原帖

从二进制数据读取整数时,我注意到memcpy比铸造解决方案慢.

版本1：reinterpret_cast,由于潜在的对齐问题而臭,但也更快(？)

int get_int_v1(const char * data) { return *reinterpret_cast<const int*>(data); }

版本2：memcpy,正确且稍慢：

int get_int_v2(const char * data) { int result; memcpy(&result,data,sizeof(result)); return result; }

我有a benchmark on Ideone.

供将来参考,代码是：

#include <cstdlib>
#include <cstdio>
#include <cstring>
#include <ctime>
#include <iostream>
#include <vector>
#include <sys/time.h>

double get_current_time()
{
    timeval tv;
    gettimeofday(&tv,NULL);
    return double (tv.tv_sec) + 0.000001 * tv.tv_usec;
}

int get_int_v1(const char * data) { return *reinterpret_cast<const int*>(data); }
int get_int_v2(const char * data) { int result; memcpy(&result,sizeof(result)); return result; }

const unsigned iterations = 200 * 1000 * 1000;

double test_v1(const char * c,unsigned & prevent_optimization)
{
    double start = get_current_time();
    for (unsigned i = 0; i != iterations; ++i)
    {
        prevent_optimization += get_int_v1(c);
    }
    return get_current_time() - start;
}

double test_v2(const char * c,unsigned & prevent_optimization)
{
    double start = get_current_time();
    for (unsigned i = 0; i != iterations; ++i)
    {
        prevent_optimization += get_int_v2(c);
    }
    return get_current_time() - start;
}

int main()
{
    srand(time(0));

    // Initialize data
    std::vector<int> numbers(1000);
    for (std::vector<int>::size_type i = 0; i != numbers.size(); ++i)
    {
        numbers[i] = i;
    }

    // Repeat benchmark 4 times.
    for (unsigned i = 0; i != 4; ++i)
    {
        unsigned p = 0;
        std::vector<int>::size_type index = rand() % numbers.size();
        const char * c = reinterpret_cast<const char *>(&numbers[index]);    
        std::cout << "v1: " << test_v1(c,p) << std::endl;
        std::cout << "v2: " << test_v2(c,p) << std::endl << std::endl;
    }
}

结果是：

v1: 0.176457
v2: 0.557588

v1: 0.17654
v2: 0.220581

v1: 0.176826
v2: 0.22012

v1: 0.176131
v2: 0.220633

我的问题是：

>我的基准是否正确？
>如果是,那么为什么v2(使用memcpy)会变慢？由于两个版本都返回了数据的副本,我认为应该没有性能差异.
>如何实施正确,快速的解决方案？

更新

我很傻,忘了考虑Ideone不执行编译器优化.我还稍微调整了一下代码并提出了以下内容：

#include <algorithm>
#include <cstdlib>
#include <cstdio>
#include <cstring>
#include <ctime>
#include <iomanip> 
#include <iostream> 
#include <vector>
#include <sys/time.h>

double get_current_time()
{
    timeval tv;
    gettimeofday(&tv,NULL);
    return double (tv.tv_sec) + 0.000001 * tv.tv_usec;
}

struct test_cast
{
    int operator()(const char * data) const 
    {
        return *((int*)data);
    }
};

struct test_memcpy
{
    int operator()(const char * data) const 
    {
        int result;
        memcpy(&result,sizeof(result));
        return result;
    }
};

struct test_std_copy
{
    int operator()(const char * data) const 
    {
        int result;
        std::copy(data,data + sizeof(int),reinterpret_cast<char *>(&result));
        return result;
    }
};

enum
{
    iterations = 2000,container_size = 2000
};

std::vector<int> get_random_numbers()
{
    std::vector<int> numbers(container_size);
    for (std::vector<int>::size_type i = 0; i != numbers.size(); ++i)
    {
        numbers[i] = rand();
    }
    return numbers;
}

std::vector<int> get_random_indices()
{
    std::vector<int> numbers(container_size);
    for (std::vector<int>::size_type i = 0; i != numbers.size(); ++i)
    {
        numbers[i] = i;
    }
    std::random_shuffle(numbers.begin(),numbers.end());
    return numbers;
}

template<typename Function>
unsigned benchmark(const Function & f,unsigned & counter)
{
    std::vector<int> container = get_random_numbers();
    std::vector<int> indices = get_random_indices();
    double start = get_current_time();
    for (unsigned iter = 0; iter != iterations; ++iter)
    {
        for (unsigned i = 0; i != container.size(); ++i)
        {
            counter += f(reinterpret_cast<const char*>(&container[indices[i]]));
        }
    }
    return unsigned(0.5 + 1000.0 * (get_current_time() - start));
}

int main()
{
    srand(time(0));
    unsigned counter = 0;

    std::cout << "cast:      " << benchmark(test_cast(),counter) << " ms" << std::endl;
    std::cout << "memcpy:    " << benchmark(test_memcpy(),counter) << " ms" << std::endl;
    std::cout << "std::copy: " << benchmark(test_std_copy(),counter) << " ms" << std::endl;
    std::cout << "(counter:  " << counter << ")" << std::endl << std::endl;

}

结果现在几乎相等(std :: copy除外,因为某些原因速度较慢)：

g++ -o test -O0 -Wall -Werror -Wextra -pedantic-errors main.cpp
cast:      56 ms
memcpy:    60 ms
std::copy: 290 ms
(counter:  2854155632)

g++ -o test -O1 -Wall -Werror -Wextra -pedantic-errors main.cpp
cast:      9 ms
memcpy:    14 ms
std::copy: 20 ms
(counter:  3524665968)

g++ -o test -O2 -Wall -Werror -Wextra -pedantic-errors main.cpp
cast:      4 ms
memcpy:    5 ms
std::copy: 20 ms
(counter:  2590914608)

g++ -o test -O3 -Wall -Werror -Wextra -pedantic-errors main.cpp
cast:      4 ms
memcpy:    5 ms
std::copy: 18 ms
(counter:  2590914608)