File: kernels-double-reduction-n.c

package info (click to toggle)
gcc-arm-none-eabi 15%3A8-2019-q3-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 571,828 kB
  • sloc: ansic: 2,937,651; cpp: 881,644; ada: 597,189; makefile: 65,528; asm: 56,499; xml: 46,621; exp: 24,747; sh: 19,684; python: 7,256; pascal: 4,370; awk: 3,497; perl: 2,695; yacc: 316; ml: 285; f90: 234; lex: 198; objc: 194; haskell: 119
file content (35 lines) | stat: -rw-r--r-- 1,152 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
/* { dg-additional-options "-O2" } */
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
/* { dg-additional-options "-fdump-tree-optimized" } */

#include <stdlib.h>

#define N 500

unsigned int a[N][N];

void  __attribute__((noinline,noclone))
foo (unsigned int n)
{
  int i, j;
  unsigned int sum = 1;

#pragma acc kernels copyin (a[0:n]) copy (sum)
  {
    for (i = 0; i < n; ++i)
      for (j = 0; j < n; ++j)
	sum += a[i][j];
  }

  if (sum != 5001)
    abort ();
}

/* Check that only one loop is analyzed, and that it can be parallelized.  */
/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint, noclone, noinline\\)\\)" 1 "parloops1" } } */
/* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
/* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops1" } } */

/* Check that the loop has been split off into a function.  */
/* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */