aarch64: Use type-qualified builtins for XTN[2] Neon intrinsics

Declare unsigned type-qualified builtins and use them for XTN[2] Neon
intrinsics. This removes the need for casts in arm_neon.h.

gcc/ChangeLog:

2021-11-08  Jonathan Wright  <jonathan.wright@arm.com>

	* config/aarch64/aarch64-simd-builtins.def: Declare unsigned
	type-qualified builtins for XTN[2].
	* config/aarch64/arm_neon.h (vmovn_high_u16): Use type-
	qualified builtin and remove casts.
	(vmovn_high_u32): Likewise.
	(vmovn_high_u64): Likewise.
	(vmovn_u16): Likewise.
	(vmovn_u32): Likewise.
	(vmovn_u64): Likewise.

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 4e298de5646c78bfaf82752274b8530497971ff3..395d5146e6e15f74a64d9b82d8ded2bd2cb98189 100644 (file)
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -235,6 +235,7 @@
 
   /* Implemented by aarch64_xtn<mode>.  */
   BUILTIN_VQN (UNOP, xtn, 0, NONE)
+  BUILTIN_VQN (UNOPU, xtn, 0, NONE)
 
   /* Implemented by aarch64_mla<mode>.  */
   BUILTIN_VDQ_BHSI (TERNOP, mla, 0, NONE)
@@ -489,7 +490,8 @@
   BUILTIN_VSDQ_I (USHIFTIMM, uqshl_n, 0, NONE)
 
   /* Implemented by aarch64_xtn2<mode>.  */
-  BUILTIN_VQN (UNOP, xtn2, 0, NONE)
+  BUILTIN_VQN (BINOP, xtn2, 0, NONE)
+  BUILTIN_VQN (BINOPU, xtn2, 0, NONE)
 
   /* Implemented by vec_unpack<su>_hi_<mode>.  */
   BUILTIN_VQW (UNOP, vec_unpacks_hi_, 10, NONE)

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 236358774abd271730ef4a2ac0f4221588e66daf..dcc1b66dfef167b65f4343497ae11480fa0649b6 100644 (file)
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -7522,24 +7522,21 @@ __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_high_u16 (uint8x8_t __a, uint16x8_t __b)
 {
-  return (uint8x16_t)
-          __builtin_aarch64_xtn2v8hi ((int8x8_t) __a, (int16x8_t) __b);
+  return __builtin_aarch64_xtn2v8hi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_high_u32 (uint16x4_t __a, uint32x4_t __b)
 {
-  return (uint16x8_t)
-          __builtin_aarch64_xtn2v4si ((int16x4_t) __a, (int32x4_t) __b);
+  return __builtin_aarch64_xtn2v4si_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_high_u64 (uint32x2_t __a, uint64x2_t __b)
 {
-  return (uint32x4_t)
-          __builtin_aarch64_xtn2v2di ((int32x2_t) __a, (int64x2_t) __b);
+  return __builtin_aarch64_xtn2v2di_uuu (__a, __b);
 }
 
 __extension__ extern __inline int8x8_t
@@ -7567,21 +7564,21 @@ __extension__ extern __inline uint8x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_u16 (uint16x8_t __a)
 {
-  return (uint8x8_t)__builtin_aarch64_xtnv8hi ((int16x8_t) __a);
+  return __builtin_aarch64_xtnv8hi_uu (__a);
 }
 
 __extension__ extern __inline uint16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_u32 (uint32x4_t __a)
 {
-  return (uint16x4_t) __builtin_aarch64_xtnv4si ((int32x4_t )__a);
+  return __builtin_aarch64_xtnv4si_uu (__a);
 }
 
 __extension__ extern __inline uint32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vmovn_u64 (uint64x2_t __a)
 {
-  return (uint32x2_t) __builtin_aarch64_xtnv2di ((int64x2_t) __a);
+  return __builtin_aarch64_xtnv2di_uu (__a);
 }
 
 __extension__ extern __inline int8x8_t