// Code generated by x/arch/internal/simdgen using 'go run . -xedPath $XED_PATH -o godefs -goroot $GOROOT go.yaml types.yaml categories.yaml'; DO NOT EDIT.

//go:build goexperiment.simd

package simd

/* AESDecryptLastRound */

// AESDecryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvShiftRows(InvSubBytes(x)), y)
//
// Asm: VAESDECLAST, CPU Feature: AVX, AES
func (x Uint8x16) AESDecryptLastRound(y Uint32x4) Uint8x16

// AESDecryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvShiftRows(InvSubBytes(x)), y)
//
// Asm: VAESDECLAST, CPU Feature: AVX512VAES
func (x Uint8x32) AESDecryptLastRound(y Uint32x8) Uint8x32

// AESDecryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvShiftRows(InvSubBytes(x)), y)
//
// Asm: VAESDECLAST, CPU Feature: AVX512VAES
func (x Uint8x64) AESDecryptLastRound(y Uint32x16) Uint8x64

/* AESDecryptOneRound */

// AESDecryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvMixColumns(InvShiftRows(InvSubBytes(x))), y)
//
// Asm: VAESDEC, CPU Feature: AVX, AES
func (x Uint8x16) AESDecryptOneRound(y Uint32x4) Uint8x16

// AESDecryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvMixColumns(InvShiftRows(InvSubBytes(x))), y)
//
// Asm: VAESDEC, CPU Feature: AVX512VAES
func (x Uint8x32) AESDecryptOneRound(y Uint32x8) Uint8x32

// AESDecryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of dw array in use.
// result = AddRoundKey(InvMixColumns(InvShiftRows(InvSubBytes(x))), y)
//
// Asm: VAESDEC, CPU Feature: AVX512VAES
func (x Uint8x64) AESDecryptOneRound(y Uint32x16) Uint8x64

/* AESEncryptLastRound */

// AESEncryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey((ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENCLAST, CPU Feature: AVX, AES
func (x Uint8x16) AESEncryptLastRound(y Uint32x4) Uint8x16

// AESEncryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey((ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENCLAST, CPU Feature: AVX512VAES
func (x Uint8x32) AESEncryptLastRound(y Uint32x8) Uint8x32

// AESEncryptLastRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey((ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENCLAST, CPU Feature: AVX512VAES
func (x Uint8x64) AESEncryptLastRound(y Uint32x16) Uint8x64

/* AESEncryptOneRound */

// AESEncryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey(MixColumns(ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENC, CPU Feature: AVX, AES
func (x Uint8x16) AESEncryptOneRound(y Uint32x4) Uint8x16

// AESEncryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey(MixColumns(ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENC, CPU Feature: AVX512VAES
func (x Uint8x32) AESEncryptOneRound(y Uint32x8) Uint8x32

// AESEncryptOneRound performs a series of operations in AES cipher algorithm defined in FIPS 197.
// x is the state array, starting from low index to high are s00, s10, s20, s30, s01, ..., s33.
// y is the chunk of w array in use.
// result = AddRoundKey(MixColumns(ShiftRows(SubBytes(x))), y)
//
// Asm: VAESENC, CPU Feature: AVX512VAES
func (x Uint8x64) AESEncryptOneRound(y Uint32x16) Uint8x64

/* AESInvMixColumns */

// AESInvMixColumns performs the InvMixColumns operation in AES cipher algorithm defined in FIPS 197.
// x is the chunk of w array in use.
// result = InvMixColumns(x)
//
// Asm: VAESIMC, CPU Feature: AVX, AES
func (x Uint32x4) AESInvMixColumns() Uint32x4

/* AESRoundKeyGenAssist */

// AESRoundKeyGenAssist performs some components of KeyExpansion in AES cipher algorithm defined in FIPS 197.
// x is an array of AES words, but only x[0] and x[2] are used.
// r is a value from the Rcon constant array.
// result[0] = XOR(SubWord(RotWord(x[0])), r)
// result[1] = SubWord(x[1])
// result[2] = XOR(SubWord(RotWord(x[2])), r)
// result[3] = SubWord(x[3])
//
// rconVal results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VAESKEYGENASSIST, CPU Feature: AVX, AES
func (x Uint32x4) AESRoundKeyGenAssist(rconVal uint8) Uint32x4

/* Abs */

// Abs computes the absolute value of each element.
//
// Asm: VPABSB, CPU Feature: AVX
func (x Int8x16) Abs() Int8x16

// Abs computes the absolute value of each element.
//
// Asm: VPABSB, CPU Feature: AVX2
func (x Int8x32) Abs() Int8x32

// Abs computes the absolute value of each element.
//
// Asm: VPABSB, CPU Feature: AVX512
func (x Int8x64) Abs() Int8x64

// Abs computes the absolute value of each element.
//
// Asm: VPABSW, CPU Feature: AVX
func (x Int16x8) Abs() Int16x8

// Abs computes the absolute value of each element.
//
// Asm: VPABSW, CPU Feature: AVX2
func (x Int16x16) Abs() Int16x16

// Abs computes the absolute value of each element.
//
// Asm: VPABSW, CPU Feature: AVX512
func (x Int16x32) Abs() Int16x32

// Abs computes the absolute value of each element.
//
// Asm: VPABSD, CPU Feature: AVX
func (x Int32x4) Abs() Int32x4

// Abs computes the absolute value of each element.
//
// Asm: VPABSD, CPU Feature: AVX2
func (x Int32x8) Abs() Int32x8

// Abs computes the absolute value of each element.
//
// Asm: VPABSD, CPU Feature: AVX512
func (x Int32x16) Abs() Int32x16

// Abs computes the absolute value of each element.
//
// Asm: VPABSQ, CPU Feature: AVX512
func (x Int64x2) Abs() Int64x2

// Abs computes the absolute value of each element.
//
// Asm: VPABSQ, CPU Feature: AVX512
func (x Int64x4) Abs() Int64x4

// Abs computes the absolute value of each element.
//
// Asm: VPABSQ, CPU Feature: AVX512
func (x Int64x8) Abs() Int64x8

/* Add */

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPS, CPU Feature: AVX
func (x Float32x4) Add(y Float32x4) Float32x4

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPS, CPU Feature: AVX
func (x Float32x8) Add(y Float32x8) Float32x8

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPS, CPU Feature: AVX512
func (x Float32x16) Add(y Float32x16) Float32x16

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPD, CPU Feature: AVX
func (x Float64x2) Add(y Float64x2) Float64x2

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPD, CPU Feature: AVX
func (x Float64x4) Add(y Float64x4) Float64x4

// Add adds corresponding elements of two vectors.
//
// Asm: VADDPD, CPU Feature: AVX512
func (x Float64x8) Add(y Float64x8) Float64x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX
func (x Int8x16) Add(y Int8x16) Int8x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX2
func (x Int8x32) Add(y Int8x32) Int8x32

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX512
func (x Int8x64) Add(y Int8x64) Int8x64

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX
func (x Int16x8) Add(y Int16x8) Int16x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX2
func (x Int16x16) Add(y Int16x16) Int16x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX512
func (x Int16x32) Add(y Int16x32) Int16x32

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX
func (x Int32x4) Add(y Int32x4) Int32x4

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX2
func (x Int32x8) Add(y Int32x8) Int32x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX512
func (x Int32x16) Add(y Int32x16) Int32x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX
func (x Int64x2) Add(y Int64x2) Int64x2

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX2
func (x Int64x4) Add(y Int64x4) Int64x4

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX512
func (x Int64x8) Add(y Int64x8) Int64x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX
func (x Uint8x16) Add(y Uint8x16) Uint8x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX2
func (x Uint8x32) Add(y Uint8x32) Uint8x32

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDB, CPU Feature: AVX512
func (x Uint8x64) Add(y Uint8x64) Uint8x64

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX
func (x Uint16x8) Add(y Uint16x8) Uint16x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX2
func (x Uint16x16) Add(y Uint16x16) Uint16x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDW, CPU Feature: AVX512
func (x Uint16x32) Add(y Uint16x32) Uint16x32

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX
func (x Uint32x4) Add(y Uint32x4) Uint32x4

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX2
func (x Uint32x8) Add(y Uint32x8) Uint32x8

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDD, CPU Feature: AVX512
func (x Uint32x16) Add(y Uint32x16) Uint32x16

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX
func (x Uint64x2) Add(y Uint64x2) Uint64x2

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX2
func (x Uint64x4) Add(y Uint64x4) Uint64x4

// Add adds corresponding elements of two vectors.
//
// Asm: VPADDQ, CPU Feature: AVX512
func (x Uint64x8) Add(y Uint64x8) Uint64x8

/* AddPairs */

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VHADDPS, CPU Feature: AVX
func (x Float32x4) AddPairs(y Float32x4) Float32x4

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VHADDPS, CPU Feature: AVX
func (x Float32x8) AddPairs(y Float32x8) Float32x8

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VHADDPD, CPU Feature: AVX
func (x Float64x2) AddPairs(y Float64x2) Float64x2

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VHADDPD, CPU Feature: AVX
func (x Float64x4) AddPairs(y Float64x4) Float64x4

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDW, CPU Feature: AVX
func (x Int16x8) AddPairs(y Int16x8) Int16x8

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDW, CPU Feature: AVX2
func (x Int16x16) AddPairs(y Int16x16) Int16x16

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDD, CPU Feature: AVX
func (x Int32x4) AddPairs(y Int32x4) Int32x4

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDD, CPU Feature: AVX2
func (x Int32x8) AddPairs(y Int32x8) Int32x8

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDW, CPU Feature: AVX
func (x Uint16x8) AddPairs(y Uint16x8) Uint16x8

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDW, CPU Feature: AVX2
func (x Uint16x16) AddPairs(y Uint16x16) Uint16x16

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDD, CPU Feature: AVX
func (x Uint32x4) AddPairs(y Uint32x4) Uint32x4

// AddPairs horizontally adds adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDD, CPU Feature: AVX2
func (x Uint32x8) AddPairs(y Uint32x8) Uint32x8

/* AddPairsSaturated */

// AddPairsSaturated horizontally adds adjacent pairs of elements with saturation.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDSW, CPU Feature: AVX
func (x Int16x8) AddPairsSaturated(y Int16x8) Int16x8

// AddPairsSaturated horizontally adds adjacent pairs of elements with saturation.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0+y1, y2+y3, ..., x0+x1, x2+x3, ...].
//
// Asm: VPHADDSW, CPU Feature: AVX2
func (x Int16x16) AddPairsSaturated(y Int16x16) Int16x16

/* AddSaturated */

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSB, CPU Feature: AVX
func (x Int8x16) AddSaturated(y Int8x16) Int8x16

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSB, CPU Feature: AVX2
func (x Int8x32) AddSaturated(y Int8x32) Int8x32

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSB, CPU Feature: AVX512
func (x Int8x64) AddSaturated(y Int8x64) Int8x64

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSW, CPU Feature: AVX
func (x Int16x8) AddSaturated(y Int16x8) Int16x8

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSW, CPU Feature: AVX2
func (x Int16x16) AddSaturated(y Int16x16) Int16x16

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDSW, CPU Feature: AVX512
func (x Int16x32) AddSaturated(y Int16x32) Int16x32

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSB, CPU Feature: AVX
func (x Uint8x16) AddSaturated(y Uint8x16) Uint8x16

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSB, CPU Feature: AVX2
func (x Uint8x32) AddSaturated(y Uint8x32) Uint8x32

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSB, CPU Feature: AVX512
func (x Uint8x64) AddSaturated(y Uint8x64) Uint8x64

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSW, CPU Feature: AVX
func (x Uint16x8) AddSaturated(y Uint16x8) Uint16x8

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSW, CPU Feature: AVX2
func (x Uint16x16) AddSaturated(y Uint16x16) Uint16x16

// AddSaturated adds corresponding elements of two vectors with saturation.
//
// Asm: VPADDUSW, CPU Feature: AVX512
func (x Uint16x32) AddSaturated(y Uint16x32) Uint16x32

/* AddSub */

// AddSub subtracts even elements and adds odd elements of two vectors.
//
// Asm: VADDSUBPS, CPU Feature: AVX
func (x Float32x4) AddSub(y Float32x4) Float32x4

// AddSub subtracts even elements and adds odd elements of two vectors.
//
// Asm: VADDSUBPS, CPU Feature: AVX
func (x Float32x8) AddSub(y Float32x8) Float32x8

// AddSub subtracts even elements and adds odd elements of two vectors.
//
// Asm: VADDSUBPD, CPU Feature: AVX
func (x Float64x2) AddSub(y Float64x2) Float64x2

// AddSub subtracts even elements and adds odd elements of two vectors.
//
// Asm: VADDSUBPD, CPU Feature: AVX
func (x Float64x4) AddSub(y Float64x4) Float64x4

/* And */

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Int8x16) And(y Int8x16) Int8x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Int8x32) And(y Int8x32) Int8x32

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Int8x64) And(y Int8x64) Int8x64

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Int16x8) And(y Int16x8) Int16x8

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Int16x16) And(y Int16x16) Int16x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Int16x32) And(y Int16x32) Int16x32

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Int32x4) And(y Int32x4) Int32x4

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Int32x8) And(y Int32x8) Int32x8

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Int32x16) And(y Int32x16) Int32x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Int64x2) And(y Int64x2) Int64x2

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Int64x4) And(y Int64x4) Int64x4

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDQ, CPU Feature: AVX512
func (x Int64x8) And(y Int64x8) Int64x8

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Uint8x16) And(y Uint8x16) Uint8x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Uint8x32) And(y Uint8x32) Uint8x32

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Uint8x64) And(y Uint8x64) Uint8x64

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Uint16x8) And(y Uint16x8) Uint16x8

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Uint16x16) And(y Uint16x16) Uint16x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Uint16x32) And(y Uint16x32) Uint16x32

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Uint32x4) And(y Uint32x4) Uint32x4

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Uint32x8) And(y Uint32x8) Uint32x8

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDD, CPU Feature: AVX512
func (x Uint32x16) And(y Uint32x16) Uint32x16

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX
func (x Uint64x2) And(y Uint64x2) Uint64x2

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPAND, CPU Feature: AVX2
func (x Uint64x4) And(y Uint64x4) Uint64x4

// And performs a bitwise AND operation between two vectors.
//
// Asm: VPANDQ, CPU Feature: AVX512
func (x Uint64x8) And(y Uint64x8) Uint64x8

/* AndNot */

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Int8x16) AndNot(y Int8x16) Int8x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Int8x32) AndNot(y Int8x32) Int8x32

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Int8x64) AndNot(y Int8x64) Int8x64

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Int16x8) AndNot(y Int16x8) Int16x8

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Int16x16) AndNot(y Int16x16) Int16x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Int16x32) AndNot(y Int16x32) Int16x32

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Int32x4) AndNot(y Int32x4) Int32x4

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Int32x8) AndNot(y Int32x8) Int32x8

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Int32x16) AndNot(y Int32x16) Int32x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Int64x2) AndNot(y Int64x2) Int64x2

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Int64x4) AndNot(y Int64x4) Int64x4

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDNQ, CPU Feature: AVX512
func (x Int64x8) AndNot(y Int64x8) Int64x8

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Uint8x16) AndNot(y Uint8x16) Uint8x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Uint8x32) AndNot(y Uint8x32) Uint8x32

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Uint8x64) AndNot(y Uint8x64) Uint8x64

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Uint16x8) AndNot(y Uint16x8) Uint16x8

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Uint16x16) AndNot(y Uint16x16) Uint16x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Uint16x32) AndNot(y Uint16x32) Uint16x32

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Uint32x4) AndNot(y Uint32x4) Uint32x4

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Uint32x8) AndNot(y Uint32x8) Uint32x8

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDND, CPU Feature: AVX512
func (x Uint32x16) AndNot(y Uint32x16) Uint32x16

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX
func (x Uint64x2) AndNot(y Uint64x2) Uint64x2

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDN, CPU Feature: AVX2
func (x Uint64x4) AndNot(y Uint64x4) Uint64x4

// AndNot performs a bitwise x &^ y.
//
// Asm: VPANDNQ, CPU Feature: AVX512
func (x Uint64x8) AndNot(y Uint64x8) Uint64x8

/* Average */

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGB, CPU Feature: AVX
func (x Uint8x16) Average(y Uint8x16) Uint8x16

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGB, CPU Feature: AVX2
func (x Uint8x32) Average(y Uint8x32) Uint8x32

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGB, CPU Feature: AVX512
func (x Uint8x64) Average(y Uint8x64) Uint8x64

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGW, CPU Feature: AVX
func (x Uint16x8) Average(y Uint16x8) Uint16x8

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGW, CPU Feature: AVX2
func (x Uint16x16) Average(y Uint16x16) Uint16x16

// Average computes the rounded average of corresponding elements.
//
// Asm: VPAVGW, CPU Feature: AVX512
func (x Uint16x32) Average(y Uint16x32) Uint16x32

/* Broadcast128 */

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VBROADCASTSS, CPU Feature: AVX2
func (x Float32x4) Broadcast128() Float32x4

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX2
func (x Float64x2) Broadcast128() Float64x2

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX2
func (x Int8x16) Broadcast128() Int8x16

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX2
func (x Int16x8) Broadcast128() Int16x8

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX2
func (x Int32x4) Broadcast128() Int32x4

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX2
func (x Int64x2) Broadcast128() Int64x2

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX2
func (x Uint8x16) Broadcast128() Uint8x16

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX2
func (x Uint16x8) Broadcast128() Uint16x8

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX2
func (x Uint32x4) Broadcast128() Uint32x4

// Broadcast128 copies element zero of its (128-bit) input to all elements of
// the 128-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX2
func (x Uint64x2) Broadcast128() Uint64x2

/* Broadcast256 */

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VBROADCASTSS, CPU Feature: AVX2
func (x Float32x4) Broadcast256() Float32x8

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VBROADCASTSD, CPU Feature: AVX2
func (x Float64x2) Broadcast256() Float64x4

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX2
func (x Int8x16) Broadcast256() Int8x32

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX2
func (x Int16x8) Broadcast256() Int16x16

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX2
func (x Int32x4) Broadcast256() Int32x8

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX2
func (x Int64x2) Broadcast256() Int64x4

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX2
func (x Uint8x16) Broadcast256() Uint8x32

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX2
func (x Uint16x8) Broadcast256() Uint16x16

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX2
func (x Uint32x4) Broadcast256() Uint32x8

// Broadcast256 copies element zero of its (128-bit) input to all elements of
// the 256-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX2
func (x Uint64x2) Broadcast256() Uint64x4

/* Broadcast512 */

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VBROADCASTSS, CPU Feature: AVX512
func (x Float32x4) Broadcast512() Float32x16

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VBROADCASTSD, CPU Feature: AVX512
func (x Float64x2) Broadcast512() Float64x8

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX512
func (x Int8x16) Broadcast512() Int8x64

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX512
func (x Int16x8) Broadcast512() Int16x32

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX512
func (x Int32x4) Broadcast512() Int32x16

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX512
func (x Int64x2) Broadcast512() Int64x8

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTB, CPU Feature: AVX512
func (x Uint8x16) Broadcast512() Uint8x64

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTW, CPU Feature: AVX512
func (x Uint16x8) Broadcast512() Uint16x32

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTD, CPU Feature: AVX512
func (x Uint32x4) Broadcast512() Uint32x16

// Broadcast512 copies element zero of its (128-bit) input to all elements of
// the 512-bit output vector.
//
// Asm: VPBROADCASTQ, CPU Feature: AVX512
func (x Uint64x2) Broadcast512() Uint64x8

/* Ceil */

// Ceil rounds elements up to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x4) Ceil() Float32x4

// Ceil rounds elements up to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x8) Ceil() Float32x8

// Ceil rounds elements up to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x2) Ceil() Float64x2

// Ceil rounds elements up to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x4) Ceil() Float64x4

/* CeilScaled */

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x4) CeilScaled(prec uint8) Float32x4

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x8) CeilScaled(prec uint8) Float32x8

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x16) CeilScaled(prec uint8) Float32x16

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x2) CeilScaled(prec uint8) Float64x2

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x4) CeilScaled(prec uint8) Float64x4

// CeilScaled rounds elements up with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x8) CeilScaled(prec uint8) Float64x8

/* CeilScaledResidue */

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x4) CeilScaledResidue(prec uint8) Float32x4

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x8) CeilScaledResidue(prec uint8) Float32x8

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x16) CeilScaledResidue(prec uint8) Float32x16

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x2) CeilScaledResidue(prec uint8) Float64x2

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x4) CeilScaledResidue(prec uint8) Float64x4

// CeilScaledResidue computes the difference after ceiling with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x8) CeilScaledResidue(prec uint8) Float64x8

/* Compress */

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPS, CPU Feature: AVX512
func (x Float32x4) Compress(mask Mask32x4) Float32x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPS, CPU Feature: AVX512
func (x Float32x8) Compress(mask Mask32x8) Float32x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPS, CPU Feature: AVX512
func (x Float32x16) Compress(mask Mask32x16) Float32x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPD, CPU Feature: AVX512
func (x Float64x2) Compress(mask Mask64x2) Float64x2

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPD, CPU Feature: AVX512
func (x Float64x4) Compress(mask Mask64x4) Float64x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VCOMPRESSPD, CPU Feature: AVX512
func (x Float64x8) Compress(mask Mask64x8) Float64x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Int8x16) Compress(mask Mask8x16) Int8x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Int8x32) Compress(mask Mask8x32) Int8x32

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Int8x64) Compress(mask Mask8x64) Int8x64

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Int16x8) Compress(mask Mask16x8) Int16x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Int16x16) Compress(mask Mask16x16) Int16x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Int16x32) Compress(mask Mask16x32) Int16x32

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Int32x4) Compress(mask Mask32x4) Int32x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Int32x8) Compress(mask Mask32x8) Int32x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Int32x16) Compress(mask Mask32x16) Int32x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Int64x2) Compress(mask Mask64x2) Int64x2

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Int64x4) Compress(mask Mask64x4) Int64x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Int64x8) Compress(mask Mask64x8) Int64x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Uint8x16) Compress(mask Mask8x16) Uint8x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Uint8x32) Compress(mask Mask8x32) Uint8x32

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSB, CPU Feature: AVX512VBMI2
func (x Uint8x64) Compress(mask Mask8x64) Uint8x64

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Uint16x8) Compress(mask Mask16x8) Uint16x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Uint16x16) Compress(mask Mask16x16) Uint16x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSW, CPU Feature: AVX512VBMI2
func (x Uint16x32) Compress(mask Mask16x32) Uint16x32

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Uint32x4) Compress(mask Mask32x4) Uint32x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Uint32x8) Compress(mask Mask32x8) Uint32x8

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSD, CPU Feature: AVX512
func (x Uint32x16) Compress(mask Mask32x16) Uint32x16

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Uint64x2) Compress(mask Mask64x2) Uint64x2

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Uint64x4) Compress(mask Mask64x4) Uint64x4

// Compress performs a compression on vector x using mask by
// selecting elements as indicated by mask, and pack them to lower indexed elements.
//
// Asm: VPCOMPRESSQ, CPU Feature: AVX512
func (x Uint64x8) Compress(mask Mask64x8) Uint64x8

/* ConcatPermute */

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Int8x16) ConcatPermute(y Int8x16, indices Uint8x16) Int8x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Uint8x16) ConcatPermute(y Uint8x16, indices Uint8x16) Uint8x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Int8x32) ConcatPermute(y Int8x32, indices Uint8x32) Int8x32

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Uint8x32) ConcatPermute(y Uint8x32, indices Uint8x32) Uint8x32

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Int8x64) ConcatPermute(y Int8x64, indices Uint8x64) Int8x64

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2B, CPU Feature: AVX512VBMI
func (x Uint8x64) ConcatPermute(y Uint8x64, indices Uint8x64) Uint8x64

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Int16x8) ConcatPermute(y Int16x8, indices Uint16x8) Int16x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Uint16x8) ConcatPermute(y Uint16x8, indices Uint16x8) Uint16x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Int16x16) ConcatPermute(y Int16x16, indices Uint16x16) Int16x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Uint16x16) ConcatPermute(y Uint16x16, indices Uint16x16) Uint16x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Int16x32) ConcatPermute(y Int16x32, indices Uint16x32) Int16x32

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2W, CPU Feature: AVX512
func (x Uint16x32) ConcatPermute(y Uint16x32, indices Uint16x32) Uint16x32

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PS, CPU Feature: AVX512
func (x Float32x4) ConcatPermute(y Float32x4, indices Uint32x4) Float32x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Int32x4) ConcatPermute(y Int32x4, indices Uint32x4) Int32x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Uint32x4) ConcatPermute(y Uint32x4, indices Uint32x4) Uint32x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PS, CPU Feature: AVX512
func (x Float32x8) ConcatPermute(y Float32x8, indices Uint32x8) Float32x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Int32x8) ConcatPermute(y Int32x8, indices Uint32x8) Int32x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Uint32x8) ConcatPermute(y Uint32x8, indices Uint32x8) Uint32x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PS, CPU Feature: AVX512
func (x Float32x16) ConcatPermute(y Float32x16, indices Uint32x16) Float32x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Int32x16) ConcatPermute(y Int32x16, indices Uint32x16) Int32x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2D, CPU Feature: AVX512
func (x Uint32x16) ConcatPermute(y Uint32x16, indices Uint32x16) Uint32x16

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PD, CPU Feature: AVX512
func (x Float64x2) ConcatPermute(y Float64x2, indices Uint64x2) Float64x2

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Int64x2) ConcatPermute(y Int64x2, indices Uint64x2) Int64x2

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Uint64x2) ConcatPermute(y Uint64x2, indices Uint64x2) Uint64x2

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PD, CPU Feature: AVX512
func (x Float64x4) ConcatPermute(y Float64x4, indices Uint64x4) Float64x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Int64x4) ConcatPermute(y Int64x4, indices Uint64x4) Int64x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Uint64x4) ConcatPermute(y Uint64x4, indices Uint64x4) Uint64x4

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2PD, CPU Feature: AVX512
func (x Float64x8) ConcatPermute(y Float64x8, indices Uint64x8) Float64x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Int64x8) ConcatPermute(y Int64x8, indices Uint64x8) Int64x8

// ConcatPermute performs a full permutation of vector x, y using indices:
// result := {xy[indices[0]], xy[indices[1]], ..., xy[indices[n]]}
// where xy is the concatenation of x (lower half) and y (upper half).
// Only the needed bits to represent xy's index are used in indices' elements.
//
// Asm: VPERMI2Q, CPU Feature: AVX512
func (x Uint64x8) ConcatPermute(y Uint64x8, indices Uint64x8) Uint64x8

/* ConcatShiftBytesRight */

// ConcatShiftBytesRight concatenates x and y and shift it right by constant bytes.
// The result vector will be the lower half of the concatenated vector.
//
// constant results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPALIGNR, CPU Feature: AVX
func (x Uint8x16) ConcatShiftBytesRight(constant uint8, y Uint8x16) Uint8x16

/* ConcatShiftBytesRightGrouped */

// ConcatShiftBytesRightGrouped concatenates x and y and shift it right by constant bytes.
// The result vector will be the lower half of the concatenated vector.
// This operation is performed grouped by each 16 byte.
//
// constant results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPALIGNR, CPU Feature: AVX2
func (x Uint8x32) ConcatShiftBytesRightGrouped(constant uint8, y Uint8x32) Uint8x32

// ConcatShiftBytesRightGrouped concatenates x and y and shift it right by constant bytes.
// The result vector will be the lower half of the concatenated vector.
// This operation is performed grouped by each 16 byte.
//
// constant results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPALIGNR, CPU Feature: AVX512
func (x Uint8x64) ConcatShiftBytesRightGrouped(constant uint8, y Uint8x64) Uint8x64

/* ConvertToInt32 */

// ConvertToInt32 converts element values to int32.
//
// Asm: VCVTTPS2DQ, CPU Feature: AVX
func (x Float32x4) ConvertToInt32() Int32x4

// ConvertToInt32 converts element values to int32.
//
// Asm: VCVTTPS2DQ, CPU Feature: AVX
func (x Float32x8) ConvertToInt32() Int32x8

// ConvertToInt32 converts element values to int32.
//
// Asm: VCVTTPS2DQ, CPU Feature: AVX512
func (x Float32x16) ConvertToInt32() Int32x16

/* ConvertToUint32 */

// ConvertToUint32 converts element values to uint32.
//
// Asm: VCVTPS2UDQ, CPU Feature: AVX512
func (x Float32x4) ConvertToUint32() Uint32x4

// ConvertToUint32 converts element values to uint32.
//
// Asm: VCVTPS2UDQ, CPU Feature: AVX512
func (x Float32x8) ConvertToUint32() Uint32x8

// ConvertToUint32 converts element values to uint32.
//
// Asm: VCVTPS2UDQ, CPU Feature: AVX512
func (x Float32x16) ConvertToUint32() Uint32x16

/* CopySign */

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGNB, CPU Feature: AVX
func (x Int8x16) CopySign(y Int8x16) Int8x16

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGNB, CPU Feature: AVX2
func (x Int8x32) CopySign(y Int8x32) Int8x32

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGNW, CPU Feature: AVX
func (x Int16x8) CopySign(y Int16x8) Int16x8

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGNW, CPU Feature: AVX2
func (x Int16x16) CopySign(y Int16x16) Int16x16

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGND, CPU Feature: AVX
func (x Int32x4) CopySign(y Int32x4) Int32x4

// CopySign returns the product of the first operand with -1, 0, or 1,
// whichever constant is nearest to the value of the second operand.
//
// Asm: VPSIGND, CPU Feature: AVX2
func (x Int32x8) CopySign(y Int32x8) Int32x8

/* Div */

// Div divides elements of two vectors.
//
// Asm: VDIVPS, CPU Feature: AVX
func (x Float32x4) Div(y Float32x4) Float32x4

// Div divides elements of two vectors.
//
// Asm: VDIVPS, CPU Feature: AVX
func (x Float32x8) Div(y Float32x8) Float32x8

// Div divides elements of two vectors.
//
// Asm: VDIVPS, CPU Feature: AVX512
func (x Float32x16) Div(y Float32x16) Float32x16

// Div divides elements of two vectors.
//
// Asm: VDIVPD, CPU Feature: AVX
func (x Float64x2) Div(y Float64x2) Float64x2

// Div divides elements of two vectors.
//
// Asm: VDIVPD, CPU Feature: AVX
func (x Float64x4) Div(y Float64x4) Float64x4

// Div divides elements of two vectors.
//
// Asm: VDIVPD, CPU Feature: AVX512
func (x Float64x8) Div(y Float64x8) Float64x8

/* DotProductPairs */

// DotProductPairs multiplies the elements and add the pairs together,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDWD, CPU Feature: AVX
func (x Int16x8) DotProductPairs(y Int16x8) Int32x4

// DotProductPairs multiplies the elements and add the pairs together,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDWD, CPU Feature: AVX2
func (x Int16x16) DotProductPairs(y Int16x16) Int32x8

// DotProductPairs multiplies the elements and add the pairs together,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDWD, CPU Feature: AVX512
func (x Int16x32) DotProductPairs(y Int16x32) Int32x16

/* DotProductPairsSaturated */

// DotProductPairsSaturated multiplies the elements and add the pairs together with saturation,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDUBSW, CPU Feature: AVX
func (x Uint8x16) DotProductPairsSaturated(y Int8x16) Int16x8

// DotProductPairsSaturated multiplies the elements and add the pairs together with saturation,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDUBSW, CPU Feature: AVX2
func (x Uint8x32) DotProductPairsSaturated(y Int8x32) Int16x16

// DotProductPairsSaturated multiplies the elements and add the pairs together with saturation,
// yielding a vector of half as many elements with twice the input element size.
//
// Asm: VPMADDUBSW, CPU Feature: AVX512
func (x Uint8x64) DotProductPairsSaturated(y Int8x64) Int16x32

/* DotProductQuadruple */

// DotProductQuadruple performs dot products on groups of 4 elements of x and y.
// DotProductQuadruple(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSD, CPU Feature: AVXVNNI
func (x Int8x16) DotProductQuadruple(y Uint8x16) Int32x4

// DotProductQuadruple performs dot products on groups of 4 elements of x and y.
// DotProductQuadruple(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSD, CPU Feature: AVXVNNI
func (x Int8x32) DotProductQuadruple(y Uint8x32) Int32x8

// DotProductQuadruple performs dot products on groups of 4 elements of x and y.
// DotProductQuadruple(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSD, CPU Feature: AVX512VNNI
func (x Int8x64) DotProductQuadruple(y Uint8x64) Int32x16

/* DotProductQuadrupleSaturated */

// DotProductQuadrupleSaturated multiplies performs dot products on groups of 4 elements of x and y.
// DotProductQuadrupleSaturated(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSDS, CPU Feature: AVXVNNI
func (x Int8x16) DotProductQuadrupleSaturated(y Uint8x16) Int32x4

// DotProductQuadrupleSaturated multiplies performs dot products on groups of 4 elements of x and y.
// DotProductQuadrupleSaturated(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSDS, CPU Feature: AVXVNNI
func (x Int8x32) DotProductQuadrupleSaturated(y Uint8x32) Int32x8

// DotProductQuadrupleSaturated multiplies performs dot products on groups of 4 elements of x and y.
// DotProductQuadrupleSaturated(x, y).Add(z) will be optimized to the full form of the underlying instruction.
//
// Asm: VPDPBUSDS, CPU Feature: AVX512VNNI
func (x Int8x64) DotProductQuadrupleSaturated(y Uint8x64) Int32x16

/* Equal */

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX
func (x Int8x16) Equal(y Int8x16) Mask8x16

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX2
func (x Int8x32) Equal(y Int8x32) Mask8x32

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX512
func (x Int8x64) Equal(y Int8x64) Mask8x64

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX
func (x Int16x8) Equal(y Int16x8) Mask16x8

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX2
func (x Int16x16) Equal(y Int16x16) Mask16x16

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX512
func (x Int16x32) Equal(y Int16x32) Mask16x32

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX
func (x Int32x4) Equal(y Int32x4) Mask32x4

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX2
func (x Int32x8) Equal(y Int32x8) Mask32x8

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX512
func (x Int32x16) Equal(y Int32x16) Mask32x16

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX
func (x Int64x2) Equal(y Int64x2) Mask64x2

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX2
func (x Int64x4) Equal(y Int64x4) Mask64x4

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX512
func (x Int64x8) Equal(y Int64x8) Mask64x8

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX
func (x Uint8x16) Equal(y Uint8x16) Mask8x16

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX2
func (x Uint8x32) Equal(y Uint8x32) Mask8x32

// Equal compares for equality.
//
// Asm: VPCMPEQB, CPU Feature: AVX512
func (x Uint8x64) Equal(y Uint8x64) Mask8x64

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX
func (x Uint16x8) Equal(y Uint16x8) Mask16x8

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX2
func (x Uint16x16) Equal(y Uint16x16) Mask16x16

// Equal compares for equality.
//
// Asm: VPCMPEQW, CPU Feature: AVX512
func (x Uint16x32) Equal(y Uint16x32) Mask16x32

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX
func (x Uint32x4) Equal(y Uint32x4) Mask32x4

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX2
func (x Uint32x8) Equal(y Uint32x8) Mask32x8

// Equal compares for equality.
//
// Asm: VPCMPEQD, CPU Feature: AVX512
func (x Uint32x16) Equal(y Uint32x16) Mask32x16

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX
func (x Uint64x2) Equal(y Uint64x2) Mask64x2

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX2
func (x Uint64x4) Equal(y Uint64x4) Mask64x4

// Equal compares for equality.
//
// Asm: VPCMPEQQ, CPU Feature: AVX512
func (x Uint64x8) Equal(y Uint64x8) Mask64x8

// Equal compares for equality.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) Equal(y Float32x4) Mask32x4

// Equal compares for equality.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) Equal(y Float32x8) Mask32x8

// Equal compares for equality.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) Equal(y Float32x16) Mask32x16

// Equal compares for equality.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) Equal(y Float64x2) Mask64x2

// Equal compares for equality.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) Equal(y Float64x4) Mask64x4

// Equal compares for equality.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) Equal(y Float64x8) Mask64x8

/* Expand */

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPS, CPU Feature: AVX512
func (x Float32x4) Expand(mask Mask32x4) Float32x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPS, CPU Feature: AVX512
func (x Float32x8) Expand(mask Mask32x8) Float32x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPS, CPU Feature: AVX512
func (x Float32x16) Expand(mask Mask32x16) Float32x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPD, CPU Feature: AVX512
func (x Float64x2) Expand(mask Mask64x2) Float64x2

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPD, CPU Feature: AVX512
func (x Float64x4) Expand(mask Mask64x4) Float64x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VEXPANDPD, CPU Feature: AVX512
func (x Float64x8) Expand(mask Mask64x8) Float64x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Int8x16) Expand(mask Mask8x16) Int8x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Int8x32) Expand(mask Mask8x32) Int8x32

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Int8x64) Expand(mask Mask8x64) Int8x64

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Int16x8) Expand(mask Mask16x8) Int16x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Int16x16) Expand(mask Mask16x16) Int16x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Int16x32) Expand(mask Mask16x32) Int16x32

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Int32x4) Expand(mask Mask32x4) Int32x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Int32x8) Expand(mask Mask32x8) Int32x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Int32x16) Expand(mask Mask32x16) Int32x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Int64x2) Expand(mask Mask64x2) Int64x2

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Int64x4) Expand(mask Mask64x4) Int64x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Int64x8) Expand(mask Mask64x8) Int64x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Uint8x16) Expand(mask Mask8x16) Uint8x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Uint8x32) Expand(mask Mask8x32) Uint8x32

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDB, CPU Feature: AVX512VBMI2
func (x Uint8x64) Expand(mask Mask8x64) Uint8x64

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Uint16x8) Expand(mask Mask16x8) Uint16x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Uint16x16) Expand(mask Mask16x16) Uint16x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDW, CPU Feature: AVX512VBMI2
func (x Uint16x32) Expand(mask Mask16x32) Uint16x32

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Uint32x4) Expand(mask Mask32x4) Uint32x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Uint32x8) Expand(mask Mask32x8) Uint32x8

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDD, CPU Feature: AVX512
func (x Uint32x16) Expand(mask Mask32x16) Uint32x16

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Uint64x2) Expand(mask Mask64x2) Uint64x2

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Uint64x4) Expand(mask Mask64x4) Uint64x4

// Expand performs an expansion on a vector x whose elements are packed to lower parts.
// The expansion is to distribute elements as indexed by mask, from lower mask elements to upper in order.
//
// Asm: VPEXPANDQ, CPU Feature: AVX512
func (x Uint64x8) Expand(mask Mask64x8) Uint64x8

/* ExtendLo2ToInt64x2 */

// ExtendLo2ToInt64x2 converts 2 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBQ, CPU Feature: AVX
func (x Int8x16) ExtendLo2ToInt64x2() Int64x2

// ExtendLo2ToInt64x2 converts 2 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWQ, CPU Feature: AVX
func (x Int16x8) ExtendLo2ToInt64x2() Int64x2

// ExtendLo2ToInt64x2 converts 2 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXDQ, CPU Feature: AVX
func (x Int32x4) ExtendLo2ToInt64x2() Int64x2

/* ExtendLo2ToUint64x2 */

// ExtendLo2ToUint64x2 converts 2 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBQ, CPU Feature: AVX
func (x Uint8x16) ExtendLo2ToUint64x2() Uint64x2

// ExtendLo2ToUint64x2 converts 2 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWQ, CPU Feature: AVX
func (x Uint16x8) ExtendLo2ToUint64x2() Uint64x2

// ExtendLo2ToUint64x2 converts 2 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXDQ, CPU Feature: AVX
func (x Uint32x4) ExtendLo2ToUint64x2() Uint64x2

/* ExtendLo4ToInt32x4 */

// ExtendLo4ToInt32x4 converts 4 lowest vector element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBD, CPU Feature: AVX
func (x Int8x16) ExtendLo4ToInt32x4() Int32x4

// ExtendLo4ToInt32x4 converts 4 lowest vector element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWD, CPU Feature: AVX
func (x Int16x8) ExtendLo4ToInt32x4() Int32x4

/* ExtendLo4ToInt64x4 */

// ExtendLo4ToInt64x4 converts 4 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBQ, CPU Feature: AVX2
func (x Int8x16) ExtendLo4ToInt64x4() Int64x4

// ExtendLo4ToInt64x4 converts 4 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWQ, CPU Feature: AVX2
func (x Int16x8) ExtendLo4ToInt64x4() Int64x4

/* ExtendLo4ToUint32x4 */

// ExtendLo4ToUint32x4 converts 4 lowest vector element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBD, CPU Feature: AVX
func (x Uint8x16) ExtendLo4ToUint32x4() Uint32x4

// ExtendLo4ToUint32x4 converts 4 lowest vector element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWD, CPU Feature: AVX
func (x Uint16x8) ExtendLo4ToUint32x4() Uint32x4

/* ExtendLo4ToUint64x4 */

// ExtendLo4ToUint64x4 converts 4 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBQ, CPU Feature: AVX2
func (x Uint8x16) ExtendLo4ToUint64x4() Uint64x4

// ExtendLo4ToUint64x4 converts 4 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWQ, CPU Feature: AVX2
func (x Uint16x8) ExtendLo4ToUint64x4() Uint64x4

/* ExtendLo8ToInt16x8 */

// ExtendLo8ToInt16x8 converts 8 lowest vector element values to int16.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBW, CPU Feature: AVX
func (x Int8x16) ExtendLo8ToInt16x8() Int16x8

/* ExtendLo8ToInt32x8 */

// ExtendLo8ToInt32x8 converts 8 lowest vector element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBD, CPU Feature: AVX2
func (x Int8x16) ExtendLo8ToInt32x8() Int32x8

/* ExtendLo8ToInt64x8 */

// ExtendLo8ToInt64x8 converts 8 lowest vector element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBQ, CPU Feature: AVX512
func (x Int8x16) ExtendLo8ToInt64x8() Int64x8

/* ExtendLo8ToUint16x8 */

// ExtendLo8ToUint16x8 converts 8 lowest vector element values to uint16.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBW, CPU Feature: AVX
func (x Uint8x16) ExtendLo8ToUint16x8() Uint16x8

/* ExtendLo8ToUint32x8 */

// ExtendLo8ToUint32x8 converts 8 lowest vector element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBD, CPU Feature: AVX2
func (x Uint8x16) ExtendLo8ToUint32x8() Uint32x8

/* ExtendLo8ToUint64x8 */

// ExtendLo8ToUint64x8 converts 8 lowest vector element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBQ, CPU Feature: AVX512
func (x Uint8x16) ExtendLo8ToUint64x8() Uint64x8

/* ExtendToInt16 */

// ExtendToInt16 converts element values to int16.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBW, CPU Feature: AVX2
func (x Int8x16) ExtendToInt16() Int16x16

// ExtendToInt16 converts element values to int16.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBW, CPU Feature: AVX512
func (x Int8x32) ExtendToInt16() Int16x32

/* ExtendToInt32 */

// ExtendToInt32 converts element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXBD, CPU Feature: AVX512
func (x Int8x16) ExtendToInt32() Int32x16

// ExtendToInt32 converts element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWD, CPU Feature: AVX2
func (x Int16x8) ExtendToInt32() Int32x8

// ExtendToInt32 converts element values to int32.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWD, CPU Feature: AVX512
func (x Int16x16) ExtendToInt32() Int32x16

/* ExtendToInt64 */

// ExtendToInt64 converts element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXWQ, CPU Feature: AVX512
func (x Int16x8) ExtendToInt64() Int64x8

// ExtendToInt64 converts element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXDQ, CPU Feature: AVX2
func (x Int32x4) ExtendToInt64() Int64x4

// ExtendToInt64 converts element values to int64.
// The result vector's elements are sign-extended.
//
// Asm: VPMOVSXDQ, CPU Feature: AVX512
func (x Int32x8) ExtendToInt64() Int64x8

/* ExtendToUint16 */

// ExtendToUint16 converts element values to uint16.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBW, CPU Feature: AVX2
func (x Uint8x16) ExtendToUint16() Uint16x16

// ExtendToUint16 converts element values to uint16.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBW, CPU Feature: AVX512
func (x Uint8x32) ExtendToUint16() Uint16x32

/* ExtendToUint32 */

// ExtendToUint32 converts element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXBD, CPU Feature: AVX512
func (x Uint8x16) ExtendToUint32() Uint32x16

// ExtendToUint32 converts element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWD, CPU Feature: AVX2
func (x Uint16x8) ExtendToUint32() Uint32x8

// ExtendToUint32 converts element values to uint32.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWD, CPU Feature: AVX512
func (x Uint16x16) ExtendToUint32() Uint32x16

/* ExtendToUint64 */

// ExtendToUint64 converts element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXWQ, CPU Feature: AVX512
func (x Uint16x8) ExtendToUint64() Uint64x8

// ExtendToUint64 converts element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXDQ, CPU Feature: AVX2
func (x Uint32x4) ExtendToUint64() Uint64x4

// ExtendToUint64 converts element values to uint64.
// The result vector's elements are zero-extended.
//
// Asm: VPMOVZXDQ, CPU Feature: AVX512
func (x Uint32x8) ExtendToUint64() Uint64x8

/* Floor */

// Floor rounds elements down to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x4) Floor() Float32x4

// Floor rounds elements down to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x8) Floor() Float32x8

// Floor rounds elements down to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x2) Floor() Float64x2

// Floor rounds elements down to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x4) Floor() Float64x4

/* FloorScaled */

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x4) FloorScaled(prec uint8) Float32x4

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x8) FloorScaled(prec uint8) Float32x8

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x16) FloorScaled(prec uint8) Float32x16

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x2) FloorScaled(prec uint8) Float64x2

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x4) FloorScaled(prec uint8) Float64x4

// FloorScaled rounds elements down with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x8) FloorScaled(prec uint8) Float64x8

/* FloorScaledResidue */

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x4) FloorScaledResidue(prec uint8) Float32x4

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x8) FloorScaledResidue(prec uint8) Float32x8

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x16) FloorScaledResidue(prec uint8) Float32x16

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x2) FloorScaledResidue(prec uint8) Float64x2

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x4) FloorScaledResidue(prec uint8) Float64x4

// FloorScaledResidue computes the difference after flooring with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x8) FloorScaledResidue(prec uint8) Float64x8

/* GaloisFieldAffineTransform */

// GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEQB, CPU Feature: AVX512GFNI
func (x Uint8x16) GaloisFieldAffineTransform(y Uint64x2, b uint8) Uint8x16

// GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEQB, CPU Feature: AVX512GFNI
func (x Uint8x32) GaloisFieldAffineTransform(y Uint64x4, b uint8) Uint8x32

// GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEQB, CPU Feature: AVX512GFNI
func (x Uint8x64) GaloisFieldAffineTransform(y Uint64x8, b uint8) Uint8x64

/* GaloisFieldAffineTransformInverse */

// GaloisFieldAffineTransformInverse computes an affine transformation in GF(2^8),
// with x inverted with respect to reduction polynomial x^8 + x^4 + x^3 + x + 1:
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512GFNI
func (x Uint8x16) GaloisFieldAffineTransformInverse(y Uint64x2, b uint8) Uint8x16

// GaloisFieldAffineTransformInverse computes an affine transformation in GF(2^8),
// with x inverted with respect to reduction polynomial x^8 + x^4 + x^3 + x + 1:
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512GFNI
func (x Uint8x32) GaloisFieldAffineTransformInverse(y Uint64x4, b uint8) Uint8x32

// GaloisFieldAffineTransformInverse computes an affine transformation in GF(2^8),
// with x inverted with respect to reduction polynomial x^8 + x^4 + x^3 + x + 1:
// x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
// corresponding to a group of 8 elements in x.
//
// b results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512GFNI
func (x Uint8x64) GaloisFieldAffineTransformInverse(y Uint64x8, b uint8) Uint8x64

/* GaloisFieldMul */

// GaloisFieldMul computes element-wise GF(2^8) multiplication with
// reduction polynomial x^8 + x^4 + x^3 + x + 1.
//
// Asm: VGF2P8MULB, CPU Feature: AVX512GFNI
func (x Uint8x16) GaloisFieldMul(y Uint8x16) Uint8x16

// GaloisFieldMul computes element-wise GF(2^8) multiplication with
// reduction polynomial x^8 + x^4 + x^3 + x + 1.
//
// Asm: VGF2P8MULB, CPU Feature: AVX512GFNI
func (x Uint8x32) GaloisFieldMul(y Uint8x32) Uint8x32

// GaloisFieldMul computes element-wise GF(2^8) multiplication with
// reduction polynomial x^8 + x^4 + x^3 + x + 1.
//
// Asm: VGF2P8MULB, CPU Feature: AVX512GFNI
func (x Uint8x64) GaloisFieldMul(y Uint8x64) Uint8x64

/* GetElem */

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRD, CPU Feature: AVX
func (x Float32x4) GetElem(index uint8) float32

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRQ, CPU Feature: AVX
func (x Float64x2) GetElem(index uint8) float64

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRB, CPU Feature: AVX512
func (x Int8x16) GetElem(index uint8) int8

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRW, CPU Feature: AVX512
func (x Int16x8) GetElem(index uint8) int16

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRD, CPU Feature: AVX
func (x Int32x4) GetElem(index uint8) int32

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRQ, CPU Feature: AVX
func (x Int64x2) GetElem(index uint8) int64

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRB, CPU Feature: AVX512
func (x Uint8x16) GetElem(index uint8) uint8

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRW, CPU Feature: AVX512
func (x Uint16x8) GetElem(index uint8) uint16

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRD, CPU Feature: AVX
func (x Uint32x4) GetElem(index uint8) uint32

// GetElem retrieves a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPEXTRQ, CPU Feature: AVX
func (x Uint64x2) GetElem(index uint8) uint64

/* GetHi */

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTF128, CPU Feature: AVX
func (x Float32x8) GetHi() Float32x4

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTF64X4, CPU Feature: AVX512
func (x Float32x16) GetHi() Float32x8

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTF128, CPU Feature: AVX
func (x Float64x4) GetHi() Float64x2

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTF64X4, CPU Feature: AVX512
func (x Float64x8) GetHi() Float64x4

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int8x32) GetHi() Int8x16

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int8x64) GetHi() Int8x32

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int16x16) GetHi() Int16x8

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int16x32) GetHi() Int16x16

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int32x8) GetHi() Int32x4

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int32x16) GetHi() Int32x8

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int64x4) GetHi() Int64x2

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int64x8) GetHi() Int64x4

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint8x32) GetHi() Uint8x16

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint8x64) GetHi() Uint8x32

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint16x16) GetHi() Uint16x8

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint16x32) GetHi() Uint16x16

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint32x8) GetHi() Uint32x4

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint32x16) GetHi() Uint32x8

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint64x4) GetHi() Uint64x2

// GetHi returns the upper half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint64x8) GetHi() Uint64x4

/* GetLo */

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTF128, CPU Feature: AVX
func (x Float32x8) GetLo() Float32x4

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTF64X4, CPU Feature: AVX512
func (x Float32x16) GetLo() Float32x8

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTF128, CPU Feature: AVX
func (x Float64x4) GetLo() Float64x2

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTF64X4, CPU Feature: AVX512
func (x Float64x8) GetLo() Float64x4

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int8x32) GetLo() Int8x16

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int8x64) GetLo() Int8x32

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int16x16) GetLo() Int16x8

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int16x32) GetLo() Int16x16

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int32x8) GetLo() Int32x4

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int32x16) GetLo() Int32x8

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Int64x4) GetLo() Int64x2

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Int64x8) GetLo() Int64x4

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint8x32) GetLo() Uint8x16

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint8x64) GetLo() Uint8x32

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint16x16) GetLo() Uint16x8

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint16x32) GetLo() Uint16x16

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint32x8) GetLo() Uint32x4

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint32x16) GetLo() Uint32x8

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI128, CPU Feature: AVX2
func (x Uint64x4) GetLo() Uint64x2

// GetLo returns the lower half of x.
//
// Asm: VEXTRACTI64X4, CPU Feature: AVX512
func (x Uint64x8) GetLo() Uint64x4

/* Greater */

// Greater compares for greater than.
//
// Asm: VPCMPGTB, CPU Feature: AVX
func (x Int8x16) Greater(y Int8x16) Mask8x16

// Greater compares for greater than.
//
// Asm: VPCMPGTB, CPU Feature: AVX2
func (x Int8x32) Greater(y Int8x32) Mask8x32

// Greater compares for greater than.
//
// Asm: VPCMPGTB, CPU Feature: AVX512
func (x Int8x64) Greater(y Int8x64) Mask8x64

// Greater compares for greater than.
//
// Asm: VPCMPGTW, CPU Feature: AVX
func (x Int16x8) Greater(y Int16x8) Mask16x8

// Greater compares for greater than.
//
// Asm: VPCMPGTW, CPU Feature: AVX2
func (x Int16x16) Greater(y Int16x16) Mask16x16

// Greater compares for greater than.
//
// Asm: VPCMPGTW, CPU Feature: AVX512
func (x Int16x32) Greater(y Int16x32) Mask16x32

// Greater compares for greater than.
//
// Asm: VPCMPGTD, CPU Feature: AVX
func (x Int32x4) Greater(y Int32x4) Mask32x4

// Greater compares for greater than.
//
// Asm: VPCMPGTD, CPU Feature: AVX2
func (x Int32x8) Greater(y Int32x8) Mask32x8

// Greater compares for greater than.
//
// Asm: VPCMPGTD, CPU Feature: AVX512
func (x Int32x16) Greater(y Int32x16) Mask32x16

// Greater compares for greater than.
//
// Asm: VPCMPGTQ, CPU Feature: AVX
func (x Int64x2) Greater(y Int64x2) Mask64x2

// Greater compares for greater than.
//
// Asm: VPCMPGTQ, CPU Feature: AVX2
func (x Int64x4) Greater(y Int64x4) Mask64x4

// Greater compares for greater than.
//
// Asm: VPCMPGTQ, CPU Feature: AVX512
func (x Int64x8) Greater(y Int64x8) Mask64x8

// Greater compares for greater than.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) Greater(y Float32x4) Mask32x4

// Greater compares for greater than.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) Greater(y Float32x8) Mask32x8

// Greater compares for greater than.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) Greater(y Float32x16) Mask32x16

// Greater compares for greater than.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) Greater(y Float64x2) Mask64x2

// Greater compares for greater than.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) Greater(y Float64x4) Mask64x4

// Greater compares for greater than.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) Greater(y Float64x8) Mask64x8

// Greater compares for greater than.
//
// Asm: VPCMPUB, CPU Feature: AVX512
func (x Uint8x64) Greater(y Uint8x64) Mask8x64

// Greater compares for greater than.
//
// Asm: VPCMPUW, CPU Feature: AVX512
func (x Uint16x32) Greater(y Uint16x32) Mask16x32

// Greater compares for greater than.
//
// Asm: VPCMPUD, CPU Feature: AVX512
func (x Uint32x16) Greater(y Uint32x16) Mask32x16

// Greater compares for greater than.
//
// Asm: VPCMPUQ, CPU Feature: AVX512
func (x Uint64x8) Greater(y Uint64x8) Mask64x8

/* GreaterEqual */

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) GreaterEqual(y Float32x4) Mask32x4

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) GreaterEqual(y Float32x8) Mask32x8

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) GreaterEqual(y Float32x16) Mask32x16

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) GreaterEqual(y Float64x2) Mask64x2

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) GreaterEqual(y Float64x4) Mask64x4

// GreaterEqual compares for greater than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) GreaterEqual(y Float64x8) Mask64x8

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPB, CPU Feature: AVX512
func (x Int8x64) GreaterEqual(y Int8x64) Mask8x64

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPW, CPU Feature: AVX512
func (x Int16x32) GreaterEqual(y Int16x32) Mask16x32

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPD, CPU Feature: AVX512
func (x Int32x16) GreaterEqual(y Int32x16) Mask32x16

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPQ, CPU Feature: AVX512
func (x Int64x8) GreaterEqual(y Int64x8) Mask64x8

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPUB, CPU Feature: AVX512
func (x Uint8x64) GreaterEqual(y Uint8x64) Mask8x64

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPUW, CPU Feature: AVX512
func (x Uint16x32) GreaterEqual(y Uint16x32) Mask16x32

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPUD, CPU Feature: AVX512
func (x Uint32x16) GreaterEqual(y Uint32x16) Mask32x16

// GreaterEqual compares for greater than or equal.
//
// Asm: VPCMPUQ, CPU Feature: AVX512
func (x Uint64x8) GreaterEqual(y Uint64x8) Mask64x8

/* InterleaveHi */

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX
func (x Int16x8) InterleaveHi(y Int16x8) Int16x8

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX
func (x Int32x4) InterleaveHi(y Int32x4) Int32x4

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX
func (x Int64x2) InterleaveHi(y Int64x2) Int64x2

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX
func (x Uint16x8) InterleaveHi(y Uint16x8) Uint16x8

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX
func (x Uint32x4) InterleaveHi(y Uint32x4) Uint32x4

// InterleaveHi interleaves the elements of the high halves of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX
func (x Uint64x2) InterleaveHi(y Uint64x2) Uint64x2

/* InterleaveHiGrouped */

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX2
func (x Int16x16) InterleaveHiGrouped(y Int16x16) Int16x16

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX512
func (x Int16x32) InterleaveHiGrouped(y Int16x32) Int16x32

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX2
func (x Int32x8) InterleaveHiGrouped(y Int32x8) Int32x8

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX512
func (x Int32x16) InterleaveHiGrouped(y Int32x16) Int32x16

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX2
func (x Int64x4) InterleaveHiGrouped(y Int64x4) Int64x4

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX512
func (x Int64x8) InterleaveHiGrouped(y Int64x8) Int64x8

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX2
func (x Uint16x16) InterleaveHiGrouped(y Uint16x16) Uint16x16

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHWD, CPU Feature: AVX512
func (x Uint16x32) InterleaveHiGrouped(y Uint16x32) Uint16x32

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX2
func (x Uint32x8) InterleaveHiGrouped(y Uint32x8) Uint32x8

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHDQ, CPU Feature: AVX512
func (x Uint32x16) InterleaveHiGrouped(y Uint32x16) Uint32x16

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX2
func (x Uint64x4) InterleaveHiGrouped(y Uint64x4) Uint64x4

// InterleaveHiGrouped interleaves the elements of the high half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKHQDQ, CPU Feature: AVX512
func (x Uint64x8) InterleaveHiGrouped(y Uint64x8) Uint64x8

/* InterleaveLo */

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX
func (x Int16x8) InterleaveLo(y Int16x8) Int16x8

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX
func (x Int32x4) InterleaveLo(y Int32x4) Int32x4

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX
func (x Int64x2) InterleaveLo(y Int64x2) Int64x2

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX
func (x Uint16x8) InterleaveLo(y Uint16x8) Uint16x8

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX
func (x Uint32x4) InterleaveLo(y Uint32x4) Uint32x4

// InterleaveLo interleaves the elements of the low halves of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX
func (x Uint64x2) InterleaveLo(y Uint64x2) Uint64x2

/* InterleaveLoGrouped */

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX2
func (x Int16x16) InterleaveLoGrouped(y Int16x16) Int16x16

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX512
func (x Int16x32) InterleaveLoGrouped(y Int16x32) Int16x32

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX2
func (x Int32x8) InterleaveLoGrouped(y Int32x8) Int32x8

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX512
func (x Int32x16) InterleaveLoGrouped(y Int32x16) Int32x16

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX2
func (x Int64x4) InterleaveLoGrouped(y Int64x4) Int64x4

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX512
func (x Int64x8) InterleaveLoGrouped(y Int64x8) Int64x8

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX2
func (x Uint16x16) InterleaveLoGrouped(y Uint16x16) Uint16x16

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLWD, CPU Feature: AVX512
func (x Uint16x32) InterleaveLoGrouped(y Uint16x32) Uint16x32

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX2
func (x Uint32x8) InterleaveLoGrouped(y Uint32x8) Uint32x8

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLDQ, CPU Feature: AVX512
func (x Uint32x16) InterleaveLoGrouped(y Uint32x16) Uint32x16

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX2
func (x Uint64x4) InterleaveLoGrouped(y Uint64x4) Uint64x4

// InterleaveLoGrouped interleaves the elements of the low half of each 128-bit subvector of x and y.
//
// Asm: VPUNPCKLQDQ, CPU Feature: AVX512
func (x Uint64x8) InterleaveLoGrouped(y Uint64x8) Uint64x8

/* IsNan */

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) IsNan(y Float32x4) Mask32x4

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) IsNan(y Float32x8) Mask32x8

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) IsNan(y Float32x16) Mask32x16

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) IsNan(y Float64x2) Mask64x2

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) IsNan(y Float64x4) Mask64x4

// IsNan checks if elements are NaN. Use as x.IsNan(x).
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) IsNan(y Float64x8) Mask64x8

/* LeadingZeros */

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Int32x4) LeadingZeros() Int32x4

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Int32x8) LeadingZeros() Int32x8

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Int32x16) LeadingZeros() Int32x16

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Int64x2) LeadingZeros() Int64x2

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Int64x4) LeadingZeros() Int64x4

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Int64x8) LeadingZeros() Int64x8

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Uint32x4) LeadingZeros() Uint32x4

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Uint32x8) LeadingZeros() Uint32x8

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTD, CPU Feature: AVX512
func (x Uint32x16) LeadingZeros() Uint32x16

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Uint64x2) LeadingZeros() Uint64x2

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Uint64x4) LeadingZeros() Uint64x4

// LeadingZeros counts the leading zeros of each element in x.
//
// Asm: VPLZCNTQ, CPU Feature: AVX512
func (x Uint64x8) LeadingZeros() Uint64x8

/* Less */

// Less compares for less than.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) Less(y Float32x4) Mask32x4

// Less compares for less than.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) Less(y Float32x8) Mask32x8

// Less compares for less than.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) Less(y Float32x16) Mask32x16

// Less compares for less than.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) Less(y Float64x2) Mask64x2

// Less compares for less than.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) Less(y Float64x4) Mask64x4

// Less compares for less than.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) Less(y Float64x8) Mask64x8

// Less compares for less than.
//
// Asm: VPCMPB, CPU Feature: AVX512
func (x Int8x64) Less(y Int8x64) Mask8x64

// Less compares for less than.
//
// Asm: VPCMPW, CPU Feature: AVX512
func (x Int16x32) Less(y Int16x32) Mask16x32

// Less compares for less than.
//
// Asm: VPCMPD, CPU Feature: AVX512
func (x Int32x16) Less(y Int32x16) Mask32x16

// Less compares for less than.
//
// Asm: VPCMPQ, CPU Feature: AVX512
func (x Int64x8) Less(y Int64x8) Mask64x8

// Less compares for less than.
//
// Asm: VPCMPUB, CPU Feature: AVX512
func (x Uint8x64) Less(y Uint8x64) Mask8x64

// Less compares for less than.
//
// Asm: VPCMPUW, CPU Feature: AVX512
func (x Uint16x32) Less(y Uint16x32) Mask16x32

// Less compares for less than.
//
// Asm: VPCMPUD, CPU Feature: AVX512
func (x Uint32x16) Less(y Uint32x16) Mask32x16

// Less compares for less than.
//
// Asm: VPCMPUQ, CPU Feature: AVX512
func (x Uint64x8) Less(y Uint64x8) Mask64x8

/* LessEqual */

// LessEqual compares for less than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) LessEqual(y Float32x4) Mask32x4

// LessEqual compares for less than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) LessEqual(y Float32x8) Mask32x8

// LessEqual compares for less than or equal.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) LessEqual(y Float32x16) Mask32x16

// LessEqual compares for less than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) LessEqual(y Float64x2) Mask64x2

// LessEqual compares for less than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) LessEqual(y Float64x4) Mask64x4

// LessEqual compares for less than or equal.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) LessEqual(y Float64x8) Mask64x8

// LessEqual compares for less than or equal.
//
// Asm: VPCMPB, CPU Feature: AVX512
func (x Int8x64) LessEqual(y Int8x64) Mask8x64

// LessEqual compares for less than or equal.
//
// Asm: VPCMPW, CPU Feature: AVX512
func (x Int16x32) LessEqual(y Int16x32) Mask16x32

// LessEqual compares for less than or equal.
//
// Asm: VPCMPD, CPU Feature: AVX512
func (x Int32x16) LessEqual(y Int32x16) Mask32x16

// LessEqual compares for less than or equal.
//
// Asm: VPCMPQ, CPU Feature: AVX512
func (x Int64x8) LessEqual(y Int64x8) Mask64x8

// LessEqual compares for less than or equal.
//
// Asm: VPCMPUB, CPU Feature: AVX512
func (x Uint8x64) LessEqual(y Uint8x64) Mask8x64

// LessEqual compares for less than or equal.
//
// Asm: VPCMPUW, CPU Feature: AVX512
func (x Uint16x32) LessEqual(y Uint16x32) Mask16x32

// LessEqual compares for less than or equal.
//
// Asm: VPCMPUD, CPU Feature: AVX512
func (x Uint32x16) LessEqual(y Uint32x16) Mask32x16

// LessEqual compares for less than or equal.
//
// Asm: VPCMPUQ, CPU Feature: AVX512
func (x Uint64x8) LessEqual(y Uint64x8) Mask64x8

/* Max */

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPS, CPU Feature: AVX
func (x Float32x4) Max(y Float32x4) Float32x4

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPS, CPU Feature: AVX
func (x Float32x8) Max(y Float32x8) Float32x8

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPS, CPU Feature: AVX512
func (x Float32x16) Max(y Float32x16) Float32x16

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPD, CPU Feature: AVX
func (x Float64x2) Max(y Float64x2) Float64x2

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPD, CPU Feature: AVX
func (x Float64x4) Max(y Float64x4) Float64x4

// Max computes the maximum of corresponding elements.
//
// Asm: VMAXPD, CPU Feature: AVX512
func (x Float64x8) Max(y Float64x8) Float64x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSB, CPU Feature: AVX
func (x Int8x16) Max(y Int8x16) Int8x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSB, CPU Feature: AVX2
func (x Int8x32) Max(y Int8x32) Int8x32

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSB, CPU Feature: AVX512
func (x Int8x64) Max(y Int8x64) Int8x64

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSW, CPU Feature: AVX
func (x Int16x8) Max(y Int16x8) Int16x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSW, CPU Feature: AVX2
func (x Int16x16) Max(y Int16x16) Int16x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSW, CPU Feature: AVX512
func (x Int16x32) Max(y Int16x32) Int16x32

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSD, CPU Feature: AVX
func (x Int32x4) Max(y Int32x4) Int32x4

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSD, CPU Feature: AVX2
func (x Int32x8) Max(y Int32x8) Int32x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSD, CPU Feature: AVX512
func (x Int32x16) Max(y Int32x16) Int32x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSQ, CPU Feature: AVX512
func (x Int64x2) Max(y Int64x2) Int64x2

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSQ, CPU Feature: AVX512
func (x Int64x4) Max(y Int64x4) Int64x4

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXSQ, CPU Feature: AVX512
func (x Int64x8) Max(y Int64x8) Int64x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUB, CPU Feature: AVX
func (x Uint8x16) Max(y Uint8x16) Uint8x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUB, CPU Feature: AVX2
func (x Uint8x32) Max(y Uint8x32) Uint8x32

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUB, CPU Feature: AVX512
func (x Uint8x64) Max(y Uint8x64) Uint8x64

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUW, CPU Feature: AVX
func (x Uint16x8) Max(y Uint16x8) Uint16x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUW, CPU Feature: AVX2
func (x Uint16x16) Max(y Uint16x16) Uint16x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUW, CPU Feature: AVX512
func (x Uint16x32) Max(y Uint16x32) Uint16x32

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUD, CPU Feature: AVX
func (x Uint32x4) Max(y Uint32x4) Uint32x4

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUD, CPU Feature: AVX2
func (x Uint32x8) Max(y Uint32x8) Uint32x8

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUD, CPU Feature: AVX512
func (x Uint32x16) Max(y Uint32x16) Uint32x16

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUQ, CPU Feature: AVX512
func (x Uint64x2) Max(y Uint64x2) Uint64x2

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUQ, CPU Feature: AVX512
func (x Uint64x4) Max(y Uint64x4) Uint64x4

// Max computes the maximum of corresponding elements.
//
// Asm: VPMAXUQ, CPU Feature: AVX512
func (x Uint64x8) Max(y Uint64x8) Uint64x8

/* Min */

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPS, CPU Feature: AVX
func (x Float32x4) Min(y Float32x4) Float32x4

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPS, CPU Feature: AVX
func (x Float32x8) Min(y Float32x8) Float32x8

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPS, CPU Feature: AVX512
func (x Float32x16) Min(y Float32x16) Float32x16

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPD, CPU Feature: AVX
func (x Float64x2) Min(y Float64x2) Float64x2

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPD, CPU Feature: AVX
func (x Float64x4) Min(y Float64x4) Float64x4

// Min computes the minimum of corresponding elements.
//
// Asm: VMINPD, CPU Feature: AVX512
func (x Float64x8) Min(y Float64x8) Float64x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSB, CPU Feature: AVX
func (x Int8x16) Min(y Int8x16) Int8x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSB, CPU Feature: AVX2
func (x Int8x32) Min(y Int8x32) Int8x32

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSB, CPU Feature: AVX512
func (x Int8x64) Min(y Int8x64) Int8x64

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSW, CPU Feature: AVX
func (x Int16x8) Min(y Int16x8) Int16x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSW, CPU Feature: AVX2
func (x Int16x16) Min(y Int16x16) Int16x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSW, CPU Feature: AVX512
func (x Int16x32) Min(y Int16x32) Int16x32

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSD, CPU Feature: AVX
func (x Int32x4) Min(y Int32x4) Int32x4

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSD, CPU Feature: AVX2
func (x Int32x8) Min(y Int32x8) Int32x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSD, CPU Feature: AVX512
func (x Int32x16) Min(y Int32x16) Int32x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSQ, CPU Feature: AVX512
func (x Int64x2) Min(y Int64x2) Int64x2

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSQ, CPU Feature: AVX512
func (x Int64x4) Min(y Int64x4) Int64x4

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINSQ, CPU Feature: AVX512
func (x Int64x8) Min(y Int64x8) Int64x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUB, CPU Feature: AVX
func (x Uint8x16) Min(y Uint8x16) Uint8x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUB, CPU Feature: AVX2
func (x Uint8x32) Min(y Uint8x32) Uint8x32

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUB, CPU Feature: AVX512
func (x Uint8x64) Min(y Uint8x64) Uint8x64

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUW, CPU Feature: AVX
func (x Uint16x8) Min(y Uint16x8) Uint16x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUW, CPU Feature: AVX2
func (x Uint16x16) Min(y Uint16x16) Uint16x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUW, CPU Feature: AVX512
func (x Uint16x32) Min(y Uint16x32) Uint16x32

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUD, CPU Feature: AVX
func (x Uint32x4) Min(y Uint32x4) Uint32x4

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUD, CPU Feature: AVX2
func (x Uint32x8) Min(y Uint32x8) Uint32x8

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUD, CPU Feature: AVX512
func (x Uint32x16) Min(y Uint32x16) Uint32x16

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUQ, CPU Feature: AVX512
func (x Uint64x2) Min(y Uint64x2) Uint64x2

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUQ, CPU Feature: AVX512
func (x Uint64x4) Min(y Uint64x4) Uint64x4

// Min computes the minimum of corresponding elements.
//
// Asm: VPMINUQ, CPU Feature: AVX512
func (x Uint64x8) Min(y Uint64x8) Uint64x8

/* Mul */

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPS, CPU Feature: AVX
func (x Float32x4) Mul(y Float32x4) Float32x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPS, CPU Feature: AVX
func (x Float32x8) Mul(y Float32x8) Float32x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPS, CPU Feature: AVX512
func (x Float32x16) Mul(y Float32x16) Float32x16

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPD, CPU Feature: AVX
func (x Float64x2) Mul(y Float64x2) Float64x2

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPD, CPU Feature: AVX
func (x Float64x4) Mul(y Float64x4) Float64x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VMULPD, CPU Feature: AVX512
func (x Float64x8) Mul(y Float64x8) Float64x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX
func (x Int16x8) Mul(y Int16x8) Int16x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX2
func (x Int16x16) Mul(y Int16x16) Int16x16

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX512
func (x Int16x32) Mul(y Int16x32) Int16x32

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX
func (x Int32x4) Mul(y Int32x4) Int32x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX2
func (x Int32x8) Mul(y Int32x8) Int32x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX512
func (x Int32x16) Mul(y Int32x16) Int32x16

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Int64x2) Mul(y Int64x2) Int64x2

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Int64x4) Mul(y Int64x4) Int64x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Int64x8) Mul(y Int64x8) Int64x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX
func (x Uint16x8) Mul(y Uint16x8) Uint16x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX2
func (x Uint16x16) Mul(y Uint16x16) Uint16x16

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLW, CPU Feature: AVX512
func (x Uint16x32) Mul(y Uint16x32) Uint16x32

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX
func (x Uint32x4) Mul(y Uint32x4) Uint32x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX2
func (x Uint32x8) Mul(y Uint32x8) Uint32x8

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLD, CPU Feature: AVX512
func (x Uint32x16) Mul(y Uint32x16) Uint32x16

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Uint64x2) Mul(y Uint64x2) Uint64x2

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Uint64x4) Mul(y Uint64x4) Uint64x4

// Mul multiplies corresponding elements of two vectors.
//
// Asm: VPMULLQ, CPU Feature: AVX512
func (x Uint64x8) Mul(y Uint64x8) Uint64x8

/* MulAdd */

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PS, CPU Feature: AVX512
func (x Float32x4) MulAdd(y Float32x4, z Float32x4) Float32x4

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PS, CPU Feature: AVX512
func (x Float32x8) MulAdd(y Float32x8, z Float32x8) Float32x8

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PS, CPU Feature: AVX512
func (x Float32x16) MulAdd(y Float32x16, z Float32x16) Float32x16

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PD, CPU Feature: AVX512
func (x Float64x2) MulAdd(y Float64x2, z Float64x2) Float64x2

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PD, CPU Feature: AVX512
func (x Float64x4) MulAdd(y Float64x4, z Float64x4) Float64x4

// MulAdd performs a fused (x * y) + z.
//
// Asm: VFMADD213PD, CPU Feature: AVX512
func (x Float64x8) MulAdd(y Float64x8, z Float64x8) Float64x8

/* MulAddSub */

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PS, CPU Feature: AVX512
func (x Float32x4) MulAddSub(y Float32x4, z Float32x4) Float32x4

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PS, CPU Feature: AVX512
func (x Float32x8) MulAddSub(y Float32x8, z Float32x8) Float32x8

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PS, CPU Feature: AVX512
func (x Float32x16) MulAddSub(y Float32x16, z Float32x16) Float32x16

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PD, CPU Feature: AVX512
func (x Float64x2) MulAddSub(y Float64x2, z Float64x2) Float64x2

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PD, CPU Feature: AVX512
func (x Float64x4) MulAddSub(y Float64x4, z Float64x4) Float64x4

// MulAddSub performs a fused (x * y) - z for odd-indexed elements, and (x * y) + z for even-indexed elements.
//
// Asm: VFMADDSUB213PD, CPU Feature: AVX512
func (x Float64x8) MulAddSub(y Float64x8, z Float64x8) Float64x8

/* MulEvenWiden */

// MulEvenWiden multiplies even-indexed elements, widening the result.
// Result[i] = v1.Even[i] * v2.Even[i].
//
// Asm: VPMULDQ, CPU Feature: AVX
func (x Int32x4) MulEvenWiden(y Int32x4) Int64x2

// MulEvenWiden multiplies even-indexed elements, widening the result.
// Result[i] = v1.Even[i] * v2.Even[i].
//
// Asm: VPMULDQ, CPU Feature: AVX2
func (x Int32x8) MulEvenWiden(y Int32x8) Int64x4

// MulEvenWiden multiplies even-indexed elements, widening the result.
// Result[i] = v1.Even[i] * v2.Even[i].
//
// Asm: VPMULUDQ, CPU Feature: AVX
func (x Uint32x4) MulEvenWiden(y Uint32x4) Uint64x2

// MulEvenWiden multiplies even-indexed elements, widening the result.
// Result[i] = v1.Even[i] * v2.Even[i].
//
// Asm: VPMULUDQ, CPU Feature: AVX2
func (x Uint32x8) MulEvenWiden(y Uint32x8) Uint64x4

/* MulHigh */

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHW, CPU Feature: AVX
func (x Int16x8) MulHigh(y Int16x8) Int16x8

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHW, CPU Feature: AVX2
func (x Int16x16) MulHigh(y Int16x16) Int16x16

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHW, CPU Feature: AVX512
func (x Int16x32) MulHigh(y Int16x32) Int16x32

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHUW, CPU Feature: AVX
func (x Uint16x8) MulHigh(y Uint16x8) Uint16x8

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHUW, CPU Feature: AVX2
func (x Uint16x16) MulHigh(y Uint16x16) Uint16x16

// MulHigh multiplies elements and stores the high part of the result.
//
// Asm: VPMULHUW, CPU Feature: AVX512
func (x Uint16x32) MulHigh(y Uint16x32) Uint16x32

/* MulSubAdd */

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PS, CPU Feature: AVX512
func (x Float32x4) MulSubAdd(y Float32x4, z Float32x4) Float32x4

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PS, CPU Feature: AVX512
func (x Float32x8) MulSubAdd(y Float32x8, z Float32x8) Float32x8

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PS, CPU Feature: AVX512
func (x Float32x16) MulSubAdd(y Float32x16, z Float32x16) Float32x16

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PD, CPU Feature: AVX512
func (x Float64x2) MulSubAdd(y Float64x2, z Float64x2) Float64x2

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PD, CPU Feature: AVX512
func (x Float64x4) MulSubAdd(y Float64x4, z Float64x4) Float64x4

// MulSubAdd performs a fused (x * y) + z for odd-indexed elements, and (x * y) - z for even-indexed elements.
//
// Asm: VFMSUBADD213PD, CPU Feature: AVX512
func (x Float64x8) MulSubAdd(y Float64x8, z Float64x8) Float64x8

/* NotEqual */

// NotEqual compares for inequality.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x4) NotEqual(y Float32x4) Mask32x4

// NotEqual compares for inequality.
//
// Asm: VCMPPS, CPU Feature: AVX
func (x Float32x8) NotEqual(y Float32x8) Mask32x8

// NotEqual compares for inequality.
//
// Asm: VCMPPS, CPU Feature: AVX512
func (x Float32x16) NotEqual(y Float32x16) Mask32x16

// NotEqual compares for inequality.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x2) NotEqual(y Float64x2) Mask64x2

// NotEqual compares for inequality.
//
// Asm: VCMPPD, CPU Feature: AVX
func (x Float64x4) NotEqual(y Float64x4) Mask64x4

// NotEqual compares for inequality.
//
// Asm: VCMPPD, CPU Feature: AVX512
func (x Float64x8) NotEqual(y Float64x8) Mask64x8

// NotEqual compares for inequality.
//
// Asm: VPCMPB, CPU Feature: AVX512
func (x Int8x64) NotEqual(y Int8x64) Mask8x64

// NotEqual compares for inequality.
//
// Asm: VPCMPW, CPU Feature: AVX512
func (x Int16x32) NotEqual(y Int16x32) Mask16x32

// NotEqual compares for inequality.
//
// Asm: VPCMPD, CPU Feature: AVX512
func (x Int32x16) NotEqual(y Int32x16) Mask32x16

// NotEqual compares for inequality.
//
// Asm: VPCMPQ, CPU Feature: AVX512
func (x Int64x8) NotEqual(y Int64x8) Mask64x8

// NotEqual compares for inequality.
//
// Asm: VPCMPUB, CPU Feature: AVX512
func (x Uint8x64) NotEqual(y Uint8x64) Mask8x64

// NotEqual compares for inequality.
//
// Asm: VPCMPUW, CPU Feature: AVX512
func (x Uint16x32) NotEqual(y Uint16x32) Mask16x32

// NotEqual compares for inequality.
//
// Asm: VPCMPUD, CPU Feature: AVX512
func (x Uint32x16) NotEqual(y Uint32x16) Mask32x16

// NotEqual compares for inequality.
//
// Asm: VPCMPUQ, CPU Feature: AVX512
func (x Uint64x8) NotEqual(y Uint64x8) Mask64x8

/* OnesCount */

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Int8x16) OnesCount() Int8x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Int8x32) OnesCount() Int8x32

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Int8x64) OnesCount() Int8x64

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Int16x8) OnesCount() Int16x8

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Int16x16) OnesCount() Int16x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Int16x32) OnesCount() Int16x32

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Int32x4) OnesCount() Int32x4

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Int32x8) OnesCount() Int32x8

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Int32x16) OnesCount() Int32x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Int64x2) OnesCount() Int64x2

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Int64x4) OnesCount() Int64x4

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Int64x8) OnesCount() Int64x8

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Uint8x16) OnesCount() Uint8x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Uint8x32) OnesCount() Uint8x32

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTB, CPU Feature: AVX512BITALG
func (x Uint8x64) OnesCount() Uint8x64

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Uint16x8) OnesCount() Uint16x8

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Uint16x16) OnesCount() Uint16x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTW, CPU Feature: AVX512BITALG
func (x Uint16x32) OnesCount() Uint16x32

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Uint32x4) OnesCount() Uint32x4

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Uint32x8) OnesCount() Uint32x8

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTD, CPU Feature: AVX512VPOPCNTDQ
func (x Uint32x16) OnesCount() Uint32x16

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Uint64x2) OnesCount() Uint64x2

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Uint64x4) OnesCount() Uint64x4

// OnesCount counts the number of set bits in each element.
//
// Asm: VPOPCNTQ, CPU Feature: AVX512VPOPCNTDQ
func (x Uint64x8) OnesCount() Uint64x8

/* Or */

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Int8x16) Or(y Int8x16) Int8x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Int8x32) Or(y Int8x32) Int8x32

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Int8x64) Or(y Int8x64) Int8x64

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Int16x8) Or(y Int16x8) Int16x8

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Int16x16) Or(y Int16x16) Int16x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Int16x32) Or(y Int16x32) Int16x32

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Int32x4) Or(y Int32x4) Int32x4

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Int32x8) Or(y Int32x8) Int32x8

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Int32x16) Or(y Int32x16) Int32x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Int64x2) Or(y Int64x2) Int64x2

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Int64x4) Or(y Int64x4) Int64x4

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORQ, CPU Feature: AVX512
func (x Int64x8) Or(y Int64x8) Int64x8

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Uint8x16) Or(y Uint8x16) Uint8x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Uint8x32) Or(y Uint8x32) Uint8x32

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Uint8x64) Or(y Uint8x64) Uint8x64

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Uint16x8) Or(y Uint16x8) Uint16x8

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Uint16x16) Or(y Uint16x16) Uint16x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Uint16x32) Or(y Uint16x32) Uint16x32

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Uint32x4) Or(y Uint32x4) Uint32x4

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Uint32x8) Or(y Uint32x8) Uint32x8

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORD, CPU Feature: AVX512
func (x Uint32x16) Or(y Uint32x16) Uint32x16

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX
func (x Uint64x2) Or(y Uint64x2) Uint64x2

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPOR, CPU Feature: AVX2
func (x Uint64x4) Or(y Uint64x4) Uint64x4

// Or performs a bitwise OR operation between two vectors.
//
// Asm: VPORQ, CPU Feature: AVX512
func (x Uint64x8) Or(y Uint64x8) Uint64x8

/* Permute */

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Int8x16) Permute(indices Uint8x16) Int8x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Uint8x16) Permute(indices Uint8x16) Uint8x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 5 bits (values 0-31) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Int8x32) Permute(indices Uint8x32) Int8x32

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 5 bits (values 0-31) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Uint8x32) Permute(indices Uint8x32) Uint8x32

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 6 bits (values 0-63) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Int8x64) Permute(indices Uint8x64) Int8x64

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 6 bits (values 0-63) of each element of indices is used
//
// Asm: VPERMB, CPU Feature: AVX512VBMI
func (x Uint8x64) Permute(indices Uint8x64) Uint8x64

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Int16x8) Permute(indices Uint16x8) Int16x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Uint16x8) Permute(indices Uint16x8) Uint16x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Int16x16) Permute(indices Uint16x16) Int16x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Uint16x16) Permute(indices Uint16x16) Uint16x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 5 bits (values 0-31) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Int16x32) Permute(indices Uint16x32) Int16x32

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 5 bits (values 0-31) of each element of indices is used
//
// Asm: VPERMW, CPU Feature: AVX512
func (x Uint16x32) Permute(indices Uint16x32) Uint16x32

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMPS, CPU Feature: AVX2
func (x Float32x8) Permute(indices Uint32x8) Float32x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMD, CPU Feature: AVX2
func (x Int32x8) Permute(indices Uint32x8) Int32x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMD, CPU Feature: AVX2
func (x Uint32x8) Permute(indices Uint32x8) Uint32x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMPS, CPU Feature: AVX512
func (x Float32x16) Permute(indices Uint32x16) Float32x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMD, CPU Feature: AVX512
func (x Int32x16) Permute(indices Uint32x16) Int32x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 4 bits (values 0-15) of each element of indices is used
//
// Asm: VPERMD, CPU Feature: AVX512
func (x Uint32x16) Permute(indices Uint32x16) Uint32x16

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 2 bits (values 0-3) of each element of indices is used
//
// Asm: VPERMPD, CPU Feature: AVX512
func (x Float64x4) Permute(indices Uint64x4) Float64x4

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 2 bits (values 0-3) of each element of indices is used
//
// Asm: VPERMQ, CPU Feature: AVX512
func (x Int64x4) Permute(indices Uint64x4) Int64x4

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 2 bits (values 0-3) of each element of indices is used
//
// Asm: VPERMQ, CPU Feature: AVX512
func (x Uint64x4) Permute(indices Uint64x4) Uint64x4

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMPD, CPU Feature: AVX512
func (x Float64x8) Permute(indices Uint64x8) Float64x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMQ, CPU Feature: AVX512
func (x Int64x8) Permute(indices Uint64x8) Int64x8

// Permute performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The low 3 bits (values 0-7) of each element of indices is used
//
// Asm: VPERMQ, CPU Feature: AVX512
func (x Uint64x8) Permute(indices Uint64x8) Uint64x8

/* PermuteOrZero */

// PermuteOrZero performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The lower four bits of each byte-sized index in indices select an element from x,
// unless the index's sign bit is set in which case zero is used instead.
//
// Asm: VPSHUFB, CPU Feature: AVX
func (x Int8x16) PermuteOrZero(indices Int8x16) Int8x16

// PermuteOrZero performs a full permutation of vector x using indices:
// result := {x[indices[0]], x[indices[1]], ..., x[indices[n]]}
// The lower four bits of each byte-sized index in indices select an element from x,
// unless the index's sign bit is set in which case zero is used instead.
//
// Asm: VPSHUFB, CPU Feature: AVX
func (x Uint8x16) PermuteOrZero(indices Int8x16) Uint8x16

/* PermuteOrZeroGrouped */

// PermuteOrZeroGrouped performs a grouped permutation of vector x using indices:
// result = {x_group0[indices[0]], x_group0[indices[1]], ..., x_group1[indices[16]], x_group1[indices[17]], ...}
// The lower four bits of each byte-sized index in indices select an element from its corresponding group in x,
// unless the index's sign bit is set in which case zero is used instead.
// Each group is of size 128-bit.
//
// Asm: VPSHUFB, CPU Feature: AVX2
func (x Int8x32) PermuteOrZeroGrouped(indices Int8x32) Int8x32

// PermuteOrZeroGrouped performs a grouped permutation of vector x using indices:
// result = {x_group0[indices[0]], x_group0[indices[1]], ..., x_group1[indices[16]], x_group1[indices[17]], ...}
// The lower four bits of each byte-sized index in indices select an element from its corresponding group in x,
// unless the index's sign bit is set in which case zero is used instead.
// Each group is of size 128-bit.
//
// Asm: VPSHUFB, CPU Feature: AVX512
func (x Int8x64) PermuteOrZeroGrouped(indices Int8x64) Int8x64

// PermuteOrZeroGrouped performs a grouped permutation of vector x using indices:
// result = {x_group0[indices[0]], x_group0[indices[1]], ..., x_group1[indices[16]], x_group1[indices[17]], ...}
// The lower four bits of each byte-sized index in indices select an element from its corresponding group in x,
// unless the index's sign bit is set in which case zero is used instead.
// Each group is of size 128-bit.
//
// Asm: VPSHUFB, CPU Feature: AVX2
func (x Uint8x32) PermuteOrZeroGrouped(indices Int8x32) Uint8x32

// PermuteOrZeroGrouped performs a grouped permutation of vector x using indices:
// result = {x_group0[indices[0]], x_group0[indices[1]], ..., x_group1[indices[16]], x_group1[indices[17]], ...}
// The lower four bits of each byte-sized index in indices select an element from its corresponding group in x,
// unless the index's sign bit is set in which case zero is used instead.
// Each group is of size 128-bit.
//
// Asm: VPSHUFB, CPU Feature: AVX512
func (x Uint8x64) PermuteOrZeroGrouped(indices Int8x64) Uint8x64

/* Reciprocal */

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCPPS, CPU Feature: AVX
func (x Float32x4) Reciprocal() Float32x4

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCPPS, CPU Feature: AVX
func (x Float32x8) Reciprocal() Float32x8

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCP14PS, CPU Feature: AVX512
func (x Float32x16) Reciprocal() Float32x16

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCP14PD, CPU Feature: AVX512
func (x Float64x2) Reciprocal() Float64x2

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCP14PD, CPU Feature: AVX512
func (x Float64x4) Reciprocal() Float64x4

// Reciprocal computes an approximate reciprocal of each element.
//
// Asm: VRCP14PD, CPU Feature: AVX512
func (x Float64x8) Reciprocal() Float64x8

/* ReciprocalSqrt */

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRTPS, CPU Feature: AVX
func (x Float32x4) ReciprocalSqrt() Float32x4

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRTPS, CPU Feature: AVX
func (x Float32x8) ReciprocalSqrt() Float32x8

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRT14PS, CPU Feature: AVX512
func (x Float32x16) ReciprocalSqrt() Float32x16

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRT14PD, CPU Feature: AVX512
func (x Float64x2) ReciprocalSqrt() Float64x2

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRT14PD, CPU Feature: AVX512
func (x Float64x4) ReciprocalSqrt() Float64x4

// ReciprocalSqrt computes an approximate reciprocal of the square root of each element.
//
// Asm: VRSQRT14PD, CPU Feature: AVX512
func (x Float64x8) ReciprocalSqrt() Float64x8

/* RotateAllLeft */

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Int32x4) RotateAllLeft(shift uint8) Int32x4

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Int32x8) RotateAllLeft(shift uint8) Int32x8

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Int32x16) RotateAllLeft(shift uint8) Int32x16

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Int64x2) RotateAllLeft(shift uint8) Int64x2

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Int64x4) RotateAllLeft(shift uint8) Int64x4

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Int64x8) RotateAllLeft(shift uint8) Int64x8

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Uint32x4) RotateAllLeft(shift uint8) Uint32x4

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Uint32x8) RotateAllLeft(shift uint8) Uint32x8

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLD, CPU Feature: AVX512
func (x Uint32x16) RotateAllLeft(shift uint8) Uint32x16

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Uint64x2) RotateAllLeft(shift uint8) Uint64x2

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Uint64x4) RotateAllLeft(shift uint8) Uint64x4

// RotateAllLeft rotates each element to the left by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPROLQ, CPU Feature: AVX512
func (x Uint64x8) RotateAllLeft(shift uint8) Uint64x8

/* RotateAllRight */

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Int32x4) RotateAllRight(shift uint8) Int32x4

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Int32x8) RotateAllRight(shift uint8) Int32x8

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Int32x16) RotateAllRight(shift uint8) Int32x16

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Int64x2) RotateAllRight(shift uint8) Int64x2

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Int64x4) RotateAllRight(shift uint8) Int64x4

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Int64x8) RotateAllRight(shift uint8) Int64x8

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Uint32x4) RotateAllRight(shift uint8) Uint32x4

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Uint32x8) RotateAllRight(shift uint8) Uint32x8

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORD, CPU Feature: AVX512
func (x Uint32x16) RotateAllRight(shift uint8) Uint32x16

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Uint64x2) RotateAllRight(shift uint8) Uint64x2

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Uint64x4) RotateAllRight(shift uint8) Uint64x4

// RotateAllRight rotates each element to the right by the number of bits specified by the immediate.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPRORQ, CPU Feature: AVX512
func (x Uint64x8) RotateAllRight(shift uint8) Uint64x8

/* RotateLeft */

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Int32x4) RotateLeft(y Int32x4) Int32x4

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Int32x8) RotateLeft(y Int32x8) Int32x8

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Int32x16) RotateLeft(y Int32x16) Int32x16

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Int64x2) RotateLeft(y Int64x2) Int64x2

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Int64x4) RotateLeft(y Int64x4) Int64x4

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Int64x8) RotateLeft(y Int64x8) Int64x8

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Uint32x4) RotateLeft(y Uint32x4) Uint32x4

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Uint32x8) RotateLeft(y Uint32x8) Uint32x8

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVD, CPU Feature: AVX512
func (x Uint32x16) RotateLeft(y Uint32x16) Uint32x16

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Uint64x2) RotateLeft(y Uint64x2) Uint64x2

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Uint64x4) RotateLeft(y Uint64x4) Uint64x4

// RotateLeft rotates each element in x to the left by the number of bits specified by y's corresponding elements.
//
// Asm: VPROLVQ, CPU Feature: AVX512
func (x Uint64x8) RotateLeft(y Uint64x8) Uint64x8

/* RotateRight */

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Int32x4) RotateRight(y Int32x4) Int32x4

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Int32x8) RotateRight(y Int32x8) Int32x8

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Int32x16) RotateRight(y Int32x16) Int32x16

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Int64x2) RotateRight(y Int64x2) Int64x2

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Int64x4) RotateRight(y Int64x4) Int64x4

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Int64x8) RotateRight(y Int64x8) Int64x8

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Uint32x4) RotateRight(y Uint32x4) Uint32x4

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Uint32x8) RotateRight(y Uint32x8) Uint32x8

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVD, CPU Feature: AVX512
func (x Uint32x16) RotateRight(y Uint32x16) Uint32x16

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Uint64x2) RotateRight(y Uint64x2) Uint64x2

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Uint64x4) RotateRight(y Uint64x4) Uint64x4

// RotateRight rotates each element in x to the right by the number of bits specified by y's corresponding elements.
//
// Asm: VPRORVQ, CPU Feature: AVX512
func (x Uint64x8) RotateRight(y Uint64x8) Uint64x8

/* RoundToEven */

// RoundToEven rounds elements to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x4) RoundToEven() Float32x4

// RoundToEven rounds elements to the nearest integer.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x8) RoundToEven() Float32x8

// RoundToEven rounds elements to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x2) RoundToEven() Float64x2

// RoundToEven rounds elements to the nearest integer.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x4) RoundToEven() Float64x4

/* RoundToEvenScaled */

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x4) RoundToEvenScaled(prec uint8) Float32x4

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x8) RoundToEvenScaled(prec uint8) Float32x8

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x16) RoundToEvenScaled(prec uint8) Float32x16

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x2) RoundToEvenScaled(prec uint8) Float64x2

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x4) RoundToEvenScaled(prec uint8) Float64x4

// RoundToEvenScaled rounds elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x8) RoundToEvenScaled(prec uint8) Float64x8

/* RoundToEvenScaledResidue */

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x4) RoundToEvenScaledResidue(prec uint8) Float32x4

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x8) RoundToEvenScaledResidue(prec uint8) Float32x8

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x16) RoundToEvenScaledResidue(prec uint8) Float32x16

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x2) RoundToEvenScaledResidue(prec uint8) Float64x2

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x4) RoundToEvenScaledResidue(prec uint8) Float64x4

// RoundToEvenScaledResidue computes the difference after rounding with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x8) RoundToEvenScaledResidue(prec uint8) Float64x8

/* SHA1FourRounds */

// SHA1FourRounds performs 4 rounds of B loop in SHA1 algorithm defined in FIPS 180-4.
// x contains the state variables a, b, c and d from upper to lower order.
// y contains the W array elements (with the state variable e added to the upper element) from upper to lower order.
// result = the state variables a', b', c', d' updated after 4 rounds.
// constant = 0 for the first 20 rounds of the loop, 1 for the next 20 rounds of the loop..., 3 for the last 20 rounds of the loop.
//
// constant results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: SHA1RNDS4, CPU Feature: SHA
func (x Uint32x4) SHA1FourRounds(constant uint8, y Uint32x4) Uint32x4

/* SHA1Message1 */

// SHA1Message1 does the XORing of 1 in SHA1 algorithm defined in FIPS 180-4.
// x = {W3, W2, W1, W0}
// y = {0, 0, W5, W4}
// result = {W3^W5, W2^W4, W1^W3, W0^W2}.
//
// Asm: SHA1MSG1, CPU Feature: SHA
func (x Uint32x4) SHA1Message1(y Uint32x4) Uint32x4

/* SHA1Message2 */

// SHA1Message2 does the calculation of 3 and 4 in SHA1 algorithm defined in FIPS 180-4.
// x = result of 2.
// y = {W15, W14, W13}
// result = {W19, W18, W17, W16}
//
// Asm: SHA1MSG2, CPU Feature: SHA
func (x Uint32x4) SHA1Message2(y Uint32x4) Uint32x4

/* SHA1NextE */

// SHA1NextE calculates the state variable e' updated after 4 rounds in SHA1 algorithm defined in FIPS 180-4.
// x contains the state variable a (before the 4 rounds), placed in the upper element.
// y is the elements of W array for next 4 rounds from upper to lower order.
// result = the elements of the W array for the next 4 rounds, with the updated state variable e' added to the upper element,
// from upper to lower order.
// For the last round of the loop, you can specify zero for y to obtain the e' value itself, or better off specifying H4:0:0:0
// for y to get e' added to H4. (Note that the value of e' is computed only from x, and values of y don't affect the
// computation of the value of e'.)
//
// Asm: SHA1NEXTE, CPU Feature: SHA
func (x Uint32x4) SHA1NextE(y Uint32x4) Uint32x4

/* SHA256Message1 */

// SHA256Message1 does the sigma and addtion of 1 in SHA1 algorithm defined in FIPS 180-4.
// x = {W0, W1, W2, W3}
// y = {W4, 0, 0, 0}
// result = {W0+σ(W1), W1+σ(W2), W2+σ(W3), W3+σ(W4)}
//
// Asm: SHA256MSG1, CPU Feature: SHA
func (x Uint32x4) SHA256Message1(y Uint32x4) Uint32x4

/* SHA256Message2 */

// SHA256Message2 does the sigma and addition of 3 in SHA1 algorithm defined in FIPS 180-4.
// x = result of 2
// y = {0, 0, W14, W15}
// result = {W16, W17, W18, W19}
//
// Asm: SHA256MSG2, CPU Feature: SHA
func (x Uint32x4) SHA256Message2(y Uint32x4) Uint32x4

/* SHA256TwoRounds */

// SHA256TwoRounds does 2 rounds of B loop to calculate updated state variables in SHA1 algorithm defined in FIPS 180-4.
// x = {h, g, d, c}
// y = {f, e, b, a}
// z = {W0+K0, W1+K1}
// result = {f', e', b', a'}
// The K array is a 64-DWORD constant array defined in page 11 of FIPS 180-4. Each element of the K array is to be added to
// the corresponding element of the W array to make the input data z.
// The updated state variables c', d', g', h' are not returned by this instruction, because they are equal to the input data
// y (the state variables a, b, e, f before the 2 rounds).
//
// Asm: SHA256RNDS2, CPU Feature: SHA
func (x Uint32x4) SHA256TwoRounds(y Uint32x4, z Uint32x4) Uint32x4

/* SaturateToInt8 */

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSWB, CPU Feature: AVX512
func (x Int16x8) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSWB, CPU Feature: AVX512
func (x Int16x16) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSWB, CPU Feature: AVX512
func (x Int16x32) SaturateToInt8() Int8x32

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x4) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x8) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x16) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x2) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x4) SaturateToInt8() Int8x16

// SaturateToInt8 converts element values to int8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x8) SaturateToInt8() Int8x16

/* SaturateToInt16 */

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSDW, CPU Feature: AVX512
func (x Int32x4) SaturateToInt16() Int16x8

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSDW, CPU Feature: AVX512
func (x Int32x8) SaturateToInt16() Int16x8

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSDW, CPU Feature: AVX512
func (x Int32x16) SaturateToInt16() Int16x16

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQW, CPU Feature: AVX512
func (x Int64x2) SaturateToInt16() Int16x8

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQW, CPU Feature: AVX512
func (x Int64x4) SaturateToInt16() Int16x8

// SaturateToInt16 converts element values to int16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQW, CPU Feature: AVX512
func (x Int64x8) SaturateToInt16() Int16x8

/* SaturateToInt16Concat */

// SaturateToInt16Concat converts element values to int16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKSSDW, CPU Feature: AVX
func (x Int32x4) SaturateToInt16Concat(y Int32x4) Int16x8

// SaturateToInt16Concat converts element values to int16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKSSDW, CPU Feature: AVX2
func (x Int32x8) SaturateToInt16Concat(y Int32x8) Int16x16

// SaturateToInt16Concat converts element values to int16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKSSDW, CPU Feature: AVX512
func (x Int32x16) SaturateToInt16Concat(y Int32x16) Int16x32

/* SaturateToInt32 */

// SaturateToInt32 converts element values to int32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQD, CPU Feature: AVX512
func (x Int64x2) SaturateToInt32() Int32x4

// SaturateToInt32 converts element values to int32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQD, CPU Feature: AVX512
func (x Int64x4) SaturateToInt32() Int32x4

// SaturateToInt32 converts element values to int32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVSQD, CPU Feature: AVX512
func (x Int64x8) SaturateToInt32() Int32x8

/* SaturateToUint8 */

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSWB, CPU Feature: AVX512
func (x Int16x8) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSWB, CPU Feature: AVX512
func (x Int16x16) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x4) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x8) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSDB, CPU Feature: AVX512
func (x Int32x16) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x2) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x4) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVSQB, CPU Feature: AVX512
func (x Int64x8) SaturateToUint8() Int8x16

// SaturateToUint8 converts element values to uint8.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSWB, CPU Feature: AVX512
func (x Uint16x32) SaturateToUint8() Uint8x32

/* SaturateToUint16 */

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSDW, CPU Feature: AVX512
func (x Uint32x4) SaturateToUint16() Uint16x8

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSDW, CPU Feature: AVX512
func (x Uint32x8) SaturateToUint16() Uint16x8

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSDW, CPU Feature: AVX512
func (x Uint32x16) SaturateToUint16() Uint16x16

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQW, CPU Feature: AVX512
func (x Uint64x2) SaturateToUint16() Uint16x8

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQW, CPU Feature: AVX512
func (x Uint64x4) SaturateToUint16() Uint16x8

// SaturateToUint16 converts element values to uint16.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQW, CPU Feature: AVX512
func (x Uint64x8) SaturateToUint16() Uint16x8

/* SaturateToUint16Concat */

// SaturateToUint16Concat converts element values to uint16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKUSDW, CPU Feature: AVX
func (x Uint32x4) SaturateToUint16Concat(y Uint32x4) Uint16x8

// SaturateToUint16Concat converts element values to uint16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKUSDW, CPU Feature: AVX2
func (x Uint32x8) SaturateToUint16Concat(y Uint32x8) Uint16x16

// SaturateToUint16Concat converts element values to uint16.
// With each 128-bit as a group:
// The converted group from the first input vector will be packed to the lower part of the result vector,
// the converted group from the second input vector will be packed to the upper part of the result vector.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPACKUSDW, CPU Feature: AVX512
func (x Uint32x16) SaturateToUint16Concat(y Uint32x16) Uint16x32

/* SaturateToUint32 */

// SaturateToUint32 converts element values to uint32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQD, CPU Feature: AVX512
func (x Uint64x2) SaturateToUint32() Uint32x4

// SaturateToUint32 converts element values to uint32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQD, CPU Feature: AVX512
func (x Uint64x4) SaturateToUint32() Uint32x4

// SaturateToUint32 converts element values to uint32.
// Conversion is done with saturation on the vector elements.
//
// Asm: VPMOVUSQD, CPU Feature: AVX512
func (x Uint64x8) SaturateToUint32() Uint32x8

/* Scale */

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPS, CPU Feature: AVX512
func (x Float32x4) Scale(y Float32x4) Float32x4

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPS, CPU Feature: AVX512
func (x Float32x8) Scale(y Float32x8) Float32x8

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPS, CPU Feature: AVX512
func (x Float32x16) Scale(y Float32x16) Float32x16

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPD, CPU Feature: AVX512
func (x Float64x2) Scale(y Float64x2) Float64x2

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPD, CPU Feature: AVX512
func (x Float64x4) Scale(y Float64x4) Float64x4

// Scale multiplies elements by a power of 2.
//
// Asm: VSCALEFPD, CPU Feature: AVX512
func (x Float64x8) Scale(y Float64x8) Float64x8

/* Select128FromPair */

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 42, 43, 50, 51, 52, 53}.Select128FromPair(3, 0, {60, 61, 62, 63, 70, 71, 72, 73})
//
// returns {70, 71, 72, 73, 40, 41, 42, 43}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2F128, CPU Feature: AVX
func (x Float32x8) Select128FromPair(lo, hi uint8, y Float32x8) Float32x8

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 50, 51}.Select128FromPair(3, 0, {60, 61, 70, 71})
//
// returns {70, 71, 40, 41}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2F128, CPU Feature: AVX
func (x Float64x4) Select128FromPair(lo, hi uint8, y Float64x4) Float64x4

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{0x40, 0x41, ..., 0x4f, 0x50, 0x51, ..., 0x5f}.Select128FromPair(3, 0,
//	     {0x60, 0x61, ..., 0x6f, 0x70, 0x71, ..., 0x7f})
//
// returns {0x70, 0x71, ..., 0x7f, 0x40, 0x41, ..., 0x4f}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Int8x32) Select128FromPair(lo, hi uint8, y Int8x32) Int8x32

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 42, 43, 44, 45, 46, 47, 50, 51, 52, 53, 54, 55, 56, 57}.Select128FromPair(3, 0,
//	 {60, 61, 62, 63, 64, 65, 66, 67, 70, 71, 72, 73, 74, 75, 76, 77})
//
// returns {70, 71, 72, 73, 74, 75, 76, 77, 40, 41, 42, 43, 44, 45, 46, 47}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Int16x16) Select128FromPair(lo, hi uint8, y Int16x16) Int16x16

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 42, 43, 50, 51, 52, 53}.Select128FromPair(3, 0, {60, 61, 62, 63, 70, 71, 72, 73})
//
// returns {70, 71, 72, 73, 40, 41, 42, 43}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Int32x8) Select128FromPair(lo, hi uint8, y Int32x8) Int32x8

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 50, 51}.Select128FromPair(3, 0, {60, 61, 70, 71})
//
// returns {70, 71, 40, 41}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Int64x4) Select128FromPair(lo, hi uint8, y Int64x4) Int64x4

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{0x40, 0x41, ..., 0x4f, 0x50, 0x51, ..., 0x5f}.Select128FromPair(3, 0,
//	     {0x60, 0x61, ..., 0x6f, 0x70, 0x71, ..., 0x7f})
//
// returns {0x70, 0x71, ..., 0x7f, 0x40, 0x41, ..., 0x4f}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Uint8x32) Select128FromPair(lo, hi uint8, y Uint8x32) Uint8x32

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 42, 43, 44, 45, 46, 47, 50, 51, 52, 53, 54, 55, 56, 57}.Select128FromPair(3, 0,
//	 {60, 61, 62, 63, 64, 65, 66, 67, 70, 71, 72, 73, 74, 75, 76, 77})
//
// returns {70, 71, 72, 73, 74, 75, 76, 77, 40, 41, 42, 43, 44, 45, 46, 47}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Uint16x16) Select128FromPair(lo, hi uint8, y Uint16x16) Uint16x16

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 42, 43, 50, 51, 52, 53}.Select128FromPair(3, 0, {60, 61, 62, 63, 70, 71, 72, 73})
//
// returns {70, 71, 72, 73, 40, 41, 42, 43}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Uint32x8) Select128FromPair(lo, hi uint8, y Uint32x8) Uint32x8

// Select128FromPair treats the 256-bit vectors x and y as a single vector of four
// 128-bit elements, and returns a 256-bit result formed by
// concatenating the two elements specified by lo and hi.
// For example,
//
//	{40, 41, 50, 51}.Select128FromPair(3, 0, {60, 61, 70, 71})
//
// returns {70, 71, 40, 41}.
//
// lo, hi result in better performance when they are constants, non-constant values will be translated into a jump table.
// lo, hi should be between 0 and 3, inclusive; other values may result in a runtime panic.
//
// Asm: VPERM2I128, CPU Feature: AVX2
func (x Uint64x4) Select128FromPair(lo, hi uint8, y Uint64x4) Uint64x4

/* SetElem */

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRD, CPU Feature: AVX
func (x Float32x4) SetElem(index uint8, y float32) Float32x4

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRQ, CPU Feature: AVX
func (x Float64x2) SetElem(index uint8, y float64) Float64x2

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRB, CPU Feature: AVX
func (x Int8x16) SetElem(index uint8, y int8) Int8x16

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRW, CPU Feature: AVX
func (x Int16x8) SetElem(index uint8, y int16) Int16x8

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRD, CPU Feature: AVX
func (x Int32x4) SetElem(index uint8, y int32) Int32x4

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRQ, CPU Feature: AVX
func (x Int64x2) SetElem(index uint8, y int64) Int64x2

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRB, CPU Feature: AVX
func (x Uint8x16) SetElem(index uint8, y uint8) Uint8x16

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRW, CPU Feature: AVX
func (x Uint16x8) SetElem(index uint8, y uint16) Uint16x8

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRD, CPU Feature: AVX
func (x Uint32x4) SetElem(index uint8, y uint32) Uint32x4

// SetElem sets a single constant-indexed element's value.
//
// index results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPINSRQ, CPU Feature: AVX
func (x Uint64x2) SetElem(index uint8, y uint64) Uint64x2

/* SetHi */

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTF128, CPU Feature: AVX
func (x Float32x8) SetHi(y Float32x4) Float32x8

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTF64X4, CPU Feature: AVX512
func (x Float32x16) SetHi(y Float32x8) Float32x16

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTF128, CPU Feature: AVX
func (x Float64x4) SetHi(y Float64x2) Float64x4

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTF64X4, CPU Feature: AVX512
func (x Float64x8) SetHi(y Float64x4) Float64x8

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int8x32) SetHi(y Int8x16) Int8x32

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int8x64) SetHi(y Int8x32) Int8x64

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int16x16) SetHi(y Int16x8) Int16x16

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int16x32) SetHi(y Int16x16) Int16x32

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int32x8) SetHi(y Int32x4) Int32x8

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int32x16) SetHi(y Int32x8) Int32x16

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int64x4) SetHi(y Int64x2) Int64x4

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int64x8) SetHi(y Int64x4) Int64x8

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint8x32) SetHi(y Uint8x16) Uint8x32

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint8x64) SetHi(y Uint8x32) Uint8x64

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint16x16) SetHi(y Uint16x8) Uint16x16

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint16x32) SetHi(y Uint16x16) Uint16x32

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint32x8) SetHi(y Uint32x4) Uint32x8

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint32x16) SetHi(y Uint32x8) Uint32x16

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint64x4) SetHi(y Uint64x2) Uint64x4

// SetHi returns x with its upper half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint64x8) SetHi(y Uint64x4) Uint64x8

/* SetLo */

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTF128, CPU Feature: AVX
func (x Float32x8) SetLo(y Float32x4) Float32x8

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTF64X4, CPU Feature: AVX512
func (x Float32x16) SetLo(y Float32x8) Float32x16

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTF128, CPU Feature: AVX
func (x Float64x4) SetLo(y Float64x2) Float64x4

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTF64X4, CPU Feature: AVX512
func (x Float64x8) SetLo(y Float64x4) Float64x8

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int8x32) SetLo(y Int8x16) Int8x32

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int8x64) SetLo(y Int8x32) Int8x64

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int16x16) SetLo(y Int16x8) Int16x16

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int16x32) SetLo(y Int16x16) Int16x32

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int32x8) SetLo(y Int32x4) Int32x8

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int32x16) SetLo(y Int32x8) Int32x16

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Int64x4) SetLo(y Int64x2) Int64x4

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Int64x8) SetLo(y Int64x4) Int64x8

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint8x32) SetLo(y Uint8x16) Uint8x32

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint8x64) SetLo(y Uint8x32) Uint8x64

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint16x16) SetLo(y Uint16x8) Uint16x16

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint16x32) SetLo(y Uint16x16) Uint16x32

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint32x8) SetLo(y Uint32x4) Uint32x8

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint32x16) SetLo(y Uint32x8) Uint32x16

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI128, CPU Feature: AVX2
func (x Uint64x4) SetLo(y Uint64x2) Uint64x4

// SetLo returns x with its lower half set to y.
//
// Asm: VINSERTI64X4, CPU Feature: AVX512
func (x Uint64x8) SetLo(y Uint64x4) Uint64x8

/* ShiftAllLeft */

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX
func (x Int16x8) ShiftAllLeft(y uint64) Int16x8

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX2
func (x Int16x16) ShiftAllLeft(y uint64) Int16x16

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX512
func (x Int16x32) ShiftAllLeft(y uint64) Int16x32

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX
func (x Int32x4) ShiftAllLeft(y uint64) Int32x4

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX2
func (x Int32x8) ShiftAllLeft(y uint64) Int32x8

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX512
func (x Int32x16) ShiftAllLeft(y uint64) Int32x16

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX
func (x Int64x2) ShiftAllLeft(y uint64) Int64x2

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX2
func (x Int64x4) ShiftAllLeft(y uint64) Int64x4

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX512
func (x Int64x8) ShiftAllLeft(y uint64) Int64x8

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX
func (x Uint16x8) ShiftAllLeft(y uint64) Uint16x8

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX2
func (x Uint16x16) ShiftAllLeft(y uint64) Uint16x16

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLW, CPU Feature: AVX512
func (x Uint16x32) ShiftAllLeft(y uint64) Uint16x32

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX
func (x Uint32x4) ShiftAllLeft(y uint64) Uint32x4

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX2
func (x Uint32x8) ShiftAllLeft(y uint64) Uint32x8

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLD, CPU Feature: AVX512
func (x Uint32x16) ShiftAllLeft(y uint64) Uint32x16

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX
func (x Uint64x2) ShiftAllLeft(y uint64) Uint64x2

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX2
func (x Uint64x4) ShiftAllLeft(y uint64) Uint64x4

// ShiftAllLeft shifts each element to the left by the specified number of bits. Emptied lower bits are zeroed.
//
// Asm: VPSLLQ, CPU Feature: AVX512
func (x Uint64x8) ShiftAllLeft(y uint64) Uint64x8

/* ShiftAllLeftConcat */

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Int16x8) ShiftAllLeftConcat(shift uint8, y Int16x8) Int16x8

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Int16x16) ShiftAllLeftConcat(shift uint8, y Int16x16) Int16x16

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Int16x32) ShiftAllLeftConcat(shift uint8, y Int16x32) Int16x32

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Int32x4) ShiftAllLeftConcat(shift uint8, y Int32x4) Int32x4

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Int32x8) ShiftAllLeftConcat(shift uint8, y Int32x8) Int32x8

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Int32x16) ShiftAllLeftConcat(shift uint8, y Int32x16) Int32x16

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Int64x2) ShiftAllLeftConcat(shift uint8, y Int64x2) Int64x2

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Int64x4) ShiftAllLeftConcat(shift uint8, y Int64x4) Int64x4

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Int64x8) ShiftAllLeftConcat(shift uint8, y Int64x8) Int64x8

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Uint16x8) ShiftAllLeftConcat(shift uint8, y Uint16x8) Uint16x8

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Uint16x16) ShiftAllLeftConcat(shift uint8, y Uint16x16) Uint16x16

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDW, CPU Feature: AVX512VBMI2
func (x Uint16x32) ShiftAllLeftConcat(shift uint8, y Uint16x32) Uint16x32

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Uint32x4) ShiftAllLeftConcat(shift uint8, y Uint32x4) Uint32x4

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Uint32x8) ShiftAllLeftConcat(shift uint8, y Uint32x8) Uint32x8

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDD, CPU Feature: AVX512VBMI2
func (x Uint32x16) ShiftAllLeftConcat(shift uint8, y Uint32x16) Uint32x16

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Uint64x2) ShiftAllLeftConcat(shift uint8, y Uint64x2) Uint64x2

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Uint64x4) ShiftAllLeftConcat(shift uint8, y Uint64x4) Uint64x4

// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHLDQ, CPU Feature: AVX512VBMI2
func (x Uint64x8) ShiftAllLeftConcat(shift uint8, y Uint64x8) Uint64x8

/* ShiftAllRight */

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAW, CPU Feature: AVX
func (x Int16x8) ShiftAllRight(y uint64) Int16x8

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAW, CPU Feature: AVX2
func (x Int16x16) ShiftAllRight(y uint64) Int16x16

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAW, CPU Feature: AVX512
func (x Int16x32) ShiftAllRight(y uint64) Int16x32

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAD, CPU Feature: AVX
func (x Int32x4) ShiftAllRight(y uint64) Int32x4

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAD, CPU Feature: AVX2
func (x Int32x8) ShiftAllRight(y uint64) Int32x8

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAD, CPU Feature: AVX512
func (x Int32x16) ShiftAllRight(y uint64) Int32x16

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAQ, CPU Feature: AVX512
func (x Int64x2) ShiftAllRight(y uint64) Int64x2

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAQ, CPU Feature: AVX512
func (x Int64x4) ShiftAllRight(y uint64) Int64x4

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAQ, CPU Feature: AVX512
func (x Int64x8) ShiftAllRight(y uint64) Int64x8

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLW, CPU Feature: AVX
func (x Uint16x8) ShiftAllRight(y uint64) Uint16x8

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLW, CPU Feature: AVX2
func (x Uint16x16) ShiftAllRight(y uint64) Uint16x16

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLW, CPU Feature: AVX512
func (x Uint16x32) ShiftAllRight(y uint64) Uint16x32

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLD, CPU Feature: AVX
func (x Uint32x4) ShiftAllRight(y uint64) Uint32x4

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLD, CPU Feature: AVX2
func (x Uint32x8) ShiftAllRight(y uint64) Uint32x8

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLD, CPU Feature: AVX512
func (x Uint32x16) ShiftAllRight(y uint64) Uint32x16

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLQ, CPU Feature: AVX
func (x Uint64x2) ShiftAllRight(y uint64) Uint64x2

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLQ, CPU Feature: AVX2
func (x Uint64x4) ShiftAllRight(y uint64) Uint64x4

// ShiftAllRight shifts each element to the right by the specified number of bits. Emptied upper bits are zeroed.
//
// Asm: VPSRLQ, CPU Feature: AVX512
func (x Uint64x8) ShiftAllRight(y uint64) Uint64x8

/* ShiftAllRightConcat */

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Int16x8) ShiftAllRightConcat(shift uint8, y Int16x8) Int16x8

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Int16x16) ShiftAllRightConcat(shift uint8, y Int16x16) Int16x16

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Int16x32) ShiftAllRightConcat(shift uint8, y Int16x32) Int16x32

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Int32x4) ShiftAllRightConcat(shift uint8, y Int32x4) Int32x4

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Int32x8) ShiftAllRightConcat(shift uint8, y Int32x8) Int32x8

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Int32x16) ShiftAllRightConcat(shift uint8, y Int32x16) Int32x16

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Int64x2) ShiftAllRightConcat(shift uint8, y Int64x2) Int64x2

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Int64x4) ShiftAllRightConcat(shift uint8, y Int64x4) Int64x4

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Int64x8) ShiftAllRightConcat(shift uint8, y Int64x8) Int64x8

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Uint16x8) ShiftAllRightConcat(shift uint8, y Uint16x8) Uint16x8

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Uint16x16) ShiftAllRightConcat(shift uint8, y Uint16x16) Uint16x16

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDW, CPU Feature: AVX512VBMI2
func (x Uint16x32) ShiftAllRightConcat(shift uint8, y Uint16x32) Uint16x32

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Uint32x4) ShiftAllRightConcat(shift uint8, y Uint32x4) Uint32x4

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Uint32x8) ShiftAllRightConcat(shift uint8, y Uint32x8) Uint32x8

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDD, CPU Feature: AVX512VBMI2
func (x Uint32x16) ShiftAllRightConcat(shift uint8, y Uint32x16) Uint32x16

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Uint64x2) ShiftAllRightConcat(shift uint8, y Uint64x2) Uint64x2

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Uint64x4) ShiftAllRightConcat(shift uint8, y Uint64x4) Uint64x4

// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the
// immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x.
//
// shift results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VPSHRDQ, CPU Feature: AVX512VBMI2
func (x Uint64x8) ShiftAllRightConcat(shift uint8, y Uint64x8) Uint64x8

/* ShiftLeft */

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Int16x8) ShiftLeft(y Int16x8) Int16x8

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Int16x16) ShiftLeft(y Int16x16) Int16x16

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Int16x32) ShiftLeft(y Int16x32) Int16x32

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX2
func (x Int32x4) ShiftLeft(y Int32x4) Int32x4

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX2
func (x Int32x8) ShiftLeft(y Int32x8) Int32x8

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX512
func (x Int32x16) ShiftLeft(y Int32x16) Int32x16

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX2
func (x Int64x2) ShiftLeft(y Int64x2) Int64x2

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX2
func (x Int64x4) ShiftLeft(y Int64x4) Int64x4

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX512
func (x Int64x8) ShiftLeft(y Int64x8) Int64x8

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Uint16x8) ShiftLeft(y Uint16x8) Uint16x8

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Uint16x16) ShiftLeft(y Uint16x16) Uint16x16

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVW, CPU Feature: AVX512
func (x Uint16x32) ShiftLeft(y Uint16x32) Uint16x32

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX2
func (x Uint32x4) ShiftLeft(y Uint32x4) Uint32x4

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX2
func (x Uint32x8) ShiftLeft(y Uint32x8) Uint32x8

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVD, CPU Feature: AVX512
func (x Uint32x16) ShiftLeft(y Uint32x16) Uint32x16

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX2
func (x Uint64x2) ShiftLeft(y Uint64x2) Uint64x2

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX2
func (x Uint64x4) ShiftLeft(y Uint64x4) Uint64x4

// ShiftLeft shifts each element in x to the left by the number of bits specified in y's corresponding elements. Emptied lower bits are zeroed.
//
// Asm: VPSLLVQ, CPU Feature: AVX512
func (x Uint64x8) ShiftLeft(y Uint64x8) Uint64x8

/* ShiftLeftConcat */

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Int16x8) ShiftLeftConcat(y Int16x8, z Int16x8) Int16x8

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Int16x16) ShiftLeftConcat(y Int16x16, z Int16x16) Int16x16

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Int16x32) ShiftLeftConcat(y Int16x32, z Int16x32) Int16x32

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Int32x4) ShiftLeftConcat(y Int32x4, z Int32x4) Int32x4

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Int32x8) ShiftLeftConcat(y Int32x8, z Int32x8) Int32x8

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Int32x16) ShiftLeftConcat(y Int32x16, z Int32x16) Int32x16

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Int64x2) ShiftLeftConcat(y Int64x2, z Int64x2) Int64x2

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Int64x4) ShiftLeftConcat(y Int64x4, z Int64x4) Int64x4

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Int64x8) ShiftLeftConcat(y Int64x8, z Int64x8) Int64x8

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Uint16x8) ShiftLeftConcat(y Uint16x8, z Uint16x8) Uint16x8

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Uint16x16) ShiftLeftConcat(y Uint16x16, z Uint16x16) Uint16x16

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVW, CPU Feature: AVX512VBMI2
func (x Uint16x32) ShiftLeftConcat(y Uint16x32, z Uint16x32) Uint16x32

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Uint32x4) ShiftLeftConcat(y Uint32x4, z Uint32x4) Uint32x4

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Uint32x8) ShiftLeftConcat(y Uint32x8, z Uint32x8) Uint32x8

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVD, CPU Feature: AVX512VBMI2
func (x Uint32x16) ShiftLeftConcat(y Uint32x16, z Uint32x16) Uint32x16

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x2) ShiftLeftConcat(y Uint64x2, z Uint64x2) Uint64x2

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x4) ShiftLeftConcat(y Uint64x4, z Uint64x4) Uint64x4

// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x.
//
// Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x8) ShiftLeftConcat(y Uint64x8, z Uint64x8) Uint64x8

/* ShiftRight */

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVW, CPU Feature: AVX512
func (x Int16x8) ShiftRight(y Int16x8) Int16x8

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVW, CPU Feature: AVX512
func (x Int16x16) ShiftRight(y Int16x16) Int16x16

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVW, CPU Feature: AVX512
func (x Int16x32) ShiftRight(y Int16x32) Int16x32

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVD, CPU Feature: AVX2
func (x Int32x4) ShiftRight(y Int32x4) Int32x4

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVD, CPU Feature: AVX2
func (x Int32x8) ShiftRight(y Int32x8) Int32x8

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVD, CPU Feature: AVX512
func (x Int32x16) ShiftRight(y Int32x16) Int32x16

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVQ, CPU Feature: AVX512
func (x Int64x2) ShiftRight(y Int64x2) Int64x2

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVQ, CPU Feature: AVX512
func (x Int64x4) ShiftRight(y Int64x4) Int64x4

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are filled with the sign bit.
//
// Asm: VPSRAVQ, CPU Feature: AVX512
func (x Int64x8) ShiftRight(y Int64x8) Int64x8

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVW, CPU Feature: AVX512
func (x Uint16x8) ShiftRight(y Uint16x8) Uint16x8

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVW, CPU Feature: AVX512
func (x Uint16x16) ShiftRight(y Uint16x16) Uint16x16

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVW, CPU Feature: AVX512
func (x Uint16x32) ShiftRight(y Uint16x32) Uint16x32

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVD, CPU Feature: AVX2
func (x Uint32x4) ShiftRight(y Uint32x4) Uint32x4

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVD, CPU Feature: AVX2
func (x Uint32x8) ShiftRight(y Uint32x8) Uint32x8

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVD, CPU Feature: AVX512
func (x Uint32x16) ShiftRight(y Uint32x16) Uint32x16

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVQ, CPU Feature: AVX2
func (x Uint64x2) ShiftRight(y Uint64x2) Uint64x2

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVQ, CPU Feature: AVX2
func (x Uint64x4) ShiftRight(y Uint64x4) Uint64x4

// ShiftRight shifts each element in x to the right by the number of bits specified in y's corresponding elements. Emptied upper bits are zeroed.
//
// Asm: VPSRLVQ, CPU Feature: AVX512
func (x Uint64x8) ShiftRight(y Uint64x8) Uint64x8

/* ShiftRightConcat */

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Int16x8) ShiftRightConcat(y Int16x8, z Int16x8) Int16x8

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Int16x16) ShiftRightConcat(y Int16x16, z Int16x16) Int16x16

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Int16x32) ShiftRightConcat(y Int16x32, z Int16x32) Int16x32

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Int32x4) ShiftRightConcat(y Int32x4, z Int32x4) Int32x4

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Int32x8) ShiftRightConcat(y Int32x8, z Int32x8) Int32x8

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Int32x16) ShiftRightConcat(y Int32x16, z Int32x16) Int32x16

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Int64x2) ShiftRightConcat(y Int64x2, z Int64x2) Int64x2

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Int64x4) ShiftRightConcat(y Int64x4, z Int64x4) Int64x4

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Int64x8) ShiftRightConcat(y Int64x8, z Int64x8) Int64x8

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Uint16x8) ShiftRightConcat(y Uint16x8, z Uint16x8) Uint16x8

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Uint16x16) ShiftRightConcat(y Uint16x16, z Uint16x16) Uint16x16

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVW, CPU Feature: AVX512VBMI2
func (x Uint16x32) ShiftRightConcat(y Uint16x32, z Uint16x32) Uint16x32

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Uint32x4) ShiftRightConcat(y Uint32x4, z Uint32x4) Uint32x4

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Uint32x8) ShiftRightConcat(y Uint32x8, z Uint32x8) Uint32x8

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVD, CPU Feature: AVX512VBMI2
func (x Uint32x16) ShiftRightConcat(y Uint32x16, z Uint32x16) Uint32x16

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x2) ShiftRightConcat(y Uint64x2, z Uint64x2) Uint64x2

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x4) ShiftRightConcat(y Uint64x4, z Uint64x4) Uint64x4

// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the
// corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x.
//
// Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2
func (x Uint64x8) ShiftRightConcat(y Uint64x8, z Uint64x8) Uint64x8

/* Sqrt */

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPS, CPU Feature: AVX
func (x Float32x4) Sqrt() Float32x4

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPS, CPU Feature: AVX
func (x Float32x8) Sqrt() Float32x8

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPS, CPU Feature: AVX512
func (x Float32x16) Sqrt() Float32x16

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPD, CPU Feature: AVX
func (x Float64x2) Sqrt() Float64x2

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPD, CPU Feature: AVX
func (x Float64x4) Sqrt() Float64x4

// Sqrt computes the square root of each element.
//
// Asm: VSQRTPD, CPU Feature: AVX512
func (x Float64x8) Sqrt() Float64x8

/* Sub */

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPS, CPU Feature: AVX
func (x Float32x4) Sub(y Float32x4) Float32x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPS, CPU Feature: AVX
func (x Float32x8) Sub(y Float32x8) Float32x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPS, CPU Feature: AVX512
func (x Float32x16) Sub(y Float32x16) Float32x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPD, CPU Feature: AVX
func (x Float64x2) Sub(y Float64x2) Float64x2

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPD, CPU Feature: AVX
func (x Float64x4) Sub(y Float64x4) Float64x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VSUBPD, CPU Feature: AVX512
func (x Float64x8) Sub(y Float64x8) Float64x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX
func (x Int8x16) Sub(y Int8x16) Int8x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX2
func (x Int8x32) Sub(y Int8x32) Int8x32

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX512
func (x Int8x64) Sub(y Int8x64) Int8x64

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX
func (x Int16x8) Sub(y Int16x8) Int16x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX2
func (x Int16x16) Sub(y Int16x16) Int16x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX512
func (x Int16x32) Sub(y Int16x32) Int16x32

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX
func (x Int32x4) Sub(y Int32x4) Int32x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX2
func (x Int32x8) Sub(y Int32x8) Int32x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX512
func (x Int32x16) Sub(y Int32x16) Int32x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX
func (x Int64x2) Sub(y Int64x2) Int64x2

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX2
func (x Int64x4) Sub(y Int64x4) Int64x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX512
func (x Int64x8) Sub(y Int64x8) Int64x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX
func (x Uint8x16) Sub(y Uint8x16) Uint8x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX2
func (x Uint8x32) Sub(y Uint8x32) Uint8x32

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBB, CPU Feature: AVX512
func (x Uint8x64) Sub(y Uint8x64) Uint8x64

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX
func (x Uint16x8) Sub(y Uint16x8) Uint16x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX2
func (x Uint16x16) Sub(y Uint16x16) Uint16x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBW, CPU Feature: AVX512
func (x Uint16x32) Sub(y Uint16x32) Uint16x32

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX
func (x Uint32x4) Sub(y Uint32x4) Uint32x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX2
func (x Uint32x8) Sub(y Uint32x8) Uint32x8

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBD, CPU Feature: AVX512
func (x Uint32x16) Sub(y Uint32x16) Uint32x16

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX
func (x Uint64x2) Sub(y Uint64x2) Uint64x2

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX2
func (x Uint64x4) Sub(y Uint64x4) Uint64x4

// Sub subtracts corresponding elements of two vectors.
//
// Asm: VPSUBQ, CPU Feature: AVX512
func (x Uint64x8) Sub(y Uint64x8) Uint64x8

/* SubPairs */

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VHSUBPS, CPU Feature: AVX
func (x Float32x4) SubPairs(y Float32x4) Float32x4

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VHSUBPS, CPU Feature: AVX
func (x Float32x8) SubPairs(y Float32x8) Float32x8

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VHSUBPD, CPU Feature: AVX
func (x Float64x2) SubPairs(y Float64x2) Float64x2

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VHSUBPD, CPU Feature: AVX
func (x Float64x4) SubPairs(y Float64x4) Float64x4

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBW, CPU Feature: AVX
func (x Int16x8) SubPairs(y Int16x8) Int16x8

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBW, CPU Feature: AVX2
func (x Int16x16) SubPairs(y Int16x16) Int16x16

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBD, CPU Feature: AVX
func (x Int32x4) SubPairs(y Int32x4) Int32x4

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBD, CPU Feature: AVX2
func (x Int32x8) SubPairs(y Int32x8) Int32x8

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBW, CPU Feature: AVX
func (x Uint16x8) SubPairs(y Uint16x8) Uint16x8

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBW, CPU Feature: AVX2
func (x Uint16x16) SubPairs(y Uint16x16) Uint16x16

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBD, CPU Feature: AVX
func (x Uint32x4) SubPairs(y Uint32x4) Uint32x4

// SubPairs horizontally subtracts adjacent pairs of elements.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBD, CPU Feature: AVX2
func (x Uint32x8) SubPairs(y Uint32x8) Uint32x8

/* SubPairsSaturated */

// SubPairsSaturated horizontally subtracts adjacent pairs of elements with saturation.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBSW, CPU Feature: AVX
func (x Int16x8) SubPairsSaturated(y Int16x8) Int16x8

// SubPairsSaturated horizontally subtracts adjacent pairs of elements with saturation.
// For x = [x0, x1, x2, x3, ...] and y = [y0, y1, y2, y3, ...], the result is [y0-y1, y2-y3, ..., x0-x1, x2-x3, ...].
//
// Asm: VPHSUBSW, CPU Feature: AVX2
func (x Int16x16) SubPairsSaturated(y Int16x16) Int16x16

/* SubSaturated */

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSB, CPU Feature: AVX
func (x Int8x16) SubSaturated(y Int8x16) Int8x16

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSB, CPU Feature: AVX2
func (x Int8x32) SubSaturated(y Int8x32) Int8x32

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSB, CPU Feature: AVX512
func (x Int8x64) SubSaturated(y Int8x64) Int8x64

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSW, CPU Feature: AVX
func (x Int16x8) SubSaturated(y Int16x8) Int16x8

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSW, CPU Feature: AVX2
func (x Int16x16) SubSaturated(y Int16x16) Int16x16

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBSW, CPU Feature: AVX512
func (x Int16x32) SubSaturated(y Int16x32) Int16x32

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSB, CPU Feature: AVX
func (x Uint8x16) SubSaturated(y Uint8x16) Uint8x16

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSB, CPU Feature: AVX2
func (x Uint8x32) SubSaturated(y Uint8x32) Uint8x32

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSB, CPU Feature: AVX512
func (x Uint8x64) SubSaturated(y Uint8x64) Uint8x64

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSW, CPU Feature: AVX
func (x Uint16x8) SubSaturated(y Uint16x8) Uint16x8

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSW, CPU Feature: AVX2
func (x Uint16x16) SubSaturated(y Uint16x16) Uint16x16

// SubSaturated subtracts corresponding elements of two vectors with saturation.
//
// Asm: VPSUBUSW, CPU Feature: AVX512
func (x Uint16x32) SubSaturated(y Uint16x32) Uint16x32

/* SumAbsDiff */

// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
//
// Asm: VPSADBW, CPU Feature: AVX
func (x Uint8x16) SumAbsDiff(y Uint8x16) Uint16x8

// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
//
// Asm: VPSADBW, CPU Feature: AVX2
func (x Uint8x32) SumAbsDiff(y Uint8x32) Uint16x16

// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
//
// Asm: VPSADBW, CPU Feature: AVX512
func (x Uint8x64) SumAbsDiff(y Uint8x64) Uint16x32

/* Trunc */

// Trunc truncates elements towards zero.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x4) Trunc() Float32x4

// Trunc truncates elements towards zero.
//
// Asm: VROUNDPS, CPU Feature: AVX
func (x Float32x8) Trunc() Float32x8

// Trunc truncates elements towards zero.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x2) Trunc() Float64x2

// Trunc truncates elements towards zero.
//
// Asm: VROUNDPD, CPU Feature: AVX
func (x Float64x4) Trunc() Float64x4

/* TruncScaled */

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x4) TruncScaled(prec uint8) Float32x4

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x8) TruncScaled(prec uint8) Float32x8

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPS, CPU Feature: AVX512
func (x Float32x16) TruncScaled(prec uint8) Float32x16

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x2) TruncScaled(prec uint8) Float64x2

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x4) TruncScaled(prec uint8) Float64x4

// TruncScaled truncates elements with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VRNDSCALEPD, CPU Feature: AVX512
func (x Float64x8) TruncScaled(prec uint8) Float64x8

/* TruncScaledResidue */

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x4) TruncScaledResidue(prec uint8) Float32x4

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x8) TruncScaledResidue(prec uint8) Float32x8

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPS, CPU Feature: AVX512
func (x Float32x16) TruncScaledResidue(prec uint8) Float32x16

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x2) TruncScaledResidue(prec uint8) Float64x2

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x4) TruncScaledResidue(prec uint8) Float64x4

// TruncScaledResidue computes the difference after truncating with specified precision.
//
// prec results in better performance when it's a constant, a non-constant value will be translated into a jump table.
//
// Asm: VREDUCEPD, CPU Feature: AVX512
func (x Float64x8) TruncScaledResidue(prec uint8) Float64x8

/* TruncateToInt8 */

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Int16x8) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Int16x16) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Int16x32) TruncateToInt8() Int8x32

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Int32x4) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Int32x8) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Int32x16) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Int64x2) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Int64x4) TruncateToInt8() Int8x16

// TruncateToInt8 converts element values to int8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Int64x8) TruncateToInt8() Int8x16

/* TruncateToInt16 */

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Int32x4) TruncateToInt16() Int16x8

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Int32x8) TruncateToInt16() Int16x8

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Int32x16) TruncateToInt16() Int16x16

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Int64x2) TruncateToInt16() Int16x8

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Int64x4) TruncateToInt16() Int16x8

// TruncateToInt16 converts element values to int16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Int64x8) TruncateToInt16() Int16x8

/* TruncateToInt32 */

// TruncateToInt32 converts element values to int32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Int64x2) TruncateToInt32() Int32x4

// TruncateToInt32 converts element values to int32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Int64x4) TruncateToInt32() Int32x4

// TruncateToInt32 converts element values to int32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Int64x8) TruncateToInt32() Int32x8

/* TruncateToUint8 */

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Uint16x8) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Uint16x16) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVWB, CPU Feature: AVX512
func (x Uint16x32) TruncateToUint8() Uint8x32

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Uint32x4) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Uint32x8) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVDB, CPU Feature: AVX512
func (x Uint32x16) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Uint64x2) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Uint64x4) TruncateToUint8() Uint8x16

// TruncateToUint8 converts element values to uint8.
// Conversion is done with truncation on the vector elements.
// Results are packed to low elements in the returned vector, its upper elements are zero-cleared.
//
// Asm: VPMOVQB, CPU Feature: AVX512
func (x Uint64x8) TruncateToUint8() Uint8x16

/* TruncateToUint16 */

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Uint32x4) TruncateToUint16() Uint16x8

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Uint32x8) TruncateToUint16() Uint16x8

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVDW, CPU Feature: AVX512
func (x Uint32x16) TruncateToUint16() Uint16x16

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Uint64x2) TruncateToUint16() Uint16x8

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Uint64x4) TruncateToUint16() Uint16x8

// TruncateToUint16 converts element values to uint16.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQW, CPU Feature: AVX512
func (x Uint64x8) TruncateToUint16() Uint16x8

/* TruncateToUint32 */

// TruncateToUint32 converts element values to uint32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Uint64x2) TruncateToUint32() Uint32x4

// TruncateToUint32 converts element values to uint32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Uint64x4) TruncateToUint32() Uint32x4

// TruncateToUint32 converts element values to uint32.
// Conversion is done with truncation on the vector elements.
//
// Asm: VPMOVQD, CPU Feature: AVX512
func (x Uint64x8) TruncateToUint32() Uint32x8

/* Xor */

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Int8x16) Xor(y Int8x16) Int8x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Int8x32) Xor(y Int8x32) Int8x32

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Int8x64) Xor(y Int8x64) Int8x64

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Int16x8) Xor(y Int16x8) Int16x8

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Int16x16) Xor(y Int16x16) Int16x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Int16x32) Xor(y Int16x32) Int16x32

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Int32x4) Xor(y Int32x4) Int32x4

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Int32x8) Xor(y Int32x8) Int32x8

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Int32x16) Xor(y Int32x16) Int32x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Int64x2) Xor(y Int64x2) Int64x2

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Int64x4) Xor(y Int64x4) Int64x4

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORQ, CPU Feature: AVX512
func (x Int64x8) Xor(y Int64x8) Int64x8

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Uint8x16) Xor(y Uint8x16) Uint8x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Uint8x32) Xor(y Uint8x32) Uint8x32

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Uint8x64) Xor(y Uint8x64) Uint8x64

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Uint16x8) Xor(y Uint16x8) Uint16x8

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Uint16x16) Xor(y Uint16x16) Uint16x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Uint16x32) Xor(y Uint16x32) Uint16x32

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Uint32x4) Xor(y Uint32x4) Uint32x4

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Uint32x8) Xor(y Uint32x8) Uint32x8

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORD, CPU Feature: AVX512
func (x Uint32x16) Xor(y Uint32x16) Uint32x16

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX
func (x Uint64x2) Xor(y Uint64x2) Uint64x2

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXOR, CPU Feature: AVX2
func (x Uint64x4) Xor(y Uint64x4) Uint64x4

// Xor performs a bitwise XOR operation between two vectors.
//
// Asm: VPXORQ, CPU Feature: AVX512
func (x Uint64x8) Xor(y Uint64x8) Uint64x8

// Float64x2 converts from Float32x4 to Float64x2
func (from Float32x4) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Float32x4 to Int8x16
func (from Float32x4) AsInt8x16() (to Int8x16)

// Int16x8 converts from Float32x4 to Int16x8
func (from Float32x4) AsInt16x8() (to Int16x8)

// Int32x4 converts from Float32x4 to Int32x4
func (from Float32x4) AsInt32x4() (to Int32x4)

// Int64x2 converts from Float32x4 to Int64x2
func (from Float32x4) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Float32x4 to Uint8x16
func (from Float32x4) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Float32x4 to Uint16x8
func (from Float32x4) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Float32x4 to Uint32x4
func (from Float32x4) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Float32x4 to Uint64x2
func (from Float32x4) AsUint64x2() (to Uint64x2)

// Float64x4 converts from Float32x8 to Float64x4
func (from Float32x8) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Float32x8 to Int8x32
func (from Float32x8) AsInt8x32() (to Int8x32)

// Int16x16 converts from Float32x8 to Int16x16
func (from Float32x8) AsInt16x16() (to Int16x16)

// Int32x8 converts from Float32x8 to Int32x8
func (from Float32x8) AsInt32x8() (to Int32x8)

// Int64x4 converts from Float32x8 to Int64x4
func (from Float32x8) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Float32x8 to Uint8x32
func (from Float32x8) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Float32x8 to Uint16x16
func (from Float32x8) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Float32x8 to Uint32x8
func (from Float32x8) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Float32x8 to Uint64x4
func (from Float32x8) AsUint64x4() (to Uint64x4)

// Float64x8 converts from Float32x16 to Float64x8
func (from Float32x16) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Float32x16 to Int8x64
func (from Float32x16) AsInt8x64() (to Int8x64)

// Int16x32 converts from Float32x16 to Int16x32
func (from Float32x16) AsInt16x32() (to Int16x32)

// Int32x16 converts from Float32x16 to Int32x16
func (from Float32x16) AsInt32x16() (to Int32x16)

// Int64x8 converts from Float32x16 to Int64x8
func (from Float32x16) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Float32x16 to Uint8x64
func (from Float32x16) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Float32x16 to Uint16x32
func (from Float32x16) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Float32x16 to Uint32x16
func (from Float32x16) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Float32x16 to Uint64x8
func (from Float32x16) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Float64x2 to Float32x4
func (from Float64x2) AsFloat32x4() (to Float32x4)

// Int8x16 converts from Float64x2 to Int8x16
func (from Float64x2) AsInt8x16() (to Int8x16)

// Int16x8 converts from Float64x2 to Int16x8
func (from Float64x2) AsInt16x8() (to Int16x8)

// Int32x4 converts from Float64x2 to Int32x4
func (from Float64x2) AsInt32x4() (to Int32x4)

// Int64x2 converts from Float64x2 to Int64x2
func (from Float64x2) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Float64x2 to Uint8x16
func (from Float64x2) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Float64x2 to Uint16x8
func (from Float64x2) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Float64x2 to Uint32x4
func (from Float64x2) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Float64x2 to Uint64x2
func (from Float64x2) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Float64x4 to Float32x8
func (from Float64x4) AsFloat32x8() (to Float32x8)

// Int8x32 converts from Float64x4 to Int8x32
func (from Float64x4) AsInt8x32() (to Int8x32)

// Int16x16 converts from Float64x4 to Int16x16
func (from Float64x4) AsInt16x16() (to Int16x16)

// Int32x8 converts from Float64x4 to Int32x8
func (from Float64x4) AsInt32x8() (to Int32x8)

// Int64x4 converts from Float64x4 to Int64x4
func (from Float64x4) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Float64x4 to Uint8x32
func (from Float64x4) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Float64x4 to Uint16x16
func (from Float64x4) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Float64x4 to Uint32x8
func (from Float64x4) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Float64x4 to Uint64x4
func (from Float64x4) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Float64x8 to Float32x16
func (from Float64x8) AsFloat32x16() (to Float32x16)

// Int8x64 converts from Float64x8 to Int8x64
func (from Float64x8) AsInt8x64() (to Int8x64)

// Int16x32 converts from Float64x8 to Int16x32
func (from Float64x8) AsInt16x32() (to Int16x32)

// Int32x16 converts from Float64x8 to Int32x16
func (from Float64x8) AsInt32x16() (to Int32x16)

// Int64x8 converts from Float64x8 to Int64x8
func (from Float64x8) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Float64x8 to Uint8x64
func (from Float64x8) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Float64x8 to Uint16x32
func (from Float64x8) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Float64x8 to Uint32x16
func (from Float64x8) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Float64x8 to Uint64x8
func (from Float64x8) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Int8x16 to Float32x4
func (from Int8x16) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Int8x16 to Float64x2
func (from Int8x16) AsFloat64x2() (to Float64x2)

// Int16x8 converts from Int8x16 to Int16x8
func (from Int8x16) AsInt16x8() (to Int16x8)

// Int32x4 converts from Int8x16 to Int32x4
func (from Int8x16) AsInt32x4() (to Int32x4)

// Int64x2 converts from Int8x16 to Int64x2
func (from Int8x16) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Int8x16 to Uint8x16
func (from Int8x16) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Int8x16 to Uint16x8
func (from Int8x16) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Int8x16 to Uint32x4
func (from Int8x16) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Int8x16 to Uint64x2
func (from Int8x16) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Int8x32 to Float32x8
func (from Int8x32) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Int8x32 to Float64x4
func (from Int8x32) AsFloat64x4() (to Float64x4)

// Int16x16 converts from Int8x32 to Int16x16
func (from Int8x32) AsInt16x16() (to Int16x16)

// Int32x8 converts from Int8x32 to Int32x8
func (from Int8x32) AsInt32x8() (to Int32x8)

// Int64x4 converts from Int8x32 to Int64x4
func (from Int8x32) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Int8x32 to Uint8x32
func (from Int8x32) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Int8x32 to Uint16x16
func (from Int8x32) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Int8x32 to Uint32x8
func (from Int8x32) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Int8x32 to Uint64x4
func (from Int8x32) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Int8x64 to Float32x16
func (from Int8x64) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Int8x64 to Float64x8
func (from Int8x64) AsFloat64x8() (to Float64x8)

// Int16x32 converts from Int8x64 to Int16x32
func (from Int8x64) AsInt16x32() (to Int16x32)

// Int32x16 converts from Int8x64 to Int32x16
func (from Int8x64) AsInt32x16() (to Int32x16)

// Int64x8 converts from Int8x64 to Int64x8
func (from Int8x64) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Int8x64 to Uint8x64
func (from Int8x64) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Int8x64 to Uint16x32
func (from Int8x64) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Int8x64 to Uint32x16
func (from Int8x64) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Int8x64 to Uint64x8
func (from Int8x64) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Int16x8 to Float32x4
func (from Int16x8) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Int16x8 to Float64x2
func (from Int16x8) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Int16x8 to Int8x16
func (from Int16x8) AsInt8x16() (to Int8x16)

// Int32x4 converts from Int16x8 to Int32x4
func (from Int16x8) AsInt32x4() (to Int32x4)

// Int64x2 converts from Int16x8 to Int64x2
func (from Int16x8) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Int16x8 to Uint8x16
func (from Int16x8) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Int16x8 to Uint16x8
func (from Int16x8) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Int16x8 to Uint32x4
func (from Int16x8) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Int16x8 to Uint64x2
func (from Int16x8) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Int16x16 to Float32x8
func (from Int16x16) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Int16x16 to Float64x4
func (from Int16x16) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Int16x16 to Int8x32
func (from Int16x16) AsInt8x32() (to Int8x32)

// Int32x8 converts from Int16x16 to Int32x8
func (from Int16x16) AsInt32x8() (to Int32x8)

// Int64x4 converts from Int16x16 to Int64x4
func (from Int16x16) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Int16x16 to Uint8x32
func (from Int16x16) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Int16x16 to Uint16x16
func (from Int16x16) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Int16x16 to Uint32x8
func (from Int16x16) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Int16x16 to Uint64x4
func (from Int16x16) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Int16x32 to Float32x16
func (from Int16x32) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Int16x32 to Float64x8
func (from Int16x32) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Int16x32 to Int8x64
func (from Int16x32) AsInt8x64() (to Int8x64)

// Int32x16 converts from Int16x32 to Int32x16
func (from Int16x32) AsInt32x16() (to Int32x16)

// Int64x8 converts from Int16x32 to Int64x8
func (from Int16x32) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Int16x32 to Uint8x64
func (from Int16x32) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Int16x32 to Uint16x32
func (from Int16x32) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Int16x32 to Uint32x16
func (from Int16x32) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Int16x32 to Uint64x8
func (from Int16x32) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Int32x4 to Float32x4
func (from Int32x4) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Int32x4 to Float64x2
func (from Int32x4) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Int32x4 to Int8x16
func (from Int32x4) AsInt8x16() (to Int8x16)

// Int16x8 converts from Int32x4 to Int16x8
func (from Int32x4) AsInt16x8() (to Int16x8)

// Int64x2 converts from Int32x4 to Int64x2
func (from Int32x4) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Int32x4 to Uint8x16
func (from Int32x4) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Int32x4 to Uint16x8
func (from Int32x4) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Int32x4 to Uint32x4
func (from Int32x4) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Int32x4 to Uint64x2
func (from Int32x4) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Int32x8 to Float32x8
func (from Int32x8) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Int32x8 to Float64x4
func (from Int32x8) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Int32x8 to Int8x32
func (from Int32x8) AsInt8x32() (to Int8x32)

// Int16x16 converts from Int32x8 to Int16x16
func (from Int32x8) AsInt16x16() (to Int16x16)

// Int64x4 converts from Int32x8 to Int64x4
func (from Int32x8) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Int32x8 to Uint8x32
func (from Int32x8) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Int32x8 to Uint16x16
func (from Int32x8) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Int32x8 to Uint32x8
func (from Int32x8) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Int32x8 to Uint64x4
func (from Int32x8) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Int32x16 to Float32x16
func (from Int32x16) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Int32x16 to Float64x8
func (from Int32x16) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Int32x16 to Int8x64
func (from Int32x16) AsInt8x64() (to Int8x64)

// Int16x32 converts from Int32x16 to Int16x32
func (from Int32x16) AsInt16x32() (to Int16x32)

// Int64x8 converts from Int32x16 to Int64x8
func (from Int32x16) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Int32x16 to Uint8x64
func (from Int32x16) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Int32x16 to Uint16x32
func (from Int32x16) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Int32x16 to Uint32x16
func (from Int32x16) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Int32x16 to Uint64x8
func (from Int32x16) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Int64x2 to Float32x4
func (from Int64x2) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Int64x2 to Float64x2
func (from Int64x2) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Int64x2 to Int8x16
func (from Int64x2) AsInt8x16() (to Int8x16)

// Int16x8 converts from Int64x2 to Int16x8
func (from Int64x2) AsInt16x8() (to Int16x8)

// Int32x4 converts from Int64x2 to Int32x4
func (from Int64x2) AsInt32x4() (to Int32x4)

// Uint8x16 converts from Int64x2 to Uint8x16
func (from Int64x2) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Int64x2 to Uint16x8
func (from Int64x2) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Int64x2 to Uint32x4
func (from Int64x2) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Int64x2 to Uint64x2
func (from Int64x2) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Int64x4 to Float32x8
func (from Int64x4) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Int64x4 to Float64x4
func (from Int64x4) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Int64x4 to Int8x32
func (from Int64x4) AsInt8x32() (to Int8x32)

// Int16x16 converts from Int64x4 to Int16x16
func (from Int64x4) AsInt16x16() (to Int16x16)

// Int32x8 converts from Int64x4 to Int32x8
func (from Int64x4) AsInt32x8() (to Int32x8)

// Uint8x32 converts from Int64x4 to Uint8x32
func (from Int64x4) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Int64x4 to Uint16x16
func (from Int64x4) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Int64x4 to Uint32x8
func (from Int64x4) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Int64x4 to Uint64x4
func (from Int64x4) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Int64x8 to Float32x16
func (from Int64x8) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Int64x8 to Float64x8
func (from Int64x8) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Int64x8 to Int8x64
func (from Int64x8) AsInt8x64() (to Int8x64)

// Int16x32 converts from Int64x8 to Int16x32
func (from Int64x8) AsInt16x32() (to Int16x32)

// Int32x16 converts from Int64x8 to Int32x16
func (from Int64x8) AsInt32x16() (to Int32x16)

// Uint8x64 converts from Int64x8 to Uint8x64
func (from Int64x8) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Int64x8 to Uint16x32
func (from Int64x8) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Int64x8 to Uint32x16
func (from Int64x8) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Int64x8 to Uint64x8
func (from Int64x8) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Uint8x16 to Float32x4
func (from Uint8x16) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Uint8x16 to Float64x2
func (from Uint8x16) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Uint8x16 to Int8x16
func (from Uint8x16) AsInt8x16() (to Int8x16)

// Int16x8 converts from Uint8x16 to Int16x8
func (from Uint8x16) AsInt16x8() (to Int16x8)

// Int32x4 converts from Uint8x16 to Int32x4
func (from Uint8x16) AsInt32x4() (to Int32x4)

// Int64x2 converts from Uint8x16 to Int64x2
func (from Uint8x16) AsInt64x2() (to Int64x2)

// Uint16x8 converts from Uint8x16 to Uint16x8
func (from Uint8x16) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Uint8x16 to Uint32x4
func (from Uint8x16) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Uint8x16 to Uint64x2
func (from Uint8x16) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Uint8x32 to Float32x8
func (from Uint8x32) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Uint8x32 to Float64x4
func (from Uint8x32) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Uint8x32 to Int8x32
func (from Uint8x32) AsInt8x32() (to Int8x32)

// Int16x16 converts from Uint8x32 to Int16x16
func (from Uint8x32) AsInt16x16() (to Int16x16)

// Int32x8 converts from Uint8x32 to Int32x8
func (from Uint8x32) AsInt32x8() (to Int32x8)

// Int64x4 converts from Uint8x32 to Int64x4
func (from Uint8x32) AsInt64x4() (to Int64x4)

// Uint16x16 converts from Uint8x32 to Uint16x16
func (from Uint8x32) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Uint8x32 to Uint32x8
func (from Uint8x32) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Uint8x32 to Uint64x4
func (from Uint8x32) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Uint8x64 to Float32x16
func (from Uint8x64) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Uint8x64 to Float64x8
func (from Uint8x64) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Uint8x64 to Int8x64
func (from Uint8x64) AsInt8x64() (to Int8x64)

// Int16x32 converts from Uint8x64 to Int16x32
func (from Uint8x64) AsInt16x32() (to Int16x32)

// Int32x16 converts from Uint8x64 to Int32x16
func (from Uint8x64) AsInt32x16() (to Int32x16)

// Int64x8 converts from Uint8x64 to Int64x8
func (from Uint8x64) AsInt64x8() (to Int64x8)

// Uint16x32 converts from Uint8x64 to Uint16x32
func (from Uint8x64) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Uint8x64 to Uint32x16
func (from Uint8x64) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Uint8x64 to Uint64x8
func (from Uint8x64) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Uint16x8 to Float32x4
func (from Uint16x8) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Uint16x8 to Float64x2
func (from Uint16x8) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Uint16x8 to Int8x16
func (from Uint16x8) AsInt8x16() (to Int8x16)

// Int16x8 converts from Uint16x8 to Int16x8
func (from Uint16x8) AsInt16x8() (to Int16x8)

// Int32x4 converts from Uint16x8 to Int32x4
func (from Uint16x8) AsInt32x4() (to Int32x4)

// Int64x2 converts from Uint16x8 to Int64x2
func (from Uint16x8) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Uint16x8 to Uint8x16
func (from Uint16x8) AsUint8x16() (to Uint8x16)

// Uint32x4 converts from Uint16x8 to Uint32x4
func (from Uint16x8) AsUint32x4() (to Uint32x4)

// Uint64x2 converts from Uint16x8 to Uint64x2
func (from Uint16x8) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Uint16x16 to Float32x8
func (from Uint16x16) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Uint16x16 to Float64x4
func (from Uint16x16) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Uint16x16 to Int8x32
func (from Uint16x16) AsInt8x32() (to Int8x32)

// Int16x16 converts from Uint16x16 to Int16x16
func (from Uint16x16) AsInt16x16() (to Int16x16)

// Int32x8 converts from Uint16x16 to Int32x8
func (from Uint16x16) AsInt32x8() (to Int32x8)

// Int64x4 converts from Uint16x16 to Int64x4
func (from Uint16x16) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Uint16x16 to Uint8x32
func (from Uint16x16) AsUint8x32() (to Uint8x32)

// Uint32x8 converts from Uint16x16 to Uint32x8
func (from Uint16x16) AsUint32x8() (to Uint32x8)

// Uint64x4 converts from Uint16x16 to Uint64x4
func (from Uint16x16) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Uint16x32 to Float32x16
func (from Uint16x32) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Uint16x32 to Float64x8
func (from Uint16x32) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Uint16x32 to Int8x64
func (from Uint16x32) AsInt8x64() (to Int8x64)

// Int16x32 converts from Uint16x32 to Int16x32
func (from Uint16x32) AsInt16x32() (to Int16x32)

// Int32x16 converts from Uint16x32 to Int32x16
func (from Uint16x32) AsInt32x16() (to Int32x16)

// Int64x8 converts from Uint16x32 to Int64x8
func (from Uint16x32) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Uint16x32 to Uint8x64
func (from Uint16x32) AsUint8x64() (to Uint8x64)

// Uint32x16 converts from Uint16x32 to Uint32x16
func (from Uint16x32) AsUint32x16() (to Uint32x16)

// Uint64x8 converts from Uint16x32 to Uint64x8
func (from Uint16x32) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Uint32x4 to Float32x4
func (from Uint32x4) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Uint32x4 to Float64x2
func (from Uint32x4) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Uint32x4 to Int8x16
func (from Uint32x4) AsInt8x16() (to Int8x16)

// Int16x8 converts from Uint32x4 to Int16x8
func (from Uint32x4) AsInt16x8() (to Int16x8)

// Int32x4 converts from Uint32x4 to Int32x4
func (from Uint32x4) AsInt32x4() (to Int32x4)

// Int64x2 converts from Uint32x4 to Int64x2
func (from Uint32x4) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Uint32x4 to Uint8x16
func (from Uint32x4) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Uint32x4 to Uint16x8
func (from Uint32x4) AsUint16x8() (to Uint16x8)

// Uint64x2 converts from Uint32x4 to Uint64x2
func (from Uint32x4) AsUint64x2() (to Uint64x2)

// Float32x8 converts from Uint32x8 to Float32x8
func (from Uint32x8) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Uint32x8 to Float64x4
func (from Uint32x8) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Uint32x8 to Int8x32
func (from Uint32x8) AsInt8x32() (to Int8x32)

// Int16x16 converts from Uint32x8 to Int16x16
func (from Uint32x8) AsInt16x16() (to Int16x16)

// Int32x8 converts from Uint32x8 to Int32x8
func (from Uint32x8) AsInt32x8() (to Int32x8)

// Int64x4 converts from Uint32x8 to Int64x4
func (from Uint32x8) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Uint32x8 to Uint8x32
func (from Uint32x8) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Uint32x8 to Uint16x16
func (from Uint32x8) AsUint16x16() (to Uint16x16)

// Uint64x4 converts from Uint32x8 to Uint64x4
func (from Uint32x8) AsUint64x4() (to Uint64x4)

// Float32x16 converts from Uint32x16 to Float32x16
func (from Uint32x16) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Uint32x16 to Float64x8
func (from Uint32x16) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Uint32x16 to Int8x64
func (from Uint32x16) AsInt8x64() (to Int8x64)

// Int16x32 converts from Uint32x16 to Int16x32
func (from Uint32x16) AsInt16x32() (to Int16x32)

// Int32x16 converts from Uint32x16 to Int32x16
func (from Uint32x16) AsInt32x16() (to Int32x16)

// Int64x8 converts from Uint32x16 to Int64x8
func (from Uint32x16) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Uint32x16 to Uint8x64
func (from Uint32x16) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Uint32x16 to Uint16x32
func (from Uint32x16) AsUint16x32() (to Uint16x32)

// Uint64x8 converts from Uint32x16 to Uint64x8
func (from Uint32x16) AsUint64x8() (to Uint64x8)

// Float32x4 converts from Uint64x2 to Float32x4
func (from Uint64x2) AsFloat32x4() (to Float32x4)

// Float64x2 converts from Uint64x2 to Float64x2
func (from Uint64x2) AsFloat64x2() (to Float64x2)

// Int8x16 converts from Uint64x2 to Int8x16
func (from Uint64x2) AsInt8x16() (to Int8x16)

// Int16x8 converts from Uint64x2 to Int16x8
func (from Uint64x2) AsInt16x8() (to Int16x8)

// Int32x4 converts from Uint64x2 to Int32x4
func (from Uint64x2) AsInt32x4() (to Int32x4)

// Int64x2 converts from Uint64x2 to Int64x2
func (from Uint64x2) AsInt64x2() (to Int64x2)

// Uint8x16 converts from Uint64x2 to Uint8x16
func (from Uint64x2) AsUint8x16() (to Uint8x16)

// Uint16x8 converts from Uint64x2 to Uint16x8
func (from Uint64x2) AsUint16x8() (to Uint16x8)

// Uint32x4 converts from Uint64x2 to Uint32x4
func (from Uint64x2) AsUint32x4() (to Uint32x4)

// Float32x8 converts from Uint64x4 to Float32x8
func (from Uint64x4) AsFloat32x8() (to Float32x8)

// Float64x4 converts from Uint64x4 to Float64x4
func (from Uint64x4) AsFloat64x4() (to Float64x4)

// Int8x32 converts from Uint64x4 to Int8x32
func (from Uint64x4) AsInt8x32() (to Int8x32)

// Int16x16 converts from Uint64x4 to Int16x16
func (from Uint64x4) AsInt16x16() (to Int16x16)

// Int32x8 converts from Uint64x4 to Int32x8
func (from Uint64x4) AsInt32x8() (to Int32x8)

// Int64x4 converts from Uint64x4 to Int64x4
func (from Uint64x4) AsInt64x4() (to Int64x4)

// Uint8x32 converts from Uint64x4 to Uint8x32
func (from Uint64x4) AsUint8x32() (to Uint8x32)

// Uint16x16 converts from Uint64x4 to Uint16x16
func (from Uint64x4) AsUint16x16() (to Uint16x16)

// Uint32x8 converts from Uint64x4 to Uint32x8
func (from Uint64x4) AsUint32x8() (to Uint32x8)

// Float32x16 converts from Uint64x8 to Float32x16
func (from Uint64x8) AsFloat32x16() (to Float32x16)

// Float64x8 converts from Uint64x8 to Float64x8
func (from Uint64x8) AsFloat64x8() (to Float64x8)

// Int8x64 converts from Uint64x8 to Int8x64
func (from Uint64x8) AsInt8x64() (to Int8x64)

// Int16x32 converts from Uint64x8 to Int16x32
func (from Uint64x8) AsInt16x32() (to Int16x32)

// Int32x16 converts from Uint64x8 to Int32x16
func (from Uint64x8) AsInt32x16() (to Int32x16)

// Int64x8 converts from Uint64x8 to Int64x8
func (from Uint64x8) AsInt64x8() (to Int64x8)

// Uint8x64 converts from Uint64x8 to Uint8x64
func (from Uint64x8) AsUint8x64() (to Uint8x64)

// Uint16x32 converts from Uint64x8 to Uint16x32
func (from Uint64x8) AsUint16x32() (to Uint16x32)

// Uint32x16 converts from Uint64x8 to Uint32x16
func (from Uint64x8) AsUint32x16() (to Uint32x16)

// AsInt8x16 converts from Mask8x16 to Int8x16
func (from Mask8x16) AsInt8x16() (to Int8x16)

// asMask converts from Int8x16 to Mask8x16
func (from Int8x16) asMask() (to Mask8x16)

func (x Mask8x16) And(y Mask8x16) Mask8x16

func (x Mask8x16) Or(y Mask8x16) Mask8x16

// AsInt8x32 converts from Mask8x32 to Int8x32
func (from Mask8x32) AsInt8x32() (to Int8x32)

// asMask converts from Int8x32 to Mask8x32
func (from Int8x32) asMask() (to Mask8x32)

func (x Mask8x32) And(y Mask8x32) Mask8x32

func (x Mask8x32) Or(y Mask8x32) Mask8x32

// AsInt8x64 converts from Mask8x64 to Int8x64
func (from Mask8x64) AsInt8x64() (to Int8x64)

// asMask converts from Int8x64 to Mask8x64
func (from Int8x64) asMask() (to Mask8x64)

func (x Mask8x64) And(y Mask8x64) Mask8x64

func (x Mask8x64) Or(y Mask8x64) Mask8x64

// AsInt16x8 converts from Mask16x8 to Int16x8
func (from Mask16x8) AsInt16x8() (to Int16x8)

// asMask converts from Int16x8 to Mask16x8
func (from Int16x8) asMask() (to Mask16x8)

func (x Mask16x8) And(y Mask16x8) Mask16x8

func (x Mask16x8) Or(y Mask16x8) Mask16x8

// AsInt16x16 converts from Mask16x16 to Int16x16
func (from Mask16x16) AsInt16x16() (to Int16x16)

// asMask converts from Int16x16 to Mask16x16
func (from Int16x16) asMask() (to Mask16x16)

func (x Mask16x16) And(y Mask16x16) Mask16x16

func (x Mask16x16) Or(y Mask16x16) Mask16x16

// AsInt16x32 converts from Mask16x32 to Int16x32
func (from Mask16x32) AsInt16x32() (to Int16x32)

// asMask converts from Int16x32 to Mask16x32
func (from Int16x32) asMask() (to Mask16x32)

func (x Mask16x32) And(y Mask16x32) Mask16x32

func (x Mask16x32) Or(y Mask16x32) Mask16x32

// AsInt32x4 converts from Mask32x4 to Int32x4
func (from Mask32x4) AsInt32x4() (to Int32x4)

// asMask converts from Int32x4 to Mask32x4
func (from Int32x4) asMask() (to Mask32x4)

func (x Mask32x4) And(y Mask32x4) Mask32x4

func (x Mask32x4) Or(y Mask32x4) Mask32x4

// AsInt32x8 converts from Mask32x8 to Int32x8
func (from Mask32x8) AsInt32x8() (to Int32x8)

// asMask converts from Int32x8 to Mask32x8
func (from Int32x8) asMask() (to Mask32x8)

func (x Mask32x8) And(y Mask32x8) Mask32x8

func (x Mask32x8) Or(y Mask32x8) Mask32x8

// AsInt32x16 converts from Mask32x16 to Int32x16
func (from Mask32x16) AsInt32x16() (to Int32x16)

// asMask converts from Int32x16 to Mask32x16
func (from Int32x16) asMask() (to Mask32x16)

func (x Mask32x16) And(y Mask32x16) Mask32x16

func (x Mask32x16) Or(y Mask32x16) Mask32x16

// AsInt64x2 converts from Mask64x2 to Int64x2
func (from Mask64x2) AsInt64x2() (to Int64x2)

// asMask converts from Int64x2 to Mask64x2
func (from Int64x2) asMask() (to Mask64x2)

func (x Mask64x2) And(y Mask64x2) Mask64x2

func (x Mask64x2) Or(y Mask64x2) Mask64x2

// AsInt64x4 converts from Mask64x4 to Int64x4
func (from Mask64x4) AsInt64x4() (to Int64x4)

// asMask converts from Int64x4 to Mask64x4
func (from Int64x4) asMask() (to Mask64x4)

func (x Mask64x4) And(y Mask64x4) Mask64x4

func (x Mask64x4) Or(y Mask64x4) Mask64x4

// AsInt64x8 converts from Mask64x8 to Int64x8
func (from Mask64x8) AsInt64x8() (to Int64x8)

// asMask converts from Int64x8 to Mask64x8
func (from Int64x8) asMask() (to Mask64x8)

func (x Mask64x8) And(y Mask64x8) Mask64x8

func (x Mask64x8) Or(y Mask64x8) Mask64x8