c - 我无法为更大的矩阵分配内存，然后〜200x200 Lapack Visual Studio in C 这是我的代码

Question

我正在对求解矩阵的执行时间进行基准测试，但我无法获得超过 ~200x200 的时间，我应该使用 1500x1500 或接近该时间。我在 VS 上运行这个。

#include <stdlib.h>
#include <stdio.h>
#include "lapacke.h"
#include "lapacke_config.h"
#include <time.h>

/* Auxiliary routines prototypes */
extern void print_matrix(lapack_complex_double *a, int m, int n);
extern void generate_matrix(lapack_complex_double * matrix, int w, int h);

/* Parameters */
#define N 179

/* Main program */
int main() {
    clock_t t;
    /* Locals */
    lapack_int n = N,info;
    lapack_int ipiv[N];
    lapack_complex_double a[N*N];
    lapack_complex_double b[N*N];

    FILE* fp1 = fopen("complexNumsLog.txt", "w");

    int w = 1, h = 1, h2 = 1, i = 0, j = 0; 


    for(i = 1; i <= N; i++){
        for(j = 1; j <= N; j++){
            w = i;
            h = i;
            h2 = j;

            generate_matrix(a, w, h);
            generate_matrix(b, w, h2);

            // print_matrix(a, w, h);
            // print_matrix(b, w, h2);

            // getchar(); 


            t = clock();
            info = LAPACKE_zgesv(LAPACK_ROW_MAJOR, w, h2, a, h, ipiv, b, h2);
            t = clock() - t;

            fprintf(fp1, "Matrix A: %3dx%3d ", w, h);
            fprintf(fp1, "Matrix B: %3dx%3d ", w, h2);
            fprintf(fp1, "%3d milliseconds %2.3f seconds\n",t,((float)t)/CLOCKS_PER_SEC);

            /* Check for the exact singularity */
            if( info > 0 ) {
                printf( "The diagonal element of the triangular factor of A,\n" );
                printf( "U(%i,%i) is zero, so that A is singular;\n", info, info );
                printf( "the solution could not be computed.\n" );
                getchar();
                exit( 1 );
            }
        }
        printf("%d\n", i);
    }
    getchar();
    exit( 0 );
} 

void print_matrix(lapack_complex_double* a, int m, int n) {
    int i, j;
    for( i = 0; i < m; i++ ) {
        for( j = 0; j < n; j++ )
            printf( " (%6.2f,%6.2f)", a[i*m+j].real, a[i*m+j].imag );
        printf( "\n" );
    }
    printf( "********************************************\n" );
}



void generate_matrix(lapack_complex_double * matrix, int w, int h){
    int i,j;
    double r;
    for(i = 0; i < w; i++){
        for(j = 0; j < h; j++){
            r = (rand()%1000 - 500)/100.0;
            matrix[i*w+j].real = r;
            r = (rand()%1000 - 500)/100.0;
            matrix[i*w+j].imag = r;;
        }
    }
}

Answer 1

你的筹码已经爆了。您的程序通常只分配几 MB 的堆栈空间，而您正尝试分配堆栈上的所有数据。当您达到大约 200x200 以上时，您很快就会耗尽堆栈空间。

要解决此问题，您需要在全局范围或堆上分配内存，其中大小仅受虚拟地址空间和/或总可用物理内存的限制。由于大小在编译时已知，因此最简单的方法是在全局范围内分配它:

/* Parameters */
#define N 179
lapack_int ipiv[N];
lapack_complex_double a[N*N];
lapack_complex_double b[N*N];    

/* Main program */
int main() {
    ...
}