I've put some work into the Google Benchmark library in order to make it easier to benchmark libc++. These changes have already been upstreamed into Google Benchmark and this patch applies the changes to the in-tree version. The main improvement in the addition of a 'compare_bench.py' script which makes it very easy to compare benchmarks. For example to compare the native STL to libc++ you would run: `$ compare_bench.py ./util_smartptr.native.out ./util_smartptr.libcxx.out` And the output would look like: RUNNING: ./util_smartptr.native.out Benchmark Time CPU Iterations ---------------------------------------------------------------- BM_SharedPtrCreateDestroy 62 ns 62 ns 10937500 BM_SharedPtrIncDecRef 31 ns 31 ns 23972603 BM_WeakPtrIncDecRef 28 ns 28 ns 23648649 RUNNING: ./util_smartptr.libcxx.out Benchmark Time CPU Iterations ---------------------------------------------------------------- BM_SharedPtrCreateDestroy 46 ns 46 ns 14957265 BM_SharedPtrIncDecRef 31 ns 31 ns 22435897 BM_WeakPtrIncDecRef 34 ns 34 ns 21084337 Comparing ./util_smartptr.native.out to ./util_smartptr.libcxx.out Benchmark Time CPU ----------------------------------------------------- BM_SharedPtrCreateDestroy -0.26 -0.26 BM_SharedPtrIncDecRef +0.00 +0.00 BM_WeakPtrIncDecRef +0.21 +0.21 git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@278147 91177308-0d34-0410-b5e6-96231b3b80d8
103 lines
2.6 KiB
C++
103 lines
2.6 KiB
C++
|
|
#include "benchmark/benchmark_api.h"
|
|
|
|
#define BASIC_BENCHMARK_TEST(x) \
|
|
BENCHMARK(x)->Arg(8)->Arg(512)->Arg(8192)
|
|
|
|
void BM_empty(benchmark::State& state) {
|
|
while (state.KeepRunning()) {
|
|
benchmark::DoNotOptimize(state.iterations());
|
|
}
|
|
}
|
|
BENCHMARK(BM_empty);
|
|
BENCHMARK(BM_empty)->ThreadPerCpu();
|
|
|
|
void BM_spin_empty(benchmark::State& state) {
|
|
while (state.KeepRunning()) {
|
|
for (int x = 0; x < state.range(0); ++x) {
|
|
benchmark::DoNotOptimize(x);
|
|
}
|
|
}
|
|
}
|
|
BASIC_BENCHMARK_TEST(BM_spin_empty);
|
|
BASIC_BENCHMARK_TEST(BM_spin_empty)->ThreadPerCpu();
|
|
|
|
void BM_spin_pause_before(benchmark::State& state) {
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
while(state.KeepRunning()) {
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
}
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_before);
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_before)->ThreadPerCpu();
|
|
|
|
|
|
void BM_spin_pause_during(benchmark::State& state) {
|
|
while(state.KeepRunning()) {
|
|
state.PauseTiming();
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
state.ResumeTiming();
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
}
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_during);
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_during)->ThreadPerCpu();
|
|
|
|
void BM_pause_during(benchmark::State& state) {
|
|
while(state.KeepRunning()) {
|
|
state.PauseTiming();
|
|
state.ResumeTiming();
|
|
}
|
|
}
|
|
BENCHMARK(BM_pause_during);
|
|
BENCHMARK(BM_pause_during)->ThreadPerCpu();
|
|
BENCHMARK(BM_pause_during)->UseRealTime();
|
|
BENCHMARK(BM_pause_during)->UseRealTime()->ThreadPerCpu();
|
|
|
|
void BM_spin_pause_after(benchmark::State& state) {
|
|
while(state.KeepRunning()) {
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_after);
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_after)->ThreadPerCpu();
|
|
|
|
|
|
void BM_spin_pause_before_and_after(benchmark::State& state) {
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
while(state.KeepRunning()) {
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
for (int i = 0; i < state.range(0); ++i) {
|
|
benchmark::DoNotOptimize(i);
|
|
}
|
|
}
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_before_and_after);
|
|
BASIC_BENCHMARK_TEST(BM_spin_pause_before_and_after)->ThreadPerCpu();
|
|
|
|
|
|
void BM_empty_stop_start(benchmark::State& state) {
|
|
while (state.KeepRunning()) { }
|
|
}
|
|
BENCHMARK(BM_empty_stop_start);
|
|
BENCHMARK(BM_empty_stop_start)->ThreadPerCpu();
|
|
|
|
BENCHMARK_MAIN()
|