[gcc r14-8207] tree-optimization/113431 - wrong dependence with invariant load

[Richard Biener]

https://gcc.gnu.org/g:b981d5c60b8ef78e2adecd6b5d7e36f9e5e61c54

commit r14-8207-gb981d5c60b8ef78e2adecd6b5d7e36f9e5e61c54
Author: Richard Biener <rguenther@suse.de>
Date:   Wed Jan 17 14:05:42 2024 +0100

    tree-optimization/113431 - wrong dependence with invariant load
    
    The vectorizer dependence analysis is confused with invariant loads
    when figuring whether the circumstances are so that we preserve
    scalar stmt execution order.  The following rectifies this.
    
            PR tree-optimization/113431
            * tree-vect-data-refs.cc (vect_preserves_scalar_order_p):
            When there is an invariant load we might not preserve
            scalar order.
    
            * gcc.dg/vect/pr113431.c: New testcase.

Diff:
---
 gcc/testsuite/gcc.dg/vect/pr113431.c | 18 ++++++++++++++++++
 gcc/tree-vect-data-refs.cc           |  6 ++++++
 2 files changed, 24 insertions(+)

diff --git a/gcc/testsuite/gcc.dg/vect/pr113431.c b/gcc/testsuite/gcc.dg/vect/pr113431.c
new file mode 100644
index 00000000000..04448d9dd81
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr113431.c
@@ -0,0 +1,18 @@
+/* { dg-additional-options "-O3 -fdump-tree-slp1-details" } */
+
+#include "tree-vect.h"
+
+int a[2][9];
+int b;
+int main()
+{
+  check_vect ();
+  for (b = 0; b < 2; b++)
+    for (long e = 8; e > 0; e--)
+      a[b][e] = a[0][1] == 0;
+  if (a[1][1] != 0)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "optimized: basic block part vectorized" 2 "slp1" { target vect_int } } } */
diff --git a/gcc/tree-vect-data-refs.cc b/gcc/tree-vect-data-refs.cc
index 0495842b350..f592aeb8028 100644
--- a/gcc/tree-vect-data-refs.cc
+++ b/gcc/tree-vect-data-refs.cc
@@ -282,6 +282,12 @@ vect_preserves_scalar_order_p (dr_vec_info *dr_info_a, dr_vec_info *dr_info_b)
       && !STMT_VINFO_GROUPED_ACCESS (stmtinfo_b))
     return true;
 
+  /* If there is a loop invariant read involved we might vectorize it in
+     the prologue, breaking scalar oder with respect to the in-loop store.  */
+  if ((DR_IS_READ (dr_info_a->dr) && integer_zerop (DR_STEP (dr_info_a->dr)))
+      || (DR_IS_READ (dr_info_b->dr) && integer_zerop (DR_STEP (dr_info_b->dr))))
+    return false;
+
   /* STMT_A and STMT_B belong to overlapping groups.  All loads are
      emitted at the position of the first scalar load.
      Stores in a group are emitted at the position of the last scalar store.