提高字符串的分配性能

Increasing allocation performance for strings

本文关键字:分配 性能 字符串      更新时间:2023-10-16

我将Java GC测试程序移植到C++(请参阅下面的代码)和Python。Java和Python的性能远高于C++,我认为这是由于每次都必须调用new才能创建字符串。我曾经尝试过使用Boost的fast_pool_allocator,但这实际上使性能从700ms恶化到1200ms。我是不是用错了分配器,还是我应该做其他事情?

EDIT:用g++ -O3 -march=native --std=c++11 garbage.cpp -lboost_system编译。g++是版本4.8.1Python的一次迭代时间约为300ms,Java的一次循环时间约为50ms。CCD_ 4给出约700ms,CCD_。

#include <string>
#include <vector>
#include <chrono>
#include <list>
#include <iostream>
#include <boost/pool/pool_alloc.hpp>
#include <memory>
//#include <gc/gc_allocator.h>

using namespace std;
#include <sstream>
typedef boost::fast_pool_allocator<char> c_allocator;
//typedef std::allocator<char> c_allocator;
typedef basic_string<char, char_traits<char>, c_allocator> pool_string;
namespace patch {
    template <typename T> pool_string to_string(const T& in) {
        std::basic_stringstream<char, char_traits<char>, c_allocator> stm;
        stm << in;
        return stm.str();
    }
}

#include "mytime.hpp"
class Garbage {
public:
    vector<pool_string> outer;
    vector<pool_string> old;
    const int nThreads = 1;
    //static auto time = chrono::high_resolution_clock();
    void go() {
//        outer.resize(1000000);
        //old.reserve(1000000);
        auto tt = mytime::msecs();
        for (int i = 0; i < 10; ++i) {
            if (i % 100 == 0) {
                cout << "DOING AN OLD" << endl;
                doOld();
                tt = mytime::msecs();
            }
            for (int j = 0; j < 1000000/nThreads; ++j)
                outer.push_back(patch::to_string(j));
            outer.clear();
            auto t = mytime::msecs();
            cout << (t - tt) << endl;
            tt = t;
        }
    }
    void doOld() {
        old.clear();
        for (int i = 0; i < 1000000/nThreads; ++i)
            old.push_back(patch::to_string(i));
    }
};
int main() {
    Garbage().go();
}

问题是每次都要使用一个新的字符串流来转换整数。

修复它:

namespace patch {
    template <typename T> pool_string to_string(const T& in) {
        return boost::lexical_cast<pool_string>(in);
    }
}

现在的时间是:

DOING AN OLD
0.175462
0.0670085
0.0669926
0.0687969
0.0692518
0.0669318
0.0669196
0.0669187
0.0668962
0.0669185
real    0m0.801s
user    0m0.784s
sys 0m0.016s

查看Coliru直播

完整参考代码:

#include <boost/pool/pool_alloc.hpp>
#include <chrono>
#include <iostream>
#include <list>
#include <memory>
#include <sstream>
#include <string>
#include <vector>
#include <boost/lexical_cast.hpp>
//#include <gc/gc_allocator.h>
using string = std::string;
namespace patch {
    template <typename T> string to_string(const T& in) {
        return boost::lexical_cast<string>(in);
    }
}
class Timer
{
    typedef std::chrono::high_resolution_clock clock;
    clock::time_point _start;
  public:
    Timer() { reset(); }
    void reset() { _start = now(); }
    double elapsed()
    {
        using namespace std::chrono;
        auto e = now() - _start;
        return duration_cast<nanoseconds>(e).count()*1.0e-9;
    }
    clock::time_point now()
    {
        return clock::now();
    }
};

class Garbage {
    public:
        std::vector<string> outer;
        std::vector<string> old;
        const int nThreads = 1;
        void go() {
            outer.resize(1000000);
            //old.reserve(1000000);
            Timer timer;
            for (int i = 0; i < 10; ++i) {
                if (i % 100 == 0) {
                    std::cout << "DOING AN OLD" << std::endl;
                    doOld();
                }
                for (int j = 0; j < 1000000/nThreads; ++j)
                    outer.push_back(patch::to_string(j));
                outer.clear();
                std::cout << timer.elapsed() << std::endl;
                timer.reset();
            }
        }
        void doOld() {
            old.clear();
            for (int i = 0; i < 1000000/nThreads; ++i)
                old.push_back(patch::to_string(i));
        }
};
int main() {
    Garbage().go();
}

由于我的机器上没有使用boost,我将代码简化为使用标准的C++11to_string(因此意外地"修复"了他发现的问题),得到了这个:

#include <string>
#include <vector>
#include <chrono>
#include <list>
#include <iostream>
#include <memory>
//#include <gc/gc_allocator.h>
#include <sstream>
using namespace std;

class Timer
{
    typedef std::chrono::high_resolution_clock clock;
    clock::time_point _start;
    public:
    Timer() { reset(); }
    void reset() { _start = now(); }
    double elapsed()
    {
        using namespace std::chrono;
        auto e = now() - _start;
        return duration_cast<nanoseconds>(e).count()*1.0e-9;
    }
    clock::time_point now()
    {
        return clock::now();
    }
};

class Garbage {
public:
    vector<string> outer;
    vector<string> old;
    const int nThreads = 1;
Timer timer;
    void go() {
//        outer.resize(1000000);
        //old.reserve(1000000);
        for (int i = 0; i < 10; ++i) {
            if (i % 100 == 0) {
                cout << "DOING AN OLD" << endl;
                doOld();
            }
            for (int j = 0; j < 1000000/nThreads; ++j)
                outer.push_back(to_string(j));
            outer.clear();
            cout << timer.elapsed() << endl;
            timer.reset();
        }
    }
    void doOld() {
        old.clear();
        for (int i = 0; i < 1000000/nThreads; ++i)
            old.push_back(to_string(i));
    }
};
int main() {
    Garbage().go();
}

编译使用:

$ g++ -O3 -std=c++11 gc.cpp
$ ./a.out
DOING AN OLD
0.414637
0.189082
0.189143
0.186336
0.184449
0.18504
0.186302
0.186055
0.183123
0.186835

从2014年4月18日星期五开始,clang 3.5版本的源代码使用相同的编译器选项给出了类似的结果。

我的处理器是AMD Phenom(tm)II X4 965,运行频率为3.6GHz(如果我没记错的话)。