[vect] Add main vectorized loop unrolling

gcc/ChangeLog:

	* tree-vect-loop.cc (vect_estimate_min_profitable_iters): Pass new
	argument suggested_unroll_factor.
	(vect_analyze_loop_costing): Likewise.
	(_loop_vec_info::_loop_vec_info): Initialize new member
	suggested_unroll_factor.
	(vect_determine_partial_vectors_and_peeling): Make epilogue of unrolled
	main loop use partial vectors.
	(vect_analyze_loop_2): Pass and use new argument
	suggested_unroll_factor.
	(vect_analyze_loop_1): Change to intialize local
	suggested_unroll_factor and use it.
	(vectorizable_reduction): Don't use single_defuse_cycle when unrolling.
	* tree-vectorizer.h (_loop_vec_info::_loop_vec_info): Add new member
	suggested_unroll_factor.
	(vector_costs::vector_costs): Add new member m_suggested_unroll_factor.
	(vector_costs::suggested_unroll_factor): New getter function.
	(finish_cost): Set return argument suggested_unroll_factor.

1 files changed, 24 insertions, 1 deletions

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 86f90ae..524c86c 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -642,6 +642,13 @@ public:
      about the reductions that generated them.  */
   hash_map<tree, vect_reusable_accumulator> reusable_accumulators;
 
+  /* The number of times that the target suggested we unroll the vector loop
+     in order to promote more ILP.  This value will be used to re-analyze the
+     loop for vectorization and if successful the value will be folded into
+     vectorization_factor (and therefore exactly divides
+     vectorization_factor).  */
+  unsigned int suggested_unroll_factor;
+
   /* Maximum runtime vectorization factor, or MAX_VECTORIZATION_FACTOR
      if there is no particular limit.  */
   unsigned HOST_WIDE_INT max_vectorization_factor;
@@ -1465,6 +1472,7 @@ public:
   unsigned int epilogue_cost () const;
   unsigned int outside_cost () const;
   unsigned int total_cost () const;
+  unsigned int suggested_unroll_factor () const;
 
 protected:
   unsigned int record_stmt_cost (stmt_vec_info, vect_cost_model_location,
@@ -1484,6 +1492,9 @@ protected:
   /* The costs of the three regions, indexed by vect_cost_model_location.  */
   unsigned int m_costs[3];
 
+  /* The suggested unrolling factor determined at finish_cost.  */
+  unsigned int m_suggested_unroll_factor;
+
   /* True if finish_cost has been called.  */
   bool m_finished;
 };
@@ -1496,6 +1507,7 @@ vector_costs::vector_costs (vec_info *vinfo, bool costing_for_scalar)
   : m_vinfo (vinfo),
     m_costing_for_scalar (costing_for_scalar),
     m_costs (),
+    m_suggested_unroll_factor(1),
     m_finished (false)
 {
 }
@@ -1544,6 +1556,15 @@ vector_costs::total_cost () const
   return body_cost () + outside_cost ();
 }
 
+/* Return the suggested unroll factor.  */
+
+inline unsigned int
+vector_costs::suggested_unroll_factor () const
+{
+  gcc_checking_assert (m_finished);
+  return m_suggested_unroll_factor;
+}
+
 #define VECT_MAX_COST 1000
 
 /* The maximum number of intermediate steps required in multi-step type
@@ -1720,12 +1741,14 @@ add_stmt_cost (vector_costs *costs, stmt_info_for_cost *i)
 static inline void
 finish_cost (vector_costs *costs, const vector_costs *scalar_costs,
 	     unsigned *prologue_cost, unsigned *body_cost,
-	     unsigned *epilogue_cost)
+	     unsigned *epilogue_cost, unsigned *suggested_unroll_factor = NULL)
 {
   costs->finish_cost (scalar_costs);
   *prologue_cost = costs->prologue_cost ();
   *body_cost = costs->body_cost ();
   *epilogue_cost = costs->epilogue_cost ();
+  if (suggested_unroll_factor)
+    *suggested_unroll_factor = costs->suggested_unroll_factor ();
 }
 
 inline void