根据建议的解决方案,我决定整理一个小型基准。
#include <cstdint>
#include <cstring>
#include <ctime>
#include <iostream>
#include <random>
#include <vector>
using namespace std;
int main()
{
random_device seed;
mt19937 rnd(seed());
uniform_int_distribution<uint8_t> random_byte(0x00, 0xff);
const size_t n = 512 * 512;
vector<uint8_t> source;
source.reserve(n);
for (size_t i = 0; i < n; i++) source.push_back(random_byte(rnd));
clock_t start;
clock_t t_constructor1 = 0; uint8_t c_constructor1 = 0;
clock_t t_constructor2 = 0; uint8_t c_constructor2 = 0;
clock_t t_assign = 0; uint8_t c_assign = 0;
clock_t t_copy = 0; uint8_t c_copy = 0;
clock_t t_memcpy = 0; uint8_t c_memcpy = 0;
for (size_t k = 0; k < 4; k++)
{
start = clock();
for (size_t i = 0; i < n/32; i++)
{
vector<uint8_t> destination(source);
c_constructor1 += destination[i];
}
t_constructor1 += clock() - start;
start = clock();
for (size_t i = 0; i < n/32; i++)
{
vector<uint8_t> destination(source.begin(), source.end());
c_constructor2 += destination[i];
}
t_constructor2 += clock() - start;
start = clock();
for (size_t i = 0; i < n/32; i++)
{
vector<uint8_t> destination;
destination.assign(source.begin(), source.end());
c_assign += destination[i];
}
t_assign += clock() - start;
start = clock();
for (size_t i = 0; i < n/32; i++)
{
vector<uint8_t> destination(source.size());
copy(source.begin(), source.end(), destination.begin());
c_copy += destination[i];
}
t_copy += clock() - start;
start = clock();
for (size_t i = 0; i < n/32; i++)
{
vector<uint8_t> destination(source.size());
memcpy(&destination[0], &source[0], n);
c_memcpy += destination[i];
}
t_memcpy += clock() - start;
}
// Verify that all copies are correct, but also prevent the compiler
// from optimising away the loops
uint8_t diff = (c_constructor1 - c_constructor2) +
(c_assign - c_copy) +
(c_memcpy - c_constructor1);
if (diff != 0) cout << "one of the methods produces invalid copies" << endl;
cout << "constructor (1): " << t_constructor1 << endl;
cout << "constructor (2): " << t_constructor2 << endl;
cout << "assign: " << t_assign << endl;
cout << "copy " << t_copy << endl;
cout << "memcpy " << t_memcpy << endl;
return 0;
}
在我的 PC 上,使用 msvc100 为 x64 编译,完全优化,这会产生以下输出:
constructor (1): 22388
constructor (2): 22333
assign: 22381
copy 2142
memcpy 2146
结果非常清楚:std::copy
性能和 一样好std::memcpy
,而构造函数 和assign
都慢一个数量级。当然,确切的数字和比率取决于矢量大小,但 msvc100 的结论是显而易见的:正如Rapptz 所建议的,使用std::copy
.
编辑:结论对于其他编译器并不明显。我也在 64 位 Linux 上进行了测试,Clang 3.2 的结果如下
constructor (1): 530000
constructor (2): 560000
assign: 560000
copy 840000
memcpy 860000
GCC 4.8 给出了类似的输出。对于 Windows 上的 GCC,memcpy
并且copy
比构造函数 和 稍慢assign
,尽管差异较小。但是,我的经验是 GCC 在 Windows 上的优化并不好。我也测试了msvc110,结果和msvc100差不多。