re PR fortran/48636 (Enable more inlining with -O2 and higher)

2012-08-11  Martin Jambor  <mjambor@suse.cz>

	PR fortran/48636
	* ipa-inline.h (condition): New fields offset, agg_contents and by_ref.
	* ipa-inline-analysis.c (agg_position_info): New type.
	(add_condition): New parameter aggpos, also store agg_contents, by_ref
	and offset.
	(dump_condition): Also dump aggregate conditions.
	(evaluate_conditions_for_known_args): Also handle aggregate
	conditions.  New parameter known_aggs.
	(evaluate_properties_for_edge): Gather known aggregate contents.
	(inline_node_duplication_hook): Pass NULL known_aggs to
	evaluate_conditions_for_known_args.
	(unmodified_parm): Split into unmodified_parm and unmodified_parm_1.
	(unmodified_parm_or_parm_agg_item): New function.
	(set_cond_stmt_execution_predicate): Handle values passed in
	aggregates.
	(set_switch_stmt_execution_predicate): Likewise.
	(will_be_nonconstant_predicate): Likewise.
	(estimate_edge_devirt_benefit): Pass new parameter known_aggs to
	ipa_get_indirect_edge_target.
	(estimate_calls_size_and_time): New parameter known_aggs, pass it
	recrsively to itself and to estimate_edge_devirt_benefit.
	(estimate_node_size_and_time): New vector known_aggs, pass it o
	functions which need it.
	(remap_predicate): New parameter offset_map, use it to remap aggregate
	conditions.
	(remap_edge_summaries): New parameter offset_map, pass it recursively
	to itself and to remap_predicate.
	(inline_merge_summary): Also create and populate vector offset_map.
	(do_estimate_edge_time): New vector of known aggregate contents,
	passed to functions which need it.
	(inline_read_section): Stream new fields of condition.
	(inline_write_summary): Likewise.
	* ipa-cp.c (ipa_get_indirect_edge_target): Also examine the aggregate
	contents.  Let all local callers pass NULL for known_aggs.

	* testsuite/gfortran.dg/pr48636.f90: New test.

From-SVN: r190313

gcc/ChangeLog

+2012-08-11  Martin Jambor  <mjambor@suse.cz>
+
+	PR fortran/48636
+	* ipa-inline.h (condition): New fields offset, agg_contents and by_ref.
+	* ipa-inline-analysis.c (agg_position_info): New type.
+	(add_condition): New parameter aggpos, also store agg_contents, by_ref
+	and offset.
+	(dump_condition): Also dump aggregate conditions.
+	(evaluate_conditions_for_known_args): Also handle aggregate
+	conditions.  New parameter known_aggs.
+	(evaluate_properties_for_edge): Gather known aggregate contents.
+	(inline_node_duplication_hook): Pass NULL known_aggs to
+	evaluate_conditions_for_known_args.
+	(unmodified_parm): Split into unmodified_parm and unmodified_parm_1.
+	(unmodified_parm_or_parm_agg_item): New function.
+	(set_cond_stmt_execution_predicate): Handle values passed in
+	aggregates.
+	(set_switch_stmt_execution_predicate): Likewise.
+	(will_be_nonconstant_predicate): Likewise.
+	(estimate_edge_devirt_benefit): Pass new parameter known_aggs to
+	ipa_get_indirect_edge_target.
+	(estimate_calls_size_and_time): New parameter known_aggs, pass it
+	recrsively to itself and to estimate_edge_devirt_benefit.
+	(estimate_node_size_and_time): New vector known_aggs, pass it o
+	functions which need it.
+	(remap_predicate): New parameter offset_map, use it to remap aggregate
+	conditions.
+	(remap_edge_summaries): New parameter offset_map, pass it recursively
+	to itself and to remap_predicate.
+	(inline_merge_summary): Also create and populate vector offset_map.
+	(do_estimate_edge_time): New vector of known aggregate contents,
+	passed to functions which need it.
+	(inline_read_section): Stream new fields of condition.
+	(inline_write_summary): Likewise.
+	* ipa-cp.c (ipa_get_indirect_edge_target): Also examine the aggregate
+	contents.  Let all local callers pass NULL for known_aggs.
+
 2012-08-11  Jan Hubicka  <jh@suse.cz>
 
 	* lto-cgraph.c (output_cgraph): Rename to ...

gcc/ipa-cp.c

@@ -1084,7 +1084,8 @@ propagate_constants_accross_call (struct cgraph_edge *cs)
 tree
 ipa_get_indirect_edge_target (struct cgraph_edge *ie,
 			      VEC (tree, heap) *known_vals,
-			      VEC (tree, heap) *known_binfos)
+			      VEC (tree, heap) *known_binfos,
+			      VEC (ipa_agg_jump_function_p, heap) *known_aggs)
 {
   int param_index = ie->indirect_info->param_index;
   HOST_WIDE_INT token, anc_offset;
@@ -1096,8 +1097,26 @@ ipa_get_indirect_edge_target (struct cgraph_edge *ie,
 
   if (!ie->indirect_info->polymorphic)
     {
-      tree t = (VEC_length (tree, known_vals) > (unsigned int) param_index
-	        ? VEC_index (tree, known_vals, param_index) : NULL);
+      tree t;
+
+      if (ie->indirect_info->agg_contents)
+	{
+	  if (VEC_length (ipa_agg_jump_function_p, known_aggs)
+	      > (unsigned int) param_index)
+	    {
+	      struct ipa_agg_jump_function *agg;
+	      agg = VEC_index (ipa_agg_jump_function_p, known_aggs,
+			       param_index);
+	      t = ipa_find_agg_cst_for_param (agg, ie->indirect_info->offset,
+					      ie->indirect_info->by_ref);
+	    }
+	  else
+	    t = NULL;
+	}
+      else
+	t = (VEC_length (tree, known_vals) > (unsigned int) param_index
+	     ? VEC_index (tree, known_vals, param_index) : NULL);
+
       if (t &&
 	  TREE_CODE (t) == ADDR_EXPR
 	  && TREE_CODE (TREE_OPERAND (t, 0)) == FUNCTION_DECL)
@@ -1106,6 +1125,7 @@ ipa_get_indirect_edge_target (struct cgraph_edge *ie,
 	return NULL_TREE;
     }
 
+  gcc_assert (!ie->indirect_info->agg_contents);
   token = ie->indirect_info->otr_token;
   anc_offset = ie->indirect_info->offset;
   otr_type = ie->indirect_info->otr_type;
@@ -1156,7 +1176,8 @@ devirtualization_time_bonus (struct cgraph_node *node,
       struct inline_summary *isummary;
       tree target;
 
-      target = ipa_get_indirect_edge_target (ie, known_csts, known_binfos);
+      target = ipa_get_indirect_edge_target (ie, known_csts, known_binfos,
+					     NULL);
       if (!target)
 	continue;
 
@@ -1673,7 +1694,7 @@ ipcp_discover_new_direct_edges (struct cgraph_node *node,
       tree target;
 
       next_ie = ie->next_callee;
-      target = ipa_get_indirect_edge_target (ie, known_vals, NULL);
+      target = ipa_get_indirect_edge_target (ie, known_vals, NULL, NULL);
       if (target)
 	ipa_make_edge_direct_to_target (ie, target);
     }

gcc/ipa-inline.h

@@ -28,9 +28,18 @@ along with GCC; see the file COPYING3.  If not see
 
 typedef struct GTY(()) condition
   {
+    /* If agg_contents is set, this is the offset from which the used data was
+       loaded.  */
+    HOST_WIDE_INT offset;
     tree val;
     int operand_num;
-    enum tree_code code;
+    ENUM_BITFIELD(tree_code) code : 16;
+    /* Set if the used data were loaded from an aggregate parameter or from
+       data received by reference.  */
+    unsigned agg_contents : 1;
+    /* If agg_contents is set, this differentiates between loads from data
+       passed by reference and by value.  */
+    unsigned by_ref : 1;
   } condition;
 
 DEF_VEC_O (condition);

gcc/ipa-prop.h

@@ -494,8 +494,9 @@ bool ipa_propagate_indirect_call_infos (struct cgraph_edge *cs,
 
 /* Indirect edge and binfo processing.  */
 tree ipa_get_indirect_edge_target (struct cgraph_edge *ie,
-				   VEC (tree, heap) *known_csts,
-				   VEC (tree, heap) *known_binfs);
+				   VEC (tree, heap) *,
+				   VEC (tree, heap) *,
+				   VEC (ipa_agg_jump_function_p, heap) *);
 struct cgraph_edge *ipa_make_edge_direct_to_target (struct cgraph_edge *, tree);
 
 /* Functions related to both.  */

gcc/testsuite/ChangeLog

+2012-08-11  Martin Jambor  <mjambor@suse.cz>
+
+	PR fortran/48636
+	* gfortran.dg/pr48636.f90: New test.
+
 2012-08-10  Jakub Jelinek  <jakub@redhat.com>
 
 	* gcc.dg/torture/vector-shuffle1.c (f): Pass vectors indirectly

gcc/testsuite/gfortran.dg/pr48636.f90

+! { dg-do compile }
+! { dg-options "-O3 -fdump-ipa-inline" }
+
+module foo
+  implicit none
+contains
+  subroutine bar(a,x)
+    real, dimension(:,:), intent(in) :: a
+    real, intent(out) :: x
+    integer :: i,j
+
+    x = 0
+    do j=1,ubound(a,2)
+       do i=1,ubound(a,1)
+          x = x + a(i,j)**2
+       end do
+    end do
+  end subroutine bar
+end module foo
+
+program main
+  use foo
+  implicit none
+  real, dimension(2,3) :: a
+  real :: x
+  integer :: i
+
+  data a /1.0, 2.0, 3.0, -1.0, -2.0, -3.0/
+
+  do i=1,2000000
+     call bar(a,x)
+  end do
+  print *,x
+end program main
+
+! { dg-final { scan-ipa-dump "bar\[^\\n\]*inline copy in MAIN" "inline" } }
+! { dg-final { cleanup-ipa-dump "inline" } }