File: parallel_offloading_map.cpp

package info (click to toggle)
llvm-toolchain-19 1%3A19.1.7-19
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 1,999,616 kB
  • sloc: cpp: 6,951,724; ansic: 1,486,157; asm: 913,598; python: 232,059; f90: 80,126; objc: 75,281; lisp: 37,276; pascal: 16,990; sh: 10,079; ml: 5,058; perl: 4,724; awk: 3,523; makefile: 3,430; javascript: 2,504; xml: 892; fortran: 664; cs: 573
file content (41 lines) | stat: -rw-r--r-- 764 bytes parent folder | download | duplicates (9) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
// RUN: %libomptarget-compilexx-run-and-check-generic

// REQUIRES: gpu

#include <cassert>
#include <iostream>

int main(int argc, char *argv[]) {
  constexpr const int num_threads = 64, N = 128;
  int array[num_threads] = {0};

#pragma omp parallel for
  for (int i = 0; i < num_threads; ++i) {
    int tmp[N];

    for (int j = 0; j < N; ++j) {
      tmp[j] = i;
    }

#pragma omp target teams distribute parallel for map(tofrom : tmp)
    for (int j = 0; j < N; ++j) {
      tmp[j] += j;
    }

    for (int j = 0; j < N; ++j) {
      array[i] += tmp[j];
    }
  }

  // Verify
  for (int i = 0; i < num_threads; ++i) {
    const int ref = (0 + N - 1) * N / 2 + i * N;
    assert(array[i] == ref);
  }

  std::cout << "PASS\n";

  return 0;
}

// CHECK: PASS