985c1a44f8
``` ----------------------------------------------------------------------------- Benchmark old new ----------------------------------------------------------------------------- bm_mismatch_two_range_overload<char>/1 0.941 ns 1.88 ns bm_mismatch_two_range_overload<char>/2 1.43 ns 2.15 ns bm_mismatch_two_range_overload<char>/3 1.95 ns 2.55 ns bm_mismatch_two_range_overload<char>/4 2.58 ns 2.90 ns bm_mismatch_two_range_overload<char>/5 3.75 ns 3.31 ns bm_mismatch_two_range_overload<char>/6 5.00 ns 3.83 ns bm_mismatch_two_range_overload<char>/7 5.59 ns 4.35 ns bm_mismatch_two_range_overload<char>/8 6.37 ns 4.84 ns bm_mismatch_two_range_overload<char>/16 11.8 ns 6.72 ns bm_mismatch_two_range_overload<char>/64 45.5 ns 2.59 ns bm_mismatch_two_range_overload<char>/512 366 ns 12.6 ns bm_mismatch_two_range_overload<char>/4096 2890 ns 91.6 ns bm_mismatch_two_range_overload<char>/32768 23038 ns 758 ns bm_mismatch_two_range_overload<char>/262144 142813 ns 6573 ns bm_mismatch_two_range_overload<char>/1048576 366679 ns 26710 ns bm_mismatch_two_range_overload<short>/1 0.934 ns 1.88 ns bm_mismatch_two_range_overload<short>/2 1.30 ns 2.58 ns bm_mismatch_two_range_overload<short>/3 1.76 ns 3.28 ns bm_mismatch_two_range_overload<short>/4 2.24 ns 3.98 ns bm_mismatch_two_range_overload<short>/5 2.80 ns 4.92 ns bm_mismatch_two_range_overload<short>/6 3.58 ns 6.01 ns bm_mismatch_two_range_overload<short>/7 4.29 ns 7.03 ns bm_mismatch_two_range_overload<short>/8 4.67 ns 7.39 ns bm_mismatch_two_range_overload<short>/16 9.86 ns 13.1 ns bm_mismatch_two_range_overload<short>/64 38.9 ns 4.55 ns bm_mismatch_two_range_overload<short>/512 348 ns 27.7 ns bm_mismatch_two_range_overload<short>/4096 2881 ns 225 ns bm_mismatch_two_range_overload<short>/32768 23111 ns 1715 ns bm_mismatch_two_range_overload<short>/262144 184846 ns 14416 ns bm_mismatch_two_range_overload<short>/1048576 742885 ns 57264 ns bm_mismatch_two_range_overload<int>/1 0.838 ns 1.19 ns bm_mismatch_two_range_overload<int>/2 1.19 ns 1.65 ns bm_mismatch_two_range_overload<int>/3 1.83 ns 2.06 ns bm_mismatch_two_range_overload<int>/4 2.38 ns 2.42 ns bm_mismatch_two_range_overload<int>/5 3.60 ns 2.47 ns bm_mismatch_two_range_overload<int>/6 3.68 ns 3.05 ns bm_mismatch_two_range_overload<int>/7 4.32 ns 3.36 ns bm_mismatch_two_range_overload<int>/8 5.18 ns 3.58 ns bm_mismatch_two_range_overload<int>/16 10.6 ns 2.84 ns bm_mismatch_two_range_overload<int>/64 39.0 ns 7.78 ns bm_mismatch_two_range_overload<int>/512 247 ns 53.9 ns bm_mismatch_two_range_overload<int>/4096 1927 ns 429 ns bm_mismatch_two_range_overload<int>/32768 15569 ns 3393 ns bm_mismatch_two_range_overload<int>/262144 125413 ns 28504 ns bm_mismatch_two_range_overload<int>/1048576 504549 ns 112729 ns ```
57 lines
2.0 KiB
C++
57 lines
2.0 KiB
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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <algorithm>
|
|
#include <benchmark/benchmark.h>
|
|
#include <random>
|
|
|
|
void BenchmarkSizes(benchmark::internal::Benchmark* Benchmark) {
|
|
Benchmark->DenseRange(1, 8);
|
|
for (size_t i = 16; i != 1 << 20; i *= 2) {
|
|
Benchmark->Arg(i - 1);
|
|
Benchmark->Arg(i);
|
|
Benchmark->Arg(i + 1);
|
|
}
|
|
}
|
|
|
|
// TODO: Look into benchmarking aligned and unaligned memory explicitly
|
|
// (currently things happen to be aligned because they are malloced that way)
|
|
template <class T>
|
|
static void bm_mismatch(benchmark::State& state) {
|
|
std::vector<T> vec1(state.range(), '1');
|
|
std::vector<T> vec2(state.range(), '1');
|
|
std::mt19937_64 rng(std::random_device{}());
|
|
|
|
vec1.back() = '2';
|
|
for (auto _ : state) {
|
|
benchmark::DoNotOptimize(vec1);
|
|
benchmark::DoNotOptimize(std::mismatch(vec1.begin(), vec1.end(), vec2.begin()));
|
|
}
|
|
}
|
|
BENCHMARK(bm_mismatch<char>)->Apply(BenchmarkSizes);
|
|
BENCHMARK(bm_mismatch<short>)->Apply(BenchmarkSizes);
|
|
BENCHMARK(bm_mismatch<int>)->Apply(BenchmarkSizes);
|
|
|
|
template <class T>
|
|
static void bm_mismatch_two_range_overload(benchmark::State& state) {
|
|
std::vector<T> vec1(state.range(), '1');
|
|
std::vector<T> vec2(state.range(), '1');
|
|
std::mt19937_64 rng(std::random_device{}());
|
|
|
|
vec1.back() = '2';
|
|
for (auto _ : state) {
|
|
benchmark::DoNotOptimize(vec1);
|
|
benchmark::DoNotOptimize(std::mismatch(vec1.begin(), vec1.end(), vec2.begin(), vec2.end()));
|
|
}
|
|
}
|
|
BENCHMARK(bm_mismatch_two_range_overload<char>)->DenseRange(1, 8)->Range(16, 1 << 20);
|
|
BENCHMARK(bm_mismatch_two_range_overload<short>)->DenseRange(1, 8)->Range(16, 1 << 20);
|
|
BENCHMARK(bm_mismatch_two_range_overload<int>)->DenseRange(1, 8)->Range(16, 1 << 20);
|
|
|
|
BENCHMARK_MAIN();
|