Recognize shuffle patterns for REV instructions on AArch64, rewrite intrinsics.

        * config/aarch64/aarch64-simd.md (aarch64_rev<REVERSE:rev-op><mode>):
        New pattern.
        * config/aarch64/aarch64.c (aarch64_evpc_rev): New function.
        (aarch64_expand_vec_perm_const_1): Add call to aarch64_evpc_rev.
        * config/aarch64/iterators.md (REVERSE): New iterator.
        (UNSPEC_REV64, UNSPEC_REV32, UNSPEC_REV16): New enum elements.
        (rev_op): New int_attribute.
        * config/aarch64/arm_neon.h (vrev16_p8, vrev16_s8, vrev16_u8,
        vrev16q_p8, vrev16q_s8, vrev16q_u8, vrev32_p8, vrev32_p16, vrev32_s8,
        vrev32_s16, vrev32_u8, vrev32_u16, vrev32q_p8, vrev32q_p16, vrev32q_s8,
        vrev32q_s16, vrev32q_u8, vrev32q_u16, vrev64_f32, vrev64_p8,
        vrev64_p16, vrev64_s8, vrev64_s16, vrev64_s32, vrev64_u8, vrev64_u16,
        vrev64_u32, vrev64q_f32, vrev64q_p8, vrev64q_p16, vrev64q_s8,
        vrev64q_s16, vrev64q_s32, vrev64q_u8, vrev64q_u16, vrev64q_u32):
        Replace temporary __asm__ with __builtin_shuffle.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@211174 138bc75d-0d04-0410-961f-82ee72b054a4

5 files changed, 341 insertions, 397 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index dc414dd26e7..1f09b046bb5 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,21 @@
+2014-06-03  Alan Lawrence  <alan.lawrence@arm.com>
+
+	* config/aarch64/aarch64-simd.md (aarch64_rev<REVERSE:rev-op><mode>):
+	New pattern.
+	* config/aarch64/aarch64.c (aarch64_evpc_rev): New function.
+	(aarch64_expand_vec_perm_const_1): Add call to aarch64_evpc_rev.
+	* config/aarch64/iterators.md (REVERSE): New iterator.
+	(UNSPEC_REV64, UNSPEC_REV32, UNSPEC_REV16): New enum elements.
+	(rev_op): New int_attribute.
+	* config/aarch64/arm_neon.h (vrev16_p8, vrev16_s8, vrev16_u8,
+	vrev16q_p8, vrev16q_s8, vrev16q_u8, vrev32_p8, vrev32_p16, vrev32_s8,
+	vrev32_s16, vrev32_u8, vrev32_u16, vrev32q_p8, vrev32q_p16, vrev32q_s8,
+	vrev32q_s16, vrev32q_u8, vrev32q_u16, vrev64_f32, vrev64_p8,
+	vrev64_p16, vrev64_s8, vrev64_s16, vrev64_s32, vrev64_u8, vrev64_u16,
+	vrev64_u32, vrev64q_f32, vrev64q_p8, vrev64q_p16, vrev64q_s8,
+	vrev64q_s16, vrev64q_s32, vrev64q_u8, vrev64q_u16, vrev64q_u32):
+	Replace temporary __asm__ with __builtin_shuffle.
+
 2014-06-03  Andrew Bennett  <andrew.bennett@imgtec.com> 
 
 	* config/mips/mips-cpus.def: Add mips32r3, mips32r5, mips64r3 and
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index c239677a581..a1f0ff53eb3 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -4196,6 +4196,15 @@
 }
 )
 
+(define_insn "aarch64_rev<REVERSE:rev_op><mode>"
+  [(set (match_operand:VALL 0 "register_operand" "=w")
+	(unspec:VALL [(match_operand:VALL 1 "register_operand" "w")]
+                    REVERSE))]
+  "TARGET_SIMD"
+  "rev<REVERSE:rev_op>\\t%0.<Vtype>, %1.<Vtype>"
+  [(set_attr "type" "neon_rev<q>")]
+)
+
 (define_insn "aarch64_st2<mode>_dreg"
   [(set (match_operand:TI 0 "aarch64_simd_struct_operand" "=Utv")
 	(unspec:TI [(match_operand:OI 1 "register_operand" "w")
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index bb33304a2fd..65ef84a8ffa 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -9058,6 +9058,80 @@ aarch64_evpc_ext (struct expand_vec_perm_d *d)
   return true;
 }
 
+/* Recognize patterns for the REV insns.  */
+
+static bool
+aarch64_evpc_rev (struct expand_vec_perm_d *d)
+{
+  unsigned int i, j, diff, nelt = d->nelt;
+  rtx (*gen) (rtx, rtx);
+
+  if (!d->one_vector_p)
+    return false;
+
+  diff = d->perm[0];
+  switch (diff)
+    {
+    case 7:
+      switch (d->vmode)
+	{
+	case V16QImode: gen = gen_aarch64_rev64v16qi; break;
+	case V8QImode: gen = gen_aarch64_rev64v8qi;  break;
+	default:
+	  return false;
+	}
+      break;
+    case 3:
+      switch (d->vmode)
+	{
+	case V16QImode: gen = gen_aarch64_rev32v16qi; break;
+	case V8QImode: gen = gen_aarch64_rev32v8qi;  break;
+	case V8HImode: gen = gen_aarch64_rev64v8hi;  break;
+	case V4HImode: gen = gen_aarch64_rev64v4hi;  break;
+	default:
+	  return false;
+	}
+      break;
+    case 1:
+      switch (d->vmode)
+	{
+	case V16QImode: gen = gen_aarch64_rev16v16qi; break;
+	case V8QImode: gen = gen_aarch64_rev16v8qi;  break;
+	case V8HImode: gen = gen_aarch64_rev32v8hi;  break;
+	case V4HImode: gen = gen_aarch64_rev32v4hi;  break;
+	case V4SImode: gen = gen_aarch64_rev64v4si;  break;
+	case V2SImode: gen = gen_aarch64_rev64v2si;  break;
+	case V4SFmode: gen = gen_aarch64_rev64v4sf;  break;
+	case V2SFmode: gen = gen_aarch64_rev64v2sf;  break;
+	default:
+	  return false;
+	}
+      break;
+    default:
+      return false;
+    }
+
+  for (i = 0; i < nelt ; i += diff + 1)
+    for (j = 0; j <= diff; j += 1)
+      {
+	/* This is guaranteed to be true as the value of diff
+	   is 7, 3, 1 and we should have enough elements in the
+	   queue to generate this.  Getting a vector mask with a
+	   value of diff other than these values implies that
+	   something is wrong by the time we get here.  */
+	gcc_assert (i + j < nelt);
+	if (d->perm[i + j] != i + diff - j)
+	  return false;
+      }
+
+  /* Success! */
+  if (d->testing_p)
+    return true;
+
+  emit_insn (gen (d->target, d->op0));
+  return true;
+}
+
 static bool
 aarch64_evpc_dup (struct expand_vec_perm_d *d)
 {
@@ -9162,7 +9236,9 @@ aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
 
   if (TARGET_SIMD)
     {
-      if (aarch64_evpc_ext (d))
+      if (aarch64_evpc_rev (d))
+	return true;
+      else if (aarch64_evpc_ext (d))
 	return true;
       else if (aarch64_evpc_zip (d))
 	return true;
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index c4b5731996c..60b28447002 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -10563,402 +10563,6 @@ vrecpeq_u32 (uint32x4_t a)
   return result;
 }
 
-__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
-vrev16_p8 (poly8x8_t a)
-{
-  poly8x8_t result;
-  __asm__ ("rev16 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vrev16_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("rev16 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vrev16_u8 (uint8x8_t a)
-{
-  uint8x8_t result;
-  __asm__ ("rev16 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
-vrev16q_p8 (poly8x16_t a)
-{
-  poly8x16_t result;
-  __asm__ ("rev16 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vrev16q_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("rev16 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vrev16q_u8 (uint8x16_t a)
-{
-  uint8x16_t result;
-  __asm__ ("rev16 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
-vrev32_p8 (poly8x8_t a)
-{
-  poly8x8_t result;
-  __asm__ ("rev32 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
-vrev32_p16 (poly16x4_t a)
-{
-  poly16x4_t result;
-  __asm__ ("rev32 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vrev32_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("rev32 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
-vrev32_s16 (int16x4_t a)
-{
-  int16x4_t result;
-  __asm__ ("rev32 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vrev32_u8 (uint8x8_t a)
-{
-  uint8x8_t result;
-  __asm__ ("rev32 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
-vrev32_u16 (uint16x4_t a)
-{
-  uint16x4_t result;
-  __asm__ ("rev32 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
-vrev32q_p8 (poly8x16_t a)
-{
-  poly8x16_t result;
-  __asm__ ("rev32 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
-vrev32q_p16 (poly16x8_t a)
-{
-  poly16x8_t result;
-  __asm__ ("rev32 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vrev32q_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("rev32 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
-vrev32q_s16 (int16x8_t a)
-{
-  int16x8_t result;
-  __asm__ ("rev32 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vrev32q_u8 (uint8x16_t a)
-{
-  uint8x16_t result;
-  __asm__ ("rev32 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
-vrev32q_u16 (uint16x8_t a)
-{
-  uint16x8_t result;
-  __asm__ ("rev32 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
-vrev64_f32 (float32x2_t a)
-{
-  float32x2_t result;
-  __asm__ ("rev64 %0.2s,%1.2s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
-vrev64_p8 (poly8x8_t a)
-{
-  poly8x8_t result;
-  __asm__ ("rev64 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
-vrev64_p16 (poly16x4_t a)
-{
-  poly16x4_t result;
-  __asm__ ("rev64 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vrev64_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("rev64 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
-vrev64_s16 (int16x4_t a)
-{
-  int16x4_t result;
-  __asm__ ("rev64 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
-vrev64_s32 (int32x2_t a)
-{
-  int32x2_t result;
-  __asm__ ("rev64 %0.2s,%1.2s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vrev64_u8 (uint8x8_t a)
-{
-  uint8x8_t result;
-  __asm__ ("rev64 %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
-vrev64_u16 (uint16x4_t a)
-{
-  uint16x4_t result;
-  __asm__ ("rev64 %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vrev64_u32 (uint32x2_t a)
-{
-  uint32x2_t result;
-  __asm__ ("rev64 %0.2s,%1.2s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
-vrev64q_f32 (float32x4_t a)
-{
-  float32x4_t result;
-  __asm__ ("rev64 %0.4s,%1.4s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
-vrev64q_p8 (poly8x16_t a)
-{
-  poly8x16_t result;
-  __asm__ ("rev64 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
-vrev64q_p16 (poly16x8_t a)
-{
-  poly16x8_t result;
-  __asm__ ("rev64 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vrev64q_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("rev64 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
-vrev64q_s16 (int16x8_t a)
-{
-  int16x8_t result;
-  __asm__ ("rev64 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
-vrev64q_s32 (int32x4_t a)
-{
-  int32x4_t result;
-  __asm__ ("rev64 %0.4s,%1.4s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vrev64q_u8 (uint8x16_t a)
-{
-  uint8x16_t result;
-  __asm__ ("rev64 %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
-vrev64q_u16 (uint16x8_t a)
-{
-  uint16x8_t result;
-  __asm__ ("rev64 %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vrev64q_u32 (uint32x4_t a)
-{
-  uint32x4_t result;
-  __asm__ ("rev64 %0.4s,%1.4s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 #define vrshrn_high_n_s16(a, b, c)                                      \
   __extension__                                                         \
     ({                                                                  \
@@ -21414,6 +21018,234 @@ vrecpxd_f64 (float64_t __a)
   return __builtin_aarch64_frecpxdf (__a);
 }
 
+
+/* vrev  */
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vrev16_p8 (poly8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vrev16_s8 (int8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vrev16_u8 (uint8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vrev16q_p8 (poly8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vrev16q_s8 (int8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vrev16q_u8 (uint8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 });
+}
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vrev32_p8 (poly8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
+vrev32_p16 (poly16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vrev32_s8 (int8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vrev32_s16 (int16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vrev32_u8 (uint8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vrev32_u16 (uint16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 1, 0, 3, 2 });
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vrev32q_p8 (poly8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
+}
+
+__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
+vrev32q_p16 (poly16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vrev32q_s8 (int8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vrev32q_s16 (int16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vrev32q_u8 (uint8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 });
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vrev32q_u16 (uint16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 });
+}
+
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vrev64_f32 (float32x2_t a)
+{
+  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
+}
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vrev64_p8 (poly8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
+}
+
+__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
+vrev64_p16 (poly16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vrev64_s8 (int8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vrev64_s16 (int16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
+}
+
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vrev64_s32 (int32x2_t a)
+{
+  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vrev64_u8 (uint8x8_t a)
+{
+  return __builtin_shuffle (a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 });
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vrev64_u16 (uint16x4_t a)
+{
+  return __builtin_shuffle (a, (uint16x4_t) { 3, 2, 1, 0 });
+}
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vrev64_u32 (uint32x2_t a)
+{
+  return __builtin_shuffle (a, (uint32x2_t) { 1, 0 });
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vrev64q_f32 (float32x4_t a)
+{
+  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vrev64q_p8 (poly8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
+}
+
+__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
+vrev64q_p16 (poly16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vrev64q_s8 (int8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vrev64q_s16 (int16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vrev64q_s32 (int32x4_t a)
+{
+  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vrev64q_u8 (uint8x16_t a)
+{
+  return __builtin_shuffle (a,
+      (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 });
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vrev64q_u16 (uint16x8_t a)
+{
+  return __builtin_shuffle (a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 });
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vrev64q_u32 (uint32x4_t a)
+{
+  return __builtin_shuffle (a, (uint32x4_t) { 1, 0, 3, 2 });
+}
+
 /* vrnd  */
 
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 05611f4cd61..05c4f7ea543 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -271,6 +271,9 @@
     UNSPEC_TRN1		; Used in vector permute patterns.
     UNSPEC_TRN2		; Used in vector permute patterns.
     UNSPEC_EXT		; Used in aarch64-simd.md.
+    UNSPEC_REV64	; Used in vector reverse patterns (permute).
+    UNSPEC_REV32	; Used in vector reverse patterns (permute).
+    UNSPEC_REV16	; Used in vector reverse patterns (permute).
     UNSPEC_AESE		; Used in aarch64-simd.md.
     UNSPEC_AESD         ; Used in aarch64-simd.md.
     UNSPEC_AESMC        ; Used in aarch64-simd.md.
@@ -896,6 +899,8 @@
 			      UNSPEC_TRN1 UNSPEC_TRN2
 			      UNSPEC_UZP1 UNSPEC_UZP2])
 
+(define_int_iterator REVERSE [UNSPEC_REV64 UNSPEC_REV32 UNSPEC_REV16])
+
 (define_int_iterator FRINT [UNSPEC_FRINTZ UNSPEC_FRINTP UNSPEC_FRINTM
 			     UNSPEC_FRINTN UNSPEC_FRINTI UNSPEC_FRINTX
 			     UNSPEC_FRINTA])
@@ -1023,6 +1028,10 @@
 			    (UNSPEC_TRN1 "trn") (UNSPEC_TRN2 "trn")
 			    (UNSPEC_UZP1 "uzp") (UNSPEC_UZP2 "uzp")])
 
+; op code for REV instructions (size within which elements are reversed).
+(define_int_attr rev_op [(UNSPEC_REV64 "64") (UNSPEC_REV32 "32")
+			 (UNSPEC_REV16 "16")])
+
 (define_int_attr perm_hilo [(UNSPEC_ZIP1 "1") (UNSPEC_ZIP2 "2")
 			    (UNSPEC_TRN1 "1") (UNSPEC_TRN2 "2")
 			    (UNSPEC_UZP1 "1") (UNSPEC_UZP2 "2")])