1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
|
/**
* Copyright (C) 2023-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#include <algorithm>
#include <boost/random/normal_distribution.hpp>
#include <random>
#include "mongo/db/pipeline/percentile_algo_bm_fixture.h"
#include "mongo/db/pipeline/percentile_algo.h"
#include "mongo/db/pipeline/percentile_algo_tdigest.h"
namespace mongo {
using std::vector;
// We'd like to test with "realistic" data so that tdigest has to do sorting and merging on a
// regular basis. The particular distribution of data shouldn't matter much.
vector<double> generateNormal(size_t n, bool presorted) {
std::mt19937 generator(2023u);
boost::random::normal_distribution<double> dist(0.0 /* mean */, 1.0 /* sigma */);
vector<double> inputs;
inputs.reserve(n);
for (size_t i = 0; i < n; i++) {
inputs.push_back(dist(generator));
}
if (presorted) {
std::sort(inputs.begin(), inputs.end());
}
return inputs;
}
void PercentileAlgoBenchmarkFixture::tdigest_normalData(benchmark::State& state,
TDigest::ScalingFunction k_limit,
double delta,
int dataSize,
bool presorted,
const std::vector<double>& ps) {
const vector<double> inputs = generateNormal(dataSize, presorted);
for (auto keepRunning : state) {
auto d = std::make_unique<TDigest>(k_limit, delta);
d->incorporate(inputs);
benchmark::DoNotOptimize(d->computePercentiles(ps));
benchmark::ClobberMemory();
}
}
void PercentileAlgoBenchmarkFixture::discrete_normalData(benchmark::State& state,
int dataSize,
bool presorted,
const std::vector<double>& ps) {
const vector<double> inputs = generateNormal(dataSize, presorted);
for (auto keepRunning : state) {
auto d = createDiscretePercentile();
d->incorporate(inputs);
benchmark::DoNotOptimize(d->computePercentiles(ps));
benchmark::ClobberMemory();
}
}
void PercentileAlgoBenchmarkFixture::tdigest_normalData_batched(benchmark::State& state,
TDigest::ScalingFunction k_limit,
double delta) {
const vector<double> inputs = generateNormal(nLarge, false /* presorted */);
for (auto keepRunning : state) {
auto d = std::make_unique<TDigest>(k_limit, delta);
vector<double> batch;
batch.reserve(delta);
for (double input : inputs) {
if (batch.size() == 5 * delta) {
d->incorporate(batch);
batch.clear();
}
batch.push_back(input);
}
if (!batch.empty()) {
d->incorporate(batch);
}
benchmark::DoNotOptimize(d->computePercentile(0.5));
benchmark::ClobberMemory();
}
}
BENCHMARK_PERCENTILE_ALGO(PercentileAlgoBenchmarkFixture);
} // namespace mongo
|