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。

公平地说，您不能将c++实现与C实现进行比较，即我所说的malloc版本。Malloc不创建对象——它只分配原始内存。然后不调用构造函数就把内存当作对象，这是拙劣的c++(可能是无效的——我把这个问题留给语言律师吧)。

也就是说，简单地将malloc更改为新的Pixel[维度*维度]并自由删除[]个像素，这与您所拥有的Pixel的简单实现没有太大区别。下面是我的盒子(E6600, 64位)上的结果:

UseArray completed in 0.269 seconds
UseVector completed in 1.665 seconds
UseVectorPushBack completed in 7.309 seconds
The whole thing completed in 9.244 seconds

但随着一个微小的变化，情况发生了变化:

Pixel.h

struct Pixel
{
    Pixel();
    Pixel(unsigned char r, unsigned char g, unsigned char b);

    unsigned char r, g, b;
};

Pixel.cc

#include "Pixel.h"

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

main.cc

#include "Pixel.h"
[rest of test harness without class Pixel]
[UseArray now uses new/delete not malloc/free]

编译如下:

$ g++ -O3 -c -o Pixel.o Pixel.cc
$ g++ -O3 -c -o main.o main.cc
$ g++ -o main main.o Pixel.o

我们得到了非常不同的结果:

UseArray completed in 2.78 seconds
UseVector completed in 1.651 seconds
UseVectorPushBack completed in 7.826 seconds
The whole thing completed in 12.258 seconds

使用Pixel的非内联构造函数，std::vector现在可以击败原始数组。

通过std::vector和std:allocator进行分配的复杂性似乎太多了，无法像简单的新Pixel[n]那样有效地进行优化。然而，我们可以看到问题仅仅是分配而不是vector访问，通过调整几个测试函数来创建vector/数组，将其移到循环之外:

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

    int dimension = 999;
    std::vector<Pixel> pixels;
    pixels.resize(dimension * dimension);

    for(int i = 0; i < 1000; ++i)
    {
        for(int i = 0; i < dimension * dimension; ++i)
        {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = 0;
        }
    }
}

and

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

    int dimension = 999;
    Pixel * pixels = new Pixel[dimension * dimension];

    for(int i = 0; i < 1000; ++i)
    {
        for(int i = 0 ; i < dimension * dimension; ++i)
        {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = 0;
        }
    }
    delete [] pixels;
}

我们现在得到这些结果:

UseArray completed in 0.254 seconds
UseVector completed in 0.249 seconds
UseVectorPushBack completed in 7.298 seconds
The whole thing completed in 7.802 seconds

从这里我们可以了解到std::vector可以与原始数组进行访问，但是如果你需要多次创建和删除vector/数组，在元素的构造函数没有内联的情况下，创建一个复杂的对象将比创建一个简单的数组花费更多的时间。我不认为这很令人惊讶。

尝试禁用检查迭代器并在发布模式下构建。您应该不会看到太大的性能差异。

一些分析器数据(像素对齐为32位):

g++ -msse3 -O3 -ftree-vectorize -g test.cpp -DNDEBUG && ./a.out
UseVector completed in 3.123 seconds
UseArray completed in 1.847 seconds
UseVectorPushBack completed in 9.186 seconds
The whole thing completed in 14.159 seconds

Blah

andrey@nv:~$ opannotate --source libcchem/src/a.out  | grep "Total samples for file" -A3
Overflow stats not available
 * Total samples for file : "/usr/include/c++/4.4/ext/new_allocator.h"
 *
 * 141008 52.5367
 */
--
 * Total samples for file : "/home/andrey/libcchem/src/test.cpp"
 *
 *  61556 22.9345
 */
--
 * Total samples for file : "/usr/include/c++/4.4/bits/stl_vector.h"
 *
 *  41956 15.6320
 */
--
 * Total samples for file : "/usr/include/c++/4.4/bits/stl_uninitialized.h"
 *
 *  20956  7.8078
 */
--
 * Total samples for file : "/usr/include/c++/4.4/bits/stl_construct.h"
 *
 *   2923  1.0891
 */

在分配器:

               :      // _GLIBCXX_RESOLVE_LIB_DEFECTS
               :      // 402. wrong new expression in [some_] allocator::construct
               :      void
               :      construct(pointer __p, const _Tp& __val)
141008 52.5367 :      { ::new((void *)__p) _Tp(__val); }

向量:

               :void UseVector()
               :{ /* UseVector() total:  60121 22.3999 */
...
               :
               :
 10790  4.0201 :        for (int i = 0; i < dimension * dimension; ++i) {
               :
   495  0.1844 :            pixels[i].r = 255;
               :
 12618  4.7012 :            pixels[i].g = 0;
               :
  2253  0.8394 :            pixels[i].b = 0;
               :
               :        }

数组

               :void UseArray()
               :{ /* UseArray() total:  35191 13.1114 */
               :
...
               :
   136  0.0507 :        for (int i = 0; i < dimension * dimension; ++i) {
               :
  9897  3.6874 :            pixels[i].r = 255;
               :
  3511  1.3081 :            pixels[i].g = 0;
               :
 21647  8.0652 :            pixels[i].b = 0;

大部分开销都在复制构造函数中。例如,

    std::vector < Pixel > pixels;//(dimension * dimension, Pixel());

    pixels.reserve(dimension * dimension);

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

        pixels[i].r = 255;

        pixels[i].g = 0;

        pixels[i].b = 0;
    }

它具有与数组相同的性能。

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;
}

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。