增加 C 中自动数组的大小后出现编译器错误

Question

我正在尝试计算 18456 个基因的相关性度量，但编译器 (Dev C) 在将宏 GENE 或 INDEX 增加到 4000 到 5000 之间的值后退出或大。例如，它适用于:

# define GENE 4000
# define INDEX 3000 

但不包括:

#define GENE 5000 
#define INDEX 100

输入文件是一个以空格分隔的文本文件，有 18456 行和 57 列。这是代码:

#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include <time.h>
#include <limits.h>
#define GENE 5000
#define N 57
#define INDEX 1000


int main (void) {

clock_t start, stop;
double t = 0.0;

int i, j, p, q, wp, wq;
double x;
double *S_matrix = (double *)malloc(INDEX * GENE * sizeof(double));
double sum_S, S_max;
double S[11] = {0};
double r = 0.0, xbar = 0.0, ybar = 0.0, sx = 0.0, sy = 0.0;

// read E matrix

FILE *fq;
double E[GENE][N] = {{0}};

if ((fq = fopen("E_disease.txt", "r")) == NULL ) 
{
     printf("Error\n");
     exit(EXIT_FAILURE);
}

fq = fopen("E_disease.txt","r");
printf("\n");

for (i=0;i<GENE;i++)
{
    for(j=0;j<N;j++)
    {
        fscanf(fq,"%lf",&x);
        E[i][j] = x;
    }
}


printf("\n");
fclose(fq);


// calculate correlation

assert((start = clock())!=-1);

for(p=0; p < INDEX; p++)
{
    for(q=0; q < GENE; q++)
    {
        for(i=0; i<11; i++)
        {

            /*compute xbar */
            for(j = i; j < N; j++) 
            {
                xbar += E[p][j];
            }

            xbar /= N;

            /*compute ybar*/
            for(j = i; j < N; j++) 
            {
                ybar += E[q][j];
            }

            ybar /= N;

            /* compute standard deviation of x*/
            for(j = i; j < N; j++) 
            {
                sx += (E[p][j] - xbar) * (E[p][j] - xbar);
            }

            sx = sqrt(sx);

            /* compute standard deviation of y */
            for(j = i; j < N; j++) 
            {
                sy += (E[q][j] - ybar) * (E[q][j] - ybar);
            }

            sy = sqrt(sy);

            /*compute r, the correlation coefficient between the two arrays */
            for( j = i; j < N; j++ ) 
            {
                r += (((E[p][j] - xbar)/sx) * ((E[q][j] - ybar)/sy));
            }

            r /= (N); 

            if(r>0)
            {
                S[i] = r;
            }
            else if(r<=0)
            {
                S[i] = 0;
            }

         }


         for(j=0, sum_S=0; j<11; j++)
         {  
             sum_S += S[j];
         }


         for(j=0, S_max = 0; j<11; j++)
         {
            if(S[j] > S_max)
            {
                S_max = S[j];
            }
         }

      S_matrix[p*GENE + q] = sum_S/(11*S_max);

  }

}

FILE * fs;

fs = fopen ("s_matrix.txt", "w+");

for(wp=0; wp<INDEX; ++wp)
{
    for(wq=0; wq<GENE; ++wq)
    {

        fprintf(fs, "%lf", S_matrix[wp*GENE + wq]);
        fprintf(fs, "\t");
    }

    fprintf(fs, "\n");
    printf("\n");
}

fclose(fs);

stop = clock();
t = (double) (stop-start)/CLOCKS_PER_SEC;


printf("Run time: %f\n", t);    

//print results 



//return (0);

getchar();

}

让我简化代码。当我运行下面的代码几次时，它通常会立即退出。有一次，它说找不到类似 0xff12345 的内容。另一次它打印出 S_matrix[55] 当我在 main 中定义常量(其余代码是相同的)就像 int GENE=100; 但只有一次。这是否意味着内存泄漏？当我编译它时它没有给出错误消息但是正在定义矩阵并为它们赋值是真的吗？

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <assert.h>
#include <time.h>
#include <limits.h>
#define GENE 100
#define N 57
#define INDEX 10




int main (void) {

//int GENE = 100;
//int N = 57;
//int INDEX = 10;
int i, j; 
double x;
double *S_matrix = (double *)malloc(INDEX * GENE * sizeof(double));
double *E = (double*)malloc(GENE*N*sizeof(double));


// read E matrix

FILE *fq;


if ((fq = fopen("E_control.txt", "r")) == NULL ) 
{
     printf("Error\n");
     exit(EXIT_FAILURE);
}

fq = fopen("E_control.txt","r");
printf("\n");

for (i=0;i<GENE;i++)
{
    for(j=0;j<N;j++)
    {
        fscanf(fq,"%lf",&x);
        E[i*GENE+j] = x;
    }
}


printf("\n");
fclose(fq);

for(i=0; i<INDEX; i++)
{
         for(j=0; j<GENE; j++)
         {        
              S_matrix[i*INDEX+j]=i*j;
         }
}

printf("%f " , S_matrix[55]);


free(S_matrix);
S_matrix=NULL;
free(E);
E=NULL;
return(0);
getchar();
getchar();

}

Answer 1

您试图在 main() 中保留 2280000 字节的堆栈空间(实际上更多)，因为固定数组声明非常大。具体来说，这一行:

double E[GENE][N] = {{0}};

等于

double E[5000][57] = {{0}};

每 double 8 字节，这很可能会耗尽您的堆栈。改为对该数组使用动态分配。例如:

double (*E)[N] = malloc(5000*sizeof(*E));

完成后不要忘记释放它。

全局固定分配也将起作用(即将其声明为全局外部 main() 功能 block 。

static double E[GENE][N];

int main()
{
    ... your code ...
}

您选择的任何方法都有潜在的优势和缺陷，因此请相应地计划。