RE: [PATCH 1/9] arm: MVE: Convert vcmp[eq|ne]* in arm_mve.h to use only 's' builtin version

[Kyrylo Tkachov via Gcc-patches]

> -----Original Message-----
> From: Gcc-patches <gcc-patches-boun...@gcc.gnu.org> On Behalf Of
> Christophe Lyon via Gcc-patches
> Sent: 30 April 2021 15:10
> To: gcc-patches@gcc.gnu.org
> Subject: [PATCH 1/9] arm: MVE: Convert vcmp[eq|ne]* in arm_mve.h to use
> only 's' builtin version
> 
> There is no need to have a signed and an unsigned version of these
> builtins. This is similar to what we do for Neon in arm_neon.h.
> This mechanical patch enables later cleanup patches.

Ok.
Thanks, the patches up to 4/9 seem good mechanical clean ups, the code gen 
changes are after 5/9. I'll get to them soon...
Kyrill

> 
> 2021-03-01  Christophe Lyon  <christophe.l...@linaro.org>
> 
>       gcc/
>       * config/arm/arm_mve.h (__arm_vcmpeq*u*, __arm_vcmpne*u*):
> Call
>       the 's' version of the builtin.
> ---
>  gcc/config/arm/arm_mve.h | 24 ++++++++++++------------
>  1 file changed, 12 insertions(+), 12 deletions(-)
> 
> diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
> index 3a40c6e..e4dfe91 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -3695,21 +3695,21 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_u8 (uint8x16_t __a, uint8x16_t __b)
>  {
> -  return __builtin_mve_vcmpneq_uv16qi (__a, __b);
> +  return __builtin_mve_vcmpneq_sv16qi ((int8x16_t)__a, (int8x16_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_u16 (uint16x8_t __a, uint16x8_t __b)
>  {
> -  return __builtin_mve_vcmpneq_uv8hi (__a, __b);
> +  return __builtin_mve_vcmpneq_sv8hi ((int16x8_t)__a, (int16x8_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_u32 (uint32x4_t __a, uint32x4_t __b)
>  {
> -  return __builtin_mve_vcmpneq_uv4si (__a, __b);
> +  return __builtin_mve_vcmpneq_sv4si ((int32x4_t)__a, (int32x4_t)__b);
>  }
> 
>  __extension__ extern __inline int8x16_t
> @@ -3932,7 +3932,7 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_n_u8 (uint8x16_t __a, uint8_t __b)
>  {
> -  return __builtin_mve_vcmpneq_n_uv16qi (__a, __b);
> +  return __builtin_mve_vcmpneq_n_sv16qi ((int8x16_t)__a, (int8_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> @@ -3953,14 +3953,14 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_u8 (uint8x16_t __a, uint8x16_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_uv16qi (__a, __b);
> +  return __builtin_mve_vcmpeqq_sv16qi ((int8x16_t)__a, (int8x16_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_n_u8 (uint8x16_t __a, uint8_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_n_uv16qi (__a, __b);
> +  return __builtin_mve_vcmpeqq_n_sv16qi ((int8x16_t)__a, (int8_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> @@ -4774,7 +4774,7 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_n_u16 (uint16x8_t __a, uint16_t __b)
>  {
> -  return __builtin_mve_vcmpneq_n_uv8hi (__a, __b);
> +  return __builtin_mve_vcmpneq_n_sv8hi ((int16x8_t)__a, (int16_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> @@ -4795,14 +4795,14 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_u16 (uint16x8_t __a, uint16x8_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_uv8hi (__a, __b);
> +  return __builtin_mve_vcmpeqq_sv8hi ((int16x8_t)__a, (int16x8_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_n_u16 (uint16x8_t __a, uint16_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_n_uv8hi (__a, __b);
> +  return __builtin_mve_vcmpeqq_n_sv8hi ((int16x8_t)__a, (int16_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> @@ -5616,7 +5616,7 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpneq_n_u32 (uint32x4_t __a, uint32_t __b)
>  {
> -  return __builtin_mve_vcmpneq_n_uv4si (__a, __b);
> +  return __builtin_mve_vcmpneq_n_sv4si ((int32x4_t)__a, (int32_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> @@ -5637,14 +5637,14 @@ __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_u32 (uint32x4_t __a, uint32x4_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_uv4si (__a, __b);
> +  return __builtin_mve_vcmpeqq_sv4si ((int32x4_t)__a, (int32x4_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
>  __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>  __arm_vcmpeqq_n_u32 (uint32x4_t __a, uint32_t __b)
>  {
> -  return __builtin_mve_vcmpeqq_n_uv4si (__a, __b);
> +  return __builtin_mve_vcmpeqq_n_sv4si ((int32x4_t)__a, (int32_t)__b);
>  }
> 
>  __extension__ extern __inline mve_pred16_t
> --
> 2.7.4