[12/15] arm: [MVE intrinsics] rework vcvtaq vcvtmq vcvtnq vcvtpq

Message ID	20240711214305.3193022-12-christophe.lyon@linaro.org
State	New
Headers	show Return-Path: <gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org> DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 19EB33875DED From: Christophe Lyon <christophe.lyon@linaro.org> To: gcc-patches@gcc.gnu.org, richard.earnshaw@arm.com, ramanara@nvidia.com Cc: Christophe Lyon <christophe.lyon@linaro.org> Subject: [PATCH 12/15] arm: [MVE intrinsics] rework vcvtaq vcvtmq vcvtnq vcvtpq Date: Thu, 11 Jul 2024 21:43:02 +0000 Message-Id: <20240711214305.3193022-12-christophe.lyon@linaro.org> In-Reply-To: <20240711214305.3193022-1-christophe.lyon@linaro.org> References: <20240711214305.3193022-1-christophe.lyon@linaro.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: list Errors-To: gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org
Series	[01/15] arm: [MVE intrinsics] improve comment for orrq shape \| expand [01/15] arm: [MVE intrinsics] improve comment for orrq shape [02/15] arm: [MVE intrinsics] remove useless resolve from create shape [03/15] arm: [MVE intrinsics] Cleanup arm-mve-builtins-functions.h [04/15] arm: [MVE intrinsics] factorize vcvtq [05/15] arm: [MVE intrinsics] add vcvt shape [06/15] arm: [MVE intrinsics] rework vcvtq [07/15] arm: [MVE intrinsics] factorize vcvtbq vcvttq [08/15] arm: [MVE intrinsics] add vcvt_f16_f32 and vcvt_f32_f16 shapes [09/15] arm: [MVE intrinsics] rework vcvtbq_f16_f32 vcvttq_f16_f32 vcvtbq_f32_f16 vcvttq_f32_f16 [10/15] arm: [MVE intrinsics] factorize vcvtaq vcvtmq vcvtnq vcvtpq [11/15] arm: [MVE intrinsics] add vcvtx shape [12/15] arm: [MVE intrinsics] rework vcvtaq vcvtmq vcvtnq vcvtpq [13/15] arm: [MVE intrinsics] rework vbicq [14/15] arm: [MVE intrinsics] factorize vorn [15/15] arm: [MVE intrinsics] rework vorn

diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc index 760378c91b1..281f3749bce 100644 --- a/gcc/config/arm/arm-mve-builtins-base.cc +++ b/gcc/config/arm/arm-mve-builtins-base.cc @@ -506,6 +506,10 @@ FUNCTION (vcmpcsq, unspec_based_mve_function_exact_insn_vcmp, (UNKNOWN, GEU, UNK FUNCTION (vcmphiq, unspec_based_mve_function_exact_insn_vcmp, (UNKNOWN, GTU, UNKNOWN, UNKNOWN, VCMPHIQ_M_U, UNKNOWN, UNKNOWN, VCMPHIQ_M_N_U, UNKNOWN)) FUNCTION_WITHOUT_M_N (vcreateq, VCREATEQ) FUNCTION (vcvtq, vcvtq_impl,) +FUNCTION_WITHOUT_N_NO_F (vcvtaq, VCVTAQ) +FUNCTION_WITHOUT_N_NO_F (vcvtmq, VCVTMQ) +FUNCTION_WITHOUT_N_NO_F (vcvtnq, VCVTNQ) +FUNCTION_WITHOUT_N_NO_F (vcvtpq, VCVTPQ) FUNCTION (vcvtbq, vcvtxq_impl, (VCVTBQ_F16_F32, VCVTBQ_M_F16_F32, VCVTBQ_F32_F16, VCVTBQ_M_F32_F16)) FUNCTION (vcvttq, vcvtxq_impl, (VCVTTQ_F16_F32, VCVTTQ_M_F16_F32, VCVTTQ_F32_F16, VCVTTQ_M_F32_F16)) FUNCTION_ONLY_N (vdupq, VDUPQ) diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def index 5a6f1a59c7c..7821007fe2c 100644 --- a/gcc/config/arm/arm-mve-builtins-base.def +++ b/gcc/config/arm/arm-mve-builtins-base.def @@ -180,6 +180,10 @@ DEF_MVE_FUNCTION (vcmpltq, cmp, all_float, m_or_none) DEF_MVE_FUNCTION (vcmpneq, cmp, all_float, m_or_none) DEF_MVE_FUNCTION (vcreateq, create, all_float, none) DEF_MVE_FUNCTION (vcvtq, vcvt, cvt, mx_or_none) +DEF_MVE_FUNCTION (vcvtaq, vcvtx, cvtx, mx_or_none) +DEF_MVE_FUNCTION (vcvtmq, vcvtx, cvtx, mx_or_none) +DEF_MVE_FUNCTION (vcvtnq, vcvtx, cvtx, mx_or_none) +DEF_MVE_FUNCTION (vcvtpq, vcvtx, cvtx, mx_or_none) DEF_MVE_FUNCTION (vcvtbq, vcvt_f16_f32, cvt_f16_f32, mx_or_none) DEF_MVE_FUNCTION (vcvtbq, vcvt_f32_f16, cvt_f32_f16, mx_or_none) DEF_MVE_FUNCTION (vcvttq, vcvt_f16_f32, cvt_f16_f32, mx_or_none) diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h index 25467769d05..89e0f631c32 100644 --- a/gcc/config/arm/arm-mve-builtins-base.h +++ b/gcc/config/arm/arm-mve-builtins-base.h @@ -55,6 +55,10 @@ extern const function_base *const vcmulq_rot270; extern const function_base *const vcmulq_rot90; extern const function_base *const vcreateq; extern const function_base *const vcvtq; +extern const function_base *const vcvtaq; +extern const function_base *const vcvtmq; +extern const function_base *const vcvtnq; +extern const function_base *const vcvtpq; extern const function_base *const vcvtbq; extern const function_base *const vcvttq; extern const function_base *const vdupq; diff --git a/gcc/config/arm/arm-mve-builtins.cc b/gcc/config/arm/arm-mve-builtins.cc index 4c554a47d85..07e63df35e4 100644 --- a/gcc/config/arm/arm-mve-builtins.cc +++ b/gcc/config/arm/arm-mve-builtins.cc @@ -227,6 +227,14 @@ CONSTEXPR const type_suffix_info type_suffixes[NUM_TYPE_SUFFIXES + 1] = { #define TYPES_cvt_f32_f16(S, D) \ D (f32, f16) +/* All the type combinations allowed by vcvtXq. */ +#define TYPES_cvtx(S, D) \ + D (s16, f16), \ + D (s32, f32), \ + \ + D (u16, f16), \ + D (u32, f32) + #define TYPES_reinterpret_signed1(D, A) \ D (A, s8), D (A, s16), D (A, s32), D (A, s64) @@ -309,6 +317,7 @@ DEF_MVE_TYPES_ARRAY (signed_32); DEF_MVE_TYPES_ARRAY (cvt); DEF_MVE_TYPES_ARRAY (cvt_f16_f32); DEF_MVE_TYPES_ARRAY (cvt_f32_f16); +DEF_MVE_TYPES_ARRAY (cvtx); DEF_MVE_TYPES_ARRAY (reinterpret_integer); DEF_MVE_TYPES_ARRAY (reinterpret_float); diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 5c35e08d754..448407627e9 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -137,10 +137,6 @@ #define vsetq_lane(__a, __b, __idx) __arm_vsetq_lane(__a, __b, __idx) #define vgetq_lane(__a, __idx) __arm_vgetq_lane(__a, __idx) #define vshlcq_m(__a, __b, __imm, __p) __arm_vshlcq_m(__a, __b, __imm, __p) -#define vcvtaq_m(__inactive, __a, __p) __arm_vcvtaq_m(__inactive, __a, __p) -#define vcvtmq_m(__inactive, __a, __p) __arm_vcvtmq_m(__inactive, __a, __p) -#define vcvtnq_m(__inactive, __a, __p) __arm_vcvtnq_m(__inactive, __a, __p) -#define vcvtpq_m(__inactive, __a, __p) __arm_vcvtpq_m(__inactive, __a, __p) #define vst4q_s8( __addr, __value) __arm_vst4q_s8( __addr, __value) @@ -151,22 +147,6 @@ #define vst4q_u32( __addr, __value) __arm_vst4q_u32( __addr, __value) #define vst4q_f16( __addr, __value) __arm_vst4q_f16( __addr, __value) #define vst4q_f32( __addr, __value) __arm_vst4q_f32( __addr, __value) -#define vcvtaq_s16_f16(__a) __arm_vcvtaq_s16_f16(__a) -#define vcvtaq_s32_f32(__a) __arm_vcvtaq_s32_f32(__a) -#define vcvtnq_s16_f16(__a) __arm_vcvtnq_s16_f16(__a) -#define vcvtnq_s32_f32(__a) __arm_vcvtnq_s32_f32(__a) -#define vcvtpq_s16_f16(__a) __arm_vcvtpq_s16_f16(__a) -#define vcvtpq_s32_f32(__a) __arm_vcvtpq_s32_f32(__a) -#define vcvtmq_s16_f16(__a) __arm_vcvtmq_s16_f16(__a) -#define vcvtmq_s32_f32(__a) __arm_vcvtmq_s32_f32(__a) -#define vcvtpq_u16_f16(__a) __arm_vcvtpq_u16_f16(__a) -#define vcvtpq_u32_f32(__a) __arm_vcvtpq_u32_f32(__a) -#define vcvtnq_u16_f16(__a) __arm_vcvtnq_u16_f16(__a) -#define vcvtnq_u32_f32(__a) __arm_vcvtnq_u32_f32(__a) -#define vcvtmq_u16_f16(__a) __arm_vcvtmq_u16_f16(__a) -#define vcvtmq_u32_f32(__a) __arm_vcvtmq_u32_f32(__a) -#define vcvtaq_u16_f16(__a) __arm_vcvtaq_u16_f16(__a) -#define vcvtaq_u32_f32(__a) __arm_vcvtaq_u32_f32(__a) #define vctp16q(__a) __arm_vctp16q(__a) #define vctp32q(__a) __arm_vctp32q(__a) #define vctp64q(__a) __arm_vctp64q(__a) @@ -200,28 +180,12 @@ #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) #define vbicq_m_n_u32(__a, __imm, __p) __arm_vbicq_m_n_u32(__a, __imm, __p) -#define vcvtaq_m_s16_f16(__inactive, __a, __p) __arm_vcvtaq_m_s16_f16(__inactive, __a, __p) -#define vcvtaq_m_u16_f16(__inactive, __a, __p) __arm_vcvtaq_m_u16_f16(__inactive, __a, __p) -#define vcvtaq_m_s32_f32(__inactive, __a, __p) __arm_vcvtaq_m_s32_f32(__inactive, __a, __p) -#define vcvtaq_m_u32_f32(__inactive, __a, __p) __arm_vcvtaq_m_u32_f32(__inactive, __a, __p) #define vshlcq_s8(__a, __b, __imm) __arm_vshlcq_s8(__a, __b, __imm) #define vshlcq_u8(__a, __b, __imm) __arm_vshlcq_u8(__a, __b, __imm) #define vshlcq_s16(__a, __b, __imm) __arm_vshlcq_s16(__a, __b, __imm) #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 vcvtmq_m_s16_f16(__inactive, __a, __p) __arm_vcvtmq_m_s16_f16(__inactive, __a, __p) -#define vcvtnq_m_s16_f16(__inactive, __a, __p) __arm_vcvtnq_m_s16_f16(__inactive, __a, __p) -#define vcvtpq_m_s16_f16(__inactive, __a, __p) __arm_vcvtpq_m_s16_f16(__inactive, __a, __p) -#define vcvtmq_m_u16_f16(__inactive, __a, __p) __arm_vcvtmq_m_u16_f16(__inactive, __a, __p) -#define vcvtnq_m_u16_f16(__inactive, __a, __p) __arm_vcvtnq_m_u16_f16(__inactive, __a, __p) -#define vcvtpq_m_u16_f16(__inactive, __a, __p) __arm_vcvtpq_m_u16_f16(__inactive, __a, __p) -#define vcvtmq_m_s32_f32(__inactive, __a, __p) __arm_vcvtmq_m_s32_f32(__inactive, __a, __p) -#define vcvtnq_m_s32_f32(__inactive, __a, __p) __arm_vcvtnq_m_s32_f32(__inactive, __a, __p) -#define vcvtpq_m_s32_f32(__inactive, __a, __p) __arm_vcvtpq_m_s32_f32(__inactive, __a, __p) -#define vcvtmq_m_u32_f32(__inactive, __a, __p) __arm_vcvtmq_m_u32_f32(__inactive, __a, __p) -#define vcvtnq_m_u32_f32(__inactive, __a, __p) __arm_vcvtnq_m_u32_f32(__inactive, __a, __p) -#define vcvtpq_m_u32_f32(__inactive, __a, __p) __arm_vcvtpq_m_u32_f32(__inactive, __a, __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) @@ -532,22 +496,6 @@ #define vornq_x_u8(__a, __b, __p) __arm_vornq_x_u8(__a, __b, __p) #define vornq_x_u16(__a, __b, __p) __arm_vornq_x_u16(__a, __b, __p) #define vornq_x_u32(__a, __b, __p) __arm_vornq_x_u32(__a, __b, __p) -#define vcvtaq_x_s16_f16(__a, __p) __arm_vcvtaq_x_s16_f16(__a, __p) -#define vcvtaq_x_s32_f32(__a, __p) __arm_vcvtaq_x_s32_f32(__a, __p) -#define vcvtaq_x_u16_f16(__a, __p) __arm_vcvtaq_x_u16_f16(__a, __p) -#define vcvtaq_x_u32_f32(__a, __p) __arm_vcvtaq_x_u32_f32(__a, __p) -#define vcvtnq_x_s16_f16(__a, __p) __arm_vcvtnq_x_s16_f16(__a, __p) -#define vcvtnq_x_s32_f32(__a, __p) __arm_vcvtnq_x_s32_f32(__a, __p) -#define vcvtnq_x_u16_f16(__a, __p) __arm_vcvtnq_x_u16_f16(__a, __p) -#define vcvtnq_x_u32_f32(__a, __p) __arm_vcvtnq_x_u32_f32(__a, __p) -#define vcvtpq_x_s16_f16(__a, __p) __arm_vcvtpq_x_s16_f16(__a, __p) -#define vcvtpq_x_s32_f32(__a, __p) __arm_vcvtpq_x_s32_f32(__a, __p) -#define vcvtpq_x_u16_f16(__a, __p) __arm_vcvtpq_x_u16_f16(__a, __p) -#define vcvtpq_x_u32_f32(__a, __p) __arm_vcvtpq_x_u32_f32(__a, __p) -#define vcvtmq_x_s16_f16(__a, __p) __arm_vcvtmq_x_s16_f16(__a, __p) -#define vcvtmq_x_s32_f32(__a, __p) __arm_vcvtmq_x_s32_f32(__a, __p) -#define vcvtmq_x_u16_f16(__a, __p) __arm_vcvtmq_x_u16_f16(__a, __p) -#define vcvtmq_x_u32_f32(__a, __p) __arm_vcvtmq_x_u32_f32(__a, __p) #define vbicq_x_f16(__a, __b, __p) __arm_vbicq_x_f16(__a, __b, __p) #define vbicq_x_f32(__a, __b, __p) __arm_vbicq_x_f32(__a, __b, __p) #define vornq_x_f16(__a, __b, __p) __arm_vornq_x_f16(__a, __b, __p) @@ -3690,118 +3638,6 @@ __arm_vst4q_f32 (float32_t * __addr, float32x4x4_t __value) __builtin_mve_vst4qv4sf (__addr, __rv.__o); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_u16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtpq_uv8hi (__a); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_u32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtpq_uv4si (__a); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_u16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtnq_uv8hi (__a); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_u32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtnq_uv4si (__a); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_u16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtmq_uv8hi (__a); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_u32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtmq_uv4si (__a); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_u16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtaq_uv8hi (__a); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_u32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtaq_uv4si (__a); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_s16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtaq_sv8hi (__a); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_s32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtaq_sv4si (__a); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_s16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtnq_sv8hi (__a); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_s32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtnq_sv4si (__a); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_s16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtpq_sv8hi (__a); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_s32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtpq_sv4si (__a); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_s16_f16 (float16x8_t __a) -{ - return __builtin_mve_vcvtmq_sv8hi (__a); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_s32_f32 (float32x4_t __a) -{ - return __builtin_mve_vcvtmq_sv4si (__a); -} - __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vornq_f16 (float16x8_t __a, float16x8_t __b) @@ -3830,119 +3666,6 @@ __arm_vbicq_f32 (float32x4_t __a, float32x4_t __b) return __builtin_mve_vbicq_fv4sf (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_sv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m_u16_f16 (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_uv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_sv4si (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m_u32_f32 (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_uv4si (__inactive, __a, __p); -} - - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_sv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_sv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_sv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m_u16_f16 (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_uv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m_u16_f16 (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_uv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m_u16_f16 (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_uv8hi (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_sv4si (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_sv4si (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_sv4si (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m_u32_f32 (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_uv4si (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m_u32_f32 (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_uv4si (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m_u32_f32 (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_uv4si (__inactive, __a, __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) @@ -4201,118 +3924,6 @@ __arm_vstrwq_scatter_base_wb_p_f32 (uint32x4_t * __addr, const int __offset, flo *__addr = __builtin_mve_vstrwq_scatter_base_wb_p_fv4sf (*__addr, __offset, __value, __p); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_x_s16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_x_s32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_x_u16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_x_u32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtaq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_x_s16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_x_s32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_x_u16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_x_u32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtnq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_x_s16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_x_s32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_x_u16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_x_u32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtpq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_x_s16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_x_s32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_x_u16_f16 (float16x8_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_x_u32_f32 (float32x4_t __a, mve_pred16_t __p) -{ - return __builtin_mve_vcvtmq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __p); -} - __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) @@ -6771,118 +6382,6 @@ __arm_vbicq (float32x4_t __a, float32x4_t __b) return __arm_vbicq_f32 (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtaq_m_s16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtaq_m_u16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtaq_m_s32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtaq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtaq_m_u32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtmq_m_s16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtnq_m_s16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtpq_m_s16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtmq_m_u16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtnq_m_u16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m (uint16x8_t __inactive, float16x8_t __a, mve_pred16_t __p) -{ - return __arm_vcvtpq_m_u16_f16 (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtmq_m_s32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtnq_m_s32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtpq_m_s32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtmq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtmq_m_u32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtnq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtnq_m_u32_f32 (__inactive, __a, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vcvtpq_m (uint32x4_t __inactive, float32x4_t __a, mve_pred16_t __p) -{ - return __arm_vcvtpq_m_u32_f32 (__inactive, __a, __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) @@ -7572,38 +7071,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshlcq_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1, p2), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshlcq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1, p2));}) -#define __arm_vcvtaq_m(p0,p1,p2) ({ __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_float16x8_t]: __arm_vcvtaq_m_s16_f16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtaq_m_s32_f32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtaq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtaq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));}) - -#define __arm_vcvtmq_m(p0,p1,p2) ({ __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_float16x8_t]: __arm_vcvtmq_m_s16_f16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtmq_m_s32_f32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtmq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtmq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));}) - -#define __arm_vcvtnq_m(p0,p1,p2) ({ __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_float16x8_t]: __arm_vcvtnq_m_s16_f16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtnq_m_s32_f32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtnq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtnq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));}) - -#define __arm_vcvtpq_m(p0,p1,p2) ({ __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_float16x8_t]: __arm_vcvtpq_m_s16_f16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtpq_m_s32_f32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtpq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtpq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));}) - #define __arm_vbicq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \

[12/15] arm: [MVE intrinsics] rework vcvtaq vcvtmq vcvtnq vcvtpq

Commit Message

Patch