OpenMP和reduce()

时间:2011-04-16 16:37:07

标签: c openmp numerical-methods

我只有3个函数,一个是控制函数,接下来的两个函数是使用OpenMP以不同的方式完成的。但是函数thread1给出了另一个得分而不是thread2和控件,我不明白为什么?

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <omp.h>

float function(float x){
    return pow(x,pow(x,sin(x)));
}



 float integrate(float begin, float end, int count){
    float score = 0 , width = (end-begin)/(1.0*count), i=begin, y1, y2;


    for(i = 0; i<count; i++){
            score += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
 }
    return score; 
 }




 float thread1(float begin, float end, int count){
    float score = 0 , width = (end-begin)/(1.0*count), y1, y2;

    int i;
    #pragma omp parallel for reduction(+:score) private(y1,i) shared(count)
    for(i = 0; i<count; i++){
        y1 = ((function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0);
       score = score + y1;
    }

    return score;
 }


 float thread2(float begin, float end, int count){
    float score = 0 , width = (end-begin)/(1.0*count), y1, y2;

    int i;
    float * tab = (float*)malloc(count * sizeof(float));

    #pragma omp parallel for
    for(i = 0; i<count; i++){
            tab[i] = (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
    }

    for(i=0; i<count; i++)
            score += tab[i];
    return score;
  }


  unsigned long long int rdtsc(void){
     unsigned long long int x;
     unsigned a, d;

    __asm__ volatile("rdtsc" : "=a" (a), "=d" (d));

    return ((unsigned long long)a) | (((unsigned long long)d) << 32);
   }






   int main(int argc, char** argv){
        unsigned long long counter = 0;


    //test
       counter = rdtsc();
       printf("control: %f \n ",integrate (atof(argv[1]), atof(argv[2]), atoi(argv[3])));
       printf("control count: %lld \n",rdtsc()-counter);
        counter = rdtsc();
       printf("thread1: %f \n ",thread1(atof(argv[1]), atof(argv[2]), atoi(argv[3])));
       printf("thread1 count: %lld \n",rdtsc()-counter);
        counter = rdtsc();
       printf("thread2: %f \n ",thread2(atof(argv[1]), atof(argv[2]), atoi(argv[3])));
       printf("thread2 count: %lld \n",rdtsc()-counter);

       return 0;
      }

以下是简单的回答:

 gcc -fopenmp zad2.c -o zad -pg -lm
 env OMP_NUM_THREADS=2 ./zad 3 13 100000
 control: 5407308.500000 
 control count: 138308058 
 thread1: 5407494.000000 
 thread1 count: 96525618 
 thread2: 5407308.500000 
 thread2 count: 104770859

更新

好的,我试图更快地完成此操作,而不是计算两次的值。

double thread3(double begin, double end, int count){
     double score = 0 , width = (end-begin)/(1.0*count), yp, yk;    
     int i,j, k;

     #pragma omp parallel private (yp,yk) 
     {
       int thread_num = omp_get_num_threads();
       k = count / thread_num;

    #pragma omp for private(i) reduction(+:score) 
    for(i=0; i<thread_num; i++){
        yp = function(begin + i*k*width);
        yk = function(begin + (i*k+1)*width);
        score += (yp + yk) * width / 2.0;
        for(j=i*k +1; j<(i+1)*k; j++){
            yp = yk;
            yk = function(begin + (j+1)*width);
            score  += (yp + yk) * width / 2.0;
        }
    }

  #pragma omp for private(i) reduction(+:score) 
  for(i = k*thread_num; i<count; i++)
    score += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
 }  
   return score;
 }

但经过几次测试后,我发现得分接近正确值,但并不相等。有时其中一个线程无法启动。当我没有使用OpenMp时,值是正确的。

1 个答案:

答案 0 :(得分:15)

你正在整合一个非常强烈的峰值函数 - x (x sin(x) - 它在你整合的范围内覆盖超过7个数量级它。这是关于32位浮点数的限制,因此根据您对数字求和的顺序会出现问题。这不是一个OpenMP的东西 - 它只是一个数值敏感的东西。

The integrated function

例如,考虑这个完全串行代码执行相同的积分:

#include <stdio.h>
#include <math.h>

float function(float x){
    return pow(x,pow(x,sin(x)));
}

int main(int argc, char **argv) {

    const float begin=3., end=13.;
    const int count = 100000;
    const float width=(end-begin)/(1.*count);

    float integral1=0., integral2=0., integral3=0.;

    /* left to right */
    for (int i=0; i<count; i++) {
         integral1 += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
    }

    /* right to left */
    for (int i=count-1; i>=0; i--) {
         integral2 += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
    }

    /* centre outwards, first right-to-left, then left-to-right */
    for (int i=count/2; i<count; i++) {
         integral3 += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
    }
    for (int i=count/2-1; i>=0; i--) {
         integral3 += (function(begin+(i*width)) + function(begin+(i+1)*width)) * width/2.0;
    }

    printf("Left to right: %lf\n", integral1);
    printf("Right to left: %lf\n", integral2);
    printf("Centre outwards: %lf\n", integral3);

    return 0;
}

运行这个,我们得到:

$ ./reduce
Left to right: 5407308.500000
Right to left: 5407430.000000
Centre outwards: 5407335.500000

- 你看到的同样的差异。用两个线程进行求和必然会改变求和的顺序,所以你的答案会改变。

这里有几个选择。如果这只是一个测试问题,并且此功能实际上并不代表您将要集成的内容,那么您可能已经很好了。否则,使用不同的数值方法可能有所帮助。

但是在这里,有一个简单的解决方案 - 数字的范围超出了float的范围,使得答案对求和顺序非常敏感,但是在{{1}的范围内舒适地拟合,使问题严重得多。请注意,更改为double并不是所有内容的神奇解决方案;在某些情况下,它只是推迟了问题,或者允许你在数值方法中提出一个缺陷。但在这里它实际上很好地解决了潜在的问题。将上面的所有double更改为float s会给出:

double

另一方面,如果你需要在范围内集成这个功能,即使是双打也不会拯救你。