OpenACC 计算圆周率（简单版）

▶ 书上的计算圆周率的简单程序，主要是使用了自定义函数

 #include <stdio.h>
 #include <stdlib.h>
 #include <math.h>
 #include <openacc.h>

 #define N   100

 #pragma acc routine seq
 float ff(const float x)
 {
     return 4.0f / (1.0f + x * x);
 }

 int main()
 {
     const float h = 1.0f / N;
     float sumf = , result;

 #pragma acc parallel loop reduction(+:sumf)
     for (int i = ; i < N; i++)
         sumf += ff(h * (i - 0.5f));

     result = h * sumf;
     printf("\nN = %d, myPi = %f, diff = %e\n", N, result, result / 3.141592653589793238 - );
     //getchar();
     return ;
 }

● 输出结果

D:\Code\OpenACC\OpenACCProject\OpenACCProject>pgcc main.c -acc -Minfo -o main_acc.exe
ff:
     , Generating acc routine seq
         Generating Tesla code
     , FMA (fused multiply-add) instruction(s) generated
main:
     , Accelerator kernel generated
         Generating Tesla code
         , #pragma acc loop gang, vector(100) /* blockIdx.x threadIdx.x */
             Generating reduction(+:sumf)
     , Generating implicit copy(sumf)

D:\Code\OpenACC\OpenACCProject\OpenACCProject>main_acc.exe
launch CUDA kernel  file=D:\Code\OpenACC\OpenACCProject\OpenACCProject\main.c function=main line= device= threadid= num_gangs= num_workers= vector_length= grid= block= shared memory=
launch CUDA kernel  file=D:\Code\OpenACC\OpenACCProject\OpenACCProject\main.c function=main line= device= threadid= num_gangs= num_workers= vector_length= grid= block= shared memory=

N = , myPi = 3.161500, diff = 6.336546e-03
PGI: "acc_shutdown" not detected, performance results might be incomplete.
 Please add the call "acc_shutdown(acc_device_nvidia)" to the end of your application to ensure that the performance results are complete.

Accelerator Kernel Timing data
D:\Code\OpenACC\OpenACCProject\OpenACCProject\main.c
  main  NVIDIA  devicenum=
    time(us):
    : compute region reached  time
        : kernel launched  time
            grid: []  block: []
            elapsed time(us): total= max= min= avg=
        : reduction kernel launched  time
            grid: []  block: []
             device time(us): total= max= min= avg=
    : data region reached  times
        : data copyin transfers:
             device time(us): total= max= min= avg=
        : data copyout transfers:
             device time(us): total= max= min= avg=