[AArch64, 5/6] Reimplement fabd intrinsics & merge rtl patterns

	* config/aarch64/aarch64-builtins.def (fabd): New builtins for modes
	VALLF.
	* config/aarch64/aarch64-simd.md (fabd<mode>_3): Extend modes from VDQF
	to VALLF.  Rename to "fabd<mode>3".
	"*fabd_scalar<mode>3): Delete.
	* config/aarch64/arm_neon.h (vabds_f32): Remove inline assembly.
	Use builtin.
	(vabdd_f64): Likewise.
	(vabd_f32): Likewise.
	(vabd_f64): Likewise.
	(vabdq_f32): Likewise.
	(vabdq_f64): Likewise.

From-SVN: r237204

4 files changed, 64 insertions, 71 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 0189481..5a3f57f 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,20 @@
 2016-06-08  Jiong Wang  <jiong.wang@arm.com>
 
+	* config/aarch64/aarch64-builtins.def (fabd): New builtins for modes
+	VALLF.
+	* config/aarch64/aarch64-simd.md (fabd<mode>_3): Extend modes from VDQF
+	to VALLF.  Rename to "fabd<mode>3".
+	"*fabd_scalar<mode>3): Delete.
+	* config/aarch64/arm_neon.h (vabds_f32): Remove inline assembly.
+	Use builtin.
+	(vabdd_f64): Likewise.
+	(vabd_f32): Likewise.
+	(vabd_f64): Likewise.
+	(vabdq_f32): Likewise.
+	(vabdq_f64): Likewise.
+
+2016-06-08  Jiong Wang  <jiong.wang@arm.com>
+
 	* config/aarch64/aarch64-builtins.def (rsqrts): New builtins for modes
 	VALLF.
 	* config/aarch64/aarch64-simd.md (aarch64_rsqrts_<mode>3): Rename to
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index e839a59..342b98b 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -457,3 +457,6 @@
 
   /* Implemented by aarch64_rsqrts<mode>.  */
   BUILTIN_VALLF (BINOP, rsqrts, 0)
+
+  /* Implemented by fabd<mode>3.  */
+  BUILTIN_VALLF (BINOP, fabd, 3)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 117cde9..32f58f4 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -474,23 +474,14 @@
   [(set_attr "type" "neon_arith_acc<q>")]
 )
 
-(define_insn "fabd<mode>_3"
-  [(set (match_operand:VDQF 0 "register_operand" "=w")
-	(abs:VDQF (minus:VDQF
-		   (match_operand:VDQF 1 "register_operand" "w")
-		   (match_operand:VDQF 2 "register_operand" "w"))))]
-  "TARGET_SIMD"
-  "fabd\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_abd_<Vetype><q>")]
-)
-
-(define_insn "*fabd_scalar<mode>3"
-  [(set (match_operand:GPF 0 "register_operand" "=w")
-        (abs:GPF (minus:GPF
-                 (match_operand:GPF 1 "register_operand" "w")
-                 (match_operand:GPF 2 "register_operand" "w"))))]
+(define_insn "fabd<mode>3"
+  [(set (match_operand:VALLF 0 "register_operand" "=w")
+	(abs:VALLF
+	  (minus:VALLF
+	    (match_operand:VALLF 1 "register_operand" "w")
+	    (match_operand:VALLF 2 "register_operand" "w"))))]
   "TARGET_SIMD"
-  "fabd\t%<s>0, %<s>1, %<s>2"
+  "fabd\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
   [(set_attr "type" "neon_fp_abd_<Vetype><q>")]
 )
 
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 72db325..f301116 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -5440,17 +5440,6 @@ vabaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c)
   return result;
 }
 
-__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
-vabd_f32 (float32x2_t a, float32x2_t b)
-{
-  float32x2_t result;
-  __asm__ ("fabd %0.2s, %1.2s, %2.2s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
 vabd_s8 (int8x8_t a, int8x8_t b)
 {
@@ -5517,17 +5506,6 @@ vabd_u32 (uint32x2_t a, uint32x2_t b)
   return result;
 }
 
-__extension__ static __inline float64_t __attribute__ ((__always_inline__))
-vabdd_f64 (float64_t a, float64_t b)
-{
-  float64_t result;
-  __asm__ ("fabd %d0, %d1, %d2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vabdl_high_s8 (int8x16_t a, int8x16_t b)
 {
@@ -5660,28 +5638,6 @@ vabdl_u32 (uint32x2_t a, uint32x2_t b)
   return result;
 }
 
-__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
-vabdq_f32 (float32x4_t a, float32x4_t b)
-{
-  float32x4_t result;
-  __asm__ ("fabd %0.4s, %1.4s, %2.4s"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
-vabdq_f64 (float64x2_t a, float64x2_t b)
-{
-  float64x2_t result;
-  __asm__ ("fabd %0.2d, %1.2d, %2.2d"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vabdq_s8 (int8x16_t a, int8x16_t b)
 {
@@ -5748,17 +5704,6 @@ vabdq_u32 (uint32x4_t a, uint32x4_t b)
   return result;
 }
 
-__extension__ static __inline float32_t __attribute__ ((__always_inline__))
-vabds_f32 (float32_t a, float32_t b)
-{
-  float32_t result;
-  __asm__ ("fabd %s0, %s1, %s2"
-           : "=w"(result)
-           : "w"(a), "w"(b)
-           : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline int16_t __attribute__ ((__always_inline__))
 vaddlv_s8 (int8x8_t a)
 {
@@ -10235,6 +10180,45 @@ vtbx2_p8 (poly8x8_t r, poly8x8x2_t tab, uint8x8_t idx)
 
 /* Start of optimal implementations in approved order.  */
 
+/* vabd.  */
+
+__extension__ static __inline float32_t __attribute__ ((__always_inline__))
+vabds_f32 (float32_t __a, float32_t __b)
+{
+  return __builtin_aarch64_fabdsf (__a, __b);
+}
+
+__extension__ static __inline float64_t __attribute__ ((__always_inline__))
+vabdd_f64 (float64_t __a, float64_t __b)
+{
+  return __builtin_aarch64_fabddf (__a, __b);
+}
+
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vabd_f32 (float32x2_t __a, float32x2_t __b)
+{
+  return __builtin_aarch64_fabdv2sf (__a, __b);
+}
+
+__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
+vabd_f64 (float64x1_t __a, float64x1_t __b)
+{
+  return (float64x1_t) {vabdd_f64 (vget_lane_f64 (__a, 0),
+				   vget_lane_f64 (__b, 0))};
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vabdq_f32 (float32x4_t __a, float32x4_t __b)
+{
+  return __builtin_aarch64_fabdv4sf (__a, __b);
+}
+
+__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
+vabdq_f64 (float64x2_t __a, float64x2_t __b)
+{
+  return __builtin_aarch64_fabdv2df (__a, __b);
+}
+
 /* vabs  */
 
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))