[ARM] Add ACLE intrinsics vqrdmlah_lane and vqrdmlsh_lane

	* config/arm/arm_neon.h (vqrdmlahq_lane_s16): New.
	(vqrdmlahq_lane_s32): New.
	(vqrdmlah_lane_s16): New.
	(vqrdmlah_lane_s32): New.
	(vqrdmlshq_lane_s16): New.
	(vqrdmlshq_lane_s32): New.
	(vqrdmlsh_lane_s16): New.
	(vqrdmlsh_lane_s32): New.
	* config/arm/arm_neon_builtins.def: Add "vqrdmlah_lane" and
	"vqrdmlsh_lane".

From-SVN: r231686

gcc/ChangeLog

 2015-12-16  Matthew Wahab  <matthew.wahab@arm.com>
 
+	* config/arm/arm_neon.h (vqrdmlahq_lane_s16): New.
+	(vqrdmlahq_lane_s32): New.
+	(vqrdmlah_lane_s16): New.
+	(vqrdmlah_lane_s32): New.
+	(vqrdmlshq_lane_s16): New.
+	(vqrdmlshq_lane_s32): New.
+	(vqrdmlsh_lane_s16): New.
+	(vqrdmlsh_lane_s32): New.
+	* config/arm/arm_neon_builtins.def: Add "vqrdmlah_lane" and
+	"vqrdmlsh_lane".
+
+2015-12-16  Matthew Wahab  <matthew.wahab@arm.com>
+
 	* config/arm/arm_neon.h (vqrdmlah_s16, vqrdmlah_s32): New.
 	(vqrdmlahq_s16, vqrdmlahq_s32): New.
 	(vqrdmlsh_s16, vqrdmlsh_s32): New.

gcc/config/arm/arm_neon.h

@@ -7096,6 +7096,56 @@ vqrdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c)
   return (int32x2_t)__builtin_neon_vqrdmulh_lanev2si (__a, __b, __c);
 }
 
+#ifdef __ARM_FEATURE_QRDMX
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vqrdmlahq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d)
+{
+  return (int16x8_t)__builtin_neon_vqrdmlah_lanev8hi (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vqrdmlahq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d)
+{
+  return (int32x4_t)__builtin_neon_vqrdmlah_lanev4si (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vqrdmlah_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d)
+{
+  return (int16x4_t)__builtin_neon_vqrdmlah_lanev4hi (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vqrdmlah_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d)
+{
+  return (int32x2_t)__builtin_neon_vqrdmlah_lanev2si (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vqrdmlshq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d)
+{
+  return (int16x8_t)__builtin_neon_vqrdmlsh_lanev8hi (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vqrdmlshq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d)
+{
+  return (int32x4_t)__builtin_neon_vqrdmlsh_lanev4si (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vqrdmlsh_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d)
+{
+  return (int16x4_t)__builtin_neon_vqrdmlsh_lanev4hi (__a, __b, __c, __d);
+}
+
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vqrdmlsh_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d)
+{
+  return (int32x2_t)__builtin_neon_vqrdmlsh_lanev2si (__a, __b, __c, __d);
+}
+#endif
+
 __extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
 vmul_n_s16 (int16x4_t __a, int16_t __b)
 {

gcc/config/arm/arm_neon_builtins.def

@@ -60,6 +60,8 @@ VAR4 (BINOP, vqdmulh_n, v4hi, v2si, v8hi, v4si)
 VAR4 (BINOP, vqrdmulh_n, v4hi, v2si, v8hi, v4si)
 VAR4 (SETLANE, vqdmulh_lane, v4hi, v2si, v8hi, v4si)
 VAR4 (SETLANE, vqrdmulh_lane, v4hi, v2si, v8hi, v4si)
+VAR4 (MAC_LANE, vqrdmlah_lane, v4hi, v2si, v8hi, v4si)
+VAR4 (MAC_LANE, vqrdmlsh_lane, v4hi, v2si, v8hi, v4si)
 VAR2 (BINOP, vqdmull, v4hi, v2si)
 VAR8 (BINOP, vshls, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di)
 VAR8 (BINOP, vshlu, v8qi, v4hi, v2si, di, v16qi, v8hi, v4si, v2di)