C 风格 Arrays 与使用 std::vector::at、std::vector::operator[] 和迭代器的 std::vector
[英]C-style Arrays vs std::vector using std::vector::at, std::vector::operator[], and iterators
问题描述
我有一个应用程序，我必须使用带有目标索引列表的第三个数组（ map ）将数据从一个数组（ input ）移动到另一个数组（ output ）。 以一种简化的方式，我想做一些类似于output[i] = input[ map[i] ]的事情。
我做了以下测试，试图估计在使用 C 风格的 arrays 和 std::vector 以及在 std::vector 使用不同的运算符和迭代器的情况下，哪一个会给我带来更好的性能。 我知道操作符std::vector::at()在进行边界检查时会降低性能，我想估计这会对性能造成多大影响，以确定它是否值得。
我编写了一个示例应用程序，在其中使用不同的结构和运算符移动数据。 我使用gprof在 Linux 下对其进行了分析。
这是应用程序源代码 ( test.cpp )：
#include <iostream>
#include <vector>
#include <assert.h>
#include <limits.h>
// Input and output vector size
const std::size_t vector_size = 4096;
// Size of the map vector. This value must be
// <= 'vector_size'
const std::size_t map_size = 2000;
// Number of iteration for each algorithm
const std::size_t num_iterations = 1000000;
// Algorithms
void __attribute__ ((noinline)) map_c_array(int *in, std::size_t *map, int *out)
{
for (std::size_t j {0}; j < map_size; j++)
out[j] = in[map[j]];
}
void __attribute__ ((noinline)) map_vector_v1(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out.at(j++) = in.at(m);
}
void __attribute__ ((noinline)) map_vector_v2(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out.at(j) = in.at(map.at(j));
}
void __attribute__ ((noinline)) map_vector_v3(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out[j++] = in[m];
}
void __attribute__ ((noinline)) map_vector_v4(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out[j] = in[map[j]];
}
void __attribute__ ((noinline)) map_vector_v5(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (std::vector<std::size_t>::const_iterator mapIt { map.begin() }; mapIt != map.end(); ++mapIt)
*outIt++ = *(inIt + *mapIt);
}
void __attribute__ ((noinline)) map_vector_v6(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (auto const& m : map)
*outIt++ = *(inIt + m);
}
// Main program
int main(int argc, char *argv[])
{
// Run the algorithm based on vectors
for (std::size_t k {0}; k < 6; ++k)
{
// Input vector. It is of size = 'vector_size'
std::vector<int> in(vector_size, 0);
// Output vector. It is of size = 'vector_size'
std::vector<int> out(vector_size, 0);
// Mask Vector. I want to do out[i] = in[ map[i] ]
// Its values are indexes of the 'in' vector, so they all need
// to be less than or equal to 'vector_size'
// It is of size = 'map_size'. To each value in this vector there will
// be a corresponding value in the 'out' vector. So, 'map_size' need to
// be less than or equal to 'vector_size'.
std::vector<std::size_t> map(map_size, 0);
// Fill input vector with random numbers
for (std::size_t i {0}; i < vector_size; ++i)
in.at(i) = static_cast<int>( static_cast<float>(rand())/RAND_MAX * INT_MIN );
// Fill the map vector with random number, not greater that the
// maximum size of the in and out vectors.
for (std::size_t i {0}; i < map_size; ++i)
map.at(i) = static_cast<std::size_t>( static_cast<float>(rand())/RAND_MAX * vector_size );
// Copy the values using each algorithm
switch (k)
{
case 0:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v1(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
case 1:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v2(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
case 2:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v3(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
case 3:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v4(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
case 4:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v5(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
case 5:
for (std::size_t i {0}; i < num_iterations; ++i )
{
map_vector_v6(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
break;
}
}
// Finally, run the algorithm based on C arrays
{
// Input vector. It is of size = 'vector_size'
int in[vector_size];
// Output vector. It is of size = 'vector_size'
int out[vector_size];
// Mask Vector. I want to do out[i] = in[ map[i] ]
// Its values are indexes of the 'in' vector, so they all need
// to be less than or equal to 'vector_size'
// It is of size = 'map_size'. To each value in this vector there will
// be a corresponding value in the 'out' vector. So, 'map_size' need to
// be less than or equal to 'vector_size'.
std::size_t map[map_size];
// Fill input vector with random numbers
for (std::size_t i {0}; i < vector_size; ++i)
in[i] = static_cast<int>( static_cast<float>(rand())/RAND_MAX * INT_MIN );
// Fill the map vector with random number, not greater that the
// maximum size of the in and out vectors.
for (std::size_t i {0}; i < map_size; ++i)
map[i] = static_cast<std::size_t>( static_cast<float>(rand())/RAND_MAX * vector_size );
for (std::size_t i {0}; i < num_iterations; ++i)
{
map_c_array(in, map, out);
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
}
}
}
（注意：我使用noinline属性来避免编译器内联我的函数，正如我想在gprof中看到的那样）。
我编译它：
g++ -o test test.cpp -Wall -g -O3 -pg
然后我得到了个人资料：
gprof test
这是结果：
Flat profile:
Each sample counts as 0.01 seconds.
% cumulative self self total
time seconds seconds calls Ts/call Ts/call name
35.42 3.29 3.29 map_vector_v2(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
17.17 4.89 1.60 map_vector_v1(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
11.34 5.94 1.05 map_vector_v3(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
10.37 6.90 0.96 map_vector_v5(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
9.72 7.81 0.90 map_vector_v4(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
8.64 8.61 0.80 map_c_array(int*, unsigned long*, int*)
7.67 9.32 0.71 map_vector_v6(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
0.00 9.32 0.00 1 0.00 0.00 _GLOBAL__sub_I__Z11map_c_arrayPiPmS_
% the percentage of the total running time of the
time program used by this function.
cumulative a running sum of the number of seconds accounted
seconds for by this function and those listed above it.
self the number of seconds accounted for by this
seconds function alone. This is the major sort for this
listing.
calls the number of times this function was invoked, if
this function is profiled, else blank.
self the average number of milliseconds spent in this
ms/call function per call, if this function is profiled,
else blank.
total the average number of milliseconds spent in this
ms/call function and its descendents per call, if this
function is profiled, else blank.
name the name of the function. This is the minor sort
for this listing. The index shows the location of
the function in the gprof listing. If the index is
in parenthesis it shows where it would appear in
the gprof listing if it were to be printed.
Copyright (C) 2012-2018 Free Software Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved.
Call graph (explanation follows)
granularity: each sample hit covers 2 byte(s) for 0.11% of 9.32 seconds
index % time self children called name
<spontaneous>
[1] 35.3 3.29 0.00 map_vector_v2(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [1]
-----------------------------------------------
<spontaneous>
[2] 17.1 1.60 0.00 map_vector_v1(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [2]
-----------------------------------------------
<spontaneous>
[3] 11.3 1.05 0.00 map_vector_v3(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [3]
-----------------------------------------------
<spontaneous>
[4] 10.3 0.96 0.00 map_vector_v5(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [4]
-----------------------------------------------
<spontaneous>
[5] 9.7 0.90 0.00 map_vector_v4(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [5]
-----------------------------------------------
<spontaneous>
[6] 8.6 0.80 0.00 map_c_array(int*, unsigned long*, int*) [6]
-----------------------------------------------
<spontaneous>
[7] 7.6 0.71 0.00 map_vector_v6(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [7]
-----------------------------------------------
0.00 0.00 1/1 __libc_csu_init [21]
[15] 0.0 0.00 0.00 1 _GLOBAL__sub_I__Z11map_c_arrayPiPmS_ [15]
-----------------------------------------------
This table describes the call tree of the program, and was sorted by
the total amount of time spent in each function and its children.
Each entry in this table consists of several lines. The line with the
index number at the left hand margin lists the current function.
The lines above it list the functions that called this function,
and the lines below it list the functions this one called.
This line lists:
index A unique number given to each element of the table.
Index numbers are sorted numerically.
The index number is printed next to every function name so
it is easier to look up where the function is in the table.
% time This is the percentage of the `total' time that was spent
in this function and its children. Note that due to
different viewpoints, functions excluded by options, etc,
these numbers will NOT add up to 100%.
self This is the total amount of time spent in this function.
children This is the total amount of time propagated into this
function by its children.
called This is the number of times the function was called.
If the function called itself recursively, the number
only includes non-recursive calls, and is followed by
a `+' and the number of recursive calls.
name The name of the current function. The index number is
printed after it. If the function is a member of a
cycle, the cycle number is printed between the
function's name and the index number.
For the function's parents, the fields have the following meanings:
self This is the amount of time that was propagated directly
from the function into this parent.
children This is the amount of time that was propagated from
the function's children into this parent.
called This is the number of times this parent called the
function `/' the total number of times the function
was called. Recursive calls to the function are not
included in the number after the `/'.
name This is the name of the parent. The parent's index
number is printed after it. If the parent is a
member of a cycle, the cycle number is printed between
the name and the index number.
If the parents of the function cannot be determined, the word
`<spontaneous>' is printed in the `name' field, and all the other
fields are blank.
For the function's children, the fields have the following meanings:
self This is the amount of time that was propagated directly
from the child into the function.
children This is the amount of time that was propagated from the
child's children to the function.
called This is the number of times the function called
this child `/' the total number of times the child
was called. Recursive calls by the child are not
listed in the number after the `/'.
name This is the name of the child. The child's index
number is printed after it. If the child is a
member of a cycle, the cycle number is printed
between the name and the index number.
If there are any cycles (circles) in the call graph, there is an
entry for the cycle-as-a-whole. This entry shows who called the
cycle (as parents) and the members of the cycle (as children.)
The `+' recursive calls entry shows the number of function calls that
were internal to the cycle, and the calls entry for each member shows,
for that member, how many times it was called from other members of
the cycle.
Copyright (C) 2012-2018 Free Software Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved.
Index by function name
[15] _GLOBAL__sub_I__Z11map_c_arrayPiPmS_ (test.cpp) [1] map_vector_v2(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [4] map_vector_v5(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
[6] map_c_array(int*, unsigned long*, int*) [3] map_vector_v3(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [7] map_vector_v6(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
[2] map_vector_v1(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&) [5] map_vector_v4(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
我看见：
- 当使用
std::vector::at()相对于std::vector:operator[]（map_vector_v1vsmap_vector_v3）时，显着的性能影响大约慢 60%。 - 似乎使用迭代器比使用
std::vector::operator[](map_vector_v6vsmap_vector_v3) 快 30% 左右。 - 我有点惊讶
map_vector_v6比使用 C 风格的 arrays (map_c_array) 稍微快一点。 - 我认为
map_vector_v5和map_vector_v6是等价的，所以我很惊讶map_vector_v6更快。
我最初的想法是使用map_vector_v1 。 但现在我想我将 go 和map_vector_v6确保我的map向量的值没有超出范围。
我想分享这个结果，以防它可以帮助其他人，或者如果我做错了什么会影响我的结果。
注意：我正在 Ubuntu 18.04 中编译和运行此代码，其中：
$ g++ --version
g++ (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Copyright (C) 2017 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
$ gprof --version
GNU gprof (GNU Binutils for Ubuntu) 2.30
Based on BSD gprof, copyright 1983 Regents of the University of California.
This program is free software. This program has absolutely no warranty.
编辑：
感谢您的所有评论。 我对我的代码进行了一些更改，例如在每次迭代中生成新的 map 和输入向量，并在每次迭代结束时对 output 向量进行一些操作以避免它被优化。 我还添加了第二个使用指针的 C 风格版本，结果证明它更快。
这是更新的代码。
#include <iostream>
#include <vector>
#include <assert.h>
#include <limits.h>
#include <math.h>
// Input and output vector size
const std::size_t vector_size = 4096;
// Size of the map vector. This value must be
// <= 'vector_size'
const std::size_t map_size = 2000;
// Number of iteration for each algorithm
const std::size_t num_iterations = 1000000;
// Algorithms
void __attribute__ ((noinline)) map_c_array(int *in, std::size_t *map, int *out)
{
for (std::size_t j {0}; j < map_size; j++)
out[j] = in[map[j]];
}
void __attribute__ ((noinline)) map_c_array_v2(int *in, std::size_t *map, int *out)
{
for (std::size_t j {0}; j < map_size; j++)
*out++ = *(in + *map++);
}
void __attribute__ ((noinline)) map_vector_v1(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out.at(j++) = in.at(m);
}
void __attribute__ ((noinline)) map_vector_v2(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out.at(j) = in.at(map.at(j));
}
void __attribute__ ((noinline)) map_vector_v3(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out[j++] = in[m];
}
void __attribute__ ((noinline)) map_vector_v4(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out[j] = in[map[j]];
}
void __attribute__ ((noinline)) map_vector_v5(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (std::vector<std::size_t>::const_iterator mapIt { map.begin() }; mapIt != map.end(); ++mapIt)
*outIt++ = *(inIt + *mapIt);
}
void __attribute__ ((noinline)) map_vector_v6(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (auto const& m : map)
*outIt++ = *(inIt + m);
}
// Main program
int main(int argc, char *argv[])
{
// Run algorithms based on vectors
for (std::size_t k {0}; k < 6; ++k)
{
// Run 'num_itertions' iteration for each algorithm
for (std::size_t i {0}; i < num_iterations; ++i )
{
// Input vector. It is of size = 'vector_size'
std::vector<int> in(vector_size, 0);
// Output vector. It is of size = 'vector_size'
std::vector<int> out(vector_size, 0);
// Mask Vector. I want to do out[i] = in[ map[i] ]
// Its values are indexes of the 'in' vector, so they all need
// to be less than or equal to 'vector_size'
// It is of size = 'map_size'. To each value in this vector there will
// be a corresponding value in the 'out' vector. So, 'map_size' need to
// be less than or equalt to 'vector_size'.
std::vector<std::size_t> map(map_size, 0);
// Fill input vector with random numbers
for (std::size_t i {0}; i < vector_size; ++i)
in.at(i) = static_cast<int>( static_cast<float>(rand())/RAND_MAX * INT_MIN );
// Fill the map vector with random number, not greater that the
// maximum size of the in and out vectors.
for (std::size_t i {0}; i < map_size; ++i)
map.at(i) = static_cast<std::size_t>( static_cast<float>(rand())/RAND_MAX * ( vector_size - 1 ) );
// Copy the values using each algorithm
switch (k)
{
case 0:
map_vector_v1(in, map, out);
break;
case 1:
map_vector_v2(in, map, out);
break;
case 2:
map_vector_v3(in, map, out);
break;
case 3:
map_vector_v4(in, map, out);
break;
case 4:
map_vector_v5(in, map, out);
break;
case 5:
map_vector_v6(in, map, out);
break;
}
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
// Do some operation in the data
for (std::size_t i {0}; i < map_size; ++i)
out[i] += rand();
}
}
// Run algorithms based on C arrays
{
// Run the algorithm based on vectors
for (std::size_t k {0}; k < 2; ++k)
{
for (std::size_t i {0}; i < num_iterations; ++i)
{
// Input vector. It is of size = 'vector_size'
int in[vector_size];
// Output vector. It is of size = 'vector_size'
int out[vector_size];
// Mask Vector. I want to do out[i] = in[ map[i] ]
// Its values are indexes of the 'in' vector, so they all need
// to be less than or equal to 'vector_size'
// It is of size = 'map_size'. To each value in this vector there will
// be a corresponding value in the 'out' vector. So, 'map_size' need to
// be less than or equalt to 'vector_size'.
std::size_t map[map_size];
// Fill input vector with random numbers
for (std::size_t i {0}; i < vector_size; ++i)
in[i] = static_cast<int>( static_cast<float>(rand())/RAND_MAX * INT_MIN );
// Fill the map vector with random number, not greater that the
// maximum size of the in and out vectors.
for (std::size_t i {0}; i < map_size; ++i)
map[i] = static_cast<std::size_t>( static_cast<float>(rand())/RAND_MAX * ( vector_size - 1 ) );
// Copy the values using each algorithm
switch (k)
{
case 0:
map_c_array(in, map, out);
break;
case 1:
map_c_array_v2(in, map, out);
break;
}
// Verify that the values were copied correctly
for (std::size_t i {0}; i < map_size; ++i)
assert( out[i] == in[map[i]] );
// Do some operation in the data
for (std::size_t i {0}; i < map_size; ++i)
out[i] += rand();
}
}
}
}
这是我现在看到的结果：
Flat profile:
Each sample counts as 0.01 seconds.
% cumulative self self total
time seconds seconds calls Ts/call Ts/call name
30.55 3.88 3.88 map_vector_v2(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
17.76 6.14 2.26 map_vector_v1(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
10.66 7.49 1.35 map_c_array(int*, unsigned long*, int*)
9.08 8.65 1.15 map_vector_v5(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
8.92 9.78 1.13 map_vector_v3(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
7.89 10.78 1.00 map_vector_v4(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
7.89 11.79 1.00 map_vector_v6(std::vector<int, std::allocator<int> > const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<int, std::allocator<int> >&)
7.58 12.75 0.96 map_c_array_v2(int*, unsigned long*, int*)
0.00 12.75 0.00 1 0.00 0.00 _GLOBAL__sub_I__Z11map_c_arrayPiPmS_
1 个解决方案
解决方案1
0 2020-06-08 21:58:44
谢谢大家的意见。
我只想总结一下我的发现。
根据我如上所述进行的测量：
- 这 3 个 forms 表现出该组中最快的执行时间：
void map_c_array_v2(int *in, std::size_t *map, int *out)
{
for (std::size_t j {0}; j < map_size; j++)
*out++ = *(in + *map++);
}
void map_vector_v4(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out[j] = in[map[j]];
}
void map_vector_v6(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (auto const& m : map)
*outIt++ = *(inIt + m);
}
- 紧随其后的是这 2 个 forms，速度慢了约 10-15%。 他们使用额外的变量来控制循环：
void map_vector_v3(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out[j++] = in[m];
}
void map_vector_v5(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::vector<int>::const_iterator inIt { in.begin() };
std::vector<int>::iterator outIt { out.begin() };
for (std::vector<std::size_t>::const_iterator mapIt { map.begin() }; mapIt != map.end(); ++mapIt)
*outIt++ = *(inIt + *mapIt);
}
- 然后这种形式慢了大约 35%。 它与更快的
map_vector_v4非常相似，不同之处在于map_vector_v4使用const引用：
void map_c_array(int *in, std::size_t *map, int *out)
{
for (std::size_t j {0}; j < map_size; j++)
out[j] = in[map[j]];
}
- 这种形式的速度要慢 2 倍。 这个使用
std::vector::at()运算符，它进行额外的边界检查：
void map_vector_v1(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
std::size_t j {0};
for (auto const& m : map)
out.at(j++) = in.at(m);
}
- 最后，这是最慢的，几乎慢了 4 倍。 这个也使用了
std::vector::at()运算符，就像前一种情况一样，但它使用了更多的运算符（3 次而不是 2 次）
void map_vector_v2(const std::vector<int> &in, const std::vector<std::size_t> &map, std::vector<int> &out)
{
for (std::size_t j{0}; j < map_size; ++j)
out.at(j) = in.at(map.at(j));
}
转换std :: vector <char*> 到一个C风格的参数矢量arv
[英]Convert std::vector<char*> to a c-style argument vector arv
std :: vector :: insert vs std :: list :: operator []
[英]std::vector::insert vs std::list::operator[]
使用unique_ptr <std::vector> 结合c样式的数组
[英]Use unique_ptr<std::vector> in combination with c-style arrays
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
std :: vector和c风格的数组
std :: vector的C样式转换
使用C样式API迭代std :: vector中的所有元素
转换std :: vector <char*> 到一个C风格的参数矢量arv
如何从 C 样式数组初始化 std::vector？
如何廉价地将 C 样式数组分配给 std::vector？
std :: vector :: insert vs std :: list :: operator []
使用unique_ptr <std::vector> 结合c样式的数组
C ++数组与std :: vector和std :: array的效率
C ++：std :: vector []运算符
相关标签