llvm-project/libcxx/benchmarks/algorithms.bench.cpp
Nilay Vaish 7f287390d7 [libc++] Add introsort to avoid O(n^2) behavior
This commit adds a benchmark that tests std::sort on an adversarial inputs,
and uses introsort in std::sort to avoid O(n^2) behavior on adversarial
inputs.

Inputs where partitions are unbalanced even after 2 log(n) pivots have
been selected, the algorithm switches to heap sort to avoid the
possibility of spending O(n^2) time on sorting the input.
Benchmark results show that the intro sort implementation does
significantly better.

Benchmarking results before this change. Time represents the sorting
time required per element:

----------------------------------------------------------------------------------------------------------
Benchmark                                                                Time             CPU   Iterations
----------------------------------------------------------------------------------------------------------
BM_Sort_uint32_QuickSortAdversary_1                                   3.75 ns         3.74 ns    187432960
BM_Sort_uint32_QuickSortAdversary_4                                   3.05 ns         3.05 ns    231211008
BM_Sort_uint32_QuickSortAdversary_16                                  2.45 ns         2.45 ns    288096256
BM_Sort_uint32_QuickSortAdversary_64                                  32.8 ns         32.8 ns     21495808
BM_Sort_uint32_QuickSortAdversary_256                                  132 ns          132 ns      5505024
BM_Sort_uint32_QuickSortAdversary_1024                                 498 ns          497 ns      1572864
BM_Sort_uint32_QuickSortAdversary_16384                               3846 ns         3845 ns       262144
BM_Sort_uint32_QuickSortAdversary_262144                             61431 ns        61400 ns       262144
BM_Sort_uint64_QuickSortAdversary_1                                   3.93 ns         3.92 ns    181141504
BM_Sort_uint64_QuickSortAdversary_4                                   3.10 ns         3.09 ns    222560256
BM_Sort_uint64_QuickSortAdversary_16                                  2.50 ns         2.50 ns    283639808
BM_Sort_uint64_QuickSortAdversary_64                                  33.2 ns         33.2 ns     21757952
BM_Sort_uint64_QuickSortAdversary_256                                  132 ns          132 ns      5505024
BM_Sort_uint64_QuickSortAdversary_1024                                 478 ns          477 ns      1572864
BM_Sort_uint64_QuickSortAdversary_16384                               3932 ns         3930 ns       262144
BM_Sort_uint64_QuickSortAdversary_262144                             61646 ns        61615 ns       262144

Benchmarking results after this change:

----------------------------------------------------------------------------------------------------------
Benchmark                                                                Time             CPU   Iterations
----------------------------------------------------------------------------------------------------------
BM_Sort_uint32_QuickSortAdversary_1                                   6.31 ns         6.30 ns    107741184
BM_Sort_uint32_QuickSortAdversary_4                                   4.51 ns         4.50 ns    158859264
BM_Sort_uint32_QuickSortAdversary_16                                  3.00 ns         3.00 ns    223608832
BM_Sort_uint32_QuickSortAdversary_64                                  44.8 ns         44.8 ns     15990784
BM_Sort_uint32_QuickSortAdversary_256                                 69.0 ns         68.9 ns      9961472
BM_Sort_uint32_QuickSortAdversary_1024                                 118 ns          118 ns      6029312
BM_Sort_uint32_QuickSortAdversary_16384                                175 ns          175 ns      4194304
BM_Sort_uint32_QuickSortAdversary_262144                               210 ns          210 ns      3407872
BM_Sort_uint64_QuickSortAdversary_1                                   6.75 ns         6.73 ns    103809024
BM_Sort_uint64_QuickSortAdversary_4                                   4.53 ns         4.53 ns    160432128
BM_Sort_uint64_QuickSortAdversary_16                                  2.98 ns         2.97 ns    234356736
BM_Sort_uint64_QuickSortAdversary_64                                  44.3 ns         44.3 ns     15990784
BM_Sort_uint64_QuickSortAdversary_256                                 69.2 ns         69.2 ns     10223616
BM_Sort_uint64_QuickSortAdversary_1024                                 119 ns          119 ns      6029312
BM_Sort_uint64_QuickSortAdversary_16384                                173 ns          173 ns      4194304
BM_Sort_uint64_QuickSortAdversary_262144                               212 ns          212 ns      3407872

Differential Revision: https://reviews.llvm.org/D113413
2021-11-16 11:38:46 -05:00

388 lines
11 KiB
C++
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#include <algorithm>
#include <cstdint>
#include <map>
#include <random>
#include <string>
#include <utility>
#include <vector>
#include "CartesianBenchmarks.h"
#include "GenerateInput.h"
#include "benchmark/benchmark.h"
#include "test_macros.h"
namespace {
enum class ValueType { Uint32, Uint64, Pair, Tuple, String };
struct AllValueTypes : EnumValuesAsTuple<AllValueTypes, ValueType, 5> {
static constexpr const char* Names[] = {
"uint32", "uint64", "pair<uint32, uint32>",
"tuple<uint32, uint64, uint32>", "string"};
};
template <class V>
using Value = std::conditional_t<
V() == ValueType::Uint32, uint32_t,
std::conditional_t<
V() == ValueType::Uint64, uint64_t,
std::conditional_t<
V() == ValueType::Pair, std::pair<uint32_t, uint32_t>,
std::conditional_t<V() == ValueType::Tuple,
std::tuple<uint32_t, uint64_t, uint32_t>,
std::string> > > >;
enum class Order {
Random,
Ascending,
Descending,
SingleElement,
PipeOrgan,
Heap,
QuickSortAdversary,
};
struct AllOrders : EnumValuesAsTuple<AllOrders, Order, 7> {
static constexpr const char* Names[] = {"Random", "Ascending",
"Descending", "SingleElement",
"PipeOrgan", "Heap",
"QuickSortAdversary"};
};
// fillAdversarialQuickSortInput fills the input vector with N int-like values.
// These values are arranged in such a way that they would invoke O(N^2)
// behavior on any quick sort implementation that satisifies certain conditions.
// Details are available in the following paper:
// "A Killer Adversary for Quicksort", M. D. McIlroy, Software—Practice &
// ExperienceVolume 29 Issue 4 April 10, 1999 pp 341344.
// https://dl.acm.org/doi/10.5555/311868.311871.
template <class T>
void fillAdversarialQuickSortInput(T& V, size_t N) {
assert(N > 0);
// If an element is equal to gas, it indicates that the value of the element
// is still to be decided and may change over the course of time.
const int gas = N - 1;
V.resize(N);
for (int i = 0; i < N; ++i) {
V[i] = gas;
}
// Candidate for the pivot position.
int candidate = 0;
int nsolid = 0;
// Populate all positions in the generated input to gas.
std::vector<int> ascVals(V.size());
// Fill up with ascending values from 0 to V.size()-1. These will act as
// indices into V.
std::iota(ascVals.begin(), ascVals.end(), 0);
std::sort(ascVals.begin(), ascVals.end(), [&](int x, int y) {
if (V[x] == gas && V[y] == gas) {
// We are comparing two inputs whose value is still to be decided.
if (x == candidate) {
V[x] = nsolid++;
} else {
V[y] = nsolid++;
}
}
if (V[x] == gas) {
candidate = x;
} else if (V[y] == gas) {
candidate = y;
}
return V[x] < V[y];
});
}
template <typename T>
void fillValues(std::vector<T>& V, size_t N, Order O) {
if (O == Order::SingleElement) {
V.resize(N, 0);
} else if (O == Order::QuickSortAdversary) {
fillAdversarialQuickSortInput(V, N);
} else {
while (V.size() < N)
V.push_back(V.size());
}
}
template <typename T>
void fillValues(std::vector<std::pair<T, T> >& V, size_t N, Order O) {
if (O == Order::SingleElement) {
V.resize(N, std::make_pair(0, 0));
} else {
while (V.size() < N)
// Half of array will have the same first element.
if (V.size() % 2) {
V.push_back(std::make_pair(V.size(), V.size()));
} else {
V.push_back(std::make_pair(0, V.size()));
}
}
}
template <typename T1, typename T2, typename T3>
void fillValues(std::vector<std::tuple<T1, T2, T3> >& V, size_t N, Order O) {
if (O == Order::SingleElement) {
V.resize(N, std::make_tuple(0, 0, 0));
} else {
while (V.size() < N)
// One third of array will have the same first element.
// One third of array will have the same first element and the same second element.
switch (V.size() % 3) {
case 0:
V.push_back(std::make_tuple(V.size(), V.size(), V.size()));
break;
case 1:
V.push_back(std::make_tuple(0, V.size(), V.size()));
break;
case 2:
V.push_back(std::make_tuple(0, 0, V.size()));
break;
}
}
}
void fillValues(std::vector<std::string>& V, size_t N, Order O) {
if (O == Order::SingleElement) {
V.resize(N, getRandomString(64));
} else {
while (V.size() < N)
V.push_back(getRandomString(64));
}
}
template <class T>
void sortValues(T& V, Order O) {
assert(std::is_sorted(V.begin(), V.end()));
switch (O) {
case Order::Random: {
std::random_device R;
std::mt19937 M(R());
std::shuffle(V.begin(), V.end(), M);
break;
}
case Order::Ascending:
std::sort(V.begin(), V.end());
break;
case Order::Descending:
std::sort(V.begin(), V.end(), std::greater<>());
break;
case Order::SingleElement:
// Nothing to do
break;
case Order::PipeOrgan:
std::sort(V.begin(), V.end());
std::reverse(V.begin() + V.size() / 2, V.end());
break;
case Order::Heap:
std::make_heap(V.begin(), V.end());
break;
case Order::QuickSortAdversary:
// Nothing to do
break;
}
}
constexpr size_t TestSetElements =
#if !TEST_HAS_FEATURE(memory_sanitizer)
1 << 18;
#else
1 << 14;
#endif
template <class ValueType>
std::vector<std::vector<Value<ValueType> > > makeOrderedValues(size_t N,
Order O) {
std::vector<std::vector<Value<ValueType> > > Ret;
const size_t NumCopies = std::max(size_t{1}, TestSetElements / N);
Ret.resize(NumCopies);
for (auto& V : Ret) {
fillValues(V, N, O);
sortValues(V, O);
}
return Ret;
}
template <class T, class U>
TEST_ALWAYS_INLINE void resetCopies(benchmark::State& state, T& Copies,
U& Orig) {
state.PauseTiming();
for (auto& Copy : Copies)
Copy = Orig;
state.ResumeTiming();
}
enum class BatchSize {
CountElements,
CountBatch,
};
template <class ValueType, class F>
void runOpOnCopies(benchmark::State& state, size_t Quantity, Order O,
BatchSize Count, F Body) {
auto Copies = makeOrderedValues<ValueType>(Quantity, O);
auto Orig = Copies;
const size_t Batch = Count == BatchSize::CountElements
? Copies.size() * Quantity
: Copies.size();
while (state.KeepRunningBatch(Batch)) {
for (auto& Copy : Copies) {
Body(Copy);
benchmark::DoNotOptimize(Copy);
}
state.PauseTiming();
Copies = Orig;
state.ResumeTiming();
}
}
template <class ValueType, class Order>
struct Sort {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order(), BatchSize::CountElements,
[](auto& Copy) { std::sort(Copy.begin(), Copy.end()); });
}
bool skip() const { return Order() == ::Order::Heap; }
std::string name() const {
return "BM_Sort" + ValueType::name() + Order::name() + "_" +
std::to_string(Quantity);
};
};
template <class ValueType, class Order>
struct StableSort {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order(), BatchSize::CountElements,
[](auto& Copy) { std::stable_sort(Copy.begin(), Copy.end()); });
}
bool skip() const { return Order() == ::Order::Heap; }
std::string name() const {
return "BM_StableSort" + ValueType::name() + Order::name() + "_" +
std::to_string(Quantity);
};
};
template <class ValueType, class Order>
struct MakeHeap {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order(), BatchSize::CountElements,
[](auto& Copy) { std::make_heap(Copy.begin(), Copy.end()); });
}
std::string name() const {
return "BM_MakeHeap" + ValueType::name() + Order::name() + "_" +
std::to_string(Quantity);
};
};
template <class ValueType>
struct SortHeap {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order::Heap, BatchSize::CountElements,
[](auto& Copy) { std::sort_heap(Copy.begin(), Copy.end()); });
}
std::string name() const {
return "BM_SortHeap" + ValueType::name() + "_" + std::to_string(Quantity);
};
};
template <class ValueType, class Order>
struct MakeThenSortHeap {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(state, Quantity, Order(), BatchSize::CountElements,
[](auto& Copy) {
std::make_heap(Copy.begin(), Copy.end());
std::sort_heap(Copy.begin(), Copy.end());
});
}
std::string name() const {
return "BM_MakeThenSortHeap" + ValueType::name() + Order::name() + "_" +
std::to_string(Quantity);
};
};
template <class ValueType, class Order>
struct PushHeap {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order(), BatchSize::CountElements, [](auto& Copy) {
for (auto I = Copy.begin(), E = Copy.end(); I != E; ++I) {
std::push_heap(Copy.begin(), I + 1);
}
});
}
bool skip() const { return Order() == ::Order::Heap; }
std::string name() const {
return "BM_PushHeap" + ValueType::name() + Order::name() + "_" +
std::to_string(Quantity);
};
};
template <class ValueType>
struct PopHeap {
size_t Quantity;
void run(benchmark::State& state) const {
runOpOnCopies<ValueType>(
state, Quantity, Order(), BatchSize::CountElements, [](auto& Copy) {
for (auto B = Copy.begin(), I = Copy.end(); I != B; --I) {
std::pop_heap(B, I);
}
});
}
std::string name() const {
return "BM_PopHeap" + ValueType::name() + "_" + std::to_string(Quantity);
};
};
} // namespace
int main(int argc, char** argv) {
benchmark::Initialize(&argc, argv);
if (benchmark::ReportUnrecognizedArguments(argc, argv))
return 1;
const std::vector<size_t> Quantities = {1 << 0, 1 << 2, 1 << 4, 1 << 6,
1 << 8, 1 << 10, 1 << 14,
// Running each benchmark in parallel consumes too much memory with MSAN
// and can lead to the test process being killed.
#if !TEST_HAS_FEATURE(memory_sanitizer)
1 << 18
#endif
};
makeCartesianProductBenchmark<Sort, AllValueTypes, AllOrders>(Quantities);
makeCartesianProductBenchmark<StableSort, AllValueTypes, AllOrders>(
Quantities);
makeCartesianProductBenchmark<MakeHeap, AllValueTypes, AllOrders>(Quantities);
makeCartesianProductBenchmark<SortHeap, AllValueTypes>(Quantities);
makeCartesianProductBenchmark<MakeThenSortHeap, AllValueTypes, AllOrders>(
Quantities);
makeCartesianProductBenchmark<PushHeap, AllValueTypes, AllOrders>(Quantities);
makeCartesianProductBenchmark<PopHeap, AllValueTypes>(Quantities);
benchmark::RunSpecifiedBenchmarks();
}