Difference between revisions of "Execution on Intel® Xeon Phi™ co-processor"

 1 #include <stdio.h>
 2 #include <stdlib.h>
 3 #include <string.h>
 4 #include <assert.h>
 5 #include <omp.h>
 6 #include <math.h>
 7 
 8 int main(int argc, char *argv[]) {
 9     int numthreads;
10     int n;
11 
12     assert(argc == 3 && "args: numthreads n");
13     sscanf(argv[1], "%d", &numthreads);
14     sscanf(argv[2], "%d", &n);
15 
16     printf("Init...\n");
17     printf("Start (%d threads)...\n", numthreads);
18     printf("%d test cases\n", n);
19 
20     int m = 1000000;
21     double ttime = omp_get_wtime();
22 
23     int i;
24     double d = 0;
25 #pragma offload target(mic:0)
26     {
27 #pragma omp parallel for private (i) schedule(static) num_threads(numthreads)
28         for(i = 0; i < n; ++i) {
29             for(int j = 0; j < m; ++j) {
30                 d = sin(d) + 0.1 + j;
31                 d = pow(0.2, d)*j;
32             }
33         }
34     }
35     double time = omp_get_wtime() - ttime;
36     fprintf(stderr, "%d %d %.6f\n", n, numthreads, time);
37     printf("time: %.6f s\n", time);
38     printf("Done d = %.6lf.\n", d);
39 
40     return 0;
41 }

 1 #include <cmath>
 2 #include <iostream>
 3 
 4 int main() {
 5     const int N = 104;
 6     double a[N];
 7     for (int i = 0; i < 1e5; i++)
 8         for (int j = 0; j < N; j++)
 9             a[j] = std::sin(std::exp(a[j]-j)*3 * i + i*j);
10     std::cout << a[4] << "\n";
11     return 0;
12 }

$ icpc speedtest.cpp -o vectorized_speedtest -O3
$ icpc speedtest.cpp -o unvectorized_speedtest -O3 -no-vec

 1 #include <cmath>
 2 #include <iostream>
 3 
 4 int main() {
 5     const int N = 104;
 6     double a;
 7     for (int i = 0; i < 1e5; i++)
 8         for (int j = 0; j < N; j++)
 9             a = std::sin(std::exp(a-j)*3 * i + i*j);
10     std::cout << a << "\n";
11     return 0;
12 }