On Tue, 7 Aug 2018 15:09:38 -0700
Cesar Philippidis <cesar_philippi...@mentor.com> wrote:
> I had previously posted this patch as part of a monster deviceptr
> patch here
> <https://gcc.gnu.org/ml/gcc-patches/2018-06/msg01911.html>. This
> patch breaks out the generic gimplifier changes. Essentially, with
> this patch, the gimplifier will now transfer deviceptr data clauses
> using GOMP_MAP_FORCE_DEVICEPTR.
>
> Is this patch OK for trunk? It bootstrapped / regression tested
> cleanly for x86_64 with nvptx offloading.
This patch also appears to fix the attached test case, which had been
associated with a different deviceptr-related patch on the og8 branch
(the other parts of which are upstream already). Perhaps you'd like to
incorporate this test into your patch? It was by James Norris
originally, IIUC.
Thanks,
Julian
ChangeLog
2018-xx-xx James Norris <???>
libgomp/
* testsuite/libgomp.oacc-fortran/deviceptr-1.f90: New test.
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/deviceptr-1.f90
@@ -0,0 +1,197 @@
+! { dg-do run }
+
+! Test the deviceptr clause with various directives
+! and in combination with other directives where
+! the deviceptr variable is implied.
+
+subroutine subr1 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc data deviceptr (a)
+
+ !$acc parallel copy (b)
+ do i = 1, N
+ a(i) = i * 2
+ b(i) = a(i)
+ end do
+ !$acc end parallel
+
+ !$acc end data
+
+end subroutine
+
+subroutine subr2 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ !$acc declare deviceptr (a)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc parallel copy (b)
+ do i = 1, N
+ a(i) = i * 4
+ b(i) = a(i)
+ end do
+ !$acc end parallel
+
+end subroutine
+
+subroutine subr3 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ !$acc declare deviceptr (a)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc kernels copy (b)
+ do i = 1, N
+ a(i) = i * 8
+ b(i) = a(i)
+ end do
+ !$acc end kernels
+
+end subroutine
+
+subroutine subr4 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc parallel deviceptr (a) copy (b)
+ do i = 1, N
+ a(i) = i * 16
+ b(i) = a(i)
+ end do
+ !$acc end parallel
+
+end subroutine
+
+subroutine subr5 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc kernels deviceptr (a) copy (b)
+ do i = 1, N
+ a(i) = i * 32
+ b(i) = a(i)
+ end do
+ !$acc end kernels
+
+end subroutine
+
+subroutine subr6 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc parallel deviceptr (a) copy (b)
+ do i = 1, N
+ b(i) = i
+ end do
+ !$acc end parallel
+
+end subroutine
+
+subroutine subr7 (a, b)
+ implicit none
+ integer, parameter :: N = 8
+ integer :: a(N)
+ integer :: b(N)
+ integer :: i = 0
+
+ !$acc data deviceptr (a)
+
+ !$acc parallel copy (b)
+ do i = 1, N
+ a(i) = i * 2
+ b(i) = a(i)
+ end do
+ !$acc end parallel
+
+ !$acc parallel copy (b)
+ do i = 1, N
+ a(i) = b(i) * 2
+ b(i) = a(i)
+ end do
+ !$acc end parallel
+
+ !$acc end data
+
+end subroutine
+
+program main
+ use iso_c_binding, only: c_ptr, c_f_pointer
+ implicit none
+ type (c_ptr) :: cp
+ integer, parameter :: N = 8
+ integer, pointer :: fp(:)
+ integer :: i = 0
+ integer :: b(N)
+
+ interface
+ function acc_malloc (s) bind (C)
+ use iso_c_binding, only: c_ptr, c_size_t
+ integer (c_size_t), value :: s
+ type (c_ptr) :: acc_malloc
+ end function
+ end interface
+
+ cp = acc_malloc (N * sizeof (fp(N)))
+ call c_f_pointer (cp, fp, [N])
+
+ call subr1 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 2) call abort
+ end do
+
+ call subr2 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 4) call abort
+ end do
+
+ call subr3 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 8) call abort
+ end do
+
+ call subr4 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 16) call abort
+ end do
+
+ call subr5 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 32) call abort
+ end do
+
+ call subr6 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i) call abort
+ end do
+
+ call subr7 (fp, b)
+
+ do i = 1, N
+ if (b(i) .ne. i * 4) call abort
+ end do
+
+end program main
