我是线程编程的新手,我有一个概念性的问题。我正在做矩阵乘法作为我班级的项目。但是,我不使用线程,然后使用线程计算答案矩阵的每个单元格的标量积,然后再次将第一个矩阵分成比例,以便每个线程都有相等的计算部分。我的问题是标量产品实现很快完成,这是我所期望的,但第三个实现并不比非线程实现更快地计算答案。例如,如果它使用2个线程,它将在大约一半的时间内处理它,因为它可以同时在矩阵的两半上工作,但事实并非如此。我觉得第三个实现中存在问题,我不认为它并行运行,代码如下。谁能让我直截了当?并非所有代码都与问题相关,但我将其包含在内,以防问题不是本地问题。 谢谢,
主程序:
#include <iostream>
#include <cstdio>
#include <cstdlib>
#include <cmath>
#include<fstream>
#include<string>
#include<sstream>
#include <matrix.h>
#include <timer.h>
#include <random_generator2.h>
const float averager=2.0; //used to find the average of the time taken to multiply the matrices.
//Precondition: The matrix has been manipulated in some way and is ready to output the statistics
//Outputs the size of the matrix along with the user elapsed time.
//Postconidition: The stats are outputted to the file that is specified with the number of threads used
//file name example: "Nonparrallel2.dat"
void output(string file, int numThreads , long double time, int n);
//argv[1] = the size of the matrix
//argv[2] = the number of threads to be used.
//argv[3] =
int main(int argc, char* argv[])
{
random_generator rg;
timer t, nonparallel, scalar, variant;
int n, total = 0, numThreads = 0;
long double totalNonP = 0, totalScalar = 0, totalVar = 0;
n = 100;
/*
* check arguments
*/
n = atoi(argv[1]);
n = (n < 1) ? 1 : n;
numThreads = atoi(argv[2]);
/*
* allocated and generate random strings
*/
int** C;
int** A;
int** B;
cout << "**NOW STARTING ANALYSIS FOR " << n << " X " << n << " MATRICES WITH " << numThreads << "!**"<< endl;
for (int timesThrough = 0; timesThrough < averager; timesThrough++)
{
cout << "Creating the matrices." << endl;
t.start();
C = create_matrix(n);
A = create_random_matrix(n, rg);
B = create_random_matrix(n, rg);
t.stop();
cout << "Timer (generate): " << t << endl;
//---------------------------------------------------------Ends non parallel-----------------------------
/*
* run algorithms
*/
cout << "Running non-parallel matrix multiplication: " << endl;
nonparallel.start();
multiply(C, A, B, n);
nonparallel.stop();
//-----------------------------------------Ends non parallel----------------------------------------------
//cout << "The correct matrix" <<endl;
//output_matrix(C, n);
cout << "Timer (multiplication): " << nonparallel << endl;
totalNonP += nonparallel.user();
//D is the transpose of B so that the p_scalarproduct function does not have to be rewritten
int** D = create_matrix(n);
for (int i = 0; i < n; i++)
for(int j = 0; j < n; j++)
D[i][j] = B[j][i];
//---------------------------------------------------Start Threaded Scalar Poduct--------------------------
cout << "Running scalar product in parallel" << endl;
scalar.start();
//Does the scalar product in parallel to multiply the two matrices.
for (int i = 0; i < n; i++)
for (int j = 0; j < n; j++){
C[i][j] = 0;
C[i][j] = p_scalarproduct(A[i],D[j],n,numThreads);
}//ends the for loop with j
scalar.stop();
cout << "Timer (scalar product in parallel): " << scalar << endl;
totalScalar += scalar.user();
//---------------------------------------------------Ends Threaded Scalar Poduct------------------------
//---------------------------------------------------Starts Threaded Variant For Loop---------------
cout << "Running the variation on the for loop." << endl;
boost :: thread** thrds;
//create threads and bind to p_variantforloop_t
thrds = new boost::thread*[numThreads];
variant.start();
for (int i = 1; i <= numThreads; i++)
thrds[i-1] = new boost::thread(boost::bind(&p_variantforloop_t,
C, A, B, ((i)*n - n)/numThreads ,(i * n)/numThreads, numThreads, n));
cout << "before join" <<endl;
// join threads
for (int i = 0; i < numThreads; i++)
thrds[i]->join();
variant.stop();
// cleanup
for (int i = 0; i < numThreads; i++)
delete thrds[i];
delete[] thrds;
cout << "Timer (variation of for loop): " << variant <<endl;
totalVar += variant.user();
//---------------------------------------------------Ends Threaded Variant For Loop------------------------
// output_matrix(A, n);
// output_matrix(B, n);
// output_matrix(E,n);
/*
* free allocated storage
*/
cout << "Deleting Storage" <<endl;
delete_matrix(A, n);
delete_matrix(B, n);
delete_matrix(C, n);
delete_matrix(D, n);
//avoids dangling pointers
A = NULL;
B = NULL;
C = NULL;
D = NULL;
}//ends the timesThrough for loop
//output the results to .dat files
output("Nonparallel", numThreads, (totalNonP / averager) , n);
output("Scalar", numThreads, (totalScalar / averager), n);
output("Variant", numThreads, (totalVar / averager), n);
cout << "Nonparallel = " << (totalNonP / averager) << endl;
cout << "Scalar = " << (totalScalar / averager) << endl;
cout << "Variant = " << (totalVar / averager) << endl;
return 0;
}
void output(string file, int numThreads , long double time, int n)
{
ofstream dataFile;
stringstream ss;
ss << numThreads;
file += ss.str();
file += ".dat";
dataFile.open(file.c_str(), ios::app);
if(dataFile.fail())
{
cout << "The output file didn't open." << endl;
exit(1);
}//ends the if statement.
dataFile << n << " " << time << endl;
dataFile.close();
}//ends optimalOutput function
矩阵文件:
#include <matrix.h>
#include <stdlib.h>
using namespace std;
int** create_matrix(int n)
{
int** matrix;
if (n < 1)
return 0;
matrix = new int*[n];
for (int i = 0; i < n; i++)
matrix[i] = new int[n];
return matrix;
}
int** create_random_matrix(int n, random_generator& rg)
{
int** matrix;
if (n < 1)
return 0;
matrix = new int*[n];
for (int i = 0; i < n; i++)
{
matrix[i] = new int[n];
for (int j = 0; j < n; j++)
//rg >> matrix[i][j];
matrix[i][j] = rand() % 100;
}
return matrix;
}
void delete_matrix(int** matrix, int n)
{
for (int i = 0; i < n; i++)
delete[] matrix[i];
delete[] matrix;
//avoids dangling pointers.
matrix = NULL;
}
/*
* non-parallel matrix multiplication
*/
void multiply(int** C, int** A, int** B, int n)
{
if ((C == A) || (C == B))
{
cout << "ERROR: C equals A or B!" << endl;
return;
}
for (int i = 0; i < n; i++)
for (int j = 0; j < n; j++)
{
C[i][j] = 0;
for (int k = 0; k < n; k++)
C[i][j] += A[i][k] * B[k][j];
}
}
void p_scalarproduct_t(int* c, int* a, int* b,
int s, int e, boost::mutex* lock)
{
int tmp;
tmp = 0;
for (int k = s; k < e; k++){
tmp += a[k] * b[k];
//cout << "a[k]= "<<a[k]<<"b[k]= "<< b[k] <<" "<<k<<endl;
}
lock->lock();
*c = *c + tmp;
lock->unlock();
}
int p_scalarproduct(int* a, int* b, int n, int m)
{
int c;
boost::mutex lock;
boost::thread** thrds;
c = 0;
/* create threads and bind to p_merge_sort_t */
thrds = new boost::thread*[m];
for (int i = 0; i < m; i++)
thrds[i] = new boost::thread(boost::bind(&p_scalarproduct_t,
&c, a, b, i*n/m, (i+1)*n/m, &lock));
/* join threads */
for (int i = 0; i < m; i++)
thrds[i]->join();
/* cleanup */
for (int i = 0; i < m; i++)
delete thrds[i];
delete[] thrds;
return c;
}
void output_matrix(int** matrix, int n)
{
cout << "[";
for (int i = 0; i < n; i++)
{
cout << "[ ";
for (int j = 0; j < n; j++)
cout << matrix[i][j] << " ";
cout << "]" << endl;
}
cout << "]" << endl;
}
void p_variantforloop_t(int** C, int** A, int** B, int s, int e, int numThreads, int n)
{
//cout << "s= " <<s<<endl<< "e= " << e << endl;
for(int i = s; i < e; i++)
for(int j = 0; j < n; j++){
C[i][j] = 0;
//cout << "i " << i << " j " << j << endl;
for (int k = 0; k < n; k++){
C[i][j] += A[i][k] * B[k][j];}
}
}//ends the function
答案 0 :(得分:3)
我的猜测是你遇到了False Sharing。尝试在p_variantforloop_t
中使用局部变量:
void p_variantforloop_t(int** C, int** A, int** B, int s, int e, int numThreads, int n)
{
for(int i = s; i < e; i++)
for(int j = 0; j < n; j++){
int accu = 0;
for (int k = 0; k < n; k++)
accu += A[i][k] * B[k][j];
C[i][j] = accu;
}
}
答案 1 :(得分:0)