core/stdarch/crates/core_arch/src/arm_shared/neon/

mod.rs

//! ARMv7 NEON intrinsics

#[rustfmt::skip]
mod generated;
#[rustfmt::skip]
#[cfg_attr(not(target_arch = "arm"), stable(feature = "neon_intrinsics", since = "1.59.0"))]
#[cfg_attr(target_arch = "arm", unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800"))]
pub use self::generated::*;

use crate::{core_arch::simd::*, hint::unreachable_unchecked, intrinsics::simd::*, mem::transmute};
#[cfg(test)]
use stdarch_test::assert_instr;

pub(crate) type p8 = u8;
pub(crate) type p16 = u16;
pub(crate) type p64 = u64;
pub(crate) type p128 = u128;

types! {
    #![cfg_attr(not(target_arch = "arm"), stable(feature = "neon_intrinsics", since = "1.59.0"))]
    #![cfg_attr(target_arch = "arm", unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800"))]

    /// ARM-specific 64-bit wide vector of eight packed `i8`.
    pub struct int8x8_t(8 x pub(crate) i8);
    /// ARM-specific 64-bit wide vector of eight packed `u8`.
    pub struct uint8x8_t(8 x pub(crate) u8);
    /// ARM-specific 64-bit wide polynomial vector of eight packed `p8`.
    pub struct poly8x8_t(8 x pub(crate) p8);
    /// ARM-specific 64-bit wide vector of four packed `i16`.
    pub struct int16x4_t(4 x pub(crate) i16);
    /// ARM-specific 64-bit wide vector of four packed `u16`.
    pub struct uint16x4_t(4 x pub(crate) u16);
    // FIXME: ARM-specific 64-bit wide vector of four packed `f16`.
    // pub struct float16x4_t(f16, f16, f16, f16);
    /// ARM-specific 64-bit wide vector of four packed `p16`.
    pub struct poly16x4_t(4 x pub(crate) p16);
    /// ARM-specific 64-bit wide vector of two packed `i32`.
    pub struct int32x2_t(2 x pub(crate) i32);
    /// ARM-specific 64-bit wide vector of two packed `u32`.
    pub struct uint32x2_t(2 x pub(crate) u32);
    /// ARM-specific 64-bit wide vector of two packed `f32`.
    pub struct float32x2_t(2 x pub(crate) f32);
    /// ARM-specific 64-bit wide vector of one packed `i64`.
    pub struct int64x1_t(1 x pub(crate) i64);
    /// ARM-specific 64-bit wide vector of one packed `u64`.
    pub struct uint64x1_t(1 x pub(crate) u64);
    /// ARM-specific 64-bit wide vector of one packed `p64`.
    pub struct poly64x1_t(1 x pub(crate) p64);

    /// ARM-specific 128-bit wide vector of sixteen packed `i8`.
    pub struct int8x16_t(16 x pub(crate) i8);
    /// ARM-specific 128-bit wide vector of sixteen packed `u8`.
    pub struct uint8x16_t(16 x pub(crate) u8);
    /// ARM-specific 128-bit wide vector of sixteen packed `p8`.
    pub struct poly8x16_t(16 x pub(crate) p8);
    /// ARM-specific 128-bit wide vector of eight packed `i16`.
    pub struct int16x8_t(8 x pub(crate) i16);
    /// ARM-specific 128-bit wide vector of eight packed `u16`.
    pub struct uint16x8_t(8 x pub(crate) u16);
    // FIXME: ARM-specific 128-bit wide vector of eight packed `f16`.
    // pub struct float16x8_t(f16, f16, f16, f16, f16, f16, f16);
    /// ARM-specific 128-bit wide vector of eight packed `p16`.
    pub struct poly16x8_t(8 x pub(crate) p16);
    /// ARM-specific 128-bit wide vector of four packed `i32`.
    pub struct int32x4_t(4 x pub(crate) i32);
    /// ARM-specific 128-bit wide vector of four packed `u32`.
    pub struct uint32x4_t(4 x pub(crate) u32);
    /// ARM-specific 128-bit wide vector of four packed `f32`.
    pub struct float32x4_t(4 x pub(crate) f32);
    /// ARM-specific 128-bit wide vector of two packed `i64`.
    pub struct int64x2_t(2 x pub(crate) i64);
    /// ARM-specific 128-bit wide vector of two packed `u64`.
    pub struct uint64x2_t(2 x pub(crate) u64);
    /// ARM-specific 128-bit wide vector of two packed `p64`.
    pub struct poly64x2_t(2 x pub(crate) p64);
}

/// ARM-specific type containing two `int8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x8x2_t(pub int8x8_t, pub int8x8_t);
/// ARM-specific type containing three `int8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x8x3_t(pub int8x8_t, pub int8x8_t, pub int8x8_t);
/// ARM-specific type containing four `int8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x8x4_t(pub int8x8_t, pub int8x8_t, pub int8x8_t, pub int8x8_t);

/// ARM-specific type containing two `int8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x16x2_t(pub int8x16_t, pub int8x16_t);
/// ARM-specific type containing three `int8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x16x3_t(pub int8x16_t, pub int8x16_t, pub int8x16_t);
/// ARM-specific type containing four `int8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int8x16x4_t(pub int8x16_t, pub int8x16_t, pub int8x16_t, pub int8x16_t);

/// ARM-specific type containing two `uint8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x8x2_t(pub uint8x8_t, pub uint8x8_t);
/// ARM-specific type containing three `uint8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x8x3_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t);
/// ARM-specific type containing four `uint8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x8x4_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t, pub uint8x8_t);

/// ARM-specific type containing two `uint8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x16x2_t(pub uint8x16_t, pub uint8x16_t);
/// ARM-specific type containing three `uint8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x16x3_t(pub uint8x16_t, pub uint8x16_t, pub uint8x16_t);
/// ARM-specific type containing four `uint8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint8x16x4_t(
    pub uint8x16_t,
    pub uint8x16_t,
    pub uint8x16_t,
    pub uint8x16_t,
);

/// ARM-specific type containing two `poly8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x8x2_t(pub poly8x8_t, pub poly8x8_t);
/// ARM-specific type containing three `poly8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x8x3_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t);
/// ARM-specific type containing four `poly8x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x8x4_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t, pub poly8x8_t);

/// ARM-specific type containing two `poly8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x16x2_t(pub poly8x16_t, pub poly8x16_t);
/// ARM-specific type containing three `poly8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x16x3_t(pub poly8x16_t, pub poly8x16_t, pub poly8x16_t);
/// ARM-specific type containing four `poly8x16_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly8x16x4_t(
    pub poly8x16_t,
    pub poly8x16_t,
    pub poly8x16_t,
    pub poly8x16_t,
);

/// ARM-specific type containing two `int16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x4x2_t(pub int16x4_t, pub int16x4_t);
/// ARM-specific type containing three `int16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x4x3_t(pub int16x4_t, pub int16x4_t, pub int16x4_t);
/// ARM-specific type containing four `int16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x4x4_t(pub int16x4_t, pub int16x4_t, pub int16x4_t, pub int16x4_t);

/// ARM-specific type containing two `int16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x8x2_t(pub int16x8_t, pub int16x8_t);
/// ARM-specific type containing three `int16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x8x3_t(pub int16x8_t, pub int16x8_t, pub int16x8_t);
/// ARM-specific type containing four `int16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int16x8x4_t(pub int16x8_t, pub int16x8_t, pub int16x8_t, pub int16x8_t);

/// ARM-specific type containing two `uint16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x4x2_t(pub uint16x4_t, pub uint16x4_t);
/// ARM-specific type containing three `uint16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x4x3_t(pub uint16x4_t, pub uint16x4_t, pub uint16x4_t);
/// ARM-specific type containing four `uint16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x4x4_t(
    pub uint16x4_t,
    pub uint16x4_t,
    pub uint16x4_t,
    pub uint16x4_t,
);

/// ARM-specific type containing two `uint16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x8x2_t(pub uint16x8_t, pub uint16x8_t);
/// ARM-specific type containing three `uint16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x8x3_t(pub uint16x8_t, pub uint16x8_t, pub uint16x8_t);
/// ARM-specific type containing four `uint16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint16x8x4_t(
    pub uint16x8_t,
    pub uint16x8_t,
    pub uint16x8_t,
    pub uint16x8_t,
);

/// ARM-specific type containing two `poly16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x4x2_t(pub poly16x4_t, pub poly16x4_t);
/// ARM-specific type containing three `poly16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x4x3_t(pub poly16x4_t, pub poly16x4_t, pub poly16x4_t);
/// ARM-specific type containing four `poly16x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x4x4_t(
    pub poly16x4_t,
    pub poly16x4_t,
    pub poly16x4_t,
    pub poly16x4_t,
);

/// ARM-specific type containing two `poly16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x8x2_t(pub poly16x8_t, pub poly16x8_t);
/// ARM-specific type containing three `poly16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x8x3_t(pub poly16x8_t, pub poly16x8_t, pub poly16x8_t);
/// ARM-specific type containing four `poly16x8_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly16x8x4_t(
    pub poly16x8_t,
    pub poly16x8_t,
    pub poly16x8_t,
    pub poly16x8_t,
);

/// ARM-specific type containing two `int32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x2x2_t(pub int32x2_t, pub int32x2_t);
/// ARM-specific type containing three `int32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x2x3_t(pub int32x2_t, pub int32x2_t, pub int32x2_t);
/// ARM-specific type containing four `int32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x2x4_t(pub int32x2_t, pub int32x2_t, pub int32x2_t, pub int32x2_t);

/// ARM-specific type containing two `int32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x4x2_t(pub int32x4_t, pub int32x4_t);
/// ARM-specific type containing three `int32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x4x3_t(pub int32x4_t, pub int32x4_t, pub int32x4_t);
/// ARM-specific type containing four `int32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int32x4x4_t(pub int32x4_t, pub int32x4_t, pub int32x4_t, pub int32x4_t);

/// ARM-specific type containing two `uint32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x2x2_t(pub uint32x2_t, pub uint32x2_t);
/// ARM-specific type containing three `uint32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x2x3_t(pub uint32x2_t, pub uint32x2_t, pub uint32x2_t);
/// ARM-specific type containing four `uint32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x2x4_t(
    pub uint32x2_t,
    pub uint32x2_t,
    pub uint32x2_t,
    pub uint32x2_t,
);

/// ARM-specific type containing two `uint32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x4x2_t(pub uint32x4_t, pub uint32x4_t);
/// ARM-specific type containing three `uint32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x4x3_t(pub uint32x4_t, pub uint32x4_t, pub uint32x4_t);
/// ARM-specific type containing four `uint32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint32x4x4_t(
    pub uint32x4_t,
    pub uint32x4_t,
    pub uint32x4_t,
    pub uint32x4_t,
);

/// ARM-specific type containing two `float32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x2x2_t(pub float32x2_t, pub float32x2_t);
/// ARM-specific type containing three `float32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x2x3_t(pub float32x2_t, pub float32x2_t, pub float32x2_t);
/// ARM-specific type containing four `float32x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x2x4_t(
    pub float32x2_t,
    pub float32x2_t,
    pub float32x2_t,
    pub float32x2_t,
);

/// ARM-specific type containing two `float32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x4x2_t(pub float32x4_t, pub float32x4_t);
/// ARM-specific type containing three `float32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x4x3_t(pub float32x4_t, pub float32x4_t, pub float32x4_t);
/// ARM-specific type containing four `float32x4_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct float32x4x4_t(
    pub float32x4_t,
    pub float32x4_t,
    pub float32x4_t,
    pub float32x4_t,
);

/// ARM-specific type containing two `int64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x1x2_t(pub int64x1_t, pub int64x1_t);
/// ARM-specific type containing three `int64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x1x3_t(pub int64x1_t, pub int64x1_t, pub int64x1_t);
/// ARM-specific type containing four `int64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x1x4_t(pub int64x1_t, pub int64x1_t, pub int64x1_t, pub int64x1_t);

/// ARM-specific type containing two `int64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x2x2_t(pub int64x2_t, pub int64x2_t);
/// ARM-specific type containing three `int64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x2x3_t(pub int64x2_t, pub int64x2_t, pub int64x2_t);
/// ARM-specific type containing four `int64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct int64x2x4_t(pub int64x2_t, pub int64x2_t, pub int64x2_t, pub int64x2_t);

/// ARM-specific type containing two `uint64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x1x2_t(pub uint64x1_t, pub uint64x1_t);
/// ARM-specific type containing three `uint64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x1x3_t(pub uint64x1_t, pub uint64x1_t, pub uint64x1_t);
/// ARM-specific type containing four `uint64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x1x4_t(
    pub uint64x1_t,
    pub uint64x1_t,
    pub uint64x1_t,
    pub uint64x1_t,
);

/// ARM-specific type containing two `uint64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x2x2_t(pub uint64x2_t, pub uint64x2_t);
/// ARM-specific type containing three `uint64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x2x3_t(pub uint64x2_t, pub uint64x2_t, pub uint64x2_t);
/// ARM-specific type containing four `uint64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct uint64x2x4_t(
    pub uint64x2_t,
    pub uint64x2_t,
    pub uint64x2_t,
    pub uint64x2_t,
);

/// ARM-specific type containing two `poly64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x1x2_t(pub poly64x1_t, pub poly64x1_t);
/// ARM-specific type containing three `poly64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x1x3_t(pub poly64x1_t, pub poly64x1_t, pub poly64x1_t);
/// ARM-specific type containing four `poly64x1_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x1x4_t(
    pub poly64x1_t,
    pub poly64x1_t,
    pub poly64x1_t,
    pub poly64x1_t,
);

/// ARM-specific type containing two `poly64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x2x2_t(pub poly64x2_t, pub poly64x2_t);
/// ARM-specific type containing three `poly64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x2x3_t(pub poly64x2_t, pub poly64x2_t, pub poly64x2_t);
/// ARM-specific type containing four `poly64x2_t` vectors.
#[repr(C)]
#[derive(Copy, Clone, Debug)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub struct poly64x2x4_t(
    pub poly64x2_t,
    pub poly64x2_t,
    pub poly64x2_t,
    pub poly64x2_t,
);

#[allow(improper_ctypes)]
extern "unadjusted" {
    // absolute value (64-bit)
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v8i8"
    )]
    fn vabs_s8_(a: int8x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v4i16"
    )]
    fn vabs_s16_(a: int16x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v2i32"
    )]
    fn vabs_s32_(a: int32x2_t) -> int32x2_t;
    // absolute value (128-bit)
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v16i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v16i8"
    )]
    fn vabsq_s8_(a: int8x16_t) -> int8x16_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v8i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v8i16"
    )]
    fn vabsq_s16_(a: int16x8_t) -> int16x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vabs.v4i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.abs.v4i32"
    )]
    fn vabsq_s32_(a: int32x4_t) -> int32x4_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmins.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.sminp.v8i8"
    )]
    fn vpmins_v8i8(a: int8x8_t, b: int8x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmins.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.sminp.v4i16"
    )]
    fn vpmins_v4i16(a: int16x4_t, b: int16x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmins.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.sminp.v2i32"
    )]
    fn vpmins_v2i32(a: int32x2_t, b: int32x2_t) -> int32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpminu.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uminp.v8i8"
    )]
    fn vpminu_v8i8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpminu.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uminp.v4i16"
    )]
    fn vpminu_v4i16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpminu.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uminp.v2i32"
    )]
    fn vpminu_v2i32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmins.v2f32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.fminp.v2f32"
    )]
    fn vpminf_v2f32(a: float32x2_t, b: float32x2_t) -> float32x2_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxs.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.smaxp.v8i8"
    )]
    fn vpmaxs_v8i8(a: int8x8_t, b: int8x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxs.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.smaxp.v4i16"
    )]
    fn vpmaxs_v4i16(a: int16x4_t, b: int16x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxs.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.smaxp.v2i32"
    )]
    fn vpmaxs_v2i32(a: int32x2_t, b: int32x2_t) -> int32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxu.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.umaxp.v8i8"
    )]
    fn vpmaxu_v8i8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxu.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.umaxp.v4i16"
    )]
    fn vpmaxu_v4i16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxu.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.umaxp.v2i32"
    )]
    fn vpmaxu_v2i32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpmaxs.v2f32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.fmaxp.v2f32"
    )]
    fn vpmaxf_v2f32(a: float32x2_t, b: float32x2_t) -> float32x2_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vraddhn.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.raddhn.v8i8"
    )]
    fn vraddhn_s16_(a: int16x8_t, b: int16x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vraddhn.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.raddhn.v4i16"
    )]
    fn vraddhn_s32_(a: int32x4_t, b: int32x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vraddhn.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.raddhn.v2i32"
    )]
    fn vraddhn_s64_(a: int64x2_t, b: int64x2_t) -> int32x2_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpadd.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.addp.v4i16"
    )]
    fn vpadd_s16_(a: int16x4_t, b: int16x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpadd.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.addp.v2i32"
    )]
    fn vpadd_s32_(a: int32x2_t, b: int32x2_t) -> int32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpadd.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.addp.v8i8"
    )]
    fn vpadd_s8_(a: int8x8_t, b: int8x8_t) -> int8x8_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v4i16.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v4i16.v8i8"
    )]
    pub(crate) fn vpaddl_s8_(a: int8x8_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v2i32.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v2i32.v4i16"
    )]
    pub(crate) fn vpaddl_s16_(a: int16x4_t) -> int32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v1i64.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v1i64.v2i32"
    )]
    pub(crate) fn vpaddl_s32_(a: int32x2_t) -> int64x1_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v8i16.v16i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v8i16.v16i8"
    )]
    pub(crate) fn vpaddlq_s8_(a: int8x16_t) -> int16x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v4i32.v8i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v4i32.v8i16"
    )]
    pub(crate) fn vpaddlq_s16_(a: int16x8_t) -> int32x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddls.v2i64.v4i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.saddlp.v2i64.v4i32"
    )]
    pub(crate) fn vpaddlq_s32_(a: int32x4_t) -> int64x2_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v4i16.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v4i16.v8i8"
    )]
    pub(crate) fn vpaddl_u8_(a: uint8x8_t) -> uint16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v2i32.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v2i32.v4i16"
    )]
    pub(crate) fn vpaddl_u16_(a: uint16x4_t) -> uint32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v1i64.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v1i64.v2i32"
    )]
    pub(crate) fn vpaddl_u32_(a: uint32x2_t) -> uint64x1_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v8i16.v16i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v8i16.v16i8"
    )]
    pub(crate) fn vpaddlq_u8_(a: uint8x16_t) -> uint16x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v4i32.v8i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v4i32.v8i16"
    )]
    pub(crate) fn vpaddlq_u16_(a: uint16x8_t) -> uint32x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.arm.neon.vpaddlu.v2i64.v4i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.aarch64.neon.uaddlp.v2i64.v4i32"
    )]
    pub(crate) fn vpaddlq_u32_(a: uint32x4_t) -> uint64x2_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctpop.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctpop.v8i8"
    )]
    fn vcnt_s8_(a: int8x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctpop.v16i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctpop.v16i8"
    )]
    fn vcntq_s8_(a: int8x16_t) -> int8x16_t;

    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v8i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v8i8"
    )]
    fn vclz_s8_(a: int8x8_t) -> int8x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v16i8")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v16i8"
    )]
    fn vclzq_s8_(a: int8x16_t) -> int8x16_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v4i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v4i16"
    )]
    fn vclz_s16_(a: int16x4_t) -> int16x4_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v8i16")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v8i16"
    )]
    fn vclzq_s16_(a: int16x8_t) -> int16x8_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v2i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v2i32"
    )]
    fn vclz_s32_(a: int32x2_t) -> int32x2_t;
    #[cfg_attr(target_arch = "arm", link_name = "llvm.ctlz.v4i32")]
    #[cfg_attr(
        any(target_arch = "aarch64", target_arch = "arm64ec"),
        link_name = "llvm.ctlz.v4i32"
    )]
    fn vclzq_s32_(a: int32x4_t) -> int32x4_t;
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_s8<const LANE: i32>(ptr: *const i8, src: int8x8_t) -> int8x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 15))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 15)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_s8<const LANE: i32>(ptr: *const i8, src: int8x16_t) -> int8x16_t {
    static_assert_uimm_bits!(LANE, 4);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_s16<const LANE: i32>(ptr: *const i16, src: int16x4_t) -> int16x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_s16<const LANE: i32>(ptr: *const i16, src: int16x8_t) -> int16x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_s32<const LANE: i32>(ptr: *const i32, src: int32x2_t) -> int32x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_s32<const LANE: i32>(ptr: *const i32, src: int32x4_t) -> int32x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 0))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr, LANE = 0)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_s64<const LANE: i32>(ptr: *const i64, src: int64x1_t) -> int64x1_t {
    static_assert!(LANE == 0);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_s64<const LANE: i32>(ptr: *const i64, src: int64x2_t) -> int64x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_u8<const LANE: i32>(ptr: *const u8, src: uint8x8_t) -> uint8x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 15))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 15)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_u8<const LANE: i32>(ptr: *const u8, src: uint8x16_t) -> uint8x16_t {
    static_assert_uimm_bits!(LANE, 4);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_u16<const LANE: i32>(ptr: *const u16, src: uint16x4_t) -> uint16x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_u16<const LANE: i32>(ptr: *const u16, src: uint16x8_t) -> uint16x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_u32<const LANE: i32>(ptr: *const u32, src: uint32x2_t) -> uint32x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_u32<const LANE: i32>(ptr: *const u32, src: uint32x4_t) -> uint32x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 0))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr, LANE = 0)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_u64<const LANE: i32>(ptr: *const u64, src: uint64x1_t) -> uint64x1_t {
    static_assert!(LANE == 0);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_u64<const LANE: i32>(ptr: *const u64, src: uint64x2_t) -> uint64x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_p8<const LANE: i32>(ptr: *const p8, src: poly8x8_t) -> poly8x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8", LANE = 15))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 15)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_p8<const LANE: i32>(ptr: *const p8, src: poly8x16_t) -> poly8x16_t {
    static_assert_uimm_bits!(LANE, 4);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_p16<const LANE: i32>(ptr: *const p16, src: poly16x4_t) -> poly16x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16", LANE = 7))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 7)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_p16<const LANE: i32>(ptr: *const p16, src: poly16x8_t) -> poly16x8_t {
    static_assert_uimm_bits!(LANE, 3);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
///
/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_lane_p64)
#[inline]
#[target_feature(enable = "neon,aes")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 0))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr, LANE = 0)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_p64<const LANE: i32>(ptr: *const p64, src: poly64x1_t) -> poly64x1_t {
    static_assert!(LANE == 0);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
///
/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_lane_p64)
#[inline]
#[target_feature(enable = "neon,aes")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_p64<const LANE: i32>(ptr: *const p64, src: poly64x2_t) -> poly64x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 1))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 1)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_lane_f32<const LANE: i32>(ptr: *const f32, src: float32x2_t) -> float32x2_t {
    static_assert_uimm_bits!(LANE, 1);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure to one lane of one register.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(2)]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32", LANE = 3))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1, LANE = 3)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_lane_f32<const LANE: i32>(ptr: *const f32, src: float32x4_t) -> float32x4_t {
    static_assert_uimm_bits!(LANE, 2);
    simd_insert!(src, LANE as u32, *ptr)
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_s8(ptr: *const i8) -> int8x8_t {
    let x = vld1_lane_s8::<0>(ptr, transmute(i8x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_s8(ptr: *const i8) -> int8x16_t {
    let x = vld1q_lane_s8::<0>(ptr, transmute(i8x16::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_s16(ptr: *const i16) -> int16x4_t {
    let x = vld1_lane_s16::<0>(ptr, transmute(i16x4::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_s16(ptr: *const i16) -> int16x8_t {
    let x = vld1q_lane_s16::<0>(ptr, transmute(i16x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_s32(ptr: *const i32) -> int32x2_t {
    let x = vld1_lane_s32::<0>(ptr, transmute(i32x2::splat(0)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_s32(ptr: *const i32) -> int32x4_t {
    let x = vld1q_lane_s32::<0>(ptr, transmute(i32x4::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_s64(ptr: *const i64) -> int64x1_t {
    #[cfg(any(target_arch = "aarch64", target_arch = "arm64ec"))]
    {
        crate::core_arch::aarch64::vld1_s64(ptr)
    }
    #[cfg(target_arch = "arm")]
    {
        crate::core_arch::arm::vld1_s64(ptr)
    }
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_s64(ptr: *const i64) -> int64x2_t {
    let x = vld1q_lane_s64::<0>(ptr, transmute(i64x2::splat(0)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_u8(ptr: *const u8) -> uint8x8_t {
    let x = vld1_lane_u8::<0>(ptr, transmute(u8x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_u8(ptr: *const u8) -> uint8x16_t {
    let x = vld1q_lane_u8::<0>(ptr, transmute(u8x16::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_u16(ptr: *const u16) -> uint16x4_t {
    let x = vld1_lane_u16::<0>(ptr, transmute(u16x4::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_u16(ptr: *const u16) -> uint16x8_t {
    let x = vld1q_lane_u16::<0>(ptr, transmute(u16x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_u32(ptr: *const u32) -> uint32x2_t {
    let x = vld1_lane_u32::<0>(ptr, transmute(u32x2::splat(0)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_u32(ptr: *const u32) -> uint32x4_t {
    let x = vld1q_lane_u32::<0>(ptr, transmute(u32x4::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_u64(ptr: *const u64) -> uint64x1_t {
    #[cfg(any(target_arch = "aarch64", target_arch = "arm64ec"))]
    {
        crate::core_arch::aarch64::vld1_u64(ptr)
    }
    #[cfg(target_arch = "arm")]
    {
        crate::core_arch::arm::vld1_u64(ptr)
    }
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_u64(ptr: *const u64) -> uint64x2_t {
    let x = vld1q_lane_u64::<0>(ptr, transmute(u64x2::splat(0)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_p8(ptr: *const p8) -> poly8x8_t {
    let x = vld1_lane_p8::<0>(ptr, transmute(u8x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_p8(ptr: *const p8) -> poly8x16_t {
    let x = vld1q_lane_p8::<0>(ptr, transmute(u8x16::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_p16(ptr: *const p16) -> poly16x4_t {
    let x = vld1_lane_p16::<0>(ptr, transmute(u16x4::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_p16(ptr: *const p16) -> poly16x8_t {
    let x = vld1q_lane_p16::<0>(ptr, transmute(u16x8::splat(0)));
    simd_shuffle!(x, x, [0, 0, 0, 0, 0, 0, 0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_f32(ptr: *const f32) -> float32x2_t {
    let x = vld1_lane_f32::<0>(ptr, transmute(f32x2::splat(0.)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
///
/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_dup_p64)
#[inline]
#[target_feature(enable = "neon,aes")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ldr)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1_dup_p64(ptr: *const p64) -> poly64x1_t {
    #[cfg(any(target_arch = "aarch64", target_arch = "arm64ec"))]
    {
        crate::core_arch::aarch64::vld1_p64(ptr)
    }
    #[cfg(target_arch = "arm")]
    {
        crate::core_arch::arm::vld1_p64(ptr)
    }
}

/// Load one single-element structure and Replicate to all lanes (of one register).
///
/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_dup_p64)
#[inline]
#[target_feature(enable = "neon,aes")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vldr"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_p64(ptr: *const p64) -> poly64x2_t {
    let x = vld1q_lane_p64::<0>(ptr, transmute(u64x2::splat(0)));
    simd_shuffle!(x, x, [0, 0])
}

/// Load one single-element structure and Replicate to all lanes (of one register).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vld1.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ld1r)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vld1q_dup_f32(ptr: *const f32) -> float32x4_t {
    let x = vld1q_lane_f32::<0>(ptr, transmute(f32x4::splat(0.)));
    simd_shuffle!(x, x, [0, 0, 0, 0])
}

// signed absolute difference and accumulate (64-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_s8(a: int8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
    simd_add(a, vabd_s8(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_s16(a: int16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
    simd_add(a, vabd_s16(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_s32(a: int32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
    simd_add(a, vabd_s32(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
    simd_add(a, vabd_u8(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_t {
    simd_add(a, vabd_u16(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaba_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_t {
    simd_add(a, vabd_u32(b, c))
}
// signed absolute difference and accumulate (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_s8(a: int8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
    simd_add(a, vabdq_s8(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t {
    simd_add(a, vabdq_s16(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.s32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("saba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t {
    simd_add(a, vabdq_s32(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_t {
    simd_add(a, vabdq_u8(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8_t {
    simd_add(a, vabdq_u16(b, c))
}
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vaba.u32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr("uaba")
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabaq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4_t {
    simd_add(a, vabdq_u32(b, c))
}

/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabs_s8(a: int8x8_t) -> int8x8_t {
    vabs_s8_(a)
}
/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabs_s16(a: int16x4_t) -> int16x4_t {
    vabs_s16_(a)
}
/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabs_s32(a: int32x2_t) -> int32x2_t {
    vabs_s32_(a)
}
/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabsq_s8(a: int8x16_t) -> int8x16_t {
    vabsq_s8_(a)
}
/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabsq_s16(a: int16x8_t) -> int16x8_t {
    vabsq_s16_(a)
}
/// Absolute value (wrapping).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vabs))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(abs)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vabsq_s32(a: int32x4_t) -> int32x4_t {
    vabsq_s32_(a)
}

/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    vpadd_s16_(a, b)
}
/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    vpadd_s32_(a, b)
}
/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    vpadd_s8_(a, b)
}
/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    transmute(vpadd_s16_(transmute(a), transmute(b)))
}
/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    transmute(vpadd_s32_(transmute(a), transmute(b)))
}
/// Add pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpadd_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    transmute(vpadd_s8_(transmute(a), transmute(b)))
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(add)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fadd)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vadd_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
    simd_add(a, b)
}

/// Vector add.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vadd))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fadd)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
    simd_add(a, b)
}

/// Signed Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_s8(a: int8x8_t, b: int8x8_t) -> int16x8_t {
    let a: int16x8_t = simd_cast(a);
    let b: int16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_s16(a: int16x4_t, b: int16x4_t) -> int32x4_t {
    let a: int32x4_t = simd_cast(a);
    let b: int32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_s32(a: int32x2_t, b: int32x2_t) -> int64x2_t {
    let a: int64x2_t = simd_cast(a);
    let b: int64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_u8(a: uint8x8_t, b: uint8x8_t) -> uint16x8_t {
    let a: uint16x8_t = simd_cast(a);
    let b: uint16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_u16(a: uint16x4_t, b: uint16x4_t) -> uint32x4_t {
    let a: uint32x4_t = simd_cast(a);
    let b: uint32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_u32(a: uint32x2_t, b: uint32x2_t) -> uint64x2_t {
    let a: uint64x2_t = simd_cast(a);
    let b: uint64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_s8(a: int8x16_t, b: int8x16_t) -> int16x8_t {
    let a: int8x8_t = simd_shuffle!(a, a, [8, 9, 10, 11, 12, 13, 14, 15]);
    let b: int8x8_t = simd_shuffle!(b, b, [8, 9, 10, 11, 12, 13, 14, 15]);
    let a: int16x8_t = simd_cast(a);
    let b: int16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_s16(a: int16x8_t, b: int16x8_t) -> int32x4_t {
    let a: int16x4_t = simd_shuffle!(a, a, [4, 5, 6, 7]);
    let b: int16x4_t = simd_shuffle!(b, b, [4, 5, 6, 7]);
    let a: int32x4_t = simd_cast(a);
    let b: int32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_s32(a: int32x4_t, b: int32x4_t) -> int64x2_t {
    let a: int32x2_t = simd_shuffle!(a, a, [2, 3]);
    let b: int32x2_t = simd_shuffle!(b, b, [2, 3]);
    let a: int64x2_t = simd_cast(a);
    let b: int64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_u8(a: uint8x16_t, b: uint8x16_t) -> uint16x8_t {
    let a: uint8x8_t = simd_shuffle!(a, a, [8, 9, 10, 11, 12, 13, 14, 15]);
    let b: uint8x8_t = simd_shuffle!(b, b, [8, 9, 10, 11, 12, 13, 14, 15]);
    let a: uint16x8_t = simd_cast(a);
    let b: uint16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_u16(a: uint16x8_t, b: uint16x8_t) -> uint32x4_t {
    let a: uint16x4_t = simd_shuffle!(a, a, [4, 5, 6, 7]);
    let b: uint16x4_t = simd_shuffle!(b, b, [4, 5, 6, 7]);
    let a: uint32x4_t = simd_cast(a);
    let b: uint32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Long (vector, high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddl2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddl_high_u32(a: uint32x4_t, b: uint32x4_t) -> uint64x2_t {
    let a: uint32x2_t = simd_shuffle!(a, a, [2, 3]);
    let b: uint32x2_t = simd_shuffle!(b, b, [2, 3]);
    let a: uint64x2_t = simd_cast(a);
    let b: uint64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_s8(a: int16x8_t, b: int8x8_t) -> int16x8_t {
    let b: int16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_s16(a: int32x4_t, b: int16x4_t) -> int32x4_t {
    let b: int32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_s32(a: int64x2_t, b: int32x2_t) -> int64x2_t {
    let b: int64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_u8(a: uint16x8_t, b: uint8x8_t) -> uint16x8_t {
    let b: uint16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_u16(a: uint32x4_t, b: uint16x4_t) -> uint32x4_t {
    let b: uint32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_u32(a: uint64x2_t, b: uint32x2_t) -> uint64x2_t {
    let b: uint64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_s8(a: int16x8_t, b: int8x16_t) -> int16x8_t {
    let b: int8x8_t = simd_shuffle!(b, b, [8, 9, 10, 11, 12, 13, 14, 15]);
    let b: int16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_s16(a: int32x4_t, b: int16x8_t) -> int32x4_t {
    let b: int16x4_t = simd_shuffle!(b, b, [4, 5, 6, 7]);
    let b: int32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Signed Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_s32(a: int64x2_t, b: int32x4_t) -> int64x2_t {
    let b: int32x2_t = simd_shuffle!(b, b, [2, 3]);
    let b: int64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_u8(a: uint16x8_t, b: uint8x16_t) -> uint16x8_t {
    let b: uint8x8_t = simd_shuffle!(b, b, [8, 9, 10, 11, 12, 13, 14, 15]);
    let b: uint16x8_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_u16(a: uint32x4_t, b: uint16x8_t) -> uint32x4_t {
    let b: uint16x4_t = simd_shuffle!(b, b, [4, 5, 6, 7]);
    let b: uint32x4_t = simd_cast(b);
    simd_add(a, b)
}

/// Unsigned Add Wide (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddw))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddw2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddw_high_u32(a: uint64x2_t, b: uint32x4_t) -> uint64x2_t {
    let b: uint32x2_t = simd_shuffle!(b, b, [2, 3]);
    let b: uint64x2_t = simd_cast(b);
    simd_add(a, b)
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_s16(a: int16x8_t, b: int16x8_t) -> int8x8_t {
    simd_cast(simd_shr(simd_add(a, b), int16x8_t::splat(8)))
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_s32(a: int32x4_t, b: int32x4_t) -> int16x4_t {
    simd_cast(simd_shr(simd_add(a, b), int32x4_t::splat(16)))
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_s64(a: int64x2_t, b: int64x2_t) -> int32x2_t {
    simd_cast(simd_shr(simd_add(a, b), int64x2_t::splat(32)))
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_u16(a: uint16x8_t, b: uint16x8_t) -> uint8x8_t {
    simd_cast(simd_shr(simd_add(a, b), uint16x8_t::splat(8)))
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_u32(a: uint32x4_t, b: uint32x4_t) -> uint16x4_t {
    simd_cast(simd_shr(simd_add(a, b), uint32x4_t::splat(16)))
}

/// Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_u64(a: uint64x2_t, b: uint64x2_t) -> uint32x2_t {
    simd_cast(simd_shr(simd_add(a, b), uint64x2_t::splat(32)))
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_s16(r: int8x8_t, a: int16x8_t, b: int16x8_t) -> int8x16_t {
    let x = simd_cast(simd_shr(simd_add(a, b), int16x8_t::splat(8)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_s32(r: int16x4_t, a: int32x4_t, b: int32x4_t) -> int16x8_t {
    let x = simd_cast(simd_shr(simd_add(a, b), int32x4_t::splat(16)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_s64(r: int32x2_t, a: int64x2_t, b: int64x2_t) -> int32x4_t {
    let x = simd_cast(simd_shr(simd_add(a, b), int64x2_t::splat(32)));
    simd_shuffle!(r, x, [0, 1, 2, 3])
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_u16(r: uint8x8_t, a: uint16x8_t, b: uint16x8_t) -> uint8x16_t {
    let x = simd_cast(simd_shr(simd_add(a, b), uint16x8_t::splat(8)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_u32(r: uint16x4_t, a: uint32x4_t, b: uint32x4_t) -> uint16x8_t {
    let x = simd_cast(simd_shr(simd_add(a, b), uint32x4_t::splat(16)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vaddhn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(addhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vaddhn_high_u64(r: uint32x2_t, a: uint64x2_t, b: uint64x2_t) -> uint32x4_t {
    let x = simd_cast(simd_shr(simd_add(a, b), uint64x2_t::splat(32)));
    simd_shuffle!(r, x, [0, 1, 2, 3])
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_s16(a: int16x8_t, b: int16x8_t) -> int8x8_t {
    vraddhn_s16_(a, b)
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_s32(a: int32x4_t, b: int32x4_t) -> int16x4_t {
    vraddhn_s32_(a, b)
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i64))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_s64(a: int64x2_t, b: int64x2_t) -> int32x2_t {
    vraddhn_s64_(a, b)
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_u16(a: uint16x8_t, b: uint16x8_t) -> uint8x8_t {
    transmute(vraddhn_s16_(transmute(a), transmute(b)))
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_u32(a: uint32x4_t, b: uint32x4_t) -> uint16x4_t {
    transmute(vraddhn_s32_(transmute(a), transmute(b)))
}

/// Rounding Add returning High Narrow.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i64))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_u64(a: uint64x2_t, b: uint64x2_t) -> uint32x2_t {
    transmute(vraddhn_s64_(transmute(a), transmute(b)))
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_s16(r: int8x8_t, a: int16x8_t, b: int16x8_t) -> int8x16_t {
    let x = vraddhn_s16_(a, b);
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_s32(r: int16x4_t, a: int32x4_t, b: int32x4_t) -> int16x8_t {
    let x = vraddhn_s32_(a, b);
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i64))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_s64(r: int32x2_t, a: int64x2_t, b: int64x2_t) -> int32x4_t {
    let x = vraddhn_s64_(a, b);
    simd_shuffle!(r, x, [0, 1, 2, 3])
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_u16(r: uint8x8_t, a: uint16x8_t, b: uint16x8_t) -> uint8x16_t {
    let x: uint8x8_t = transmute(vraddhn_s16_(transmute(a), transmute(b)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_u32(r: uint16x4_t, a: uint32x4_t, b: uint32x4_t) -> uint16x8_t {
    let x: uint16x4_t = transmute(vraddhn_s32_(transmute(a), transmute(b)));
    simd_shuffle!(r, x, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Rounding Add returning High Narrow (high half).
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vraddhn.i64))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(raddhn2)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vraddhn_high_u64(r: uint32x2_t, a: uint64x2_t, b: uint64x2_t) -> uint32x4_t {
    let x: uint32x2_t = transmute(vraddhn_s64_(transmute(a), transmute(b)));
    simd_shuffle!(r, x, [0, 1, 2, 3])
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s8))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_s8(a: int8x8_t) -> int16x4_t {
    vpaddl_s8_(a)
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_s16(a: int16x4_t) -> int32x2_t {
    vpaddl_s16_(a)
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_s32(a: int32x2_t) -> int64x1_t {
    vpaddl_s32_(a)
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s8))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_s8(a: int8x16_t) -> int16x8_t {
    vpaddlq_s8_(a)
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_s16(a: int16x8_t) -> int32x4_t {
    vpaddlq_s16_(a)
}

/// Signed Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.s32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(saddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_s32(a: int32x4_t) -> int64x2_t {
    vpaddlq_s32_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u8))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_u8(a: uint8x8_t) -> uint16x4_t {
    vpaddl_u8_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_u16(a: uint16x4_t) -> uint32x2_t {
    vpaddl_u16_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddl_u32(a: uint32x2_t) -> uint64x1_t {
    vpaddl_u32_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u8))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_u8(a: uint8x16_t) -> uint16x8_t {
    vpaddlq_u8_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u16))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_u16(a: uint16x8_t) -> uint32x4_t {
    vpaddlq_u16_(a)
}

/// Unsigned Add Long Pairwise.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpaddl.u32))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uaddlp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpaddlq_u32(a: uint32x4_t) -> uint64x2_t {
    vpaddlq_u32_(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_s16(a: int16x8_t) -> int8x8_t {
    simd_cast(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_s32(a: int32x4_t) -> int16x4_t {
    simd_cast(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_s64(a: int64x2_t) -> int32x2_t {
    simd_cast(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_u16(a: uint16x8_t) -> uint8x8_t {
    simd_cast(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_u32(a: uint32x4_t) -> uint16x4_t {
    simd_cast(a)
}

/// Vector narrow integer.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(xtn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovn_u64(a: uint64x2_t) -> uint32x2_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_s8(a: int8x8_t) -> int16x8_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_s16(a: int16x4_t) -> int32x4_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_s32(a: int32x2_t) -> int64x2_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_u8(a: uint8x8_t) -> uint16x8_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_u16(a: uint16x4_t) -> uint32x4_t {
    simd_cast(a)
}

/// Vector long move.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmovl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uxtl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovl_u32(a: uint32x2_t) -> uint64x2_t {
    simd_cast(a)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_s8(a: int8x8_t) -> int8x8_t {
    let b = int8x8_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_s8(a: int8x16_t) -> int8x16_t {
    let b = int8x16_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_s16(a: int16x4_t) -> int16x4_t {
    let b = int16x4_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_s16(a: int16x8_t) -> int16x8_t {
    let b = int16x8_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_s32(a: int32x2_t) -> int32x2_t {
    let b = int32x2_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_s32(a: int32x4_t) -> int32x4_t {
    let b = int32x4_t::splat(-1);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_u8(a: uint8x8_t) -> uint8x8_t {
    let b = uint8x8_t::splat(255);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_u8(a: uint8x16_t) -> uint8x16_t {
    let b = uint8x16_t::splat(255);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_u16(a: uint16x4_t) -> uint16x4_t {
    let b = uint16x4_t::splat(65_535);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_u16(a: uint16x8_t) -> uint16x8_t {
    let b = uint16x8_t::splat(65_535);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_u32(a: uint32x2_t) -> uint32x2_t {
    let b = uint32x2_t::splat(4_294_967_295);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_u32(a: uint32x4_t) -> uint32x4_t {
    let b = uint32x4_t::splat(4_294_967_295);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvn_p8(a: poly8x8_t) -> poly8x8_t {
    let b = poly8x8_t::splat(255);
    simd_xor(a, b)
}

/// Vector bitwise not.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vmvn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(mvn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmvnq_p8(a: poly8x16_t) -> poly8x16_t {
    let b = poly8x16_t::splat(255);
    simd_xor(a, b)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    let c = int8x8_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
    let c = int8x16_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    let c = int16x4_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
    let c = int16x8_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    let c = int32x2_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
    let c = int32x4_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
    let c = int64x1_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
    let c = int64x2_t::splat(-1);
    simd_and(simd_xor(b, c), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    let c = int8x8_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
    let c = int8x16_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    let c = int16x4_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
    let c = int16x8_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    let c = int32x2_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
    let c = int32x4_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbic_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
    let c = int64x1_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise bit clear
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbic))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bic)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbicq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
    let c = int64x2_t::splat(-1);
    simd_and(simd_xor(b, transmute(c)), a)
}

/// Bitwise Select instructions. This instruction sets each bit in the destination SIMD&FP register
/// to the corresponding bit from the first source SIMD&FP register when the original
/// destination bit was 1, otherwise from the second source SIMD&FP register.

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_s8(a: uint8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
    let not = int8x8_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_s16(a: uint16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
    let not = int16x4_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_s32(a: uint32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
    let not = int32x2_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_s64(a: uint64x1_t, b: int64x1_t, c: int64x1_t) -> int64x1_t {
    let not = int64x1_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
    let not = int8x8_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_t {
    let not = int16x4_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_t {
    let not = int32x2_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_u64(a: uint64x1_t, b: uint64x1_t, c: uint64x1_t) -> uint64x1_t {
    let not = int64x1_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_f32(a: uint32x2_t, b: float32x2_t, c: float32x2_t) -> float32x2_t {
    let not = int32x2_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_p8(a: uint8x8_t, b: poly8x8_t, c: poly8x8_t) -> poly8x8_t {
    let not = int8x8_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbsl_p16(a: uint16x4_t, b: poly16x4_t, c: poly16x4_t) -> poly16x4_t {
    let not = int16x4_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_s8(a: uint8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
    let not = int8x16_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_s16(a: uint16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t {
    let not = int16x8_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_s32(a: uint32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t {
    let not = int32x4_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_s64(a: uint64x2_t, b: int64x2_t, c: int64x2_t) -> int64x2_t {
    let not = int64x2_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_t {
    let not = int8x16_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8_t {
    let not = int16x8_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4_t {
    let not = int32x4_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint64x2_t {
    let not = int64x2_t::splat(-1);
    simd_or(simd_and(a, b), simd_and(simd_xor(a, transmute(not)), c))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_p8(a: uint8x16_t, b: poly8x16_t, c: poly8x16_t) -> poly8x16_t {
    let not = int8x16_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_p16(a: uint16x8_t, b: poly16x8_t, c: poly16x8_t) -> poly16x8_t {
    let not = int16x8_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Bitwise Select. (128-bit)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vbsl))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(bsl)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vbslq_f32(a: uint32x4_t, b: float32x4_t, c: float32x4_t) -> float32x4_t {
    let not = int32x4_t::splat(-1);
    transmute(simd_or(
        simd_and(a, transmute(b)),
        simd_and(simd_xor(a, transmute(not)), transmute(c)),
    ))
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    let c = int8x8_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
    let c = int8x16_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    let c = int16x4_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
    let c = int16x8_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    let c = int32x2_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
    let c = int32x4_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
    let c = int64x1_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
    let c = int64x2_t::splat(-1);
    simd_or(simd_xor(b, c), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    let c = int8x8_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
    let c = int8x16_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    let c = int16x4_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
    let c = int16x8_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    let c = int32x2_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
    let c = int32x4_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vorn_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
    let c = int64x1_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Vector bitwise inclusive OR NOT
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vorn))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(orn)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vornq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
    let c = int64x2_t::splat(-1);
    simd_or(simd_xor(b, transmute(c)), a)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    vpmins_v8i8(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    vpmins_v4i16(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(sminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    vpmins_v2i32(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    vpminu_v8i8(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    vpminu_v4i16(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(uminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    vpminu_v2i32(a, b)
}

/// Folding minimum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmin))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fminp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmin_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
    vpminf_v2f32(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(smaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
    vpmaxs_v8i8(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(smaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
    vpmaxs_v4i16(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(smaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
    vpmaxs_v2i32(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(umaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
    vpmaxu_v8i8(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(umaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
    vpmaxu_v4i16(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(umaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
    vpmaxu_v2i32(a, b)
}

/// Folding maximum of adjacent pairs
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(vpmax))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fmaxp)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vpmax_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
    vpmaxf_v2f32(a, b)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 1))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_u64<const IMM5: i32>(v: uint64x2_t) -> u64 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 0))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_u64<const IMM5: i32>(v: uint64x1_t) -> u64 {
    static_assert!(IMM5 == 0);
    simd_extract!(v, 0)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_u16<const IMM5: i32>(v: uint16x4_t) -> u16 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_s16<const IMM5: i32>(v: int16x4_t) -> i16 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_p16<const IMM5: i32>(v: poly16x4_t) -> p16 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 1))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_u32<const IMM5: i32>(v: uint32x2_t) -> u32 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 1))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_s32<const IMM5: i32>(v: int32x2_t) -> i32 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 1))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_f32<const IMM5: i32>(v: float32x2_t) -> f32 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 1))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_f32<const IMM5: i32>(v: float32x4_t) -> f32 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 0))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_p64<const IMM5: i32>(v: poly64x1_t) -> p64 {
    static_assert!(IMM5 == 0);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 0))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_p64<const IMM5: i32>(v: poly64x2_t) -> p64 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 0))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_s64<const IMM5: i32>(v: int64x1_t) -> i64 {
    static_assert!(IMM5 == 0);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 0))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_s64<const IMM5: i32>(v: int64x2_t) -> i64 {
    static_assert_uimm_bits!(IMM5, 1);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_u16<const IMM5: i32>(v: uint16x8_t) -> u16 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_u32<const IMM5: i32>(v: uint32x4_t) -> u32 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_s16<const IMM5: i32>(v: int16x8_t) -> i16 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_p16<const IMM5: i32>(v: poly16x8_t) -> p16 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_s32<const IMM5: i32>(v: int32x4_t) -> i32 {
    static_assert_uimm_bits!(IMM5, 2);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_u8<const IMM5: i32>(v: uint8x8_t) -> u8 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_s8<const IMM5: i32>(v: int8x8_t) -> i8 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_lane_p8<const IMM5: i32>(v: poly8x8_t) -> p8 {
    static_assert_uimm_bits!(IMM5, 3);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_u8<const IMM5: i32>(v: uint8x16_t) -> u8 {
    static_assert_uimm_bits!(IMM5, 4);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_s8<const IMM5: i32>(v: int8x16_t) -> i8 {
    static_assert_uimm_bits!(IMM5, 4);
    simd_extract!(v, IMM5 as u32)
}

/// Move vector element to general-purpose register
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[rustc_legacy_const_generics(1)]
#[cfg_attr(test, assert_instr(nop, IMM5 = 2))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vgetq_lane_p8<const IMM5: i32>(v: poly8x16_t) -> p8 {
    static_assert_uimm_bits!(IMM5, 4);
    simd_extract!(v, IMM5 as u32)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_s8(a: int8x16_t) -> int8x8_t {
    simd_shuffle!(a, a, [8, 9, 10, 11, 12, 13, 14, 15])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_s16(a: int16x8_t) -> int16x4_t {
    simd_shuffle!(a, a, [4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_s32(a: int32x4_t) -> int32x2_t {
    simd_shuffle!(a, a, [2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_s64(a: int64x2_t) -> int64x1_t {
    int64x1_t([simd_extract!(a, 1)])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_u8(a: uint8x16_t) -> uint8x8_t {
    simd_shuffle!(a, a, [8, 9, 10, 11, 12, 13, 14, 15])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_u16(a: uint16x8_t) -> uint16x4_t {
    simd_shuffle!(a, a, [4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_u32(a: uint32x4_t) -> uint32x2_t {
    simd_shuffle!(a, a, [2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_u64(a: uint64x2_t) -> uint64x1_t {
    uint64x1_t([simd_extract!(a, 1)])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_p8(a: poly8x16_t) -> poly8x8_t {
    simd_shuffle!(a, a, [8, 9, 10, 11, 12, 13, 14, 15])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_p16(a: poly16x8_t) -> poly16x4_t {
    simd_shuffle!(a, a, [4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(ext)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_high_f32(a: float32x4_t) -> float32x2_t {
    simd_shuffle!(a, a, [2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "vget_low_s8", since = "1.60.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_s8(a: int8x16_t) -> int8x8_t {
    simd_shuffle!(a, a, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_s16(a: int16x8_t) -> int16x4_t {
    simd_shuffle!(a, a, [0, 1, 2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_s32(a: int32x4_t) -> int32x2_t {
    simd_shuffle!(a, a, [0, 1])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_s64(a: int64x2_t) -> int64x1_t {
    int64x1_t([simd_extract!(a, 0)])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_u8(a: uint8x16_t) -> uint8x8_t {
    simd_shuffle!(a, a, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_u16(a: uint16x8_t) -> uint16x4_t {
    simd_shuffle!(a, a, [0, 1, 2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_u32(a: uint32x4_t) -> uint32x2_t {
    simd_shuffle!(a, a, [0, 1])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_u64(a: uint64x2_t) -> uint64x1_t {
    uint64x1_t([simd_extract!(a, 0)])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_p8(a: poly8x16_t) -> poly8x8_t {
    simd_shuffle!(a, a, [0, 1, 2, 3, 4, 5, 6, 7])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_p16(a: poly16x8_t) -> poly16x4_t {
    simd_shuffle!(a, a, [0, 1, 2, 3])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(test, assert_instr(nop))]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vget_low_f32(a: float32x4_t) -> float32x2_t {
    simd_shuffle!(a, a, [0, 1])
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_s8(value: i8) -> int8x16_t {
    int8x16_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_s16(value: i16) -> int16x8_t {
    int16x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_s32(value: i32) -> int32x4_t {
    int32x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_s64(value: i64) -> int64x2_t {
    int64x2_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_u8(value: u8) -> uint8x16_t {
    uint8x16_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_u16(value: u16) -> uint16x8_t {
    uint16x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_u32(value: u32) -> uint32x4_t {
    uint32x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_u64(value: u64) -> uint64x2_t {
    uint64x2_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_p8(value: p8) -> poly8x16_t {
    poly8x16_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_p16(value: p16) -> poly16x8_t {
    poly16x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdupq_n_f32(value: f32) -> float32x4_t {
    float32x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
///
/// Private vfp4 version used by FMA intriniscs because LLVM does
/// not inline the non-vfp4 version in vfp4 functions.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
unsafe fn vdupq_n_f32_vfp4(value: f32) -> float32x4_t {
    float32x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_s8(value: i8) -> int8x8_t {
    int8x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_s16(value: i16) -> int16x4_t {
    int16x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_s32(value: i32) -> int32x2_t {
    int32x2_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fmov)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_s64(value: i64) -> int64x1_t {
    int64x1_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_u8(value: u8) -> uint8x8_t {
    uint8x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_u16(value: u16) -> uint16x4_t {
    uint16x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_u32(value: u32) -> uint32x2_t {
    uint32x2_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fmov)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_u64(value: u64) -> uint64x1_t {
    uint64x1_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_p8(value: p8) -> poly8x8_t {
    poly8x8_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_p16(value: p16) -> poly16x4_t {
    poly16x4_t::splat(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vdup_n_f32(value: f32) -> float32x2_t {
    float32x2_t::splat(value)
}

/// Duplicate vector element to vector or scalar
///
/// Private vfp4 version used by FMA intriniscs because LLVM does
/// not inline the non-vfp4 version in vfp4 functions.
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
unsafe fn vdup_n_f32_vfp4(value: f32) -> float32x2_t {
    float32x2_t::splat(value)
}

/// Load SIMD&FP register (immediate offset)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(nop))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(nop)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vldrq_p128(a: *const p128) -> p128 {
    *a
}

/// Store SIMD&FP register (immediate offset)
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr(nop))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(nop)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vstrq_p128(a: *mut p128, b: p128) {
    *a = b;
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_s8(value: i8) -> int8x8_t {
    vdup_n_s8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_s16(value: i16) -> int16x4_t {
    vdup_n_s16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_s32(value: i32) -> int32x2_t {
    vdup_n_s32(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fmov)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_s64(value: i64) -> int64x1_t {
    vdup_n_s64(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_u8(value: u8) -> uint8x8_t {
    vdup_n_u8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_u16(value: u16) -> uint16x4_t {
    vdup_n_u16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_u32(value: u32) -> uint32x2_t {
    vdup_n_u32(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(fmov)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_u64(value: u64) -> uint64x1_t {
    vdup_n_u64(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_p8(value: p8) -> poly8x8_t {
    vdup_n_p8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_p16(value: p16) -> poly16x4_t {
    vdup_n_p16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmov_n_f32(value: f32) -> float32x2_t {
    vdup_n_f32(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_s8(value: i8) -> int8x16_t {
    vdupq_n_s8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_s16(value: i16) -> int16x8_t {
    vdupq_n_s16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_s32(value: i32) -> int32x4_t {
    vdupq_n_s32(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_s64(value: i64) -> int64x2_t {
    vdupq_n_s64(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_u8(value: u8) -> uint8x16_t {
    vdupq_n_u8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_u16(value: u16) -> uint16x8_t {
    vdupq_n_u16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_u32(value: u32) -> uint32x4_t {
    vdupq_n_u32(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vmov"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_u64(value: u64) -> uint64x2_t {
    vdupq_n_u64(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.8"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_p8(value: p8) -> poly8x16_t {
    vdupq_n_p8(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.16"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_p16(value: p16) -> poly16x8_t {
    vdupq_n_p16(value)
}

/// Duplicate vector element to vector or scalar
#[inline]
#[target_feature(enable = "neon")]
#[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vdup.32"))]
#[cfg_attr(
    all(test, any(target_arch = "aarch64", target_arch = "arm64ec")),
    assert_instr(dup)
)]
#[cfg_attr(
    not(target_arch = "arm"),
    stable(feature = "neon_intrinsics", since = "1.59.0")
)]
#[cfg_attr(
    target_arch = "arm",
    unstable(feature = "stdarch_arm_neon_intrinsics", issue = "111800")
)]
pub unsafe fn vmovq_n_f32(value: f32) -> float32x4_t {
    vdupq_n_f32(value)
}

/// Extract vector from pair of vectors
#