以下程序基本上与
here所述的程序相同.当我使用两个线程(NTHREADS == 2)运行和编译程序时,我得到以下运行时间：
real 0m14.120s user 0m25.570s sys 0m0.050s
当它只运行一个线程(NTHREADS == 1)时,我的运行时间明显更好,即使它只使用一个核心.
real 0m4.705s user 0m4.660s sys 0m0.010s
我的系统是双核,我知道random_r是线程安全的,我很确定它是非阻塞的.当没有random_r运行相同的程序,并且使用余弦和正弦的计算作为替代时,双线程版本的运行时间大约在预期的1/2的时间内.
#include <pthread.h> #include <stdlib.h> #include <stdio.h> #define NTHREADS 2 #define PRNG_BUFSZ 8 #define ITERATIONS 1000000000 void* thread_run(void* arg) { int r1,i,totalIterations = ITERATIONS / NTHREADS; for (i = 0; i < totalIterations; i++){ random_r((struct random_data*)arg,&r1); } printf("%i\n",r1); } int main(int argc,char** argv) { struct random_data* rand_states = (struct random_data*)calloc(NTHREADS,sizeof(struct random_data)); char* rand_statebufs = (char*)calloc(NTHREADS,PRNG_BUFSZ); pthread_t* thread_ids; int t = 0; thread_ids = (pthread_t*)calloc(NTHREADS,sizeof(pthread_t)); /* create threads */ for (t = 0; t < NTHREADS; t++) { initstate_r(random(),&rand_statebufs[t],PRNG_BUFSZ,&rand_states[t]); pthread_create(&thread_ids[t],NULL,&thread_run,&rand_states[t]); } for (t = 0; t < NTHREADS; t++) { pthread_join(thread_ids[t],NULL); } free(thread_ids); free(rand_states); free(rand_statebufs); }
解决方法
一个非常简单的改变,将数据放在内存中：
struct random_data* rand_states = (struct random_data*)calloc(NTHREADS * 64,sizeof(struct random_data));
char* rand_statebufs = (char*)calloc(NTHREADS*64,PRNG_BUFSZ);
pthread_t* thread_ids;
int t = 0;
thread_ids = (pthread_t*)calloc(NTHREADS,sizeof(pthread_t));
/* create threads */
for (t = 0; t < NTHREADS; t++) {
initstate_r(random(),&rand_statebufs[t*64],&rand_states[t*64]);
pthread_create(&thread_ids[t],&rand_states[t*64]);
}
导致我的双核机器运行时间快得多.
这将确认它是要测试的怀疑 – 您在两个单独的线程中在相同的高速缓存行上突变值,因此具有高速缓存争用. Herb Sutter的‘machine architecture – what your programming language never told you’ talk值得一看,如果你还没有了解的话,他会在大约1:20左右的时候展示虚假的分享.
制定缓存行大小,并创建每个线程的数据,使其与之对齐.
将所有线程的数据放入一个结构体中,这样做比较简单：
#define CACHE_LINE_SIZE 64
struct thread_data {
struct random_data random_data;
char statebuf[PRNG_BUFSZ];
char padding[CACHE_LINE_SIZE - sizeof ( struct random_data )-PRNG_BUFSZ];
};
int main ( int argc,char** argv )
{
printf ( "%zd\n",sizeof ( struct thread_data ) );
void* apointer;
if ( posix_memalign ( &apointer,sizeof ( struct thread_data ),NTHREADS * sizeof ( struct thread_data ) ) )
exit ( 1 );
struct thread_data* thread_states = apointer;
memset ( apointer,NTHREADS * sizeof ( struct thread_data ) );
pthread_t* thread_ids;
int t = 0;
thread_ids = ( pthread_t* ) calloc ( NTHREADS,sizeof ( pthread_t ) );
/* create threads */
for ( t = 0; t < NTHREADS; t++ ) {
initstate_r ( random(),thread_states[t].statebuf,&thread_states[t].random_data );
pthread_create ( &thread_ids[t],&thread_states[t].random_data );
}
for ( t = 0; t < NTHREADS; t++ ) {
pthread_join ( thread_ids[t],NULL );
}
free ( thread_ids );
free ( thread_states );
}
与CACHE_LINE_SIZE 64：
refugio:$gcc -O3 -o bin/nixuz_random_r src/nixuz_random_r.c -lpthread refugio:$time bin/nixuz_random_r 64 63499495 944240966 real 0m1.278s user 0m2.540s sys 0m0.000s
或者您可以使用双倍的缓存行大小,并使用malloc – 额外的填充确保突变的内存是分开的行,因为malloc是16(IIRC)而不是64字节对齐.
(我将ITERATIONS减少了十倍,而不是笨蛋快速的机器)
