File: parallel_target_teams_reduction.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 (33 lines) | stat: -rw-r--r-- 684 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
 
// RUN: %libomptarget-compilexx-run-and-check-generic
// RUN: %libomptarget-compileoptxx-run-and-check-generic

// FIXME: This is a bug in host offload, this should run fine.
// REQUIRES: gpu

#include <iostream>
#include <vector>

#define N 8

int main() {
  std::vector<int> avec(N);
  int *a = avec.data();
#pragma omp parallel for
  for (int i = 0; i < N; i++) {
    a[i] = 0;
#pragma omp target teams distribute parallel for reduction(+ : a[i])
    for (int j = 0; j < N; j++)
      a[i] += 1;
  }

  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  // CHECK: 8
  for (int i = 0; i < N; i++)
    std::cout << a[i] << std::endl;
}