mirror of
https://github.com/google/benchmark.git
synced 2024-11-26 07:32:19 +00:00
f92903cc53
This is a shameless rip-off of https://github.com/google/benchmark/pull/646
I did promise to look into why that proposed PR was producing
so much worse assembly, and so i finally did.
The reason is - that diff changes `size_t` (unsigned) to `int64_t` (signed).
There is this nice little `assert`:
7a1c370283/include/benchmark/benchmark.h (L744)
It ensures that we didn't magically decide to advance our iterator
when we should have finished benchmarking.
When `cached_` was unsigned, the `assert` was `cached_ UGT 0`.
But we only ever get to that `assert` if `cached_ NE 0`,
and naturally if `cached_` is not `0`, then it is bigger than `0`,
so the `assert` is tautological, and gets folded away.
But now that `cached_` became signed, the assert became `cached_ SGT 0`.
And we still only know that `cached_ NE 0`, so the assert can't be
optimized out, or at least it doesn't currently.
Regardless of whether or not that is a bug in itself,
that particular diff would have regressed the normal 64-bit systems,
by halving the maximal iteration space (since we go from unsigned counter
to signed one, of the same bit-width), which seems like a bug.
And just so it happens, fixing *this* bug, fixes the other bug.
This produces fully (bit-by-bit) identical state_assembly_test.s
The filecheck change is actually needed regardless of this patch,
else this test does not pass for me even without this diff.
64 lines
1.6 KiB
C++
64 lines
1.6 KiB
C++
#undef NDEBUG
|
|
#include <cassert>
|
|
#include <cstddef>
|
|
|
|
#include "benchmark/benchmark.h"
|
|
|
|
#if __cplusplus >= 201103L
|
|
#error C++11 or greater detected. Should be C++03.
|
|
#endif
|
|
|
|
#ifdef BENCHMARK_HAS_CXX11
|
|
#error C++11 or greater detected by the library. BENCHMARK_HAS_CXX11 is defined.
|
|
#endif
|
|
|
|
void BM_empty(benchmark::State& state) {
|
|
while (state.KeepRunning()) {
|
|
volatile benchmark::IterationCount x = state.iterations();
|
|
((void)x);
|
|
}
|
|
}
|
|
BENCHMARK(BM_empty);
|
|
|
|
// The new C++11 interface for args/ranges requires initializer list support.
|
|
// Therefore we provide the old interface to support C++03.
|
|
void BM_old_arg_range_interface(benchmark::State& state) {
|
|
assert((state.range(0) == 1 && state.range(1) == 2) ||
|
|
(state.range(0) == 5 && state.range(1) == 6));
|
|
while (state.KeepRunning()) {
|
|
}
|
|
}
|
|
BENCHMARK(BM_old_arg_range_interface)->ArgPair(1, 2)->RangePair(5, 5, 6, 6);
|
|
|
|
template <class T, class U>
|
|
void BM_template2(benchmark::State& state) {
|
|
BM_empty(state);
|
|
}
|
|
BENCHMARK_TEMPLATE2(BM_template2, int, long);
|
|
|
|
template <class T>
|
|
void BM_template1(benchmark::State& state) {
|
|
BM_empty(state);
|
|
}
|
|
BENCHMARK_TEMPLATE(BM_template1, long);
|
|
BENCHMARK_TEMPLATE1(BM_template1, int);
|
|
|
|
template <class T>
|
|
struct BM_Fixture : public ::benchmark::Fixture {
|
|
};
|
|
|
|
BENCHMARK_TEMPLATE_F(BM_Fixture, BM_template1, long)(benchmark::State& state) {
|
|
BM_empty(state);
|
|
}
|
|
BENCHMARK_TEMPLATE1_F(BM_Fixture, BM_template2, int)(benchmark::State& state) {
|
|
BM_empty(state);
|
|
}
|
|
|
|
void BM_counters(benchmark::State& state) {
|
|
BM_empty(state);
|
|
state.counters["Foo"] = 2;
|
|
}
|
|
BENCHMARK(BM_counters);
|
|
|
|
BENCHMARK_MAIN();
|