2

I am using SSE to implement matrix multiplication, but I found there exists memory leak(see the picture below), the memory usage is increasing from 400M to 1G or more.

enter image description here

But, I free the memory in the code.

The following are codes

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

And I guess maybe the memory leak is in Shuffle_Matrix_Multiply function in sse_matrix.h file. But, I am not sure, and now, the memory usage is increasing and my system will crash.

Hope someone can help to figure out and thanks in advance.

Improve this question
1
  • 1
    Best way is to use some appropriate memory profiling tool like valgrind. Commented Jan 3, 2016 at 11:49

2 Answers 2

Reset to default
1

You never free the _a and _b allocated in SSE_4_Matrix.

You also allocate a lot dynamically just to throw it away a bit later. For example the _a and _b could be arrays of 16 floats in stack.

Improve this answer
Sign up to request clarification or add additional context in comments.

1 Comment

thanks, after free _a and _b, the memory usage is about 190M and never increase again. The _a and _b are small arrays, and I did not take them into account, but, since the matrix dimension is large and there are so many loops, it can cause large memory leak. So it is _a and _b caused the memory leak.
1

I would like to use a header file to help me to check memory leak. The header file as follows: 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

In my project, i will use MemoryLeakChecker.hpp in the file including main function as follows: 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; }

Run your program in debug mode in Visual Studio, you can get the memory leak log in output window after your program exited. Also, you can find the place where memory leaked in the memory leak log.

Improve this answer

2 Comments

Thanks, it is truly detected memory leak, and the out put is Detected memory leaks! Dumping objects -> {160} normal block at 0x006C5620, 16 bytes long. Data: < > A0 01 00 00 A4 01 00 00 A8 01 00 00 AC 01 00 00 {159} normal block at 0x006C5530, 176 bytes long. Data: < > 9C FA 18 00 0C 00 00 00 0C 00 00 00 84 FA 18 00 Object dump complete. And I wonder how can I know at which line of the code the memory leaks from the log.
@Alexander Yau First, you can use _crtBreakAlloc = 160; in your main function as mentioned above in my answer. If it does not work, you can double click on the memory leak line in your output windows, then you can locate the code line where memory leaked.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.