I've backported this patch from trunk to gomp-4_0-branch which teaches
the gimplifier to inspect the type of the value being pointed to when
deciding what type of implicit data mapping is necessary for a variable.
More discussing on this patch can be found here
<https://gcc.gnu.org/ml/gcc-patches/2016-01/msg00873.html>.
Cesar
2016-01-15 Cesar Philippidis <ce...@codesourcery.com>
gcc/
* gimplify.c (oacc_default_clause): Decode reference and pointer
types for both kernels and parallel regions.
libgomp/
* testsuite/libgomp.oacc-fortran/kernels-data.f90: New test.
diff --git a/gcc/gimplify.c b/gcc/gimplify.c
index 17144d1..eda2e9c 100644
--- a/gcc/gimplify.c
+++ b/gcc/gimplify.c
@@ -5994,6 +5994,10 @@ oacc_default_clause (struct gimplify_omp_ctx *ctx, tree decl, unsigned flags)
{
const char *rkind;
bool on_device = false;
+ tree type = TREE_TYPE (decl);
+
+ if (lang_hooks.decls.omp_privatize_by_reference (decl))
+ type = TREE_TYPE (type);
if ((ctx->region_type & (ORT_ACC_PARALLEL | ORT_ACC_KERNELS)) != 0
&& is_global_var (decl)
@@ -6012,7 +6016,7 @@ oacc_default_clause (struct gimplify_omp_ctx *ctx, tree decl, unsigned flags)
/* Scalars are default 'copy' under kernels, non-scalars are default
'present_or_copy'. */
flags |= GOVD_MAP;
- if (!AGGREGATE_TYPE_P (TREE_TYPE (decl)))
+ if (!AGGREGATE_TYPE_P (type))
flags |= GOVD_MAP_FORCE;
rkind = "kernels";
@@ -6020,12 +6024,6 @@ oacc_default_clause (struct gimplify_omp_ctx *ctx, tree decl, unsigned flags)
case ORT_ACC_PARALLEL:
{
- tree type = TREE_TYPE (decl);
-
- if (TREE_CODE (type) == REFERENCE_TYPE
- || POINTER_TYPE_P (type))
- type = TREE_TYPE (type);
-
if (on_device || AGGREGATE_TYPE_P (type))
/* Aggregates default to 'present_or_copy'. */
flags |= GOVD_MAP;
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/non-scalar-data.f90 b/libgomp/testsuite/libgomp.oacc-fortran/non-scalar-data.f90
new file mode 100644
index 0000000..4afb562
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/non-scalar-data.f90
@@ -0,0 +1,50 @@
+! Ensure that a non-scalar dummy arguments which are implicitly used inside
+! offloaded regions are properly mapped using present_or_copy.
+
+! { dg-do run }
+
+program main
+ implicit none
+
+ integer, parameter :: n = 100
+ integer :: array(n), i
+
+ !$acc data copy(array)
+ call kernels(array, n)
+
+ !$acc update host(array)
+
+ do i = 1, n
+ if (array(i) .ne. i) call abort
+ end do
+
+ call parallel(array, n)
+ !$acc end data
+
+ do i = 1, n
+ if (array(i) .ne. i+i) call abort
+ end do
+end program main
+
+subroutine kernels (array, n)
+ integer, dimension (n) :: array
+ integer :: n, i
+
+ !$acc kernels
+ do i = 1, n
+ array(i) = i
+ end do
+ !$acc end kernels
+end subroutine kernels
+
+
+subroutine parallel (array, n)
+ integer, dimension (n) :: array
+ integer :: n, i
+
+ !$acc parallel
+ do i = 1, n
+ array(i) = i+i
+ end do
+ !$acc end parallel
+end subroutine parallel
