aarch64: Use type-qualified builtins for ADDP Neon intrinsics

Declare unsigned type-qualified builtins and use them to implement
the pairwise addition 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:
	* config/aarch64/arm_neon.h (vpaddq_u8): Use type-qualified
	builtin and remove casts.
	(vpaddq_u16): Likewise.
	(vpaddq_u32): Likewise.
	(vpaddq_u64): Likewise.
	(vpadd_u8): Likewise.
	(vpadd_u16): Likewise.
	(vpadd_u32): Likewise.
	(vpaddd_u64): Likewise.

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 6f632f6ba00fd60b730aafead31b3e749b26f7fa..f09ff8dbe37f5af38ff9bc2b8bc6d9ff571ba3eb 100644 (file)
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -51,7 +51,9 @@
   BUILTIN_VHSDF_HSDF (BINOP, fmulx, 0, FP)
   BUILTIN_VHSDF_DF (UNOP, sqrt, 2, FP)
   BUILTIN_VDQ_I (BINOP, addp, 0, NONE)
+  BUILTIN_VDQ_I (BINOPU, addp, 0, NONE)
   VAR1 (UNOP, addp, 0, NONE, di)
+  VAR1 (UNOPU, addp, 0, NONE, di)
   BUILTIN_VDQ_BHSI (UNOP, clrsb, 2, NONE)
   BUILTIN_VDQ_BHSI (UNOP, clz, 2, NONE)
   BUILTIN_VS (UNOP, ctz, 2, NONE)

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 288f0176baeb101180b666faefabda72cf0bbb59..ce0162343e6b2acb3c0dc85802b7354cbee08b18 100644 (file)
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -8011,32 +8011,28 @@ __extension__ extern __inline uint8x16_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpaddq_u8 (uint8x16_t __a, uint8x16_t __b)
 {
-  return (uint8x16_t) __builtin_aarch64_addpv16qi ((int8x16_t) __a,
-                                                  (int8x16_t) __b);
+  return __builtin_aarch64_addpv16qi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpaddq_u16 (uint16x8_t __a, uint16x8_t __b)
 {
-  return (uint16x8_t) __builtin_aarch64_addpv8hi ((int16x8_t) __a,
-                                                 (int16x8_t) __b);
+  return __builtin_aarch64_addpv8hi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint32x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpaddq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
-  return (uint32x4_t) __builtin_aarch64_addpv4si ((int32x4_t) __a,
-                                                 (int32x4_t) __b);
+  return __builtin_aarch64_addpv4si_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint64x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpaddq_u64 (uint64x2_t __a, uint64x2_t __b)
 {
-  return (uint64x2_t) __builtin_aarch64_addpv2di ((int64x2_t) __a,
-                                                 (int64x2_t) __b);
+  return __builtin_aarch64_addpv2di_uuu (__a, __b);
 }
 
 __extension__ extern __inline int16x4_t
@@ -20293,24 +20289,21 @@ __extension__ extern __inline uint8x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpadd_u8 (uint8x8_t __a, uint8x8_t __b)
 {
-  return (uint8x8_t) __builtin_aarch64_addpv8qi ((int8x8_t) __a,
-                                                (int8x8_t) __b);
+  return __builtin_aarch64_addpv8qi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpadd_u16 (uint16x4_t __a, uint16x4_t __b)
 {
-  return (uint16x4_t) __builtin_aarch64_addpv4hi ((int16x4_t) __a,
-                                                 (int16x4_t) __b);
+  return __builtin_aarch64_addpv4hi_uuu (__a, __b);
 }
 
 __extension__ extern __inline uint32x2_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpadd_u32 (uint32x2_t __a, uint32x2_t __b)
 {
-  return (uint32x2_t) __builtin_aarch64_addpv2si ((int32x2_t) __a,
-                                                 (int32x2_t) __b);
+  return __builtin_aarch64_addpv2si_uuu (__a, __b);
 }
 
 __extension__ extern __inline float32_t
@@ -20338,7 +20331,7 @@ __extension__ extern __inline uint64_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vpaddd_u64 (uint64x2_t __a)
 {
-  return __builtin_aarch64_addpdi ((int64x2_t) __a);
+  return __builtin_aarch64_addpdi_uu (__a);
 }
 
 /* vqabs */