1. 技术文章
  2. Why is valarray so slow?

Why is valarray so slow?

由 不问归期 提交于 2019-11-29 20:43:57

I suspect that the reason c = a*b is so much slower than performing the operations an element at a time is that the 

template<class T> valarray<T> operator*
    (const valarray<T>&, const valarray<T>&);

operator must allocate memory to put the result into, then returns that by value.

Even if a "swaptimization" is used to perform the copy, that function still has the overhead of

  • allocating the new block for the resulting valarray
  • initializing the new valarray (it's possible that this might be optimized away)
  • putting the results into the new valarray
  • paging in the memory for the new valarray as it is initialized or set with result values
  • deallocating the old valarray that gets replaced by the result

I just tried it on a Linux x86-64 system (Sandy Bridge CPU):

gcc 4.5.0:

double operator* 9.64185 ms
valarray operator* 9.36987 ms
valarray[i] operator* 9.35815 ms

Intel ICC 12.0.2:

double operator* 7.76757 ms
valarray operator* 9.60208 ms
valarray[i] operator* 7.51409 ms

In both cases I just used -O3 and no other optimisation-related flags.

It looks like the MS C++ compiler and/or valarray implementation suck.

Here's the OP's code modified for Linux:

#include <iostream>
#include <valarray>
#include <iostream>
#include <ctime>

using namespace std ;

double gettime_hp();

int main()
{
    enum { N = 5*1024*1024 };
    valarray<double> a(N), b(N), c(N) ;
    int i,j;
    for(  j=0 ; j<8 ; ++j )
    {
        for(  i=0 ; i<N ; ++i )
        {
            a[i]=rand();
            b[i]=rand();
        }

        double* a1 = &a[0], *b1 = &b[0], *c1 = &c[0] ;
        double dtime=gettime_hp();
        for(  i=0 ; i<N ; ++i ) c1[i] = a1[i] * b1[i] ;
        dtime=gettime_hp()-dtime;
        cout << "double operator* " << dtime << " ms\n" ;

        dtime=gettime_hp();
        c = a*b ;
        dtime=gettime_hp()-dtime;
        cout << "valarray operator* " << dtime << " ms\n" ;

        dtime=gettime_hp();
        for(  i=0 ; i<N ; ++i ) c[i] = a[i] * b[i] ;
        dtime=gettime_hp()-dtime;
        cout << "valarray[i] operator* " << dtime<< " ms\n" ;

        cout << "------------------------------------------------------\n" ;
    }
}

double gettime_hp()
{
    struct timespec timestamp;

    clock_gettime(CLOCK_REALTIME, &timestamp);
    return timestamp.tv_sec * 1000.0 + timestamp.tv_nsec * 1.0e-6;
}
Leo Bellantoni

The whole point of valarray is to be fast on vector machines, which x86 machines just aren't.

A good implementation on a nonvector machine should be able to match the performance that you get with something like

for (i=0; i < N; ++i) 
    c1[i] = a1[i] * b1[i];

and a bad one of course won't. Unless there is something in the hardware to expedite parallel processing, that is going to be pretty close to the best that you can do.

shangping

I finally got this through using delayed evaluation. The code may be ugly since I am just starting learning these C++ advanced concepts.

Here is the code:

#include <iostream>
#include <valarray>
#include <iostream>
#include "windows.h"

using namespace std;
SYSTEMTIME stime;
LARGE_INTEGER sys_freq;

double gettime_hp();

// To improve the c = a*b (it will generate a temporary first, assigned to 'c' and delete the temporary.
// Which causes the program really slow
// The solution is the expression template and let the compiler to decide when all the expression is known.


// Delayed evaluation
//typedef valarray<double> Vector;
class Vector;

class VecMul
{
    public:
        const Vector& va;
        const Vector& vb;
        //Vector& vc;
        VecMul(const Vector& v1, const Vector& v2): va(v1), vb(v2) {}
        operator Vector();
};

class Vector:public valarray<double>
{
    valarray<double> *p;

    public:
        explicit Vector(int n)
        {
            p = new valarray<double>(n);
        }
        Vector& operator = (const VecMul &m)
        {
            for(int i=0; i<m.va.size(); i++)
                (*p)[i] = (m.va)[i]*(m.vb)[i]; // Ambiguous
            return *this;
        }
        double& operator[](int i) const {return (*p)[i];} //const vector_type[i]
        int size()const {return (*p).size();}
};


inline VecMul operator*(const Vector& v1, const Vector& v2)
{
    return VecMul(v1, v2);
}


int main()
{
    enum {N = 5*1024*1024};
    Vector a(N), b(N), c(N);
    QueryPerformanceFrequency(&sys_freq);
    int i, j;
    for (j=0 ; j<8 ; ++j)
    {
        for (i=0 ; i<N ; ++i)
        {
            a[i] = rand();
            b[i] = rand();
        }

        double* a1 = &a[0], *b1 = &b[0], *c1 = &c[0];
        double dtime = gettime_hp();
        for (i=0 ; i<N ; ++i)
            c1[i] = a1[i] * b1[i];
        dtime = gettime_hp()-dtime;
        cout << "double operator* " << dtime << " ms\n";

        dtime = gettime_hp();
        c = a*b;
        dtime = gettime_hp()-dtime;
        cout << "valarray operator* " << dtime << " ms\n";

        dtime = gettime_hp();
        for (i=0 ; i<N ; ++i)
            c[i] = a[i] * b[i];
        dtime = gettime_hp() - dtime;
        cout << "valarray[i] operator* " << dtime << " ms\n";

        cout << "------------------------------------------------------\n";
    }
}

double gettime_hp()
{
    LARGE_INTEGER tick;
    extern LARGE_INTEGER sys_freq;
    QueryPerformanceCounter(&tick);
    return (double)tick.QuadPart*1000.0/sys_freq.QuadPart;
}

The running result on Visual studio is:

double operator* 41.2031 ms
valarray operator* 43.8407 ms
valarray[i] operator* 42.49 ms
Puppy

I'm compiling in release x64, Visual Studio 2010. I changed your code very slightly:

    double* a1 = &a[0], *b1 = &b[0], *c1 = &c[0];
    double dtime = gettime_hp();
    for (i=0 ; i<N ; ++i)
        a1[i] *= b1[i];
    dtime = gettime_hp() - dtime;
    cout << "double operator* " << dtime << " ms\n";

    dtime = gettime_hp();
    a *= b;
    dtime = gettime_hp() - dtime;
    cout << "valarray operator* " << dtime << " ms\n";

    dtime = gettime_hp();
    for (i=0 ; i<N ; ++i)
        a[i] *= b[i];
    dtime = gettime_hp() - dtime;
    cout << "valarray[i] operator* " << dtime<< " ms\n";

    cout << "------------------------------------------------------\n" ;

Here you can see that I used *= instead of c = a * b. In more modern mathematical libraries, very complex expression template mechanisms are used that eliminate this problem. In this case, I actually got very slightly faster results from valarray, although that's probably just because the contents were already in a cache. The overhead that you are seeing is simply redundant temporaries and nothing intrinsic to valarray, specifically- you'd see the same behaviour with something like std::string.

Lin Xuelei

I think Michael Burr's reply is right. And maybe you can create a virtual type as the type the return value of operator +, and reload another operator= for this virtual type like operator=(virtual type& v){&valarray=&v;v=NULL;} (roughly speaking).

Of course, it is difficult to implement the idea on valarray. But when you create a new class, you can try this idea. And then, the efficiency for operator+ is almost the same as operator+=.

user2778496

Hmm..I tested Blitz++ and it's same as valarray... And moreover, the Blitz++ [] operator is very slow.

#include <blitz/array.h>
#include <iostream>

#ifdef WIN32
#include "windows.h"
LARGE_INTEGER sys_freq;
#endif

#ifdef LINUX
<ctime>
#endif

using namespace std;
SYSTEMTIME stime;

__forceinline double gettime_hp();
double gettime_hp()
{
    #ifdef WIN32
        LARGE_INTEGER tick;
        extern LARGE_INTEGER sys_freq;
        QueryPerformanceCounter(&tick);
        return (double)tick.QuadPart * 1000.0 / sys_freq.QuadPart;
    #endif

    #ifdef LINUX
        struct timespec timestamp;

        clock_gettime(CLOCK_REALTIME, &timestamp);
        return timestamp.tv_sec * 1000.0 + timestamp.tv_nsec * 1.0e-6;
    #endif
}
BZ_USING_NAMESPACE(blitz)

int main()
{
    int N = 5*1024*1024;

    // Create three-dimensional arrays of double
    Array<double, 1> a(N), b(N), c(N);

    int i, j;

    #ifdef WIN32
        QueryPerformanceFrequency(&sys_freq);
    #endif

    for (j=0 ; j<8 ; ++j)
    {
        for (i=0 ; i<N ; ++i)
        {
            a[i] = rand();
            b[i] = rand();
        }

        double* a1 = a.data(), *b1 = b.data(), *c1 = c.data();
        double dtime = gettime_hp();
        for (i=0 ; i<N ; ++i)
            c1[i] = a1[i] * b1[i];
        dtime = gettime_hp() - dtime;
        cout << "double operator* " << dtime << " ms\n";

        dtime = gettime_hp();
        c = a*b;
        dtime = gettime_hp() - dtime;
        cout << "blitz operator* " << dtime << " ms\n";

        dtime = gettime_hp();
        for (i=0 ; i<N ; ++i)
            c[i] = a[i] * b[i];
        dtime = gettime_hp() - dtime;
        cout << "blitz[i] operator* " << dtime<< " ms\n";

        cout << "------------------------------------------------------\n";
    }
}
标签
c++
valarray
易学教程内所有资源均来自网络或用户发布的内容，如有违反法律规定的内容欢迎反馈！
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!