Merge of HSA

2016-01-19  Martin Jambor  <mjambor@suse.cz>
	    Martin Liska  <mliska@suse.cz>
	    Michael Matz <matz@suse.de>

libgomp/
	* plugin/Makefrag.am: Add HSA plugin requirements.
	* plugin/configfrag.ac (HSA_RUNTIME_INCLUDE): New variable.
	(HSA_RUNTIME_LIB): Likewise.
	(HSA_RUNTIME_CPPFLAGS): Likewise.
	(HSA_RUNTIME_INCLUDE): New substitution.
	(HSA_RUNTIME_LIB): Likewise.
	(HSA_RUNTIME_LDFLAGS): Likewise.
	(hsa-runtime): New configure option.
	(hsa-runtime-include): Likewise.
	(hsa-runtime-lib): Likewise.
	(PLUGIN_HSA): New substitution variable.
	Fill HSA_RUNTIME_INCLUDE and HSA_RUNTIME_LIB according to the new
	configure options.
	(PLUGIN_HSA_CPPFLAGS): Likewise.
	(PLUGIN_HSA_LDFLAGS): Likewise.
	(PLUGIN_HSA_LIBS): Likewise.
	Check that we have access to HSA run-time.
	* libgomp-plugin.h (offload_target_type): New element
	OFFLOAD_TARGET_TYPE_HSA.
	* libgomp.h (gomp_target_task): New fields firstprivate_copies and
	args.
	(bool gomp_create_target_task): Updated.
	(gomp_device_descr): Extra parameter of run_func and async_run_func,
	new field can_run_func.
	* libgomp_g.h (GOMP_target_ext): Update prototype.
	* oacc-host.c (host_run): Added a new parameter args.
	* target.c (calculate_firstprivate_requirements): New function.
	(copy_firstprivate_data): Likewise.
	(gomp_target_fallback_firstprivate): Use them.
	(gomp_target_unshare_firstprivate): New function.
	(gomp_get_target_fn_addr): Allow returning NULL for shared memory
	devices.
	(GOMP_target): Do host fallback for all shared memory devices.  Do not
	pass any args to plugins.
	(GOMP_target_ext): Introduce device-specific argument parameter args.
	Allow host fallback if device shares memory.  Do not remap data if
	device has shared memory.
	(gomp_target_task_fn): Likewise.  Also treat shared memory devices
	like host fallback for mappings.
	(GOMP_target_data): Treat shared memory devices like host fallback.
	(GOMP_target_data_ext): Likewise.
	(GOMP_target_update): Likewise.
	(GOMP_target_update_ext): Likewise.  Also pass NULL as args to
	gomp_create_target_task.
	(GOMP_target_enter_exit_data): Likewise.
	(omp_target_alloc): Treat shared memory devices like host fallback.
	(omp_target_free): Likewise.
	(omp_target_is_present): Likewise.
	(omp_target_memcpy): Likewise.
	(omp_target_memcpy_rect): Likewise.
	(omp_target_associate_ptr): Likewise.
	(gomp_load_plugin_for_device): Also load can_run.
	* task.c (GOMP_PLUGIN_target_task_completion): Free
	firstprivate_copies.
	(gomp_create_target_task): Accept new argument args and store it to
	ttask.
	* plugin/plugin-hsa.c: New file.

gcc/
	* Makefile.in (OBJS): Add new source files.
	(GTFILES): Add hsa.c.
	* common.opt (disable_hsa): New variable.
	(-Whsa): New warning.
	* config.in (ENABLE_HSA): New.
	* configure.ac: Treat hsa differently from other accelerators.
	(OFFLOAD_TARGETS): Define ENABLE_OFFLOADING according to
	$enable_offloading.
	(ENABLE_HSA): Define ENABLE_HSA according to $enable_hsa.
	* doc/install.texi (Configuration): Document --with-hsa-runtime,
	--with-hsa-runtime-include, --with-hsa-runtime-lib and
	--with-hsa-kmt-lib.
	* doc/invoke.texi (-Whsa): Document.
	(hsa-gen-debug-stores): Likewise.
	* lto-wrapper.c (compile_images_for_offload_targets): Do not attempt
	to invoke offload compiler for hsa acclerator.
	* opts.c (common_handle_option): Determine whether HSA offloading
	should be performed.
	* params.def (PARAM_HSA_GEN_DEBUG_STORES): New parameter.
	* builtin-types.def (BT_FN_VOID_UINT_PTR_INT_PTR): New.
	(BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_INT_INT): Removed.
	(BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_PTR): New.
	* gimple-low.c (lower_stmt): Also handle GIMPLE_OMP_GRID_BODY.
	* gimple-pretty-print.c (dump_gimple_omp_for): Also handle
	GF_OMP_FOR_KIND_GRID_LOOP.
	(dump_gimple_omp_block): Also handle GIMPLE_OMP_GRID_BODY.
	(pp_gimple_stmt_1): Likewise.
	* gimple-walk.c (walk_gimple_stmt): Likewise.
	* gimple.c (gimple_build_omp_grid_body): New function.
	(gimple_copy): Also handle GIMPLE_OMP_GRID_BODY.
	* gimple.def (GIMPLE_OMP_GRID_BODY): New.
	* gimple.h (enum gf_mask): Added GF_OMP_PARALLEL_GRID_PHONY,
	GF_OMP_FOR_KIND_GRID_LOOP, GF_OMP_FOR_GRID_PHONY and
	GF_OMP_TEAMS_GRID_PHONY.
	(gimple_statement_omp_single_layout): Updated comments.
	(gimple_build_omp_grid_body): New function.
	(gimple_has_substatements): Also handle GIMPLE_OMP_GRID_BODY.
	(gimple_omp_for_grid_phony): New function.
	(gimple_omp_for_set_grid_phony): Likewise.
	(gimple_omp_parallel_grid_phony): Likewise.
	(gimple_omp_parallel_set_grid_phony): Likewise.
	(gimple_omp_teams_grid_phony): Likewise.
	(gimple_omp_teams_set_grid_phony): Likewise.
	(gimple_return_set_retbnd): Also handle GIMPLE_OMP_GRID_BODY.
	* omp-builtins.def (BUILT_IN_GOMP_OFFLOAD_REGISTER): New.
	(BUILT_IN_GOMP_OFFLOAD_UNREGISTER): Likewise.
	(BUILT_IN_GOMP_TARGET): Updated type.
	* omp-low.c: Include symbol-summary.h, hsa.h and params.h.
	(adjust_for_condition): New function.
	(get_omp_for_step_from_incr): Likewise.
	(extract_omp_for_data): Moved parts to adjust_for_condition and
	get_omp_for_step_from_incr.
	(build_outer_var_ref): Handle GIMPLE_OMP_GRID_BODY.
	(fixup_child_record_type): Bail out if receiver_decl is NULL.
	(scan_sharing_clauses): Handle OMP_CLAUSE__GRIDDIM_.
	(scan_omp_parallel): Do not create child functions for phony
	constructs.
	(check_omp_nesting_restrictions): Handle GIMPLE_OMP_GRID_BODY.
	(scan_omp_1_op): Checking assert we are not remapping to
	ERROR_MARK.  Also also handle GIMPLE_OMP_GRID_BODY.
	(parallel_needs_hsa_kernel_p): New function.
	(expand_parallel_call): Register apprpriate parallel child
	functions as HSA kernels.
	(grid_launch_attributes_trees): New type.
	(grid_attr_trees): New variable.
	(grid_create_kernel_launch_attr_types): New function.
	(grid_insert_store_range_dim): Likewise.
	(grid_get_kernel_launch_attributes): Likewise.
	(get_target_argument_identifier_1): Likewise.
	(get_target_argument_identifier): Likewise.
	(get_target_argument_value): Likewise.
	(push_target_argument_according_to_value): Likewise.
	(get_target_arguments): Likewise.
	(expand_omp_target): Call get_target_arguments instead of looking
	up for teams and thread limit.
	(grid_expand_omp_for_loop): New function.
	(grid_arg_decl_map): New type.
	(grid_remap_kernel_arg_accesses): New function.
	(grid_expand_target_kernel_body): New function.
	(expand_omp): Call it.
	(lower_omp_for): Do not emit phony constructs.
	(lower_omp_taskreg): Do not emit phony constructs but create for them
	a temporary variable receiver_decl.
	(lower_omp_taskreg): Do not emit phony constructs.
	(lower_omp_teams): Likewise.
	(lower_omp_grid_body): New function.
	(lower_omp_1): Call it.
	(grid_reg_assignment_to_local_var_p): New function.
	(grid_seq_only_contains_local_assignments): Likewise.
	(grid_find_single_omp_among_assignments_1): Likewise.
	(grid_find_single_omp_among_assignments): Likewise.
	(grid_find_ungridifiable_statement): Likewise.
	(grid_target_follows_gridifiable_pattern): Likewise.
	(grid_remap_prebody_decls): Likewise.
	(grid_copy_leading_local_assignments): Likewise.
	(grid_process_kernel_body_copy): Likewise.
	(grid_attempt_target_gridification): Likewise.
	(grid_gridify_all_targets_stmt): Likewise.
	(grid_gridify_all_targets): Likewise.
	(execute_lower_omp): Call grid_gridify_all_targets.
	(make_gimple_omp_edges): Handle GIMPLE_OMP_GRID_BODY.
	* tree-core.h (omp_clause_code): Added OMP_CLAUSE__GRIDDIM_.
	(tree_omp_clause): Added union field dimension.
	* tree-pretty-print.c (dump_omp_clause): Handle OMP_CLAUSE__GRIDDIM_.
	* tree.c (omp_clause_num_ops): Added number of arguments of
	OMP_CLAUSE__GRIDDIM_.
	(omp_clause_code_name): Added name of OMP_CLAUSE__GRIDDIM_.
	(walk_tree_1): Handle OMP_CLAUSE__GRIDDIM_.
	* tree.h (OMP_CLAUSE_GRIDDIM_DIMENSION): New.
	(OMP_CLAUSE_SET_GRIDDIM_DIMENSION): Likewise.
	(OMP_CLAUSE_GRIDDIM_SIZE): Likewise.
	(OMP_CLAUSE_GRIDDIM_GROUP): Likewise.
	* passes.def: Schedule pass_ipa_hsa and pass_gen_hsail.
	* tree-pass.h (make_pass_gen_hsail): Declare.
	(make_pass_ipa_hsa): Likewise.
	* ipa-hsa.c: New file.
	* lto-section-in.c (lto_section_name): Add hsa section name.
	* lto-streamer.h (lto_section_type): Add hsa section.
	* timevar.def (TV_IPA_HSA): New.
        * hsa-brig-format.h: New file.
	* hsa-brig.c: New file.
	* hsa-dump.c: Likewise.
	* hsa-gen.c: Likewise.
	* hsa.c: Likewise.
	* hsa.h: Likewise.
	* toplev.c (compile_file): Call hsa_output_brig.
	* hsa-regalloc.c: New file.

gcc/fortran/
	* types.def (BT_FN_VOID_UINT_PTR_INT_PTR): New.
	(BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_INT_INT): Removed.
	(BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_PTR): New.

gcc/lto/
	* lto-partition.c: Include "hsa.h"
	(add_symbol_to_partition_1): Put hsa implementations into the
	same partition as host implementations.

liboffloadmic/
	* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_async_run): New
	unused parameter.
	(GOMP_OFFLOAD_run): Likewise.

include/
	* gomp-constants.h (GOMP_DEVICE_HSA): New macro.
	(GOMP_VERSION_HSA): Likewise.
	(GOMP_TARGET_ARG_DEVICE_MASK): Likewise.
	(GOMP_TARGET_ARG_DEVICE_ALL): Likewise.
	(GOMP_TARGET_ARG_SUBSEQUENT_PARAM): Likewise.
	(GOMP_TARGET_ARG_ID_MASK): Likewise.
	(GOMP_TARGET_ARG_NUM_TEAMS): Likewise.
	(GOMP_TARGET_ARG_THREAD_LIMIT): Likewise.
	(GOMP_TARGET_ARG_VALUE_SHIFT): Likewise.
	(GOMP_TARGET_ARG_HSA_KERNEL_ATTRIBUTES): Likewise.

From-SVN: r232549

1 files changed, 63 insertions, 2 deletions

diff --git a/gcc/gimple.h b/gcc/gimple.h
index b30a9b8..6d15dab 100644
--- a/gcc/gimple.h
+++ b/gcc/gimple.h
@@ -146,6 +146,7 @@ enum gf_mask {
     GF_CALL_CTRL_ALTERING       = 1 << 7,
     GF_CALL_WITH_BOUNDS 	= 1 << 8,
     GF_OMP_PARALLEL_COMBINED	= 1 << 0,
+    GF_OMP_PARALLEL_GRID_PHONY = 1 << 1,
     GF_OMP_TASK_TASKLOOP	= 1 << 0,
     GF_OMP_FOR_KIND_MASK	= (1 << 4) - 1,
     GF_OMP_FOR_KIND_FOR		= 0,
@@ -153,12 +154,14 @@ enum gf_mask {
     GF_OMP_FOR_KIND_TASKLOOP	= 2,
     GF_OMP_FOR_KIND_CILKFOR     = 3,
     GF_OMP_FOR_KIND_OACC_LOOP	= 4,
+    GF_OMP_FOR_KIND_GRID_LOOP = 5,
     /* Flag for SIMD variants of OMP_FOR kinds.  */
     GF_OMP_FOR_SIMD		= 1 << 3,
     GF_OMP_FOR_KIND_SIMD	= GF_OMP_FOR_SIMD | 0,
     GF_OMP_FOR_KIND_CILKSIMD	= GF_OMP_FOR_SIMD | 1,
     GF_OMP_FOR_COMBINED		= 1 << 4,
     GF_OMP_FOR_COMBINED_INTO	= 1 << 5,
+    GF_OMP_FOR_GRID_PHONY	= 1 << 6,
     GF_OMP_TARGET_KIND_MASK	= (1 << 4) - 1,
     GF_OMP_TARGET_KIND_REGION	= 0,
     GF_OMP_TARGET_KIND_DATA	= 1,
@@ -172,6 +175,7 @@ enum gf_mask {
     GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA = 9,
     GF_OMP_TARGET_KIND_OACC_DECLARE = 10,
     GF_OMP_TARGET_KIND_OACC_HOST_DATA = 11,
+    GF_OMP_TEAMS_GRID_PHONY	= 1 << 0,
 
     /* True on an GIMPLE_OMP_RETURN statement if the return does not require
        a thread synchronization via some sort of barrier.  The exact barrier
@@ -733,7 +737,7 @@ struct GTY((tag("GSS_OMP_SINGLE_LAYOUT")))
 {
   /* [ WORD 1-7 ] : base class */
 
-  /* [ WORD 7 ]  */
+  /* [ WORD 8 ]  */
   tree clauses;
 };
 
@@ -1454,6 +1458,7 @@ gomp_task *gimple_build_omp_task (gimple_seq, tree, tree, tree, tree,
 				       tree, tree);
 gimple *gimple_build_omp_section (gimple_seq);
 gimple *gimple_build_omp_master (gimple_seq);
+gimple *gimple_build_omp_grid_body (gimple_seq);
 gimple *gimple_build_omp_taskgroup (gimple_seq);
 gomp_continue *gimple_build_omp_continue (tree, tree);
 gomp_ordered *gimple_build_omp_ordered (gimple_seq, tree);
@@ -1714,6 +1719,7 @@ gimple_has_substatements (gimple *g)
     case GIMPLE_OMP_CRITICAL:
     case GIMPLE_WITH_CLEANUP_EXPR:
     case GIMPLE_TRANSACTION:
+    case GIMPLE_OMP_GRID_BODY:
       return true;
 
     default:
@@ -5079,6 +5085,24 @@ gimple_omp_for_set_pre_body (gimple *gs, gimple_seq pre_body)
   omp_for_stmt->pre_body = pre_body;
 }
 
+/* Return the kernel_phony of OMP_FOR statement.  */
+
+static inline bool
+gimple_omp_for_grid_phony (const gomp_for *omp_for)
+{
+  return (gimple_omp_subcode (omp_for) & GF_OMP_FOR_GRID_PHONY) != 0;
+}
+
+/* Set kernel_phony flag of OMP_FOR to VALUE.  */
+
+static inline void
+gimple_omp_for_set_grid_phony (gomp_for *omp_for, bool value)
+{
+  if (value)
+    omp_for->subcode |= GF_OMP_FOR_GRID_PHONY;
+  else
+    omp_for->subcode &= ~GF_OMP_FOR_GRID_PHONY;
+}
 
 /* Return the clauses associated with OMP_PARALLEL GS.  */
 
@@ -5165,6 +5189,24 @@ gimple_omp_parallel_set_data_arg (gomp_parallel *omp_parallel_stmt,
   omp_parallel_stmt->data_arg = data_arg;
 }
 
+/* Return the kernel_phony flag of OMP_PARALLEL_STMT.  */
+
+static inline bool
+gimple_omp_parallel_grid_phony (const gomp_parallel *stmt)
+{
+  return (gimple_omp_subcode (stmt) & GF_OMP_PARALLEL_GRID_PHONY) != 0;
+}
+
+/* Set kernel_phony flag of OMP_PARALLEL_STMT to VALUE.  */
+
+static inline void
+gimple_omp_parallel_set_grid_phony (gomp_parallel *stmt, bool value)
+{
+  if (value)
+    stmt->subcode |= GF_OMP_PARALLEL_GRID_PHONY;
+  else
+    stmt->subcode &= ~GF_OMP_PARALLEL_GRID_PHONY;
+}
 
 /* Return the clauses associated with OMP_TASK GS.  */
 
@@ -5638,6 +5680,24 @@ gimple_omp_teams_set_clauses (gomp_teams *omp_teams_stmt, tree clauses)
   omp_teams_stmt->clauses = clauses;
 }
 
+/* Return the kernel_phony flag of an OMP_TEAMS_STMT.  */
+
+static inline bool
+gimple_omp_teams_grid_phony (const gomp_teams *omp_teams_stmt)
+{
+  return (gimple_omp_subcode (omp_teams_stmt) & GF_OMP_TEAMS_GRID_PHONY) != 0;
+}
+
+/* Set kernel_phony flag of an OMP_TEAMS_STMT to VALUE.  */
+
+static inline void
+gimple_omp_teams_set_grid_phony (gomp_teams *omp_teams_stmt, bool value)
+{
+  if (value)
+    omp_teams_stmt->subcode |= GF_OMP_TEAMS_GRID_PHONY;
+  else
+    omp_teams_stmt->subcode &= ~GF_OMP_TEAMS_GRID_PHONY;
+}
 
 /* Return the clauses associated with OMP_SECTIONS GS.  */
 
@@ -6002,7 +6062,8 @@ gimple_return_set_retbnd (gimple *gs, tree retval)
     case GIMPLE_OMP_RETURN:			\
     case GIMPLE_OMP_ATOMIC_LOAD:		\
     case GIMPLE_OMP_ATOMIC_STORE:		\
-    case GIMPLE_OMP_CONTINUE
+    case GIMPLE_OMP_CONTINUE:			\
+    case GIMPLE_OMP_GRID_BODY
 
 static inline bool
 is_gimple_omp (const gimple *stmt)