GIMPLE store merging pass

2016-10-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>

	PR middle-end/22141
	* Makefile.in (OBJS): Add gimple-ssa-store-merging.o.
	* common.opt (fstore-merging): New Optimization option.
	* opts.c (default_options_table): Add entry for
	OPT_ftree_store_merging.
	* fold-const.h (can_native_encode_type_p): Declare prototype.
	* fold-const.c (can_native_encode_type_p): Define.
	* params.def (PARAM_STORE_MERGING_ALLOW_UNALIGNED): Define.
	(PARAM_MAX_STORES_TO_MERGE): Likewise.
	* timevar.def (TV_GIMPLE_STORE_MERGING): New timevar.
	* passes.def: Insert pass_tree_store_merging.
	* tree-pass.h (make_pass_store_merging): Declare extern
	prototype.
	* gimple-ssa-store-merging.c: New file.
	* doc/invoke.texi (Optimization Options): Document
	-fstore-merging.
	(--param documentation): Document store-merging-allow-unaligned
	and max-stores-to-merge.

2016-10-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
            Jakub Jelinek  <jakub@redhat.com>
            Andrew Pinski  <pinskia@gmail.com>

	PR middle-end/22141
	PR rtl-optimization/23684
	* gcc.c-torture/execute/pr22141-1.c: New test.
	* gcc.c-torture/execute/pr22141-2.c: Likewise.
	* gcc.target/aarch64/ldp_stp_1.c: Adjust for -fstore-merging.
	* gcc.target/aarch64/ldp_stp_4.c: Likewise.
	* gcc.dg/store_merging_1.c: New test.
	* gcc.dg/store_merging_2.c: Likewise.
	* gcc.dg/store_merging_3.c: Likewise.
	* gcc.dg/store_merging_4.c: Likewise.
	* gcc.dg/store_merging_5.c: Likewise.
	* gcc.dg/store_merging_6.c: Likewise.
	* gcc.dg/store_merging_7.c: Likewise.
	* gcc.target/i386/pr22141.c: Likewise.
	* gcc.target/i386/pr34012.c: Add -fno-store-merging to dg-options.
	* g++.dg/init/new17.C: Likewise.



Co-Authored-By: Andrew Pinski <pinskia@gmail.com>
Co-Authored-By: Jakub Jelinek <jakub@redhat.com>

From-SVN: r241649

15 files changed, 711 insertions, 32 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index b4d7ec0..3a4041d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,24 @@
+2016-10-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+            Jakub Jelinek  <jakub@redhat.com>
+            Andrew Pinski  <pinskia@gmail.com>
+
+	PR middle-end/22141
+	PR rtl-optimization/23684
+	* gcc.c-torture/execute/pr22141-1.c: New test.
+	* gcc.c-torture/execute/pr22141-2.c: Likewise.
+	* gcc.target/aarch64/ldp_stp_1.c: Adjust for -fstore-merging.
+	* gcc.target/aarch64/ldp_stp_4.c: Likewise.
+	* gcc.dg/store_merging_1.c: New test.
+	* gcc.dg/store_merging_2.c: Likewise.
+	* gcc.dg/store_merging_3.c: Likewise.
+	* gcc.dg/store_merging_4.c: Likewise.
+	* gcc.dg/store_merging_5.c: Likewise.
+	* gcc.dg/store_merging_6.c: Likewise.
+	* gcc.dg/store_merging_7.c: Likewise.
+	* gcc.target/i386/pr22141.c: Likewise.
+	* gcc.target/i386/pr34012.c: Add -fno-store-merging to dg-options.
+	* g++.dg/init/new17.C: Likewise.
+
 2016-10-26  Will Schmidt <will_schmidt@vnet.ibm.com>
 
 	PR middle-end/72747
diff --git a/gcc/testsuite/g++.dg/init/new17.C b/gcc/testsuite/g++.dg/init/new17.C
index a7b1659..f6a3231 100644
--- a/gcc/testsuite/g++.dg/init/new17.C
+++ b/gcc/testsuite/g++.dg/init/new17.C
@@ -1,5 +1,5 @@
 // { dg-do compile }
-// { dg-options "-O2 -fstrict-aliasing -fdump-tree-optimized" }
+// { dg-options "-O2 -fstrict-aliasing -fno-store-merging -fdump-tree-optimized" }
 
 // Test that placement new does not introduce an unnecessary memory
 // barrier.
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr22141-1.c b/gcc/testsuite/gcc.c-torture/execute/pr22141-1.c
new file mode 100644
index 0000000..7c888b4
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr22141-1.c
@@ -0,0 +1,122 @@
+/* PR middle-end/22141 */
+
+extern void abort (void);
+
+struct S
+{
+  struct T
+    {
+      char a;
+      char b;
+      char c;
+      char d;
+    } t;
+} u;
+
+struct U
+{
+  struct S s[4];
+};
+
+void __attribute__((noinline))
+c1 (struct T *p)
+{
+  if (p->a != 1 || p->b != 2 || p->c != 3 || p->d != 4)
+    abort ();
+  __builtin_memset (p, 0xaa, sizeof (*p));
+}
+
+void __attribute__((noinline))
+c2 (struct S *p)
+{
+  c1 (&p->t);
+}
+
+void __attribute__((noinline))
+c3 (struct U *p)
+{
+  c2 (&p->s[2]);
+}
+
+void __attribute__((noinline))
+f1 (void)
+{
+  u = (struct S) { { 1, 2, 3, 4 } };
+}
+
+void __attribute__((noinline))
+f2 (void)
+{
+  u.t.a = 1;
+  u.t.b = 2;
+  u.t.c = 3;
+  u.t.d = 4;
+}
+
+void __attribute__((noinline))
+f3 (void)
+{
+  u.t.d = 4;
+  u.t.b = 2;
+  u.t.a = 1;
+  u.t.c = 3;
+}
+
+void __attribute__((noinline))
+f4 (void)
+{
+  struct S v;
+  v.t.a = 1;
+  v.t.b = 2;
+  v.t.c = 3;
+  v.t.d = 4;
+  c2 (&v);
+}
+
+void __attribute__((noinline))
+f5 (struct S *p)
+{
+  p->t.a = 1;
+  p->t.c = 3;
+  p->t.d = 4;
+  p->t.b = 2;
+}
+
+void __attribute__((noinline))
+f6 (void)
+{
+  struct U v;
+  v.s[2].t.a = 1;
+  v.s[2].t.b = 2;
+  v.s[2].t.c = 3;
+  v.s[2].t.d = 4;
+  c3 (&v);
+}
+
+void __attribute__((noinline))
+f7 (struct U *p)
+{
+  p->s[2].t.a = 1;
+  p->s[2].t.c = 3;
+  p->s[2].t.d = 4;
+  p->s[2].t.b = 2;
+}
+
+int
+main (void)
+{
+  struct U w;
+  f1 ();
+  c2 (&u);
+  f2 ();
+  c1 (&u.t);
+  f3 ();
+  c2 (&u);
+  f4 ();
+  f5 (&u);
+  c2 (&u);
+  f6 ();
+  f7 (&w);
+  c3 (&w);
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr22141-2.c b/gcc/testsuite/gcc.c-torture/execute/pr22141-2.c
new file mode 100644
index 0000000..cb9cc79
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr22141-2.c
@@ -0,0 +1,122 @@
+/* PR middle-end/22141 */
+
+extern void abort (void);
+
+struct S
+{
+  struct T
+    {
+      char a;
+      char b;
+      char c;
+      char d;
+    } t;
+} u __attribute__((aligned));
+
+struct U
+{
+  struct S s[4];
+};
+
+void __attribute__((noinline))
+c1 (struct T *p)
+{
+  if (p->a != 1 || p->b != 2 || p->c != 3 || p->d != 4)
+    abort ();
+  __builtin_memset (p, 0xaa, sizeof (*p));
+}
+
+void __attribute__((noinline))
+c2 (struct S *p)
+{
+  c1 (&p->t);
+}
+
+void __attribute__((noinline))
+c3 (struct U *p)
+{
+  c2 (&p->s[2]);
+}
+
+void __attribute__((noinline))
+f1 (void)
+{
+  u = (struct S) { { 1, 2, 3, 4 } };
+}
+
+void __attribute__((noinline))
+f2 (void)
+{
+  u.t.a = 1;
+  u.t.b = 2;
+  u.t.c = 3;
+  u.t.d = 4;
+}
+
+void __attribute__((noinline))
+f3 (void)
+{
+  u.t.d = 4;
+  u.t.b = 2;
+  u.t.a = 1;
+  u.t.c = 3;
+}
+
+void __attribute__((noinline))
+f4 (void)
+{
+  struct S v __attribute__((aligned));
+  v.t.a = 1;
+  v.t.b = 2;
+  v.t.c = 3;
+  v.t.d = 4;
+  c2 (&v);
+}
+
+void __attribute__((noinline))
+f5 (struct S *p)
+{
+  p->t.a = 1;
+  p->t.c = 3;
+  p->t.d = 4;
+  p->t.b = 2;
+}
+
+void __attribute__((noinline))
+f6 (void)
+{
+  struct U v __attribute__((aligned));
+  v.s[2].t.a = 1;
+  v.s[2].t.b = 2;
+  v.s[2].t.c = 3;
+  v.s[2].t.d = 4;
+  c3 (&v);
+}
+
+void __attribute__((noinline))
+f7 (struct U *p)
+{
+  p->s[2].t.a = 1;
+  p->s[2].t.c = 3;
+  p->s[2].t.d = 4;
+  p->s[2].t.b = 2;
+}
+
+int
+main (void)
+{
+  struct U w __attribute__((aligned));
+  f1 ();
+  c2 (&u);
+  f2 ();
+  c1 (&u.t);
+  f3 ();
+  c2 (&u);
+  f4 ();
+  f5 (&u);
+  c2 (&u);
+  f6 ();
+  f7 (&w);
+  c3 (&w);
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/store_merging_1.c b/gcc/testsuite/gcc.dg/store_merging_1.c
new file mode 100644
index 0000000..35f4d82
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_1.c
@@ -0,0 +1,35 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+struct bar {
+  int a;
+  char b;
+  char c;
+  char d;
+  char e;
+  char f;
+  char g;
+};
+
+void
+foo1 (struct bar *p)
+{
+  p->b = 0;
+  p->a = 0;
+  p->c = 0;
+  p->d = 0;
+  p->e = 0;
+}
+
+void
+foo2 (struct bar *p)
+{
+  p->b = 0;
+  p->a = 0;
+  p->c = 1;
+  p->d = 0;
+  p->e = 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 2 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_2.c b/gcc/testsuite/gcc.dg/store_merging_2.c
new file mode 100644
index 0000000..8e2acf3
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_2.c
@@ -0,0 +1,80 @@
+/* { dg-do run } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+struct bar
+{
+  int a;
+  unsigned char b;
+  unsigned char c;
+  short d;
+  unsigned char e;
+  unsigned char f;
+  unsigned char g;
+};
+
+__attribute__ ((noinline)) void
+foozero (struct bar *p)
+{
+  p->b = 0;
+  p->a = 0;
+  p->c = 0;
+  p->d = 0;
+  p->e = 0;
+  p->f = 0;
+  p->g = 0;
+}
+
+__attribute__ ((noinline)) void
+foo1 (struct bar *p)
+{
+  p->b = 1;
+  p->a = 2;
+  p->c = 3;
+  p->d = 4;
+  p->e = 5;
+  p->f = 0;
+  p->g = 0xff;
+}
+
+__attribute__ ((noinline)) void
+foo2 (struct bar *p, struct bar *p2)
+{
+  p->b = 0xff;
+  p2->b = 0xa;
+  p->a = 0xfffff;
+  p2->c = 0xc;
+  p->c = 0xff;
+  p2->d = 0xbf;
+  p->d = 0xfff;
+}
+
+int
+main (void)
+{
+  struct bar b1, b2;
+  foozero (&b1);
+  foozero (&b2);
+
+  foo1 (&b1);
+  if (b1.b != 1 || b1.a != 2 || b1.c != 3 || b1.d != 4 || b1.e != 5
+      || b1.f != 0 || b1.g != 0xff)
+    __builtin_abort ();
+
+  foozero (&b1);
+  /* Make sure writes to aliasing struct pointers preserve the
+     correct order.  */
+  foo2 (&b1, &b1);
+  if (b1.b != 0xa || b1.a != 0xfffff || b1.c != 0xff || b1.d != 0xfff)
+    __builtin_abort ();
+
+  foozero (&b1);
+  foo2 (&b1, &b2);
+  if (b1.a != 0xfffff || b1.b != 0xff || b1.c != 0xff || b1.d != 0xfff
+      || b2.b != 0xa || b2.c != 0xc || b2.d != 0xbf)
+    __builtin_abort ();
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 2 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_3.c b/gcc/testsuite/gcc.dg/store_merging_3.c
new file mode 100644
index 0000000..caf356d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_3.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging-details" } */
+
+/* Make sure stores to volatile addresses don't get combined with
+   other accesses.  */
+
+struct bar
+{
+  int a;
+  char b;
+  char c;
+  volatile short d;
+  char e;
+  char f;
+  char g;
+};
+
+void
+foozero (struct bar *p)
+{
+  p->b = 0xa;
+  p->a = 0xb;
+  p->c = 0xc;
+  p->d = 0;
+  p->e = 0xd;
+  p->f = 0xe;
+  p->g = 0xf;
+}
+
+/* { dg-final { scan-tree-dump "Volatile access terminates all chains" "store-merging" } } */
+/* { dg-final { scan-tree-dump-times "=\{v\} 0;" 1 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_4.c b/gcc/testsuite/gcc.dg/store_merging_4.c
new file mode 100644
index 0000000..a3d6769
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_4.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+/* Check that we can merge interleaving stores that are guaranteed
+   to be non-aliasing.  */
+
+struct bar
+{
+  int a;
+  char b;
+  char c;
+  short d;
+  char e;
+  char f;
+  char g;
+};
+
+void
+foozero (struct bar *restrict p, struct bar *restrict p2)
+{
+  p->b = 0xff;
+  p2->b = 0xa;
+  p->a = 0xfffff;
+  p2->a = 0xab;
+  p2->c = 0xc;
+  p->c = 0xff;
+  p2->d = 0xbf;
+  p->d = 0xfff;
+}
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 2 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_5.c b/gcc/testsuite/gcc.dg/store_merging_5.c
new file mode 100644
index 0000000..4ffe512
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_5.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+/* Make sure that non-aliasing non-constant interspersed stores do not
+   stop chains.  */
+
+struct bar {
+  int a;
+  char b;
+  char c;
+  char d;
+  char e;
+  char g;
+};
+
+void
+foo1 (struct bar *p, char tmp)
+{
+  p->a = 0;
+  p->b = 0;
+  p->g = tmp;
+  p->c = 0;
+  p->d = 0;
+  p->e = 0;
+}
+
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 1 "store-merging" } } */
+/* { dg-final { scan-tree-dump-times "MEM\\\[.*\\\]" 1 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_6.c b/gcc/testsuite/gcc.dg/store_merging_6.c
new file mode 100644
index 0000000..42b5c4f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_6.c
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+/* Check that we can widen accesses to bitfields.  */
+
+struct bar {
+  int a : 3;
+  unsigned char b : 4;
+  unsigned char c : 1;
+  char d;
+  char e;
+  char f;
+  char g;
+};
+
+__attribute__ ((noinline)) void
+foozero (struct bar *p)
+{
+  p->b = 0;
+  p->a = 0;
+  p->c = 0;
+  p->d = 0;
+  p->e = 0;
+  p->f = 0;
+  p->g = 0;
+}
+
+__attribute__ ((noinline)) void
+foo1 (struct bar *p)
+{
+  p->b = 3;
+  p->a = 2;
+  p->c = 1;
+  p->d = 4;
+  p->e = 5;
+}
+
+int
+main (void)
+{
+  struct bar p;
+  foozero (&p);
+  foo1 (&p);
+  if (p.a != 2 || p.b != 3 || p.c != 1 || p.d != 4 || p.e != 5
+      || p.f != 0 || p.g != 0)
+    __builtin_abort ();
+
+  return 0;
+}
+
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 2 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.dg/store_merging_7.c b/gcc/testsuite/gcc.dg/store_merging_7.c
new file mode 100644
index 0000000..4be352f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/store_merging_7.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target non_strict_align } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+
+/* Check that we can merge consecutive array members through the pointer.
+   PR rtl-optimization/23684.  */
+
+void
+foo (char *input)
+{
+  input = __builtin_assume_aligned (input, 8);
+  input[0] = 'H';
+  input[1] = 'e';
+  input[2] = 'l';
+  input[3] = 'l';
+  input[4] = 'o';
+  input[5] = ' ';
+  input[6] = 'w';
+  input[7] = 'o';
+  input[8] = 'r';
+  input[9] = 'l';
+  input[10] = 'd';
+  input[11] = '\0';
+}
+
+/* { dg-final { scan-tree-dump-times "Merging successful" 1 "store-merging" } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/ldp_stp_1.c b/gcc/testsuite/gcc.target/aarch64/ldp_stp_1.c
index f02e55f..9de4e77 100644
--- a/gcc/testsuite/gcc.target/aarch64/ldp_stp_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/ldp_stp_1.c
@@ -3,22 +3,22 @@
 int arr[4][4];
 
 void
-foo ()
+foo (int x, int y)
 {
-  arr[0][1] = 1;
-  arr[1][0] = -1;
-  arr[2][0] = 1;
-  arr[1][1] = -1;
-  arr[0][2] = 1;
-  arr[0][3] = -1;
-  arr[1][2] = 1;
-  arr[2][1] = -1;
-  arr[3][0] = 1;
-  arr[3][1] = -1;
-  arr[2][2] = 1;
-  arr[1][3] = -1;
-  arr[2][3] = 1;
-  arr[3][2] = -1;
+  arr[0][1] = x;
+  arr[1][0] = y;
+  arr[2][0] = x;
+  arr[1][1] = y;
+  arr[0][2] = x;
+  arr[0][3] = y;
+  arr[1][2] = x;
+  arr[2][1] = y;
+  arr[3][0] = x;
+  arr[3][1] = y;
+  arr[2][2] = x;
+  arr[1][3] = y;
+  arr[2][3] = x;
+  arr[3][2] = y;
 }
 
 /* { dg-final { scan-assembler-times "stp\tw\[0-9\]+, w\[0-9\]" 7 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/ldp_stp_4.c b/gcc/testsuite/gcc.target/aarch64/ldp_stp_4.c
index 40056b1..824f0d2 100644
--- a/gcc/testsuite/gcc.target/aarch64/ldp_stp_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/ldp_stp_4.c
@@ -3,22 +3,22 @@
 float arr[4][4];
 
 void
-foo ()
+foo (float x, float y)
 {
-  arr[0][1] = 1;
-  arr[1][0] = -1;
-  arr[2][0] = 1;
-  arr[1][1] = -1;
-  arr[0][2] = 1;
-  arr[0][3] = -1;
-  arr[1][2] = 1;
-  arr[2][1] = -1;
-  arr[3][0] = 1;
-  arr[3][1] = -1;
-  arr[2][2] = 1;
-  arr[1][3] = -1;
-  arr[2][3] = 1;
-  arr[3][2] = -1;
+  arr[0][1] = x;
+  arr[1][0] = y;
+  arr[2][0] = x;
+  arr[1][1] = y;
+  arr[0][2] = x;
+  arr[0][3] = y;
+  arr[1][2] = x;
+  arr[2][1] = y;
+  arr[3][0] = x;
+  arr[3][1] = y;
+  arr[2][2] = x;
+  arr[1][3] = y;
+  arr[2][3] = x;
+  arr[3][2] = y;
 }
 
 /* { dg-final { scan-assembler-times "stp\ts\[0-9\]+, s\[0-9\]" 7 } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr22141.c b/gcc/testsuite/gcc.target/i386/pr22141.c
new file mode 100644
index 0000000..036422e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr22141.c
@@ -0,0 +1,126 @@
+/* PR middle-end/22141 */
+/* { dg-do compile } */
+/* { dg-options "-Os" } */
+
+extern void abort (void);
+
+struct S
+{
+  struct T
+    {
+      char a;
+      char b;
+      char c;
+      char d;
+    } t;
+} u;
+
+struct U
+{
+  struct S s[4];
+};
+
+void __attribute__((noinline))
+c1 (struct T *p)
+{
+  if (p->a != 1 || p->b != 2 || p->c != 3 || p->d != 4)
+    abort ();
+  __builtin_memset (p, 0xaa, sizeof (*p));
+}
+
+void __attribute__((noinline))
+c2 (struct S *p)
+{
+  c1 (&p->t);
+}
+
+void __attribute__((noinline))
+c3 (struct U *p)
+{
+  c2 (&p->s[2]);
+}
+
+void __attribute__((noinline))
+f1 (void)
+{
+  u = (struct S) { { 1, 2, 3, 4 } };
+}
+
+void __attribute__((noinline))
+f2 (void)
+{
+  u.t.a = 1;
+  u.t.b = 2;
+  u.t.c = 3;
+  u.t.d = 4;
+}
+
+void __attribute__((noinline))
+f3 (void)
+{
+  u.t.d = 4;
+  u.t.b = 2;
+  u.t.a = 1;
+  u.t.c = 3;
+}
+
+void __attribute__((noinline))
+f4 (void)
+{
+  struct S v;
+  v.t.a = 1;
+  v.t.b = 2;
+  v.t.c = 3;
+  v.t.d = 4;
+  c2 (&v);
+}
+
+void __attribute__((noinline))
+f5 (struct S *p)
+{
+  p->t.a = 1;
+  p->t.c = 3;
+  p->t.d = 4;
+  p->t.b = 2;
+}
+
+void __attribute__((noinline))
+f6 (void)
+{
+  struct U v;
+  v.s[2].t.a = 1;
+  v.s[2].t.b = 2;
+  v.s[2].t.c = 3;
+  v.s[2].t.d = 4;
+  c3 (&v);
+}
+
+void __attribute__((noinline))
+f7 (struct U *p)
+{
+  p->s[2].t.a = 1;
+  p->s[2].t.c = 3;
+  p->s[2].t.d = 4;
+  p->s[2].t.b = 2;
+}
+
+int
+main (void)
+{
+  struct U w;
+  f1 ();
+  c2 (&u);
+  f2 ();
+  c1 (&u.t);
+  f3 ();
+  c2 (&u);
+  f4 ();
+  f5 (&u);
+  c2 (&u);
+  f6 ();
+  f7 (&w);
+  c3 (&w);
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times "67305985\|4030201" 7 } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr34012.c b/gcc/testsuite/gcc.target/i386/pr34012.c
index 00b1240..d0cffa05 100644
--- a/gcc/testsuite/gcc.target/i386/pr34012.c
+++ b/gcc/testsuite/gcc.target/i386/pr34012.c
@@ -1,7 +1,7 @@
 /* PR rtl-optimization/34012 */
 /* { dg-do compile } */
 /* { dg-require-effective-target lp64 } */
-/* { dg-options "-O2" } */
+/* { dg-options "-O2 -fno-store-merging" } */
 
 void bar (long int *);
 void