0
我試圖在8核心羣集上實現此代碼。它有2個插座，每個插座有4個內核。我正在嘗試使用pthread_attr_setaffinity_np函數創建8個線程並設置親和力。但是當我看着我在VTunes中的表現時，它顯示我正在創建3969個奇數線程。我不明白爲什麼和如何！最重要的是，我的表現與無親和力設置（操作系統線程調度）完全相同。有人可以幫我調試這個問題嗎？我的代碼運行得很好，但我無法控制線程！提前致謝。無法設置處理器親和力
-------------------------------------- CODE ------- ------------------------------------
const int num_thrd=8;
bool RCTAlgorithmBackprojection(RabbitCtGlobalData* r)
{
float O_L = r->O_L;
float R_L = r->R_L;
double* A_n = r->A_n;
float* I_n = r->I_n;
float* f_L = r->f_L;*/
cpu_set_t cpu[num_thrd];
pthread_t thread[num_thrd];
pthread_attr_t attr[num_thrd];
for(int i =0; i< num_thrd; i++)
{
threadCopy[i].L = r->L;
threadCopy[i].O_L = r->O_L;
threadCopy[i].R_L = r->R_L;
threadCopy[i].A_n = r->A_n;
threadCopy[i].I_n = r->I_n;
threadCopy[i].f_L = r->f_L;
threadCopy[i].slice= i;
threadCopy[i].S_x = r->S_x;
threadCopy[i].S_y = r->S_y;
pthread_attr_init(&attr[i]);
CPU_ZERO(&cpu[i]);
CPU_SET(i, &cpu[i]);
pthread_attr_setaffinity_np(&attr[i], CPU_SETSIZE, &cpu[i]);
int rc=pthread_create(&thread[i], &attr[i], backProject, (void*)&threadCopy[i]);
if (rc!=0)
{
cout<<"Can't create thread\n"<<endl;
return -1;
}
// sleep(1);
}
for (int i = 0; i < num_thrd; i++) {
pthread_join(thread[i], NULL);
}
//s_rcgd = r;
return true;
}
void* backProject (void* parm)
{
copyStruct* s = (copyStruct*)parm; // retrive the slice info
unsigned int L = s->L;
float O_L = s->O_L;
float R_L = s->R_L;
double* A_n = s->A_n;
float* I_n = s->I_n;
float* f_L = s->f_L;
int slice1 = s->slice;
//cout<<"The size of volume is L= "<<L<<endl;
int from = (slice1 * L)/num_thrd; // note that this 'slicing' works fine
int to = ((slice1+1) * L)/num_thrd; // even if SIZE is not divisible by num_thrd
//cout<<"computing slice " << slice1<< " from row " << from<< " to " << to-1<<endl;
for (unsigned int k=from; k<to; k++)
{
double z = O_L + (double)k * R_L;
for (unsigned int j=0; j<L; j++)
{
double y = O_L + (double)j * R_L;
for (unsigned int i=0; i<L; i++)
{
double x = O_L + (double)i * R_L;
double w_n = A_n[2] * x + A_n[5] * y + A_n[8] * z + A_n[11];
double u_n = (A_n[0] * x + A_n[3] * y + A_n[6] * z + A_n[9])/w_n;
double v_n = (A_n[1] * x + A_n[4] * y + A_n[7] * z + A_n[10])/w_n;
f_L[k * L * L + j * L + i] += (float)(1.0/(w_n * w_n) * p_hat_n(u_n, v_n));
}
}
}
//cout<<" finished slice "<<slice1<<endl;
return NULL;
}