From 4a773bf2f08656a39ac75cf6b4871c8cec8b5007 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 20 Sep 2022 15:27:46 +0100
Subject: [PATCH] vect: Fix missed gather load opportunity

While writing a testcase for PR106794, I noticed that we failed
to vectorise the testcase in the patch for SVE.  The code that
recognises gather loads tries to optimise the point at which
the offset is calculated, to avoid unnecessary extensions or
truncations:

	  /* Don't include the conversion if the target is happy with
	     the current offset type.  */

But breaking only makes sense if we're at an SSA_NAME (which could
then be vectorised).  We shouldn't break on a conversion embedded
in a generic expression.

gcc/
	* tree-vect-data-refs.cc (vect_check_gather_scatter): Restrict
	early-out optimisation to SSA_NAMEs.

gcc/testsuite/
	* gcc.dg/vect/vect-gather-5.c: New test.
---
 gcc/testsuite/gcc.dg/vect/vect-gather-5.c | 42 +++++++++++++++++++++++
 gcc/tree-vect-data-refs.cc                |  1 +
 2 files changed, 43 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-gather-5.c

diff --git a/gcc/testsuite/gcc.dg/vect/vect-gather-5.c b/gcc/testsuite/gcc.dg/vect/vect-gather-5.c
new file mode 100644
index 000000000000..8b5074bba885
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-gather-5.c
@@ -0,0 +1,42 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+
+#ifdef __aarch64__
+#pragma GCC target "+sve"
+#endif
+
+long a[100], b[100], c[100];
+
+void g1 ()
+{
+  for (int i = 0; i < 100; i += 2)
+    {
+      c[i] += a[b[i]] + 1;
+      c[i + 1] += a[b[i + 1]] + 2;
+    }
+}
+
+long g2 ()
+{
+  long res = 0;
+  for (int i = 0; i < 100; i += 2)
+    {
+      res += a[b[i + 1]];
+      res += a[b[i]];
+    }
+  return res;
+}
+
+long g3 ()
+{
+  long res = 0;
+  for (int i = 0; i < 100; i += 2)
+    {
+      res += a[b[i]];
+      res += a[b[i + 1]];
+    }
+  return res;
+}
+
+/* { dg-final { scan-tree-dump-times {add new stmt[^\n]*GATHER_LOAD} 3 "vect" { target aarch64*-*-* } } } */
+/* { dg-final { scan-tree-dump-not {add new stmt[^\n]*VEC_PERM_EXPR} "vect" { target aarch64*-*-* } } } */
diff --git a/gcc/tree-vect-data-refs.cc b/gcc/tree-vect-data-refs.cc
index b279a82551eb..e03b50498d16 100644
--- a/gcc/tree-vect-data-refs.cc
+++ b/gcc/tree-vect-data-refs.cc
@@ -4151,6 +4151,7 @@ vect_check_gather_scatter (stmt_vec_info stmt_info, loop_vec_info loop_vinfo,
 	  /* Don't include the conversion if the target is happy with
 	     the current offset type.  */
 	  if (use_ifn_p
+	      && TREE_CODE (off) == SSA_NAME
 	      && !POINTER_TYPE_P (TREE_TYPE (off))
 	      && vect_gather_scatter_fn_p (loop_vinfo, DR_IS_READ (dr),
 					   masked_p, vectype, memory_type,
-- 
2.47.2