mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-28 15:26:08 +00:00
1a5af34e6f
Locale objects use atomic reference counting, which may be very expensive in parallel applications. The classic locale is used by default by all streams and can be very contended. But it's never destroyed, so the reference counting is also completely pointless on the classic locale. Currently ~70% of time in the parallel stringstream benchmarks is spent in locale ctor/dtor. And the execution radically slows down with more threads. Avoid reference counting on the classic locale. With this change parallel benchmarks start to scale with threads. This is a re-application of f8afc53d641c (aka PR #72112) which was reverted in 4e0c48b907f1 because it broke the sanitizer builds due to an initialization order fiasco. This issue has now been fixed by ensuring that the locale is constinit'ed. Co-authored-by: Dmitry Vyukov <dvyukov@google.com>
88 lines
2.2 KiB
C++
88 lines
2.2 KiB
C++
#include "benchmark/benchmark.h"
|
|
#include "test_macros.h"
|
|
|
|
#include <mutex>
|
|
#include <sstream>
|
|
|
|
TEST_NOINLINE double istream_numbers();
|
|
|
|
double istream_numbers(std::locale* loc) {
|
|
const char* a[] = {"-6 69 -71 2.4882e-02 -100 101 -2.00005 5000000 -50000000",
|
|
"-25 71 7 -9.3262e+01 -100 101 -2.00005 5000000 -50000000",
|
|
"-14 53 46 -6.7026e-02 -100 101 -2.00005 5000000 -50000000"};
|
|
|
|
int a1, a2, a3, a4, a5, a6, a7;
|
|
double f1 = 0.0, f2 = 0.0, q = 0.0;
|
|
for (int i = 0; i < 3; i++) {
|
|
std::istringstream s(a[i]);
|
|
if (loc)
|
|
s.imbue(*loc);
|
|
s >> a1 >> a2 >> a3 >> f1 >> a4 >> a5 >> f2 >> a6 >> a7;
|
|
q += (a1 + a2 + a3 + a4 + a5 + a6 + a7 + f1 + f2) / 1000000;
|
|
}
|
|
return q;
|
|
}
|
|
|
|
struct LocaleSelector {
|
|
std::locale* imbue;
|
|
std::locale old;
|
|
static std::mutex mutex;
|
|
|
|
LocaleSelector(benchmark::State& state) {
|
|
std::lock_guard guard(mutex);
|
|
switch (state.range(0)) {
|
|
case 0: {
|
|
old = std::locale::global(std::locale::classic());
|
|
imbue = nullptr;
|
|
break;
|
|
}
|
|
case 1: {
|
|
old = std::locale::global(std::locale::classic());
|
|
thread_local std::locale loc("en_US.UTF-8");
|
|
imbue = &loc;
|
|
break;
|
|
}
|
|
case 2: {
|
|
old = std::locale::global(std::locale::classic());
|
|
static std::locale loc("en_US.UTF-8");
|
|
imbue = &loc;
|
|
break;
|
|
}
|
|
case 3: {
|
|
old = std::locale::global(std::locale("en_US.UTF-8"));
|
|
imbue = nullptr;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
~LocaleSelector() {
|
|
std::lock_guard guard(mutex);
|
|
std::locale::global(old);
|
|
}
|
|
};
|
|
|
|
std::mutex LocaleSelector::mutex;
|
|
|
|
static void BM_Istream_numbers(benchmark::State& state) {
|
|
LocaleSelector sel(state);
|
|
double i = 0;
|
|
while (state.KeepRunning())
|
|
benchmark::DoNotOptimize(i += istream_numbers(sel.imbue));
|
|
}
|
|
BENCHMARK(BM_Istream_numbers)->DenseRange(0, 3)->UseRealTime()->Threads(1)->ThreadPerCpu();
|
|
|
|
static void BM_Ostream_number(benchmark::State& state) {
|
|
LocaleSelector sel(state);
|
|
while (state.KeepRunning()) {
|
|
std::ostringstream ss;
|
|
if (sel.imbue)
|
|
ss.imbue(*sel.imbue);
|
|
ss << 0;
|
|
benchmark::DoNotOptimize(ss.str().c_str());
|
|
}
|
|
}
|
|
BENCHMARK(BM_Ostream_number)->DenseRange(0, 3)->UseRealTime()->Threads(1)->ThreadPerCpu();
|
|
|
|
BENCHMARK_MAIN();
|