[gcc r11-8736] tree-optimization/101445 - fix negative stride SLP vect with gaps

[gcc r11-8736] tree-optimization/101445 - fix negative stride SLP vect with gaps

[Richard Biener]

https://gcc.gnu.org/g:1eee5fa556432fb6eab3a479c95609c5f3791ccb

commit r11-8736-g1eee5fa556432fb6eab3a479c95609c5f3791ccb
Author: Richard Biener <rguenther@suse.de>
Date:   Wed Jul 14 11:06:58 2021 +0200

    tree-optimization/101445 - fix negative stride SLP vect with gaps
    
    The following fixes the IV adjustment for the gap in a negative
    stride SLP vectorization.  The adjustment was in the wrong direction,
    now fixes as in the patch.
    
    2021-07-14  Richard Biener  <rguenther@suse.de>
    
            PR tree-optimization/101445
            * tree-vect-stmts.c (vectorizable_load): Do the gap adjustment
            of the IV in the correct direction for negative stride
            accesses.
    
            * gcc.dg/vect/pr101445.c: New testcase.
    
    (cherry picked from commit a967a3efd39280fe3f5774e45490e991f8e99059)

Diff:
---
 gcc/testsuite/gcc.dg/vect/pr101445.c | 28 ++++++++++++++++++++++++++++
 gcc/tree-vect-stmts.c                |  6 ++++++
 2 files changed, 34 insertions(+)

diff --git a/gcc/testsuite/gcc.dg/vect/pr101445.c b/gcc/testsuite/gcc.dg/vect/pr101445.c
new file mode 100644
index 00000000000..f8a6e9ce6f7
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr101445.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include "tree-vect.h"
+
+int a[35] = { 1, 1, 3 };
+
+void __attribute__((noipa))
+foo ()
+{
+  for (int b = 4; b >= 0; b--)
+    {
+      int tem = a[b * 5 + 3 + 1];
+      a[b * 5 + 3] = tem;
+      a[b * 5 + 2] = tem;
+      a[b * 5 + 1] = tem;
+      a[b * 5 + 0] = tem;
+    }
+}
+
+int main()
+{
+  check_vect ();
+  foo ();
+  for (int d = 0; d < 25; d++)
+    if (a[d] != 0)
+      __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index bd2a1c89e67..2c86f06a57b 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -9737,6 +9737,9 @@ vectorizable_load (vec_info *vinfo,
 		  poly_wide_int bump_val
 		    = (wi::to_wide (TYPE_SIZE_UNIT (elem_type))
 		       * group_gap_adj);
+		  if (tree_int_cst_sgn
+			(vect_dr_behavior (vinfo, dr_info)->step) == -1)
+		    bump_val = -bump_val;
 		  tree bump = wide_int_to_tree (sizetype, bump_val);
 		  dataref_ptr = bump_vector_ptr (vinfo, dataref_ptr, ptr_incr,
 						 gsi, stmt_info, bump);
@@ -9750,6 +9753,9 @@ vectorizable_load (vec_info *vinfo,
 	      poly_wide_int bump_val
 		= (wi::to_wide (TYPE_SIZE_UNIT (elem_type))
 		   * group_gap_adj);
+	      if (tree_int_cst_sgn
+		    (vect_dr_behavior (vinfo, dr_info)->step) == -1)
+		bump_val = -bump_val;
 	      tree bump = wide_int_to_tree (sizetype, bump_val);
 	      dataref_ptr = bump_vector_ptr (vinfo, dataref_ptr, ptr_incr, gsi,
 					     stmt_info, bump);