From f8ea7cb08dc13e3cb78bb3b4017c556c9838263b Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Tue, 21 Jan 2014 20:12:06 +0100
Subject: [PATCH] re PR target/59003 (profiledbootstrap miscompiles gcc during
 stagefeedback --with-tune=amdfam10)

	PR target/59003
	* config/i386/i386.c (expand_small_movmem_or_setmem): If mode is
	smaller than size, perform several stores or loads and stores
	at dst + count - size to store or copy all of size bytes, rather
	than just last modesize bytes.

	* gcc.dg/tree-prof/pr59003.c: New test.

From-SVN: r206896
---
 gcc/ChangeLog                            |  8 +++++++
 gcc/config/i386/i386.c                   | 20 +++++++++++-----
 gcc/testsuite/ChangeLog                  |  3 +++
 gcc/testsuite/gcc.dg/tree-prof/pr59003.c | 29 ++++++++++++++++++++++++
 4 files changed, 54 insertions(+), 6 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-prof/pr59003.c

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a571495fb3a..9efc19abde3 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2014-01-21  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/59003
+	* config/i386/i386.c (expand_small_movmem_or_setmem): If mode is
+	smaller than size, perform several stores or loads and stores
+	at dst + count - size to store or copy all of size bytes, rather
+	than just last modesize bytes.
+
 2014-01-20  DJ Delorie  <dj@redhat.com>
 
 	* config/rl78/rl78.c (rl78_propogate_register_origins): Verify
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 1a4d5683e34..4629053af79 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -23397,16 +23397,24 @@ expand_small_movmem_or_setmem (rtx destmem, rtx srcmem,
     }
 
   destmem = offset_address (destmem, count, 1);
-  destmem = offset_address (destmem, GEN_INT (-size - GET_MODE_SIZE (mode)),
+  destmem = offset_address (destmem, GEN_INT (-2 * size),
 			    GET_MODE_SIZE (mode));
-  if (issetmem)
-    emit_move_insn (destmem, gen_lowpart (mode, value));
-  else
+  if (!issetmem)
     {
       srcmem = offset_address (srcmem, count, 1);
-      srcmem = offset_address (srcmem, GEN_INT (-size - GET_MODE_SIZE (mode)),
+      srcmem = offset_address (srcmem, GEN_INT (-2 * size),
 			       GET_MODE_SIZE (mode));
-      emit_move_insn (destmem, srcmem);
+    }
+  for (n = 0; n * GET_MODE_SIZE (mode) < size; n++)
+    {
+      if (issetmem)
+	emit_move_insn (destmem, gen_lowpart (mode, value));
+      else
+	{
+	  emit_move_insn (destmem, srcmem);
+	  srcmem = offset_address (srcmem, modesize, GET_MODE_SIZE (mode));
+	}
+      destmem = offset_address (destmem, modesize, GET_MODE_SIZE (mode));
     }
   emit_jump_insn (gen_jump (done_label));
   emit_barrier ();
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index addd796ff01..f7f6f88e26a 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,8 @@
 2014-01-21  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/59003
+	* gcc.dg/tree-prof/pr59003.c: New test.
+
 	PR middle-end/59860
 	* gcc.dg/strlenopt-4.c: Expect the same counts on s390*-* as on all
 	other targets.
diff --git a/gcc/testsuite/gcc.dg/tree-prof/pr59003.c b/gcc/testsuite/gcc.dg/tree-prof/pr59003.c
new file mode 100644
index 00000000000..b4ca9ea856e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-prof/pr59003.c
@@ -0,0 +1,29 @@
+/* PR target/59003 */
+/* { dg-options "-O2" } */
+/* { dg-options "-O2 -mtune=amdfam10" { target i?86-*-* x86_64-*-* } } */
+
+__attribute__((noinline, noclone)) void *
+foo (void *p, unsigned int q)
+{
+  return __builtin_memset (p, 0, q * 4UL);
+}
+
+char buf[128] __attribute__((aligned (32)));
+
+int
+main ()
+{
+  int i;
+  for (i = 0; i < 100000; i++)
+    foo (buf + 4, 1 + (i & 1));
+  for (i = 0; i < 128; i++)
+    {
+      buf[i] = 'X';
+      asm volatile ("" : : : "memory");
+    }
+  foo (buf + 32, 7);
+  for (i = 0; i < 128; i++)
+    if (buf[i] != ((i < 32 || i >= 32 + 28) ? 'X' : 0))
+      __builtin_abort ();
+  return 0;
+}