[v2][AArch64, 3/6] Reimplement frsqrte intrinsics

[Jiong Wang <jiong.wang@foss.arm.com>]

[-- Attachment #1: Type: text/plain, Size: 808 bytes --]

These intrinsics were implemented before the instruction pattern
"aarch64_rsqrte<mode>" added, that these intrinsics were implemented through
inline assembly.

This mirgrate the implementation to builtin.

gcc/
2016-06-06  Jiong Wang<jiong.wang@arm.com>

         * config/aarch64/aarch64-builtins.def (rsqrte): New builtins for modes
         VALLF.
         * config/aarch64/aarch64-simd.md (aarch64_rsqrte_<mode>2): Rename to
         "aarch64_rsqrte<mode>".
         * config/aarch64/aarch64.c (get_rsqrte_type): Update gen* name.
         * config/aarch64/arm_neon.h (vrsqrts_f32): Remove inline assembly.  Use
         builtin.
         (vrsqrted_f64): Likewise.
         (vrsqrte_f32): Likewise.
         (vrsqrte_f64): Likewise.
         (vrsqrteq_f32): Likewise.
         (vrsqrteq_f64): Likewise.


[-- Attachment #2: 3.patch --]
[-- Type: text/x-patch, Size: 5704 bytes --]

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 25a5270766401bd2f31ccacdafee83c183bdf775..f60f84c42fefd32bace6f4aa690f97ca54f3e4b6 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -451,3 +451,6 @@
   BUILTIN_VALLI (BINOP_SUS, ucvtf, 3)
   BUILTIN_VALLF (BINOP, fcvtzs, 3)
   BUILTIN_VALLF (BINOP_USS, fcvtzu, 3)
+
+  /* Implemented by aarch64_rsqrte<mode>.  */
+  BUILTIN_VALLF (UNOP, rsqrte, 0)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index ca90b666a7e3888057b7d9e8562a2544a006cf0f..941214680262ef1015cbb23f518b4999f962bf9b 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -382,7 +382,7 @@
   [(set_attr "type" "neon<fp>_mul_<Vetype>_scalar<q>")]
 )
 
-(define_insn "aarch64_rsqrte_<mode>2"
+(define_insn "aarch64_rsqrte<mode>"
   [(set (match_operand:VALLF 0 "register_operand" "=w")
 	(unspec:VALLF [(match_operand:VALLF 1 "register_operand" "w")]
 		     UNSPEC_RSQRTE))]
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index ad07fe196a814ace78d43f66e70280d20a4476b5..acfb39dc025d74fe531d439bb87c52d18955ee7c 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -7349,11 +7349,11 @@ get_rsqrte_type (machine_mode mode)
 {
   switch (mode)
   {
-    case DFmode:   return gen_aarch64_rsqrte_df2;
-    case SFmode:   return gen_aarch64_rsqrte_sf2;
-    case V2DFmode: return gen_aarch64_rsqrte_v2df2;
-    case V2SFmode: return gen_aarch64_rsqrte_v2sf2;
-    case V4SFmode: return gen_aarch64_rsqrte_v4sf2;
+    case DFmode:   return gen_aarch64_rsqrtedf;
+    case SFmode:   return gen_aarch64_rsqrtesf;
+    case V2DFmode: return gen_aarch64_rsqrtev2df;
+    case V2SFmode: return gen_aarch64_rsqrtev2sf;
+    case V4SFmode: return gen_aarch64_rsqrtev4sf;
     default: gcc_unreachable ();
   }
 }
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 04bce9ab80c151877619ee75e7cb50f5951099f7..e4f7a66abcc59f306de289d22e9d09cfe32c0c87 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -9163,28 +9163,6 @@ vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        result;                                                          \
      })
 
-__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
-vrsqrte_f32 (float32x2_t a)
-{
-  float32x2_t result;
-  __asm__ ("frsqrte %0.2s,%1.2s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
-vrsqrte_f64 (float64x1_t a)
-{
-  float64x1_t result;
-  __asm__ ("frsqrte %d0,%d1"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
 vrsqrte_u32 (uint32x2_t a)
 {
@@ -9196,39 +9174,6 @@ vrsqrte_u32 (uint32x2_t a)
   return result;
 }
 
-__extension__ static __inline float64_t __attribute__ ((__always_inline__))
-vrsqrted_f64 (float64_t a)
-{
-  float64_t result;
-  __asm__ ("frsqrte %d0,%d1"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
-vrsqrteq_f32 (float32x4_t a)
-{
-  float32x4_t result;
-  __asm__ ("frsqrte %0.4s,%1.4s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
-vrsqrteq_f64 (float64x2_t a)
-{
-  float64x2_t result;
-  __asm__ ("frsqrte %0.2d,%1.2d"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vrsqrteq_u32 (uint32x4_t a)
 {
@@ -9240,17 +9185,6 @@ vrsqrteq_u32 (uint32x4_t a)
   return result;
 }
 
-__extension__ static __inline float32_t __attribute__ ((__always_inline__))
-vrsqrtes_f32 (float32_t a)
-{
-  float32_t result;
-  __asm__ ("frsqrte %s0,%s1"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vrsqrts_f32 (float32x2_t a, float32x2_t b)
 {
@@ -21504,6 +21438,44 @@ vrshrd_n_u64 (uint64_t __a, const int __b)
   return __builtin_aarch64_urshr_ndi_uus (__a, __b);
 }
 
+/* vrsqrte.  */
+
+__extension__ static __inline float32_t __attribute__ ((__always_inline__))
+vrsqrtes_f32 (float32_t __a)
+{
+  return __builtin_aarch64_rsqrtesf (__a);
+}
+
+__extension__ static __inline float64_t __attribute__ ((__always_inline__))
+vrsqrted_f64 (float64_t __a)
+{
+  return __builtin_aarch64_rsqrtedf (__a);
+}
+
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vrsqrte_f32 (float32x2_t __a)
+{
+  return __builtin_aarch64_rsqrtev2sf (__a);
+}
+
+__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
+vrsqrte_f64 (float64x1_t __a)
+{
+  return (float64x1_t) {vrsqrted_f64 (vget_lane_f64 (__a, 0))};
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vrsqrteq_f32 (float32x4_t __a)
+{
+  return __builtin_aarch64_rsqrtev4sf (__a);
+}
+
+__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
+vrsqrteq_f64 (float64x2_t __a)
+{
+  return __builtin_aarch64_rsqrtev2df (__a);
+}
+
 /* vrsra */
 
 __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))