[PATCH AArch64] Add a builtin for rbit(q?)_p8; add intrinsics and tests.

gcc/:

	* config/aarch64/aarch64-simd.md (aarch64_rbit<mode>): New pattern.
	* config/aarch64/aarch64-simd-builtins.def (rbit): New builtin.
	* config/aarch64/arm_neon.h (vrbit_s8, vrbit_u8, vrbitq_s8, vrbitq_u8):
	Replace temporary asm with call to builtin.
	(vrbit_p8, vrbitq_p8): New functions.

gcc/testsuite/:

	* gcc.target/aarch64/simd/vrbit_1.c: New test.

From-SVN: r214943

3 files changed, 49 insertions, 44 deletions

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 4f3bd12..aa19130 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -344,6 +344,8 @@
 
   VAR5 (UNOPU, bswap, 10, v4hi, v8hi, v2si, v4si, v2di)
 
+  BUILTIN_VB (UNOP, rbit, 0)
+
   /* Implemented by
      aarch64_<PERMUTE:perm_insn><PERMUTE:perm_hilo><mode>.  */
   BUILTIN_VALL (BINOP, zip1, 0)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index c489636..8ffc75e 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -294,6 +294,15 @@
   [(set_attr "type" "neon_rev<q>")]
 )
 
+(define_insn "aarch64_rbit<mode>"
+  [(set (match_operand:VB 0 "register_operand" "=w")
+	(unspec:VB [(match_operand:VB 1 "register_operand" "w")]
+		   UNSPEC_RBIT))]
+  "TARGET_SIMD"
+  "rbit\\t%0.<Vbtype>, %1.<Vbtype>"
+  [(set_attr "type" "neon_rbit")]
+)
+
 (define_insn "*aarch64_mul3_elt<mode>"
  [(set (match_operand:VMUL 0 "register_operand" "=w")
     (mult:VMUL
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 0a86172..86926b9 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -10407,50 +10407,6 @@ vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        result;                                                          \
      })
 
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vrbit_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("rbit %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vrbit_u8 (uint8x8_t a)
-{
-  uint8x8_t result;
-  __asm__ ("rbit %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vrbitq_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("rbit %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vrbitq_u8 (uint8x16_t a)
-{
-  uint8x16_t result;
-  __asm__ ("rbit %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
 vrecpe_u32 (uint32x2_t a)
 {
@@ -20781,6 +20737,44 @@ vqsubd_u64 (uint64_t __a, uint64_t __b)
   return __builtin_aarch64_uqsubdi_uuu (__a, __b);
 }
 
+/* vrbit  */
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vrbit_p8 (poly8x8_t __a)
+{
+  return (poly8x8_t) __builtin_aarch64_rbitv8qi ((int8x8_t) __a);
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vrbit_s8 (int8x8_t __a)
+{
+  return __builtin_aarch64_rbitv8qi (__a);
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vrbit_u8 (uint8x8_t __a)
+{
+  return (uint8x8_t) __builtin_aarch64_rbitv8qi ((int8x8_t) __a);
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vrbitq_p8 (poly8x16_t __a)
+{
+  return (poly8x16_t) __builtin_aarch64_rbitv16qi ((int8x16_t)__a);
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vrbitq_s8 (int8x16_t __a)
+{
+  return __builtin_aarch64_rbitv16qi (__a);
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vrbitq_u8 (uint8x16_t __a)
+{
+  return (uint8x16_t) __builtin_aarch64_rbitv16qi ((int8x16_t) __a);
+}
+
 /* vrecpe  */
 
 __extension__ static __inline float32_t __attribute__ ((__always_inline__))