RE: [PATCH 06/10] arm: Fix overloading of MVE scalar constant parameters on vbicq, vmvnq_m

[Kyrylo Tkachov via Gcc-patches]

> -----Original Message-----
> From: Andrea Corallo <andrea.cora...@arm.com>
> Sent: Friday, April 28, 2023 12:30 PM
> To: gcc-patches@gcc.gnu.org
> Cc: Kyrylo Tkachov <kyrylo.tkac...@arm.com>; Richard Earnshaw
> <richard.earns...@arm.com>; Stam Markianos-Wright <Stam.Markianos-
> wri...@arm.com>
> Subject: [PATCH 06/10] arm: Fix overloading of MVE scalar constant
> parameters on vbicq, vmvnq_m
> 
> From: Stam Markianos-Wright <stam.markianos-wri...@arm.com>
> 
> We found this as part of the wider testsuite updates.
> 
> The applicable tests are authored by Andrea earlier in this patch series
> 
> Ok for trunk?

Ok.
Thanks,
Kyrill

> 
> gcc/ChangeLog:
> 
>       * config/arm/arm_mve.h (__arm_vbicq): Change coerce on
>       scalar constant.
>       (__arm_vmvnq_m): Likewise.
> ---
>  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 3d386f320c3..3a1cffb4063 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -35906,10 +35906,10 @@ extern void *__ARM_undef;
>  #define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
>    __typeof(p1) __p1 = (p1); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0,
> \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce1 (__p1, int)), \
> +  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce3 (p1, int)), \
>    int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]:
> __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t),
> __ARM_mve_coerce(__p1, int8x16_t)), \
>    int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]:
> __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce(__p1, int16x8_t)), \
>    int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]:
> __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce(__p1, int32x4_t)), \
> @@ -38825,10 +38825,10 @@ extern void *__ARM_undef;
>  #define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
>    __typeof(p1) __p1 = (p1); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0,
> \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce1 (__p1, int)), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce1 (__p1, int)), \
> +  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce3 (p1, int)), \
> +  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce3 (p1, int)), \
>    int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]:
> __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t),
> __ARM_mve_coerce(__p1, int8x16_t)), \
>    int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]:
> __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce(__p1, int16x8_t)), \
>    int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]:
> __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce(__p1, int32x4_t)), \
> @@ -40962,10 +40962,10 @@ extern void *__ARM_undef;
>    int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]:
> __arm_vmvnq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t),
> __ARM_mve_coerce(__p1, uint8x16_t), p2), \
>    int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]:
> __arm_vmvnq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce(__p1, uint16x8_t), p2), \
>    int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]:
> __arm_vmvnq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce(__p1, uint32x4_t), p2), \
> -  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce1(__p1, int) , p2), \
> -  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce1(__p1, int) , p2), \
> -  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce1(__p1, int) , p2), \
> -  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce1(__p1, int) , p2));})
> +  int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t),
> __ARM_mve_coerce3(p1, int) , p2), \
> +  int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t),
> __ARM_mve_coerce3(p1, int) , p2), \
> +  int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t),
> __ARM_mve_coerce3(p1, int) , p2), \
> +  int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]:
> __arm_vmvnq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t),
> __ARM_mve_coerce3(p1, int) , p2));})
> 
>  #define __arm_vorrq_m_n(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
>    _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
> --
> 2.25.1