[PATCH] aarch64: Use type-qualified builtins for ADDP Neon intrinsics

[Richard Sandiford]

Jonathan Wright <Jonathan.Wright@arm.com> writes:
> Hi,
>
> This patch declares unsigned type-qualified builtins and uses them to
> implement the pairwise addition Neon intrinsics. This removes the need
> for many casts in arm_neon.h.
>
> Bootstrapped and regression tested on aarch64-none-linux-gnu - no
> issues.
>
> Ok for master?
>
> Thanks,
> Jonathan
>
> ---
>
> 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.

OK, thanks.  Was initially caught out by vpaddd_u64 not oreviously
having a return cast, but of course that's because it's scalar,
and so an implicit cast was allowed.  So the patch is still
avoiding two casts there.

Richard

>
> diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
> index 035bddcb660e34146b709fdae244571cdeb06272..7d6de6728cf7c63872e09850a394101f7abf21d4 100644
> --- 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 ac871d4e503c634b453cd1f1d3e61182ce4a5a88..ab46897d784b81bec9654d87557640ca4c1e5681 100644
> --- 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 */