From 5ea2965b499f9e491e45db19fedbccfccb75076a Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Tue, 14 Nov 2023 11:37:13 +0100
Subject: [PATCH] tree-optimization/112281 - loop distribution and zero
 dependence distances

We currently distribute

  for (c = 2; c; c--)
    for (e = 0; e < 2; e++) {
      d[c] = b = d[c + 1];
      d[c + 1].a = 0;
    }

in a wrong way where the inner loop zero dependence distance should
make us preserve stmt execution order.  We fail to do so since we
only look for a fully zero distance vector rather than looking at
the innermost loop distance.  This is somewhat similar to PR87022
where we instead looked at the outermost loop distance and changed
this to what we do now.  The following switches us to look at the
innermost loop distance.

	PR tree-optimization/112281
	* tree-loop-distribution.cc (pg_add_dependence_edges):
	Preserve stmt order when the innermost loop has exact
	overlap.

	* gcc.dg/torture/pr112281.c: New testcase.
---
 gcc/testsuite/gcc.dg/torture/pr112281.c | 19 +++++++++++++++++++
 gcc/tree-loop-distribution.cc           |  7 ++++---
 2 files changed, 23 insertions(+), 3 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/torture/pr112281.c

diff --git a/gcc/testsuite/gcc.dg/torture/pr112281.c b/gcc/testsuite/gcc.dg/torture/pr112281.c
new file mode 100644
index 000000000000..3f0a61a93766
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr112281.c
@@ -0,0 +1,19 @@
+/* { dg-do run } */
+/* { dg-additional-options "-ftree-loop-distribution" } */
+
+struct {
+  int : 8;
+  int a;
+} b, d[4] = {{0}, {0}, {0}, {5}};
+int c, e;
+int main()
+{
+  for (c = 2; c; c--)
+    for (e = 0; e < 2; e++) {
+      d[c] = b = d[c + 1];
+      d[c + 1].a = 0;
+    }
+  if (b.a != 0)
+    __builtin_abort();
+  return 0;
+}
diff --git a/gcc/tree-loop-distribution.cc b/gcc/tree-loop-distribution.cc
index 8abfa9920701..8e92af61c57f 100644
--- a/gcc/tree-loop-distribution.cc
+++ b/gcc/tree-loop-distribution.cc
@@ -2163,9 +2163,10 @@ loop_distribution::pg_add_dependence_edges (struct graph *rdg, int dir,
 		 gcc.dg/tree-ssa/pr94969.c.  */
 	      if (DDR_NUM_DIST_VECTS (ddr) != 1)
 		this_dir = 2;
-	      /* If the overlap is exact preserve stmt order.  */
-	      else if (lambda_vector_zerop (DDR_DIST_VECT (ddr, 0),
-					    DDR_NB_LOOPS (ddr)))
+	      /* If the dependence distance is zero in the innermost
+		 loop preserve stmt order.  */
+	      else if (DDR_DIST_VECT (ddr, 0)
+			 [DDR_LOOP_NEST (ddr).length () - 1] == 0)
 		;
 	      /* Else as the distance vector is lexicographic positive swap
 		 the dependence direction.  */
-- 
2.47.2