loop.texi: Document possibility not to perform disambiguation of loops with multiple latches.

	* doc/loop.texi: Document possibility not to perform disambiguation
	of loops with multiple latches.
	* cfgloopmanip.c (alp_enum_p): Removed.
	(add_loop): Handle subloops.  Use get_loop_body_with_size.
	(create_preheader): Do not allow ENTRY_BLOCK_PTR to be preheader.
	* cfghooks.c (redirect_edge_and_branch_force): Set dominator for
	the new forwarder block.
	(make_forwarder_block): Only call new_bb_cbk if it is not NULL.
	Handle the case latch is NULL.
	* tree-ssa-dom.c (tree_ssa_dominator_optimize): Avoid cfg modifications
	when marking loop exits.
	* ifcvt.c (if_convert): Ditto.  Mark loop exits even if cfg cannot
	be modified.
	* loop-init.c (loop_optimizer_init): Do not modify cfg.  Call
	disambiguate_loops_with_multiple_latches.
	* tree-cfgcleanup.c (cleanup_tree_cfg_loop): Calculate dominators
	before fix_loop_structure.
	* cfgloop.c: Include pointer-set.h and output.h.
	(canonicalize_loop_headers, HEADER_BLOCK, LATCH_EDGE,
	update_latch_info, mfb_keep_just, mfb_keep_nonlatch): Removed.
	(get_loop_latch_edges, find_subloop_latch_edge_by_profile,
	find_subloop_latch_edge_by_ivs, find_subloop_latch_edge,
	mfb_redirect_edges_in_set, form_subloop, merge_latch_edges,
	disambiguate_multiple_latches, get_loop_body_with_size,
	disambiguate_loops_with_multiple_latches): New functions.
	(flow_loop_dump): Dump multiple latch edges.
	(flow_loop_nodes_find): Handle loops with multiple latches.
	(flow_loops_find): Ditto. Do not call canonicalize_loop_headers.
	(glb_enum_p): Modified.
	(get_loop_body): Use get_loop_body_with_size.
	* cfgloop.h (LOOPS_HAVE_RECORDED_EXITS): New flag.
	(AVOID_CFG_MODIFICATIONS): New constant.
	(disambiguate_loops_with_multiple_latches, add_loop,
	get_loop_body_with_size): Declare.
	* Makefile.in (cfgloop.o): Add pointer-set.h and output.h.

	* gcc.dg/tree-ssa/loop-25.c: New test.

From-SVN: r121670

gcc/ChangeLog

+2007-02-06  Zdenek Dvorak <dvorakz@suse.cz>
+
+	* doc/loop.texi: Document possibility not to perform disambiguation
+	of loops with multiple latches.
+	* cfgloopmanip.c (alp_enum_p): Removed.
+	(add_loop): Handle subloops.  Use get_loop_body_with_size.
+	(create_preheader): Do not allow ENTRY_BLOCK_PTR to be preheader.
+	* cfghooks.c (redirect_edge_and_branch_force): Set dominator for
+	the new forwarder block.
+	(make_forwarder_block): Only call new_bb_cbk if it is not NULL.
+	Handle the case latch is NULL.
+	* tree-ssa-dom.c (tree_ssa_dominator_optimize): Avoid cfg modifications
+	when marking loop exits.
+	* ifcvt.c (if_convert): Ditto.  Mark loop exits even if cfg cannot
+	be modified.
+	* loop-init.c (loop_optimizer_init): Do not modify cfg.  Call
+	disambiguate_loops_with_multiple_latches.
+	* tree-cfgcleanup.c (cleanup_tree_cfg_loop): Calculate dominators
+	before fix_loop_structure.
+	* cfgloop.c: Include pointer-set.h and output.h.
+	(canonicalize_loop_headers, HEADER_BLOCK, LATCH_EDGE,
+	update_latch_info, mfb_keep_just, mfb_keep_nonlatch): Removed.
+	(get_loop_latch_edges, find_subloop_latch_edge_by_profile,
+	find_subloop_latch_edge_by_ivs, find_subloop_latch_edge,
+	mfb_redirect_edges_in_set, form_subloop, merge_latch_edges,
+	disambiguate_multiple_latches, get_loop_body_with_size,
+	disambiguate_loops_with_multiple_latches): New functions.
+	(flow_loop_dump): Dump multiple latch edges.
+	(flow_loop_nodes_find): Handle loops with multiple latches.
+	(flow_loops_find): Ditto. Do not call canonicalize_loop_headers.
+	(glb_enum_p): Modified.
+	(get_loop_body): Use get_loop_body_with_size.
+	* cfgloop.h (LOOPS_HAVE_RECORDED_EXITS): New flag.
+	(AVOID_CFG_MODIFICATIONS): New constant.
+	(disambiguate_loops_with_multiple_latches, add_loop,
+	get_loop_body_with_size): Declare.
+	* Makefile.in (cfgloop.o): Add pointer-set.h and output.h.
+
 2007-02-06  Seongbae Park <seongbae.park@gmail.com>
 
 	PR inline-asm/28686

gcc/Makefile.in

@@ -2585,7 +2585,7 @@ cfgcleanup.o : cfgcleanup.c $(CONFIG_H) $(SYSTEM_H) coretypes.h $(TM_H) \
    $(REGS_H) $(EMIT_RTL_H) $(CFGLAYOUT_H) tree-pass.h $(CFGLOOP_H) $(EXPR_H)
 cfgloop.o : cfgloop.c $(CONFIG_H) $(SYSTEM_H) $(RTL_H) coretypes.h $(TM_H) \
    $(BASIC_BLOCK_H) hard-reg-set.h $(CFGLOOP_H) $(FLAGS_H) $(FUNCTION_H) \
-   $(OBSTACK_H) toplev.h $(TREE_FLOW_H) $(TREE_H)
+   $(OBSTACK_H) toplev.h $(TREE_FLOW_H) $(TREE_H) pointer-set.h output.h
 cfgloopanal.o : cfgloopanal.c $(CONFIG_H) $(SYSTEM_H) $(RTL_H) \
    $(BASIC_BLOCK_H) hard-reg-set.h $(CFGLOOP_H) $(EXPR_H) coretypes.h $(TM_H) \
    $(OBSTACK_H) output.h

gcc/cfghooks.c

@@ -378,6 +378,10 @@ redirect_edge_and_branch_force (edge e, basic_block dest)
     rescan_loop_exit (e, false, true);
 
   ret = cfg_hooks->redirect_edge_and_branch_force (e, dest);
+  if (ret != NULL
+      && dom_info_available_p (CDI_DOMINATORS))
+    set_immediate_dominator (CDI_DOMINATORS, ret, src);
+
   if (current_loops != NULL)
     {
       if (ret != NULL)
@@ -724,7 +728,8 @@ make_forwarder_block (basic_block bb, bool (*redirect_edge_p) (edge),
 	fallthru->count = 0;
 
       jump = redirect_edge_and_branch_force (e, bb);
-      if (jump)
+      if (jump != NULL
+	  && new_bb_cbk != NULL)
 	new_bb_cbk (jump);
     }
 
@@ -742,9 +747,12 @@ make_forwarder_block (basic_block bb, bool (*redirect_edge_p) (edge),
       /* If we do not split a loop header, then both blocks belong to the
 	 same loop.  In case we split loop header and do not redirect the
 	 latch edge to DUMMY, then DUMMY belongs to the outer loop, and
-	 BB becomes the new header.  */
+	 BB becomes the new header.  If latch is not recorded for the loop,
+	 we leave this updating on the caller (this may only happen during
+	 loop analysis).  */
       loop = dummy->loop_father;
       if (loop->header == dummy
+	  && loop->latch != NULL
 	  && find_edge (loop->latch, dummy) == NULL)
 	{
 	  remove_bb_from_loops (dummy);

gcc/cfgloop.h

@@ -168,11 +168,13 @@ enum
   LOOPS_HAVE_PREHEADERS = 1,
   LOOPS_HAVE_SIMPLE_LATCHES = 2,
   LOOPS_HAVE_MARKED_IRREDUCIBLE_REGIONS = 4,
-  LOOPS_HAVE_RECORDED_EXITS = 8
+  LOOPS_HAVE_RECORDED_EXITS = 8,
+  LOOPS_MAY_HAVE_MULTIPLE_LATCHES = 16
 };
 
 #define LOOPS_NORMAL (LOOPS_HAVE_PREHEADERS | LOOPS_HAVE_SIMPLE_LATCHES \
 		      | LOOPS_HAVE_MARKED_IRREDUCIBLE_REGIONS)
+#define AVOID_CFG_MODIFICATIONS (LOOPS_MAY_HAVE_MULTIPLE_LATCHES)
 
 typedef struct loop *loop_p;
 DEF_VEC_P (loop_p);
@@ -198,6 +200,7 @@ struct loops
 
 /* Loop recognition.  */
 extern int flow_loops_find (struct loops *);
+extern void disambiguate_loops_with_multiple_latches (void);
 extern void flow_loops_free (struct loops *);
 extern void flow_loops_dump (FILE *,
 			     void (*)(const struct loop *, FILE *, int), int);
@@ -215,6 +218,7 @@ void rescan_loop_exit (edge, bool, bool);
 /* Loop data structure manipulation/querying.  */
 extern void flow_loop_tree_node_add (struct loop *, struct loop *);
 extern void flow_loop_tree_node_remove (struct loop *);
+extern void add_loop (struct loop *, struct loop *);
 extern bool flow_loop_nested_p	(const struct loop *, const struct loop *);
 extern bool flow_bb_inside_loop_p (const struct loop *, const basic_block);
 extern struct loop * find_common_loop (struct loop *, struct loop *);
@@ -229,6 +233,8 @@ extern void mark_loop_exit_edges (void);
 
 /* Loops & cfg manipulation.  */
 extern basic_block *get_loop_body (const struct loop *);
+extern unsigned get_loop_body_with_size (const struct loop *, basic_block *,
+					 unsigned);
 extern basic_block *get_loop_body_in_dom_order (const struct loop *);
 extern basic_block *get_loop_body_in_bfs_order (const struct loop *);
 extern VEC (edge, heap) *get_loop_exit_edges (const struct loop *);

gcc/cfgloopmanip.c

@@ -38,11 +38,9 @@ static void loop_redirect_edge (edge, basic_block);
 static void remove_bbs (basic_block *, int);
 static bool rpe_enum_p (basic_block, void *);
 static int find_path (edge, basic_block **);
-static bool alp_enum_p (basic_block, void *);
 static void fix_loop_placements (struct loop *, bool *);
 static bool fix_bb_placement (basic_block);
 static void fix_bb_placements (basic_block, bool *);
-static void place_new_loop (struct loop *);
 static basic_block create_preheader (struct loop *, int);
 static void unloop (struct loop *, bool *);
 
@@ -395,39 +393,54 @@ remove_path (edge e)
   return true;
 }
 
-/* Predicate for enumeration in add_loop.  */
-static bool
-alp_enum_p (basic_block bb, void *alp_header)
+/* Creates place for a new LOOP in loops structure.  */
+
+static void
+place_new_loop (struct loop *loop)
 {
-  return bb != (basic_block) alp_header;
+  loop->num = number_of_loops ();
+  VEC_safe_push (loop_p, heap, current_loops->larray, loop);
 }
 
 /* Given LOOP structure with filled header and latch, find the body of the
    corresponding loop and add it to loops tree.  Insert the LOOP as a son of
    outer.  */
 
-static void
+void
 add_loop (struct loop *loop, struct loop *outer)
 {
   basic_block *bbs;
   int i, n;
+  struct loop *subloop;
 
   /* Add it to loop structure.  */
   place_new_loop (loop);
   flow_loop_tree_node_add (outer, loop);
 
   /* Find its nodes.  */
-  bbs = XCNEWVEC (basic_block, n_basic_blocks);
-  n = dfs_enumerate_from (loop->latch, 1, alp_enum_p,
-			  bbs, n_basic_blocks, loop->header);
+  bbs = XNEWVEC (basic_block, n_basic_blocks);
+  n = get_loop_body_with_size (loop, bbs, n_basic_blocks);
 
   for (i = 0; i < n; i++)
     {
+      if (bbs[i]->loop_father == outer)
+	{
 	  remove_bb_from_loops (bbs[i]);
 	  add_bb_to_loop (bbs[i], loop);
+	  continue;
+	}
+
+      loop->num_nodes++;
+
+      /* If we find a direct subloop of OUTER, move it to LOOP.  */
+      subloop = bbs[i]->loop_father;
+      if (subloop->outer == outer
+	  && subloop->header == bbs[i])
+	{
+	  flow_loop_tree_node_remove (subloop);
+	  flow_loop_tree_node_add (loop, subloop);
+	}
     }
-  remove_bb_from_loops (loop->header);
-  add_bb_to_loop (loop->header, loop);
 
   free (bbs);
 }
@@ -631,14 +644,6 @@ fix_loop_placements (struct loop *loop, bool *irred_invalidated)
     }
 }
 
-/* Creates place for a new LOOP in loops structure.  */
-static void
-place_new_loop (struct loop *loop)
-{
-  loop->num = number_of_loops ();
-  VEC_safe_push (loop_p, heap, current_loops->larray, loop);
-}
-
 /* Copies copy of LOOP as subloop of TARGET loop, placing newly
    created loop into loops structure.  */
 struct loop *
@@ -1115,12 +1120,15 @@ create_preheader (struct loop *loop, int flags)
   gcc_assert (nentry);
   if (nentry == 1)
     {
-      /* Get an edge that is different from the one from loop->latch
-	 to loop->header.  */
-      e = EDGE_PRED (loop->header,
-		     EDGE_PRED (loop->header, 0)->src == loop->latch);
+      e = loop_preheader_edge (loop);
 
-      if (!(flags & CP_SIMPLE_PREHEADERS) || single_succ_p (e->src))
+      if (/* We do not allow entry block to be the loop preheader, since we
+	     cannot emit code there.  */
+	  e->src != ENTRY_BLOCK_PTR
+	  /* If we want simple preheaders, also force the preheader to have
+	     just a single successor.  */
+	  && !((flags & CP_SIMPLE_PREHEADERS)
+	       && !single_succ_p (e->src)))
 	return NULL;
     }
 

gcc/doc/loop.texi

@@ -48,11 +48,17 @@ a single header, or if there is a branching in the middle of the loop.
 The representation of loops in GCC however allows only loops with a
 single latch.  During loop analysis, headers of such loops are split and
 forwarder blocks are created in order to disambiguate their structures.
-A heuristic based on profile information is used to determine whether
-the latches correspond to sub-loops or to control flow in a single loop.
-This means that the analysis sometimes changes the CFG, and if you run
-it in the middle of an optimization pass, you must be able to deal with
-the new blocks.
+Heuristic based on profile information and structure of the induction
+variables in the loops is used to determine whether the latches
+correspond to sub-loops or to control flow in a single loop.  This means
+that the analysis sometimes changes the CFG, and if you run it in the
+middle of an optimization pass, you must be able to deal with the new
+blocks.  You may avoid CFG changes by passing
+@code{LOOPS_MAY_HAVE_MULTIPLE_LATCHES} flag to the loop discovery,
+note however that most other loop manipulation functions will not work
+correctly for loops with multiple latch edges (the functions that only
+query membership of blocks to loops and subloop relationships, or
+enumerate and test loop exits, can be expected to work).
 
 Body of the loop is the set of blocks that are dominated by its header,
 and reachable from its latch against the direction of edges in CFG.  The
@@ -96,6 +102,13 @@ bitmask.  These flags specify what other properties of the loop
 structures should be calculated/enforced and preserved later:
 
 @itemize
+@item @code{LOOPS_MAY_HAVE_MULTIPLE_LATCHES}: If this flag is set, no
+changes to CFG will be performed in the loop analysis, in particular,
+loops with multiple latch edges will not be disambiguated.  If a loop
+has multiple latches, its latch block is set to NULL.  Most of
+the loop manipulation functions will not work for loops in this shape.
+No other flags that require CFG changes can be passed to
+loop_optimizer_init.
 @item @code{LOOPS_HAVE_PREHEADERS}: Forwarder blocks are created in such
 a way that each loop has only one entry edge, and additionally, the
 source block of this entry edge has only one successor.  This creates a

gcc/ifcvt.c

@@ -3908,18 +3908,13 @@ if_convert (int x_life_data_ok)
   num_true_changes = 0;
   life_data_ok = (x_life_data_ok != 0);
 
-  if ((! targetm.cannot_modify_jumps_p ())
-      && (!flag_reorder_blocks_and_partition || !no_new_pseudos
-	  || !targetm.have_named_sections))
-    {
-      loop_optimizer_init (0);
+  loop_optimizer_init (AVOID_CFG_MODIFICATIONS);
   if (current_loops)
     {
       mark_loop_exit_edges ();
       loop_optimizer_finalize ();
     }
   free_dominance_info (CDI_DOMINATORS);
-    }
 
   /* Compute postdominators if we think we'll use them.  */
   if (HAVE_conditional_execution || life_data_ok)

gcc/loop-init.c

@@ -40,22 +40,11 @@ Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA
 void
 loop_optimizer_init (unsigned flags)
 {
-  edge e;
-  edge_iterator ei;
   struct loops *loops;
 
   gcc_assert (!current_loops);
   loops = XCNEW (struct loops);
 
-  /* Avoid annoying special cases of edges going to exit
-     block.  */
-
-  for (ei = ei_start (EXIT_BLOCK_PTR->preds); (e = ei_safe_edge (ei)); )
-    if ((e->flags & EDGE_FALLTHRU) && !single_succ_p (e->src))
-      split_edge (e);
-    else
-      ei_next (&ei);
-
   /* Find the loops.  */
 
   flow_loops_find (loops);
@@ -69,6 +58,19 @@ loop_optimizer_init (unsigned flags)
       return;
     }
 
+  if (flags & LOOPS_MAY_HAVE_MULTIPLE_LATCHES)
+    {
+      /* If the loops may have multiple latches, we cannot canonicalize
+	 them further (and most of the loop manipulation functions will
+	 not work).  However, we avoid modifying cfg, which some
+	 passes may want.  */
+      gcc_assert ((flags & ~(LOOPS_MAY_HAVE_MULTIPLE_LATCHES
+			     | LOOPS_HAVE_RECORDED_EXITS)) == 0);
+      current_loops->state = LOOPS_MAY_HAVE_MULTIPLE_LATCHES;
+    }
+  else
+    disambiguate_loops_with_multiple_latches ();
+
   /* Create pre-headers.  */
   if (flags & LOOPS_HAVE_PREHEADERS)
     create_preheaders (CP_SIMPLE_PREHEADERS);

gcc/testsuite/ChangeLog

+2007-02-06  Zdenek Dvorak <dvorakz@suse.cz>
+
+	* gcc.dg/tree-ssa/loop-25.c: New test.
+
 2007-02-06  Richard Henderson  <rth@redhat.com>
 
 	* gcc.target/i386/cvt-1.c: Don't expect xmm registers.

gcc/testsuite/gcc.dg/tree-ssa/loop-25.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-vrp1" } */
+
+int foo(void);
+void bla(void);
+void bar(void);
+
+void test1 (void)
+{
+  unsigned i;
+
+  /* Only one loop should be found here.  */
+  i = 0;
+  while (1)
+    {
+      i++;
+      if (i == 100)
+	break;
+
+      if (foo ())
+	bla ();
+      else
+	bar ();
+    }
+}
+
+void test2 (void)
+{
+  unsigned i, j;
+
+  /* Two loops should be found, in this case.  */
+  i = j = 0;
+  while (1)
+    {
+      j++;
+      foo ();
+      if (j < 100)
+	continue;
+
+      i++;
+      j = 0;
+      if (i == 100)
+	break;
+    }
+}
+
+void test3 (void)
+{
+  unsigned i, j, k;
+
+  /* Three loops.  */
+  i = j = k = 0;
+  while (1)
+    {
+      j++;
+      foo ();
+      if (j < 100)
+	continue;
+
+      j = 0;
+      k++;
+      if (k < 100)
+	continue;
+
+      k = 0;
+      i++;
+      if (i == 100)
+	break;
+    }
+}
+
+void test4 (void)
+{
+  unsigned i, j, k;
+
+  /* Two loops with a nested subloop.  */
+  i = j = 0;
+  while (1)
+    {
+      j++;
+      foo ();
+      for (k = 0; k < 100; k++)
+	foo ();
+
+      if (j < 100)
+	continue;
+
+      i++;
+      j = 0;
+      if (i == 100)
+	break;
+    }
+}
+
+
+void test5 (void)
+{
+  unsigned i, j;
+
+  /* Both subloop and non-subloop back edges.  */
+  i = j = 0;
+  while (1)
+    {
+      j++;
+      foo ();
+      if (j < 100)
+	continue;
+      j = 0;
+
+      i++;
+      if (i == 100)
+	break;
+
+      if (foo ())
+	bla ();
+      else
+	bar ();
+    }
+}
+
+/* { dg-final { scan-tree-dump-times "Disambiguating loop" 5 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "Found latch edge" 5 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "Merged latch edges" 2 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "4 loops found" 2 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "3 loops found" 2 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "2 loops found" 1 "vrp1" } } */
+
+/* { dg-final { cleanup-tree-dump "vrp1" } } */

gcc/tree-cfgcleanup.c

@@ -582,8 +582,8 @@ cleanup_tree_cfg_loop (void)
   if (changed)
     {
       bitmap changed_bbs = BITMAP_ALLOC (NULL);
-      fix_loop_structure (changed_bbs);
       calculate_dominance_info (CDI_DOMINATORS);
+      fix_loop_structure (changed_bbs);
 
       /* This usually does nothing.  But sometimes parts of cfg that originally
 	 were inside a loop get out of it due to edge removal (since they

gcc/tree-ssa-dom.c

@@ -279,7 +279,7 @@ tree_ssa_dominator_optimize (void)
   /* We need to know which edges exit loops so that we can
      aggressively thread through loop headers to an exit
      edge.  */
-  loop_optimizer_init (0);
+  loop_optimizer_init (AVOID_CFG_MODIFICATIONS);
   if (current_loops)
     {
       mark_loop_exit_edges ();