skatrak wrote:
Moving to draft because I've noticed this doesn't currently work whenever there
are different calls to new DeviceRTL loop functions. The state machine rewrite
optimization of OpenMPOpt causes the following code to not run properly,
whereas the same code without the `unused_problematic` subroutine in it (or
compiled with `-mllvm -openmp-opt-disable-state-machine-rewrite`) works:
```f90
! flang -fopenmp -fopenmp-version=52 --offload-arch=gfx1030 test.f90 &&
OMP_TARGET_OFFLOAD=MANDATORY ./a.out
subroutine test_subroutine(counter)
implicit none
integer, intent(out) :: counter
integer :: i1, i2, n1, n2
n1 = 100
n2 = 50
counter = 0
!$omp target teams distribute reduction(+:counter)
do i1=1, n1
!$omp parallel do reduction(+:counter)
do i2=1, n2
counter = counter + 1
end do
end do
end subroutine
program main
implicit none
integer :: counter
call test_subroutine(counter)
! Should print: 5000
print '(I0)', counter
end program
subroutine foo(i)
integer, intent(inout) :: i
end subroutine
! The presence of this unreachable function in the compilation unit causes
! the result of `test_subroutine` to be incorrect. Removing the `distribute`
! OpenMP directive avoids the problem.
subroutine unused_problematic()
implicit none
integer :: i
!$omp target teams
!$omp distribute
do i=1, 100
call foo(i)
end do
!$omp end target teams
end subroutine
```
https://github.com/llvm/llvm-project/pull/150927
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
