Implement vabdq using the new MVE builtins framework. 2022-09-08 Christophe Lyon <christophe.l...@arm.com>
gcc/ * config/arm/arm-mve-builtins-base.cc (FUNCTION_WITHOUT_N): New. (vabdq): New. * config/arm/arm-mve-builtins-base.def (vabdq): New. * config/arm/arm-mve-builtins-base.h (vabdq): New. * config/arm/arm_mve.h (vabdq): Remove. (vabdq_m): Remove. (vabdq_x): Remove. (vabdq_u8): Remove. (vabdq_s8): Remove. (vabdq_u16): Remove. (vabdq_s16): Remove. (vabdq_u32): Remove. (vabdq_s32): Remove. (vabdq_f16): Remove. (vabdq_f32): Remove. (vabdq_m_s8): Remove. (vabdq_m_s32): Remove. (vabdq_m_s16): Remove. (vabdq_m_u8): Remove. (vabdq_m_u32): Remove. (vabdq_m_u16): Remove. (vabdq_m_f32): Remove. (vabdq_m_f16): Remove. (vabdq_x_s8): Remove. (vabdq_x_s16): Remove. (vabdq_x_s32): Remove. (vabdq_x_u8): Remove. (vabdq_x_u16): Remove. (vabdq_x_u32): Remove. (vabdq_x_f16): Remove. (vabdq_x_f32): Remove. (__arm_vabdq_u8): Remove. (__arm_vabdq_s8): Remove. (__arm_vabdq_u16): Remove. (__arm_vabdq_s16): Remove. (__arm_vabdq_u32): Remove. (__arm_vabdq_s32): Remove. (__arm_vabdq_m_s8): Remove. (__arm_vabdq_m_s32): Remove. (__arm_vabdq_m_s16): Remove. (__arm_vabdq_m_u8): Remove. (__arm_vabdq_m_u32): Remove. (__arm_vabdq_m_u16): Remove. (__arm_vabdq_x_s8): Remove. (__arm_vabdq_x_s16): Remove. (__arm_vabdq_x_s32): Remove. (__arm_vabdq_x_u8): Remove. (__arm_vabdq_x_u16): Remove. (__arm_vabdq_x_u32): Remove. (__arm_vabdq_f16): Remove. (__arm_vabdq_f32): Remove. (__arm_vabdq_m_f32): Remove. (__arm_vabdq_m_f16): Remove. (__arm_vabdq_x_f16): Remove. (__arm_vabdq_x_f32): Remove. (__arm_vabdq): Remove. (__arm_vabdq_m): Remove. (__arm_vabdq_x): Remove. --- gcc/config/arm/arm-mve-builtins-base.cc | 10 + gcc/config/arm/arm-mve-builtins-base.def | 2 + gcc/config/arm/arm-mve-builtins-base.h | 1 + gcc/config/arm/arm_mve.h | 431 ----------------------- 4 files changed, 13 insertions(+), 431 deletions(-) diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc index 8c125657c67..a74119db917 100644 --- a/gcc/config/arm/arm-mve-builtins-base.cc +++ b/gcc/config/arm/arm-mve-builtins-base.cc @@ -146,6 +146,16 @@ namespace arm_mve { UNSPEC##_M_S, -1, -1, \ UNSPEC##_M_N_S, -1, -1)) + /* Helper for builtins with only unspec codes, _m predicated + overrides, but no _n version. */ +#define FUNCTION_WITHOUT_N(NAME, UNSPEC) FUNCTION \ + (NAME, unspec_mve_function_exact_insn, \ + (UNSPEC##_S, UNSPEC##_U, UNSPEC##_F, \ + -1, -1, -1, \ + UNSPEC##_M_S, UNSPEC##_M_U, UNSPEC##_M_F, \ + -1, -1, -1)) + +FUNCTION_WITHOUT_N (vabdq, VABDQ) FUNCTION_WITH_RTX_M_N (vaddq, PLUS, VADDQ) FUNCTION_WITH_RTX_M (vandq, AND, VANDQ) FUNCTION_WITHOUT_M_N (vcreateq, VCREATEQ) diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def index 5b9966341ce..9230837fd43 100644 --- a/gcc/config/arm/arm-mve-builtins-base.def +++ b/gcc/config/arm/arm-mve-builtins-base.def @@ -18,6 +18,7 @@ <http://www.gnu.org/licenses/>. */ #define REQUIRES_FLOAT false +DEF_MVE_FUNCTION (vabdq, binary, all_integer, mx_or_none) DEF_MVE_FUNCTION (vaddq, binary_opt_n, all_integer, mx_or_none) DEF_MVE_FUNCTION (vandq, binary, all_integer, mx_or_none) DEF_MVE_FUNCTION (vcreateq, create, all_integer_with_64, none) @@ -41,6 +42,7 @@ DEF_MVE_FUNCTION (vuninitializedq, inherent, all_integer_with_64, none) #undef REQUIRES_FLOAT #define REQUIRES_FLOAT true +DEF_MVE_FUNCTION (vabdq, binary, all_float, mx_or_none) DEF_MVE_FUNCTION (vaddq, binary_opt_n, all_float, mx_or_none) DEF_MVE_FUNCTION (vandq, binary, all_float, mx_or_none) DEF_MVE_FUNCTION (vcreateq, create, all_float, none) diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h index eeb747d52ad..d9d45d1925a 100644 --- a/gcc/config/arm/arm-mve-builtins-base.h +++ b/gcc/config/arm/arm-mve-builtins-base.h @@ -23,6 +23,7 @@ namespace arm_mve { namespace functions { +extern const function_base *const vabdq; extern const function_base *const vaddq; extern const function_base *const vandq; extern const function_base *const vcreateq; diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 44b383dbe08..175d9955c33 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -77,7 +77,6 @@ #define vbicq(__a, __b) __arm_vbicq(__a, __b) #define vaddvq_p(__a, __p) __arm_vaddvq_p(__a, __p) #define vaddvaq(__a, __b) __arm_vaddvaq(__a, __b) -#define vabdq(__a, __b) __arm_vabdq(__a, __b) #define vshlq_r(__a, __b) __arm_vshlq_r(__a, __b) #define vqshlq(__a, __b) __arm_vqshlq(__a, __b) #define vqshlq_r(__a, __b) __arm_vqshlq_r(__a, __b) @@ -218,7 +217,6 @@ #define vqshluq_m(__inactive, __a, __imm, __p) __arm_vqshluq_m(__inactive, __a, __imm, __p) #define vabavq_p(__a, __b, __c, __p) __arm_vabavq_p(__a, __b, __c, __p) #define vshlq_m(__inactive, __a, __b, __p) __arm_vshlq_m(__inactive, __a, __b, __p) -#define vabdq_m(__inactive, __a, __b, __p) __arm_vabdq_m(__inactive, __a, __b, __p) #define vbicq_m(__inactive, __a, __b, __p) __arm_vbicq_m(__inactive, __a, __b, __p) #define vbrsrq_m(__inactive, __a, __b, __p) __arm_vbrsrq_m(__inactive, __a, __b, __p) #define vcaddq_rot270_m(__inactive, __a, __b, __p) __arm_vcaddq_rot270_m(__inactive, __a, __b, __p) @@ -355,7 +353,6 @@ #define viwdupq_x_u32(__a, __b, __imm, __p) __arm_viwdupq_x_u32(__a, __b, __imm, __p) #define vminq_x(__a, __b, __p) __arm_vminq_x(__a, __b, __p) #define vmaxq_x(__a, __b, __p) __arm_vmaxq_x(__a, __b, __p) -#define vabdq_x(__a, __b, __p) __arm_vabdq_x(__a, __b, __p) #define vabsq_x(__a, __p) __arm_vabsq_x(__a, __p) #define vclsq_x(__a, __p) __arm_vclsq_x(__a, __p) #define vclzq_x(__a, __p) __arm_vclzq_x(__a, __p) @@ -652,7 +649,6 @@ #define vbicq_u8(__a, __b) __arm_vbicq_u8(__a, __b) #define vaddvq_p_u8(__a, __p) __arm_vaddvq_p_u8(__a, __p) #define vaddvaq_u8(__a, __b) __arm_vaddvaq_u8(__a, __b) -#define vabdq_u8(__a, __b) __arm_vabdq_u8(__a, __b) #define vshlq_r_u8(__a, __b) __arm_vshlq_r_u8(__a, __b) #define vqshlq_u8(__a, __b) __arm_vqshlq_u8(__a, __b) #define vqshlq_r_u8(__a, __b) __arm_vqshlq_r_u8(__a, __b) @@ -698,7 +694,6 @@ #define vbrsrq_n_s8(__a, __b) __arm_vbrsrq_n_s8(__a, __b) #define vbicq_s8(__a, __b) __arm_vbicq_s8(__a, __b) #define vaddvaq_s8(__a, __b) __arm_vaddvaq_s8(__a, __b) -#define vabdq_s8(__a, __b) __arm_vabdq_s8(__a, __b) #define vshlq_n_s8(__a, __imm) __arm_vshlq_n_s8(__a, __imm) #define vrshrq_n_s8(__a, __imm) __arm_vrshrq_n_s8(__a, __imm) #define vqshlq_n_s8(__a, __imm) __arm_vqshlq_n_s8(__a, __imm) @@ -722,7 +717,6 @@ #define vbicq_u16(__a, __b) __arm_vbicq_u16(__a, __b) #define vaddvq_p_u16(__a, __p) __arm_vaddvq_p_u16(__a, __p) #define vaddvaq_u16(__a, __b) __arm_vaddvaq_u16(__a, __b) -#define vabdq_u16(__a, __b) __arm_vabdq_u16(__a, __b) #define vshlq_r_u16(__a, __b) __arm_vshlq_r_u16(__a, __b) #define vqshlq_u16(__a, __b) __arm_vqshlq_u16(__a, __b) #define vqshlq_r_u16(__a, __b) __arm_vqshlq_r_u16(__a, __b) @@ -768,7 +762,6 @@ #define vbrsrq_n_s16(__a, __b) __arm_vbrsrq_n_s16(__a, __b) #define vbicq_s16(__a, __b) __arm_vbicq_s16(__a, __b) #define vaddvaq_s16(__a, __b) __arm_vaddvaq_s16(__a, __b) -#define vabdq_s16(__a, __b) __arm_vabdq_s16(__a, __b) #define vshlq_n_s16(__a, __imm) __arm_vshlq_n_s16(__a, __imm) #define vrshrq_n_s16(__a, __imm) __arm_vrshrq_n_s16(__a, __imm) #define vqshlq_n_s16(__a, __imm) __arm_vqshlq_n_s16(__a, __imm) @@ -792,7 +785,6 @@ #define vbicq_u32(__a, __b) __arm_vbicq_u32(__a, __b) #define vaddvq_p_u32(__a, __p) __arm_vaddvq_p_u32(__a, __p) #define vaddvaq_u32(__a, __b) __arm_vaddvaq_u32(__a, __b) -#define vabdq_u32(__a, __b) __arm_vabdq_u32(__a, __b) #define vshlq_r_u32(__a, __b) __arm_vshlq_r_u32(__a, __b) #define vqshlq_u32(__a, __b) __arm_vqshlq_u32(__a, __b) #define vqshlq_r_u32(__a, __b) __arm_vqshlq_r_u32(__a, __b) @@ -838,7 +830,6 @@ #define vbrsrq_n_s32(__a, __b) __arm_vbrsrq_n_s32(__a, __b) #define vbicq_s32(__a, __b) __arm_vbicq_s32(__a, __b) #define vaddvaq_s32(__a, __b) __arm_vaddvaq_s32(__a, __b) -#define vabdq_s32(__a, __b) __arm_vabdq_s32(__a, __b) #define vshlq_n_s32(__a, __imm) __arm_vshlq_n_s32(__a, __imm) #define vrshrq_n_s32(__a, __imm) __arm_vrshrq_n_s32(__a, __imm) #define vqshlq_n_s32(__a, __imm) __arm_vqshlq_n_s32(__a, __imm) @@ -894,7 +885,6 @@ #define vcaddq_rot90_f16(__a, __b) __arm_vcaddq_rot90_f16(__a, __b) #define vcaddq_rot270_f16(__a, __b) __arm_vcaddq_rot270_f16(__a, __b) #define vbicq_f16(__a, __b) __arm_vbicq_f16(__a, __b) -#define vabdq_f16(__a, __b) __arm_vabdq_f16(__a, __b) #define vshlltq_n_s8(__a, __imm) __arm_vshlltq_n_s8(__a, __imm) #define vshllbq_n_s8(__a, __imm) __arm_vshllbq_n_s8(__a, __imm) #define vbicq_n_s16(__a, __imm) __arm_vbicq_n_s16(__a, __imm) @@ -950,7 +940,6 @@ #define vcaddq_rot90_f32(__a, __b) __arm_vcaddq_rot90_f32(__a, __b) #define vcaddq_rot270_f32(__a, __b) __arm_vcaddq_rot270_f32(__a, __b) #define vbicq_f32(__a, __b) __arm_vbicq_f32(__a, __b) -#define vabdq_f32(__a, __b) __arm_vabdq_f32(__a, __b) #define vshlltq_n_s16(__a, __imm) __arm_vshlltq_n_s16(__a, __imm) #define vshllbq_n_s16(__a, __imm) __arm_vshllbq_n_s16(__a, __imm) #define vbicq_n_s32(__a, __imm) __arm_vbicq_n_s32(__a, __imm) @@ -1460,12 +1449,6 @@ #define vshlq_m_u32(__inactive, __a, __b, __p) __arm_vshlq_m_u32(__inactive, __a, __b, __p) #define vabavq_p_u32(__a, __b, __c, __p) __arm_vabavq_p_u32(__a, __b, __c, __p) #define vshlq_m_s32(__inactive, __a, __b, __p) __arm_vshlq_m_s32(__inactive, __a, __b, __p) -#define vabdq_m_s8(__inactive, __a, __b, __p) __arm_vabdq_m_s8(__inactive, __a, __b, __p) -#define vabdq_m_s32(__inactive, __a, __b, __p) __arm_vabdq_m_s32(__inactive, __a, __b, __p) -#define vabdq_m_s16(__inactive, __a, __b, __p) __arm_vabdq_m_s16(__inactive, __a, __b, __p) -#define vabdq_m_u8(__inactive, __a, __b, __p) __arm_vabdq_m_u8(__inactive, __a, __b, __p) -#define vabdq_m_u32(__inactive, __a, __b, __p) __arm_vabdq_m_u32(__inactive, __a, __b, __p) -#define vabdq_m_u16(__inactive, __a, __b, __p) __arm_vabdq_m_u16(__inactive, __a, __b, __p) #define vbicq_m_s8(__inactive, __a, __b, __p) __arm_vbicq_m_s8(__inactive, __a, __b, __p) #define vbicq_m_s32(__inactive, __a, __b, __p) __arm_vbicq_m_s32(__inactive, __a, __b, __p) #define vbicq_m_s16(__inactive, __a, __b, __p) __arm_vbicq_m_s16(__inactive, __a, __b, __p) @@ -1700,8 +1683,6 @@ #define vshrntq_m_n_s16(__a, __b, __imm, __p) __arm_vshrntq_m_n_s16(__a, __b, __imm, __p) #define vshrntq_m_n_u32(__a, __b, __imm, __p) __arm_vshrntq_m_n_u32(__a, __b, __imm, __p) #define vshrntq_m_n_u16(__a, __b, __imm, __p) __arm_vshrntq_m_n_u16(__a, __b, __imm, __p) -#define vabdq_m_f32(__inactive, __a, __b, __p) __arm_vabdq_m_f32(__inactive, __a, __b, __p) -#define vabdq_m_f16(__inactive, __a, __b, __p) __arm_vabdq_m_f16(__inactive, __a, __b, __p) #define vbicq_m_f32(__inactive, __a, __b, __p) __arm_vbicq_m_f32(__inactive, __a, __b, __p) #define vbicq_m_f16(__inactive, __a, __b, __p) __arm_vbicq_m_f16(__inactive, __a, __b, __p) #define vbrsrq_m_n_f32(__inactive, __a, __b, __p) __arm_vbrsrq_m_n_f32(__inactive, __a, __b, __p) @@ -2060,12 +2041,6 @@ #define vmaxq_x_u8(__a, __b, __p) __arm_vmaxq_x_u8(__a, __b, __p) #define vmaxq_x_u16(__a, __b, __p) __arm_vmaxq_x_u16(__a, __b, __p) #define vmaxq_x_u32(__a, __b, __p) __arm_vmaxq_x_u32(__a, __b, __p) -#define vabdq_x_s8(__a, __b, __p) __arm_vabdq_x_s8(__a, __b, __p) -#define vabdq_x_s16(__a, __b, __p) __arm_vabdq_x_s16(__a, __b, __p) -#define vabdq_x_s32(__a, __b, __p) __arm_vabdq_x_s32(__a, __b, __p) -#define vabdq_x_u8(__a, __b, __p) __arm_vabdq_x_u8(__a, __b, __p) -#define vabdq_x_u16(__a, __b, __p) __arm_vabdq_x_u16(__a, __b, __p) -#define vabdq_x_u32(__a, __b, __p) __arm_vabdq_x_u32(__a, __b, __p) #define vabsq_x_s8(__a, __p) __arm_vabsq_x_s8(__a, __p) #define vabsq_x_s16(__a, __p) __arm_vabsq_x_s16(__a, __p) #define vabsq_x_s32(__a, __p) __arm_vabsq_x_s32(__a, __p) @@ -2201,8 +2176,6 @@ #define vminnmq_x_f32(__a, __b, __p) __arm_vminnmq_x_f32(__a, __b, __p) #define vmaxnmq_x_f16(__a, __b, __p) __arm_vmaxnmq_x_f16(__a, __b, __p) #define vmaxnmq_x_f32(__a, __b, __p) __arm_vmaxnmq_x_f32(__a, __b, __p) -#define vabdq_x_f16(__a, __b, __p) __arm_vabdq_x_f16(__a, __b, __p) -#define vabdq_x_f32(__a, __b, __p) __arm_vabdq_x_f32(__a, __b, __p) #define vabsq_x_f16(__a, __p) __arm_vabsq_x_f16(__a, __p) #define vabsq_x_f32(__a, __p) __arm_vabsq_x_f32(__a, __p) #define vnegq_x_f16(__a, __p) __arm_vnegq_x_f16(__a, __p) @@ -3211,13 +3184,6 @@ __arm_vaddvaq_u8 (uint32_t __a, uint8x16_t __b) return __builtin_mve_vaddvaq_uv16qi (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __builtin_mve_vabdq_uv16qi (__a, __b); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r_u8 (uint8x16_t __a, int32_t __b) @@ -3533,13 +3499,6 @@ __arm_vaddvaq_s8 (int32_t __a, int8x16_t __b) return __builtin_mve_vaddvaq_sv16qi (__a, __b); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_mve_vabdq_sv16qi (__a, __b); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n_s8 (int8x16_t __a, const int __imm) @@ -3703,13 +3662,6 @@ __arm_vaddvaq_u16 (uint32_t __a, uint16x8_t __b) return __builtin_mve_vaddvaq_uv8hi (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __builtin_mve_vabdq_uv8hi (__a, __b); -} - __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r_u16 (uint16x8_t __a, int32_t __b) @@ -4025,13 +3977,6 @@ __arm_vaddvaq_s16 (int32_t __a, int16x8_t __b) return __builtin_mve_vaddvaq_sv8hi (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_mve_vabdq_sv8hi (__a, __b); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n_s16 (int16x8_t __a, const int __imm) @@ -4195,13 +4140,6 @@ __arm_vaddvaq_u32 (uint32_t __a, uint32x4_t __b) return __builtin_mve_vaddvaq_uv4si (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __builtin_mve_vabdq_uv4si (__a, __b); -} - __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r_u32 (uint32x4_t __a, int32_t __b) @@ -4517,13 +4455,6 @@ __arm_vaddvaq_s32 (int32_t __a, int32x4_t __b) return __builtin_mve_vaddvaq_sv4si (__a, __b); } -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_mve_vabdq_sv4si (__a, __b); -} - __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n_s32 (int32x4_t __a, const int __imm) @@ -7715,48 +7646,6 @@ __arm_vshlq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred1 return __builtin_mve_vshlq_m_sv4si (__inactive, __a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv8hi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_u8 (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv8hi (__inactive, __a, __b, __p); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) @@ -11432,48 +11321,6 @@ __arm_vmaxq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) return __builtin_mve_vmaxq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv16qi (__arm_vuninitializedq_s8 (), __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_u8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv16qi (__arm_vuninitializedq_u8 (), __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_u16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vabsq_x_s8 (int8x16_t __a, mve_pred16_t __p) @@ -13692,13 +13539,6 @@ __arm_vbicq_f16 (float16x8_t __a, float16x8_t __b) return __builtin_mve_vbicq_fv8hf (__a, __b); } -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_f16 (float16x8_t __a, float16x8_t __b) -{ - return __builtin_mve_vabdq_fv8hf (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq_n_f32 (float32x4_t __a, float32_t __b) @@ -13895,13 +13735,6 @@ __arm_vbicq_f32 (float32x4_t __a, float32x4_t __b) return __builtin_mve_vbicq_fv4sf (__a, __b); } -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __builtin_mve_vabdq_fv4sf (__a, __b); -} - __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcvttq_f16_f32 (float16x8_t __a, float32x4_t __b) @@ -14666,20 +14499,6 @@ __arm_vcvtq_m_n_f32_s32 (float32x4_t __inactive, int32x4_t __a, const int __imm6 return __builtin_mve_vcvtq_m_n_to_f_sv4sf (__inactive, __a, __imm6, __p); } -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_fv4sf (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m_f16 (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_fv8hf (__inactive, __a, __b, __p); -} - __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) @@ -15274,20 +15093,6 @@ __arm_vmaxnmq_x_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) return __builtin_mve_vmaxnmq_m_fv4sf (__arm_vuninitializedq_f32 (), __a, __b, __p); } -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vabdq_m_fv4sf (__arm_vuninitializedq_f32 (), __a, __b, __p); -} - __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vabsq_x_f16 (float16x8_t __a, mve_pred16_t __p) @@ -16652,13 +16457,6 @@ __arm_vaddvaq (uint32_t __a, uint8x16_t __b) return __arm_vaddvaq_u8 (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (uint8x16_t __a, uint8x16_t __b) -{ - return __arm_vabdq_u8 (__a, __b); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r (uint8x16_t __a, int32_t __b) @@ -16974,13 +16772,6 @@ __arm_vaddvaq (int32_t __a, int8x16_t __b) return __arm_vaddvaq_s8 (__a, __b); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (int8x16_t __a, int8x16_t __b) -{ - return __arm_vabdq_s8 (__a, __b); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n (int8x16_t __a, const int __imm) @@ -17142,13 +16933,6 @@ __arm_vaddvaq (uint32_t __a, uint16x8_t __b) return __arm_vaddvaq_u16 (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (uint16x8_t __a, uint16x8_t __b) -{ - return __arm_vabdq_u16 (__a, __b); -} - __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r (uint16x8_t __a, int32_t __b) @@ -17464,13 +17248,6 @@ __arm_vaddvaq (int32_t __a, int16x8_t __b) return __arm_vaddvaq_s16 (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (int16x8_t __a, int16x8_t __b) -{ - return __arm_vabdq_s16 (__a, __b); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n (int16x8_t __a, const int __imm) @@ -17632,13 +17409,6 @@ __arm_vaddvaq (uint32_t __a, uint32x4_t __b) return __arm_vaddvaq_u32 (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (uint32x4_t __a, uint32x4_t __b) -{ - return __arm_vabdq_u32 (__a, __b); -} - __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_r (uint32x4_t __a, int32_t __b) @@ -17954,13 +17724,6 @@ __arm_vaddvaq (int32_t __a, int32x4_t __b) return __arm_vaddvaq_s32 (__a, __b); } -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (int32x4_t __a, int32x4_t __b) -{ - return __arm_vabdq_s32 (__a, __b); -} - __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vshlq_n (int32x4_t __a, const int __imm) @@ -21111,48 +20874,6 @@ __arm_vshlq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t return __arm_vshlq_m_s32 (__inactive, __a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_s8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_s32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_s16 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_u8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_u32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_u16 (__inactive, __a, __b, __p); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) @@ -24359,48 +24080,6 @@ __arm_vmaxq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) return __arm_vmaxq_x_u32 (__a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_s8 (__a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_s16 (__a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_s32 (__a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_u8 (__a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_u16 (__a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_u32 (__a, __b, __p); -} - __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vabsq_x (int8x16_t __a, mve_pred16_t __p) @@ -26195,13 +25874,6 @@ __arm_vbicq (float16x8_t __a, float16x8_t __b) return __arm_vbicq_f16 (__a, __b); } -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (float16x8_t __a, float16x8_t __b) -{ - return __arm_vabdq_f16 (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq (float32x4_t __a, float32_t __b) @@ -26398,13 +26070,6 @@ __arm_vbicq (float32x4_t __a, float32x4_t __b) return __arm_vbicq_f32 (__a, __b); } -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq (float32x4_t __a, float32x4_t __b) -{ - return __arm_vabdq_f32 (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpeqq_m (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) @@ -27154,20 +26819,6 @@ __arm_vcvtq_m_n (float32x4_t __inactive, int32x4_t __a, const int __imm6, mve_pr return __arm_vcvtq_m_n_f32_s32 (__inactive, __a, __imm6, __p); } -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_f32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_m_f16 (__inactive, __a, __b, __p); -} - __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) @@ -27686,20 +27337,6 @@ __arm_vmaxnmq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) return __arm_vmaxnmq_x_f32 (__a, __b, __p); } -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_f16 (__a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabdq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_vabdq_x_f32 (__a, __b, __p); -} - __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vabsq_x (float16x8_t __a, mve_pred16_t __p) @@ -28554,18 +28191,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_n_f16_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_n_f32_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));}) -#define __arm_vabdq(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_vabdq_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_vabdq_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_vabdq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t)), \ - int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));}) - #define __arm_vbicq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ @@ -29746,19 +29371,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmpgeq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcmpgeq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));}) -#define __arm_vabdq_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_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_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_vabdq_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_vabdq_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_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \ - int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));}) - #define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -30228,18 +29840,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_wb_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ int (*)[__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_base_wb_p_f32 (p0, p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) -#define __arm_vabdq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ - __typeof(p2) __p2 = (p2); \ - _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_x_s8 (__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_vabdq_x_s16 (__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_vabdq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vabdq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \ - int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vabdq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));}) - #define __arm_vabsq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int8x16_t]: __arm_vabsq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \ @@ -30762,16 +30362,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vbicq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));}) -#define __arm_vabdq(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_vabdq_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_vabdq_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_vabdq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));}) - #define __arm_vcmpeqq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ @@ -31416,17 +31006,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_p_u16(__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_p_u32(__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) -#define __arm_vabdq_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_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_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_vabdq_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_vabdq_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_uint8x16_t][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_m_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) - #define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -31834,16 +31413,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t]: __arm_vrev64q_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vrev64q_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2));}) -#define __arm_vabdq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ - __typeof(p2) __p2 = (p2); \ - _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vabdq_x_s8 (__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_vabdq_x_s16 (__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_vabdq_x_s32 (__ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabdq_x_u8 (__ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabdq_x_u16 (__ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabdq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) - #define __arm_vbicq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ -- 2.34.1