Jonathan Wright <jonathan.wri...@arm.com> writes:
> Hi,
>
> This patch declares unsigned and polynomial type-qualified builtins for
> vcombine_* Neon intrinsics. Using these builtins 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:
>
> 2021-11-10 Jonathan Wright <jonathan.wri...@arm.com>
>
> * config/aarch64/aarch64-builtins.c (TYPES_COMBINE): Delete.
> (TYPES_COMBINEP): Delete.
> * config/aarch64/aarch64-simd-builtins.def: Declare type-
> qualified builtins for vcombine_* intrinsics.
> * config/aarch64/arm_neon.h (vcombine_s8): Remove unnecessary
> cast.
> (vcombine_s16): Likewise.
> (vcombine_s32): Likewise.
> (vcombine_f32): Likewise.
> (vcombine_u8): Use type-qualified builtin and remove casts.
> (vcombine_u16): Likewise.
> (vcombine_u32): Likewise.
> (vcombine_u64): Likewise.
> (vcombine_p8): Likewise.
> (vcombine_p16): Likewise.
> (vcombine_p64): Likewise.
> (vcombine_bf16): Remove unnecessary cast.
> * config/aarch64/iterators.md (VDC_I): New mode iterator.
> (VDC_P): New mode iterator.
>
> diff --git a/gcc/config/aarch64/aarch64-builtins.c
> b/gcc/config/aarch64/aarch64-builtins.c
> index
> f286401ff3ab01dd860ae22858ca07e364247414..7abf8747b69591815068709af42598c47d73269e
> 100644
> --- a/gcc/config/aarch64/aarch64-builtins.c
> +++ b/gcc/config/aarch64/aarch64-builtins.c
> @@ -353,17 +353,6 @@
> aarch64_types_unsigned_shiftacc_qualifiers[SIMD_MAX_BUILTIN_ARGS]
> qualifier_immediate };
> #define TYPES_USHIFTACC (aarch64_types_unsigned_shiftacc_qualifiers)
>
> -
> -static enum aarch64_type_qualifiers
> -aarch64_types_combine_qualifiers[SIMD_MAX_BUILTIN_ARGS]
> - = { qualifier_none, qualifier_none, qualifier_none };
> -#define TYPES_COMBINE (aarch64_types_combine_qualifiers)
> -
> -static enum aarch64_type_qualifiers
> -aarch64_types_combine_p_qualifiers[SIMD_MAX_BUILTIN_ARGS]
> - = { qualifier_poly, qualifier_poly, qualifier_poly };
> -#define TYPES_COMBINEP (aarch64_types_combine_p_qualifiers)
> -
> static enum aarch64_type_qualifiers
> aarch64_types_load1_qualifiers[SIMD_MAX_BUILTIN_ARGS]
> = { qualifier_none, qualifier_const_pointer_map_mode };
> diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def
> b/gcc/config/aarch64/aarch64-simd-builtins.def
> index
> 404696a71e0c1fc37cdf53fc42439a28bc9a745a..ab5f3a098f2047d0f1ba933f4418609678102c3d
> 100644
> --- a/gcc/config/aarch64/aarch64-simd-builtins.def
> +++ b/gcc/config/aarch64/aarch64-simd-builtins.def
> @@ -43,8 +43,9 @@
> help describe the attributes (for example, pure) for the intrinsic
> function. */
>
> - BUILTIN_VDC (COMBINE, combine, 0, AUTO_FP)
> - VAR1 (COMBINEP, combine, 0, NONE, di)
> + BUILTIN_VDC (BINOP, combine, 0, AUTO_FP)
> + BUILTIN_VDC_I (BINOPU, combine, 0, NONE)
> + BUILTIN_VDC_P (BINOPP, combine, 0, NONE)
> BUILTIN_VB (BINOPP, pmul, 0, NONE)
> VAR1 (BINOPP, pmull, 0, NONE, v8qi)
> VAR1 (BINOPP, pmull_hi, 0, NONE, v16qi)
> diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
> index
> 7abd1821840f84a79c37c40a33214294b06edbc6..c374e90f31546886a519ba270113ccedd4ca7abf
> 100644
> --- a/gcc/config/aarch64/arm_neon.h
> +++ b/gcc/config/aarch64/arm_neon.h
> @@ -5975,21 +5975,21 @@ __extension__ extern __inline int8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_s8 (int8x8_t __a, int8x8_t __b)
> {
> - return (int8x16_t) __builtin_aarch64_combinev8qi (__a, __b);
> + return __builtin_aarch64_combinev8qi (__a, __b);
> }
>
> __extension__ extern __inline int16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_s16 (int16x4_t __a, int16x4_t __b)
> {
> - return (int16x8_t) __builtin_aarch64_combinev4hi (__a, __b);
> + return __builtin_aarch64_combinev4hi (__a, __b);
> }
>
> __extension__ extern __inline int32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_s32 (int32x2_t __a, int32x2_t __b)
> {
> - return (int32x4_t) __builtin_aarch64_combinev2si (__a, __b);
> + return __builtin_aarch64_combinev2si (__a, __b);
> }
>
> __extension__ extern __inline int64x2_t
> @@ -6010,38 +6010,35 @@ __extension__ extern __inline float32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_f32 (float32x2_t __a, float32x2_t __b)
> {
> - return (float32x4_t) __builtin_aarch64_combinev2sf (__a, __b);
> + return __builtin_aarch64_combinev2sf (__a, __b);
> }
>
> __extension__ extern __inline uint8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_u8 (uint8x8_t __a, uint8x8_t __b)
> {
> - return (uint8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a,
> - (int8x8_t) __b);
> + return __builtin_aarch64_combinev8qi_uuu (__a, __b);
> }
>
> __extension__ extern __inline uint16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_u16 (uint16x4_t __a, uint16x4_t __b)
> {
> - return (uint16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a,
> - (int16x4_t) __b);
> + return __builtin_aarch64_combinev4hi_uuu (__a, __b);
> }
>
> __extension__ extern __inline uint32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_u32 (uint32x2_t __a, uint32x2_t __b)
> {
> - return (uint32x4_t) __builtin_aarch64_combinev2si ((int32x2_t) __a,
> - (int32x2_t) __b);
> + return __builtin_aarch64_combinev2si_uuu (__a, __b);
> }
>
> __extension__ extern __inline uint64x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_u64 (uint64x1_t __a, uint64x1_t __b)
> {
> - return (uint64x2_t) __builtin_aarch64_combinedi (__a[0], __b[0]);
> + return __builtin_aarch64_combinedi_uuu (__a[0], __b[0]);
> }
>
> __extension__ extern __inline float64x2_t
> @@ -6055,23 +6052,21 @@ __extension__ extern __inline poly8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_p8 (poly8x8_t __a, poly8x8_t __b)
> {
> - return (poly8x16_t) __builtin_aarch64_combinev8qi ((int8x8_t) __a,
> - (int8x8_t) __b);
> + return __builtin_aarch64_combinev8qi_ppp (__a, __b);
> }
>
> __extension__ extern __inline poly16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_p16 (poly16x4_t __a, poly16x4_t __b)
> {
> - return (poly16x8_t) __builtin_aarch64_combinev4hi ((int16x4_t) __a,
> - (int16x4_t) __b);
> + return __builtin_aarch64_combinev4hi_ppp (__a, __b);
> }
>
> __extension__ extern __inline poly64x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_p64 (poly64x1_t __a, poly64x1_t __b)
> {
> - return (poly64x2_t) __builtin_aarch64_combinedi_ppp (__a[0], __b[0]);
> + return __builtin_aarch64_combinedi_ppp (__a[0], __b[0]);
> }
>
> /* Start of temporary inline asm implementations. */
> @@ -30648,7 +30643,7 @@ __extension__ extern __inline bfloat16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vcombine_bf16 (bfloat16x4_t __a, bfloat16x4_t __b)
> {
> - return (bfloat16x8_t)__builtin_aarch64_combinev4bf (__a, __b);
> + return __builtin_aarch64_combinev4bf (__a, __b);
> }
>
> /* vdup */
> diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
> index
> 9389242a1c269cf3b108ef4abbcc3d3f5bf08842..1598e19751ff5112a072118a629755272f48e83b
> 100644
> --- a/gcc/config/aarch64/iterators.md
> +++ b/gcc/config/aarch64/iterators.md
> @@ -238,6 +238,12 @@
> ;; Double vector modes for combines.
> (define_mode_iterator VDC [V8QI V4HI V4BF V4HF V2SI V2SF DI DF])
>
> +;; Integer modes for vector combines.
> +(define_mode_iterator VDC_I [V8QI V4HI V2SI DI])
I think just VD_I would be better for this, placed near VQ_I.
(Surprised to see that we didn't have it already.)
OK with that change, thanks.
Richard
> +
> +;; Polynomial modes for vector combines.
> +(define_mode_iterator VDC_P [V8QI V4HI DI])
> +
> ;; Advanced SIMD modes except double int.
> (define_mode_iterator VDQIF [V8QI V16QI V4HI V8HI V2SI V4SI V2SF V4SF V2DF])
> (define_mode_iterator VDQIF_F16 [V8QI V16QI V4HI V8HI V2SI V4SI
