File: lambda_mapping.cpp

package info (click to toggle)
llvm-toolchain-16 1%3A16.0.6-15~deb12u1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,634,792 kB
  • sloc: cpp: 6,179,261; ansic: 1,216,205; asm: 741,319; python: 196,614; objc: 75,325; f90: 49,640; lisp: 32,396; pascal: 12,286; sh: 9,394; perl: 7,442; ml: 5,494; awk: 3,523; makefile: 2,723; javascript: 1,206; xml: 886; fortran: 581; cs: 573
file content (53 lines) | stat: -rw-r--r-- 1,108 bytes parent folder | download | duplicates (2)
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
42
43
44
45
46
47
48
49
50
51
52
53
// RUN: %libomptarget-compilexx-run-and-check-generic

// Error on the gpu that crashes the host
// UNSUPPORTED: amdgcn-amd-amdhsa
// UNSUPPORTED: amdgcn-amd-amdhsa-LTO

#include <iostream>

template <typename LOOP_BODY>
inline void forall(int Begin, int End, LOOP_BODY LoopBody) {
#pragma omp target parallel for schedule(static)
  for (int I = Begin; I < End; ++I) {
    LoopBody(I);
  }
}

#define N (1000)

//
// Demonstration of the RAJA abstraction using lambdas
// Requires data mapping onto the target section
//
int main() {
  double A[N], B[N], C[N];

  for (int I = 0; I < N; I++) {
    A[I] = I + 1;
    B[I] = -I;
    C[I] = -9;
  }

#pragma omp target data map(tofrom : C[0 : N]) map(to : A[0 : N], B[0 : N])
  {
    forall(0, N, [&](int I) { C[I] += A[I] + B[I]; });
  }

  int Fail = 0;
  for (int I = 0; I < N; I++) {
    if (C[I] != -8) {
      std::cout << "Failed at " << I << " with val " << C[I] << std::endl;
      Fail = 1;
    }
  }

  // CHECK: Succeeded
  if (Fail) {
    std::cout << "Failed" << std::endl;
  } else {
    std::cout << "Succeeded" << std::endl;
  }

  return 0;
}