[gcc(refs/vendors/vrull/heads/slp-improvements)] Fix (perf regression): revert to previous ordering

[gcc(refs/vendors/vrull/heads/slp-improvements)] Fix (perf regression): revert to previous ordering

[Philipp Tomsich]

https://gcc.gnu.org/g:d8a63369bf3cb2a8f6450162683b51a388021312

commit d8a63369bf3cb2a8f6450162683b51a388021312
Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
Date:   Tue Jan 23 17:58:05 2024 +0100

    Fix (perf regression): revert to previous ordering
    
    The 'more natural' ABCD ordering (as opposed to the ACBD order) of all
    nodes from the refactored implementation resulted in a x264
    regression, where the number of tbl instructions has increased from 26
    to 286 in total.
    
    This changes the order back to ACBD, reducing the number of
    tbl-instructions back to 26 and resolves the observed performance
    regression from the fix for #356.
    
    Ref #356
    
    Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>

Diff:
---
 gcc/tree-vect-slp.cc | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index f7970bafd45..6b5edf1cebc 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -1920,14 +1920,14 @@ try_rearrange_oprnd_info (vec<slp_oprnd_info> &oprnds_info, unsigned group_size)
       {
 	/* Given oprnd[0] -> A1, A1, B1, B1, A2, A2, B2, B2, ...
 	   Given oprnd[1] -> C1, C1, D1, D1, C2, C2, D2, D2, ...
-	   Create a single node -> A1, B1, C1, D1, A2, B2, C2, D2, ...  */
+	   Create a single node -> A1, C1, B1, D1, A2, C2, B2, D2, ...  */
 
 	/* The ordering here is at least to some extent arbitrary.
 	   A generilized version needs to use some explicit ordering.  */
-	oprnds_info[0]->def_stmts[j+1] = oprnds_info[0]->def_stmts[j+2];
-	oprnds_info[0]->ops[j+1] = oprnds_info[0]->ops[j+2];
-	oprnds_info[0]->def_stmts[j+2] = oprnds_info[1]->def_stmts[j];
-	oprnds_info[0]->ops[j+2] = oprnds_info[1]->ops[j];
+	oprnds_info[0]->def_stmts[j+1] = oprnds_info[1]->def_stmts[j];
+	oprnds_info[0]->ops[j+1] = oprnds_info[1]->ops[j];
+	oprnds_info[0]->def_stmts[j+2] = oprnds_info[0]->def_stmts[j+2];
+	oprnds_info[0]->ops[j+2] = oprnds_info[0]->ops[j+2];
 	oprnds_info[0]->def_stmts[j+3] = oprnds_info[1]->def_stmts[j+2];
 	oprnds_info[0]->ops[j+3] = oprnds_info[1]->ops[j+2];
       }
@@ -2817,7 +2817,7 @@ fail:
 	}
       else if (rearrange_pattern == SLP_OPRND_PATTERN_AABB)
 	{
-	   /* Given a single node -> A1, B1, C1, D1, A2, B2, C2, D2, ...
+	   /* Given a single node -> A1, C1, B1, D1, A2, C2, B2, D2, ...
 	      Create node "one" -> A1, A1, B1, B1, A2, A2, B2, B2, ...
 	      Create node "two" -> C1, C1, D1, D1, C2, C2, D2, D2, ...  */
 
@@ -2825,11 +2825,11 @@ fail:
 	    {
 	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 0));
 	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 0));
-	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 1));
-	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 1));
+	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 2));
+	      SLP_TREE_LANE_PERMUTATION(one).safe_push (std::make_pair (0, j + 2));
 
-	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 2));
-	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 2));
+	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 1));
+	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 1));
 	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 3));
 	      SLP_TREE_LANE_PERMUTATION(two).safe_push (std::make_pair (0, j + 3));
 	    }