我在OpenCV中通过与仅用于简单数组求和和和乘法的正常操作进行比较来测试parallel_for_。

我有一个由100个整数组成的数组，每个整数分成10个，并使用parallel_for_运行。

然后，我也有正常的0到99运算，用于求和和和多次叠加。

然后我测量了经过的时间，正常操作比parallel_for_操作快。

我的CPU是Intel（R）Core（TM）i7-2600 Quard Core CPU。CCD_ 4运算求和耗时0.002秒（耗时2个时钟周期），乘法耗时0.003秒（耗时3个时钟循环）。

但正常操作需要0.0000秒（不到一个点击周期）才能完成求和和和乘法运算。我错过了什么？我的代码如下。

测试等级

#include <opencv2coreinternal.hpp>
#include <opencv2corecore.hpp>
#include <tbbtbb.h>
using namespace tbb;
using namespace cv;
template <class type>
class Parallel_clipBufferValues:public cv::ParallelLoopBody
{
   private:
       type *buffertoClip;
       type maxSegment;
       char typeOperation;//m = mul, s = summation
       static double total;
   public:
       Parallel_clipBufferValues(){ParallelLoopBody::ParallelLoopBody();};
       Parallel_clipBufferValues(type *buffertoprocess, const type max, const char op): buffertoClip(buffertoprocess), maxSegment(max), typeOperation(op){ 
           if(typeOperation == 's')
                total = 0; 
           else if(typeOperation == 'm')
                total = 1; 
       }
       ~Parallel_clipBufferValues(){ParallelLoopBody::~ParallelLoopBody();};
       virtual void operator()(const cv::Range &r) const{
           double tot = 0;        
           type *inputOutputBufferPTR = buffertoClip+(r.start*maxSegment);
           for(int i = 0; i < 10; ++i)
           {
               if(typeOperation == 's')
                  total += *(inputOutputBufferPTR+i);
               else if(typeOperation == 'm')
                  total *= *(inputOutputBufferPTR+i);
           }
       }
       static double getTotal(){return total;}
       void normalOperation(){
           //int iteration = sizeof(buffertoClip)/sizeof(type);
           if(typeOperation == 'm')
           {
               for(int i = 0; i < 100; ++i)
               {
                  total *= buffertoClip[i];
               }
           }
           else if(typeOperation == 's')
           {
               for(int i = 0; i < 100; ++i)
               {
                  total += buffertoClip[i];
               }
           }
       }
};

主要

    #include "stdafx.h"
    #include "TestClass.h"
    #include <ctime>
    double Parallel_clipBufferValues<int>::total;
    int _tmain(int argc, _TCHAR* argv[])
    {
        const int SIZE=100;
        int myTab[SIZE];
        double totalSum_by_parallel;
        double totalSun_by_normaloperation;
        double elapsed_secs_parallel;
        double elapsed_secs_normal;
        for(int i = 1; i <= SIZE; i++)
        {
            myTab[i-1] = i;
        }
        int maxSeg =10;
        clock_t begin_parallel = clock();
        cv::parallel_for_(cv::Range(0,maxSeg), Parallel_clipBufferValues<int>(myTab, maxSeg, 'm'));
        totalSum_by_parallel = Parallel_clipBufferValues<int>::getTotal();
        clock_t end_parallel = clock();
        elapsed_secs_parallel = double(end_parallel - begin_parallel) / CLOCKS_PER_SEC;
        clock_t begin_normal = clock();
        Parallel_clipBufferValues<int> norm_op(myTab, maxSeg, 'm');
        norm_op.normalOperation();
        totalSun_by_normaloperation = norm_op.getTotal();
        clock_t end_normal = clock();
        elapsed_secs_normal = double(end_normal - begin_normal) / CLOCKS_PER_SEC;
        return 0;
    }