diff options
author | Christophe Lyon <christophe.lyon@arm.com> | 2023-02-21 23:05:21 +0000 |
---|---|---|
committer | Christophe Lyon <christophe.lyon@arm.com> | 2023-05-11 21:04:10 +0200 |
commit | 817a406a6fd83c1b699fbc7e77f874168004c9e1 (patch) | |
tree | 248dc9cb8674e288b350a6e499929bb32d02f0a6 | |
parent | 1af6d1db3e31475e76c49f91d06a8c89edd495dc (diff) | |
download | gcc-817a406a6fd83c1b699fbc7e77f874168004c9e1.tar.gz |
arm: [MVE intrinsics] rework vabavq
Implement vabavq using the new MVE builtins framework.
2022-10-25 Christophe Lyon <christophe.lyon@arm.com>
gcc/
* config/arm/arm-mve-builtins-base.cc (vabavq): New.
* config/arm/arm-mve-builtins-base.def (vabavq): New.
* config/arm/arm-mve-builtins-base.h (vabavq): New.
* config/arm/arm_mve.h (vabavq): Remove.
(vabavq_p): Remove.
(vabavq_s8): Remove.
(vabavq_s16): Remove.
(vabavq_s32): Remove.
(vabavq_u8): Remove.
(vabavq_u16): Remove.
(vabavq_u32): Remove.
(vabavq_p_s8): Remove.
(vabavq_p_u8): Remove.
(vabavq_p_s16): Remove.
(vabavq_p_u16): Remove.
(vabavq_p_s32): Remove.
(vabavq_p_u32): Remove.
(__arm_vabavq_s8): Remove.
(__arm_vabavq_s16): Remove.
(__arm_vabavq_s32): Remove.
(__arm_vabavq_u8): Remove.
(__arm_vabavq_u16): Remove.
(__arm_vabavq_u32): Remove.
(__arm_vabavq_p_s8): Remove.
(__arm_vabavq_p_u8): Remove.
(__arm_vabavq_p_s16): Remove.
(__arm_vabavq_p_u16): Remove.
(__arm_vabavq_p_s32): Remove.
(__arm_vabavq_p_u32): Remove.
(__arm_vabavq): Remove.
(__arm_vabavq_p): Remove.
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.cc | 1 | ||||
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.def | 1 | ||||
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.h | 1 | ||||
-rw-r--r-- | gcc/config/arm/arm_mve.h | 215 |
4 files changed, 3 insertions, 215 deletions
diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc index 8a5ab990337..a81cf4cba5e 100644 --- a/gcc/config/arm/arm-mve-builtins-base.cc +++ b/gcc/config/arm/arm-mve-builtins-base.cc @@ -241,6 +241,7 @@ namespace arm_mve { (-1, -1, UNSPEC##_F, \ -1, -1, UNSPEC##_P_F)) +FUNCTION_PRED_P_S_U (vabavq, VABAVQ) FUNCTION_WITHOUT_N (vabdq, VABDQ) FUNCTION (vabsq, unspec_based_mve_function_exact_insn, (ABS, ABS, ABS, -1, -1, -1, VABSQ_M_S, -1, VABSQ_M_F, -1, -1, -1)) FUNCTION_WITH_RTX_M_N (vaddq, PLUS, VADDQ) diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def index cf0ed4b58df..934f45bc220 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 (vabavq, binary_acca_int32, all_integer, p_or_none) DEF_MVE_FUNCTION (vabdq, binary, all_integer, mx_or_none) DEF_MVE_FUNCTION (vabsq, unary, all_signed, mx_or_none) DEF_MVE_FUNCTION (vaddlvaq, unary_widen_acc, integer_32, p_or_none) diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h index 4f09bebf1cb..1d29a940200 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 vabavq; extern const function_base *const vabdq; extern const function_base *const vabsq; extern const function_base *const vaddlvaq; diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 86fa7fcf789..f8afe19e86e 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -65,7 +65,6 @@ #define vrmlsldavhxq(__a, __b) __arm_vrmlsldavhxq(__a, __b) #define vrmlsldavhq(__a, __b) __arm_vrmlsldavhq(__a, __b) #define vrmlaldavhxq(__a, __b) __arm_vrmlaldavhxq(__a, __b) -#define vabavq(__a, __b, __c) __arm_vabavq(__a, __b, __c) #define vbicq_m_n(__a, __imm, __p) __arm_vbicq_m_n(__a, __imm, __p) #define vrmlaldavhaq(__a, __b, __c) __arm_vrmlaldavhaq(__a, __b, __c) #define vshlcq(__a, __b, __imm) __arm_vshlcq(__a, __b, __imm) @@ -104,7 +103,6 @@ #define vmlsldavxq_p(__a, __b, __p) __arm_vmlsldavxq_p(__a, __b, __p) #define vsriq_m(__a, __b, __imm, __p) __arm_vsriq_m(__a, __b, __imm, __p) #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 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) @@ -447,9 +445,6 @@ #define vrmlaldavhq_s32(__a, __b) __arm_vrmlaldavhq_s32(__a, __b) #define vcvttq_f16_f32(__a, __b) __arm_vcvttq_f16_f32(__a, __b) #define vcvtbq_f16_f32(__a, __b) __arm_vcvtbq_f16_f32(__a, __b) -#define vabavq_s8(__a, __b, __c) __arm_vabavq_s8(__a, __b, __c) -#define vabavq_s16(__a, __b, __c) __arm_vabavq_s16(__a, __b, __c) -#define vabavq_s32(__a, __b, __c) __arm_vabavq_s32(__a, __b, __c) #define vbicq_m_n_s16(__a, __imm, __p) __arm_vbicq_m_n_s16(__a, __imm, __p) #define vbicq_m_n_s32(__a, __imm, __p) __arm_vbicq_m_n_s32(__a, __imm, __p) #define vbicq_m_n_u16(__a, __imm, __p) __arm_vbicq_m_n_u16(__a, __imm, __p) @@ -470,9 +465,6 @@ #define vshlcq_u16(__a, __b, __imm) __arm_vshlcq_u16(__a, __b, __imm) #define vshlcq_s32(__a, __b, __imm) __arm_vshlcq_s32(__a, __b, __imm) #define vshlcq_u32(__a, __b, __imm) __arm_vshlcq_u32(__a, __b, __imm) -#define vabavq_u8(__a, __b, __c) __arm_vabavq_u8(__a, __b, __c) -#define vabavq_u16(__a, __b, __c) __arm_vabavq_u16(__a, __b, __c) -#define vabavq_u32(__a, __b, __c) __arm_vabavq_u32(__a, __b, __c) #define vpselq_u8(__a, __b, __p) __arm_vpselq_u8(__a, __b, __p) #define vpselq_s8(__a, __b, __p) __arm_vpselq_s8(__a, __b, __p) #define vmvnq_m_u8(__inactive, __a, __p) __arm_vmvnq_m_u8(__inactive, __a, __p) @@ -620,22 +612,16 @@ #define vsriq_m_n_s8(__a, __b, __imm, __p) __arm_vsriq_m_n_s8(__a, __b, __imm, __p) #define vcvtq_m_n_f16_u16(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_f16_u16(__inactive, __a, __imm6, __p) #define vqshluq_m_n_s8(__inactive, __a, __imm, __p) __arm_vqshluq_m_n_s8(__inactive, __a, __imm, __p) -#define vabavq_p_s8(__a, __b, __c, __p) __arm_vabavq_p_s8(__a, __b, __c, __p) #define vsriq_m_n_u8(__a, __b, __imm, __p) __arm_vsriq_m_n_u8(__a, __b, __imm, __p) -#define vabavq_p_u8(__a, __b, __c, __p) __arm_vabavq_p_u8(__a, __b, __c, __p) #define vcvtq_m_n_f16_s16(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_f16_s16(__inactive, __a, __imm6, __p) #define vsriq_m_n_s16(__a, __b, __imm, __p) __arm_vsriq_m_n_s16(__a, __b, __imm, __p) #define vcvtq_m_n_f32_u32(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_f32_u32(__inactive, __a, __imm6, __p) #define vqshluq_m_n_s16(__inactive, __a, __imm, __p) __arm_vqshluq_m_n_s16(__inactive, __a, __imm, __p) -#define vabavq_p_s16(__a, __b, __c, __p) __arm_vabavq_p_s16(__a, __b, __c, __p) #define vsriq_m_n_u16(__a, __b, __imm, __p) __arm_vsriq_m_n_u16(__a, __b, __imm, __p) -#define vabavq_p_u16(__a, __b, __c, __p) __arm_vabavq_p_u16(__a, __b, __c, __p) #define vcvtq_m_n_f32_s32(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_f32_s32(__inactive, __a, __imm6, __p) #define vsriq_m_n_s32(__a, __b, __imm, __p) __arm_vsriq_m_n_s32(__a, __b, __imm, __p) #define vqshluq_m_n_s32(__inactive, __a, __imm, __p) __arm_vqshluq_m_n_s32(__inactive, __a, __imm, __p) -#define vabavq_p_s32(__a, __b, __c, __p) __arm_vabavq_p_s32(__a, __b, __c, __p) #define vsriq_m_n_u32(__a, __b, __imm, __p) __arm_vsriq_m_n_u32(__a, __b, __imm, __p) -#define vabavq_p_u32(__a, __b, __c, __p) __arm_vabavq_p_u32(__a, __b, __c, __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) @@ -2094,48 +2080,6 @@ __arm_vrmlaldavhq_s32 (int32x4_t __a, int32x4_t __b) return __builtin_mve_vrmlaldavhq_sv4si (__a, __b); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_s8 (uint32_t __a, int8x16_t __b, int8x16_t __c) -{ - return __builtin_mve_vabavq_sv16qi (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_s16 (uint32_t __a, int16x8_t __b, int16x8_t __c) -{ - return __builtin_mve_vabavq_sv8hi (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_s32 (uint32_t __a, int32x4_t __b, int32x4_t __c) -{ - return __builtin_mve_vabavq_sv4si (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_u8 (uint32_t __a, uint8x16_t __b, uint8x16_t __c) -{ - return __builtin_mve_vabavq_uv16qi(__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_u16 (uint32_t __a, uint16x8_t __b, uint16x8_t __c) -{ - return __builtin_mve_vabavq_uv8hi(__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_u32 (uint32_t __a, uint32x4_t __b, uint32x4_t __c) -{ - return __builtin_mve_vabavq_uv4si(__a, __b, __c); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m_n_s16 (int16x8_t __a, const int __imm, mve_pred16_t __p) @@ -2988,13 +2932,6 @@ __arm_vqshluq_m_n_s8 (uint8x16_t __inactive, int8x16_t __a, const int __imm, mve return __builtin_mve_vqshluq_m_n_sv16qi (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_s8 (uint32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_sv16qi (__a, __b, __c, __p); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_t __p) @@ -3002,13 +2939,6 @@ __arm_vsriq_m_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_ return __builtin_mve_vsriq_m_n_uv16qi (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_u8 (uint32_t __a, uint8x16_t __b, uint8x16_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_uv16qi (__a, __b, __c, __p); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m_n_s16 (int16x8_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p) @@ -3023,13 +2953,6 @@ __arm_vqshluq_m_n_s16 (uint16x8_t __inactive, int16x8_t __a, const int __imm, mv return __builtin_mve_vqshluq_m_n_sv8hi (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_s16 (uint32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_sv8hi (__a, __b, __c, __p); -} - __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p) @@ -3037,13 +2960,6 @@ __arm_vsriq_m_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16 return __builtin_mve_vsriq_m_n_uv8hi (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_u16 (uint32_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_uv8hi (__a, __b, __c, __p); -} - __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m_n_s32 (int32x4_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p) @@ -3058,13 +2974,6 @@ __arm_vqshluq_m_n_s32 (uint32x4_t __inactive, int32x4_t __a, const int __imm, mv return __builtin_mve_vqshluq_m_n_sv4si (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_s32 (uint32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_sv4si (__a, __b, __c, __p); -} - __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p) @@ -3072,13 +2981,6 @@ __arm_vsriq_m_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16 return __builtin_mve_vsriq_m_n_uv4si (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p_u32 (uint32_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p) -{ - return __builtin_mve_vabavq_p_uv4si (__a, __b, __c, __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) @@ -9440,48 +9342,6 @@ __arm_vrmlaldavhq (int32x4_t __a, int32x4_t __b) return __arm_vrmlaldavhq_s32 (__a, __b); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, int8x16_t __b, int8x16_t __c) -{ - return __arm_vabavq_s8 (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, int16x8_t __b, int16x8_t __c) -{ - return __arm_vabavq_s16 (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, int32x4_t __b, int32x4_t __c) -{ - return __arm_vabavq_s32 (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, uint8x16_t __b, uint8x16_t __c) -{ - return __arm_vabavq_u8 (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, uint16x8_t __b, uint16x8_t __c) -{ - return __arm_vabavq_u16 (__a, __b, __c); -} - -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq (uint32_t __a, uint32x4_t __b, uint32x4_t __c) -{ - return __arm_vabavq_u32 (__a, __b, __c); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_m_n (int16x8_t __a, const int __imm, mve_pred16_t __p) @@ -10322,13 +10182,6 @@ __arm_vqshluq_m (uint8x16_t __inactive, int8x16_t __a, const int __imm, mve_pred return __arm_vqshluq_m_n_s8 (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, int8x16_t __b, int8x16_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_s8 (__a, __b, __c, __p); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_t __p) @@ -10336,13 +10189,6 @@ __arm_vsriq_m (uint8x16_t __a, uint8x16_t __b, const int __imm, mve_pred16_t __p return __arm_vsriq_m_n_u8 (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, uint8x16_t __b, uint8x16_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_u8 (__a, __b, __c, __p); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m (int16x8_t __a, int16x8_t __b, const int __imm, mve_pred16_t __p) @@ -10357,13 +10203,6 @@ __arm_vqshluq_m (uint16x8_t __inactive, int16x8_t __a, const int __imm, mve_pred return __arm_vqshluq_m_n_s16 (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, int16x8_t __b, int16x8_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_s16 (__a, __b, __c, __p); -} - __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p) @@ -10371,13 +10210,6 @@ __arm_vsriq_m (uint16x8_t __a, uint16x8_t __b, const int __imm, mve_pred16_t __p return __arm_vsriq_m_n_u16 (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, uint16x8_t __b, uint16x8_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_u16 (__a, __b, __c, __p); -} - __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m (int32x4_t __a, int32x4_t __b, const int __imm, mve_pred16_t __p) @@ -10392,13 +10224,6 @@ __arm_vqshluq_m (uint32x4_t __inactive, int32x4_t __a, const int __imm, mve_pred return __arm_vqshluq_m_n_s32 (__inactive, __a, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, int32x4_t __b, int32x4_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_s32 (__a, __b, __c, __p); -} - __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vsriq_m (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p) @@ -10406,13 +10231,6 @@ __arm_vsriq_m (uint32x4_t __a, uint32x4_t __b, const int __imm, mve_pred16_t __p return __arm_vsriq_m_n_u32 (__a, __b, __imm, __p); } -__extension__ extern __inline uint32_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vabavq_p (uint32_t __a, uint32x4_t __b, uint32x4_t __c, mve_pred16_t __p) -{ - return __arm_vabavq_p_u32 (__a, __b, __c, __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) @@ -16642,17 +16460,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmladhq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmladhq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));}) -#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ - __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_vabavq_p_s8(__p0, __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_vabavq_p_s16(__p0, __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_vabavq_p_s32(__p0, __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_vabavq_p_u8(__p0, __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_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_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -17637,28 +17444,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2, p3), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2, p3));}) -#define __arm_vabavq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ - __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_vabavq_s8 (__p0, __ARM_mve_coerce(__p1, int8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \ - int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vabavq_s16 (__p0, __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vabavq_s32 (__p0, __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vabavq_u8 (__p0, __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vabavq_u16 (__p0, __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vabavq_u32 (__p0, __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) - -#define __arm_vabavq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ - __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_vabavq_p_s8(__p0, __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_vabavq_p_s16(__p0, __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_vabavq_p_s32(__p0, __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_vabavq_p_u8(__p0, __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_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_vmlaldavaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ |