aarch64: Use type-qualified builtins for UHSUB Neon intrinsics

Declare unsigned type-qualified builtins and use them to implement
halving-subtract Neon intrinsics. This removes the need for many
casts in arm_neon.h.

gcc/ChangeLog:

2021-11-09  Jonathan Wright  <jonathan.wright@arm.com>

	* config/aarch64/aarch64-simd-builtins.def: Use BINOPU type
	qualifiers in generator macros for uhsub builtins.
	* config/aarch64/arm_neon.h (vhsub_s8): Remove unnecessary
	cast.
	(vhsub_s16): Likewise.
	(vhsub_s32): Likewise.
	(vhsub_u8): Use type-qualified builtin and remove casts.
	(vhsub_u16): Likewise.
	(vhsub_u32): Likewise.
	(vhsubq_s8): Remove unnecessary cast.
	(vhsubq_s16): Likewise.
	(vhsubq_s32): Likewise.
	(vhsubq_u8): Use type-qualified builtin and remove casts.
	(vhsubq_u16): Likewise.
	(vhsubq_u32): Likewise.

2 files changed, 13 insertions, 19 deletions

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index e21ca76..0d5d22e 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -179,7 +179,7 @@
   BUILTIN_VDQ_BHSI (BINOP, shadd, 0, NONE)
   BUILTIN_VDQ_BHSI (BINOP, shsub, 0, NONE)
   BUILTIN_VDQ_BHSI (BINOPU, uhadd, 0, NONE)
-  BUILTIN_VDQ_BHSI (BINOP, uhsub, 0, NONE)
+  BUILTIN_VDQ_BHSI (BINOPU, uhsub, 0, NONE)
   BUILTIN_VDQ_BHSI (BINOP, srhadd, 0, NONE)
   BUILTIN_VDQ_BHSI (BINOPU, urhadd, 0, NONE)
 
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 0848b01..05af357 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -1956,90 +1956,84 @@ __extension__ extern __inline int8x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_s8 (int8x8_t __a, int8x8_t __b)
 {
-  return (int8x8_t)__builtin_aarch64_shsubv8qi (__a, __b);
+  return __builtin_aarch64_shsubv8qi (__a, __b);
 }
 
 __extension__ extern __inline int16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_s16 (int16x4_t __a, int16x4_t __b)
 {
-  return (int16x4_t) __builtin_aarch64_shsubv4hi (__a, __b);
+  return __builtin_aarch64_shsubv4hi (__a, __b);
 }
 
 __extension__ extern __inline int32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_s32 (int32x2_t __a, int32x2_t __b)
 {
-  return (int32x2_t) __builtin_aarch64_shsubv2si (__a, __b);
+  return __builtin_aarch64_shsubv2si (__a, __b);
 }
 
 __extension__ extern __inline uint8x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_u8 (uint8x8_t __a, uint8x8_t __b)
 {
-  return (uint8x8_t) __builtin_aarch64_uhsubv8qi ((int8x8_t) __a,
-						  (int8x8_t) __b);
+  return __builtin_aarch64_uhsubv8qi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_u16 (uint16x4_t __a, uint16x4_t __b)
 {
-  return (uint16x4_t) __builtin_aarch64_uhsubv4hi ((int16x4_t) __a,
-						   (int16x4_t) __b);
+  return __builtin_aarch64_uhsubv4hi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsub_u32 (uint32x2_t __a, uint32x2_t __b)
 {
-  return (uint32x2_t) __builtin_aarch64_uhsubv2si ((int32x2_t) __a,
-						   (int32x2_t) __b);
+  return __builtin_aarch64_uhsubv2si_uuu (__a, __b);
 }
 
 __extension__ extern __inline int8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_s8 (int8x16_t __a, int8x16_t __b)
 {
-  return (int8x16_t) __builtin_aarch64_shsubv16qi (__a, __b);
+  return __builtin_aarch64_shsubv16qi (__a, __b);
 }
 
 __extension__ extern __inline int16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_s16 (int16x8_t __a, int16x8_t __b)
 {
-  return (int16x8_t) __builtin_aarch64_shsubv8hi (__a, __b);
+  return __builtin_aarch64_shsubv8hi (__a, __b);
 }
 
 __extension__ extern __inline int32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_s32 (int32x4_t __a, int32x4_t __b)
 {
-  return (int32x4_t) __builtin_aarch64_shsubv4si (__a, __b);
+  return __builtin_aarch64_shsubv4si (__a, __b);
 }
 
 __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_u8 (uint8x16_t __a, uint8x16_t __b)
 {
-  return (uint8x16_t) __builtin_aarch64_uhsubv16qi ((int8x16_t) __a,
-						    (int8x16_t) __b);
+  return __builtin_aarch64_uhsubv16qi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_u16 (uint16x8_t __a, uint16x8_t __b)
 {
-  return (uint16x8_t) __builtin_aarch64_uhsubv8hi ((int16x8_t) __a,
-						   (int16x8_t) __b);
+  return __builtin_aarch64_uhsubv8hi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vhsubq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
-  return (uint32x4_t) __builtin_aarch64_uhsubv4si ((int32x4_t) __a,
-						   (int32x4_t) __b);
+  return __builtin_aarch64_uhsubv4si_uuu (__a, __b);
 }
 
 __extension__ extern __inline int8x8_t