include "test_iterators.h"
+
+static void bm_starts_with_contiguous_iter_with_memcmp_optimization(benchmark::State& state) {
+  std::vector<int> a(state.range(), 1);
+  std::vector<int> p(state.range(), 1);
+
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(a);
+    benchmark::DoNotOptimize(p);
+
+    auto begin1 = contiguous_iterator(a.data());
+    auto end1   = contiguous_iterator(a.data() + a.size());
+    auto begin2 = contiguous_iterator(p.data());
+    auto end2   = contiguous_iterator(p.data() + p.size());
+
+    benchmark::DoNotOptimize(std::ranges::starts_with(begin1, end1, begin2, end2));
+  }
+}
+BENCHMARK(bm_starts_with_contiguous_iter_with_memcmp_optimization)->RangeMultiplier(16)->Range(16, 16 << 20);
+
+static void bm_starts_with_contiguous_iter(benchmark::State& state) {
+  std::vector<int> a(state.range(), 1);
+  std::vector<int> p(state.range(), 1);
+
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(a);
+    benchmark::DoNotOptimize(p);
+
+    auto begin1 = contiguous_iterator(a.data());
+    auto end1   = contiguous_iterator(a.data() + a.size());
+    auto begin2 = contiguous_iterator(p.data());
+    auto end2   = contiguous_iterator(p.data() + p.size());
+
+    benchmark::DoNotOptimize(
+        std::ranges::starts_with(begin1, end1, begin2, end2, [](const int a, const int b) { return a == b; }));
----------------
var-const wrote:

Maybe comment to explain why we're using a lambda here/how this test is different from the `memcmp`-optimized one? Can be a very brief comment -- e.g.
> Using a custom comparator to make sure the `memcmp` optimization doesn't get invoked.

https://github.com/llvm/llvm-project/pull/84570