From: Richard Biener <rguenther@suse.de>
Date: Wed, 13 Nov 2024 10:32:13 +0000 (+0100)
Subject: Do not consider overrun for VMAT_ELEMENTWISE
X-Git-Tag: basepoints/gcc-16~4323
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=6d85a0bc2e09221bdb412bc47aefbcd10c546fd5;p=thirdparty%2Fgcc.git

Do not consider overrun for VMAT_ELEMENTWISE

When we classify an SLP access as VMAT_ELEMENTWISE we still consider
overrun - the reset of it is later overwritten.  The following fixes
this, resolving a few RISC-V FAILs with --param vect-force-slp=1.

	* tree-vect-stmts.cc (get_group_load_store_type): For
	VMAT_ELEMENTWISE there's no overrun.
---

diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 3147ff247a54..5d731205675e 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -2093,7 +2093,6 @@ get_group_load_store_type (vec_info *vinfo, stmt_vec_info stmt_info,
 	      if (SLP_TREE_LANES (slp_node) == 1)
 		{
 		  *memory_access_type = VMAT_ELEMENTWISE;
-		  overrun_p = false;
 		  if (dump_enabled_p ())
 		    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
 				     "single-element interleaving not supported "
@@ -2110,7 +2109,8 @@ get_group_load_store_type (vec_info *vinfo, stmt_vec_info stmt_info,
 		}
 	    }
 
-	  overrun_p = loop_vinfo && gap != 0;
+	  overrun_p = (loop_vinfo && gap != 0
+		       && *memory_access_type != VMAT_ELEMENTWISE);
 	  if (overrun_p && vls_type != VLS_LOAD)
 	    {
 	      dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,