我一直认为std::vector是“作为数组实现的”,等等等等。今天我去测试了一下,结果似乎不是这样:

以下是一些测试结果:

UseArray completed in 2.619 seconds
UseVector completed in 9.284 seconds
UseVectorPushBack completed in 14.669 seconds
The whole thing completed in 26.591 seconds

这大约要慢3 - 4倍!这并不能证明“向量可能会慢几纳秒”的评论是正确的。

我使用的代码是:

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

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

        std::vector<Pixel> pixels;
        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()
{
    TestTimer t("UseVectorPushBack");

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

        std::vector<Pixel> pixels;
            pixels.reserve(dimension * dimension);

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

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

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

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

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

        free(pixels);
    }
}

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

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

    return 0;
}

我做错了吗?还是我刚刚打破了这个性能神话?

我使用Visual Studio 2005中的发布模式。


在Visual c++中,#define _SECURE_SCL 0将UseVector减少了一半(减少到4秒)。在我看来,这真的是件大事。


当前回答

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;
}

其他回答

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。

GNU's STL (and others), given vector<T>(n), default constructs a prototypal object T() - the compiler will optimise away the empty constructor - but then a copy of whatever garbage happened to be in the memory addresses now reserved for the object is taken by the STL's __uninitialized_fill_n_aux, which loops populating copies of that object as the default values in the vector. So, "my" STL is not looping constructing, but constructing then loop/copying. It's counter intuitive, but I should have remembered as I commented on a recent stackoverflow question about this very point: the construct/copy can be more efficient for reference counted objects etc..

So:

vector<T> x(n);

or

vector<T> x;
x.resize(n);

是-在许多STL实现中-类似于:

T temp;
for (int i = 0; i < n; ++i)
    x[i] = temp;

The issue being that the current generation of compiler optimisers don't seem to work from the insight that temp is uninitialised garbage, and fail to optimise out the loop and default copy constructor invocations. You could credibly argue that compilers absolutely shouldn't optimise this away, as a programmer writing the above has a reasonable expectation that all the objects will be identical after the loop, even if garbage (usual caveats about 'identical'/operator== vs memcmp/operator= etc apply). The compiler can't be expected to have any extra insight into the larger context of std::vector<> or the later usage of the data that would suggest this optimisation safe.

这可以与更明显的直接实现形成对比:

for (int i = 0; i < n; ++i)
    x[i] = T();

我们可以期待一个编译器优化。

为了更明确地解释vector行为的这一方面,可以考虑:

std::vector<big_reference_counted_object> x(10000);

显然,如果我们创建10000个独立对象,而不是创建10000个引用相同数据的对象,这是一个很大的区别。有一种合理的观点认为,保护普通c++用户不意外地做一些如此昂贵的事情的好处超过了现实世界中难以优化的拷贝构造的非常小的成本。

原始答案(供参考/理解评论): 没有机会。Vector和数组一样快,至少如果你合理地保留空间. ...

当我第一次看您的代码时,这很难说是一个公平的比较;我还以为你不是在比较苹果和苹果。所以我想,让构造函数和析构函数在所有测试中都被调用;然后比较。

const size_t dimension = 1000;

void UseArray() {
    TestTimer t("UseArray");
    for(size_t j = 0; j < dimension; ++j) {
        Pixel* pixels = new Pixel[dimension * dimension];
        for(size_t i = 0 ; i < dimension * dimension; ++i) {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = (unsigned char) (i % 255);
        }
        delete[] pixels;
    }
}

void UseVector() {
    TestTimer t("UseVector");
    for(size_t j = 0; j < dimension; ++j) {
        std::vector<Pixel> pixels(dimension * dimension);
        for(size_t i = 0; i < dimension * dimension; ++i) {
            pixels[i].r = 255;
            pixels[i].g = 0;
            pixels[i].b = (unsigned char) (i % 255);
        }
    }
}

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

    UseArray();
    UseVector();

    return 0;
}

我的想法是,在这样的设置下,它们应该是完全相同的。事实证明,我错了。

UseArray completed in 3.06 seconds
UseVector completed in 4.087 seconds
The whole thing completed in 10.14 seconds

那么为什么会出现30%的性能损失呢?STL的所有内容都在头文件中,因此编译器应该能够理解所需的所有内容。

我的想法是,它是在循环如何初始化默认构造函数的所有值。所以我做了一个测试:

class Tester {
public:
    static int count;
    static int count2;
    Tester() { count++; }
    Tester(const Tester&) { count2++; }
};
int Tester::count = 0;
int Tester::count2 = 0;

int main() {
    std::vector<Tester> myvec(300);
    printf("Default Constructed: %i\nCopy Constructed: %i\n", Tester::count, Tester::count2);

    return 0;
}

结果如我所料:

Default Constructed: 1
Copy Constructed: 300

这显然是减速的根源,因为vector使用复制构造函数从默认构造的对象初始化元素。

这意味着,以下伪操作顺序发生在向量的构造过程中:

Pixel pixel;
for (auto i = 0; i < N; ++i) vector[i] = pixel;

由于编译器创建了隐式复制构造函数,扩展为:

Pixel pixel;
for (auto i = 0; i < N; ++i) {
    vector[i].r = pixel.r;
    vector[i].g = pixel.g;
    vector[i].b = pixel.b;
}

所以默认像素保持未初始化,而其余的初始化使用默认像素的未初始化值。

与New[]/Delete[]相比:

int main() {
    Tester* myvec = new Tester[300];

    printf("Default Constructed: %i\nCopy Constructed:%i\n", Tester::count, Tester::count2);

    delete[] myvec;

    return 0;
}

Default Constructed: 300
Copy Constructed: 0

它们都保留了未初始化的值,并且没有对序列进行两次迭代。

有了这些信息,我们如何进行测试呢?让我们试着重写隐式复制构造函数。

Pixel(const Pixel&) {}

结果呢?

UseArray completed in 2.617 seconds
UseVector completed in 2.682 seconds
The whole thing completed in 5.301 seconds

总而言之,如果你经常制作数百个向量:重新考虑你的算法。

在任何情况下,STL实现都不会因为某些未知的原因而变慢,它只是完全按照你的要求去做;希望你能明白。

这是一个古老而流行的问题。

在这一点上,许多程序员将使用c++ 11。在c++ 11中,OP的代码对于UseArray或UseVector运行得同样快。

UseVector completed in 3.74482 seconds
UseArray completed in 3.70414 seconds

基本的问题是,当你的像素结构未初始化时,std::vector<T>::resize(size_t, T const&=T())接受一个默认构造的像素并复制它。编译器没有注意到它被要求复制未初始化的数据,所以它实际执行了复制。

在c++ 11中,std::vector<T>::resize有两个重载。第一个是std::vector<T>::resize(size_t),另一个是std::vector<T>::resize(size_t, T const&)。这意味着当调用resize而不带第二个参数时,它只是默认构造,而编译器足够聪明,可以意识到默认构造什么也不做,因此它跳过了缓冲区的传递。

(添加这两个重载是为了处理可移动、可构造和不可复制类型——处理未初始化数据时的性能提升是一个额外的好处)。

push_back解决方案还执行fencepost检查,这降低了它的速度,因此它仍然比malloc版本慢。

现场示例(我还用chrono::high_resolution_clock替换了计时器)。

注意,如果你有一个通常需要初始化的结构,但你想在增加缓冲区后处理它,你可以使用自定义std::vector分配器来做到这一点。如果你想把它移动到一个更正常的std::vector,我相信仔细使用allocator_traits和重写==可能会成功,但我不确定。

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。