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

2 files changed, 244 insertions, 0 deletions

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;
+}