我做了一些长期以来一直想做的广泛测试。不妨分享一下。

这是我的双启动机i7-3770, 16GB Ram, x86_64, Windows 8.1和Ubuntu 16.04。更多信息和结论，备注如下。测试了MSVS 2017和g++(在Windows和Linux上)。

测试程序

#include <iostream>
#include <chrono>
//#include <algorithm>
#include <array>
#include <locale>
#include <vector>
#include <queue>
#include <deque>

// Note: total size of array must not exceed 0x7fffffff B = 2,147,483,647B
//  which means that largest int array size is 536,870,911
// Also image size cannot be larger than 80,000,000B
constexpr int long g_size = 100000;
int g_A[g_size];


int main()
{
    std::locale loc("");
    std::cout.imbue(loc);
    constexpr int long size = 100000;  // largest array stack size

    // stack allocated c array
    std::chrono::steady_clock::time_point start = std::chrono::steady_clock::now();
    int A[size];
    for (int i = 0; i < size; i++)
        A[i] = i;

    auto duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "c-style stack array duration=" << duration / 1000.0 << "ms\n";
    std::cout << "c-style stack array size=" << sizeof(A) << "B\n\n";

    // global stack c array
    start = std::chrono::steady_clock::now();
    for (int i = 0; i < g_size; i++)
        g_A[i] = i;

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "global c-style stack array duration=" << duration / 1000.0 << "ms\n";
    std::cout << "global c-style stack array size=" << sizeof(g_A) << "B\n\n";

    // raw c array heap array
    start = std::chrono::steady_clock::now();
    int* AA = new int[size];    // bad_alloc() if it goes higher than 1,000,000,000
    for (int i = 0; i < size; i++)
        AA[i] = i;

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "c-style heap array duration=" << duration / 1000.0 << "ms\n";
    std::cout << "c-style heap array size=" << sizeof(AA) << "B\n\n";
    delete[] AA;

    // std::array<>
    start = std::chrono::steady_clock::now();
    std::array<int, size> AAA;
    for (int i = 0; i < size; i++)
        AAA[i] = i;
    //std::sort(AAA.begin(), AAA.end());

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "std::array duration=" << duration / 1000.0 << "ms\n";
    std::cout << "std::array size=" << sizeof(AAA) << "B\n\n";

    // std::vector<>
    start = std::chrono::steady_clock::now();
    std::vector<int> v;
    for (int i = 0; i < size; i++)
        v.push_back(i);
    //std::sort(v.begin(), v.end());

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "std::vector duration=" << duration / 1000.0 << "ms\n";
    std::cout << "std::vector size=" << v.size() * sizeof(v.back()) << "B\n\n";

    // std::deque<>
    start = std::chrono::steady_clock::now();
    std::deque<int> dq;
    for (int i = 0; i < size; i++)
        dq.push_back(i);
    //std::sort(dq.begin(), dq.end());

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "std::deque duration=" << duration / 1000.0 << "ms\n";
    std::cout << "std::deque size=" << dq.size() * sizeof(dq.back()) << "B\n\n";

    // std::queue<>
    start = std::chrono::steady_clock::now();
    std::queue<int> q;
    for (int i = 0; i < size; i++)
        q.push(i);

    duration = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start).count();
    std::cout << "std::queue duration=" << duration / 1000.0 << "ms\n";
    std::cout << "std::queue size=" << q.size() * sizeof(q.front()) << "B\n\n";
}

结果

//////////////////////////////////////////////////////////////////////////////////////////
// with MSVS 2017:
// >> cl /std:c++14 /Wall -O2 array_bench.cpp
//
// c-style stack array duration=0.15ms
// c-style stack array size=400,000B
//
// global c-style stack array duration=0.130ms
// global c-style stack array size=400,000B
//
// c-style heap array duration=0.90ms
// c-style heap array size=4B
//
// std::array duration=0.20ms
// std::array size=400,000B
//
// std::vector duration=0.544ms
// std::vector size=400,000B
//
// std::deque duration=1.375ms
// std::deque size=400,000B
//
// std::queue duration=1.491ms
// std::queue size=400,000B
//
//////////////////////////////////////////////////////////////////////////////////////////
//
// with g++ version:
//      - (tdm64-1) 5.1.0 on Windows
//      - (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609 on Ubuntu 16.04
// >> g++ -std=c++14 -Wall -march=native -O2 array_bench.cpp -o array_bench
//
// c-style stack array duration=0ms
// c-style stack array size=400,000B
//
// global c-style stack array duration=0.124ms
// global c-style stack array size=400,000B
//
// c-style heap array duration=0.648ms
// c-style heap array size=8B
//
// std::array duration=1ms
// std::array size=400,000B
//
// std::vector duration=0.402ms
// std::vector size=400,000B
//
// std::deque duration=0.234ms
// std::deque size=400,000B
//
// std::queue duration=0.304ms
// std::queue size=400,000
//
//////////////////////////////////////////////////////////////////////////////////////////

笔记

平均10次组装。 我最初也使用std::sort()执行测试(您可以看到它被注释掉了)，但后来删除了它们，因为没有显著的相对差异。

我的结论和评论

notice how global c-style array takes almost as much time as the heap c-style array Out of all tests I noticed a remarkable stability in std::array's time variations between consecutive runs, while others especially std:: data structs varied wildly in comparison O3 optimization didn't show any noteworthy time differences Removing optimization on Windows cl (no -O2) and on g++ (Win/Linux no -O2, no -march=native) increases times SIGNIFICANTLY. Particularly for std::data structs. Overall higher times on MSVS than g++, but std::array and c-style arrays faster on Windows without optimization g++ produces faster code than microsoft's compiler (apparently it runs faster even on Windows).

判决

当然，这是用于优化构建的代码。既然问题是关于std::vector，那么是的，它是!比普通数组(优化/未优化)慢。但是当您进行基准测试时，您自然希望生成优化的代码。

对我来说，这个节目的明星是std::array。

一个更好的基准测试(我认为…)，编译器由于优化可以改变代码，因为分配的向量/数组的结果不会在任何地方使用。 结果:

$ g++ test.cpp -o test -O3 -march=native
$ ./test 
UseArray inner completed in 0.652 seconds
UseArray completed in 0.773 seconds
UseVector inner completed in 0.638 seconds
UseVector completed in 0.757 seconds
UseVectorPushBack inner completed in 6.732 seconds
UseVectorPush completed in 6.856 seconds
The whole thing completed in 8.387 seconds

编译器:

gcc version 6.2.0 20161019 (Debian 6.2.0-9)

CPU:

model name  : Intel(R) Core(TM) i7-3630QM CPU @ 2.40GHz

代码是:

#include <cstdlib>
#include <vector>

#include <iostream>
#include <string>

#include <boost/date_time/posix_time/ptime.hpp>
#include <boost/date_time/microsec_time_clock.hpp>

class TestTimer
{
    public:
        TestTimer(const std::string & name) : name(name),
            start(boost::date_time::microsec_clock<boost::posix_time::ptime>::local_time())
        {
        }

        ~TestTimer()
        {
            using namespace std;
            using namespace boost;

            posix_time::ptime now(date_time::microsec_clock<posix_time::ptime>::local_time());
            posix_time::time_duration d = now - start;

            cout << name << " completed in " << d.total_milliseconds() / 1000.0 <<
                " seconds" << endl;
        }

    private:
        std::string name;
        boost::posix_time::ptime start;
};

struct Pixel
{
    Pixel()
    {
    }

    Pixel(unsigned char r, unsigned char g, unsigned char b) : r(r), g(g), b(b)
    {
    }

    unsigned char r, g, b;
};

void UseVector(std::vector<std::vector<Pixel> >& results)
{
    TestTimer t("UseVector inner");

    for(int i = 0; i < 1000; ++i)
    {
        int dimension = 999;

        std::vector<Pixel>& pixels = results.at(i);
        pixels.resize(dimension * dimension);

        for(int i = 0; i < dimension * dimension; ++i)
        {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = 0;
        }
    }
}

void UseVectorPushBack(std::vector<std::vector<Pixel> >& results)
{
    TestTimer t("UseVectorPushBack inner");

    for(int i = 0; i < 1000; ++i)
    {
        int dimension = 999;

        std::vector<Pixel>& pixels = results.at(i);
            pixels.reserve(dimension * dimension);

        for(int i = 0; i < dimension * dimension; ++i)
            pixels.push_back(Pixel(255, 0, 0));
    }
}

void UseArray(Pixel** results)
{
    TestTimer t("UseArray inner");

    for(int i = 0; i < 1000; ++i)
    {
        int dimension = 999;

        Pixel * pixels = (Pixel *)malloc(sizeof(Pixel) * dimension * dimension);

        results[i] = pixels;

        for(int i = 0 ; i < dimension * dimension; ++i)
        {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = 0;
        }

        // free(pixels);
    }
}

void UseArray()
{
    TestTimer t("UseArray");
    Pixel** array = (Pixel**)malloc(sizeof(Pixel*)* 1000);
    UseArray(array);
    for(int i=0;i<1000;++i)
        free(array[i]);
    free(array);
}

void UseVector()
{
    TestTimer t("UseVector");
    {
        std::vector<std::vector<Pixel> > vector(1000, std::vector<Pixel>());
        UseVector(vector);
    }
}

void UseVectorPushBack()
{
    TestTimer t("UseVectorPush");
    {
        std::vector<std::vector<Pixel> > vector(1000, std::vector<Pixel>());
        UseVectorPushBack(vector);
    }
}


int main()
{
    TestTimer t1("The whole thing");

    UseArray();
    UseVector();
    UseVectorPushBack();

    return 0;
}

下面是vector中的push_back方法的工作原理:

vector在初始化时分配X个空间。 如下所述，它检查当前底层数组中是否有空间用于该项。 它复制push_back调用中的项。

调用push_back X项后:

vector将kX的空间重新分配到第二个数组中。 它将第一个数组的项复制到第二个数组。 丢弃第一个数组。 现在使用第二个数组作为存储，直到它达到kX项。

重复。如果你没有预留空间，它肯定会变慢。更重要的是，如果复制项目的成本很高，那么像这样的“push_back”会让你生吞活剥。

至于向量和数组的区别，我同意其他人的观点。在发布版中运行，打开优化，并放入更多的标志，这样微软的友好人员就不会为你而烦恼了。

还有一件事，如果你不需要调整大小，使用Boost.Array。

顺便说一下，你在使用vector的类中看到的减速也发生在标准类型中，比如int。这是一个多线程代码:

#include <iostream>
#include <cstdio>
#include <map>
#include <string>
#include <typeinfo>
#include <vector>
#include <pthread.h>
#include <sstream>
#include <fstream>
using namespace std;

//pthread_mutex_t map_mutex=PTHREAD_MUTEX_INITIALIZER;

long long num=500000000;
int procs=1;

struct iterate
{
    int id;
    int num;
    void * member;
    iterate(int a, int b, void *c) : id(a), num(b), member(c) {}
};

//fill out viterate and piterate
void * viterate(void * input)
{
    printf("am in viterate\n");
    iterate * info=static_cast<iterate *> (input);
    // reproduce member type
    vector<int> test= *static_cast<vector<int>*> (info->member);
    for (int i=info->id; i<test.size(); i+=info->num)
    {
        //printf("am in viterate loop\n");
        test[i];
    }
    pthread_exit(NULL);
}

void * piterate(void * input)
{
    printf("am in piterate\n");
    iterate * info=static_cast<iterate *> (input);;
    int * test=static_cast<int *> (info->member);
    for (int i=info->id; i<num; i+=info->num) {
        //printf("am in piterate loop\n");
        test[i];
    }
    pthread_exit(NULL);
}

int main()
{
    cout<<"producing vector of size "<<num<<endl;
    vector<int> vtest(num);
    cout<<"produced  a vector of size "<<vtest.size()<<endl;
    pthread_t thread[procs];

    iterate** it=new iterate*[procs];
    int ans;
    void *status;

    cout<<"begining to thread through the vector\n";
    for (int i=0; i<procs; i++) {
        it[i]=new iterate(i, procs, (void *) &vtest);
    //  ans=pthread_create(&thread[i],NULL,viterate, (void *) it[i]);
    }
    for (int i=0; i<procs; i++) {
        pthread_join(thread[i], &status);
    }
    cout<<"end of threading through the vector";
    //reuse the iterate structures

    cout<<"producing a pointer with size "<<num<<endl;
    int * pint=new int[num];
    cout<<"produced a pointer with size "<<num<<endl;

    cout<<"begining to thread through the pointer\n";
    for (int i=0; i<procs; i++) {
        it[i]->member=&pint;
        ans=pthread_create(&thread[i], NULL, piterate, (void*) it[i]);
    }
    for (int i=0; i<procs; i++) {
        pthread_join(thread[i], &status);
    }
    cout<<"end of threading through the pointer\n";

    //delete structure array for iterate
    for (int i=0; i<procs; i++) {
        delete it[i];
    }
    delete [] it;

    //delete pointer
    delete [] pint;

    cout<<"end of the program"<<endl;
    return 0;
}

代码中的行为表明vector的实例化是代码中最长的部分。一旦你通过瓶颈。其余的代码运行得非常快。无论在多少个线程上运行，这都是正确的。

顺便说一下，忽略那些疯狂的包含数。我一直在使用这段代码来测试一个项目的东西，所以包含的数量不断增长。

好问题。我来这里是希望能找到一些简单的方法来加快矢量测试的速度。结果跟我想象的不太一样!

优化有帮助，但这还不够。通过优化，我仍然看到UseArray和UseVector之间的2X性能差异。有趣的是，UseVector明显比没有优化的UseVectorPushBack慢。

# g++ -Wall -Wextra -pedantic -o vector vector.cpp
# ./vector
UseArray completed in 20.68 seconds
UseVector completed in 120.509 seconds
UseVectorPushBack completed in 37.654 seconds
The whole thing completed in 178.845 seconds
# g++ -Wall -Wextra -pedantic -O3 -o vector vector.cpp
# ./vector
UseArray completed in 3.09 seconds
UseVector completed in 6.09 seconds
UseVectorPushBack completed in 9.847 seconds
The whole thing completed in 19.028 seconds

想法1 -使用new[]代替malloc

我尝试在UseArray中将malloc()更改为new[]，以便构造对象。从单个字段分配到分配一个Pixel实例。哦，重命名内循环变量为j。

void UseArray()
{
    TestTimer t("UseArray");

    for(int i = 0; i < 1000; ++i)
    {   
        int dimension = 999;

        // Same speed as malloc().
        Pixel * pixels = new Pixel[dimension * dimension];

        for(int j = 0 ; j < dimension * dimension; ++j)
            pixels[j] = Pixel(255, 0, 0);

        delete[] pixels;
    }
}

令人惊讶的是(对我来说)，这些变化没有任何不同。甚至没有更改为new[]，这将默认构造所有的像素。看起来gcc在使用new[]时可以优化默认构造函数调用，但在使用vector时就不行。

想法#2 -删除重复的操作符[]调用

我还尝试摆脱三重运算符[]查找，并缓存对像素[j]的引用。这实际上降低了UseVector的速度!哦。

for(int j = 0; j < dimension * dimension; ++j)
{
    // Slower than accessing pixels[j] three times.
    Pixel &pixel = pixels[j];
    pixel.r = 255;
    pixel.g = 0;
    pixel.b = 0;
}

# ./vector 
UseArray completed in 3.226 seconds
UseVector completed in 7.54 seconds
UseVectorPushBack completed in 9.859 seconds
The whole thing completed in 20.626 seconds

想法#3 -删除构造函数

如果完全删除构造函数呢?然后，也许gcc可以在创建向量时优化所有对象的结构。如果我们把像素改为:

struct Pixel
{
    unsigned char r, g, b;
};

结果:大约快10%。还是比数组慢。嗯。

# ./vector 
UseArray completed in 3.239 seconds
UseVector completed in 5.567 seconds

想法4 -使用迭代器而不是循环索引

如何使用vector<Pixel>::iterator代替循环索引?

for (std::vector<Pixel>::iterator j = pixels.begin(); j != pixels.end(); ++j)
{
    j->r = 255;
    j->g = 0;
    j->b = 0;
}

结果:

# ./vector 
UseArray completed in 3.264 seconds
UseVector completed in 5.443 seconds

没有什么不同。至少没有变慢。我认为这将具有类似于#2的性能，其中我使用了Pixel&引用。

结论

即使一些聪明的cookie找到了如何使vector循环和数组循环一样快的方法，这也不能说明std::vector的默认行为。编译器足够聪明，可以优化所有c++特性，并使STL容器像原始数组一样快。

底线是，当使用std::vector时，编译器无法优化掉无操作的默认构造函数调用。如果你使用普通的new[]，它就能很好地优化它们。但不是std::vector。即使你可以重写你的代码，以消除构造函数调用，在这里的咒语:“编译器比你聪明。STL和普通c一样快，不用担心。”

这似乎取决于编译器标志。下面是一个基准代码:

#include <chrono>
#include <cmath>
#include <ctime>
#include <iostream>
#include <vector>


int main(){

    int size = 1000000; // reduce this number in case your program crashes
    int L = 10;

    std::cout << "size=" << size << " L=" << L << std::endl;
    {
        srand( time(0) );
        double * data = new double[size];
        double result = 0.;
        std::chrono::steady_clock::time_point start = std::chrono::steady_clock::now();
        for( int l = 0; l < L; l++ ) {
            for( int i = 0; i < size; i++ ) data[i] = rand() % 100;
            for( int i = 0; i < size; i++ ) result += data[i] * data[i];
        }
        std::chrono::steady_clock::time_point end   = std::chrono::steady_clock::now();
        auto duration = std::chrono::duration_cast<std::chrono::microseconds>(end - start).count();
        std::cout << "Calculation result is " << sqrt(result) << "\n";
        std::cout << "Duration of C style heap array:    " << duration << "ms\n";
        delete data;
    }

    {
        srand( 1 + time(0) );
        double data[size]; // technically, non-compliant with C++ standard.
        double result = 0.;
        std::chrono::steady_clock::time_point start = std::chrono::steady_clock::now();
        for( int l = 0; l < L; l++ ) {
            for( int i = 0; i < size; i++ ) data[i] = rand() % 100;
            for( int i = 0; i < size; i++ ) result += data[i] * data[i];
        }
        std::chrono::steady_clock::time_point end   = std::chrono::steady_clock::now();
        auto duration = std::chrono::duration_cast<std::chrono::microseconds>(end - start).count();
        std::cout << "Calculation result is " << sqrt(result) << "\n";
        std::cout << "Duration of C99 style stack array: " << duration << "ms\n";
    }

    {
        srand( 2 + time(0) );
        std::vector<double> data( size );
        double result = 0.;
        std::chrono::steady_clock::time_point start = std::chrono::steady_clock::now();
        for( int l = 0; l < L; l++ ) {
            for( int i = 0; i < size; i++ ) data[i] = rand() % 100;
            for( int i = 0; i < size; i++ ) result += data[i] * data[i];
        }
        std::chrono::steady_clock::time_point end   = std::chrono::steady_clock::now();
        auto duration = std::chrono::duration_cast<std::chrono::microseconds>(end - start).count();
        std::cout << "Calculation result is " << sqrt(result) << "\n";
        std::cout << "Duration of std::vector array:     " << duration << "ms\n";
    }

    return 0;
}

不同的优化标志给出不同的答案:

$ g++ -O0 benchmark.cpp 
$ ./a.out 
size=1000000 L=10
Calculation result is 181182
Duration of C style heap array:    118441ms
Calculation result is 181240
Duration of C99 style stack array: 104920ms
Calculation result is 181210
Duration of std::vector array:     124477ms
$g++ -O3 benchmark.cpp
$ ./a.out 
size=1000000 L=10
Calculation result is 181213
Duration of C style heap array:    107803ms
Calculation result is 181198
Duration of C99 style stack array: 87247ms
Calculation result is 181204
Duration of std::vector array:     89083ms
$ g++ -Ofast benchmark.cpp 
$ ./a.out 
size=1000000 L=10
Calculation result is 181164
Duration of C style heap array:    93530ms
Calculation result is 181179
Duration of C99 style stack array: 80620ms
Calculation result is 181191
Duration of std::vector array:     78830ms

您的确切结果会有所不同，但这在我的机器上是非常典型的。