File: close_enter_exit.c

package info (click to toggle)
llvm-toolchain-15 1%3A15.0.6-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,554,644 kB
  • sloc: cpp: 5,922,452; ansic: 1,012,136; asm: 674,362; python: 191,568; objc: 73,855; f90: 42,327; lisp: 31,913; pascal: 11,973; javascript: 10,144; sh: 9,421; perl: 7,447; ml: 5,527; awk: 3,523; makefile: 2,520; xml: 885; cs: 573; fortran: 567
file content (108 lines) | stat: -rw-r--r-- 2,620 bytes parent folder | download | duplicates (5)
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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
// RUN: %libomptarget-compile-run-and-check-generic

// REQUIRES: unified_shared_memory
// UNSUPPORTED: clang-6, clang-7, clang-8, clang-9

// Fails on amdgpu with error: GPU Memory Error
// XFAIL: amdgcn-amd-amdhsa

#include <omp.h>
#include <stdio.h>

#pragma omp requires unified_shared_memory

#define N 1024

int main(int argc, char *argv[]) {
  int fails;
  void *host_alloc = 0, *device_alloc = 0;
  int *a = (int *)malloc(N * sizeof(int));
  int dev = omp_get_default_device();

  // Init
  for (int i = 0; i < N; ++i) {
    a[i] = 10;
  }
  host_alloc = &a[0];

  //
  // map + target no close
  //
#pragma omp target data map(tofrom : a[ : N]) map(tofrom : device_alloc)
  {
#pragma omp target map(tofrom : device_alloc)
    { device_alloc = &a[0]; }
  }

  // CHECK: a used from unified memory.
  if (device_alloc == host_alloc)
    printf("a used from unified memory.\n");

  //
  // map + target with close
  //
  device_alloc = 0;
#pragma omp target data map(close, tofrom : a[ : N]) map(tofrom : device_alloc)
  {
#pragma omp target map(tofrom : device_alloc)
    { device_alloc = &a[0]; }
  }
  // CHECK: a copied to device.
  if (device_alloc != host_alloc)
    printf("a copied to device.\n");

  //
  // map + use_device_ptr no close
  //
  device_alloc = 0;
#pragma omp target data map(tofrom : a[ : N]) use_device_ptr(a)
  { device_alloc = &a[0]; }

  // CHECK: a used from unified memory with use_device_ptr.
  if (device_alloc == host_alloc)
    printf("a used from unified memory with use_device_ptr.\n");

  //
  // map + use_device_ptr close
  //
  device_alloc = 0;
#pragma omp target data map(close, tofrom : a[ : N]) use_device_ptr(a)
  { device_alloc = &a[0]; }

  // CHECK: a used from device memory with use_device_ptr.
  if (device_alloc != host_alloc)
    printf("a used from device memory with use_device_ptr.\n");

  //
  // map enter/exit + close
  //
  device_alloc = 0;
#pragma omp target enter data map(close, to : a[ : N])

#pragma omp target map(from : device_alloc)
  {
    device_alloc = &a[0];
    a[0] = 99;
  }

  // 'close' is missing, so the runtime must check whether s is actually in
  // shared memory in order to determine whether to transfer data and delete the
  // allocation.
#pragma omp target exit data map(from : a[ : N])

  // CHECK: a has been mapped to the device.
  if (device_alloc != host_alloc)
    printf("a has been mapped to the device.\n");

  // CHECK: a[0]=99
  // CHECK: a is present: 0
  printf("a[0]=%d\n", a[0]);
  printf("a is present: %d\n", omp_target_is_present(a, dev));

  free(a);

  // CHECK: Done!
  printf("Done!\n");

  return 0;
}