> -----Original Message----- > From: Christophe Lyon <christophe.l...@arm.com> > Sent: Friday, May 5, 2023 9:39 AM > To: gcc-patches@gcc.gnu.org; Kyrylo Tkachov <kyrylo.tkac...@arm.com>; > Richard Earnshaw <richard.earns...@arm.com>; Richard Sandiford > <richard.sandif...@arm.com> > Cc: Christophe Lyon <christophe.l...@arm.com> > Subject: [PATCH 05/23] arm: [MVE intrinsics] rework vqrdmulhq > > Implement vqrdmulhq using the new MVE builtins framework. Ok. Thanks, Kyrill > > 2022-09-08 Christophe Lyon <christophe.l...@arm.com> > > gcc/ > * config/arm/arm-mve-builtins-base.cc (vqrdmulhq): New. > * config/arm/arm-mve-builtins-base.def (vqrdmulhq): New. > * config/arm/arm-mve-builtins-base.h (vqrdmulhq): New. > * config/arm/arm_mve.h (vqrdmulhq): Remove. > (vqrdmulhq_m): Remove. > (vqrdmulhq_s8): Remove. > (vqrdmulhq_n_s8): Remove. > (vqrdmulhq_s16): Remove. > (vqrdmulhq_n_s16): Remove. > (vqrdmulhq_s32): Remove. > (vqrdmulhq_n_s32): Remove. > (vqrdmulhq_m_n_s8): Remove. > (vqrdmulhq_m_n_s32): Remove. > (vqrdmulhq_m_n_s16): Remove. > (vqrdmulhq_m_s8): Remove. > (vqrdmulhq_m_s32): Remove. > (vqrdmulhq_m_s16): Remove. > (__arm_vqrdmulhq_s8): Remove. > (__arm_vqrdmulhq_n_s8): Remove. > (__arm_vqrdmulhq_s16): Remove. > (__arm_vqrdmulhq_n_s16): Remove. > (__arm_vqrdmulhq_s32): Remove. > (__arm_vqrdmulhq_n_s32): Remove. > (__arm_vqrdmulhq_m_n_s8): Remove. > (__arm_vqrdmulhq_m_n_s32): Remove. > (__arm_vqrdmulhq_m_n_s16): Remove. > (__arm_vqrdmulhq_m_s8): Remove. > (__arm_vqrdmulhq_m_s32): Remove. > (__arm_vqrdmulhq_m_s16): Remove. > (__arm_vqrdmulhq): Remove. > (__arm_vqrdmulhq_m): Remove. > --- > gcc/config/arm/arm-mve-builtins-base.cc | 1 + > gcc/config/arm/arm-mve-builtins-base.def | 1 + > gcc/config/arm/arm-mve-builtins-base.h | 1 + > gcc/config/arm/arm_mve.h | 213 ----------------------- > 4 files changed, 3 insertions(+), 213 deletions(-) > > diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm- > mve-builtins-base.cc > index f5e48519b19..8c125657c67 100644 > --- a/gcc/config/arm/arm-mve-builtins-base.cc > +++ b/gcc/config/arm/arm-mve-builtins-base.cc > @@ -158,6 +158,7 @@ FUNCTION_WITH_RTX_M_N_NO_N_F (vorrq, IOR, > VORRQ) > FUNCTION_WITH_M_N_NO_F (vqaddq, VQADDQ) > FUNCTION_WITH_M_N_NO_U_F (vqdmulhq, VQDMULHQ) > FUNCTION_WITH_M_N_NO_F (vqrshlq, VQRSHLQ) > +FUNCTION_WITH_M_N_NO_U_F (vqrdmulhq, VQRDMULHQ) > FUNCTION_WITH_M_N_NO_F (vqsubq, VQSUBQ) > FUNCTION (vreinterpretq, vreinterpretq_impl,) > FUNCTION_WITHOUT_N_NO_F (vrhaddq, VRHADDQ) > diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm- > mve-builtins-base.def > index e6dc2b00aaa..5b9966341ce 100644 > --- a/gcc/config/arm/arm-mve-builtins-base.def > +++ b/gcc/config/arm/arm-mve-builtins-base.def > @@ -29,6 +29,7 @@ DEF_MVE_FUNCTION (vmulq, binary_opt_n, all_integer, > mx_or_none) > DEF_MVE_FUNCTION (vorrq, binary_orrq, all_integer, mx_or_none) > DEF_MVE_FUNCTION (vqaddq, binary_opt_n, all_integer, m_or_none) > DEF_MVE_FUNCTION (vqdmulhq, binary_opt_n, all_signed, m_or_none) > +DEF_MVE_FUNCTION (vqrdmulhq, binary_opt_n, all_signed, m_or_none) > DEF_MVE_FUNCTION (vqrshlq, binary_round_lshift, all_integer, m_or_none) > DEF_MVE_FUNCTION (vqsubq, binary_opt_n, all_integer, m_or_none) > DEF_MVE_FUNCTION (vreinterpretq, unary_convert, reinterpret_integer, > none) > diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm- > mve-builtins-base.h > index 31ba3fece82..eeb747d52ad 100644 > --- a/gcc/config/arm/arm-mve-builtins-base.h > +++ b/gcc/config/arm/arm-mve-builtins-base.h > @@ -34,6 +34,7 @@ extern const function_base *const vmulq; > extern const function_base *const vorrq; > extern const function_base *const vqaddq; > extern const function_base *const vqdmulhq; > +extern const function_base *const vqrdmulhq; > extern const function_base *const vqrshlq; > extern const function_base *const vqsubq; > extern const function_base *const vreinterpretq; > diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h > index 636945d6ef0..44b383dbe08 100644 > --- a/gcc/config/arm/arm_mve.h > +++ b/gcc/config/arm/arm_mve.h > @@ -94,7 +94,6 @@ > #define vcmpgtq(__a, __b) __arm_vcmpgtq(__a, __b) > #define vcmpgeq(__a, __b) __arm_vcmpgeq(__a, __b) > #define vqshluq(__a, __imm) __arm_vqshluq(__a, __imm) > -#define vqrdmulhq(__a, __b) __arm_vqrdmulhq(__a, __b) > #define vmlsdavxq(__a, __b) __arm_vmlsdavxq(__a, __b) > #define vmlsdavq(__a, __b) __arm_vmlsdavq(__a, __b) > #define vmladavxq(__a, __b) __arm_vmladavxq(__a, __b) > @@ -249,7 +248,6 @@ > #define vqrdmlashq_m(__a, __b, __c, __p) __arm_vqrdmlashq_m(__a, __b, > __c, __p) > #define vqrdmlsdhq_m(__inactive, __a, __b, __p) > __arm_vqrdmlsdhq_m(__inactive, __a, __b, __p) > #define vqrdmlsdhxq_m(__inactive, __a, __b, __p) > __arm_vqrdmlsdhxq_m(__inactive, __a, __b, __p) > -#define vqrdmulhq_m(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m(__inactive, __a, __b, __p) > #define vqshlq_m_n(__inactive, __a, __imm, __p) > __arm_vqshlq_m_n(__inactive, __a, __imm, __p) > #define vqshlq_m(__inactive, __a, __b, __p) __arm_vqshlq_m(__inactive, > __a, __b, __p) > #define vrshrq_m(__inactive, __a, __imm, __p) __arm_vrshrq_m(__inactive, > __a, __imm, __p) > @@ -682,8 +680,6 @@ > #define vshlq_r_s8(__a, __b) __arm_vshlq_r_s8(__a, __b) > #define vqshlq_s8(__a, __b) __arm_vqshlq_s8(__a, __b) > #define vqshlq_r_s8(__a, __b) __arm_vqshlq_r_s8(__a, __b) > -#define vqrdmulhq_s8(__a, __b) __arm_vqrdmulhq_s8(__a, __b) > -#define vqrdmulhq_n_s8(__a, __b) __arm_vqrdmulhq_n_s8(__a, __b) > #define vornq_s8(__a, __b) __arm_vornq_s8(__a, __b) > #define vmulltq_int_s8(__a, __b) __arm_vmulltq_int_s8(__a, __b) > #define vmullbq_int_s8(__a, __b) __arm_vmullbq_int_s8(__a, __b) > @@ -754,8 +750,6 @@ > #define vshlq_r_s16(__a, __b) __arm_vshlq_r_s16(__a, __b) > #define vqshlq_s16(__a, __b) __arm_vqshlq_s16(__a, __b) > #define vqshlq_r_s16(__a, __b) __arm_vqshlq_r_s16(__a, __b) > -#define vqrdmulhq_s16(__a, __b) __arm_vqrdmulhq_s16(__a, __b) > -#define vqrdmulhq_n_s16(__a, __b) __arm_vqrdmulhq_n_s16(__a, __b) > #define vornq_s16(__a, __b) __arm_vornq_s16(__a, __b) > #define vmulltq_int_s16(__a, __b) __arm_vmulltq_int_s16(__a, __b) > #define vmullbq_int_s16(__a, __b) __arm_vmullbq_int_s16(__a, __b) > @@ -826,8 +820,6 @@ > #define vshlq_r_s32(__a, __b) __arm_vshlq_r_s32(__a, __b) > #define vqshlq_s32(__a, __b) __arm_vqshlq_s32(__a, __b) > #define vqshlq_r_s32(__a, __b) __arm_vqshlq_r_s32(__a, __b) > -#define vqrdmulhq_s32(__a, __b) __arm_vqrdmulhq_s32(__a, __b) > -#define vqrdmulhq_n_s32(__a, __b) __arm_vqrdmulhq_n_s32(__a, __b) > #define vornq_s32(__a, __b) __arm_vornq_s32(__a, __b) > #define vmulltq_int_s32(__a, __b) __arm_vmulltq_int_s32(__a, __b) > #define vmullbq_int_s32(__a, __b) __arm_vmullbq_int_s32(__a, __b) > @@ -1597,12 +1589,6 @@ > #define vqrdmlsdhxq_m_s8(__inactive, __a, __b, __p) > __arm_vqrdmlsdhxq_m_s8(__inactive, __a, __b, __p) > #define vqrdmlsdhxq_m_s32(__inactive, __a, __b, __p) > __arm_vqrdmlsdhxq_m_s32(__inactive, __a, __b, __p) > #define vqrdmlsdhxq_m_s16(__inactive, __a, __b, __p) > __arm_vqrdmlsdhxq_m_s16(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_n_s8(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_n_s8(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_n_s32(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_n_s32(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_n_s16(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_n_s16(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_s8(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_s8(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_s32(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_s32(__inactive, __a, __b, __p) > -#define vqrdmulhq_m_s16(__inactive, __a, __b, __p) > __arm_vqrdmulhq_m_s16(__inactive, __a, __b, __p) > #define vqshlq_m_n_s8(__inactive, __a, __imm, __p) > __arm_vqshlq_m_n_s8(__inactive, __a, __imm, __p) > #define vqshlq_m_n_s32(__inactive, __a, __imm, __p) > __arm_vqshlq_m_n_s32(__inactive, __a, __imm, __p) > #define vqshlq_m_n_s16(__inactive, __a, __imm, __p) > __arm_vqshlq_m_n_s16(__inactive, __a, __imm, __p) > @@ -3421,20 +3407,6 @@ __arm_vqshlq_r_s8 (int8x16_t __a, int32_t __b) > return __builtin_mve_vqshlq_r_sv16qi (__a, __b); > } > > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_s8 (int8x16_t __a, int8x16_t __b) > -{ > - return __builtin_mve_vqrdmulhq_sv16qi (__a, __b); > -} > - > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_n_s8 (int8x16_t __a, int8_t __b) > -{ > - return __builtin_mve_vqrdmulhq_n_sv16qi (__a, __b); > -} > - > __extension__ extern __inline int8x16_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq_s8 (int8x16_t __a, int8x16_t __b) > @@ -3927,20 +3899,6 @@ __arm_vqshlq_r_s16 (int16x8_t __a, int32_t __b) > return __builtin_mve_vqshlq_r_sv8hi (__a, __b); > } > > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_s16 (int16x8_t __a, int16x8_t __b) > -{ > - return __builtin_mve_vqrdmulhq_sv8hi (__a, __b); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_n_s16 (int16x8_t __a, int16_t __b) > -{ > - return __builtin_mve_vqrdmulhq_n_sv8hi (__a, __b); > -} > - > __extension__ extern __inline int16x8_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq_s16 (int16x8_t __a, int16x8_t __b) > @@ -4433,20 +4391,6 @@ __arm_vqshlq_r_s32 (int32x4_t __a, int32_t __b) > return __builtin_mve_vqshlq_r_sv4si (__a, __b); > } > > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_s32 (int32x4_t __a, int32x4_t __b) > -{ > - return __builtin_mve_vqrdmulhq_sv4si (__a, __b); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_n_s32 (int32x4_t __a, int32_t __b) > -{ > - return __builtin_mve_vqrdmulhq_n_sv4si (__a, __b); > -} > - > __extension__ extern __inline int32x4_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq_s32 (int32x4_t __a, int32x4_t __b) > @@ -8674,48 +8618,6 @@ __arm_vqrdmlsdhxq_m_s16 (int16x8_t __inactive, > int16x8_t __a, int16x8_t __b, mve > return __builtin_mve_vqrdmlsdhxq_m_sv8hi (__inactive, __a, __b, __p); > } > > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_n_s8 (int8x16_t __inactive, int8x16_t __a, int8_t __b, > mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_n_sv16qi (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_n_s32 (int32x4_t __inactive, int32x4_t __a, int32_t > __b, mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_n_sv4si (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_n_s16 (int16x8_t __inactive, int16x8_t __a, int16_t > __b, mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_n_sv8hi (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, > mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_sv16qi (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t > __b, mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_sv4si (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t > __b, mve_pred16_t __p) > -{ > - return __builtin_mve_vqrdmulhq_m_sv8hi (__inactive, __a, __b, __p); > -} > - > __extension__ extern __inline int8x16_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vqshlq_m_n_s8 (int8x16_t __inactive, int8x16_t __a, const int __imm, > mve_pred16_t __p) > @@ -16946,20 +16848,6 @@ __arm_vqshlq_r (int8x16_t __a, int32_t __b) > return __arm_vqshlq_r_s8 (__a, __b); > } > > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int8x16_t __a, int8x16_t __b) > -{ > - return __arm_vqrdmulhq_s8 (__a, __b); > -} > - > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int8x16_t __a, int8_t __b) > -{ > - return __arm_vqrdmulhq_n_s8 (__a, __b); > -} > - > __extension__ extern __inline int8x16_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq (int8x16_t __a, int8x16_t __b) > @@ -17450,20 +17338,6 @@ __arm_vqshlq_r (int16x8_t __a, int32_t __b) > return __arm_vqshlq_r_s16 (__a, __b); > } > > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int16x8_t __a, int16x8_t __b) > -{ > - return __arm_vqrdmulhq_s16 (__a, __b); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int16x8_t __a, int16_t __b) > -{ > - return __arm_vqrdmulhq_n_s16 (__a, __b); > -} > - > __extension__ extern __inline int16x8_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq (int16x8_t __a, int16x8_t __b) > @@ -17954,20 +17828,6 @@ __arm_vqshlq_r (int32x4_t __a, int32_t __b) > return __arm_vqshlq_r_s32 (__a, __b); > } > > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int32x4_t __a, int32x4_t __b) > -{ > - return __arm_vqrdmulhq_s32 (__a, __b); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq (int32x4_t __a, int32_t __b) > -{ > - return __arm_vqrdmulhq_n_s32 (__a, __b); > -} > - > __extension__ extern __inline int32x4_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vornq (int32x4_t __a, int32x4_t __b) > @@ -22154,48 +22014,6 @@ __arm_vqrdmlsdhxq_m (int16x8_t __inactive, > int16x8_t __a, int16x8_t __b, mve_pre > return __arm_vqrdmlsdhxq_m_s16 (__inactive, __a, __b, __p); > } > > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_n_s8 (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_n_s32 (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_n_s16 (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int8x16_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_s8 (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int32x4_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_s32 (__inactive, __a, __b, __p); > -} > - > -__extension__ extern __inline int16x8_t > -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > -__arm_vqrdmulhq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, > mve_pred16_t __p) > -{ > - return __arm_vqrdmulhq_m_s16 (__inactive, __a, __b, __p); > -} > - > __extension__ extern __inline int8x16_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > __arm_vqshlq_m_n (int8x16_t __inactive, int8x16_t __a, const int __imm, > mve_pred16_t __p) > @@ -29075,16 +28893,6 @@ extern void *__ARM_undef; > int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 > (__ARM_mve_coerce(__p0, uint16x8_t), p1), \ > int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 > (__ARM_mve_coerce(__p0, uint32x4_t), p1));}) > > -#define __arm_vqrdmulhq(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_int8x16_t][__ARM_mve_type_int8x16_t]: > __arm_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), > __ARM_mve_coerce(__p1, int32x4_t)), \ > - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: > __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), > __ARM_mve_coerce3(p1, int)), \ > - int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: > __arm_vqrdmulhq_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_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), > __ARM_mve_coerce3(p1, int)));}) > - > #define __arm_vmlaldavxq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ > __typeof(p1) __p1 = (p1); \ > _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, > \ > @@ -30833,16 +30641,6 @@ extern void *__ARM_undef; > int (*)[__ARM_mve_type_uint16x8_t]: __arm_vqshlq_n_u16 > (__ARM_mve_coerce(__p0, uint16x8_t), p1), \ > int (*)[__ARM_mve_type_uint32x4_t]: __arm_vqshlq_n_u32 > (__ARM_mve_coerce(__p0, uint32x4_t), p1));}) > > -#define __arm_vqrdmulhq(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_int8x16_t][__ARM_mve_type_int8x16_t]: > __arm_vqrdmulhq_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_vqrdmulhq_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_vqrdmulhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), > __ARM_mve_coerce(__p1, int32x4_t)), \ > - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: > __arm_vqrdmulhq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), > __ARM_mve_coerce3(p1, int)), \ > - int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: > __arm_vqrdmulhq_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_vqrdmulhq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), > __ARM_mve_coerce3(p1, int)));}) > - > #define __arm_vornq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ > __typeof(p1) __p1 = (p1); \ > _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, > \ > @@ -32455,17 +32253,6 @@ extern void *__ARM_undef; > int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: > __arm_vsliq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), > __ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \ > int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: > __arm_vsliq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), > __ARM_mve_coerce(__p1, uint32x4_t), p2, p3));}) > > -#define __arm_vqrdmulhq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ > - __typeof(p1) __p1 = (p1); \ > - __typeof(p2) __p2 = (p2); \ > - _Generic( (int > (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typ > eid(__p2)])0, \ > - int > (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve > _type_int8x16_t]: __arm_vqrdmulhq_m_s8 (__ARM_mve_coerce(__p0, > int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, > int8x16_t), p3), \ > - int > (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve > _type_int16x8_t]: __arm_vqrdmulhq_m_s16 (__ARM_mve_coerce(__p0, > int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, > int16x8_t), p3), \ > - int > (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve > _type_int32x4_t]: __arm_vqrdmulhq_m_s32 (__ARM_mve_coerce(__p0, > int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, > int32x4_t), p3), \ > - int > (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve > _type_int_n]: __arm_vqrdmulhq_m_n_s8 (__ARM_mve_coerce(__p0, > int8x16_t), __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce3(p2, > int), p3), \ > - int > (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve > _type_int_n]: __arm_vqrdmulhq_m_n_s16 (__ARM_mve_coerce(__p0, > int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce3(p2, > int), p3), \ > - int > (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve > _type_int_n]: __arm_vqrdmulhq_m_n_s32 (__ARM_mve_coerce(__p0, > int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce3(p2, > int), p3));}) > - > #define __arm_vqrdmlsdhxq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ > __typeof(p1) __p1 = (p1); \ > __typeof(p2) __p2 = (p2); \ > -- > 2.34.1
RE: [PATCH 05/23] arm: [MVE intrinsics] rework vqrdmulhq
Kyrylo Tkachov via Gcc-patches Fri, 05 May 2023 03:01:53 -0700
- RE: [PATCH 04/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 11/23] arm: [MVE intrinsics] add un... Christophe Lyon via Gcc-patches
- RE: [PATCH 11/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 09/23] arm: [MVE intrinsics] add su... Christophe Lyon via Gcc-patches
- RE: [PATCH 09/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 08/23] arm: [MVE intrinsics] add bi... Christophe Lyon via Gcc-patches
- RE: [PATCH 08/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 07/23] arm: [MVE intrinsics] rework... Christophe Lyon via Gcc-patches
- RE: [PATCH 07/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 05/23] arm: [MVE intrinsics] rework... Christophe Lyon via Gcc-patches
- RE: [PATCH 05/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 21/23] arm: [MVE intrinsics] add bi... Christophe Lyon via Gcc-patches
- RE: [PATCH 21/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 18/23] arm: [MVE intrinsics] add bi... Christophe Lyon via Gcc-patches
- RE: [PATCH 18/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 03/23] arm: [MVE intrinsics] rework... Christophe Lyon via Gcc-patches
- RE: [PATCH 03/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 22/23] arm: [MVE intrinsics] factor... Christophe Lyon via Gcc-patches
- RE: [PATCH 22/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches
- [PATCH 13/23] arm: [MVE intrinsics] factor... Christophe Lyon via Gcc-patches
- RE: [PATCH 13/23] arm: [MVE intrinsic... Kyrylo Tkachov via Gcc-patches