File: omp_host_pinned_memory.c

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-12
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,496,180 kB
  • sloc: cpp: 5,593,972; ansic: 986,872; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,538; xml: 953; cs: 573; fortran: 567
file content (33 lines) | stat: -rw-r--r-- 788 bytes parent folder | download | duplicates (7) 
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-compile-run-and-check-nvptx64-nvidia-cuda
// REQUIRES: nvptx64-nvidia-cuda

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

// Allocate pinned memory on the host
void *llvm_omp_target_alloc_host(size_t, int);

int main() {
  const int N = 64;
  const int device = omp_get_default_device();
  const int host = omp_get_initial_device();

  int *hst_ptr = llvm_omp_target_alloc_host(N * sizeof(int), device);

  for (int i = 0; i < N; ++i)
    hst_ptr[i] = 2;

#pragma omp target teams distribute parallel for device(device) \
           map(tofrom:hst_ptr[0 : N])
  for (int i = 0; i < N; ++i)
    hst_ptr[i] -= 1;

  int sum = 0;
  for (int i = 0; i < N; ++i)
    sum += hst_ptr[i];

  omp_target_free(hst_ptr, device);
  // CHECK: PASS
  if (sum == N)
    printf ("PASS\n");
}