File: small_trip_count_thread_limit.cpp

package info (click to toggle)
llvm-toolchain-21 1%3A21.1.8-2
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 2,236,724 kB
  • sloc: cpp: 7,619,776; ansic: 1,433,958; asm: 1,058,748; python: 252,197; f90: 94,671; objc: 70,753; lisp: 42,813; pascal: 18,401; sh: 8,601; ml: 5,111; perl: 4,720; makefile: 3,719; awk: 3,523; javascript: 2,272; xml: 892; fortran: 770
file content (28 lines) | stat: -rw-r--r-- 717 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
// clang-format off
// RUN: %libomptarget-compilexx-generic
// RUN: env LIBOMPTARGET_INFO=16 \
// RUN:   %libomptarget-run-generic 2>&1 | %fcheck-generic

// REQUIRES: gpu

int main(int argc, char *argv[]) {
  constexpr const int block_size = 256;
  constexpr const int grid_size = 4;
  constexpr const int count = block_size * grid_size;

  int *data = new int[count];

#pragma omp target teams distribute parallel for thread_limit(block_size) map(from: data[0:count])
  for (int i = 0; i < count; ++i)
    data[i] = i;

  for (int i = 0; i < count; ++i)
    if (data[i] != i)
      return 1;

  delete[] data;

  return 0;
}

// CHECK: Launching kernel {{.*}} with [4,1,1] blocks and [256,1,1] threads in SPMD mode