Use "oacc kernels" attribute for OpenACC kernels
Thomas Schwinge
thomas@codesourcery.com
Fri May 12 09:22:00 GMT 2017
Hi!
On Wed, 10 May 2017 18:28:38 +0200, Jakub Jelinek <jakub@redhat.com> wrote:
> On Mon, May 08, 2017 at 09:29:28PM +0200, Thomas Schwinge wrote:
> > Use "oacc kernels" attribute for OpenACC kernels
> > * omp-expand.c (expand_omp_target)
> > <GF_OMP_TARGET_KIND_OACC_KERNELS>: Set "oacc kernels" attribute.
>
> I think
> * omp-expand.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
> Set "oacc kernels" attribute.
> fits better.
So you overrule how Emacs Change Log mode's fill-paragraph things this
should be formatted. ;-)
> > @@ -7451,7 +7457,7 @@ expand_omp_target (struct omp_region *region)
> > break;
> > case BUILT_IN_GOACC_PARALLEL:
> > {
> > - oacc_set_fn_attrib (child_fn, clauses, oacc_kernels_p, &args);
> > + oacc_set_fn_attrib (child_fn, clauses, &args);
> > tagging = true;
> > }
> > /* FALLTHRU */
>
> The {}s aren't needed around this, could you drop them?
Done, but aren't such cleanups usually requested to be done separately of
actual code changes?
> > + pos = tree_cons (purpose[ix],
> > + build_int_cst (integer_type_node, dims[ix]),
> > + pos);
>
> pos); would fit on the earlier line.
As already split over more than one line, I thought it was clearer if the
"chain" parameter was on its own line -- but you get to overrule me
there, too. ;-)
> Ok with those changes.
Thanks; committed to trunk in r247955:
commit 1d3ea8fcacec29c9a89d9d0a505ed5fbdd5ad73e
Author: tschwinge <tschwinge@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Fri May 12 09:02:55 2017 +0000
Use "oacc kernels" attribute for OpenACC kernels
gcc/
* omp-expand.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
Set "oacc kernels" attribute.
* omp-general.c (oacc_set_fn_attrib): Remove is_kernel formal
parameter. Adjust all users.
(oacc_fn_attrib_kernels_p): Remove function.
* omp-offload.c (execute_oacc_device_lower): Look for "oacc
kernels" attribute instead of calling oacc_fn_attrib_kernels_p.
* tree-ssa-loop.c (gate_oacc_kernels): Likewise.
* tree-parloops.c (create_parallel_loop): If oacc_kernels_p,
assert "oacc kernels" attribute is set.
gcc/testsuite/
* c-c++-common/goacc/classify-kernels-unparallelized.c: Adjust.
* c-c++-common/goacc/classify-kernels.c: Likewise.
* c-c++-common/goacc/classify-parallel.c: Likewise.
* c-c++-common/goacc/classify-routine.c: Likewise.
* gfortran.dg/goacc/classify-kernels-unparallelized.f95: Likewise.
* gfortran.dg/goacc/classify-kernels.f95: Likewise.
* gfortran.dg/goacc/classify-parallel.f95: Likewise.
* gfortran.dg/goacc/classify-routine.f95: Likewise.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@247955 138bc75d-0d04-0410-961f-82ee72b054a4
---
gcc/ChangeLog | 13 ++++++++++++
gcc/omp-expand.c | 20 ++++++++++--------
gcc/omp-general.c | 18 ++--------------
gcc/omp-general.h | 4 +---
gcc/omp-offload.c | 24 +++++++++++-----------
gcc/testsuite/ChangeLog | 9 ++++++++
.../goacc/classify-kernels-unparallelized.c | 8 ++++----
.../c-c++-common/goacc/classify-kernels.c | 8 ++++----
.../c-c++-common/goacc/classify-parallel.c | 2 +-
.../c-c++-common/goacc/classify-routine.c | 2 +-
.../goacc/classify-kernels-unparallelized.f95 | 8 ++++----
.../gfortran.dg/goacc/classify-kernels.f95 | 8 ++++----
.../gfortran.dg/goacc/classify-parallel.f95 | 2 +-
.../gfortran.dg/goacc/classify-routine.f95 | 2 +-
gcc/tree-parloops.c | 5 ++++-
gcc/tree-ssa-loop.c | 5 +----
16 files changed, 74 insertions(+), 64 deletions(-)
diff --git gcc/ChangeLog gcc/ChangeLog
index e1f8cf5..aeb22df 100644
--- gcc/ChangeLog
+++ gcc/ChangeLog
@@ -1,3 +1,16 @@
+2017-05-12 Thomas Schwinge <thomas@codesourcery.com>
+
+ * omp-expand.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
+ Set "oacc kernels" attribute.
+ * omp-general.c (oacc_set_fn_attrib): Remove is_kernel formal
+ parameter. Adjust all users.
+ (oacc_fn_attrib_kernels_p): Remove function.
+ * omp-offload.c (execute_oacc_device_lower): Look for "oacc
+ kernels" attribute instead of calling oacc_fn_attrib_kernels_p.
+ * tree-ssa-loop.c (gate_oacc_kernels): Likewise.
+ * tree-parloops.c (create_parallel_loop): If oacc_kernels_p,
+ assert "oacc kernels" attribute is set.
+
2017-05-11 Carl Love <cel@us.ibm.com>
* config/rs6000/rs6000-c: Add support for built-in functions
diff --git gcc/omp-expand.c gcc/omp-expand.c
index 5c48b78..7a7c747 100644
--- gcc/omp-expand.c
+++ gcc/omp-expand.c
@@ -7083,7 +7083,16 @@ expand_omp_target (struct omp_region *region)
exit_bb = region->exit;
if (gimple_omp_target_kind (entry_stmt) == GF_OMP_TARGET_KIND_OACC_KERNELS)
- mark_loops_in_oacc_kernels_region (region->entry, region->exit);
+ {
+ mark_loops_in_oacc_kernels_region (region->entry, region->exit);
+
+ /* Further down, both OpenACC kernels and OpenACC parallel constructs
+ will be mappted to BUILT_IN_GOACC_PARALLEL, and to distinguish the
+ two, there is an "oacc kernels" attribute set for OpenACC kernels. */
+ DECL_ATTRIBUTES (child_fn)
+ = tree_cons (get_identifier ("oacc kernels"),
+ NULL_TREE, DECL_ATTRIBUTES (child_fn));
+ }
if (offloaded)
{
@@ -7266,7 +7275,6 @@ expand_omp_target (struct omp_region *region)
enum built_in_function start_ix;
location_t clause_loc;
unsigned int flags_i = 0;
- bool oacc_kernels_p = false;
switch (gimple_omp_target_kind (entry_stmt))
{
@@ -7287,8 +7295,6 @@ expand_omp_target (struct omp_region *region)
flags_i |= GOMP_TARGET_FLAG_EXIT_DATA;
break;
case GF_OMP_TARGET_KIND_OACC_KERNELS:
- oacc_kernels_p = true;
- /* FALLTHROUGH */
case GF_OMP_TARGET_KIND_OACC_PARALLEL:
start_ix = BUILT_IN_GOACC_PARALLEL;
break;
@@ -7450,10 +7456,8 @@ expand_omp_target (struct omp_region *region)
args.quick_push (get_target_arguments (&gsi, entry_stmt));
break;
case BUILT_IN_GOACC_PARALLEL:
- {
- oacc_set_fn_attrib (child_fn, clauses, oacc_kernels_p, &args);
- tagging = true;
- }
+ oacc_set_fn_attrib (child_fn, clauses, &args);
+ tagging = true;
/* FALLTHRU */
case BUILT_IN_GOACC_ENTER_EXIT_DATA:
case BUILT_IN_GOACC_UPDATE:
diff --git gcc/omp-general.c gcc/omp-general.c
index 3f9aec8..9a5ed88 100644
--- gcc/omp-general.c
+++ gcc/omp-general.c
@@ -515,11 +515,10 @@ oacc_replace_fn_attrib (tree fn, tree dims)
/* Scan CLAUSES for launch dimensions and attach them to the oacc
function attribute. Push any that are non-constant onto the ARGS
- list, along with an appropriate GOMP_LAUNCH_DIM tag. IS_KERNEL is
- true, if these are for a kernels region offload function. */
+ list, along with an appropriate GOMP_LAUNCH_DIM tag. */
void
-oacc_set_fn_attrib (tree fn, tree clauses, bool is_kernel, vec<tree> *args)
+oacc_set_fn_attrib (tree fn, tree clauses, vec<tree> *args)
{
/* Must match GOMP_DIM ordering. */
static const omp_clause_code ids[]
@@ -545,9 +544,6 @@ oacc_set_fn_attrib (tree fn, tree clauses, bool is_kernel, vec<tree> *args)
non_const |= GOMP_DIM_MASK (ix);
}
attr = tree_cons (NULL_TREE, dim, attr);
- /* Note kernelness with TREE_PUBLIC. */
- if (is_kernel)
- TREE_PUBLIC (attr) = 1;
}
oacc_replace_fn_attrib (fn, attr);
@@ -616,16 +612,6 @@ oacc_get_fn_attrib (tree fn)
return lookup_attribute (OACC_FN_ATTRIB, DECL_ATTRIBUTES (fn));
}
-/* Return true if this oacc fn attrib is for a kernels offload
- region. We use the TREE_PUBLIC flag of each dimension -- only
- need to check the first one. */
-
-bool
-oacc_fn_attrib_kernels_p (tree attr)
-{
- return TREE_PUBLIC (TREE_VALUE (attr));
-}
-
/* Extract an oacc execution dimension from FN. FN must be an
offloaded function or routine that has already had its execution
dimensions lowered to the target-specific values. */
diff --git gcc/omp-general.h gcc/omp-general.h
index 3cf7fce..d28eb4b 100644
--- gcc/omp-general.h
+++ gcc/omp-general.h
@@ -82,11 +82,9 @@ extern int omp_max_vf (void);
extern int omp_max_simt_vf (void);
extern tree oacc_launch_pack (unsigned code, tree device, unsigned op);
extern void oacc_replace_fn_attrib (tree fn, tree dims);
-extern void oacc_set_fn_attrib (tree fn, tree clauses, bool is_kernel,
- vec<tree> *args);
+extern void oacc_set_fn_attrib (tree fn, tree clauses, vec<tree> *args);
extern tree oacc_build_routine_dims (tree clauses);
extern tree oacc_get_fn_attrib (tree fn);
-extern bool oacc_fn_attrib_kernels_p (tree attr);
extern int oacc_get_fn_dim_size (tree fn, int axis);
extern int oacc_get_ifn_dim_arg (const gimple *stmt);
diff --git gcc/omp-offload.c gcc/omp-offload.c
index beeeb71..d24f131 100644
--- gcc/omp-offload.c
+++ gcc/omp-offload.c
@@ -619,7 +619,6 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
tree purpose[GOMP_DIM_MAX];
unsigned ix;
tree pos = TREE_VALUE (attrs);
- bool is_kernel = oacc_fn_attrib_kernels_p (attrs);
/* Make sure the attribute creator attached the dimension
information. */
@@ -666,13 +665,8 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
/* Replace the attribute with new values. */
pos = NULL_TREE;
for (ix = GOMP_DIM_MAX; ix--;)
- {
- pos = tree_cons (purpose[ix],
- build_int_cst (integer_type_node, dims[ix]),
- pos);
- if (is_kernel)
- TREE_PUBLIC (pos) = 1;
- }
+ pos = tree_cons (purpose[ix],
+ build_int_cst (integer_type_node, dims[ix]), pos);
oacc_replace_fn_attrib (fn, pos);
}
}
@@ -1455,10 +1449,16 @@ execute_oacc_device_lower ()
int fn_level = oacc_fn_attrib_level (attrs);
if (dump_file)
- fprintf (dump_file, oacc_fn_attrib_kernels_p (attrs)
- ? "Function is kernels offload\n"
- : fn_level < 0 ? "Function is parallel offload\n"
- : "Function is routine level %d\n", fn_level);
+ {
+ if (fn_level >= 0)
+ fprintf (dump_file, "Function is OpenACC routine level %d\n",
+ fn_level);
+ else if (lookup_attribute ("oacc kernels",
+ DECL_ATTRIBUTES (current_function_decl)))
+ fprintf (dump_file, "Function is OpenACC kernels offload\n");
+ else
+ fprintf (dump_file, "Function is OpenACC parallel offload\n");
+ }
unsigned outer_mask = fn_level >= 0 ? GOMP_DIM_MASK (fn_level) - 1 : 0;
unsigned used_mask = oacc_loop_partition (loops, outer_mask);
diff --git gcc/testsuite/ChangeLog gcc/testsuite/ChangeLog
index 5ed40a5..52865d3 100644
--- gcc/testsuite/ChangeLog
+++ gcc/testsuite/ChangeLog
@@ -1,5 +1,14 @@
2017-05-12 Thomas Schwinge <thomas@codesourcery.com>
+ * c-c++-common/goacc/classify-kernels-unparallelized.c: Adjust.
+ * c-c++-common/goacc/classify-kernels.c: Likewise.
+ * c-c++-common/goacc/classify-parallel.c: Likewise.
+ * c-c++-common/goacc/classify-routine.c: Likewise.
+ * gfortran.dg/goacc/classify-kernels-unparallelized.f95: Likewise.
+ * gfortran.dg/goacc/classify-kernels.f95: Likewise.
+ * gfortran.dg/goacc/classify-parallel.f95: Likewise.
+ * gfortran.dg/goacc/classify-routine.f95: Likewise.
+
* c-c++-common/goacc/classify-kernels-unparallelized.c: New file.
* c-c++-common/goacc/classify-kernels.c: Likewise.
* c-c++-common/goacc/classify-parallel.c: Likewise.
diff --git gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
index a76351c..70ff428 100644
--- gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
+++ gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
@@ -24,16 +24,16 @@ void KERNELS ()
}
/* Check the offloaded function's attributes.
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } } */
+ { 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 \\(, , \\), omp target entrypoint\\)\\)" 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 kernels offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-kernels.c gcc/testsuite/c-c++-common/goacc/classify-kernels.c
index 199a73e..c8b0fda 100644
--- gcc/testsuite/c-c++-common/goacc/classify-kernels.c
+++ gcc/testsuite/c-c++-common/goacc/classify-kernels.c
@@ -20,16 +20,16 @@ void KERNELS ()
}
/* Check the offloaded function's attributes.
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } } */
+ { 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 be parallelized.
{ dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), omp target entrypoint\\)\\)" 1 "parloops1" } }
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
{ dg-final { scan-tree-dump-not "FAILED:" "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 kernels offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-parallel.c gcc/testsuite/c-c++-common/goacc/classify-parallel.c
index 9d48c1b..4f97301 100644
--- gcc/testsuite/c-c++-common/goacc/classify-parallel.c
+++ gcc/testsuite/c-c++-common/goacc/classify-parallel.c
@@ -23,6 +23,6 @@ void PARALLEL ()
/* 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 parallel offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-routine.c gcc/testsuite/c-c++-common/goacc/classify-routine.c
index 72b02c2..fd89fc1 100644
--- gcc/testsuite/c-c++-common/goacc/classify-routine.c
+++ gcc/testsuite/c-c++-common/goacc/classify-routine.c
@@ -25,6 +25,6 @@ void ROUTINE ()
/* 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 routine level 1" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target, oacc function \\(0 1, 1 0, 1 0\\)\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95 gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
index fd46d0d..9887d35 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
@@ -26,16 +26,16 @@ program main
end program main
! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } }
+! { 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 \\(, , \\), omp target entrypoint\\)\\)" 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 kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95 gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
index 053d27c..69c89a9 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
@@ -22,16 +22,16 @@ program main
end program main
! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } }
+! { 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 be parallelized.
! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), omp target entrypoint\\)\\)" 1 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
! { dg-final { scan-tree-dump-not "FAILED:" "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 kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95 gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
index 087ff48..e215c79 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
@@ -25,6 +25,6 @@ end program main
! 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 parallel offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-routine.f95 gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
index 319d767..4ca4067 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
@@ -24,6 +24,6 @@ end subroutine ROUTINE
! 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 routine level 1" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target, oacc function \\(0 0, 1 0, 1 0\\)\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/tree-parloops.c gcc/tree-parloops.c
index 7393011..6ce9d84 100644
--- gcc/tree-parloops.c
+++ gcc/tree-parloops.c
@@ -2043,10 +2043,13 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
/* Prepare the GIMPLE_OMP_PARALLEL statement. */
if (oacc_kernels_p)
{
+ gcc_checking_assert (lookup_attribute ("oacc kernels",
+ DECL_ATTRIBUTES (cfun->decl)));
+
tree clause = build_omp_clause (loc, OMP_CLAUSE_NUM_GANGS);
OMP_CLAUSE_NUM_GANGS_EXPR (clause)
= build_int_cst (integer_type_node, n_threads);
- oacc_set_fn_attrib (cfun->decl, clause, true, NULL);
+ oacc_set_fn_attrib (cfun->decl, clause, NULL);
}
else
{
diff --git gcc/tree-ssa-loop.c gcc/tree-ssa-loop.c
index 8b25b41..10c43f3 100644
--- gcc/tree-ssa-loop.c
+++ gcc/tree-ssa-loop.c
@@ -152,10 +152,7 @@ gate_oacc_kernels (function *fn)
if (!flag_openacc)
return false;
- tree oacc_function_attr = oacc_get_fn_attrib (fn->decl);
- if (oacc_function_attr == NULL_TREE)
- return false;
- if (!oacc_fn_attrib_kernels_p (oacc_function_attr))
+ if (!lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (fn->decl)))
return false;
struct loop *loop;
Committed to gomp-4_0-branch in r247956:
commit 01a98ef0ceb7afc15b7a97054bbff1db0ccf9fb4
Author: tschwinge <tschwinge@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Fri May 12 09:03:37 2017 +0000
Use "oacc kernels" attribute for OpenACC kernels
gcc/
* omp-low.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
Set "oacc kernels" attribute.
(set_oacc_fn_attrib): Remove is_kernel formal parameter. Adjust
all users.
(oacc_fn_attrib_kernels_p): Remove function.
(oacc_validate_dims, execute_oacc_device_lower): Look for "oacc
kernels" attribute instead of calling oacc_fn_attrib_kernels_p.
* tree-ssa-loop.c (gate_oacc_kernels): Likewise.
* config/nvptx/nvptx.c (nvptx_goacc_validate_dims): Likewise.
* tree-parloops.c (create_parallel_loop): If oacc_kernels_p,
assert "oacc kernels" attribute is set.
gcc/testsuite/
* c-c++-common/goacc/oaccdevlow-kernels.c: Adjust.
* c-c++-common/goacc/oaccdevlow-parallel.c: Likewise.
* c-c++-common/goacc/oaccdevlow-routine.c: Likewise.
* gfortran.dg/goacc/oaccdevlow-kernels.f95: Likewise.
* gfortran.dg/goacc/oaccdevlow-parallel.f95: Likewise.
* gfortran.dg/goacc/oaccdevlow-routine.f95: Likewise.
trunk r247955
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/branches/gomp-4_0-branch@247956 138bc75d-0d04-0410-961f-82ee72b054a4
---
gcc/ChangeLog.gomp | 14 +++++
gcc/config/nvptx/nvptx.c | 4 +-
gcc/omp-low.c | 65 ++++++++++------------
gcc/omp-low.h | 3 +-
gcc/testsuite/ChangeLog.gomp | 7 +++
.../goacc/classify-kernels-unparallelized.c | 8 +--
.../c-c++-common/goacc/classify-kernels.c | 8 +--
.../c-c++-common/goacc/classify-parallel.c | 2 +-
.../c-c++-common/goacc/classify-routine.c | 2 +-
.../goacc/classify-kernels-unparallelized.f95 | 8 +--
.../gfortran.dg/goacc/classify-kernels.f95 | 8 +--
.../gfortran.dg/goacc/classify-parallel.f95 | 2 +-
.../gfortran.dg/goacc/classify-routine.f95 | 2 +-
gcc/tree-parloops.c | 5 +-
gcc/tree-ssa-loop.c | 5 +-
15 files changed, 76 insertions(+), 67 deletions(-)
diff --git gcc/ChangeLog.gomp gcc/ChangeLog.gomp
index 5139796..8cd46c3 100644
--- gcc/ChangeLog.gomp
+++ gcc/ChangeLog.gomp
@@ -1,3 +1,17 @@
+2017-05-12 Thomas Schwinge <thomas@codesourcery.com>
+
+ * omp-low.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
+ Set "oacc kernels" attribute.
+ (set_oacc_fn_attrib): Remove is_kernel formal parameter. Adjust
+ all users.
+ (oacc_fn_attrib_kernels_p): Remove function.
+ (oacc_validate_dims, execute_oacc_device_lower): Look for "oacc
+ kernels" attribute instead of calling oacc_fn_attrib_kernels_p.
+ * tree-ssa-loop.c (gate_oacc_kernels): Likewise.
+ * config/nvptx/nvptx.c (nvptx_goacc_validate_dims): Likewise.
+ * tree-parloops.c (create_parallel_loop): If oacc_kernels_p,
+ assert "oacc kernels" attribute is set.
+
2017-05-11 Cesar Philippidis <cesar@codesourcery.com>
* gimplify.c (gomp_needs_data_present): Ensure that the
diff --git gcc/config/nvptx/nvptx.c gcc/config/nvptx/nvptx.c
index f790728..f3c1525 100644
--- gcc/config/nvptx/nvptx.c
+++ gcc/config/nvptx/nvptx.c
@@ -4284,10 +4284,8 @@ nvptx_goacc_validate_dims (tree decl, int dims[], int fn_level)
construct could not be parallelized, but only do that for -O2 and
higher, as otherwise we're not expecting any parallelization to
happen. */
- tree oacc_function_attr = get_oacc_fn_attrib (decl);
if (optimize >= 2
- && oacc_function_attr
- && oacc_fn_attrib_kernels_p (oacc_function_attr))
+ && lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (decl)))
{
bool avoid_offloading_p = true;
for (unsigned ix = 0; ix != GOMP_DIM_MAX; ix++)
diff --git gcc/omp-low.c gcc/omp-low.c
index a681800..18872f9 100644
--- gcc/omp-low.c
+++ gcc/omp-low.c
@@ -13136,11 +13136,10 @@ replace_oacc_fn_attrib (tree fn, tree dims)
/* Scan CLAUSES for launch dimensions and attach them to the oacc
function attribute. Push any that are non-constant onto the ARGS
- list, along with an appropriate GOMP_LAUNCH_DIM tag. IS_KERNEL is
- true, if these are for a kernels region offload function. */
+ list, along with an appropriate GOMP_LAUNCH_DIM tag. */
void
-set_oacc_fn_attrib (tree fn, tree clauses, bool is_kernel, vec<tree> *args)
+set_oacc_fn_attrib (tree fn, tree clauses, vec<tree> *args)
{
/* Must match GOMP_DIM ordering. */
static const omp_clause_code ids[]
@@ -13165,9 +13164,6 @@ set_oacc_fn_attrib (tree fn, tree clauses, bool is_kernel, vec<tree> *args)
non_const |= GOMP_DIM_MASK (ix);
}
attr = tree_cons (NULL_TREE, dim, attr);
- /* Note kernelness with TREE_PUBLIC. */
- if (is_kernel)
- TREE_PUBLIC (attr) = 1;
}
replace_oacc_fn_attrib (fn, attr);
@@ -13423,16 +13419,6 @@ get_oacc_fn_attrib (tree fn)
return lookup_attribute (OACC_FN_ATTRIB, DECL_ATTRIBUTES (fn));
}
-/* Return true if this oacc fn attrib is for a kernels offload
- region. We use the TREE_PUBLIC flag of each dimension -- only
- need to check the first one. */
-
-bool
-oacc_fn_attrib_kernels_p (tree attr)
-{
- return TREE_PUBLIC (TREE_VALUE (attr));
-}
-
/* Return level at which oacc routine may spawn a partitioned loop, or
-1 if it is not a routine (i.e. is an offload fn). */
@@ -13815,7 +13801,16 @@ expand_omp_target (struct omp_region *region)
exit_bb = region->exit;
if (gimple_omp_target_kind (entry_stmt) == GF_OMP_TARGET_KIND_OACC_KERNELS)
- mark_loops_in_oacc_kernels_region (region->entry, region->exit);
+ {
+ mark_loops_in_oacc_kernels_region (region->entry, region->exit);
+
+ /* Further down, both OpenACC kernels and OpenACC parallel constructs
+ will be mappted to BUILT_IN_GOACC_PARALLEL, and to distinguish the
+ two, there is an "oacc kernels" attribute set for OpenACC kernels. */
+ DECL_ATTRIBUTES (child_fn)
+ = tree_cons (get_identifier ("oacc kernels"),
+ NULL_TREE, DECL_ATTRIBUTES (child_fn));
+ }
if (offloaded)
{
@@ -13995,7 +13990,6 @@ expand_omp_target (struct omp_region *region)
enum built_in_function start_ix;
location_t clause_loc;
unsigned int flags_i = 0;
- bool oacc_kernels_p = false;
switch (gimple_omp_target_kind (entry_stmt))
{
@@ -14016,8 +14010,6 @@ expand_omp_target (struct omp_region *region)
flags_i |= GOMP_TARGET_FLAG_EXIT_DATA;
break;
case GF_OMP_TARGET_KIND_OACC_KERNELS:
- oacc_kernels_p = true;
- /* FALLTHROUGH */
case GF_OMP_TARGET_KIND_OACC_PARALLEL:
start_ix = BUILT_IN_GOACC_PARALLEL;
break;
@@ -14179,10 +14171,8 @@ expand_omp_target (struct omp_region *region)
args.quick_push (get_target_arguments (&gsi, entry_stmt));
break;
case BUILT_IN_GOACC_PARALLEL:
- {
- set_oacc_fn_attrib (child_fn, clauses, oacc_kernels_p, &args);
- tagging = true;
- }
+ set_oacc_fn_attrib (child_fn, clauses, &args);
+ tagging = true;
/* FALLTHRU */
case BUILT_IN_GOACC_ENTER_EXIT_DATA:
case BUILT_IN_GOACC_UPDATE:
@@ -20249,7 +20239,6 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
tree purpose[GOMP_DIM_MAX];
unsigned ix;
tree pos = TREE_VALUE (attrs);
- bool is_kernel = oacc_fn_attrib_kernels_p (attrs);
/* Make sure the attribute creator attached the dimension
information. */
@@ -20270,7 +20259,8 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
and/or dimensions. */
check = false;
#endif
- if (!is_kernel && check)
+ if (check
+ && !lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (fn)))
{
static char const *const axes[] =
/* Must be kept in sync with GOMP_DIM enumeration. */
@@ -20326,13 +20316,8 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
/* Replace the attribute with new values. */
pos = NULL_TREE;
for (ix = GOMP_DIM_MAX; ix--;)
- {
- pos = tree_cons (purpose[ix],
- build_int_cst (integer_type_node, dims[ix]),
- pos);
- if (is_kernel)
- TREE_PUBLIC (pos) = 1;
- }
+ pos = tree_cons (purpose[ix],
+ build_int_cst (integer_type_node, dims[ix]), pos);
replace_oacc_fn_attrib (fn, pos);
}
}
@@ -21191,10 +21176,16 @@ execute_oacc_device_lower ()
int fn_level = oacc_fn_attrib_level (attrs);
if (dump_file)
- fprintf (dump_file, oacc_fn_attrib_kernels_p (attrs)
- ? "Function is kernels offload\n"
- : fn_level < 0 ? "Function is parallel offload\n"
- : "Function is routine level %d\n", fn_level);
+ {
+ if (fn_level >= 0)
+ fprintf (dump_file, "Function is OpenACC routine level %d\n",
+ fn_level);
+ else if (lookup_attribute ("oacc kernels",
+ DECL_ATTRIBUTES (current_function_decl)))
+ fprintf (dump_file, "Function is OpenACC kernels offload\n");
+ else
+ fprintf (dump_file, "Function is OpenACC parallel offload\n");
+ }
unsigned outer_mask = fn_level >= 0 ? GOMP_DIM_MASK (fn_level) - 1 : 0;
unsigned used_mask = oacc_loop_partition (loops, outer_mask);
diff --git gcc/omp-low.h gcc/omp-low.h
index 2602a12..0ea5308 100644
--- gcc/omp-low.h
+++ gcc/omp-low.h
@@ -34,8 +34,7 @@ extern void replace_oacc_fn_attrib (tree, tree);
extern int verify_oacc_routine_clauses (tree, tree *, location_t, const char *);
extern tree build_oacc_routine_dims (tree);
extern tree get_oacc_fn_attrib (tree);
-extern void set_oacc_fn_attrib (tree, tree, bool, vec<tree> *);
-extern bool oacc_fn_attrib_kernels_p (tree);
+extern void set_oacc_fn_attrib (tree, tree, vec<tree> *);
extern int get_oacc_ifn_dim_arg (const gimple *);
extern int get_oacc_fn_dim_size (tree, int);
diff --git gcc/testsuite/ChangeLog.gomp gcc/testsuite/ChangeLog.gomp
index b5dd1a4..9f2b7be 100644
--- gcc/testsuite/ChangeLog.gomp
+++ gcc/testsuite/ChangeLog.gomp
@@ -1,5 +1,12 @@
2017-05-12 Thomas Schwinge <thomas@codesourcery.com>
+ * c-c++-common/goacc/oaccdevlow-kernels.c: Adjust.
+ * c-c++-common/goacc/oaccdevlow-parallel.c: Likewise.
+ * c-c++-common/goacc/oaccdevlow-routine.c: Likewise.
+ * gfortran.dg/goacc/oaccdevlow-kernels.f95: Likewise.
+ * gfortran.dg/goacc/oaccdevlow-parallel.f95: Likewise.
+ * gfortran.dg/goacc/oaccdevlow-routine.f95: Likewise.
+
* c-c++-common/goacc/classify-kernels-unparallelized.c: New file.
* c-c++-common/goacc/classify-kernels.c: Likewise.
* c-c++-common/goacc/classify-parallel.c: Likewise.
diff --git gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
index a76351c..70ff428 100644
--- gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
+++ gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c
@@ -24,16 +24,16 @@ void KERNELS ()
}
/* Check the offloaded function's attributes.
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } } */
+ { 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 \\(, , \\), omp target entrypoint\\)\\)" 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 kernels offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-kernels.c gcc/testsuite/c-c++-common/goacc/classify-kernels.c
index 199a73e..c8b0fda 100644
--- gcc/testsuite/c-c++-common/goacc/classify-kernels.c
+++ gcc/testsuite/c-c++-common/goacc/classify-kernels.c
@@ -20,16 +20,16 @@ void KERNELS ()
}
/* Check the offloaded function's attributes.
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } } */
+ { 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 be parallelized.
{ dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), omp target entrypoint\\)\\)" 1 "parloops1" } }
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
{ dg-final { scan-tree-dump-not "FAILED:" "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 kernels offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-parallel.c gcc/testsuite/c-c++-common/goacc/classify-parallel.c
index 9d48c1b..4f97301 100644
--- gcc/testsuite/c-c++-common/goacc/classify-parallel.c
+++ gcc/testsuite/c-c++-common/goacc/classify-parallel.c
@@ -23,6 +23,6 @@ void PARALLEL ()
/* 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 parallel offload" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/c-c++-common/goacc/classify-routine.c gcc/testsuite/c-c++-common/goacc/classify-routine.c
index d37fb4a..f54c394 100644
--- gcc/testsuite/c-c++-common/goacc/classify-routine.c
+++ gcc/testsuite/c-c++-common/goacc/classify-routine.c
@@ -25,6 +25,6 @@ void ROUTINE ()
/* 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 routine level 1" 1 "oaccdevlow" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
{ dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target \\(worker\\), oacc function \\(0 1, 1 0, 1 0\\)\\)\\)" 1 "oaccdevlow" } } */
diff --git gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95 gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
index fd46d0d..9887d35 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95
@@ -26,16 +26,16 @@ program main
end program main
! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } }
+! { 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 \\(, , \\), omp target entrypoint\\)\\)" 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 kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95 gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
index 053d27c..69c89a9 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95
@@ -22,16 +22,16 @@ program main
end program main
! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(omp target entrypoint\\)\\)" 1 "ompexp" } }
+! { 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 be parallelized.
! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), omp target entrypoint\\)\\)" 1 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
! { dg-final { scan-tree-dump-not "FAILED:" "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 kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95 gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
index 087ff48..e215c79 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-parallel.f95
@@ -25,6 +25,6 @@ end program main
! 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 parallel offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/testsuite/gfortran.dg/goacc/classify-routine.f95 gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
index dd71a84..445ff9a 100644
--- gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
+++ gcc/testsuite/gfortran.dg/goacc/classify-routine.f95
@@ -24,6 +24,6 @@ end subroutine ROUTINE
! 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 routine level 1" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target, oacc function \\(0 1, 1 0, 1 0\\)\\)\\)" 1 "oaccdevlow" } }
diff --git gcc/tree-parloops.c gcc/tree-parloops.c
index 2e55b79..a94f7a2 100644
--- gcc/tree-parloops.c
+++ gcc/tree-parloops.c
@@ -2041,10 +2041,13 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
/* Prepare the GIMPLE_OMP_PARALLEL statement. */
if (oacc_kernels_p)
{
+ gcc_checking_assert (lookup_attribute ("oacc kernels",
+ DECL_ATTRIBUTES (cfun->decl)));
+
tree clause = build_omp_clause (loc, OMP_CLAUSE_NUM_GANGS);
OMP_CLAUSE_NUM_GANGS_EXPR (clause)
= build_int_cst (integer_type_node, n_threads);
- set_oacc_fn_attrib (cfun->decl, clause, true, NULL);
+ set_oacc_fn_attrib (cfun->decl, clause, NULL);
}
else
{
diff --git gcc/tree-ssa-loop.c gcc/tree-ssa-loop.c
index 06354e3..da9a806 100644
--- gcc/tree-ssa-loop.c
+++ gcc/tree-ssa-loop.c
@@ -151,10 +151,7 @@ gate_oacc_kernels (function *fn)
if (!flag_openacc)
return false;
- tree oacc_function_attr = get_oacc_fn_attrib (fn->decl);
- if (oacc_function_attr == NULL_TREE)
- return false;
- if (!oacc_fn_attrib_kernels_p (oacc_function_attr))
+ if (!lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (fn->decl)))
return false;
struct loop *loop;
Grüße
Thomas
More information about the Gcc-patches
mailing list