Fundamentals of Parallelism on Intel Architecture笔记

#pragma omp simd
for循环前对for循环显式simd优化

#pragma omp declare simd
函数前使函数生成simd版本

#pargma ivdep
for循环前忽略vector dependence

#pargma vector nontemporal
跳过过渡cache，直接stream到最下层cache

#include <omp.h>
int nt = omp_get_max_threads();

omp最多线程数

#pragma omp parallel private(A) share(B)
{
    int C;
    omp_get_thread_num();
}

omp多线程运行
每个thread有独立的A变量，B变量在所有thread间share
每个thread有独立C

export OMP_NUM_THREADS=5
限制omp线程数

fork thread:

#include <pthread.h>
int pthread_create(pthread_t *tidp,const pthread_attr_t *attr,
(void*)(*start_rtn)(void*),void *arg);

fork出一个thread
-lpthread

fork process:

pid = fork();

parent进程pid = 0，child进程pid!=0