diff options
author | Christophe Lyon <christophe.lyon@arm.com> | 2023-01-10 15:44:02 +0000 |
---|---|---|
committer | Christophe Lyon <christophe.lyon@arm.com> | 2023-05-03 16:58:27 +0200 |
commit | 632f70d8652b806d0390e37d1a6f1bc0a25ce238 (patch) | |
tree | 25d5dc6ec08a38fca81f585250b418cff66896e5 | |
parent | 67e4e59172d9a28aface08b123c02e27d25e005e (diff) | |
download | gcc-632f70d8652b806d0390e37d1a6f1bc0a25ce238.zip gcc-632f70d8652b806d0390e37d1a6f1bc0a25ce238.tar.gz gcc-632f70d8652b806d0390e37d1a6f1bc0a25ce238.tar.bz2 |
arm: [MVE intrinsics] rework vandq veorq
Implement vamdq, veorq using the new MVE builtins framework.
2022-09-08 Christophe Lyon <christophe.lyon@arm.com>
gcc/
* config/arm/arm-mve-builtins-base.cc (FUNCTION_WITH_RTX_M): New.
(vandq,veorq): New.
* config/arm/arm-mve-builtins-base.def (vandq, veorq): New.
* config/arm/arm-mve-builtins-base.h (vandq, veorq): New.
* config/arm/arm_mve.h (vandq): Remove.
(vandq_m): Remove.
(vandq_x): Remove.
(vandq_u8): Remove.
(vandq_s8): Remove.
(vandq_u16): Remove.
(vandq_s16): Remove.
(vandq_u32): Remove.
(vandq_s32): Remove.
(vandq_f16): Remove.
(vandq_f32): Remove.
(vandq_m_s8): Remove.
(vandq_m_s32): Remove.
(vandq_m_s16): Remove.
(vandq_m_u8): Remove.
(vandq_m_u32): Remove.
(vandq_m_u16): Remove.
(vandq_m_f32): Remove.
(vandq_m_f16): Remove.
(vandq_x_s8): Remove.
(vandq_x_s16): Remove.
(vandq_x_s32): Remove.
(vandq_x_u8): Remove.
(vandq_x_u16): Remove.
(vandq_x_u32): Remove.
(vandq_x_f16): Remove.
(vandq_x_f32): Remove.
(__arm_vandq_u8): Remove.
(__arm_vandq_s8): Remove.
(__arm_vandq_u16): Remove.
(__arm_vandq_s16): Remove.
(__arm_vandq_u32): Remove.
(__arm_vandq_s32): Remove.
(__arm_vandq_m_s8): Remove.
(__arm_vandq_m_s32): Remove.
(__arm_vandq_m_s16): Remove.
(__arm_vandq_m_u8): Remove.
(__arm_vandq_m_u32): Remove.
(__arm_vandq_m_u16): Remove.
(__arm_vandq_x_s8): Remove.
(__arm_vandq_x_s16): Remove.
(__arm_vandq_x_s32): Remove.
(__arm_vandq_x_u8): Remove.
(__arm_vandq_x_u16): Remove.
(__arm_vandq_x_u32): Remove.
(__arm_vandq_f16): Remove.
(__arm_vandq_f32): Remove.
(__arm_vandq_m_f32): Remove.
(__arm_vandq_m_f16): Remove.
(__arm_vandq_x_f16): Remove.
(__arm_vandq_x_f32): Remove.
(__arm_vandq): Remove.
(__arm_vandq_m): Remove.
(__arm_vandq_x): Remove.
(veorq_m): Remove.
(veorq_x): Remove.
(veorq_u8): Remove.
(veorq_s8): Remove.
(veorq_u16): Remove.
(veorq_s16): Remove.
(veorq_u32): Remove.
(veorq_s32): Remove.
(veorq_f16): Remove.
(veorq_f32): Remove.
(veorq_m_s8): Remove.
(veorq_m_s32): Remove.
(veorq_m_s16): Remove.
(veorq_m_u8): Remove.
(veorq_m_u32): Remove.
(veorq_m_u16): Remove.
(veorq_m_f32): Remove.
(veorq_m_f16): Remove.
(veorq_x_s8): Remove.
(veorq_x_s16): Remove.
(veorq_x_s32): Remove.
(veorq_x_u8): Remove.
(veorq_x_u16): Remove.
(veorq_x_u32): Remove.
(veorq_x_f16): Remove.
(veorq_x_f32): Remove.
(__arm_veorq_u8): Remove.
(__arm_veorq_s8): Remove.
(__arm_veorq_u16): Remove.
(__arm_veorq_s16): Remove.
(__arm_veorq_u32): Remove.
(__arm_veorq_s32): Remove.
(__arm_veorq_m_s8): Remove.
(__arm_veorq_m_s32): Remove.
(__arm_veorq_m_s16): Remove.
(__arm_veorq_m_u8): Remove.
(__arm_veorq_m_u32): Remove.
(__arm_veorq_m_u16): Remove.
(__arm_veorq_x_s8): Remove.
(__arm_veorq_x_s16): Remove.
(__arm_veorq_x_s32): Remove.
(__arm_veorq_x_u8): Remove.
(__arm_veorq_x_u16): Remove.
(__arm_veorq_x_u32): Remove.
(__arm_veorq_f16): Remove.
(__arm_veorq_f32): Remove.
(__arm_veorq_m_f32): Remove.
(__arm_veorq_m_f16): Remove.
(__arm_veorq_x_f16): Remove.
(__arm_veorq_x_f32): Remove.
(__arm_veorq): Remove.
(__arm_veorq_m): Remove.
(__arm_veorq_x): Remove.
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.cc | 10 | ||||
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.def | 4 | ||||
-rw-r--r-- | gcc/config/arm/arm-mve-builtins-base.h | 2 | ||||
-rw-r--r-- | gcc/config/arm/arm_mve.h | 862 |
4 files changed, 16 insertions, 862 deletions
diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc index a5342ab..d3c0e1a 100644 --- a/gcc/config/arm/arm-mve-builtins-base.cc +++ b/gcc/config/arm/arm-mve-builtins-base.cc @@ -94,7 +94,17 @@ namespace arm_mve { UNSPEC##_M_S, UNSPEC##_M_U, UNSPEC##_M_F, \ UNSPEC##_M_N_S, UNSPEC##_M_N_U, UNSPEC##_M_N_F)) + /* Helper for builtins with RTX codes, and _m predicated overrides. */ +#define FUNCTION_WITH_RTX_M(NAME, RTX, UNSPEC) FUNCTION \ + (NAME, unspec_based_mve_function_exact_insn, \ + (RTX, RTX, RTX, \ + -1, -1, -1, \ + UNSPEC##_M_S, UNSPEC##_M_U, UNSPEC##_M_F, \ + -1, -1, -1)) + FUNCTION_WITH_RTX_M_N (vaddq, PLUS, VADDQ) +FUNCTION_WITH_RTX_M (vandq, AND, VANDQ) +FUNCTION_WITH_RTX_M (veorq, XOR, VEORQ) FUNCTION_WITH_RTX_M_N (vmulq, MULT, VMULQ) FUNCTION (vreinterpretq, vreinterpretq_impl,) FUNCTION_WITH_RTX_M_N (vsubq, MINUS, VSUBQ) diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def index 624558c..a933c9f 100644 --- a/gcc/config/arm/arm-mve-builtins-base.def +++ b/gcc/config/arm/arm-mve-builtins-base.def @@ -19,6 +19,8 @@ #define REQUIRES_FLOAT false 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 (veorq, binary, all_integer, mx_or_none) DEF_MVE_FUNCTION (vmulq, binary_opt_n, all_integer, mx_or_none) DEF_MVE_FUNCTION (vreinterpretq, unary_convert, reinterpret_integer, none) DEF_MVE_FUNCTION (vsubq, binary_opt_n, all_integer, mx_or_none) @@ -27,6 +29,8 @@ DEF_MVE_FUNCTION (vuninitializedq, inherent, all_integer_with_64, none) #define REQUIRES_FLOAT true 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 (veorq, binary, all_float, mx_or_none) DEF_MVE_FUNCTION (vmulq, binary_opt_n, all_float, mx_or_none) DEF_MVE_FUNCTION (vreinterpretq, unary_convert, reinterpret_float, none) DEF_MVE_FUNCTION (vsubq, binary_opt_n, all_float, mx_or_none) diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h index 30f8549..4fcf557 100644 --- a/gcc/config/arm/arm-mve-builtins-base.h +++ b/gcc/config/arm/arm-mve-builtins-base.h @@ -24,6 +24,8 @@ namespace arm_mve { namespace functions { extern const function_base *const vaddq; +extern const function_base *const vandq; +extern const function_base *const veorq; extern const function_base *const vmulq; extern const function_base *const vreinterpretq; extern const function_base *const vsubq; diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 42a1af2..0ad0122 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -77,14 +77,12 @@ #define vmaxq(__a, __b) __arm_vmaxq(__a, __b) #define vhsubq(__a, __b) __arm_vhsubq(__a, __b) #define vhaddq(__a, __b) __arm_vhaddq(__a, __b) -#define veorq(__a, __b) __arm_veorq(__a, __b) #define vcmphiq(__a, __b) __arm_vcmphiq(__a, __b) #define vcmpeqq(__a, __b) __arm_vcmpeqq(__a, __b) #define vcmpcsq(__a, __b) __arm_vcmpcsq(__a, __b) #define vcaddq_rot90(__a, __b) __arm_vcaddq_rot90(__a, __b) #define vcaddq_rot270(__a, __b) __arm_vcaddq_rot270(__a, __b) #define vbicq(__a, __b) __arm_vbicq(__a, __b) -#define vandq(__a, __b) __arm_vandq(__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) @@ -236,12 +234,10 @@ #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 vandq_m(__inactive, __a, __b, __p) __arm_vandq_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) #define vcaddq_rot90_m(__inactive, __a, __b, __p) __arm_vcaddq_rot90_m(__inactive, __a, __b, __p) -#define veorq_m(__inactive, __a, __b, __p) __arm_veorq_m(__inactive, __a, __b, __p) #define vhaddq_m(__inactive, __a, __b, __p) __arm_vhaddq_m(__inactive, __a, __b, __p) #define vhcaddq_rot270_m(__inactive, __a, __b, __p) __arm_vhcaddq_rot270_m(__inactive, __a, __b, __p) #define vhcaddq_rot90_m(__inactive, __a, __b, __p) __arm_vhcaddq_rot90_m(__inactive, __a, __b, __p) @@ -404,10 +400,8 @@ #define vhsubq_x(__a, __b, __p) __arm_vhsubq_x(__a, __b, __p) #define vrhaddq_x(__a, __b, __p) __arm_vrhaddq_x(__a, __b, __p) #define vrmulhq_x(__a, __b, __p) __arm_vrmulhq_x(__a, __b, __p) -#define vandq_x(__a, __b, __p) __arm_vandq_x(__a, __b, __p) #define vbicq_x(__a, __b, __p) __arm_vbicq_x(__a, __b, __p) #define vbrsrq_x(__a, __b, __p) __arm_vbrsrq_x(__a, __b, __p) -#define veorq_x(__a, __b, __p) __arm_veorq_x(__a, __b, __p) #define vmovlbq_x(__a, __p) __arm_vmovlbq_x(__a, __p) #define vmovltq_x(__a, __p) __arm_vmovltq_x(__a, __p) #define vmvnq_x(__a, __p) __arm_vmvnq_x(__a, __p) @@ -702,7 +696,6 @@ #define vhsubq_n_u8(__a, __b) __arm_vhsubq_n_u8(__a, __b) #define vhaddq_u8(__a, __b) __arm_vhaddq_u8(__a, __b) #define vhaddq_n_u8(__a, __b) __arm_vhaddq_n_u8(__a, __b) -#define veorq_u8(__a, __b) __arm_veorq_u8(__a, __b) #define vcmpneq_n_u8(__a, __b) __arm_vcmpneq_n_u8(__a, __b) #define vcmphiq_u8(__a, __b) __arm_vcmphiq_u8(__a, __b) #define vcmphiq_n_u8(__a, __b) __arm_vcmphiq_n_u8(__a, __b) @@ -713,7 +706,6 @@ #define vcaddq_rot90_u8(__a, __b) __arm_vcaddq_rot90_u8(__a, __b) #define vcaddq_rot270_u8(__a, __b) __arm_vcaddq_rot270_u8(__a, __b) #define vbicq_u8(__a, __b) __arm_vbicq_u8(__a, __b) -#define vandq_u8(__a, __b) __arm_vandq_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) @@ -781,12 +773,10 @@ #define vhcaddq_rot270_s8(__a, __b) __arm_vhcaddq_rot270_s8(__a, __b) #define vhaddq_s8(__a, __b) __arm_vhaddq_s8(__a, __b) #define vhaddq_n_s8(__a, __b) __arm_vhaddq_n_s8(__a, __b) -#define veorq_s8(__a, __b) __arm_veorq_s8(__a, __b) #define vcaddq_rot90_s8(__a, __b) __arm_vcaddq_rot90_s8(__a, __b) #define vcaddq_rot270_s8(__a, __b) __arm_vcaddq_rot270_s8(__a, __b) #define vbrsrq_n_s8(__a, __b) __arm_vbrsrq_n_s8(__a, __b) #define vbicq_s8(__a, __b) __arm_vbicq_s8(__a, __b) -#define vandq_s8(__a, __b) __arm_vandq_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) @@ -812,7 +802,6 @@ #define vhsubq_n_u16(__a, __b) __arm_vhsubq_n_u16(__a, __b) #define vhaddq_u16(__a, __b) __arm_vhaddq_u16(__a, __b) #define vhaddq_n_u16(__a, __b) __arm_vhaddq_n_u16(__a, __b) -#define veorq_u16(__a, __b) __arm_veorq_u16(__a, __b) #define vcmpneq_n_u16(__a, __b) __arm_vcmpneq_n_u16(__a, __b) #define vcmphiq_u16(__a, __b) __arm_vcmphiq_u16(__a, __b) #define vcmphiq_n_u16(__a, __b) __arm_vcmphiq_n_u16(__a, __b) @@ -823,7 +812,6 @@ #define vcaddq_rot90_u16(__a, __b) __arm_vcaddq_rot90_u16(__a, __b) #define vcaddq_rot270_u16(__a, __b) __arm_vcaddq_rot270_u16(__a, __b) #define vbicq_u16(__a, __b) __arm_vbicq_u16(__a, __b) -#define vandq_u16(__a, __b) __arm_vandq_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) @@ -891,12 +879,10 @@ #define vhcaddq_rot270_s16(__a, __b) __arm_vhcaddq_rot270_s16(__a, __b) #define vhaddq_s16(__a, __b) __arm_vhaddq_s16(__a, __b) #define vhaddq_n_s16(__a, __b) __arm_vhaddq_n_s16(__a, __b) -#define veorq_s16(__a, __b) __arm_veorq_s16(__a, __b) #define vcaddq_rot90_s16(__a, __b) __arm_vcaddq_rot90_s16(__a, __b) #define vcaddq_rot270_s16(__a, __b) __arm_vcaddq_rot270_s16(__a, __b) #define vbrsrq_n_s16(__a, __b) __arm_vbrsrq_n_s16(__a, __b) #define vbicq_s16(__a, __b) __arm_vbicq_s16(__a, __b) -#define vandq_s16(__a, __b) __arm_vandq_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) @@ -922,7 +908,6 @@ #define vhsubq_n_u32(__a, __b) __arm_vhsubq_n_u32(__a, __b) #define vhaddq_u32(__a, __b) __arm_vhaddq_u32(__a, __b) #define vhaddq_n_u32(__a, __b) __arm_vhaddq_n_u32(__a, __b) -#define veorq_u32(__a, __b) __arm_veorq_u32(__a, __b) #define vcmpneq_n_u32(__a, __b) __arm_vcmpneq_n_u32(__a, __b) #define vcmphiq_u32(__a, __b) __arm_vcmphiq_u32(__a, __b) #define vcmphiq_n_u32(__a, __b) __arm_vcmphiq_n_u32(__a, __b) @@ -933,7 +918,6 @@ #define vcaddq_rot90_u32(__a, __b) __arm_vcaddq_rot90_u32(__a, __b) #define vcaddq_rot270_u32(__a, __b) __arm_vcaddq_rot270_u32(__a, __b) #define vbicq_u32(__a, __b) __arm_vbicq_u32(__a, __b) -#define vandq_u32(__a, __b) __arm_vandq_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) @@ -1001,12 +985,10 @@ #define vhcaddq_rot270_s32(__a, __b) __arm_vhcaddq_rot270_s32(__a, __b) #define vhaddq_s32(__a, __b) __arm_vhaddq_s32(__a, __b) #define vhaddq_n_s32(__a, __b) __arm_vhaddq_n_s32(__a, __b) -#define veorq_s32(__a, __b) __arm_veorq_s32(__a, __b) #define vcaddq_rot90_s32(__a, __b) __arm_vcaddq_rot90_s32(__a, __b) #define vcaddq_rot270_s32(__a, __b) __arm_vcaddq_rot270_s32(__a, __b) #define vbrsrq_n_s32(__a, __b) __arm_vbrsrq_n_s32(__a, __b) #define vbicq_s32(__a, __b) __arm_vbicq_s32(__a, __b) -#define vandq_s32(__a, __b) __arm_vandq_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) @@ -1059,7 +1041,6 @@ #define vmaxnmq_f16(__a, __b) __arm_vmaxnmq_f16(__a, __b) #define vmaxnmavq_f16(__a, __b) __arm_vmaxnmavq_f16(__a, __b) #define vmaxnmaq_f16(__a, __b) __arm_vmaxnmaq_f16(__a, __b) -#define veorq_f16(__a, __b) __arm_veorq_f16(__a, __b) #define vcmulq_rot90_f16(__a, __b) __arm_vcmulq_rot90_f16(__a, __b) #define vcmulq_rot270_f16(__a, __b) __arm_vcmulq_rot270_f16(__a, __b) #define vcmulq_rot180_f16(__a, __b) __arm_vcmulq_rot180_f16(__a, __b) @@ -1067,7 +1048,6 @@ #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 vandq_f16(__a, __b) __arm_vandq_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) @@ -1120,7 +1100,6 @@ #define vmaxnmq_f32(__a, __b) __arm_vmaxnmq_f32(__a, __b) #define vmaxnmavq_f32(__a, __b) __arm_vmaxnmavq_f32(__a, __b) #define vmaxnmaq_f32(__a, __b) __arm_vmaxnmaq_f32(__a, __b) -#define veorq_f32(__a, __b) __arm_veorq_f32(__a, __b) #define vcmulq_rot90_f32(__a, __b) __arm_vcmulq_rot90_f32(__a, __b) #define vcmulq_rot270_f32(__a, __b) __arm_vcmulq_rot270_f32(__a, __b) #define vcmulq_rot180_f32(__a, __b) __arm_vcmulq_rot180_f32(__a, __b) @@ -1128,7 +1107,6 @@ #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 vandq_f32(__a, __b) __arm_vandq_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) @@ -1662,12 +1640,6 @@ #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 vandq_m_s8(__inactive, __a, __b, __p) __arm_vandq_m_s8(__inactive, __a, __b, __p) -#define vandq_m_s32(__inactive, __a, __b, __p) __arm_vandq_m_s32(__inactive, __a, __b, __p) -#define vandq_m_s16(__inactive, __a, __b, __p) __arm_vandq_m_s16(__inactive, __a, __b, __p) -#define vandq_m_u8(__inactive, __a, __b, __p) __arm_vandq_m_u8(__inactive, __a, __b, __p) -#define vandq_m_u32(__inactive, __a, __b, __p) __arm_vandq_m_u32(__inactive, __a, __b, __p) -#define vandq_m_u16(__inactive, __a, __b, __p) __arm_vandq_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) @@ -1692,12 +1664,6 @@ #define vcaddq_rot90_m_u8(__inactive, __a, __b, __p) __arm_vcaddq_rot90_m_u8(__inactive, __a, __b, __p) #define vcaddq_rot90_m_u32(__inactive, __a, __b, __p) __arm_vcaddq_rot90_m_u32(__inactive, __a, __b, __p) #define vcaddq_rot90_m_u16(__inactive, __a, __b, __p) __arm_vcaddq_rot90_m_u16(__inactive, __a, __b, __p) -#define veorq_m_s8(__inactive, __a, __b, __p) __arm_veorq_m_s8(__inactive, __a, __b, __p) -#define veorq_m_s32(__inactive, __a, __b, __p) __arm_veorq_m_s32(__inactive, __a, __b, __p) -#define veorq_m_s16(__inactive, __a, __b, __p) __arm_veorq_m_s16(__inactive, __a, __b, __p) -#define veorq_m_u8(__inactive, __a, __b, __p) __arm_veorq_m_u8(__inactive, __a, __b, __p) -#define veorq_m_u32(__inactive, __a, __b, __p) __arm_veorq_m_u32(__inactive, __a, __b, __p) -#define veorq_m_u16(__inactive, __a, __b, __p) __arm_veorq_m_u16(__inactive, __a, __b, __p) #define vhaddq_m_n_s8(__inactive, __a, __b, __p) __arm_vhaddq_m_n_s8(__inactive, __a, __b, __p) #define vhaddq_m_n_s32(__inactive, __a, __b, __p) __arm_vhaddq_m_n_s32(__inactive, __a, __b, __p) #define vhaddq_m_n_s16(__inactive, __a, __b, __p) __arm_vhaddq_m_n_s16(__inactive, __a, __b, __p) @@ -2006,8 +1972,6 @@ #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 vandq_m_f32(__inactive, __a, __b, __p) __arm_vandq_m_f32(__inactive, __a, __b, __p) -#define vandq_m_f16(__inactive, __a, __b, __p) __arm_vandq_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) @@ -2036,8 +2000,6 @@ #define vcvtq_m_n_s16_f16(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_s16_f16(__inactive, __a, __imm6, __p) #define vcvtq_m_n_u32_f32(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_u32_f32(__inactive, __a, __imm6, __p) #define vcvtq_m_n_u16_f16(__inactive, __a, __imm6, __p) __arm_vcvtq_m_n_u16_f16(__inactive, __a, __imm6, __p) -#define veorq_m_f32(__inactive, __a, __b, __p) __arm_veorq_m_f32(__inactive, __a, __b, __p) -#define veorq_m_f16(__inactive, __a, __b, __p) __arm_veorq_m_f16(__inactive, __a, __b, __p) #define vfmaq_m_f32(__a, __b, __c, __p) __arm_vfmaq_m_f32(__a, __b, __c, __p) #define vfmaq_m_f16(__a, __b, __c, __p) __arm_vfmaq_m_f16(__a, __b, __c, __p) #define vfmaq_m_n_f32(__a, __b, __c, __p) __arm_vfmaq_m_n_f32(__a, __b, __c, __p) @@ -2467,12 +2429,6 @@ #define vrmulhq_x_u8(__a, __b, __p) __arm_vrmulhq_x_u8(__a, __b, __p) #define vrmulhq_x_u16(__a, __b, __p) __arm_vrmulhq_x_u16(__a, __b, __p) #define vrmulhq_x_u32(__a, __b, __p) __arm_vrmulhq_x_u32(__a, __b, __p) -#define vandq_x_s8(__a, __b, __p) __arm_vandq_x_s8(__a, __b, __p) -#define vandq_x_s16(__a, __b, __p) __arm_vandq_x_s16(__a, __b, __p) -#define vandq_x_s32(__a, __b, __p) __arm_vandq_x_s32(__a, __b, __p) -#define vandq_x_u8(__a, __b, __p) __arm_vandq_x_u8(__a, __b, __p) -#define vandq_x_u16(__a, __b, __p) __arm_vandq_x_u16(__a, __b, __p) -#define vandq_x_u32(__a, __b, __p) __arm_vandq_x_u32(__a, __b, __p) #define vbicq_x_s8(__a, __b, __p) __arm_vbicq_x_s8(__a, __b, __p) #define vbicq_x_s16(__a, __b, __p) __arm_vbicq_x_s16(__a, __b, __p) #define vbicq_x_s32(__a, __b, __p) __arm_vbicq_x_s32(__a, __b, __p) @@ -2485,12 +2441,6 @@ #define vbrsrq_x_n_u8(__a, __b, __p) __arm_vbrsrq_x_n_u8(__a, __b, __p) #define vbrsrq_x_n_u16(__a, __b, __p) __arm_vbrsrq_x_n_u16(__a, __b, __p) #define vbrsrq_x_n_u32(__a, __b, __p) __arm_vbrsrq_x_n_u32(__a, __b, __p) -#define veorq_x_s8(__a, __b, __p) __arm_veorq_x_s8(__a, __b, __p) -#define veorq_x_s16(__a, __b, __p) __arm_veorq_x_s16(__a, __b, __p) -#define veorq_x_s32(__a, __b, __p) __arm_veorq_x_s32(__a, __b, __p) -#define veorq_x_u8(__a, __b, __p) __arm_veorq_x_u8(__a, __b, __p) -#define veorq_x_u16(__a, __b, __p) __arm_veorq_x_u16(__a, __b, __p) -#define veorq_x_u32(__a, __b, __p) __arm_veorq_x_u32(__a, __b, __p) #define vmovlbq_x_s8(__a, __p) __arm_vmovlbq_x_s8(__a, __p) #define vmovlbq_x_s16(__a, __p) __arm_vmovlbq_x_s16(__a, __p) #define vmovlbq_x_u8(__a, __p) __arm_vmovlbq_x_u8(__a, __p) @@ -2641,14 +2591,10 @@ #define vrndaq_x_f32(__a, __p) __arm_vrndaq_x_f32(__a, __p) #define vrndxq_x_f16(__a, __p) __arm_vrndxq_x_f16(__a, __p) #define vrndxq_x_f32(__a, __p) __arm_vrndxq_x_f32(__a, __p) -#define vandq_x_f16(__a, __b, __p) __arm_vandq_x_f16(__a, __b, __p) -#define vandq_x_f32(__a, __b, __p) __arm_vandq_x_f32(__a, __b, __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 vbrsrq_x_n_f16(__a, __b, __p) __arm_vbrsrq_x_n_f16(__a, __b, __p) #define vbrsrq_x_n_f32(__a, __b, __p) __arm_vbrsrq_x_n_f32(__a, __b, __p) -#define veorq_x_f16(__a, __b, __p) __arm_veorq_x_f16(__a, __b, __p) -#define veorq_x_f32(__a, __b, __p) __arm_veorq_x_f32(__a, __b, __p) #define vornq_x_f16(__a, __b, __p) __arm_vornq_x_f16(__a, __b, __p) #define vornq_x_f32(__a, __b, __p) __arm_vornq_x_f32(__a, __b, __p) #define vorrq_x_f16(__a, __b, __p) __arm_vorrq_x_f16(__a, __b, __p) @@ -3647,13 +3593,6 @@ __arm_vhaddq_n_u8 (uint8x16_t __a, uint8_t __b) return __builtin_mve_vhaddq_n_uv16qi (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __builtin_mve_veorq_uv16qi (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq_n_u8 (uint8x16_t __a, uint8_t __b) @@ -3726,13 +3665,6 @@ __arm_vbicq_u8 (uint8x16_t __a, uint8x16_t __b) return __builtin_mve_vbicq_uv16qi (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_u8 (uint8x16_t __a, uint8x16_t __b) -{ - return __builtin_mve_vandq_uv16qi (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p_u8 (uint8x16_t __a, mve_pred16_t __p) @@ -4204,13 +4136,6 @@ __arm_vhaddq_n_s8 (int8x16_t __a, int8_t __b) __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_mve_veorq_sv16qi (__a, __b); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90_s8 (int8x16_t __a, int8x16_t __b) { return __builtin_mve_vcaddq_rot90v16qi (__a, __b); @@ -4237,13 +4162,6 @@ __arm_vbicq_s8 (int8x16_t __a, int8x16_t __b) return __builtin_mve_vbicq_sv16qi (__a, __b); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_s8 (int8x16_t __a, int8x16_t __b) -{ - return __builtin_mve_vandq_sv16qi (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq_s8 (int32_t __a, int8x16_t __b) @@ -4419,13 +4337,6 @@ __arm_vhaddq_n_u16 (uint16x8_t __a, uint16_t __b) return __builtin_mve_vhaddq_n_uv8hi (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __builtin_mve_veorq_uv8hi (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq_n_u16 (uint16x8_t __a, uint16_t __b) @@ -4498,13 +4409,6 @@ __arm_vbicq_u16 (uint16x8_t __a, uint16x8_t __b) return __builtin_mve_vbicq_uv8hi (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_u16 (uint16x8_t __a, uint16x8_t __b) -{ - return __builtin_mve_vandq_uv8hi (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p_u16 (uint16x8_t __a, mve_pred16_t __p) @@ -4976,13 +4880,6 @@ __arm_vhaddq_n_s16 (int16x8_t __a, int16_t __b) __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_mve_veorq_sv8hi (__a, __b); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90_s16 (int16x8_t __a, int16x8_t __b) { return __builtin_mve_vcaddq_rot90v8hi (__a, __b); @@ -5009,13 +4906,6 @@ __arm_vbicq_s16 (int16x8_t __a, int16x8_t __b) return __builtin_mve_vbicq_sv8hi (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_s16 (int16x8_t __a, int16x8_t __b) -{ - return __builtin_mve_vandq_sv8hi (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq_s16 (int32_t __a, int16x8_t __b) @@ -5191,13 +5081,6 @@ __arm_vhaddq_n_u32 (uint32x4_t __a, uint32_t __b) return __builtin_mve_vhaddq_n_uv4si (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __builtin_mve_veorq_uv4si (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq_n_u32 (uint32x4_t __a, uint32_t __b) @@ -5270,13 +5153,6 @@ __arm_vbicq_u32 (uint32x4_t __a, uint32x4_t __b) return __builtin_mve_vbicq_uv4si (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_u32 (uint32x4_t __a, uint32x4_t __b) -{ - return __builtin_mve_vandq_uv4si (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p_u32 (uint32x4_t __a, mve_pred16_t __p) @@ -5748,13 +5624,6 @@ __arm_vhaddq_n_s32 (int32x4_t __a, int32_t __b) __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_mve_veorq_sv4si (__a, __b); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90_s32 (int32x4_t __a, int32x4_t __b) { return __builtin_mve_vcaddq_rot90v4si (__a, __b); @@ -5781,13 +5650,6 @@ __arm_vbicq_s32 (int32x4_t __a, int32x4_t __b) return __builtin_mve_vbicq_sv4si (__a, __b); } -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_s32 (int32x4_t __a, int32x4_t __b) -{ - return __builtin_mve_vandq_sv4si (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq_s32 (int32_t __a, int32x4_t __b) @@ -9177,48 +9039,6 @@ __arm_vabdq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pr __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv8hi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_u8 (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_uv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_uv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_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) { return __builtin_mve_vbicq_m_sv16qi (__inactive, __a, __b, __p); @@ -9387,48 +9207,6 @@ __arm_vcaddq_rot90_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_s8 (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_s16 (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv8hi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_u8 (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv16qi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv4si (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_u16 (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv8hi (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vhaddq_m_n_s8 (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p) { return __builtin_mve_vhaddq_m_n_sv16qi (__inactive, __a, __b, __p); @@ -14287,48 +14065,6 @@ __arm_vrmulhq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv16qi (__arm_vuninitializedq_s8 (), __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_u8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_uv16qi (__arm_vuninitializedq_u8 (), __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_u16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) { return __builtin_mve_vbicq_m_sv16qi (__arm_vuninitializedq_s8 (), __a, __b, __p); @@ -14411,48 +14147,6 @@ __arm_vbrsrq_x_n_u32 (uint32x4_t __a, int32_t __b, mve_pred16_t __p) return __builtin_mve_vbrsrq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv16qi (__arm_vuninitializedq_s8 (), __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv8hi (__arm_vuninitializedq_s16 (), __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_sv4si (__arm_vuninitializedq_s32 (), __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_u8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv16qi (__arm_vuninitializedq_u8 (), __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_u16 (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv8hi (__arm_vuninitializedq_u16 (), __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_u32 (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_uv4si (__arm_vuninitializedq_u32 (), __a, __b, __p); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vmovlbq_x_s8 (int8x16_t __a, mve_pred16_t __p) @@ -16302,13 +15996,6 @@ __arm_vmaxnmaq_f16 (float16x8_t __a, float16x8_t __b) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_f16 (float16x8_t __a, float16x8_t __b) -{ - return __builtin_mve_veorq_fv8hf (__a, __b); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmulq_rot90_f16 (float16x8_t __a, float16x8_t __b) { return __builtin_mve_vcmulq_rot90v8hf (__a, __b); @@ -16358,13 +16045,6 @@ __arm_vbicq_f16 (float16x8_t __a, float16x8_t __b) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_f16 (float16x8_t __a, float16x8_t __b) -{ - return __builtin_mve_vandq_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); @@ -16526,13 +16206,6 @@ __arm_vmaxnmaq_f32 (float32x4_t __a, float32x4_t __b) __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __builtin_mve_veorq_fv4sf (__a, __b); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmulq_rot90_f32 (float32x4_t __a, float32x4_t __b) { return __builtin_mve_vcmulq_rot90v4sf (__a, __b); @@ -16582,13 +16255,6 @@ __arm_vbicq_f32 (float32x4_t __a, float32x4_t __b) __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_f32 (float32x4_t __a, float32x4_t __b) -{ - return __builtin_mve_vandq_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); @@ -17374,20 +17040,6 @@ __arm_vabdq_m_f16 (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_fv4sf (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m_f16 (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_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) { return __builtin_mve_vbicq_m_fv4sf (__inactive, __a, __b, __p); @@ -17584,20 +17236,6 @@ __arm_vcvtq_m_n_u16_f16 (uint16x8_t __inactive, float16x8_t __a, const int __imm __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_f32 (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_fv4sf (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m_f16 (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_fv8hf (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vfmaq_m_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p) { return __builtin_mve_vfmaq_m_fv4sf (__a, __b, __c, __p); @@ -18458,20 +18096,6 @@ __arm_vrndxq_x_f32 (float32x4_t __a, mve_pred16_t __p) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_vandq_m_fv4sf (__arm_vuninitializedq_f32 (), __a, __b, __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) { return __builtin_mve_vbicq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p); @@ -18500,20 +18124,6 @@ __arm_vbrsrq_x_n_f32 (float32x4_t __a, int32_t __b, mve_pred16_t __p) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __builtin_mve_veorq_m_fv4sf (__arm_vuninitializedq_f32 (), __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vornq_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) { return __builtin_mve_vornq_m_fv8hf (__arm_vuninitializedq_f16 (), __a, __b, __p); @@ -19428,13 +19038,6 @@ __arm_vhaddq (uint8x16_t __a, uint8_t __b) return __arm_vhaddq_n_u8 (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (uint8x16_t __a, uint8x16_t __b) -{ - return __arm_veorq_u8 (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq (uint8x16_t __a, uint8_t __b) @@ -19505,13 +19108,6 @@ __arm_vbicq (uint8x16_t __a, uint8x16_t __b) return __arm_vbicq_u8 (__a, __b); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (uint8x16_t __a, uint8x16_t __b) -{ - return __arm_vandq_u8 (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p (uint8x16_t __a, mve_pred16_t __p) @@ -19983,13 +19579,6 @@ __arm_vhaddq (int8x16_t __a, int8_t __b) __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (int8x16_t __a, int8x16_t __b) -{ - return __arm_veorq_s8 (__a, __b); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90 (int8x16_t __a, int8x16_t __b) { return __arm_vcaddq_rot90_s8 (__a, __b); @@ -20016,13 +19605,6 @@ __arm_vbicq (int8x16_t __a, int8x16_t __b) return __arm_vbicq_s8 (__a, __b); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (int8x16_t __a, int8x16_t __b) -{ - return __arm_vandq_s8 (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq (int32_t __a, int8x16_t __b) @@ -20198,13 +19780,6 @@ __arm_vhaddq (uint16x8_t __a, uint16_t __b) return __arm_vhaddq_n_u16 (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (uint16x8_t __a, uint16x8_t __b) -{ - return __arm_veorq_u16 (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq (uint16x8_t __a, uint16_t __b) @@ -20275,13 +19850,6 @@ __arm_vbicq (uint16x8_t __a, uint16x8_t __b) return __arm_vbicq_u16 (__a, __b); } -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (uint16x8_t __a, uint16x8_t __b) -{ - return __arm_vandq_u16 (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p (uint16x8_t __a, mve_pred16_t __p) @@ -20753,13 +20321,6 @@ __arm_vhaddq (int16x8_t __a, int16_t __b) __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (int16x8_t __a, int16x8_t __b) -{ - return __arm_veorq_s16 (__a, __b); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90 (int16x8_t __a, int16x8_t __b) { return __arm_vcaddq_rot90_s16 (__a, __b); @@ -20786,13 +20347,6 @@ __arm_vbicq (int16x8_t __a, int16x8_t __b) return __arm_vbicq_s16 (__a, __b); } -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (int16x8_t __a, int16x8_t __b) -{ - return __arm_vandq_s16 (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq (int32_t __a, int16x8_t __b) @@ -20968,13 +20522,6 @@ __arm_vhaddq (uint32x4_t __a, uint32_t __b) return __arm_vhaddq_n_u32 (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (uint32x4_t __a, uint32x4_t __b) -{ - return __arm_veorq_u32 (__a, __b); -} - __extension__ extern __inline mve_pred16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmpneq (uint32x4_t __a, uint32_t __b) @@ -21045,13 +20592,6 @@ __arm_vbicq (uint32x4_t __a, uint32x4_t __b) return __arm_vbicq_u32 (__a, __b); } -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (uint32x4_t __a, uint32x4_t __b) -{ - return __arm_vandq_u32 (__a, __b); -} - __extension__ extern __inline uint32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvq_p (uint32x4_t __a, mve_pred16_t __p) @@ -21523,13 +21063,6 @@ __arm_vhaddq (int32x4_t __a, int32_t __b) __extension__ extern __inline int32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (int32x4_t __a, int32x4_t __b) -{ - return __arm_veorq_s32 (__a, __b); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcaddq_rot90 (int32x4_t __a, int32x4_t __b) { return __arm_vcaddq_rot90_s32 (__a, __b); @@ -21556,13 +21089,6 @@ __arm_vbicq (int32x4_t __a, int32x4_t __b) return __arm_vbicq_s32 (__a, __b); } -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (int32x4_t __a, int32x4_t __b) -{ - return __arm_vandq_s32 (__a, __b); -} - __extension__ extern __inline int32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vaddvaq (int32_t __a, int32x4_t __b) @@ -24911,48 +24437,6 @@ __arm_vabdq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16 __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_s8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_s32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_s16 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_u8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_u32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_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) { return __arm_vbicq_m_s8 (__inactive, __a, __b, __p); @@ -25121,48 +24605,6 @@ __arm_vcaddq_rot90_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (int8x16_t __inactive, int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_s8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_s32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (int16x8_t __inactive, int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_s16 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (uint8x16_t __inactive, uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_u8 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_u32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (uint16x8_t __inactive, uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_u16 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vhaddq_m (int8x16_t __inactive, int8x16_t __a, int8_t __b, mve_pred16_t __p) { return __arm_vhaddq_m_n_s8 (__inactive, __a, __b, __p); @@ -29552,48 +28994,6 @@ __arm_vrmulhq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) __extension__ extern __inline int8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_s8 (__a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_s16 (__a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_s32 (__a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_u8 (__a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_u16 (__a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_u32 (__a, __b, __p); -} - -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) { return __arm_vbicq_x_s8 (__a, __b, __p); @@ -29676,48 +29076,6 @@ __arm_vbrsrq_x (uint32x4_t __a, int32_t __b, mve_pred16_t __p) return __arm_vbrsrq_x_n_u32 (__a, __b, __p); } -__extension__ extern __inline int8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (int8x16_t __a, int8x16_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_s8 (__a, __b, __p); -} - -__extension__ extern __inline int16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (int16x8_t __a, int16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_s16 (__a, __b, __p); -} - -__extension__ extern __inline int32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (int32x4_t __a, int32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_s32 (__a, __b, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_u8 (__a, __b, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (uint16x8_t __a, uint16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_u16 (__a, __b, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (uint32x4_t __a, uint32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_u32 (__a, __b, __p); -} - __extension__ extern __inline int16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vmovlbq_x (int8x16_t __a, mve_pred16_t __p) @@ -31129,13 +30487,6 @@ __arm_vmaxnmaq (float16x8_t __a, float16x8_t __b) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (float16x8_t __a, float16x8_t __b) -{ - return __arm_veorq_f16 (__a, __b); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmulq_rot90 (float16x8_t __a, float16x8_t __b) { return __arm_vcmulq_rot90_f16 (__a, __b); @@ -31185,13 +30536,6 @@ __arm_vbicq (float16x8_t __a, float16x8_t __b) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (float16x8_t __a, float16x8_t __b) -{ - return __arm_vandq_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); @@ -31353,13 +30697,6 @@ __arm_vmaxnmaq (float32x4_t __a, float32x4_t __b) __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq (float32x4_t __a, float32x4_t __b) -{ - return __arm_veorq_f32 (__a, __b); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vcmulq_rot90 (float32x4_t __a, float32x4_t __b) { return __arm_vcmulq_rot90_f32 (__a, __b); @@ -31409,13 +30746,6 @@ __arm_vbicq (float32x4_t __a, float32x4_t __b) __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq (float32x4_t __a, float32x4_t __b) -{ - return __arm_vandq_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); @@ -32186,20 +31516,6 @@ __arm_vabdq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pre __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_m_f32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_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) { return __arm_vbicq_m_f32 (__inactive, __a, __b, __p); @@ -32396,20 +31712,6 @@ __arm_vcvtq_m_n (uint16x8_t __inactive, float16x8_t __a, const int __imm6, mve_p __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (float32x4_t __inactive, float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_f32 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_m (float16x8_t __inactive, float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_m_f16 (__inactive, __a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vfmaq_m (float32x4_t __a, float32x4_t __b, float32x4_t __c, mve_pred16_t __p) { return __arm_vfmaq_m_f32 (__a, __b, __c, __p); @@ -33012,20 +32314,6 @@ __arm_vrndxq_x (float32x4_t __a, mve_pred16_t __p) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_f16 (__a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vandq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_vandq_x_f32 (__a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vbicq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) { return __arm_vbicq_x_f16 (__a, __b, __p); @@ -33054,20 +32342,6 @@ __arm_vbrsrq_x (float32x4_t __a, int32_t __b, mve_pred16_t __p) __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_f16 (__a, __b, __p); -} - -__extension__ extern __inline float32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_veorq_x (float32x4_t __a, float32x4_t __b, mve_pred16_t __p) -{ - return __arm_veorq_x_f32 (__a, __b, __p); -} - -__extension__ extern __inline float16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vornq_x (float16x8_t __a, float16x8_t __b, mve_pred16_t __p) { return __arm_vornq_x_f16 (__a, __b, __p); @@ -33678,18 +32952,6 @@ extern void *__ARM_undef; 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_vandq(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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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, \ @@ -33868,18 +33130,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_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_vcmulq_rot90_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));}) -#define __arm_veorq(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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t)));}) - #define __arm_vmaxnmaq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ @@ -35060,19 +34310,6 @@ extern void *__ARM_undef; 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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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); \ @@ -35180,19 +34417,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcmulq_rot90_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_vcmulq_rot90_m_f32(__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));}) -#define __arm_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));}) - #define __arm_vfmaq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -35588,18 +34812,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_float16x8_t]: __arm_vabsq_x_f16 (__ARM_mve_coerce(__p1, float16x8_t), p2), \ int (*)[__ARM_mve_type_float32x4_t]: __arm_vabsq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), p2));}) -#define __arm_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_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, \ @@ -35679,18 +34891,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t]: __arm_vcvtq_x_n_f16_u16 (__ARM_mve_coerce(__p1, uint16x8_t), p2, p3), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vcvtq_x_n_f32_u32 (__ARM_mve_coerce(__p1, uint32x4_t), p2, p3));}) -#define __arm_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_x_f32 (__ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));}) - #define __arm_vmaxnmq_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ @@ -36251,16 +35451,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vhaddq_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_vhaddq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));}) -#define __arm_veorq(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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t)));}) - #define __arm_vcaddq_rot90(p0,p1) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ @@ -36304,16 +35494,6 @@ 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_vandq(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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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, \ @@ -36998,17 +36178,6 @@ extern void *__ARM_undef; 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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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); \ @@ -37053,17 +36222,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot90_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_vcaddq_rot90_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) -#define __arm_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) - #define __arm_vmladavaq_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -37360,16 +36518,6 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vcaddq_rot90_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_vcaddq_rot90_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) -#define __arm_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_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_veorq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) - #define __arm_vmovlbq_x(p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int8x16_t]: __arm_vmovlbq_x_s8 (__ARM_mve_coerce(__p1, int8x16_t), p2), \ @@ -37478,16 +36626,6 @@ extern void *__ARM_undef; 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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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_vandq_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, \ |