gomp-constants.h (GOMP_VERSION_NVIDIA_PTX): Increment.

	inlude/
	* gomp-constants.h (GOMP_VERSION_NVIDIA_PTX): Increment.
	(GOMP_DIM_GANG, GOMP_DIM_WORKER, GOMP_DIM_VECTOR, GOMP_DIM_MAX,
	GOMP_DIM_MASK): New.
	(GOMP_LAUNCH_DIM, GOMP_LAUNCH_ASYNC, GOMP_LAUNCH_WAIT): New.
	(GOMP_LAUNCH_CODE_SHIFT, GOMP_LAUNCH_DEVICE_SHIFT,
	GOMP_LAUNCH_OP_SHIFT): New.
	(GOMP_LAUNCH_PACK, GOMP_LAUNCH_CODE, GOMP_LAUNCH_DEVICE,
	GOMP_LAUNCH_OP): New.
	(GOMP_LAUNCH_OP_MAX): New.

	libgomp/
	* libgomp.h (acc_dispatch_t): Replace separate geometry args with
	array.
	* libgomp.map (GOACC_parallel_keyed): New.
	* oacc-parallel.c (goacc_wait): Take pointer to va_list.  Adjust
	all callers.
	(GOACC_parallel_keyed): New interface.  Lose geometry arguments
	and take keyed varargs list.  Adjust call to exec_func.
	(GOACC_parallel): Force host fallback.
	* libgomp_g.h (GOACC_parallel): Remove.
	(GOACC_parallel_keyed): Declare.
	* plugin/plugin-nvptx.c (struct targ_fn_launch): New struct.
	(stuct targ_gn_descriptor): Replace name field with launch field.
	(nvptx_exec): Lose separate geometry args, take array.  Process
	dynamic dimensions and adjust.
	(struct nvptx_tdata): Replace fn_names field with fn_descs.
	(GOMP_OFFLOAD_load_image): Adjust for change in function table
	data.
	(GOMP_OFFLOAD_openacc_parallel): Adjust for change in dimension
	passing.
	* oacc-host.c (host_openacc_exec): Adjust for change in dimension
	passing.

	gcc/
	* config/nvptx/nvptx.c: Include omp-low.h and gomp-constants.h.
	(nvptx_record_offload_symbol): Record function execution geometry.
	* config/nvptx/mkoffload.c (process): Include launch geometry in
	function data.
	* omp-low.c (oacc_launch_pack): New.
	(replace_oacc_fn_attrib): New.
	(set_oacc_fn_attrib): New.
	(get_oacc_fn_attrib): New.
	(expand_omp_target): Create keyed varargs for GOACC_parallel call
	generation.
	* omp-low.h (get_oacc_fn_attrib): Declare.
	* builtin-types.def (DEF_FUNCTION_TyPE_VAR_6): New.
	(DEF_FUNCTION_TYPE_VAR_11): Delete.
	* tree.h (OMP_CLAUSE_EXPR): New.
	* omp-builtins.def (BUILT_IN_GOACC_PARALLEL): Change target fn name.

	gcc/lto/
	* lto-lang.c (DEF_FUNCTION_TYPE_VAR_6): New.
	(DEF_FUNCTION_TYPE_VAR_11): Delete.

	gcc/c-family/
	* c-common.c (DEF_FUNCTION_TYPE_VAR_6): New.
	(DEF_FUNCTION_TYPE_VAR_11): Delete.

	gcc/fortran/
	* f95-lang.c (DEF_FUNCTION_TYPE_VAR_6): New.
	(DEF_FUNCTION_TYPE_VAR_11): Delete.
	* types.def (DEF_FUNCTION_TYPE_VAR_6): New.
	(DEF_FUNCTION_TYPE_VAR_11): Delete.

	gcc/ada/
	* gcc-interface/utils.c (DEF_FUNCTION_TYPE_VAR_6): Define

From-SVN: r228220

17 files changed, 308 insertions, 114 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 89b9e16..7fa6517 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,21 @@
+2015-09-28  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* config/nvptx/nvptx.c: Include omp-low.h and gomp-constants.h.
+	(nvptx_record_offload_symbol): Record function execution geometry.
+	* config/nvptx/mkoffload.c (process): Include launch geometry in
+	function data.
+	* omp-low.c (oacc_launch_pack): New.
+	(replace_oacc_fn_attrib): New.
+	(set_oacc_fn_attrib): New.
+	(get_oacc_fn_attrib): New.
+	(expand_omp_target): Create keyed varargs for GOACC_parallel call
+	generation.
+	* omp-low.h (get_oacc_fn_attrib): Declare.
+	* builtin-types.def (DEF_FUNCTION_TyPE_VAR_6): New.
+	(DEF_FUNCTION_TYPE_VAR_11): Delete.
+	* tree.h (OMP_CLAUSE_EXPR): New.
+	* omp-builtins.def (BUILT_IN_GOACC_PARALLEL): Change target fn name.
+
 2015-09-28  Aditya Kumar  <aditya.k7@samsung.com>
             Sebastian Pop  <s.pop@samsung.com>
 
diff --git a/gcc/ada/ChangeLog b/gcc/ada/ChangeLog
index ad9cf14..efb2d3a 100644
--- a/gcc/ada/ChangeLog
+++ b/gcc/ada/ChangeLog
@@ -1,3 +1,7 @@
+2015-09-28  Tom de Vries  <tom@codesourcery.com>
+
+	* gcc-interface/utils.c (DEF_FUNCTION_TYPE_VAR_6): Define
+
 2015-09-17  Eric Botcazou  <ebotcazou@adacore.com>
 
 	* gcc-interface/trans.c (emit_check): Do not touch TREE_SIDE_EFFECTS.
diff --git a/gcc/ada/gcc-interface/utils.c b/gcc/ada/gcc-interface/utils.c
index f54f2f0..672b910 100644
--- a/gcc/ada/gcc-interface/utils.c
+++ b/gcc/ada/gcc-interface/utils.c
@@ -5376,6 +5376,8 @@ enum c_builtin_type
 #define DEF_FUNCTION_TYPE_VAR_4(NAME, RETURN, ARG1, ARG2, ARG3, ARG4) NAME,
 #define DEF_FUNCTION_TYPE_VAR_5(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5) \
 				NAME,
+#define DEF_FUNCTION_TYPE_VAR_6(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6) NAME,
 #define DEF_FUNCTION_TYPE_VAR_7(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7) NAME,
 #define DEF_FUNCTION_TYPE_VAR_11(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
@@ -5398,6 +5400,7 @@ enum c_builtin_type
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
 #undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
@@ -5505,6 +5508,9 @@ install_builtin_function_types (void)
   def_fn_type (ENUM, RETURN, 1, 4, ARG1, ARG2, ARG3, ARG4);
 #define DEF_FUNCTION_TYPE_VAR_5(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5) \
   def_fn_type (ENUM, RETURN, 1, 5, ARG1, ARG2, ARG3, ARG4, ARG5);
+#define DEF_FUNCTION_TYPE_VAR_6(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6)				\
+  def_fn_type (ENUM, RETURN, 1, 6, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6);
 #define DEF_FUNCTION_TYPE_VAR_7(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7)				\
   def_fn_type (ENUM, RETURN, 1, 7, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6, ARG7);
@@ -5533,6 +5539,7 @@ install_builtin_function_types (void)
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
 #undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
diff --git a/gcc/builtin-types.def b/gcc/builtin-types.def
index 0e34531..9d20dcc 100644
--- a/gcc/builtin-types.def
+++ b/gcc/builtin-types.def
@@ -590,15 +590,14 @@ DEF_FUNCTION_TYPE_VAR_5 (BT_FN_INT_STRING_SIZE_INT_SIZE_CONST_STRING_VAR,
 DEF_FUNCTION_TYPE_VAR_5 (BT_FN_INT_INT_INT_INT_INT_INT_VAR,
 			 BT_INT, BT_INT, BT_INT, BT_INT, BT_INT, BT_INT)
 
+DEF_FUNCTION_TYPE_VAR_6 (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_VAR,
+			 BT_VOID, BT_INT, BT_PTR_FN_VOID_PTR, BT_SIZE,
+			 BT_PTR, BT_PTR, BT_PTR)
+
 DEF_FUNCTION_TYPE_VAR_7 (BT_FN_VOID_INT_SIZE_PTR_PTR_PTR_INT_INT_VAR,
 			 BT_VOID, BT_INT, BT_SIZE, BT_PTR, BT_PTR,
 			 BT_PTR, BT_INT, BT_INT)
 
-DEF_FUNCTION_TYPE_VAR_11 (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_INT_INT_INT_INT_INT_VAR,
-			  BT_VOID, BT_INT, BT_PTR_FN_VOID_PTR, BT_SIZE,
-			  BT_PTR, BT_PTR, BT_PTR, BT_INT, BT_INT, BT_INT,
-			  BT_INT, BT_INT)
-
 DEF_POINTER_TYPE (BT_PTR_FN_VOID_VAR, BT_FN_VOID_VAR)
 DEF_FUNCTION_TYPE_3 (BT_FN_PTR_PTR_FN_VOID_VAR_PTR_SIZE,
 		     BT_PTR, BT_PTR_FN_VOID_VAR, BT_PTR, BT_SIZE)
diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog
index 32d0d25..769f74a 100644
--- a/gcc/c-family/ChangeLog
+++ b/gcc/c-family/ChangeLog
@@ -1,3 +1,8 @@
+2015-09-28  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* c-common.c (DEF_FUNCTION_TYPE_VAR_6): New.
+	(DEF_FUNCTION_TYPE_VAR_11): Delete.
+
 2015-09-25  Marek Polacek  <polacek@redhat.com>
 
 	* c-ubsan.c (ubsan_instrument_division): Remove unnecessary code.
diff --git a/gcc/c-family/c-common.c b/gcc/c-family/c-common.c
index 879f4db..e539527 100644
--- a/gcc/c-family/c-common.c
+++ b/gcc/c-family/c-common.c
@@ -5548,10 +5548,10 @@ enum c_builtin_type
 #define DEF_FUNCTION_TYPE_VAR_4(NAME, RETURN, ARG1, ARG2, ARG3, ARG4) NAME,
 #define DEF_FUNCTION_TYPE_VAR_5(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5) \
 				NAME,
+#define DEF_FUNCTION_TYPE_VAR_6(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6) NAME,
 #define DEF_FUNCTION_TYPE_VAR_7(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7) NAME,
-#define DEF_FUNCTION_TYPE_VAR_11(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11) NAME,
 #define DEF_POINTER_TYPE(NAME, TYPE) NAME,
 #include "builtin-types.def"
 #undef DEF_PRIMITIVE_TYPE
@@ -5570,8 +5570,8 @@ enum c_builtin_type
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
   BT_LAST
 };
@@ -5664,13 +5664,12 @@ c_define_builtins (tree va_list_ref_type_node, tree va_list_arg_type_node)
   def_fn_type (ENUM, RETURN, 1, 4, ARG1, ARG2, ARG3, ARG4);
 #define DEF_FUNCTION_TYPE_VAR_5(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5) \
   def_fn_type (ENUM, RETURN, 1, 5, ARG1, ARG2, ARG3, ARG4, ARG5);
+#define DEF_FUNCTION_TYPE_VAR_6(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6) \
+  def_fn_type (ENUM, RETURN, 1, 6, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6);
 #define DEF_FUNCTION_TYPE_VAR_7(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7)				\
   def_fn_type (ENUM, RETURN, 1, 7, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6, ARG7);
-#define DEF_FUNCTION_TYPE_VAR_11(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11) \
-  def_fn_type (ENUM, RETURN, 1, 11, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6,      \
-	       ARG7, ARG8, ARG9, ARG10, ARG11);
 #define DEF_POINTER_TYPE(ENUM, TYPE) \
   builtin_types[(int) ENUM] = build_pointer_type (builtin_types[(int) TYPE]);
 
@@ -5692,8 +5691,8 @@ c_define_builtins (tree va_list_ref_type_node, tree va_list_arg_type_node)
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
   builtin_types[(int) BT_LAST] = NULL_TREE;
 
diff --git a/gcc/config/nvptx/mkoffload.c b/gcc/config/nvptx/mkoffload.c
index ba0454e..e0ff8fc 100644
--- a/gcc/config/nvptx/mkoffload.c
+++ b/gcc/config/nvptx/mkoffload.c
@@ -842,6 +842,8 @@ process (FILE *in, FILE *out)
 {
   const char *input = read_file (in);
   Token *tok = tokenize (input);
+  const char *comma;
+  id_map const *id;
 
   do
     tok = parse_file (tok);
@@ -853,21 +855,25 @@ process (FILE *in, FILE *out)
   write_stmts (out, rev_stmts (fns));
   fprintf (out, ";\n\n");
 
-  fprintf (out, "static const char *const var_mappings[] = {\n");
-  for (id_map *id = var_ids; id; id = id->next)
-    fprintf (out, "\t\"%s\"%s\n", id->ptx_name, id->next ? "," : "");
-  fprintf (out, "};\n\n");
-  fprintf (out, "static const char *const func_mappings[] = {\n");
-  for (id_map *id = func_ids; id; id = id->next)
-    fprintf (out, "\t\"%s\"%s\n", id->ptx_name, id->next ? "," : "");
-  fprintf (out, "};\n\n");
+  fprintf (out, "static const char *const var_mappings[] = {");
+  for (comma = "", id = var_ids; id; comma = ",", id = id->next)
+    fprintf (out, "%s\n\t%s", comma, id->ptx_name);
+  fprintf (out, "\n};\n\n");
+
+  fprintf (out, "static const struct nvptx_fn {\n"
+	   "  const char *name;\n"
+	   "  unsigned short dim[3];\n"
+	   "} func_mappings[] = {\n");
+  for (comma = "", id = func_ids; id; comma = ",", id = id->next)
+    fprintf (out, "%s\n\t{%s}", comma, id->ptx_name);
+  fprintf (out, "\n};\n\n");
 
   fprintf (out,
 	   "static const struct nvptx_tdata {\n"
 	   "  const char *ptx_src;\n"
 	   "  const char *const *var_names;\n"
 	   "  __SIZE_TYPE__ var_num;\n"
-	   "  const char *const *fn_names;\n"
+	   "  const struct nvptx_fn *fn_names;\n"
 	   "  __SIZE_TYPE__ fn_num;\n"
 	   "} target_data = {\n"
 	   "  ptx_code,\n"
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 1069d0e..0569a19 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -56,6 +56,8 @@
 #include "cfgrtl.h"
 #include "stor-layout.h"
 #include "builtins.h"
+#include "omp-low.h"
+#include "gomp-constants.h"
 
 /* This file should be included last.  */
 #include "target-def.h"
@@ -2066,9 +2068,51 @@ nvptx_vector_alignment (const_tree type)
 static void
 nvptx_record_offload_symbol (tree decl)
 {
-  fprintf (asm_out_file, "//:%s_MAP %s\n",
-	   TREE_CODE (decl) == VAR_DECL ? "VAR" : "FUNC",
-	   IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)));
+  switch (TREE_CODE (decl))
+    {
+    case VAR_DECL:
+      fprintf (asm_out_file, "//:VAR_MAP \"%s\"\n",
+	       IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)));
+      break;
+
+    case FUNCTION_DECL:
+      {
+	tree attr = get_oacc_fn_attrib (decl);
+	tree dims = NULL_TREE;
+	unsigned ix;
+
+	if (attr)
+	  dims = TREE_VALUE (attr);
+	fprintf (asm_out_file, "//:FUNC_MAP \"%s\"",
+		 IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl)));
+
+	for (ix = 0; ix != GOMP_DIM_MAX; ix++)
+	  {
+	    int size = 1;
+
+	    /* TODO: This check can go away once the dimension default
+	       machinery is merged to trunk.  */
+	    if (dims)
+	      {
+		tree dim = TREE_VALUE (dims);
+
+		if (dim)
+		  size = TREE_INT_CST_LOW (dim);
+
+		gcc_assert (!TREE_PURPOSE (dims));
+		dims = TREE_CHAIN (dims);
+	      }
+	    
+	    fprintf (asm_out_file, ", %#x", size);
+	  }
+	
+	fprintf (asm_out_file, "\n");
+      }
+      break;
+  
+    default:
+      gcc_unreachable ();
+    }
 }
 
 /* Implement TARGET_ASM_FILE_START.  Write the kinds of things ptxas expects
diff --git a/gcc/fortran/ChangeLog b/gcc/fortran/ChangeLog
index 6901ade..5159b8b 100644
--- a/gcc/fortran/ChangeLog
+++ b/gcc/fortran/ChangeLog
@@ -1,3 +1,10 @@
+2015-09-28  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* f95-lang.c (DEF_FUNCTION_TYPE_VAR_6): New.
+	(DEF_FUNCTION_TYPE_VAR_11): Delete.
+	* types.def (DEF_FUNCTION_TYPE_VAR_6): New.
+	(DEF_FUNCTION_TYPE_VAR_11): Delete.
+
 2015-09-26  Mikael Morin  <mikael@gcc.gnu.org>
 
 	PR fortran/67721
diff --git a/gcc/fortran/f95-lang.c b/gcc/fortran/f95-lang.c
index c42d0dd..0bcfb3f 100644
--- a/gcc/fortran/f95-lang.c
+++ b/gcc/fortran/f95-lang.c
@@ -635,10 +635,10 @@ gfc_init_builtin_functions (void)
 			    ARG6, ARG7, ARG8) NAME,
 #define DEF_FUNCTION_TYPE_VAR_0(NAME, RETURN) NAME,
 #define DEF_FUNCTION_TYPE_VAR_2(NAME, RETURN, ARG1, ARG2) NAME,
+#define DEF_FUNCTION_TYPE_VAR_6(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				 ARG6) NAME,
 #define DEF_FUNCTION_TYPE_VAR_7(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7) NAME,
-#define DEF_FUNCTION_TYPE_VAR_11(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11) NAME,
 #define DEF_POINTER_TYPE(NAME, TYPE) NAME,
 #include "types.def"
 #undef DEF_PRIMITIVE_TYPE
@@ -653,8 +653,8 @@ gfc_init_builtin_functions (void)
 #undef DEF_FUNCTION_TYPE_8
 #undef DEF_FUNCTION_TYPE_VAR_0
 #undef DEF_FUNCTION_TYPE_VAR_2
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
     BT_LAST
   };
@@ -1096,8 +1096,8 @@ gfc_init_builtin_functions (void)
 					builtin_types[(int) ARG1],     	\
 					builtin_types[(int) ARG2],     	\
 					NULL_TREE);
-#define DEF_FUNCTION_TYPE_VAR_7(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				ARG6, ARG7)				\
+#define DEF_FUNCTION_TYPE_VAR_6(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6)	\
   builtin_types[(int) ENUM]						\
     = build_varargs_function_type_list (builtin_types[(int) RETURN],   	\
 					builtin_types[(int) ARG1],     	\
@@ -1106,10 +1106,9 @@ gfc_init_builtin_functions (void)
 					builtin_types[(int) ARG4],	\
 					builtin_types[(int) ARG5],	\
 					builtin_types[(int) ARG6],	\
-					builtin_types[(int) ARG7],	\
 					NULL_TREE);
-#define DEF_FUNCTION_TYPE_VAR_11(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11)	\
+#define DEF_FUNCTION_TYPE_VAR_7(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				ARG6, ARG7)				\
   builtin_types[(int) ENUM]						\
     = build_varargs_function_type_list (builtin_types[(int) RETURN],   	\
 					builtin_types[(int) ARG1],     	\
@@ -1119,10 +1118,6 @@ gfc_init_builtin_functions (void)
 					builtin_types[(int) ARG5],	\
 					builtin_types[(int) ARG6],	\
 					builtin_types[(int) ARG7],	\
-					builtin_types[(int) ARG8],	\
-					builtin_types[(int) ARG9],	\
-					builtin_types[(int) ARG10],	\
-					builtin_types[(int) ARG11],	\
 					NULL_TREE);
 #define DEF_POINTER_TYPE(ENUM, TYPE)			\
   builtin_types[(int) ENUM]				\
@@ -1140,8 +1135,8 @@ gfc_init_builtin_functions (void)
 #undef DEF_FUNCTION_TYPE_8
 #undef DEF_FUNCTION_TYPE_VAR_0
 #undef DEF_FUNCTION_TYPE_VAR_2
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
   builtin_types[(int) BT_LAST] = NULL_TREE;
 
diff --git a/gcc/fortran/types.def b/gcc/fortran/types.def
index 62cac49..c460b59 100644
--- a/gcc/fortran/types.def
+++ b/gcc/fortran/types.def
@@ -219,7 +219,6 @@ DEF_FUNCTION_TYPE_VAR_7 (BT_FN_VOID_INT_SIZE_PTR_PTR_PTR_INT_INT_VAR,
 			 BT_VOID, BT_INT, BT_SIZE, BT_PTR, BT_PTR,
 			 BT_PTR, BT_INT, BT_INT)
 
-DEF_FUNCTION_TYPE_VAR_11 (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_INT_INT_INT_INT_INT_VAR,
+DEF_FUNCTION_TYPE_VAR_6 (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_VAR,
 			  BT_VOID, BT_INT, BT_PTR_FN_VOID_PTR, BT_SIZE,
-			  BT_PTR, BT_PTR, BT_PTR, BT_INT, BT_INT, BT_INT,
-			  BT_INT, BT_INT)
+			  BT_PTR, BT_PTR, BT_PTR)
diff --git a/gcc/lto/ChangeLog b/gcc/lto/ChangeLog
index 8d3c83f..265f5f8 100644
--- a/gcc/lto/ChangeLog
+++ b/gcc/lto/ChangeLog
@@ -1,3 +1,8 @@
+2015-09-28  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* lto-lang.c (DEF_FUNCTION_TYPE_VAR_6): New.
+	(DEF_FUNCTION_TYPE_VAR_11): Delete.
+
 2015-08-31  Richard Biener  <rguenther@suse.de>
 
 	* lto.c (compare_tree_sccs_1): Compare DECL_ABSTRACT_ORIGIN.
diff --git a/gcc/lto/lto-lang.c b/gcc/lto/lto-lang.c
index 6d6a853..67ccf57 100644
--- a/gcc/lto/lto-lang.c
+++ b/gcc/lto/lto-lang.c
@@ -160,10 +160,10 @@ enum lto_builtin_type
 #define DEF_FUNCTION_TYPE_VAR_4(NAME, RETURN, ARG1, ARG2, ARG3, ARG4) NAME,
 #define DEF_FUNCTION_TYPE_VAR_5(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG6) \
 				NAME,
+#define DEF_FUNCTION_TYPE_VAR_6(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				 ARG6) NAME,
 #define DEF_FUNCTION_TYPE_VAR_7(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7) NAME,
-#define DEF_FUNCTION_TYPE_VAR_11(NAME, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11) NAME,
 #define DEF_POINTER_TYPE(NAME, TYPE) NAME,
 #include "builtin-types.def"
 #undef DEF_PRIMITIVE_TYPE
@@ -182,8 +182,8 @@ enum lto_builtin_type
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
   BT_LAST
 };
@@ -668,13 +668,12 @@ lto_define_builtins (tree va_list_ref_type_node ATTRIBUTE_UNUSED,
   def_fn_type (ENUM, RETURN, 1, 4, ARG1, ARG2, ARG3, ARG4);
 #define DEF_FUNCTION_TYPE_VAR_5(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5) \
   def_fn_type (ENUM, RETURN, 1, 5, ARG1, ARG2, ARG3, ARG4, ARG5);
+#define DEF_FUNCTION_TYPE_VAR_6(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
+				 ARG6)	\
+  def_fn_type (ENUM, RETURN, 1, 6, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6);
 #define DEF_FUNCTION_TYPE_VAR_7(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
 				ARG6, ARG7)				\
   def_fn_type (ENUM, RETURN, 1, 7, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6, ARG7);
-#define DEF_FUNCTION_TYPE_VAR_11(ENUM, RETURN, ARG1, ARG2, ARG3, ARG4, ARG5, \
-				 ARG6, ARG7, ARG8, ARG9, ARG10, ARG11)	\
-  def_fn_type (ENUM, RETURN, 1, 11, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6,	\
-	       ARG7, ARG8, ARG9, ARG10, ARG11);
 #define DEF_POINTER_TYPE(ENUM, TYPE) \
   builtin_types[(int) ENUM] = build_pointer_type (builtin_types[(int) TYPE]);
 
@@ -696,8 +695,8 @@ lto_define_builtins (tree va_list_ref_type_node ATTRIBUTE_UNUSED,
 #undef DEF_FUNCTION_TYPE_VAR_3
 #undef DEF_FUNCTION_TYPE_VAR_4
 #undef DEF_FUNCTION_TYPE_VAR_5
+#undef DEF_FUNCTION_TYPE_VAR_6
 #undef DEF_FUNCTION_TYPE_VAR_7
-#undef DEF_FUNCTION_TYPE_VAR_11
 #undef DEF_POINTER_TYPE
   builtin_types[(int) BT_LAST] = NULL_TREE;
 
diff --git a/gcc/omp-builtins.def b/gcc/omp-builtins.def
index 50f1321..d09bdb6 100644
--- a/gcc/omp-builtins.def
+++ b/gcc/omp-builtins.def
@@ -38,8 +38,8 @@ DEF_GOACC_BUILTIN (BUILT_IN_GOACC_DATA_END, "GOACC_data_end",
 DEF_GOACC_BUILTIN (BUILT_IN_GOACC_ENTER_EXIT_DATA, "GOACC_enter_exit_data",
 		   BT_FN_VOID_INT_SIZE_PTR_PTR_PTR_INT_INT_VAR,
 		   ATTR_NOTHROW_LIST)
-DEF_GOACC_BUILTIN (BUILT_IN_GOACC_PARALLEL, "GOACC_parallel",
-		   BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_INT_INT_INT_INT_INT_VAR,
+DEF_GOACC_BUILTIN (BUILT_IN_GOACC_PARALLEL, "GOACC_parallel_keyed",
+		   BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_VAR,
 		   ATTR_NOTHROW_LIST)
 DEF_GOACC_BUILTIN (BUILT_IN_GOACC_UPDATE, "GOACC_update",
 		   BT_FN_VOID_INT_SIZE_PTR_PTR_PTR_INT_INT_VAR,
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index cb00758..8bcad08 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -82,7 +82,6 @@ along with GCC; see the file COPYING3.  If not see
 #include "lto-section-names.h"
 #include "gomp-constants.h"
 
-
 /* Lowering of OMP parallel and workshare constructs proceeds in two
    phases.  The first phase scans the function looking for OMP statements
    and then for variables that must be replaced to satisfy data sharing
@@ -8869,6 +8868,110 @@ expand_omp_atomic (struct omp_region *region)
 }
 
 
+/* Encode an oacc launc argument.  This matches the GOMP_LAUNCH_PACK
+   macro on gomp-constants.h.  We do not check for overflow.  */
+
+static tree
+oacc_launch_pack (unsigned code, tree device, unsigned op)
+{
+  tree res;
+  
+  res = build_int_cst (unsigned_type_node, GOMP_LAUNCH_PACK (code, 0, op));
+  if (device)
+    {
+      device = fold_build2 (LSHIFT_EXPR, unsigned_type_node,
+			    device, build_int_cst (unsigned_type_node,
+						   GOMP_LAUNCH_DEVICE_SHIFT));
+      res = fold_build2 (BIT_IOR_EXPR, unsigned_type_node, res, device);
+    }
+  return res;
+}
+
+/* Look for compute grid dimension clauses and convert to an attribute
+   attached to FN.  This permits the target-side code to (a) massage
+   the dimensions, (b) emit that data and (c) optimize.  Non-constant
+   dimensions are pushed onto ARGS.
+
+   The attribute value is a TREE_LIST.  A set of dimensions is
+   represented as a list of INTEGER_CST.  Those that are runtime
+   expres are represented as an INTEGER_CST of zero.
+
+   TOOO. Normally the attribute will just contain a single such list.  If
+   however it contains a list of lists, this will represent the use of
+   device_type.  Each member of the outer list is an assoc list of
+   dimensions, keyed by the device type.  The first entry will be the
+   default.  Well, that's the plan.  */
+
+#define OACC_FN_ATTRIB "oacc function"
+
+/* Replace any existing oacc fn attribute with updated dimensions.  */
+
+void
+replace_oacc_fn_attrib (tree fn, tree dims)
+{
+  tree ident = get_identifier (OACC_FN_ATTRIB);
+  tree attribs = DECL_ATTRIBUTES (fn);
+
+  /* If we happen to be present as the first attrib, drop it.  */
+  if (attribs && TREE_PURPOSE (attribs) == ident)
+    attribs = TREE_CHAIN (attribs);
+  DECL_ATTRIBUTES (fn) = tree_cons (ident, dims, attribs);
+}
+
+/* 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.  */
+
+static void
+set_oacc_fn_attrib (tree fn, tree clauses, vec<tree> *args)
+{
+  /* Must match GOMP_DIM ordering.  */
+  static const omp_clause_code ids[]
+    = { OMP_CLAUSE_NUM_GANGS, OMP_CLAUSE_NUM_WORKERS,
+	OMP_CLAUSE_VECTOR_LENGTH };
+  unsigned ix;
+  tree dims[GOMP_DIM_MAX];
+  tree attr = NULL_TREE;
+  unsigned non_const = 0;
+
+  for (ix = GOMP_DIM_MAX; ix--;)
+    {
+      tree clause = find_omp_clause (clauses, ids[ix]);
+      tree dim = NULL_TREE;
+
+      if (clause)
+	dim = OMP_CLAUSE_EXPR (clause, ids[ix]);
+      dims[ix] = dim;
+      if (dim && TREE_CODE (dim) != INTEGER_CST)
+	{
+	  dim = integer_zero_node;
+	  non_const |= GOMP_DIM_MASK (ix);
+	}
+      attr = tree_cons (NULL_TREE, dim, attr);
+    }
+
+  replace_oacc_fn_attrib (fn, attr);
+
+  if (non_const)
+    {
+      /* Push a dynamic argument set.  */
+      args->safe_push (oacc_launch_pack (GOMP_LAUNCH_DIM,
+					 NULL_TREE, non_const));
+      for (unsigned ix = 0; ix != GOMP_DIM_MAX; ix++)
+	if (non_const & GOMP_DIM_MASK (ix))
+	  args->safe_push (dims[ix]);
+    }
+}
+
+/* Retrieve the oacc function attrib and return it.  Non-oacc
+   functions will return NULL.  */
+
+tree
+get_oacc_fn_attrib (tree fn)
+{
+  return lookup_attribute (OACC_FN_ATTRIB, DECL_ATTRIBUTES (fn));
+}
+
 /* Expand the GIMPLE_OMP_TARGET starting at REGION.  */
 
 static void
@@ -8889,10 +8992,10 @@ expand_omp_target (struct omp_region *region)
   offloaded = is_gimple_omp_offloaded (entry_stmt);
   switch (gimple_omp_target_kind (entry_stmt))
     {
-    case GF_OMP_TARGET_KIND_REGION:
-    case GF_OMP_TARGET_KIND_UPDATE:
     case GF_OMP_TARGET_KIND_OACC_PARALLEL:
     case GF_OMP_TARGET_KIND_OACC_KERNELS:
+    case GF_OMP_TARGET_KIND_REGION:
+    case GF_OMP_TARGET_KIND_UPDATE:
     case GF_OMP_TARGET_KIND_OACC_UPDATE:
     case GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA:
       data_region = false;
@@ -9224,6 +9327,7 @@ expand_omp_target (struct omp_region *region)
     }
 
   gimple *g;
+  bool tagging = false;
   /* The maximum number used by any start_ix, without varargs.  */
   auto_vec<tree, 11> args;
   args.quick_push (device);
@@ -9259,88 +9363,87 @@ expand_omp_target (struct omp_region *region)
       break;
     case BUILT_IN_GOACC_PARALLEL:
       {
-	tree t_num_gangs, t_num_workers, t_vector_length;
-
-	/* Default values for num_gangs, num_workers, and vector_length.  */
-	t_num_gangs = t_num_workers = t_vector_length
-	  = fold_convert_loc (gimple_location (entry_stmt),
-			      integer_type_node, integer_one_node);
-	/* ..., but if present, use the value specified by the respective
-	   clause, making sure that are of the correct type.  */
-	c = find_omp_clause (clauses, OMP_CLAUSE_NUM_GANGS);
-	if (c)
-	  t_num_gangs = fold_convert_loc (OMP_CLAUSE_LOCATION (c),
-					  integer_type_node,
-					  OMP_CLAUSE_NUM_GANGS_EXPR (c));
-	c = find_omp_clause (clauses, OMP_CLAUSE_NUM_WORKERS);
-	if (c)
-	  t_num_workers = fold_convert_loc (OMP_CLAUSE_LOCATION (c),
-					    integer_type_node,
-					    OMP_CLAUSE_NUM_WORKERS_EXPR (c));
-	c = find_omp_clause (clauses, OMP_CLAUSE_VECTOR_LENGTH);
-	if (c)
-	  t_vector_length = fold_convert_loc (OMP_CLAUSE_LOCATION (c),
-					      integer_type_node,
-					      OMP_CLAUSE_VECTOR_LENGTH_EXPR (c));
-	args.quick_push (t_num_gangs);
-	args.quick_push (t_num_workers);
-	args.quick_push (t_vector_length);
+	set_oacc_fn_attrib (child_fn, clauses, &args);
+	tagging = true;
       }
       /* FALLTHRU */
     case BUILT_IN_GOACC_ENTER_EXIT_DATA:
     case BUILT_IN_GOACC_UPDATE:
       {
-	tree t_async;
-	int t_wait_idx;
-
-	/* Default values for t_async.  */
-	t_async = fold_convert_loc (gimple_location (entry_stmt),
-				    integer_type_node,
-				    build_int_cst (integer_type_node,
-						   GOMP_ASYNC_SYNC));
-	/* ..., but if present, use the value specified by the respective
+	tree t_async = NULL_TREE;
+
+	/* If present, use the value specified by the respective
 	   clause, making sure that is of the correct type.  */
 	c = find_omp_clause (clauses, OMP_CLAUSE_ASYNC);
 	if (c)
 	  t_async = fold_convert_loc (OMP_CLAUSE_LOCATION (c),
 				      integer_type_node,
 				      OMP_CLAUSE_ASYNC_EXPR (c));
-
-	args.quick_push (t_async);
-	/* Save the index, and... */
-	t_wait_idx = args.length ();
-	/* ... push a default value.  */
-	args.quick_push (fold_convert_loc (gimple_location (entry_stmt),
-					   integer_type_node,
-					   integer_zero_node));
-	c = find_omp_clause (clauses, OMP_CLAUSE_WAIT);
-	if (c)
+	else if (!tagging)
+	  /* Default values for t_async.  */
+	  t_async = fold_convert_loc (gimple_location (entry_stmt),
+				      integer_type_node,
+				      build_int_cst (integer_type_node,
+						     GOMP_ASYNC_SYNC));
+	if (tagging && t_async)
 	  {
-	    int n = 0;
+	    unsigned HOST_WIDE_INT i_async;
 
-	    for (; c; c = OMP_CLAUSE_CHAIN (c))
+	    if (TREE_CODE (t_async) == INTEGER_CST)
 	      {
-		if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_WAIT)
-		  {
-		    args.safe_push (fold_convert_loc (OMP_CLAUSE_LOCATION (c),
-						      integer_type_node,
-						      OMP_CLAUSE_WAIT_EXPR (c)));
-		    n++;
-		  }
+		/* See if we can pack the async arg in to the tag's
+		   operand.  */
+		i_async = TREE_INT_CST_LOW (t_async);
+
+		if (i_async < GOMP_LAUNCH_OP_MAX)
+		  t_async = NULL_TREE;
 	      }
+	    if (t_async)
+	      i_async = GOMP_LAUNCH_OP_MAX;
+	    args.safe_push (oacc_launch_pack
+			    (GOMP_LAUNCH_ASYNC, NULL_TREE, i_async));
+	  }
+	if (t_async)
+	  args.safe_push (t_async);
 
-	    /* Now that we know the number, replace the default value.  */
-	    args.ordered_remove (t_wait_idx);
-	    args.quick_insert (t_wait_idx,
-			       fold_convert_loc (gimple_location (entry_stmt),
-						 integer_type_node,
-						 build_int_cst (integer_type_node, n)));
+	/* Save the argument index, and ... */
+	unsigned t_wait_idx = args.length ();
+	unsigned num_waits = 0;
+	c = find_omp_clause (clauses, OMP_CLAUSE_WAIT);
+	if (!tagging || c)
+	  /* ... push a placeholder.  */
+	  args.safe_push (integer_zero_node);
+
+	for (; c; c = OMP_CLAUSE_CHAIN (c))
+	  if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_WAIT)
+	    {
+	      args.safe_push (fold_convert_loc (OMP_CLAUSE_LOCATION (c),
+						integer_type_node,
+						OMP_CLAUSE_WAIT_EXPR (c)));
+	      num_waits++;
+	    }
+
+	if (!tagging || num_waits)
+	  {
+	    tree len;
+
+	    /* Now that we know the number, update the placeholder.  */
+	    if (tagging)
+	      len = oacc_launch_pack (GOMP_LAUNCH_WAIT, NULL_TREE, num_waits);
+	    else
+	      len = build_int_cst (integer_type_node, num_waits);
+	    len = fold_convert_loc (gimple_location (entry_stmt),
+				    unsigned_type_node, len);
+	    args[t_wait_idx] = len;
 	  }
       }
       break;
     default:
       gcc_unreachable ();
     }
+  if (tagging)
+    /*  Push terminal marker - zero.  */
+    args.safe_push (oacc_launch_pack (0, NULL_TREE, 0));
 
   g = gimple_build_call_vec (builtin_decl_explicit (start_ix), args);
   gimple_set_location (g, gimple_location (entry_stmt));
diff --git a/gcc/omp-low.h b/gcc/omp-low.h
index 44e35a3..4730815 100644
--- a/gcc/omp-low.h
+++ b/gcc/omp-low.h
@@ -29,6 +29,7 @@ extern tree omp_reduction_init_op (location_t, enum tree_code, tree);
 extern tree omp_reduction_init (tree, tree);
 extern bool make_gimple_omp_edges (basic_block, struct omp_region **, int *);
 extern void omp_finish_file (void);
+extern tree get_oacc_fn_attrib (tree);
 
 extern GTY(()) vec<tree, va_gc> *offload_funcs;
 extern GTY(()) vec<tree, va_gc> *offload_vars;
diff --git a/gcc/tree.h b/gcc/tree.h
index e500151..35c72b6 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -1,3 +1,4 @@
+
 /* Definitions for the ubiquitous 'tree' type for GNU compilers.
    Copyright (C) 1989-2015 Free Software Foundation, Inc.
 
@@ -1369,6 +1370,8 @@ extern void protected_set_expr_location (tree, location_t);
   OMP_CLAUSE_OPERAND (OMP_CLAUSE_SUBCODE_CHECK (NODE, OMP_CLAUSE_SCHEDULE), 0)
 
 /* OpenACC clause expressions  */
+#define OMP_CLAUSE_EXPR(NODE, CLAUSE) \
+  OMP_CLAUSE_OPERAND (OMP_CLAUSE_SUBCODE_CHECK (NODE, CLAUSE), 0)
 #define OMP_CLAUSE_GANG_EXPR(NODE) \
   OMP_CLAUSE_OPERAND ( \
     OMP_CLAUSE_SUBCODE_CHECK (NODE, OMP_CLAUSE_GANG), 0)