Question

我正在使用SSE来实现矩阵乘法，但我发现存在内存泄漏（见下图），内存使用量从400M增加到1G或更多。

但是，我释放了代码中的内存。

以下是代码

main.cpp

#include "sse_matrix.h"
#include <ctime>

int main(int argc, char* argv[])
{
    vector<float> left(size, 0);
    vector<float> right(size, 0);
    vector<float> result(size, 0);
    // initialize value
    for (int i = 0; i < dim; i ++)
    {
        for (int j = 0; j < dim; j ++)
        {
            left[i*dim + j] = j;
            right[i*dim + j] = j;
        }

    }
    cout << "1. INFO: value initialized, starting matrix multiplication" << endl;
    // calculate the result
    clock_t my_time = clock();
    SSE_Matrix_Multiply(&left, &right, &result);
    cout << "2. INFO: SSE matrix multiplication result has got" << endl;
    /*for (int i = 0; i < dim; i ++)
    {
        for (int j = 0; j < dim; j ++)
        {
            cout << result[i * dim + j] << " ";
        }
        cout << endl;
    }*/
    cout << "3. INFO: " << float(clock() - my_time)/1000.0 << endl;
    system("pause");

    return 0;

}

sse_matrix.h

#ifndef __SSE_MATRIX_H
#define __SSE_MATRIX_H

#include <vector>
#include <iostream>
using std::cin;
using std::cout;
using std::endl;
using std::vector;

//#define dim 8
//#define size (dim * dim)

const int dim = 4096;
const int size = dim * dim;

struct Matrix_Info 
{
    vector<float> * A;
    int ax, ay;
    vector<float> * B;
    int bx, by;
    vector<float> * C;
    int cx, cy;
    int m;
    int n;
};

void Transpose_Matrix_SSE(float * matrix)
{
    __m128 row1 = _mm_loadu_ps(&matrix[0*4]);
    __m128 row2 = _mm_loadu_ps(&matrix[1*4]);
    __m128 row3 = _mm_loadu_ps(&matrix[2*4]);
    __m128 row4 = _mm_loadu_ps(&matrix[3*4]);
    _MM_TRANSPOSE4_PS(row1, row2, row3, row4);
    _mm_storeu_ps(&matrix[0*4], row1);
    _mm_storeu_ps(&matrix[1*4], row2);
    _mm_storeu_ps(&matrix[2*4], row3);
    _mm_storeu_ps(&matrix[3*4], row4);

}

float * Shuffle_Matrix_Multiply(float * left, float * right)
{
    __m128 _t1, _t2, _sum;
    _sum = _mm_setzero_ps(); // set all value of _sum to zero
    float * _result = new float[size];
    float _res[4] = {0};
    for (int i = 0; i < 4; i ++)
    {
        for (int j = 0; j < 4; j ++)
        {
            _t1 = _mm_loadu_ps(left + i * 4);
            _t2 = _mm_loadu_ps(right + j * 4);
            _sum = _mm_mul_ps(_t1, _t2);
            _mm_storeu_ps(_res, _sum);
            _result[i * 4 + j] = _res[0] + _res[1] + _res[2] + _res[3];
        }
    }
    return _result;
}

float * SSE_4_Matrix(struct Matrix_Info * my_info)
{
    int m = my_info->m;
    int n = my_info->n;
    int ax = my_info->ax;
    int ay = my_info->ay;
    int bx = my_info->bx;
    int by = my_info->by;
    //1. split Matrix A and Matrix B
    float * _a = new float[16];
    float * _b = new float[16];
    for (int i = 0; i < m; i ++)
    {
        for (int j = 0; j < m; j ++)
        {
            _a[i*m + j] = (*my_info->A)[(i + ax) * n + j + ay];
            _b[i*m + j] = (*my_info->B)[(i + bx) * n + j + by];
        }
    }
    //2. transpose Matrix B
    Transpose_Matrix_SSE(_b);
    //3. calculate result and return a float pointer
    return Shuffle_Matrix_Multiply(_a, _b);
}

int Matrix_Multiply(struct Matrix_Info * my_info)
{
    int m = my_info->m;
    int n = my_info->n;
    int cx = my_info->cx;
    int cy = my_info->cy;
    for (int i = 0; i < m; i ++)
    {
        for (int j = 0; j < m; j ++)
        {
            float * temp = SSE_4_Matrix(my_info);
            (*my_info->C)[(i + cx) * n + j + cy] += temp[i*m + j];
            delete [] temp;
        }
    }
    return 0;
}

void SSE_Matrix_Multiply(vector<float> * left, vector<float> * right, vector<float> * result)
{
    struct Matrix_Info my_info;
    my_info.A = left;
    my_info.B = right;
    my_info.C = result;
    my_info.n = dim;
    my_info.m = 4;

    // Matrix A row:i, column:j
    for (int i = 0; i < dim; i += 4)
    {
        for (int j = 0; j < dim; j += 4)
        {
            // Matrix B row:j column:k
            for (int k = 0; k < dim; k += 4)
            {
                my_info.ax = i;
                my_info.ay = j;
                my_info.bx = j;
                my_info.by = k;
                my_info.cx = i;
                my_info.cy = k;
                Matrix_Multiply(&my_info);
            }
        }
    }
}

#endif

我想也许内存泄漏可能在Shuffle_Matrix_Multiply文件的sse_matrix.h函数中。但是，我不确定，现在，内存使用量正在增加，我的系统将崩溃。

希望有人可以帮助提前弄清楚并提前感谢。

Answer 1

你永远不会释放SSE_4_Matrix中分配的_a和_b。

你也会动态分配很多东西，以便稍后扔掉它。例如，_a和_b可以是堆栈中16个浮点数的数组。

Answer 2

我想使用头文件来帮助我检查内存泄漏。头文件如下： MemoryLeakChecker.hpp

#ifndef __MemoryLeakChecker_H__
#define __MemoryLeakChecker_H__

#include <crtdbg.h>
#include <cassert>

//for memory leak check
#ifdef _DEBUG
#define DEBUG_CLIENTBLOCK new(_CLIENT_BLOCK,__FILE__,__LINE__)
#else
#define DEBUG_CLIENTBLOCK
#endif
#define _CRTDBG_MAP_ALLOC
#ifdef _DEBUG
#define new DEBUG_CLIENTBLOCK
#endif

inline void checkMemoryLeak() {
  _CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF | _CRTDBG_LEAK_CHECK_DF);
  int m_count = _CrtDumpMemoryLeaks();
  assert(m_count == 0);
}

#endif

在我的项目中，我将在包含MemoryLeakChecker.hpp函数的文件中使用main，如下所示： MemoryLeakTest.cpp

#include "MemoryLeakChecker.hpp"

int main() {
  //_crtBreakAlloc = 148;  //if you only know the memory leak block number is 148 after checking memory leak log, use this to locate the code causing memory leak. 
  //do some things
  atexit(checkMemoryLeak);  //check all leak after main() function called
  return 0;
}

在debug中以Visual Studio模式运行您的程序，您可以在程序退出后在输出窗口中获取memory leak log。此外，您可以在memory leak log找到内存泄漏的地方。

C ++内存泄漏，如何检测

2 个答案: