Move EXTRACT_LAST_REDUCTION costing to vectorizable_condition

gcc.target/aarch64/sve/clastb_[57].c started failing after the increase
in the cost of vec_to_scalar (r278452).  The problem is that we were
double-counting the cost of the CLASTB: once in vect_model_reduction_cost
as a vec_to_scalar and once in vectorizable_condition as a plain
vector_stmt.

Based on the TODO above vect_model_reduction_cost, I think the
preferred long-term direction is for vectorizable_* to cost these
things itself, so that's what the patch does (for this one case only).

2019-11-22  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* tree-vect-stmts.c (vect_model_simple_cost): Take an optional
	vect_cost_for_stmt.
	(vectorizable_condition): Calculate the cost of EXTRACT_LAST_REDUCTION
	here rather than...
	* tree-vect-loop.c (vect_model_reduction_cost): ...here.

From-SVN: r278611

gcc/ChangeLog

+2019-11-22  Richard Sandiford  <richard.sandiford@arm.com>
+
+	* tree-vect-stmts.c (vect_model_simple_cost): Take an optional
+	vect_cost_for_stmt.
+	(vectorizable_condition): Calculate the cost of EXTRACT_LAST_REDUCTION
+	here rather than...
+	* tree-vect-loop.c (vect_model_reduction_cost): ...here.
+
 2019-11-22  Claudiu Zissulescu  <claziss@synopsys.com>
 
 	* config/arc/arc.md (bic_f): Use cc_set_register predicate.

gcc/tree-vect-loop.c

@@ -3924,8 +3924,11 @@ vect_model_reduction_cost (stmt_vec_info stmt_info, internal_fn reduc_fn,
 
   code = gimple_assign_rhs_code (orig_stmt_info->stmt);
 
-  if (reduction_type == EXTRACT_LAST_REDUCTION
-      || reduction_type == FOLD_LEFT_REDUCTION)
+  if (reduction_type == EXTRACT_LAST_REDUCTION)
+    /* No extra instructions are needed in the prologue.  The loop body
+       operations are costed in vectorizable_condition.  */
+    inside_cost = 0;
+  else if (reduction_type == FOLD_LEFT_REDUCTION)
     {
       /* No extra instructions needed in the prologue.  */
       prologue_cost = 0;

gcc/tree-vect-stmts.c

@@ -860,7 +860,8 @@ vect_model_simple_cost (stmt_vec_info stmt_info, int ncopies,
 			enum vect_def_type *dt,
 			int ndts,
 			slp_tree node,
-			stmt_vector_for_cost *cost_vec)
+			stmt_vector_for_cost *cost_vec,
+			vect_cost_for_stmt kind = vector_stmt)
 {
   int inside_cost = 0, prologue_cost = 0;
 
@@ -907,7 +908,7 @@ vect_model_simple_cost (stmt_vec_info stmt_info, int ncopies,
     }
 
   /* Pass the inside-of-loop statements to the target-specific cost model.  */
-  inside_cost += record_stmt_cost (cost_vec, ncopies, vector_stmt,
+  inside_cost += record_stmt_cost (cost_vec, ncopies, kind,
 				   stmt_info, 0, vect_body);
 
   if (dump_enabled_p ())
@@ -10084,15 +10085,18 @@ vectorizable_condition (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
 		return false;
 	    }
 	}
-      if (expand_vec_cond_expr_p (vectype, comp_vectype,
-				     cond_code))
-	{
-	  STMT_VINFO_TYPE (stmt_info) = condition_vec_info_type;
-	  vect_model_simple_cost (stmt_info, ncopies, dts, ndts, slp_node,
-				  cost_vec);
-	  return true;
-	}
-      return false;
+
+      vect_cost_for_stmt kind = vector_stmt;
+      if (reduction_type == EXTRACT_LAST_REDUCTION)
+	/* Count one reduction-like operation per vector.  */
+	kind = vec_to_scalar;
+      else if (!expand_vec_cond_expr_p (vectype, comp_vectype, cond_code))
+	return false;
+
+      STMT_VINFO_TYPE (stmt_info) = condition_vec_info_type;
+      vect_model_simple_cost (stmt_info, ncopies, dts, ndts, slp_node,
+			      cost_vec, kind);
+      return true;
     }
 
   /* Transform.  */