[gcc r15-3712] tree-optimization/116573 - .SELECT_VL for SLP

[Richard Biener]

https://gcc.gnu.org/g:5e3a4a01785e2d5135528a07bb8116af9c55ddf8

commit r15-3712-g5e3a4a01785e2d5135528a07bb8116af9c55ddf8
Author: Richard Biener <rguenther@suse.de>
Date:   Tue Sep 17 11:20:10 2024 +0200

    tree-optimization/116573 - .SELECT_VL for SLP
    
    The following restores the use of .SELECT_VL for testcases where it
    is safe to use even when using SLP.  I've for now restricted it
    to single-lane SLP plus optimistically allow store-lane nodes
    and assume single-lane roots are not widened but at most to
    load-lane who should be fine.
    
            PR tree-optimization/116573
            * tree-vect-loop.cc (vect_analyze_loop_2): Allow .SELECV_VL
            for SLP but disable it when there's multi-lane instances.
            * tree-vect-stmts.cc (vectorizable_store): Only compute the
            ptr increment when generating code.
            (vectorizable_load): Likewise.

Diff:
---
 gcc/tree-vect-loop.cc  | 15 ++++++++++++++-
 gcc/tree-vect-stmts.cc | 10 ++++++----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index d42694d19747..c6778ab5f154 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -3084,10 +3084,23 @@ start_over:
       if (direct_internal_fn_supported_p (IFN_SELECT_VL, iv_type,
 					  OPTIMIZE_FOR_SPEED)
 	  && LOOP_VINFO_LENS (loop_vinfo).length () == 1
-	  && LOOP_VINFO_LENS (loop_vinfo)[0].factor == 1 && !slp
+	  && LOOP_VINFO_LENS (loop_vinfo)[0].factor == 1
 	  && (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
 	      || !LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ()))
 	LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) = true;
+
+      /* If any of the SLP instances cover more than a single lane
+	 we cannot use .SELECT_VL at the moment, even if the number
+	 of lanes is uniform throughout the SLP graph.  */
+      if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo))
+	for (slp_instance inst : LOOP_VINFO_SLP_INSTANCES (loop_vinfo))
+	  if (SLP_TREE_LANES (SLP_INSTANCE_TREE (inst)) != 1
+	      && !(SLP_INSTANCE_KIND (inst) == slp_inst_kind_store
+		   && SLP_INSTANCE_TREE (inst)->ldst_lanes))
+	    {
+	      LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) = false;
+	      break;
+	    }
     }
 
   /* Decide whether this loop_vinfo should use partial vectors or peeling,
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 495f45e40e63..33cdccae7849 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -8744,8 +8744,9 @@ vectorizable_store (vec_info *vinfo,
 	aggr_type = build_array_type_nelts (elem_type, group_size * nunits);
       else
 	aggr_type = vectype;
-      bump = vect_get_data_ptr_increment (vinfo, gsi, dr_info, aggr_type,
-					  memory_access_type, loop_lens);
+      if (!costing_p)
+	bump = vect_get_data_ptr_increment (vinfo, gsi, dr_info, aggr_type,
+					    memory_access_type, loop_lens);
     }
 
   if (mask && !costing_p)
@@ -10820,8 +10821,9 @@ vectorizable_load (vec_info *vinfo,
 	aggr_type = build_array_type_nelts (elem_type, group_size * nunits);
       else
 	aggr_type = vectype;
-      bump = vect_get_data_ptr_increment (vinfo, gsi, dr_info, aggr_type,
-					  memory_access_type, loop_lens);
+      if (!costing_p)
+	bump = vect_get_data_ptr_increment (vinfo, gsi, dr_info, aggr_type,
+					    memory_access_type, loop_lens);
     }
 
   auto_vec<tree> vec_offsets;