행렬 표준곱 연산속도저하문제

리눅스상에서 동적할당으로 행렬생성해서 곱셈연산하는데 너무 느립니다
크기가 너무커서 배열생성도할수없고 막막하네요

void standard_matrix_multiplication (int n,int MatrixA[n][n],int MatrixB[n][n],int MatrixC[n][n])
{
int i,j,k;
Standard_Mul_Count=0;
Standard_Add_Sub_Count=0;
for(i=0;i for(j=0;j MatrixC[i][j]=0;
for(i=0;i for(j=0;j for(k=0;k MatrixC[i][j]+=MatrixA[i][k]*MatrixB[k][j],Standard_Mul_Count++,Standard_Add_Sub_Count++; //곱하고 더해서
}

void test (int inputk)
{
int i,j,k;
int temp;
printf("k=%d\n",inputk);
for(temp=1,i=0;i temp*=2; //e^(k-2)부터 시작
for(i=0;i<7;i++) //standard run
{
int MatrixA[temp][temp];
int MatrixB[temp][temp];
int MatrixC[temp][temp];
for(j=0;j for(k=0;k {
MatrixA[j][k]=rand()%10;
MatrixB[j][k]=rand()%10;
}
standard_matrix_multiplication(temp,MatrixA,MatrixB,MatrixC);
temp*=2;

printf("=========================\n");
printf("2^(%d-3) Standard Strassen\n",inputk);
printf("mul %d ",Standard_Mul_Count);
printf("\nadd/sub %d",Standard_Add_Sub_Count);
printf("\n");
printf("=========================\n");
}
return;
}
int main ()
{
int i,j;
int **MatrixA;
int **MatrixB;
int **MatrixC;
MatrixA=(int**)malloc(sizeof(int*)*2048);
MatrixB=(int**)malloc(sizeof(int*)*2048);
MatrixC=(int**)malloc(sizeof(int*)*2048);

for(i=0;i<2048;i++)
{
MatrixA[i]=(int*)malloc(sizeof(int*)*2048);
MatrixB[i]=(int*)malloc(sizeof(int*)*2048);
MatrixC[i]=(int*)malloc(sizeof(int*)*2048);
printf("1");
}
printf("\n");
for(i=0;i<2048;i++)
for(j=0;j<2048;j++)
{MatrixA[i][j]=rand()%10,MatrixB[i][j]=rand()%10;
}
printf("\nasdf\n");
standard_matrix_multiplication(2048,MatrixA,MatrixB,MatrixC);
printf("\nasdf\n");
test(8);
}