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.

From-SVN: r247955

gcc/ChangeLog

+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

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:

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.  */

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);
 

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);

gcc/testsuite/ChangeLog

 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.

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" } } */

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" } } */

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" } } */

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" } } */

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" } }

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" } }

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" } }

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" } }

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
     {

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;