File: classify-kernels-unparallelized-parloops.f95

package info (click to toggle)
gcc-arm-none-eabi 15%3A12.2.rel1-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 959,712 kB
  • sloc: cpp: 3,275,382; ansic: 2,061,766; ada: 840,956; f90: 208,513; makefile: 76,132; asm: 73,433; xml: 50,448; exp: 34,146; sh: 32,436; objc: 15,637; fortran: 14,012; python: 11,991; pascal: 6,787; awk: 4,779; perl: 3,054; yacc: 338; ml: 285; lex: 201; haskell: 122
file content (48 lines) | stat: -rw-r--r-- 2,102 bytes parent folder | download
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
! Check offloaded function's attributes and classification for unparallelized
! OpenACC kernels.

! { dg-additional-options "--param openacc-kernels=parloops" }

! { dg-additional-options "-O2" }
! { dg-additional-options "-fopt-info-optimized-omp" }
! { dg-additional-options "-fdump-tree-ompexp" }
! { dg-additional-options "-fdump-tree-parloops1-all" }
! { dg-additional-options "-fdump-tree-oaccloops" }

! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.

program main
  implicit none
  integer, parameter :: n = 1024
  integer, dimension (0:n-1) :: a, b, c
  integer :: i

  ! An "external" mapping of loop iterations/array indices makes the loop
  ! unparallelizable.
  integer, external :: f

  call setup(a, b)

  !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1)) ! { dg-line l_compute1 }
  ! { dg-optimized {assigned OpenACC seq loop parallelism} {} { target *-*-* } l_compute1 }
  do i = 0, n - 1
     c(i) = a(f (i)) + b(f (i))
  end do
  !$acc end kernels
end program main

! Check the offloaded function's attributes.
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels, omp target entrypoint\\)\\)" 1 "ompexp" } }

! Check that exactly one OpenACC kernels construct is analyzed, and that it
! can't be parallelized.
! { dg-final { scan-tree-dump-times "FAILED:" 1 "parloops1" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
! { dg-final { scan-tree-dump-not "SUCCESS: may be parallelized" "parloops1" } }

! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
! { dg-final { scan-tree-dump-times "(?n)Function is unparallelized OpenACC kernels offload" 1 "oaccloops" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccloops" } }