From: Richard Biener <rguenther@suse.de>
Date: Tue, 10 Mar 2026 13:34:56 +0000 (+0100)
Subject: Cost scalar into vect_body
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=7eb6d800c9cc4ea79b108a22c56620587fbc0fb7;p=thirdparty%2Fgcc.git

Cost scalar into vect_body

The following adjusts vect_compute_single_scalar_iteration_cost to
record stmts as vect_body rather than vect_prologue so that
scalar_costs->body_cost () will not be zero.

	* tree-vect-loop.cc (vect_compute_single_scalar_iteration_cost):
	Record stmt cost to vect_body.
---

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 1452677c461..cc40f43c252 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -1413,7 +1413,7 @@ vect_compute_single_scalar_iteration_cost (loop_vec_info loop_vinfo)
 	  /* We are using vect_prologue here to avoid scaling twice
 	     by the inner loop factor.  */
 	  record_stmt_cost (&LOOP_VINFO_SCALAR_ITERATION_COST (loop_vinfo),
-			    factor, kind, stmt_info, 0, vect_prologue);
+			    factor, kind, stmt_info, 0, vect_body);
         }
     }