【发布时间】:2021-09-18 06:19:13
【问题描述】:
我尝试测试两个向量的内积的 OpenMP 和 MPI 并行实现(动态计算元素值)并发现 OpenMP 比 MPI 慢。 我使用的 MPI 代码如下,
#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include <omp.h>
#include <mpi.h>
int main(int argc, char* argv[])
{
double ttime = -omp_get_wtime();
int np, my_rank;
MPI_Init(&argc, &argv);
MPI_Comm_size(MPI_COMM_WORLD, &np);
MPI_Comm_rank(MPI_COMM_WORLD, &my_rank);
int n = 10000;
int repeat = 10000;
int sublength = (int)(ceil((double)(n) / (double)(np)));
int nstart = my_rank * sublength;
int nend = nstart + sublength;
if (nend >n )
{
nend = n;
sublength = nend - nstart;
}
double dot = 0;
double sum = 1;
int j, k;
double time = -omp_get_wtime();
for (j = 0; j < repeat; j++)
{
double loc_dot = 0;
for (k = 0; k < sublength; k++)
{
double temp = sin((sum+ nstart +k +j)/(double)(n));
loc_dot += (temp * temp);
}
MPI_Allreduce(&loc_dot, &dot, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
sum += (dot/(double)(n));
}
time += omp_get_wtime();
if (my_rank == 0)
{
ttime += omp_get_wtime();
printf("np = %d sum = %f, loop time = %f sec, total time = %f \n", np, sum, time, ttime);
}
return 0;
}
我尝试了几种不同的 OpenMP 实现。 这是不复杂且接近我能达到的最佳性能的版本。
#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include <omp.h>
int main(int argc, char* argv[])
{
int n = 10000;
int repeat = 10000;
int np = 1;
if (argc > 1)
{
np = atoi(argv[1]);
}
omp_set_num_threads(np);
int nstart =0;
int sublength =n;
double loc_dot = 0;
double sum = 1;
#pragma omp parallel
{
int i, j, k;
double time = -omp_get_wtime();
for (j = 0; j < repeat; j++)
{
#pragma omp for reduction(+: loc_dot)
for (k = 0; k < sublength; k++)
{
double temp = sin((sum+ nstart +k +j)/(double)(n));
loc_dot += (temp * temp);
}
#pragma omp single
{
sum += (loc_dot/(double)(n));
loc_dot =0;
}
}
time += omp_get_wtime();
#pragma omp single nowait
printf("sum = %f, time = %f sec, np = %d\n", sum, time, np);
}
return 0;
}
这是我的测试结果:
OMP
sum = 6992.953984, time = 0.409850 sec, np = 1
sum = 6992.953984, time = 0.270875 sec, np = 2
sum = 6992.953984, time = 0.186024 sec, np = 4
sum = 6992.953984, time = 0.144010 sec, np = 8
sum = 6992.953984, time = 0.115188 sec, np = 16
sum = 6992.953984, time = 0.195485 sec, np = 32
MPI
sum = 6992.953984, time = 0.381701 sec, np = 1
sum = 6992.953984, time = 0.243513 sec, np = 2
sum = 6992.953984, time = 0.158326 sec, np = 4
sum = 6992.953984, time = 0.102489 sec, np = 8
sum = 6992.953984, time = 0.063975 sec, np = 16
sum = 6992.953984, time = 0.044748 sec, np = 32
谁能告诉我我错过了什么? 谢谢!
更新: 我为 OMP 编写了一个可接受的 reduce 函数。现在的性能接近 MPI 减少功能。代码如下。
#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include <omp.h>
double darr[2][64];
int nreduce=0;
#pragma omp threadprivate(nreduce)
double OMP_Allreduce_dsum(double loc_dot,int tid,int np)
{
darr[nreduce][tid]=loc_dot;
#pragma omp barrier
double dsum =0;
int i;
for (i=0; i<np; i++)
{
dsum += darr[nreduce][i];
}
nreduce=1-nreduce;
return dsum;
}
int main(int argc, char* argv[])
{
int np = 1;
if (argc > 1)
{
np = atoi(argv[1]);
}
omp_set_num_threads(np);
double ttime = -omp_get_wtime();
int n = 10000;
int repeat = 10000;
#pragma omp parallel
{
int tid = omp_get_thread_num();
int sublength = (int)(ceil((double)(n) / (double)(np)));
int nstart = tid * sublength;
int nend = nstart + sublength;
if (nend >n )
{
nend = n;
sublength = nend - nstart;
}
double sum = 1;
double time = -omp_get_wtime();
int j, k;
for (j = 0; j < repeat; j++)
{
double loc_dot = 0;
for (k = 0; k < sublength; k++)
{
double temp = sin((sum+ nstart +k +j)/(double)(n));
loc_dot += (temp * temp);
}
double dot =OMP_Allreduce_dsum(loc_dot,tid,np);
sum +=(dot/(double)(n));
}
time += omp_get_wtime();
#pragma omp master
{
ttime += omp_get_wtime();
printf("np = %d sum = %f, loop time = %f sec, total time = %f \n", np, sum, time, ttime);
}
}
return 0;
}
【问题讨论】:
-
如果你在单核上运行你的代码有多快?
-
机器?操作系统?用的编译器?使用编译器标志?使用 MPI 实现?如果没有这些信息,任何人都只是猜测。
-
机器:Intel(R) Xeon(R) Gold 6152 CPU @ 2.10GHz。操作系统:Centos-7,编译器:Intel 18.0.1。编译器标志:-qopenmp。编译命令:mpiicc -qopenmp r_mpi.c -o r_mpi。 icc -qopenmp r_omp.c -o r_omp。运行命令:mpiexec -n 4 r_mpi, r_omp 4。我不确定 MPI 的实现。
-
请使用优化标志,如
-O3(根据您的需要,可能还有-march=native和-ffast-math)!默认情况下,ICC 不应像任何其他编译器一样优化代码。 -
我已经尝试过 -O3 -march=native -ffast-math 和 -lm。那些标志会加速一点,但不会改变趋势。
标签: c parallel-processing openmp reduction