re PR tree-optimization/77445 (Performance drop after r239219 on coremark test)

	PR middle-end/77445
	* gcc.dg/tree-ssa/pr77445-2.c: Update testcase to check that all
	threading is done.
	* tree-ssa-threadbackward.c (profitable_jump_thread_path): Dump
	statistics of the analyzed path; allow threading for speed when
	any of BBs along the path are optimized for speed.

From-SVN: r245135

4 files changed, 42 insertions, 4 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 7a11db8..07da434 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2017-02-02  Jan Hubicka  <hubicka@ucw.cz>
+
+	PR middle-end/77445
+	* tree-ssa-threadbackward.c (profitable_jump_thread_path): Dump
+	statistics of the analyzed path; allow threading for speed when
+	any of BBs along the path are optimized for speed.
+
 2017-02-02  Eric Botcazou  <ebotcazou@adacore.com>
 
 	PR middle-end/78468
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 04312df..dcc69fe 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2017-02-02  Jan Hubicka  <hubicka@ucw.cz>
+
+	PR middle-end/77445
+	* gcc.dg/tree-ssa/pr77445-2.c: Update testcase to check that all
+	threading is done.
+
 2017-02-02  Tamar Christina  <tamar.christina@arm.com>
 
 	PR middle-end/78142
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
index 6e576e5..88e3b94 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread1-details-blocks-stats" } */
+/* { dg-options "-O2 -fdump-tree-thread-details-blocks-stats" } */
 typedef enum STATES {
 	START=0,
 	INVALID,
@@ -121,3 +121,7 @@ enum STATES FMS( u8 **in , u32 *transitions) {
    increase much.  */
 /* { dg-final { scan-tree-dump "Jumps threaded: 1\[1-9\]" "thread1" } } */
 /* { dg-final { scan-tree-dump-times "Invalid sum" 2 "thread1" } } */
+/* { dg-final { scan-tree-dump-not "not considered" "thread1" } } */
+/* { dg-final { scan-tree-dump-not "not considered" "thread2" } } */
+/* { dg-final { scan-tree-dump-not "not considered" "thread3" } } */
+/* { dg-final { scan-tree-dump-not "not considered" "thread4" } } */
diff --git a/gcc/tree-ssa-threadbackward.c b/gcc/tree-ssa-threadbackward.c
index 51f30a7..24def1d 100644
--- a/gcc/tree-ssa-threadbackward.c
+++ b/gcc/tree-ssa-threadbackward.c
@@ -159,6 +159,10 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
   bool threaded_through_latch = false;
   bool multiway_branch_in_path = false;
   bool threaded_multiway_branch = false;
+  bool contains_hot_bb = false;
+
+  if (dump_file && (dump_flags & TDF_DETAILS))
+    fprintf (dump_file, "Checking profitability of path (backwards): ");
 
   /* Count the number of instructions on the path: as these instructions
      will have to be duplicated, we will not record the path if there
@@ -168,6 +172,8 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
     {
       basic_block bb = (*path)[j];
 
+      if (dump_file && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file, " bb:%i", bb->index);
       /* Remember, blocks in the path are stored in opposite order
 	 in the PATH array.  The last entry in the array represents
 	 the block with an outgoing edge that we will redirect to the
@@ -177,6 +183,7 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
 	 branch.  */
       if (j < path_length - 1)
 	{
+	  int orig_n_insns = n_insns;
 	  if (bb->loop_father != loop)
 	    {
 	      path_crosses_loops = true;
@@ -219,6 +226,8 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
 		}
 	    }
 
+	  if (!contains_hot_bb && speed_p)
+	    contains_hot_bb |= optimize_bb_for_speed_p (bb);
 	  for (gsi = gsi_after_labels (bb);
 	       !gsi_end_p (gsi);
 	       gsi_next_nondebug (&gsi))
@@ -229,8 +238,10 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
 		  && !(gimple_code (stmt) == GIMPLE_ASSIGN
 		       && gimple_assign_rhs_code (stmt) == ASSERT_EXPR)
 		  && !is_gimple_debug (stmt))
-	        n_insns += estimate_num_insns (stmt, &eni_size_weights);
+		n_insns += estimate_num_insns (stmt, &eni_size_weights);
 	    }
+	  if (dump_file && (dump_flags & TDF_DETAILS))
+	    fprintf (dump_file, " (%i insns)", n_insns-orig_n_insns);
 
 	  /* We do not look at the block with the threaded branch
 	     in this loop.  So if any block with a last statement that
@@ -264,7 +275,13 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
      last block in the threading path.  So don't count it against our
      statement count.  */
 
-  n_insns-= estimate_num_insns (stmt, &eni_size_weights);
+  int stmt_insns = estimate_num_insns (stmt, &eni_size_weights);
+  n_insns-= stmt_insns;
+
+  if (dump_file && (dump_flags & TDF_DETAILS))
+    fprintf (dump_file, "\n  Control statement insns: %i\n"
+	     "  Overall: %i insns\n",
+	     stmt_insns, n_insns);
 
   /* We have found a constant value for ARG.  For GIMPLE_SWITCH
      and GIMPLE_GOTO, we use it as-is.  However, for a GIMPLE_COND
@@ -311,7 +328,11 @@ profitable_jump_thread_path (vec<basic_block, va_gc> *&path,
       return NULL;
     }
 
-  if (speed_p && optimize_edge_for_speed_p (taken_edge))
+  /* Threading is profitable if the path duplicated is hot but also
+     in a case we separate cold path from hot path and permit optimization
+     of the hot path later.  Be on the agressive side here. In some testcases,
+     as in PR 78407 this leads to noticeable improvements.  */
+  if (speed_p && (optimize_edge_for_speed_p (taken_edge) || contains_hot_bb))
     {
       if (n_insns >= PARAM_VALUE (PARAM_MAX_FSM_THREAD_PATH_INSNS))
 	{