From afb119beca72d64c166127445ca6883358e24174 Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Fri, 10 May 2013 07:52:25 +0000
Subject: [PATCH] tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Do
 not disable peeling when we version for aliasing.

2013-05-10  Richard Biener  <rguenther@suse.de>

	* tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Do not
	disable peeling when we version for aliasing.
	(vector_alignment_reachable_p): Honor explicit user alignment.
	(vect_supportable_dr_alignment): Likewise.
	* tree-vect-loop-manip.c (vect_can_advance_ivs_p): Use
	STMT_VINFO_LOOP_PHI_EVOLUTION_PART instead of recomputing it.
	* tree-vect-loop.c (vect_transform_loop): First apply versioning,
	then peeling to arrange for the cost-model check to come first.

	* gcc.target/i386/avx256-unaligned-load-2.c: Make well-defined.
	* gcc.target/i386/l_fma_double_1.c: Adjust.
	* gcc.target/i386/l_fma_double_2.c: Likewise.
	* gcc.target/i386/l_fma_double_3.c: Likewise.
	* gcc.target/i386/l_fma_double_4.c: Likewise.
	* gcc.target/i386/l_fma_double_5.c: Likewise.
	* gcc.target/i386/l_fma_double_6.c: Likewise.
	* gcc.target/i386/l_fma_float_1.c: Likewise.
	* gcc.target/i386/l_fma_float_2.c: Likewise.
	* gcc.target/i386/l_fma_float_3.c: Likewise.
	* gcc.target/i386/l_fma_float_4.c: Likewise.
	* gcc.target/i386/l_fma_float_5.c: Likewise.
	* gcc.target/i386/l_fma_float_6.c: Likewise.

From-SVN: r198767
---
 gcc/ChangeLog                                 | 11 +++++++
 gcc/testsuite/ChangeLog                       | 16 ++++++++++
 .../gcc.target/i386/avx256-unaligned-load-2.c | 21 +++-----------
 .../gcc.target/i386/l_fma_double_1.c          | 23 ++++++++-------
 .../gcc.target/i386/l_fma_double_2.c          | 11 +++----
 .../gcc.target/i386/l_fma_double_3.c          | 23 ++++++++-------
 .../gcc.target/i386/l_fma_double_4.c          | 11 +++----
 .../gcc.target/i386/l_fma_double_5.c          | 11 +++----
 .../gcc.target/i386/l_fma_double_6.c          | 11 +++----
 gcc/testsuite/gcc.target/i386/l_fma_float_1.c | 20 ++++++-------
 gcc/testsuite/gcc.target/i386/l_fma_float_2.c |  8 ++---
 gcc/testsuite/gcc.target/i386/l_fma_float_3.c | 20 ++++++-------
 gcc/testsuite/gcc.target/i386/l_fma_float_4.c |  8 ++---
 gcc/testsuite/gcc.target/i386/l_fma_float_5.c |  8 ++---
 gcc/testsuite/gcc.target/i386/l_fma_float_6.c |  8 ++---
 gcc/tree-vect-data-refs.c                     | 29 ++++++++-----------
 gcc/tree-vect-loop-manip.c                    | 27 +++--------------
 gcc/tree-vect-loop.c                          | 17 ++++++-----
 18 files changed, 141 insertions(+), 142 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index b6101bad68d..c7d6db9a744 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,14 @@
+2013-05-10  Richard Biener  <rguenther@suse.de>
+
+	* tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Do not
+	disable peeling when we version for aliasing.
+	(vector_alignment_reachable_p): Honor explicit user alignment.
+	(vect_supportable_dr_alignment): Likewise.
+	* tree-vect-loop-manip.c (vect_can_advance_ivs_p): Use
+	STMT_VINFO_LOOP_PHI_EVOLUTION_PART instead of recomputing it.
+	* tree-vect-loop.c (vect_transform_loop): First apply versioning,
+	then peeling to arrange for the cost-model check to come first.
+
 2013-05-10  Alan Modra  <amodra@gmail.com>
 
 	* configure.ac (HAVE_AS_TLS): Swap powerpc64 and powerpc cases.
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 3ab939af5f5..7656de9b0ab 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,19 @@
+2013-05-10  Richard Biener  <rguenther@suse.de>
+
+	* gcc.target/i386/avx256-unaligned-load-2.c: Make well-defined.
+	* gcc.target/i386/l_fma_double_1.c: Adjust.
+	* gcc.target/i386/l_fma_double_2.c: Likewise.
+	* gcc.target/i386/l_fma_double_3.c: Likewise.
+	* gcc.target/i386/l_fma_double_4.c: Likewise.
+	* gcc.target/i386/l_fma_double_5.c: Likewise.
+	* gcc.target/i386/l_fma_double_6.c: Likewise.
+	* gcc.target/i386/l_fma_float_1.c: Likewise.
+	* gcc.target/i386/l_fma_float_2.c: Likewise.
+	* gcc.target/i386/l_fma_float_3.c: Likewise.
+	* gcc.target/i386/l_fma_float_4.c: Likewise.
+	* gcc.target/i386/l_fma_float_5.c: Likewise.
+	* gcc.target/i386/l_fma_float_6.c: Likewise.
+
 2013-05-08  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/51226
diff --git a/gcc/testsuite/gcc.target/i386/avx256-unaligned-load-2.c b/gcc/testsuite/gcc.target/i386/avx256-unaligned-load-2.c
index 2947d9eab3e..e3ec8542e01 100644
--- a/gcc/testsuite/gcc.target/i386/avx256-unaligned-load-2.c
+++ b/gcc/testsuite/gcc.target/i386/avx256-unaligned-load-2.c
@@ -1,26 +1,13 @@
 /* { dg-do compile { target { ! ia32 } } } */
 /* { dg-options "-O3 -dp -mavx -mavx256-split-unaligned-load" } */
 
-#define N 1024
-
-char **ep;
-char **fp;
-
 void
-avx_test (void)
+avx_test (char **cp, char **ep)
 {
   int i;
-  char **ap;
-  char **bp;
-  char **cp;
-
-  ap = ep;
-  bp = fp;
-  for (i = 128; i >= 0; i--)
-    {
-      *ap++ = *cp++;
-      *bp++ = 0;
-    }
+  char **ap = __builtin_assume_aligned (ep, 32);
+  for (i = 128; i > 0; i--)
+    *ap++ = *cp++;
 }
 
 /* { dg-final { scan-assembler-not "avx_loaddqu256" } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_1.c b/gcc/testsuite/gcc.target/i386/l_fma_double_1.c
index 270659359f4..b3ffcf2c00f 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_1.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_1.c
@@ -4,23 +4,24 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_1.h"
 
 /* { dg-final { scan-assembler-times "vfmadd132pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd231pd" 4  } } */
+/* { dg-final { scan-assembler-times "vfmadd213pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfmsub132pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmsub231pd" 4  } } */
+/* { dg-final { scan-assembler-times "vfmsub213pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd231pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub231pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmadd213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmsub213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmadd213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmsub213sd" 16  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 28  } } */
+/* { dg-final { scan-assembler-times "vfmadd213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfmsub213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmadd213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmsub213sd" 28 } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_2.c b/gcc/testsuite/gcc.target/i386/l_fma_double_2.c
index e8933e25d53..713b24b7c27 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_2.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_2.c
@@ -4,7 +4,8 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_2.h"
 
@@ -12,7 +13,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 56  } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 56 } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_3.c b/gcc/testsuite/gcc.target/i386/l_fma_double_3.c
index 00c756775c8..cbc6ef832aa 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_3.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_3.c
@@ -4,23 +4,24 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_3.h"
 
 /* { dg-final { scan-assembler-times "vfmadd132pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd231pd" 4  } } */
+/* { dg-final { scan-assembler-times "vfmadd213pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfmsub132pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmsub231pd" 4  } } */
+/* { dg-final { scan-assembler-times "vfmsub213pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd231pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub231pd" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmadd213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfmsub213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmadd213sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 16  } } */
-/* { dg-final { scan-assembler-times "vfnmsub213sd" 16  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfmadd213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfmsub213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmadd213sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 28 } } */
+/* { dg-final { scan-assembler-times "vfnmsub213sd" 28 } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_4.c b/gcc/testsuite/gcc.target/i386/l_fma_double_4.c
index 09970bdb5c6..d571aca1b01 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_4.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_4.c
@@ -4,7 +4,8 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_4.h"
 
@@ -12,7 +13,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 56 } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_5.c b/gcc/testsuite/gcc.target/i386/l_fma_double_5.c
index 2a1428e4d9c..56d86369bc3 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_5.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_5.c
@@ -4,7 +4,8 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_5.h"
 
@@ -12,7 +13,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 56  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 56  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 56  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_double_6.c b/gcc/testsuite/gcc.target/i386/l_fma_double_6.c
index 092032aa0b5..f22763d6f99 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_double_6.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_double_6.c
@@ -4,7 +4,8 @@
 /* Test that the compiler properly optimizes floating point multiply
    and add instructions into FMA3 instructions.  */
 
-#define TYPE double
+typedef double adouble __attribute__((aligned(sizeof (double))));
+#define TYPE adouble
 
 #include "l_fma_6.h"
 
@@ -12,7 +13,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132pd" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132pd" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132sd" 32 } } */
-/* { dg-final { scan-assembler-times "vfmsub132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132sd" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132sd" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132sd" 56 } } */
+/* { dg-final { scan-assembler-times "vfmsub132sd" 56  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132sd" 56  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132sd" 56  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_1.c b/gcc/testsuite/gcc.target/i386/l_fma_float_1.c
index 4bcd81de9da..b2f58ac2f95 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_1.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_1.c
@@ -9,18 +9,18 @@
 #include "l_fma_1.h"
 
 /* { dg-final { scan-assembler-times "vfmadd132ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd231ps" 4  } } */
+/* { dg-final { scan-assembler-times "vfmadd213ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfmsub132ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmsub231ps" 4  } } */
+/* { dg-final { scan-assembler-times "vfmsub213ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd231ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub231ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmadd213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub213ss" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfmadd213ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfmsub213ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfnmadd213ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 60 } } */
+/* { dg-final { scan-assembler-times "vfnmsub213ss" 60 } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_2.c b/gcc/testsuite/gcc.target/i386/l_fma_float_2.c
index 34b7fcb6dd5..6377585bffe 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_2.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_2.c
@@ -12,7 +12,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 64  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 120  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_3.c b/gcc/testsuite/gcc.target/i386/l_fma_float_3.c
index 6ff2c6eacd5..878babb31c5 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_3.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_3.c
@@ -9,18 +9,18 @@
 #include "l_fma_3.h"
 
 /* { dg-final { scan-assembler-times "vfmadd132ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd231ps" 4  } } */
+/* { dg-final { scan-assembler-times "vfmadd213ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfmsub132ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmsub231ps" 4  } } */
+/* { dg-final { scan-assembler-times "vfmsub213ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmadd231ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 4  } } */
 /* { dg-final { scan-assembler-times "vfnmsub231ps" 4  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmadd213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfmsub213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmadd213ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 32  } } */
-/* { dg-final { scan-assembler-times "vfnmsub213ss" 32  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfmadd213ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfmsub213ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfnmadd213ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 60  } } */
+/* { dg-final { scan-assembler-times "vfnmsub213ss" 60  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_4.c b/gcc/testsuite/gcc.target/i386/l_fma_float_4.c
index 39548bfa76b..bacb01e7f3f 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_4.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_4.c
@@ -12,7 +12,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 64  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 120  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_5.c b/gcc/testsuite/gcc.target/i386/l_fma_float_5.c
index 83d79512592..a32fc41d9f9 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_5.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_5.c
@@ -12,7 +12,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 64  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 120  } } */
diff --git a/gcc/testsuite/gcc.target/i386/l_fma_float_6.c b/gcc/testsuite/gcc.target/i386/l_fma_float_6.c
index 1eefc817c36..a7a74fb4222 100644
--- a/gcc/testsuite/gcc.target/i386/l_fma_float_6.c
+++ b/gcc/testsuite/gcc.target/i386/l_fma_float_6.c
@@ -12,7 +12,7 @@
 /* { dg-final { scan-assembler-times "vfmsub132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmadd132ps" 8  } } */
 /* { dg-final { scan-assembler-times "vfnmsub132ps" 8  } } */
-/* { dg-final { scan-assembler-times "vfmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfmsub132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmadd132ss" 64  } } */
-/* { dg-final { scan-assembler-times "vfnmsub132ss" 64  } } */
+/* { dg-final { scan-assembler-times "vfmadd132ss" 120 } } */
+/* { dg-final { scan-assembler-times "vfmsub132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ss" 120  } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ss" 120  } } */
diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index c1b5826ee12..bf0b510db44 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -1024,7 +1024,8 @@ vector_alignment_reachable_p (struct data_reference *dr)
       if (dump_enabled_p ())
 	dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, 
                          "Unknown misalignment, is_packed = %d",is_packed);
-      if (targetm.vectorize.vector_alignment_reachable (type, is_packed))
+      if ((TYPE_USER_ALIGN (type) && !is_packed)
+	  || targetm.vectorize.vector_alignment_reachable (type, is_packed))
 	return true;
       else
 	return false;
@@ -1323,7 +1324,6 @@ vect_enhance_data_refs_alignment (loop_vec_info loop_vinfo)
   bool stat;
   gimple stmt;
   stmt_vec_info stmt_info;
-  int vect_versioning_for_alias_required;
   unsigned int npeel = 0;
   bool all_misalignments_unknown = true;
   unsigned int vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
@@ -1510,15 +1510,8 @@ vect_enhance_data_refs_alignment (loop_vec_info loop_vinfo)
         }
     }
 
-  vect_versioning_for_alias_required
-    = LOOP_REQUIRES_VERSIONING_FOR_ALIAS (loop_vinfo);
-
-  /* Temporarily, if versioning for alias is required, we disable peeling
-     until we support peeling and versioning.  Often peeling for alignment
-     will require peeling for loop-bound, which in turn requires that we
-     know how to adjust the loop ivs after the loop.  */
-  if (vect_versioning_for_alias_required
-      || !vect_can_advance_ivs_p (loop_vinfo)
+  /* Check if we can possibly peel the loop.  */
+  if (!vect_can_advance_ivs_p (loop_vinfo)
       || !slpeel_can_duplicate_loop_p (loop, single_exit (loop)))
     do_peeling = false;
 
@@ -4722,9 +4715,10 @@ vect_supportable_dr_alignment (struct data_reference *dr,
       if (!known_alignment_for_access_p (dr))
 	is_packed = not_size_aligned (DR_REF (dr));
 
-      if (targetm.vectorize.
-	  support_vector_misalignment (mode, type,
-				       DR_MISALIGNMENT (dr), is_packed))
+      if ((TYPE_USER_ALIGN (type) && !is_packed)
+	  || targetm.vectorize.
+	       support_vector_misalignment (mode, type,
+					    DR_MISALIGNMENT (dr), is_packed))
 	/* Can't software pipeline the loads, but can at least do them.  */
 	return dr_unaligned_supported;
     }
@@ -4736,9 +4730,10 @@ vect_supportable_dr_alignment (struct data_reference *dr,
       if (!known_alignment_for_access_p (dr))
 	is_packed = not_size_aligned (DR_REF (dr));
 
-     if (targetm.vectorize.
-         support_vector_misalignment (mode, type,
-				      DR_MISALIGNMENT (dr), is_packed))
+     if ((TYPE_USER_ALIGN (type) && !is_packed)
+	 || targetm.vectorize.
+	      support_vector_misalignment (mode, type,
+					   DR_MISALIGNMENT (dr), is_packed))
        return dr_unaligned_supported;
     }
 
diff --git a/gcc/tree-vect-loop-manip.c b/gcc/tree-vect-loop-manip.c
index bff5c22130e..82e724f1d9c 100644
--- a/gcc/tree-vect-loop-manip.c
+++ b/gcc/tree-vect-loop-manip.c
@@ -1555,7 +1555,6 @@ vect_can_advance_ivs_p (loop_vec_info loop_vinfo)
     dump_printf_loc (MSG_NOTE, vect_location, "vect_can_advance_ivs_p:");
   for (gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next (&gsi))
     {
-      tree access_fn = NULL;
       tree evolution_part;
 
       phi = gsi_stmt (gsi);
@@ -1588,31 +1587,13 @@ vect_can_advance_ivs_p (loop_vec_info loop_vinfo)
 
       /* Analyze the evolution function.  */
 
-      access_fn = instantiate_parameters
-	(loop, analyze_scalar_evolution (loop, PHI_RESULT (phi)));
-
-      if (!access_fn)
-	{
-	  if (dump_enabled_p ())
-	    dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
-                             "No Access function.");
-	  return false;
-	}
-
-      STRIP_NOPS (access_fn);
-      if (dump_enabled_p ())
-        {
-	  dump_printf_loc (MSG_NOTE, vect_location,
-                           "Access function of PHI: ");
-	  dump_generic_expr (MSG_NOTE, TDF_SLIM, access_fn);
-        }
-
-      evolution_part = evolution_part_in_loop_num (access_fn, loop->num);
-
+      evolution_part
+	= STMT_VINFO_LOOP_PHI_EVOLUTION_PART (vinfo_for_stmt (phi));
       if (evolution_part == NULL_TREE)
         {
 	  if (dump_enabled_p ())
-	    dump_printf (MSG_MISSED_OPTIMIZATION, "No evolution.");
+	    dump_printf (MSG_MISSED_OPTIMIZATION,
+			 "No access function or evolution.");
 	  return false;
         }
 
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 40eccea5500..0fb2daed370 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -5499,6 +5499,16 @@ vect_transform_loop (loop_vec_info loop_vinfo)
       check_profitability = true;
     }
 
+  /* Version the loop first, if required, so the profitability check
+     comes first.  */
+
+  if (LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT (loop_vinfo)
+      || LOOP_REQUIRES_VERSIONING_FOR_ALIAS (loop_vinfo))
+    {
+      vect_loop_versioning (loop_vinfo, th, check_profitability);
+      check_profitability = false;
+    }
+
   /* Peel the loop if there are data refs with unknown alignment.
      Only one data ref with unknown store is allowed.  */
 
@@ -5508,13 +5518,6 @@ vect_transform_loop (loop_vec_info loop_vinfo)
       check_profitability = false;
     }
 
-  if (LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT (loop_vinfo)
-      || LOOP_REQUIRES_VERSIONING_FOR_ALIAS (loop_vinfo))
-    {
-      vect_loop_versioning (loop_vinfo, th, check_profitability);
-      check_profitability = false;
-    }
-
   /* If the loop has a symbolic number of iterations 'n' (i.e. it's not a
      compile time constant), or it is a constant that doesn't divide by the
      vectorization factor, then an epilog loop needs to be created.