re PR middle-end/43864 (Same basic blocks should be merged)

2011-09-27  Tom de Vries  <tom@codesourcery.com>

	PR middle-end/43864
	* tree-ssa-tail-merge.c: New file.
	(struct same_succ_def): Define.
	(same_succ, const_same_succ): New typedef.
	(struct bb_cluster_def): Define.
	(bb_cluster, const_bb_cluster): New typedef.
	(struct aux_bb_info): Define.
	(BB_SIZE, BB_SAME_SUCC, BB_CLUSTER, BB_VOP_AT_EXIT): Define.
	(gvn_uses_equal): New function.
	(same_succ_print, same_succ_print_traverse, update_dep_bb)
	(stmt_update_dep_bb, local_def, same_succ_hash)
	(inverse_flags, same_succ_equal, same_succ_alloc, same_succ_delete)
	(same_succ_reset): New function.
	(same_succ_htab, same_succ_edge_flags)
	(deleted_bbs, deleted_bb_preds): New var.
	(debug_same_succ): New function.
	(worklist): New var.
	(print_worklist, add_to_worklist, find_same_succ_bb, find_same_succ)
	(init_worklist, delete_worklist, delete_basic_block_same_succ)
	(same_succ_flush_bbs, purge_bbs, update_worklist): New function.
	(print_cluster, debug_cluster, update_rep_bb)
	(add_bb_to_cluster, new_cluster, delete_cluster): New function.
	(all_clusters): New var.
	(alloc_cluster_vectors, reset_cluster_vectors, delete_cluster_vectors)
	(merge_clusters, set_cluster): New function.
	(gimple_equal_p, gsi_advance_bw_nondebug_nonlocal, find_duplicate)
	(same_phi_alternatives_1, same_phi_alternatives, bb_has_non_vop_phi)
	(deps_ok_for_redirect_from_bb_to_bb, deps_ok_for_redirect)
	(find_clusters_1, find_clusters): New function.
	(update_vuses, vop_phi, vop_at_entry, replace_block_by): New function.
	(update_bbs): New var.
	(apply_clusters): New function.
	(update_debug_stmt, update_debug_stmts): New function.
	(tail_merge_optimize): New function.
	tree-pass.h (tail_merge_optimize): Declare.
	* tree-ssa-pre.c (execute_pre): Use tail_merge_optimize.
	* Makefile.in (OBJS-common): Add tree-ssa-tail-merge.o.
	(tree-ssa-tail-merge.o): New rule.
	* opts.c (default_options_table): Set OPT_ftree_tail_merge by default at
	OPT_LEVELS_2_PLUS.
	* tree-ssa-sccvn.c (vn_valueize): Move to ...
	* tree-ssa-sccvn.h (vn_valueize): Here.
	* timevar.def (TV_TREE_TAIL_MERGE): New timevar.
	* common.opt (ftree-tail-merge): New switch.
	* params.def (PARAM_MAX_TAIL_MERGE_COMPARISONS)
	(PARAM_MAX_TAIL_MERGE_ITERATIONS): New parameter.
	* doc/invoke.texi (Optimization Options, -O2): Add -ftree-tail-merge.
	(-ftree-tail-merge, max-tail-merge-comparisons)
	(max-tail-merge-iterations): New item.

From-SVN: r179275

gcc/ChangeLog

@@ -1,3 +1,55 @@
+2011-09-27  Tom de Vries  <tom@codesourcery.com>
+
+	PR middle-end/43864
+	* tree-ssa-tail-merge.c: New file.
+	(struct same_succ_def): Define.
+	(same_succ, const_same_succ): New typedef.
+	(struct bb_cluster_def): Define.
+	(bb_cluster, const_bb_cluster): New typedef.
+	(struct aux_bb_info): Define.
+	(BB_SIZE, BB_SAME_SUCC, BB_CLUSTER, BB_VOP_AT_EXIT): Define.
+	(gvn_uses_equal): New function.
+	(same_succ_print, same_succ_print_traverse, update_dep_bb)
+	(stmt_update_dep_bb, local_def, same_succ_hash)
+	(inverse_flags, same_succ_equal, same_succ_alloc, same_succ_delete)
+	(same_succ_reset): New function.
+	(same_succ_htab, same_succ_edge_flags)
+	(deleted_bbs, deleted_bb_preds): New var.
+	(debug_same_succ): New function.
+	(worklist): New var.
+	(print_worklist, add_to_worklist, find_same_succ_bb, find_same_succ)
+	(init_worklist, delete_worklist, delete_basic_block_same_succ)
+	(same_succ_flush_bbs, purge_bbs, update_worklist): New function.
+	(print_cluster, debug_cluster, update_rep_bb)
+	(add_bb_to_cluster, new_cluster, delete_cluster): New function.
+	(all_clusters): New var.
+	(alloc_cluster_vectors, reset_cluster_vectors, delete_cluster_vectors)
+	(merge_clusters, set_cluster): New function.
+	(gimple_equal_p, gsi_advance_bw_nondebug_nonlocal, find_duplicate)
+	(same_phi_alternatives_1, same_phi_alternatives, bb_has_non_vop_phi)
+	(deps_ok_for_redirect_from_bb_to_bb, deps_ok_for_redirect)
+	(find_clusters_1, find_clusters): New function.
+	(update_vuses, vop_phi, vop_at_entry, replace_block_by): New function.
+	(update_bbs): New var.
+	(apply_clusters): New function.
+	(update_debug_stmt, update_debug_stmts): New function.
+	(tail_merge_optimize): New function.
+	tree-pass.h (tail_merge_optimize): Declare.
+	* tree-ssa-pre.c (execute_pre): Use tail_merge_optimize.
+	* Makefile.in (OBJS-common): Add tree-ssa-tail-merge.o.
+	(tree-ssa-tail-merge.o): New rule.
+	* opts.c (default_options_table): Set OPT_ftree_tail_merge by default at
+	OPT_LEVELS_2_PLUS.
+	* tree-ssa-sccvn.c (vn_valueize): Move to ...
+	* tree-ssa-sccvn.h (vn_valueize): Here.
+	* timevar.def (TV_TREE_TAIL_MERGE): New timevar.
+	* common.opt (ftree-tail-merge): New switch.
+	* params.def (PARAM_MAX_TAIL_MERGE_COMPARISONS)
+	(PARAM_MAX_TAIL_MERGE_ITERATIONS): New parameter.
+	* doc/invoke.texi (Optimization Options, -O2): Add -ftree-tail-merge.
+	(-ftree-tail-merge, max-tail-merge-comparisons)
+	(max-tail-merge-iterations): New item.
+
 2011-09-27  Jan Hubicka  <jh@suse.cz>
 
 	* ipa-inline-analysis.c (MAX_TIME): Reduce to avoid overflows.

gcc/Makefile.in

@@ -1476,6 +1476,7 @@ OBJS = \
 	tree-ssa-sccvn.o \
 	tree-ssa-sink.o \
 	tree-ssa-structalias.o \
+	tree-ssa-tail-merge.o \
 	tree-ssa-ter.o \
 	tree-ssa-threadedge.o \
 	tree-ssa-threadupdate.o \
@@ -2382,6 +2383,13 @@ stor-layout.o : stor-layout.c $(CONFIG_H) $(SYSTEM_H) coretypes.h $(TM_H) \
    $(TREE_H) $(PARAMS_H) $(FLAGS_H) $(FUNCTION_H) $(EXPR_H) output.h $(RTL_H) \
    $(GGC_H) $(TM_P_H) $(TARGET_H) langhooks.h $(REGS_H) gt-stor-layout.h \
    $(DIAGNOSTIC_CORE_H) $(CGRAPH_H) $(TREE_INLINE_H) $(TREE_DUMP_H) $(GIMPLE_H)
+tree-ssa-tail-merge.o: tree-ssa-tail-merge.c \
+   $(SYSTEM_H) $(CONFIG_H) coretypes.h $(TM_H) $(BITMAP_H) \
+   $(FLAGS_H) $(TM_P_H) $(BASIC_BLOCK_H) output.h \
+   $(TREE_H) $(TREE_FLOW_H) $(TREE_INLINE_H) \
+   $(GIMPLE_H) $(FUNCTION_H) \
+   $(TIMEVAR_H) tree-ssa-sccvn.h \
+   $(CGRAPH_H) gimple-pretty-print.h tree-pretty-print.h $(PARAMS_H)
 tree-ssa-structalias.o: tree-ssa-structalias.c \
    $(SYSTEM_H) $(CONFIG_H) coretypes.h $(TM_H) $(GGC_H) $(OBSTACK_H) $(BITMAP_H) \
    $(FLAGS_H) $(TM_P_H) $(BASIC_BLOCK_H) output.h \

gcc/common.opt

@@ -1945,6 +1945,10 @@ ftree-dominator-opts
 Common Report Var(flag_tree_dom) Optimization
 Enable dominator optimizations
 
+ftree-tail-merge
+Common Report Var(flag_tree_tail_merge) Optimization
+Enable tail merging on trees
+
 ftree-dse
 Common Report Var(flag_tree_dse) Optimization
 Enable dead store elimination

gcc/doc/invoke.texi

@@ -407,7 +407,7 @@ Objective-C and Objective-C++ Dialects}.
 -ftree-phiprop -ftree-loop-distribution -ftree-loop-distribute-patterns @gol
 -ftree-loop-ivcanon -ftree-loop-linear -ftree-loop-optimize @gol
 -ftree-parallelize-loops=@var{n} -ftree-pre -ftree-pta -ftree-reassoc @gol
--ftree-sink -ftree-sra -ftree-switch-conversion @gol
+-ftree-sink -ftree-sra -ftree-switch-conversion -ftree-tail-merge @gol
 -ftree-ter -ftree-vect-loop-version -ftree-vectorize -ftree-vrp @gol
 -funit-at-a-time -funroll-all-loops -funroll-loops @gol
 -funsafe-loop-optimizations -funsafe-math-optimizations -funswitch-loops @gol
@@ -6137,7 +6137,7 @@ also turns on the following optimization flags:
 -fsched-interblock  -fsched-spec @gol
 -fschedule-insns  -fschedule-insns2 @gol
 -fstrict-aliasing -fstrict-overflow @gol
--ftree-switch-conversion @gol
+-ftree-switch-conversion -ftree-tail-merge @gol
 -ftree-pre @gol
 -ftree-vrp}
 
@@ -7020,6 +7020,13 @@ Perform conversion of simple initializations in a switch to
 initializations from a scalar array.  This flag is enabled by default
 at @option{-O2} and higher.
 
+@item -ftree-tail-merge
+Look for identical code sequences.  When found, replace one with a jump to the
+other.  This optimization is known as tail merging or cross jumping.  This flag
+is enabled by default at @option{-O2} and higher.  The run time of this pass can
+be limited using @option{max-tail-merge-comparisons} parameter and
+@option{max-tail-merge-iterations} parameter.
+
 @item -ftree-dce
 @opindex ftree-dce
 Perform dead code elimination (DCE) on trees.  This flag is enabled by
@@ -8603,6 +8610,14 @@ This is used to avoid quadratic behavior in hoisting algorithm.
 The value of 0 will avoid limiting the search, but may slow down compilation
 of huge functions.  The default value is 30.
 
+@item max-tail-merge-comparisons
+The maximum amount of similar bbs to compare a bb with.  This is used to
+avoid quadratic behaviour in tree tail merging.  The default value is 10.
+
+@item max-tail-merge-iterations
+The maximum amount of iterations of the pass over the function.  This is used to
+limit run time in tree tail merging.  The default value is 2.
+
 @item max-unrolled-insns
 The maximum number of instructions that a loop should have if that loop
 is unrolled, and if the loop is unrolled, it determines how many times

gcc/opts.c

@@ -484,6 +484,7 @@ static const struct default_options default_options_table[] =
     { OPT_LEVELS_2_PLUS, OPT_falign_jumps, NULL, 1 },
     { OPT_LEVELS_2_PLUS, OPT_falign_labels, NULL, 1 },
     { OPT_LEVELS_2_PLUS, OPT_falign_functions, NULL, 1 },
+    { OPT_LEVELS_2_PLUS, OPT_ftree_tail_merge, NULL, 1 },
 
     /* -O3 optimizations.  */
     { OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },

gcc/params.def

@@ -921,6 +921,15 @@ DEFPARAM (PARAM_TREE_REASSOC_WIDTH,
 	  "reassociated tree. If 0, use the target dependent heuristic.",
 	  0, 0, 0)
 
+DEFPARAM (PARAM_MAX_TAIL_MERGE_COMPARISONS,
+          "max-tail-merge-comparisons",
+          "Maximum amount of similar bbs to compare a bb with",
+          10, 0, 0)
+
+DEFPARAM (PARAM_MAX_TAIL_MERGE_ITERATIONS,
+          "max-tail-merge-iterations",
+          "Maximum amount of iterations of the pass over a function",
+          2, 0, 0)
 
 /*
 Local variables:

gcc/timevar.def

@@ -127,6 +127,7 @@ DEFTIMEVAR (TV_TREE_GIMPLIFY	     , "tree gimplify")
 DEFTIMEVAR (TV_TREE_EH		     , "tree eh")
 DEFTIMEVAR (TV_TREE_CFG		     , "tree CFG construction")
 DEFTIMEVAR (TV_TREE_CLEANUP_CFG	     , "tree CFG cleanup")
+DEFTIMEVAR (TV_TREE_TAIL_MERGE       , "tree tail merge")
 DEFTIMEVAR (TV_TREE_VRP              , "tree VRP")
 DEFTIMEVAR (TV_TREE_COPY_PROP        , "tree copy propagation")
 DEFTIMEVAR (TV_FIND_REFERENCED_VARS  , "tree find ref. vars")

gcc/tree-pass.h

@@ -401,6 +401,7 @@ extern struct gimple_opt_pass pass_call_cdce;
 extern struct gimple_opt_pass pass_merge_phi;
 extern struct gimple_opt_pass pass_split_crit_edges;
 extern struct gimple_opt_pass pass_pre;
+extern unsigned int tail_merge_optimize (unsigned int);
 extern struct gimple_opt_pass pass_profile;
 extern struct gimple_opt_pass pass_strip_predict_hints;
 extern struct gimple_opt_pass pass_lower_complex_O0;

gcc/tree-ssa-pre.c

@@ -4915,7 +4915,6 @@ execute_pre (bool do_fre)
   statistics_counter_event (cfun, "Constified", pre_stats.constified);
 
   clear_expression_ids ();
-  free_scc_vn ();
   if (!do_fre)
     {
       remove_dead_inserted_code ();
@@ -4925,6 +4924,17 @@ execute_pre (bool do_fre)
   scev_finalize ();
   fini_pre (do_fre);
 
+  if (!do_fre)
+    /* TODO: tail_merge_optimize may merge all predecessors of a block, in which
+       case we can merge the block with the remaining predecessor of the block.
+       It should either:
+       - call merge_blocks after each tail merge iteration
+       - call merge_blocks after all tail merge iterations
+       - mark TODO_cleanup_cfg when necessary
+       - share the cfg cleanup with fini_pre.  */
+    todo |= tail_merge_optimize (todo);
+  free_scc_vn ();
+
   return todo;
 }
 

gcc/tree-ssa-sccvn.c

@@ -2820,19 +2820,6 @@ stmt_has_constants (gimple stmt)
   return false;
 }
 
-/* Valueize NAME if it is an SSA name, otherwise just return it.  */
-
-static inline tree
-vn_valueize (tree name)
-{
-  if (TREE_CODE (name) == SSA_NAME)
-    {
-      tree tem = SSA_VAL (name);
-      return tem == VN_TOP ? name : tem;
-    }
-  return name;
-}
-
 /* Replace SSA_NAMES in expr with their value numbers, and return the
    result.
    This is performed in place. */

gcc/tree-ssa-sccvn.h

@@ -215,4 +215,18 @@ unsigned int get_constant_value_id (tree);
 unsigned int get_or_alloc_constant_value_id (tree);
 bool value_id_constant_p (unsigned int);
 tree fully_constant_vn_reference_p (vn_reference_t);
+
+/* Valueize NAME if it is an SSA name, otherwise just return it.  */
+
+static inline tree
+vn_valueize (tree name)
+{
+  if (TREE_CODE (name) == SSA_NAME)
+    {
+      tree tem = VN_INFO (name)->valnum;
+      return tem == VN_TOP ? name : tem;
+    }
+  return name;
+}
+
 #endif /* TREE_SSA_SCCVN_H  */