benchmark/test/complexity_test.cc

229 lines
8.5 KiB
C++
Raw Normal View History

2016-06-01 21:08:01 +00:00
#undef NDEBUG
#include <algorithm>
#include <cassert>
2016-06-03 16:33:17 +00:00
#include <cmath>
#include <cstdlib>
#include <vector>
2021-11-10 16:22:31 +00:00
#include "benchmark/benchmark.h"
#include "output_test.h"
2016-06-01 21:08:01 +00:00
namespace {
#define ADD_COMPLEXITY_CASES(...) \
int CONCAT(dummy, __LINE__) = AddComplexityTest(__VA_ARGS__)
int AddComplexityTest(const std::string &test_name,
const std::string &big_o_test_name,
const std::string &rms_test_name,
const std::string &big_o, int family_index) {
SetSubstitutions({{"%name", test_name},
{"%bigo_name", big_o_test_name},
{"%rms_name", rms_test_name},
{"%bigo_str", "[ ]* %float " + big_o},
{"%bigo", big_o},
{"%rms", "[ ]*[0-9]+ %"}});
AddCases(
TC_ConsoleOut,
{{"^%bigo_name %bigo_str %bigo_str[ ]*$"},
{"^%bigo_name", MR_Not}, // Assert we we didn't only matched a name.
{"^%rms_name %rms %rms[ ]*$", MR_Next}});
AddCases(
TC_JSONOut,
{{"\"name\": \"%bigo_name\",$"},
{"\"family_index\": " + std::to_string(family_index) + ",$", MR_Next},
{"\"per_family_instance_index\": 0,$", MR_Next},
{"\"run_name\": \"%name\",$", MR_Next},
{"\"run_type\": \"aggregate\",$", MR_Next},
{"\"repetitions\": %int,$", MR_Next},
{"\"threads\": 1,$", MR_Next},
{"\"aggregate_name\": \"BigO\",$", MR_Next},
{"\"aggregate_unit\": \"time\",$", MR_Next},
{"\"cpu_coefficient\": %float,$", MR_Next},
{"\"real_coefficient\": %float,$", MR_Next},
{"\"big_o\": \"%bigo\",$", MR_Next},
{"\"time_unit\": \"ns\"$", MR_Next},
{"}", MR_Next},
{"\"name\": \"%rms_name\",$"},
{"\"family_index\": " + std::to_string(family_index) + ",$", MR_Next},
{"\"per_family_instance_index\": 0,$", MR_Next},
{"\"run_name\": \"%name\",$", MR_Next},
{"\"run_type\": \"aggregate\",$", MR_Next},
{"\"repetitions\": %int,$", MR_Next},
{"\"threads\": 1,$", MR_Next},
{"\"aggregate_name\": \"RMS\",$", MR_Next},
{"\"aggregate_unit\": \"percentage\",$", MR_Next},
{"\"rms\": %float$", MR_Next},
{"}", MR_Next}});
AddCases(TC_CSVOut, {{"^\"%bigo_name\",,%float,%float,%bigo,,,,,$"},
{"^\"%bigo_name\"", MR_Not},
{"^\"%rms_name\",,%float,%float,,,,,,$", MR_Next}});
2016-06-01 21:08:01 +00:00
return 0;
}
} // end namespace
// ========================================================================= //
// --------------------------- Testing BigO O(1) --------------------------- //
// ========================================================================= //
2021-11-10 16:22:31 +00:00
void BM_Complexity_O1(benchmark::State &state) {
for (auto _ : state) {
for (int i = 0; i < 1024; ++i) {
2023-03-06 14:47:54 +00:00
benchmark::DoNotOptimize(i);
}
}
state.SetComplexityN(state.range(0));
}
BENCHMARK(BM_Complexity_O1)->Range(1, 1 << 18)->Complexity(benchmark::o1);
BENCHMARK(BM_Complexity_O1)->Range(1, 1 << 18)->Complexity();
Iteration counts should be `uint64_t` globally. (#817) 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`: https://github.com/google/benchmark/blob/7a1c37028359ca9d386d719a6ad527743cf1b753/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.
2019-05-13 09:33:11 +00:00
BENCHMARK(BM_Complexity_O1)
->Range(1, 1 << 18)
->Complexity([](benchmark::IterationCount) { return 1.0; });
const char *one_test_name = "BM_Complexity_O1";
const char *big_o_1_test_name = "BM_Complexity_O1_BigO";
const char *rms_o_1_test_name = "BM_Complexity_O1_RMS";
const char *enum_big_o_1 = "\\([0-9]+\\)";
// FIXME: Tolerate both '(1)' and 'lgN' as output when the complexity is auto
// deduced.
// See https://github.com/google/benchmark/issues/272
const char *auto_big_o_1 = "(\\([0-9]+\\))|(lgN)";
const char *lambda_big_o_1 = "f\\(N\\)";
2016-06-01 21:08:01 +00:00
// Add enum tests
ADD_COMPLEXITY_CASES(one_test_name, big_o_1_test_name, rms_o_1_test_name,
enum_big_o_1, /*family_index=*/0);
2016-06-01 21:08:01 +00:00
// Add auto enum tests
ADD_COMPLEXITY_CASES(one_test_name, big_o_1_test_name, rms_o_1_test_name,
auto_big_o_1, /*family_index=*/1);
2016-06-01 21:08:01 +00:00
// Add lambda tests
ADD_COMPLEXITY_CASES(one_test_name, big_o_1_test_name, rms_o_1_test_name,
lambda_big_o_1, /*family_index=*/2);
2016-06-01 21:08:01 +00:00
// ========================================================================= //
// --------------------------- Testing BigO O(N) --------------------------- //
// ========================================================================= //
std::vector<int> ConstructRandomVector(int64_t size) {
2016-06-01 21:08:01 +00:00
std::vector<int> v;
v.reserve(static_cast<size_t>(size));
2016-06-01 21:08:01 +00:00
for (int i = 0; i < size; ++i) {
v.push_back(static_cast<int>(std::rand() % size));
2016-06-01 21:08:01 +00:00
}
return v;
}
2021-11-10 16:22:31 +00:00
void BM_Complexity_O_N(benchmark::State &state) {
auto v = ConstructRandomVector(state.range(0));
// Test worst case scenario (item not in vector)
const int64_t item_not_in_vector = state.range(0) * 2;
for (auto _ : state) {
2023-03-06 14:47:54 +00:00
auto it = std::find(v.begin(), v.end(), item_not_in_vector);
benchmark::DoNotOptimize(it);
}
state.SetComplexityN(state.range(0));
}
BENCHMARK(BM_Complexity_O_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
->Complexity(benchmark::oN);
BENCHMARK(BM_Complexity_O_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
Iteration counts should be `uint64_t` globally. (#817) 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`: https://github.com/google/benchmark/blob/7a1c37028359ca9d386d719a6ad527743cf1b753/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.
2019-05-13 09:33:11 +00:00
->Complexity([](benchmark::IterationCount n) -> double {
return static_cast<double>(n);
});
BENCHMARK(BM_Complexity_O_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
->Complexity();
const char *n_test_name = "BM_Complexity_O_N";
const char *big_o_n_test_name = "BM_Complexity_O_N_BigO";
const char *rms_o_n_test_name = "BM_Complexity_O_N_RMS";
const char *enum_auto_big_o_n = "N";
const char *lambda_big_o_n = "f\\(N\\)";
2016-05-24 20:25:59 +00:00
2016-06-01 21:08:01 +00:00
// Add enum tests
ADD_COMPLEXITY_CASES(n_test_name, big_o_n_test_name, rms_o_n_test_name,
enum_auto_big_o_n, /*family_index=*/3);
2016-06-01 21:08:01 +00:00
// Add lambda tests
ADD_COMPLEXITY_CASES(n_test_name, big_o_n_test_name, rms_o_n_test_name,
lambda_big_o_n, /*family_index=*/4);
2016-06-01 21:08:01 +00:00
// ========================================================================= //
// ------------------------- Testing BigO O(N*lgN) ------------------------- //
// ========================================================================= //
2021-11-10 16:22:31 +00:00
static void BM_Complexity_O_N_log_N(benchmark::State &state) {
auto v = ConstructRandomVector(state.range(0));
for (auto _ : state) {
std::sort(v.begin(), v.end());
}
state.SetComplexityN(state.range(0));
}
static const double kLog2E = 1.44269504088896340736;
BENCHMARK(BM_Complexity_O_N_log_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
->Complexity(benchmark::oNLogN);
BENCHMARK(BM_Complexity_O_N_log_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
Iteration counts should be `uint64_t` globally. (#817) 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`: https://github.com/google/benchmark/blob/7a1c37028359ca9d386d719a6ad527743cf1b753/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.
2019-05-13 09:33:11 +00:00
->Complexity([](benchmark::IterationCount n) {
return kLog2E * static_cast<double>(n) * log(static_cast<double>(n));
});
BENCHMARK(BM_Complexity_O_N_log_N)
->RangeMultiplier(2)
->Range(1 << 10, 1 << 16)
->Complexity();
const char *n_lg_n_test_name = "BM_Complexity_O_N_log_N";
const char *big_o_n_lg_n_test_name = "BM_Complexity_O_N_log_N_BigO";
const char *rms_o_n_lg_n_test_name = "BM_Complexity_O_N_log_N_RMS";
const char *enum_auto_big_o_n_lg_n = "NlgN";
const char *lambda_big_o_n_lg_n = "f\\(N\\)";
2016-06-01 21:08:01 +00:00
// Add enum tests
ADD_COMPLEXITY_CASES(n_lg_n_test_name, big_o_n_lg_n_test_name,
rms_o_n_lg_n_test_name, enum_auto_big_o_n_lg_n,
/*family_index=*/6);
2016-06-01 21:08:01 +00:00
// Add lambda tests
ADD_COMPLEXITY_CASES(n_lg_n_test_name, big_o_n_lg_n_test_name,
rms_o_n_lg_n_test_name, lambda_big_o_n_lg_n,
/*family_index=*/7);
2016-06-01 21:08:01 +00:00
// ========================================================================= //
// -------- Testing formatting of Complexity with captured args ------------ //
// ========================================================================= //
2021-11-10 16:22:31 +00:00
void BM_ComplexityCaptureArgs(benchmark::State &state, int n) {
for (auto _ : state) {
// This test requires a non-zero CPU time to avoid divide-by-zero
2023-03-06 14:47:54 +00:00
auto iterations = state.iterations();
benchmark::DoNotOptimize(iterations);
}
state.SetComplexityN(n);
}
BENCHMARK_CAPTURE(BM_ComplexityCaptureArgs, capture_test, 100)
->Complexity(benchmark::oN)
->Ranges({{1, 2}, {3, 4}});
const std::string complexity_capture_name =
"BM_ComplexityCaptureArgs/capture_test";
ADD_COMPLEXITY_CASES(complexity_capture_name, complexity_capture_name + "_BigO",
complexity_capture_name + "_RMS", "N", /*family_index=*/9);
2016-06-01 21:08:01 +00:00
// ========================================================================= //
// --------------------------- TEST CASES END ------------------------------ //
// ========================================================================= //
int main(int argc, char *argv[]) { RunOutputTests(argc, argv); }