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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
// { dg-options "-std=gnu++11" }
// Copyright (C) 2011-2016 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library. This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.
// This library 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
// GNU General Public License for more details.
// You should have received a copy of the GNU General Public License along
// with this library; see the file COPYING3. If not see
// <http://www.gnu.org/licenses/>.
#include <sstream>
#include <tr1/unordered_set>
#include <unordered_set>
#include <testsuite_performance.h>
namespace
{
// Bench using an unordered_set<int>. Hash functor for int is quite
// predictable so it helps bench very specific use cases.
template<typename _ContType>
void bench(const char* desc)
{
using namespace __gnu_test;
time_counter time;
resource_counter resource;
const int nb = 200000;
start_counters(time, resource);
_ContType us;
for (int i = 0; i != nb; ++i)
us.insert(i);
stop_counters(time, resource);
std::ostringstream ostr;
ostr << desc << ": first insert";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
// Here is the worst erase use case when hashtable implementation was
// something like vector<forward_list<>>. Erasing from the end was very
// costly because we need to return the iterator following the erased
// one, as the hashtable is getting emptier at each step there are
// more and more empty bucket to loop through to reach the end of the
// container and find out that it was in fact the last element.
for (int j = nb - 1; j >= 0; --j)
{
auto it = us.find(j);
if (it != us.end())
us.erase(it);
}
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": erase from iterator";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
// This is a worst insertion use case for the current implementation as
// we insert an element at the beginning of the hashtable and then we
// insert starting at the end so that each time we need to seek up to the
// first bucket to find the first non-empty one.
us.insert(0);
for (int i = nb - 1; i >= 0; --i)
us.insert(i);
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": second insert";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
for (int j = nb - 1; j >= 0; --j)
us.erase(j);
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": erase from key";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
}
// Bench using unordered_set<string> that show how important it is to cache
// hash code as computing string hash code is quite expensive compared to
// computing it for int.
template<typename _ContType>
void bench_str(const char* desc)
{
using namespace __gnu_test;
time_counter time;
resource_counter resource;
const int nb = 200000;
// First generate once strings that are going to be used throughout the
// bench:
std::ostringstream ostr;
std::vector<std::string> strs;
strs.reserve(nb);
for (int i = 0; i != nb; ++i)
{
ostr.str("");
ostr << "string #" << i;
strs.push_back(ostr.str());
}
start_counters(time, resource);
_ContType us;
for (int i = 0; i != nb; ++i)
us.insert(strs[i]);
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": first insert";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
for (int j = nb - 1; j >= 0; --j)
{
auto it = us.find(strs[j]);
if (it != us.end())
us.erase(it);
}
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": erase from iterator";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
us.insert(strs[0]);
for (int i = nb - 1; i >= 0; --i)
us.insert(strs[i]);
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": second insert";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
start_counters(time, resource);
for (int j = nb - 1; j >= 0; --j)
us.erase(strs[j]);
stop_counters(time, resource);
ostr.str("");
ostr << desc << ": erase from key";
report_performance(__FILE__, ostr.str().c_str(), time, resource);
}
}
template<bool cache>
using __uset =
std::__uset_hashtable<int, std::hash<int>, std::equal_to<int>,
std::allocator<int>,
std::__uset_traits<cache>>;
template<bool cache>
using __tr1_uset =
std::tr1::__unordered_set<int, std::hash<int>, std::equal_to<int>,
std::allocator<int>,
cache>;
template<bool cache>
using __str_uset =
std::__uset_hashtable<std::string, std::hash<std::string>,
std::equal_to<std::string>,
std::allocator<std::string>,
std::__uset_traits<cache>>;
template<bool cache>
using __tr1_str_uset =
std::tr1::__unordered_set<std::string, std::hash<std::string>,
std::equal_to<std::string>,
std::allocator<std::string>,
cache>;
int main()
{
bench<__tr1_uset<false>>(
"std::tr1::unordered_set<int> without hash code cached");
bench<__tr1_uset<true>>(
"std::tr1::unordered_set<int> with hash code cached");
bench<__uset<false>>(
"std::unordered_set<int> without hash code cached");
bench<__uset<true>>(
"std::unordered_set<int> with hash code cached");
bench<std::unordered_set<int>>(
"std::unordered_set<int> default cache");
bench_str<__tr1_str_uset<false>>(
"std::tr1::unordered_set<string> without hash code cached");
bench_str<__tr1_str_uset<true>>(
"std::tr1::unordered_set<string> with hash code cached");
bench_str<__str_uset<false>>(
"std::unordered_set<string> without hash code cached");
bench_str<__str_uset<true>>(
"std::unordered_set<string> with hash code cached");
bench_str<std::unordered_set<std::string>>(
"std::unordered_set<string> default cache");
return 0;
}
|
