CppUtils/xbyak/xbyak.h

#pragma once
#ifndef XBYAK_XBYAK_H_
#define XBYAK_XBYAK_H_
/*!
	@file xbyak.h
	@brief Xbyak ; JIT assembler for x86(IA32)/x64 by C++
	@author herumi
	@url https://github.com/herumi/xbyak
	@note modified new BSD license
	http://opensource.org/licenses/BSD-3-Clause
*/
#if (not +0) && !defined(XBYAK_NO_OP_NAMES) // trick to detect whether 'not' is operator or not
	#define XBYAK_NO_OP_NAMES
#endif

#include <stdio.h> // for debug print
#include <assert.h>
#include <list>
#include <string>
#include <algorithm>
#ifndef NDEBUG
#include <iostream>
#endif

// #define XBYAK_DISABLE_AVX512

#if !defined(XBYAK_USE_MMAP_ALLOCATOR) && !defined(XBYAK_DONT_USE_MMAP_ALLOCATOR)
	#define XBYAK_USE_MMAP_ALLOCATOR
#endif
#if !defined(__GNUC__) || defined(__MINGW32__)
	#undef XBYAK_USE_MMAP_ALLOCATOR
#endif

#ifdef __GNUC__
	#define XBYAK_GNUC_PREREQ(major, minor) ((__GNUC__) * 100 + (__GNUC_MINOR__) >= (major) * 100 + (minor))
#else
	#define XBYAK_GNUC_PREREQ(major, minor) 0
#endif

// This covers -std=(gnu|c)++(0x|11|1y), -stdlib=libc++, and modern Microsoft.
#if ((defined(_MSC_VER) && (_MSC_VER >= 1600)) || defined(_LIBCPP_VERSION) ||\
	 			 ((__cplusplus >= 201103) || defined(__GXX_EXPERIMENTAL_CXX0X__)))
	#include <unordered_set>
	#define XBYAK_STD_UNORDERED_SET std::unordered_set
	#include <unordered_map>
	#define XBYAK_STD_UNORDERED_MAP std::unordered_map
	#define XBYAK_STD_UNORDERED_MULTIMAP std::unordered_multimap

/*
	Clang/llvm-gcc and ICC-EDG in 'GCC-mode' always claim to be GCC 4.2, using
	libstdcxx 20070719 (from GCC 4.2.1, the last GPL 2 version).
*/
#elif XBYAK_GNUC_PREREQ(4, 5) || (XBYAK_GNUC_PREREQ(4, 2) && __GLIBCXX__ >= 20070719) || defined(__INTEL_COMPILER) || defined(__llvm__)
	#include <tr1/unordered_set>
	#define XBYAK_STD_UNORDERED_SET std::tr1::unordered_set
	#include <tr1/unordered_map>
	#define XBYAK_STD_UNORDERED_MAP std::tr1::unordered_map
	#define XBYAK_STD_UNORDERED_MULTIMAP std::tr1::unordered_multimap

#elif defined(_MSC_VER) && (_MSC_VER >= 1500) && (_MSC_VER < 1600)
	#include <unordered_set>
	#define XBYAK_STD_UNORDERED_SET std::tr1::unordered_set
	#include <unordered_map>
	#define XBYAK_STD_UNORDERED_MAP std::tr1::unordered_map
	#define XBYAK_STD_UNORDERED_MULTIMAP std::tr1::unordered_multimap

#else
	#include <set>
	#define XBYAK_STD_UNORDERED_SET std::set
	#include <map>
	#define XBYAK_STD_UNORDERED_MAP std::map
	#define XBYAK_STD_UNORDERED_MULTIMAP std::multimap
#endif
#ifdef _WIN32
	#ifndef WIN32_LEAN_AND_MEAN
		#define WIN32_LEAN_AND_MEAN
	#endif
	#include <windows.h>
	#include <malloc.h>
	#define XBYAK_TLS __declspec(thread)
#elif defined(__GNUC__)
	#include <unistd.h>
	#include <sys/mman.h>
	#include <stdlib.h>
	#define XBYAK_TLS __thread
#endif
#if defined(__APPLE__) && !defined(XBYAK_DONT_USE_MAP_JIT)
	#define XBYAK_USE_MAP_JIT
	#include <sys/sysctl.h>
	#ifndef MAP_JIT
		#define MAP_JIT 0x800
	#endif
#endif
#if !defined(_MSC_VER) || (_MSC_VER >= 1600)
	#include <stdint.h>
#endif

#if !defined(MFD_CLOEXEC) // defined only linux 3.17 or later
	#undef XBYAK_USE_MEMFD
#endif

#if defined(_WIN64) || defined(__MINGW64__) || (defined(__CYGWIN__) && defined(__x86_64__))
	#define XBYAK64_WIN
#elif defined(__x86_64__)
	#define XBYAK64_GCC
#endif
#if !defined(XBYAK64) && !defined(XBYAK32)
	#if defined(XBYAK64_GCC) || defined(XBYAK64_WIN)
		#define XBYAK64
	#else
		#define XBYAK32
	#endif
#endif

#if (__cplusplus >= 201103) || (defined(_MSC_VER) && _MSC_VER >= 1800)
	#undef XBYAK_TLS
	#define XBYAK_TLS thread_local
	#define XBYAK_VARIADIC_TEMPLATE
	#define XBYAK_NOEXCEPT noexcept
#else
	#define XBYAK_NOEXCEPT throw()
#endif

// require c++14 or later
// Visual Studio 2017 version 15.0 or later
// g++-6 or later
#if ((__cplusplus >= 201402L) && !(!defined(__clang__) && defined(__GNUC__) && (__GNUC__ <= 5))) || (defined(_MSC_VER) && _MSC_VER >= 1910)
	#define XBYAK_CONSTEXPR constexpr
#else
	#define XBYAK_CONSTEXPR
#endif

#ifdef _MSC_VER
	#pragma warning(push)
	#pragma warning(disable : 4514) /* remove inline function */
	#pragma warning(disable : 4786) /* identifier is too long */
	#pragma warning(disable : 4503) /* name is too long */
	#pragma warning(disable : 4127) /* constant expresison */
#endif

namespace Xbyak {

enum {
	DEFAULT_MAX_CODE_SIZE = 4096,
	VERSION = 0x6010 /* 0xABCD = A.BC(D) */
};

#ifndef MIE_INTEGER_TYPE_DEFINED
#define MIE_INTEGER_TYPE_DEFINED
// for backward compatibility
typedef uint64_t uint64;
typedef int64_t sint64;
typedef uint32_t uint32;
typedef uint16_t uint16;
typedef uint8_t uint8;
#endif

#ifndef MIE_ALIGN
	#ifdef _MSC_VER
		#define MIE_ALIGN(x) __declspec(align(x))
	#else
		#define MIE_ALIGN(x) __attribute__((aligned(x)))
	#endif
#endif
#ifndef MIE_PACK // for shufps
	#define MIE_PACK(x, y, z, w) ((x) * 64 + (y) * 16 + (z) * 4 + (w))
#endif

enum {
	ERR_NONE = 0,
	ERR_BAD_ADDRESSING,
	ERR_CODE_IS_TOO_BIG,
	ERR_BAD_SCALE,
	ERR_ESP_CANT_BE_INDEX,
	ERR_BAD_COMBINATION,
	ERR_BAD_SIZE_OF_REGISTER,
	ERR_IMM_IS_TOO_BIG,
	ERR_BAD_ALIGN,
	ERR_LABEL_IS_REDEFINED,
	ERR_LABEL_IS_TOO_FAR,
	ERR_LABEL_IS_NOT_FOUND,
	ERR_CODE_ISNOT_COPYABLE,
	ERR_BAD_PARAMETER,
	ERR_CANT_PROTECT,
	ERR_CANT_USE_64BIT_DISP,
	ERR_OFFSET_IS_TOO_BIG,
	ERR_MEM_SIZE_IS_NOT_SPECIFIED,
	ERR_BAD_MEM_SIZE,
	ERR_BAD_ST_COMBINATION,
	ERR_OVER_LOCAL_LABEL, // not used
	ERR_UNDER_LOCAL_LABEL,
	ERR_CANT_ALLOC,
	ERR_ONLY_T_NEAR_IS_SUPPORTED_IN_AUTO_GROW,
	ERR_BAD_PROTECT_MODE,
	ERR_BAD_PNUM,
	ERR_BAD_TNUM,
	ERR_BAD_VSIB_ADDRESSING,
	ERR_CANT_CONVERT,
	ERR_LABEL_ISNOT_SET_BY_L,
	ERR_LABEL_IS_ALREADY_SET_BY_L,
	ERR_BAD_LABEL_STR,
	ERR_MUNMAP,
	ERR_OPMASK_IS_ALREADY_SET,
	ERR_ROUNDING_IS_ALREADY_SET,
	ERR_K0_IS_INVALID,
	ERR_EVEX_IS_INVALID,
	ERR_SAE_IS_INVALID,
	ERR_ER_IS_INVALID,
	ERR_INVALID_BROADCAST,
	ERR_INVALID_OPMASK_WITH_MEMORY,
	ERR_INVALID_ZERO,
	ERR_INVALID_RIP_IN_AUTO_GROW,
	ERR_INVALID_MIB_ADDRESS,
	ERR_X2APIC_IS_NOT_SUPPORTED,
	ERR_NOT_SUPPORTED,
	ERR_SAME_REGS_ARE_INVALID,
	ERR_INTERNAL // Put it at last.
};

inline const char *ConvertErrorToString(int err)
{
	static const char *errTbl[] = {
		"none",
		"bad addressing",
		"code is too big",
		"bad scale",
		"esp can't be index",
		"bad combination",
		"bad size of register",
		"imm is too big",
		"bad align",
		"label is redefined",
		"label is too far",
		"label is not found",
		"code is not copyable",
		"bad parameter",
		"can't protect",
		"can't use 64bit disp(use (void*))",
		"offset is too big",
		"MEM size is not specified",
		"bad mem size",
		"bad st combination",
		"over local label",
		"under local label",
		"can't alloc",
		"T_SHORT is not supported in AutoGrow",
		"bad protect mode",
		"bad pNum",
		"bad tNum",
		"bad vsib addressing",
		"can't convert",
		"label is not set by L()",
		"label is already set by L()",
		"bad label string",
		"err munmap",
		"opmask is already set",
		"rounding is already set",
		"k0 is invalid",
		"evex is invalid",
		"sae(suppress all exceptions) is invalid",
		"er(embedded rounding) is invalid",
		"invalid broadcast",
		"invalid opmask with memory",
		"invalid zero",
		"invalid rip in AutoGrow",
		"invalid mib address",
		"x2APIC is not supported",
		"not supported",
		"same regs are invalid",
		"internal error"
	};
	assert(ERR_INTERNAL + 1 == sizeof(errTbl) / sizeof(*errTbl));
	return err <= ERR_INTERNAL ? errTbl[err] : "unknown err";
}

#ifdef XBYAK_NO_EXCEPTION
namespace local {

inline int& GetErrorRef() {
	static XBYAK_TLS int err = 0;
	return err;
}

inline void SetError(int err) {
	if (local::GetErrorRef()) return; // keep the first err code
	local::GetErrorRef() = err;
}

} // local

inline void ClearError() {
	local::GetErrorRef() = 0;
}
inline int GetError() { return local::GetErrorRef(); }

#define XBYAK_THROW(err) { local::SetError(err); return; }
#define XBYAK_THROW_RET(err, r) { local::SetError(err); return r; }

#else
class Error : public std::exception {
	int err_;
public:
	explicit Error(int err) : err_(err)
	{
		if (err_ < 0 || err_ > ERR_INTERNAL) {
			err_ = ERR_INTERNAL;
		}
	}
	operator int() const { return err_; }
	const char *what() const XBYAK_NOEXCEPT
	{
		return ConvertErrorToString(err_);
	}
};

// dummy functions
inline void ClearError() { }
inline int GetError() { return 0; }

inline const char *ConvertErrorToString(const Error& err)
{
	return err.what();
}

#define XBYAK_THROW(err) { throw Error(err); }
#define XBYAK_THROW_RET(err, r) { throw Error(err); }

#endif

inline void *AlignedMalloc(size_t size, size_t alignment)
{
#ifdef __MINGW32__
	return __mingw_aligned_malloc(size, alignment);
#elif defined(_WIN32)
	return _aligned_malloc(size, alignment);
#else
	void *p;
	int ret = posix_memalign(&p, alignment, size);
	return (ret == 0) ? p : 0;
#endif
}

inline void AlignedFree(void *p)
{
#ifdef __MINGW32__
	__mingw_aligned_free(p);
#elif defined(_MSC_VER)
	_aligned_free(p);
#else
	free(p);
#endif
}

template<class To, class From>
inline const To CastTo(From p) XBYAK_NOEXCEPT
{
	return (const To)(size_t)(p);
}
namespace inner {

static const size_t ALIGN_PAGE_SIZE = 4096;

inline bool IsInDisp8(uint32_t x) { return 0xFFFFFF80 <= x || x <= 0x7F; }
inline bool IsInInt32(uint64_t x) { return ~uint64_t(0x7fffffffu) <= x || x <= 0x7FFFFFFFU; }

inline uint32_t VerifyInInt32(uint64_t x)
{
#ifdef XBYAK64
	if (!IsInInt32(x)) XBYAK_THROW_RET(ERR_OFFSET_IS_TOO_BIG, 0)
#endif
	return static_cast<uint32_t>(x);
}

enum LabelMode {
	LasIs, // as is
	Labs, // absolute
	LaddTop // (addr + top) for mov(reg, label) with AutoGrow
};

} // inner

/*
	custom allocator
*/
struct Allocator {
	virtual uint8_t *alloc(size_t size) { return reinterpret_cast<uint8_t*>(AlignedMalloc(size, inner::ALIGN_PAGE_SIZE)); }
	virtual void free(uint8_t *p) { AlignedFree(p); }
	virtual ~Allocator() {}
	/* override to return false if you call protect() manually */
	virtual bool useProtect() const { return true; }
};

#ifdef XBYAK_USE_MMAP_ALLOCATOR
#ifdef XBYAK_USE_MAP_JIT
namespace util {

inline int getMacOsVersionPure()
{
	char buf[64];
	size_t size = sizeof(buf);
	int err = sysctlbyname("kern.osrelease", buf, &size, NULL, 0);
	if (err != 0) return 0;
	char *endp;
	int major = strtol(buf, &endp, 10);
	if (*endp != '.') return 0;
	return major;
}

inline int getMacOsVersion()
{
	static const int version = getMacOsVersionPure();
	return version;
}

} // util
#endif
class MmapAllocator : Allocator {
	typedef XBYAK_STD_UNORDERED_MAP<uintptr_t, size_t> SizeList;
	SizeList sizeList_;
public:
	uint8_t *alloc(size_t size)
	{
		const size_t alignedSizeM1 = inner::ALIGN_PAGE_SIZE - 1;
		size = (size + alignedSizeM1) & ~alignedSizeM1;
#if defined(MAP_ANONYMOUS)
		int mode = MAP_PRIVATE | MAP_ANONYMOUS;
#elif defined(MAP_ANON)
		int mode = MAP_PRIVATE | MAP_ANON;
#else
		#error "not supported"
#endif
#if defined(XBYAK_USE_MAP_JIT)
		const int mojaveVersion = 18;
		if (util::getMacOsVersion() >= mojaveVersion) mode |= MAP_JIT;
#endif
		int fd = -1;
#if defined(XBYAK_USE_MEMFD)
		fd = memfd_create("xbyak", MFD_CLOEXEC);
		if (fd != -1) {
			mode = MAP_SHARED;
			if (ftruncate(fd, size) != 0) XBYAK_THROW_RET(ERR_CANT_ALLOC, 0)
		}
#endif
		void *p = mmap(NULL, size, PROT_READ | PROT_WRITE, mode, fd, 0);
#if defined(XBYAK_USE_MEMFD)
		if (fd != -1) close(fd);
#endif
		if (p == MAP_FAILED) XBYAK_THROW_RET(ERR_CANT_ALLOC, 0)
		assert(p);
		sizeList_[(uintptr_t)p] = size;
		return (uint8_t*)p;
	}
	void free(uint8_t *p)
	{
		if (p == 0) return;
		SizeList::iterator i = sizeList_.find((uintptr_t)p);
		if (i == sizeList_.end()) XBYAK_THROW(ERR_BAD_PARAMETER)
		if (munmap((void*)i->first, i->second) < 0) XBYAK_THROW(ERR_MUNMAP)
		sizeList_.erase(i);
	}
};
#endif

class Address;
class Reg;

class Operand {
	static const uint8_t EXT8BIT = 0x20;
	unsigned int idx_:6; // 0..31 + EXT8BIT = 1 if spl/bpl/sil/dil
	unsigned int kind_:10;
	unsigned int bit_:14;
protected:
	unsigned int zero_:1;
	unsigned int mask_:3;
	unsigned int rounding_:3;
	void setIdx(int idx) { idx_ = idx; }
public:
	enum Kind {
		NONE = 0,
		MEM = 1 << 0,
		REG = 1 << 1,
		MMX = 1 << 2,
		FPU = 1 << 3,
		XMM = 1 << 4,
		YMM = 1 << 5,
		ZMM = 1 << 6,
		OPMASK = 1 << 7,
		BNDREG = 1 << 8,
		TMM = 1 << 9
	};
	enum Code {
#ifdef XBYAK64
		RAX = 0, RCX, RDX, RBX, RSP, RBP, RSI, RDI, R8, R9, R10, R11, R12, R13, R14, R15,
		R8D = 8, R9D, R10D, R11D, R12D, R13D, R14D, R15D,
		R8W = 8, R9W, R10W, R11W, R12W, R13W, R14W, R15W,
		R8B = 8, R9B, R10B, R11B, R12B, R13B, R14B, R15B,
		SPL = 4, BPL, SIL, DIL,
#endif
		EAX = 0, ECX, EDX, EBX, ESP, EBP, ESI, EDI,
		AX = 0, CX, DX, BX, SP, BP, SI, DI,
		AL = 0, CL, DL, BL, AH, CH, DH, BH
	};
	XBYAK_CONSTEXPR Operand() : idx_(0), kind_(0), bit_(0), zero_(0), mask_(0), rounding_(0) { }
	XBYAK_CONSTEXPR Operand(int idx, Kind kind, int bit, bool ext8bit = 0)
		: idx_(static_cast<uint8_t>(idx | (ext8bit ? EXT8BIT : 0)))
		, kind_(kind)
		, bit_(bit)
		, zero_(0), mask_(0), rounding_(0)
	{
		assert((bit_ & (bit_ - 1)) == 0); // bit must be power of two
	}
	XBYAK_CONSTEXPR Kind getKind() const { return static_cast<Kind>(kind_); }
	XBYAK_CONSTEXPR int getIdx() const { return idx_ & (EXT8BIT - 1); }
	XBYAK_CONSTEXPR bool isNone() const { return kind_ == 0; }
	XBYAK_CONSTEXPR bool isMMX() const { return is(MMX); }
	XBYAK_CONSTEXPR bool isXMM() const { return is(XMM); }
	XBYAK_CONSTEXPR bool isYMM() const { return is(YMM); }
	XBYAK_CONSTEXPR bool isZMM() const { return is(ZMM); }
	XBYAK_CONSTEXPR bool isTMM() const { return is(TMM); }
	XBYAK_CONSTEXPR bool isXMEM() const { return is(XMM | MEM); }
	XBYAK_CONSTEXPR bool isYMEM() const { return is(YMM | MEM); }
	XBYAK_CONSTEXPR bool isZMEM() const { return is(ZMM | MEM); }
	XBYAK_CONSTEXPR bool isOPMASK() const { return is(OPMASK); }
	XBYAK_CONSTEXPR bool isBNDREG() const { return is(BNDREG); }
	XBYAK_CONSTEXPR bool isREG(int bit = 0) const { return is(REG, bit); }
	XBYAK_CONSTEXPR bool isMEM(int bit = 0) const { return is(MEM, bit); }
	XBYAK_CONSTEXPR bool isFPU() const { return is(FPU); }
	XBYAK_CONSTEXPR bool isExt8bit() const { return (idx_ & EXT8BIT) != 0; }
	XBYAK_CONSTEXPR bool isExtIdx() const { return (getIdx() & 8) != 0; }
	XBYAK_CONSTEXPR bool isExtIdx2() const { return (getIdx() & 16) != 0; }
	XBYAK_CONSTEXPR bool hasEvex() const { return isZMM() || isExtIdx2() || getOpmaskIdx() || getRounding(); }
	XBYAK_CONSTEXPR bool hasRex() const { return isExt8bit() || isREG(64) || isExtIdx(); }
	XBYAK_CONSTEXPR bool hasZero() const { return zero_; }
	XBYAK_CONSTEXPR int getOpmaskIdx() const { return mask_; }
	XBYAK_CONSTEXPR int getRounding() const { return rounding_; }
	void setKind(Kind kind)
	{
		if ((kind & (XMM|YMM|ZMM|TMM)) == 0) return;
		kind_ = kind;
		bit_ = kind == XMM ? 128 : kind == YMM ? 256 : kind == ZMM ? 512 : 8192;
	}
	// err if MMX/FPU/OPMASK/BNDREG
	void setBit(int bit);
	void setOpmaskIdx(int idx, bool /*ignore_idx0*/ = true)
	{
		if (mask_) XBYAK_THROW(ERR_OPMASK_IS_ALREADY_SET)
		mask_ = idx;
	}
	void setRounding(int idx)
	{
		if (rounding_) XBYAK_THROW(ERR_ROUNDING_IS_ALREADY_SET)
		rounding_ = idx;
	}
	void setZero() { zero_ = true; }
	// ah, ch, dh, bh?
	bool isHigh8bit() const
	{
		if (!isBit(8)) return false;
		if (isExt8bit()) return false;
		const int idx = getIdx();
		return AH <= idx && idx <= BH;
	}
	// any bit is accetable if bit == 0
	XBYAK_CONSTEXPR bool is(int kind, uint32_t bit = 0) const
	{
		return (kind == 0 || (kind_ & kind)) && (bit == 0 || (bit_ & bit)); // cf. you can set (8|16)
	}
	XBYAK_CONSTEXPR bool isBit(uint32_t bit) const { return (bit_ & bit) != 0; }
	XBYAK_CONSTEXPR uint32_t getBit() const { return bit_; }
	const char *toString() const
	{
		const int idx = getIdx();
		if (kind_ == REG) {
			if (isExt8bit()) {
				static const char *tbl[4] = { "spl", "bpl", "sil", "dil" };
				return tbl[idx - 4];
			}
			static const char *tbl[4][16] = {
				{ "al", "cl", "dl", "bl", "ah", "ch", "dh", "bh", "r8b", "r9b", "r10b",  "r11b", "r12b", "r13b", "r14b", "r15b" },
				{ "ax", "cx", "dx", "bx", "sp", "bp", "si", "di", "r8w", "r9w", "r10w",  "r11w", "r12w", "r13w", "r14w", "r15w" },
				{ "eax", "ecx", "edx", "ebx", "esp", "ebp", "esi", "edi", "r8d", "r9d", "r10d",  "r11d", "r12d", "r13d", "r14d", "r15d" },
				{ "rax", "rcx", "rdx", "rbx", "rsp", "rbp", "rsi", "rdi", "r8", "r9", "r10",  "r11", "r12", "r13", "r14", "r15" },
			};
			return tbl[bit_ == 8 ? 0 : bit_ == 16 ? 1 : bit_ == 32 ? 2 : 3][idx];
		} else if (isOPMASK()) {
			static const char *tbl[8] = { "k0", "k1", "k2", "k3", "k4", "k5", "k6", "k7" };
			return tbl[idx];
		} else if (isTMM()) {
			static const char *tbl[8] = {
				"tmm0", "tmm1", "tmm2", "tmm3", "tmm4", "tmm5", "tmm6", "tmm7"
			};
			return tbl[idx];
		} else if (isZMM()) {
			static const char *tbl[32] = {
				"zmm0", "zmm1", "zmm2", "zmm3", "zmm4", "zmm5", "zmm6", "zmm7", "zmm8", "zmm9", "zmm10", "zmm11", "zmm12", "zmm13", "zmm14", "zmm15",
				"zmm16", "zmm17", "zmm18", "zmm19", "zmm20", "zmm21", "zmm22", "zmm23", "zmm24", "zmm25", "zmm26", "zmm27", "zmm28", "zmm29", "zmm30", "zmm31"
			};
			return tbl[idx];
		} else if (isYMM()) {
			static const char *tbl[32] = {
				"ymm0", "ymm1", "ymm2", "ymm3", "ymm4", "ymm5", "ymm6", "ymm7", "ymm8", "ymm9", "ymm10", "ymm11", "ymm12", "ymm13", "ymm14", "ymm15",
				"ymm16", "ymm17", "ymm18", "ymm19", "ymm20", "ymm21", "ymm22", "ymm23", "ymm24", "ymm25", "ymm26", "ymm27", "ymm28", "ymm29", "ymm30", "ymm31"
			};
			return tbl[idx];
		} else if (isXMM()) {
			static const char *tbl[32] = {
				"xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5", "xmm6", "xmm7", "xmm8", "xmm9", "xmm10", "xmm11", "xmm12", "xmm13", "xmm14", "xmm15",
				"xmm16", "xmm17", "xmm18", "xmm19", "xmm20", "xmm21", "xmm22", "xmm23", "xmm24", "xmm25", "xmm26", "xmm27", "xmm28", "xmm29", "xmm30", "xmm31"
			};
			return tbl[idx];
		} else if (isMMX()) {
			static const char *tbl[8] = { "mm0", "mm1", "mm2", "mm3", "mm4", "mm5", "mm6", "mm7" };
			return tbl[idx];
		} else if (isFPU()) {
			static const char *tbl[8] = { "st0", "st1", "st2", "st3", "st4", "st5", "st6", "st7" };
			return tbl[idx];
		} else if (isBNDREG()) {
			static const char *tbl[4] = { "bnd0", "bnd1", "bnd2", "bnd3" };
			return tbl[idx];
		}
		XBYAK_THROW_RET(ERR_INTERNAL, 0);
	}
	bool isEqualIfNotInherited(const Operand& rhs) const { return idx_ == rhs.idx_ && kind_ == rhs.kind_ && bit_ == rhs.bit_ && zero_ == rhs.zero_ && mask_ == rhs.mask_ && rounding_ == rhs.rounding_; }
	bool operator==(const Operand& rhs) const;
	bool operator!=(const Operand& rhs) const { return !operator==(rhs); }
	const Address& getAddress() const;
	const Reg& getReg() const;
};

inline void Operand::setBit(int bit)
{
	if (bit != 8 && bit != 16 && bit != 32 && bit != 64 && bit != 128 && bit != 256 && bit != 512 && bit != 8192) goto ERR;
	if (isBit(bit)) return;
	if (is(MEM | OPMASK)) {
		bit_ = bit;
		return;
	}
	if (is(REG | XMM | YMM | ZMM | TMM)) {
		int idx = getIdx();
		// err if converting ah, bh, ch, dh
		if (isREG(8) && (4 <= idx && idx < 8) && !isExt8bit()) goto ERR;
		Kind kind = REG;
		switch (bit) {
		case 8:
			if (idx >= 16) goto ERR;
#ifdef XBYAK32
			if (idx >= 4) goto ERR;
#else
			if (4 <= idx && idx < 8) idx |= EXT8BIT;
#endif
			break;
		case 16:
		case 32:
		case 64:
			if (idx >= 16) goto ERR;
			break;
		case 128: kind = XMM; break;
		case 256: kind = YMM; break;
		case 512: kind = ZMM; break;
		case 8192: kind = TMM; break;
		}
		idx_ = idx;
		kind_ = kind;
		bit_ = bit;
		if (bit >= 128) return; // keep mask_ and rounding_
		mask_ = 0;
		rounding_ = 0;
		return;
	}
ERR:
	XBYAK_THROW(ERR_CANT_CONVERT)
}

class Label;

struct Reg8;
struct Reg16;
struct Reg32;
#ifdef XBYAK64
struct Reg64;
#endif
class Reg : public Operand {
public:
	XBYAK_CONSTEXPR Reg() { }
	XBYAK_CONSTEXPR Reg(int idx, Kind kind, int bit = 0, bool ext8bit = false) : Operand(idx, kind, bit, ext8bit) { }
	// convert to Reg8/Reg16/Reg32/Reg64/XMM/YMM/ZMM
	Reg changeBit(int bit) const { Reg r(*this); r.setBit(bit); return r; }
	uint8_t getRexW() const { return isREG(64) ? 8 : 0; }
	uint8_t getRexR() const { return isExtIdx() ? 4 : 0; }
	uint8_t getRexX() const { return isExtIdx() ? 2 : 0; }
	uint8_t getRexB() const { return isExtIdx() ? 1 : 0; }
	uint8_t getRex(const Reg& base = Reg()) const
	{
		uint8_t rex = getRexW() | getRexR() | base.getRexW() | base.getRexB();
		if (rex || isExt8bit() || base.isExt8bit()) rex |= 0x40;
		return rex;
	}
	Reg8 cvt8() const;
	Reg16 cvt16() const;
	Reg32 cvt32() const;
#ifdef XBYAK64
	Reg64 cvt64() const;
#endif
};

inline const Reg& Operand::getReg() const
{
	assert(!isMEM());
	return static_cast<const Reg&>(*this);
}

struct Reg8 : public Reg {
	explicit XBYAK_CONSTEXPR Reg8(int idx = 0, bool ext8bit = false) : Reg(idx, Operand::REG, 8, ext8bit) { }
};

struct Reg16 : public Reg {
	explicit XBYAK_CONSTEXPR Reg16(int idx = 0) : Reg(idx, Operand::REG, 16) { }
};

struct Mmx : public Reg {
	explicit XBYAK_CONSTEXPR Mmx(int idx = 0, Kind kind = Operand::MMX, int bit = 64) : Reg(idx, kind, bit) { }
};

struct EvexModifierRounding {
	enum {
		T_RN_SAE = 1,
		T_RD_SAE = 2,
		T_RU_SAE = 3,
		T_RZ_SAE = 4,
		T_SAE = 5
	};
	explicit XBYAK_CONSTEXPR EvexModifierRounding(int rounding) : rounding(rounding) {}
	int rounding;
};
struct EvexModifierZero{ XBYAK_CONSTEXPR EvexModifierZero() {}};

struct Xmm : public Mmx {
	explicit XBYAK_CONSTEXPR Xmm(int idx = 0, Kind kind = Operand::XMM, int bit = 128) : Mmx(idx, kind, bit) { }
	XBYAK_CONSTEXPR Xmm(Kind kind, int idx) : Mmx(idx, kind, kind == XMM ? 128 : kind == YMM ? 256 : 512) { }
	Xmm operator|(const EvexModifierRounding& emr) const { Xmm r(*this); r.setRounding(emr.rounding); return r; }
	Xmm copyAndSetIdx(int idx) const { Xmm ret(*this); ret.setIdx(idx); return ret; }
	Xmm copyAndSetKind(Operand::Kind kind) const { Xmm ret(*this); ret.setKind(kind); return ret; }
};

struct Ymm : public Xmm {
	explicit XBYAK_CONSTEXPR Ymm(int idx = 0, Kind kind = Operand::YMM, int bit = 256) : Xmm(idx, kind, bit) { }
	Ymm operator|(const EvexModifierRounding& emr) const { Ymm r(*this); r.setRounding(emr.rounding); return r; }
};

struct Zmm : public Ymm {
	explicit XBYAK_CONSTEXPR Zmm(int idx = 0) : Ymm(idx, Operand::ZMM, 512) { }
	Zmm operator|(const EvexModifierRounding& emr) const { Zmm r(*this); r.setRounding(emr.rounding); return r; }
};

#ifdef XBYAK64
struct Tmm : public Reg {
	explicit XBYAK_CONSTEXPR Tmm(int idx = 0, Kind kind = Operand::TMM, int bit = 8192) : Reg(idx, kind, bit) { }
};
#endif

struct Opmask : public Reg {
	explicit XBYAK_CONSTEXPR Opmask(int idx = 0) : Reg(idx, Operand::OPMASK, 64) {}
};

struct BoundsReg : public Reg {
	explicit XBYAK_CONSTEXPR BoundsReg(int idx = 0) : Reg(idx, Operand::BNDREG, 128) {}
};

template<class T>T operator|(const T& x, const Opmask& k) { T r(x); r.setOpmaskIdx(k.getIdx()); return r; }
template<class T>T operator|(const T& x, const EvexModifierZero&) { T r(x); r.setZero(); return r; }
template<class T>T operator|(const T& x, const EvexModifierRounding& emr) { T r(x); r.setRounding(emr.rounding); return r; }

struct Fpu : public Reg {
	explicit XBYAK_CONSTEXPR Fpu(int idx = 0) : Reg(idx, Operand::FPU, 32) { }
};

struct Reg32e : public Reg {
	explicit XBYAK_CONSTEXPR Reg32e(int idx, int bit) : Reg(idx, Operand::REG, bit) {}
};
struct Reg32 : public Reg32e {
	explicit XBYAK_CONSTEXPR Reg32(int idx = 0) : Reg32e(idx, 32) {}
};
#ifdef XBYAK64
struct Reg64 : public Reg32e {
	explicit XBYAK_CONSTEXPR Reg64(int idx = 0) : Reg32e(idx, 64) {}
};
struct RegRip {
	int64_t disp_;
	const Label* label_;
	bool isAddr_;
	explicit XBYAK_CONSTEXPR RegRip(int64_t disp = 0, const Label* label = 0, bool isAddr = false) : disp_(disp), label_(label), isAddr_(isAddr) {}
	friend const RegRip operator+(const RegRip& r, int disp) {
		return RegRip(r.disp_ + disp, r.label_, r.isAddr_);
	}
	friend const RegRip operator-(const RegRip& r, int disp) {
		return RegRip(r.disp_ - disp, r.label_, r.isAddr_);
	}
	friend const RegRip operator+(const RegRip& r, int64_t disp) {
		return RegRip(r.disp_ + disp, r.label_, r.isAddr_);
	}
	friend const RegRip operator-(const RegRip& r, int64_t disp) {
		return RegRip(r.disp_ - disp, r.label_, r.isAddr_);
	}
	friend const RegRip operator+(const RegRip& r, const Label& label) {
		if (r.label_ || r.isAddr_) XBYAK_THROW_RET(ERR_BAD_ADDRESSING, RegRip());
		return RegRip(r.disp_, &label);
	}
	friend const RegRip operator+(const RegRip& r, const void *addr) {
		if (r.label_ || r.isAddr_) XBYAK_THROW_RET(ERR_BAD_ADDRESSING, RegRip());
		return RegRip(r.disp_ + (int64_t)addr, 0, true);
	}
};
#endif

inline Reg8 Reg::cvt8() const
{
	Reg r = changeBit(8); return Reg8(r.getIdx(), r.isExt8bit());
}

inline Reg16 Reg::cvt16() const
{
	return Reg16(changeBit(16).getIdx());
}

inline Reg32 Reg::cvt32() const
{
	return Reg32(changeBit(32).getIdx());
}

#ifdef XBYAK64
inline Reg64 Reg::cvt64() const
{
	return Reg64(changeBit(64).getIdx());
}
#endif

#ifndef XBYAK_DISABLE_SEGMENT
// not derived from Reg
class Segment {
	int idx_;
public:
	enum {
		es, cs, ss, ds, fs, gs
	};
	explicit XBYAK_CONSTEXPR Segment(int idx) : idx_(idx) { assert(0 <= idx_ && idx_ < 6); }
	int getIdx() const { return idx_; }
	const char *toString() const
	{
		static const char tbl[][3] = {
			"es", "cs", "ss", "ds", "fs", "gs"
		};
		return tbl[idx_];
	}
};
#endif

class RegExp {
public:
#ifdef XBYAK64
	enum { i32e = 32 | 64 };
#else
	enum { i32e = 32 };
#endif
	XBYAK_CONSTEXPR RegExp(size_t disp = 0) : scale_(0), disp_(disp) { }
	XBYAK_CONSTEXPR RegExp(const Reg& r, int scale = 1)
		: scale_(scale)
		, disp_(0)
	{
		if (!r.isREG(i32e) && !r.is(Reg::XMM|Reg::YMM|Reg::ZMM|Reg::TMM)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		if (scale == 0) return;
		if (scale != 1 && scale != 2 && scale != 4 && scale != 8) XBYAK_THROW(ERR_BAD_SCALE)
		if (r.getBit() >= 128 || scale != 1) { // xmm/ymm is always index
			index_ = r;
		} else {
			base_ = r;
		}
	}
	bool isVsib(int bit = 128 | 256 | 512) const { return index_.isBit(bit); }
	RegExp optimize() const
	{
		RegExp exp = *this;
		// [reg * 2] => [reg + reg]
		if (index_.isBit(i32e) && !base_.getBit() && scale_ == 2) {
			exp.base_ = index_;
			exp.scale_ = 1;
		}
		return exp;
	}
	bool operator==(const RegExp& rhs) const
	{
		return base_ == rhs.base_ && index_ == rhs.index_ && disp_ == rhs.disp_ && scale_ == rhs.scale_;
	}
	const Reg& getBase() const { return base_; }
	const Reg& getIndex() const { return index_; }
	int getScale() const { return scale_; }
	size_t getDisp() const { return disp_; }
	XBYAK_CONSTEXPR void verify() const
	{
		if (base_.getBit() >= 128) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		if (index_.getBit() && index_.getBit() <= 64) {
			if (index_.getIdx() == Operand::ESP) XBYAK_THROW(ERR_ESP_CANT_BE_INDEX)
			if (base_.getBit() && base_.getBit() != index_.getBit()) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		}
	}
	friend RegExp operator+(const RegExp& a, const RegExp& b);
	friend RegExp operator-(const RegExp& e, size_t disp);
	uint8_t getRex() const
	{
		uint8_t rex = index_.getRexX() | base_.getRexB();
		return rex ? uint8_t(rex | 0x40) : 0;
	}
private:
	/*
		[base_ + index_ * scale_ + disp_]
		base : Reg32e, index : Reg32e(w/o esp), Xmm, Ymm
	*/
	Reg base_;
	Reg index_;
	int scale_;
	size_t disp_;
};

inline RegExp operator+(const RegExp& a, const RegExp& b)
{
	if (a.index_.getBit() && b.index_.getBit()) XBYAK_THROW_RET(ERR_BAD_ADDRESSING, RegExp())
	RegExp ret = a;
	if (!ret.index_.getBit()) { ret.index_ = b.index_; ret.scale_ = b.scale_; }
	if (b.base_.getBit()) {
		if (ret.base_.getBit()) {
			if (ret.index_.getBit()) XBYAK_THROW_RET(ERR_BAD_ADDRESSING, RegExp())
			// base + base => base + index * 1
			ret.index_ = b.base_;
			// [reg + esp] => [esp + reg]
			if (ret.index_.getIdx() == Operand::ESP) std::swap(ret.base_, ret.index_);
			ret.scale_ = 1;
		} else {
			ret.base_ = b.base_;
		}
	}
	ret.disp_ += b.disp_;
	return ret;
}
inline RegExp operator*(const Reg& r, int scale)
{
	return RegExp(r, scale);
}
inline RegExp operator*(int scale, const Reg& r)
{
	return r * scale;
}
inline RegExp operator-(const RegExp& e, size_t disp)
{
	RegExp ret = e;
	ret.disp_ -= disp;
	return ret;
}

// 2nd parameter for constructor of CodeArray(maxSize, userPtr, alloc)
void *const AutoGrow = (void*)1; //-V566
void *const DontSetProtectRWE = (void*)2; //-V566

class CodeArray {
	enum Type {
		USER_BUF = 1, // use userPtr(non alignment, non protect)
		ALLOC_BUF, // use new(alignment, protect)
		AUTO_GROW // automatically move and grow memory if necessary
	};
	CodeArray(const CodeArray& rhs);
	void operator=(const CodeArray&);
	bool isAllocType() const { return type_ == ALLOC_BUF || type_ == AUTO_GROW; }
	struct AddrInfo {
		size_t codeOffset; // position to write
		size_t jmpAddr; // value to write
		int jmpSize; // size of jmpAddr
		inner::LabelMode mode;
		AddrInfo(size_t _codeOffset, size_t _jmpAddr, int _jmpSize, inner::LabelMode _mode)
			: codeOffset(_codeOffset), jmpAddr(_jmpAddr), jmpSize(_jmpSize), mode(_mode) {}
		uint64_t getVal(const uint8_t *top) const
		{
			uint64_t disp = (mode == inner::LaddTop) ? jmpAddr + size_t(top) : (mode == inner::LasIs) ? jmpAddr : jmpAddr - size_t(top);
			if (jmpSize == 4) disp = inner::VerifyInInt32(disp);
			return disp;
		}
	};
	typedef std::list<AddrInfo> AddrInfoList;
	AddrInfoList addrInfoList_;
	const Type type_;
#ifdef XBYAK_USE_MMAP_ALLOCATOR
	MmapAllocator defaultAllocator_;
#else
	Allocator defaultAllocator_;
#endif
	Allocator *alloc_;
protected:
	size_t maxSize_;
	uint8_t *top_;
	size_t size_;
	bool isCalledCalcJmpAddress_;

	bool useProtect() const { return alloc_->useProtect(); }
	/*
		allocate new memory and copy old data to the new area
	*/
	void growMemory()
	{
		const size_t newSize = (std::max<size_t>)(DEFAULT_MAX_CODE_SIZE, maxSize_ * 2);
		uint8_t *newTop = alloc_->alloc(newSize);
		if (newTop == 0) XBYAK_THROW(ERR_CANT_ALLOC)
		for (size_t i = 0; i < size_; i++) newTop[i] = top_[i];
		alloc_->free(top_);
		top_ = newTop;
		maxSize_ = newSize;
	}
	/*
		calc jmp address for AutoGrow mode
	*/
	void calcJmpAddress()
	{
		if (isCalledCalcJmpAddress_) return;
		for (AddrInfoList::const_iterator i = addrInfoList_.begin(), ie = addrInfoList_.end(); i != ie; ++i) {
			uint64_t disp = i->getVal(top_);
			rewrite(i->codeOffset, disp, i->jmpSize);
		}
		isCalledCalcJmpAddress_ = true;
	}
public:
	enum ProtectMode {
		PROTECT_RW = 0, // read/write
		PROTECT_RWE = 1, // read/write/exec
		PROTECT_RE = 2 // read/exec
	};
	explicit CodeArray(size_t maxSize, void *userPtr = 0, Allocator *allocator = 0)
		: type_(userPtr == AutoGrow ? AUTO_GROW : (userPtr == 0 || userPtr == DontSetProtectRWE) ? ALLOC_BUF : USER_BUF)
		, alloc_(allocator ? allocator : (Allocator*)&defaultAllocator_)
		, maxSize_(maxSize)
		, top_(type_ == USER_BUF ? reinterpret_cast<uint8_t*>(userPtr) : alloc_->alloc((std::max<size_t>)(maxSize, 1)))
		, size_(0)
		, isCalledCalcJmpAddress_(false)
	{
		if (maxSize_ > 0 && top_ == 0) XBYAK_THROW(ERR_CANT_ALLOC)
		if ((type_ == ALLOC_BUF && userPtr != DontSetProtectRWE && useProtect()) && !setProtectMode(PROTECT_RWE, false)) {
			alloc_->free(top_);
			XBYAK_THROW(ERR_CANT_PROTECT)
		}
	}
	virtual ~CodeArray()
	{
		if (isAllocType()) {
			if (useProtect()) setProtectModeRW(false);
			alloc_->free(top_);
		}
	}
	bool setProtectMode(ProtectMode mode, bool throwException = true)
	{
		bool isOK = protect(top_, maxSize_, mode);
		if (isOK) return true;
		if (throwException) XBYAK_THROW_RET(ERR_CANT_PROTECT, false)
		return false;
	}
	bool setProtectModeRE(bool throwException = true) { return setProtectMode(PROTECT_RE, throwException); }
	bool setProtectModeRW(bool throwException = true) { return setProtectMode(PROTECT_RW, throwException); }
	void resetSize()
	{
		size_ = 0;
		addrInfoList_.clear();
		isCalledCalcJmpAddress_ = false;
	}
	void db(int code)
	{
		if (size_ >= maxSize_) {
			if (type_ == AUTO_GROW) {
				growMemory();
			} else {
				XBYAK_THROW(ERR_CODE_IS_TOO_BIG)
			}
		}
		top_[size_++] = static_cast<uint8_t>(code);
	}
	void db(const uint8_t *code, size_t codeSize)
	{
		for (size_t i = 0; i < codeSize; i++) db(code[i]);
	}
	void db(uint64_t code, size_t codeSize)
	{
		if (codeSize > 8) XBYAK_THROW(ERR_BAD_PARAMETER)
		for (size_t i = 0; i < codeSize; i++) db(static_cast<uint8_t>(code >> (i * 8)));
	}
	void dw(uint32_t code) { db(code, 2); }
	void dd(uint32_t code) { db(code, 4); }
	void dq(uint64_t code) { db(code, 8); }
	const uint8_t *getCode() const { return top_; }
	template<class F>
	const F getCode() const { return reinterpret_cast<F>(top_); }
	const uint8_t *getCurr() const { return &top_[size_]; }
	template<class F>
	const F getCurr() const { return reinterpret_cast<F>(&top_[size_]); }
	size_t getSize() const { return size_; }
	void setSize(size_t size)
	{
		if (size > maxSize_) XBYAK_THROW(ERR_OFFSET_IS_TOO_BIG)
		size_ = size;
	}
	void dump() const
	{
		const uint8_t *p = getCode();
		size_t bufSize = getSize();
		size_t remain = bufSize;
		for (int i = 0; i < 4; i++) {
			size_t disp = 16;
			if (remain < 16) {
				disp = remain;
			}
			for (size_t j = 0; j < 16; j++) {
				if (j < disp) {
					printf("%02X", p[i * 16 + j]);
				}
			}
			putchar('\n');
			remain -= disp;
			if (remain == 0) {
				break;
			}
		}
	}
	/*
		@param offset [in] offset from top
		@param disp [in] offset from the next of jmp
		@param size [in] write size(1, 2, 4, 8)
	*/
	void rewrite(size_t offset, uint64_t disp, size_t size)
	{
		assert(offset < maxSize_);
		if (size != 1 && size != 2 && size != 4 && size != 8) XBYAK_THROW(ERR_BAD_PARAMETER)
		uint8_t *const data = top_ + offset;
		for (size_t i = 0; i < size; i++) {
			data[i] = static_cast<uint8_t>(disp >> (i * 8));
		}
	}
	void save(size_t offset, size_t val, int size, inner::LabelMode mode)
	{
		addrInfoList_.push_back(AddrInfo(offset, val, size, mode));
	}
	bool isAutoGrow() const { return type_ == AUTO_GROW; }
	bool isCalledCalcJmpAddress() const { return isCalledCalcJmpAddress_; }
	/**
		change exec permission of memory
		@param addr [in] buffer address
		@param size [in] buffer size
		@param protectMode [in] mode(RW/RWE/RE)
		@return true(success), false(failure)
	*/
	static inline bool protect(const void *addr, size_t size, int protectMode)
	{
#if defined(_WIN32)
		const DWORD c_rw = PAGE_READWRITE;
		const DWORD c_rwe = PAGE_EXECUTE_READWRITE;
		const DWORD c_re = PAGE_EXECUTE_READ;
		DWORD mode;
#else
		const int c_rw = PROT_READ | PROT_WRITE;
		const int c_rwe = PROT_READ | PROT_WRITE | PROT_EXEC;
		const int c_re = PROT_READ | PROT_EXEC;
		int mode;
#endif
		switch (protectMode) {
		case PROTECT_RW: mode = c_rw; break;
		case PROTECT_RWE: mode = c_rwe; break;
		case PROTECT_RE: mode = c_re; break;
		default:
			return false;
		}
#if defined(_WIN32)
		DWORD oldProtect;
		return VirtualProtect(const_cast<void*>(addr), size, mode, &oldProtect) != 0;
#elif defined(__GNUC__)
		size_t pageSize = sysconf(_SC_PAGESIZE);
		size_t iaddr = reinterpret_cast<size_t>(addr);
		size_t roundAddr = iaddr & ~(pageSize - static_cast<size_t>(1));
#ifndef NDEBUG
		if (pageSize != 4096) fprintf(stderr, "large page(%zd) is used. not tested enough.\n", pageSize);
#endif
		return mprotect(reinterpret_cast<void*>(roundAddr), size + (iaddr - roundAddr), mode) == 0;
#else
		return true;
#endif
	}
	/**
		get aligned memory pointer
		@param addr [in] address
		@param alignedSize [in] power of two
		@return aligned addr by alingedSize
	*/
	static inline uint8_t *getAlignedAddress(uint8_t *addr, size_t alignedSize = 16)
	{
		return reinterpret_cast<uint8_t*>((reinterpret_cast<size_t>(addr) + alignedSize - 1) & ~(alignedSize - static_cast<size_t>(1)));
	}
};

class Address : public Operand {
public:
	enum Mode {
		M_ModRM,
		M_64bitDisp,
		M_rip,
		M_ripAddr
	};
	XBYAK_CONSTEXPR Address(uint32_t sizeBit, bool broadcast, const RegExp& e)
		: Operand(0, MEM, sizeBit), e_(e), label_(0), mode_(M_ModRM), broadcast_(broadcast)
	{
		e_.verify();
	}
#ifdef XBYAK64
	explicit XBYAK_CONSTEXPR Address(size_t disp)
		: Operand(0, MEM, 64), e_(disp), label_(0), mode_(M_64bitDisp), broadcast_(false){ }
	XBYAK_CONSTEXPR Address(uint32_t sizeBit, bool broadcast, const RegRip& addr)
		: Operand(0, MEM, sizeBit), e_(addr.disp_), label_(addr.label_), mode_(addr.isAddr_ ? M_ripAddr : M_rip), broadcast_(broadcast) { }
#endif
	RegExp getRegExp(bool optimize = true) const
	{
		return optimize ? e_.optimize() : e_;
	}
	Mode getMode() const { return mode_; }
	bool is32bit() const { return e_.getBase().getBit() == 32 || e_.getIndex().getBit() == 32; }
	bool isOnlyDisp() const { return !e_.getBase().getBit() && !e_.getIndex().getBit(); } // for mov eax
	size_t getDisp() const { return e_.getDisp(); }
	uint8_t getRex() const
	{
		if (mode_ != M_ModRM) return 0;
		return getRegExp().getRex();
	}
	bool is64bitDisp() const { return mode_ == M_64bitDisp; } // for moffset
	bool isBroadcast() const { return broadcast_; }
	const Label* getLabel() const { return label_; }
	bool operator==(const Address& rhs) const
	{
		return getBit() == rhs.getBit() && e_ == rhs.e_ && label_ == rhs.label_ && mode_ == rhs.mode_ && broadcast_ == rhs.broadcast_;
	}
	bool operator!=(const Address& rhs) const { return !operator==(rhs); }
	bool isVsib() const { return e_.isVsib(); }
private:
	RegExp e_;
	const Label* label_;
	Mode mode_;
	bool broadcast_;
};

inline const Address& Operand::getAddress() const
{
	assert(isMEM());
	return static_cast<const Address&>(*this);
}

inline bool Operand::operator==(const Operand& rhs) const
{
	if (isMEM() && rhs.isMEM()) return this->getAddress() == rhs.getAddress();
	return isEqualIfNotInherited(rhs);
}

class AddressFrame {
	void operator=(const AddressFrame&);
	AddressFrame(const AddressFrame&);
public:
	const uint32_t bit_;
	const bool broadcast_;
	explicit XBYAK_CONSTEXPR AddressFrame(uint32_t bit, bool broadcast = false) : bit_(bit), broadcast_(broadcast) { }
	Address operator[](const RegExp& e) const
	{
		return Address(bit_, broadcast_, e);
	}
	Address operator[](const void *disp) const
	{
		return Address(bit_, broadcast_, RegExp(reinterpret_cast<size_t>(disp)));
	}
#ifdef XBYAK64
	Address operator[](uint64_t disp) const { return Address(disp); }
	Address operator[](const RegRip& addr) const { return Address(bit_, broadcast_, addr); }
#endif
};

struct JmpLabel {
	size_t endOfJmp; /* offset from top to the end address of jmp */
	int jmpSize;
	inner::LabelMode mode;
	size_t disp; // disp for [rip + disp]
	explicit JmpLabel(size_t endOfJmp = 0, int jmpSize = 0, inner::LabelMode mode = inner::LasIs, size_t disp = 0)
		: endOfJmp(endOfJmp), jmpSize(jmpSize), mode(mode), disp(disp)
	{
	}
};

class LabelManager;

class Label {
	mutable LabelManager *mgr;
	mutable int id;
	friend class LabelManager;
public:
	Label() : mgr(0), id(0) {}
	Label(const Label& rhs);
	Label& operator=(const Label& rhs);
	~Label();
	void clear() { mgr = 0; id = 0; }
	int getId() const { return id; }
	const uint8_t *getAddress() const;

	// backward compatibility
	static inline std::string toStr(int num)
	{
		char buf[16];
#if defined(_MSC_VER) && (_MSC_VER < 1900)
		_snprintf_s
#else
		snprintf
#endif
		(buf, sizeof(buf), ".%08x", num);
		return buf;
	}
};

class LabelManager {
	// for string label
	struct SlabelVal {
		size_t offset;
		SlabelVal(size_t offset) : offset(offset) {}
	};
	typedef XBYAK_STD_UNORDERED_MAP<std::string, SlabelVal> SlabelDefList;
	typedef XBYAK_STD_UNORDERED_MULTIMAP<std::string, const JmpLabel> SlabelUndefList;
	struct SlabelState {
		SlabelDefList defList;
		SlabelUndefList undefList;
	};
	typedef std::list<SlabelState> StateList;
	// for Label class
	struct ClabelVal {
		ClabelVal(size_t offset = 0) : offset(offset), refCount(1) {}
		size_t offset;
		int refCount;
	};
	typedef XBYAK_STD_UNORDERED_MAP<int, ClabelVal> ClabelDefList;
	typedef XBYAK_STD_UNORDERED_MULTIMAP<int, const JmpLabel> ClabelUndefList;
	typedef XBYAK_STD_UNORDERED_SET<Label*> LabelPtrList;

	CodeArray *base_;
	// global : stateList_.front(), local : stateList_.back()
	StateList stateList_;
	mutable int labelId_;
	ClabelDefList clabelDefList_;
	ClabelUndefList clabelUndefList_;
	LabelPtrList labelPtrList_;

	int getId(const Label& label) const
	{
		if (label.id == 0) label.id = labelId_++;
		return label.id;
	}
	template<class DefList, class UndefList, class T>
	void define_inner(DefList& defList, UndefList& undefList, const T& labelId, size_t addrOffset)
	{
		// add label
		typename DefList::value_type item(labelId, addrOffset);
		std::pair<typename DefList::iterator, bool> ret = defList.insert(item);
		if (!ret.second) XBYAK_THROW(ERR_LABEL_IS_REDEFINED)
		// search undefined label
		for (;;) {
			typename UndefList::iterator itr = undefList.find(labelId);
			if (itr == undefList.end()) break;
			const JmpLabel *jmp = &itr->second;
			const size_t offset = jmp->endOfJmp - jmp->jmpSize;
			size_t disp;
			if (jmp->mode == inner::LaddTop) {
				disp = addrOffset;
			} else if (jmp->mode == inner::Labs) {
				disp = size_t(base_->getCurr());
			} else {
				disp = addrOffset - jmp->endOfJmp + jmp->disp;
#ifdef XBYAK64
				if (jmp->jmpSize <= 4 && !inner::IsInInt32(disp)) XBYAK_THROW(ERR_OFFSET_IS_TOO_BIG)
#endif
				if (jmp->jmpSize == 1 && !inner::IsInDisp8((uint32_t)disp)) XBYAK_THROW(ERR_LABEL_IS_TOO_FAR)
			}
			if (base_->isAutoGrow()) {
				base_->save(offset, disp, jmp->jmpSize, jmp->mode);
			} else {
				base_->rewrite(offset, disp, jmp->jmpSize);
			}
			undefList.erase(itr);
		}
	}
	template<class DefList, class T>
	bool getOffset_inner(const DefList& defList, size_t *offset, const T& label) const
	{
		typename DefList::const_iterator i = defList.find(label);
		if (i == defList.end()) return false;
		*offset = i->second.offset;
		return true;
	}
	friend class Label;
	void incRefCount(int id, Label *label)
	{
		clabelDefList_[id].refCount++;
		labelPtrList_.insert(label);
	}
	void decRefCount(int id, Label *label)
	{
		labelPtrList_.erase(label);
		ClabelDefList::iterator i = clabelDefList_.find(id);
		if (i == clabelDefList_.end()) return;
		if (i->second.refCount == 1) {
			clabelDefList_.erase(id);
		} else {
			--i->second.refCount;
		}
	}
	template<class T>
	bool hasUndefinedLabel_inner(const T& list) const
	{
#ifndef NDEBUG
		for (typename T::const_iterator i = list.begin(); i != list.end(); ++i) {
			std::cerr << "undefined label:" << i->first << std::endl;
		}
#endif
		return !list.empty();
	}
	// detach all labels linked to LabelManager
	void resetLabelPtrList()
	{
		for (LabelPtrList::iterator i = labelPtrList_.begin(), ie = labelPtrList_.end(); i != ie; ++i) {
			(*i)->clear();
		}
		labelPtrList_.clear();
	}
public:
	LabelManager()
	{
		reset();
	}
	~LabelManager()
	{
		resetLabelPtrList();
	}
	void reset()
	{
		base_ = 0;
		labelId_ = 1;
		stateList_.clear();
		stateList_.push_back(SlabelState());
		stateList_.push_back(SlabelState());
		clabelDefList_.clear();
		clabelUndefList_.clear();
		resetLabelPtrList();
		ClearError();
	}
	void enterLocal()
	{
		stateList_.push_back(SlabelState());
	}
	void leaveLocal()
	{
		if (stateList_.size() <= 2) XBYAK_THROW(ERR_UNDER_LOCAL_LABEL)
		if (hasUndefinedLabel_inner(stateList_.back().undefList)) XBYAK_THROW(ERR_LABEL_IS_NOT_FOUND)
		stateList_.pop_back();
	}
	void set(CodeArray *base) { base_ = base; }
	void defineSlabel(std::string label)
	{
		if (label == "@b" || label == "@f") XBYAK_THROW(ERR_BAD_LABEL_STR)
		if (label == "@@") {
			SlabelDefList& defList = stateList_.front().defList;
			SlabelDefList::iterator i = defList.find("@f");
			if (i != defList.end()) {
				defList.erase(i);
				label = "@b";
			} else {
				i = defList.find("@b");
				if (i != defList.end()) {
					defList.erase(i);
				}
				label = "@f";
			}
		}
		SlabelState& st = *label.c_str() == '.' ? stateList_.back() : stateList_.front();
		define_inner(st.defList, st.undefList, label, base_->getSize());
	}
	void defineClabel(Label& label)
	{
		define_inner(clabelDefList_, clabelUndefList_, getId(label), base_->getSize());
		label.mgr = this;
		labelPtrList_.insert(&label);
	}
	void assign(Label& dst, const Label& src)
	{
		ClabelDefList::const_iterator i = clabelDefList_.find(src.id);
		if (i == clabelDefList_.end()) XBYAK_THROW(ERR_LABEL_ISNOT_SET_BY_L)
		define_inner(clabelDefList_, clabelUndefList_, dst.id, i->second.offset);
		dst.mgr = this;
		labelPtrList_.insert(&dst);
	}
	bool getOffset(size_t *offset, std::string& label) const
	{
		const SlabelDefList& defList = stateList_.front().defList;
		if (label == "@b") {
			if (defList.find("@f") != defList.end()) {
				label = "@f";
			} else if (defList.find("@b") == defList.end()) {
				XBYAK_THROW_RET(ERR_LABEL_IS_NOT_FOUND, false)
			}
		} else if (label == "@f") {
			if (defList.find("@f") != defList.end()) {
				label = "@b";
			}
		}
		const SlabelState& st = *label.c_str() == '.' ? stateList_.back() : stateList_.front();
		return getOffset_inner(st.defList, offset, label);
	}
	bool getOffset(size_t *offset, const Label& label) const
	{
		return getOffset_inner(clabelDefList_, offset, getId(label));
	}
	void addUndefinedLabel(const std::string& label, const JmpLabel& jmp)
	{
		SlabelState& st = *label.c_str() == '.' ? stateList_.back() : stateList_.front();
		st.undefList.insert(SlabelUndefList::value_type(label, jmp));
	}
	void addUndefinedLabel(const Label& label, const JmpLabel& jmp)
	{
		clabelUndefList_.insert(ClabelUndefList::value_type(label.id, jmp));
	}
	bool hasUndefSlabel() const
	{
		for (StateList::const_iterator i = stateList_.begin(), ie = stateList_.end(); i != ie; ++i) {
			if (hasUndefinedLabel_inner(i->undefList)) return true;
		}
		return false;
	}
	bool hasUndefClabel() const { return hasUndefinedLabel_inner(clabelUndefList_); }
	const uint8_t *getCode() const { return base_->getCode(); }
	bool isReady() const { return !base_->isAutoGrow() || base_->isCalledCalcJmpAddress(); }
};

inline Label::Label(const Label& rhs)
{
	id = rhs.id;
	mgr = rhs.mgr;
	if (mgr) mgr->incRefCount(id, this);
}
inline Label& Label::operator=(const Label& rhs)
{
	if (id) XBYAK_THROW_RET(ERR_LABEL_IS_ALREADY_SET_BY_L, *this)
	id = rhs.id;
	mgr = rhs.mgr;
	if (mgr) mgr->incRefCount(id, this);
	return *this;
}
inline Label::~Label()
{
	if (id && mgr) mgr->decRefCount(id, this);
}
inline const uint8_t* Label::getAddress() const
{
	if (mgr == 0 || !mgr->isReady()) return 0;
	size_t offset;
	if (!mgr->getOffset(&offset, *this)) return 0;
	return mgr->getCode() + offset;
}

typedef enum {
	DefaultEncoding,
	VexEncoding,
	EvexEncoding
} PreferredEncoding;

class CodeGenerator : public CodeArray {
public:
	enum LabelType {
		T_SHORT,
		T_NEAR,
		T_FAR, // far jump
		T_AUTO // T_SHORT if possible
	};
private:
	CodeGenerator operator=(const CodeGenerator&); // don't call
#ifdef XBYAK64
	enum { i32e = 32 | 64, BIT = 64 };
	static const uint64_t dummyAddr = uint64_t(0x1122334455667788ull);
	typedef Reg64 NativeReg;
#else
	enum { i32e = 32, BIT = 32 };
	static const size_t dummyAddr = 0x12345678;
	typedef Reg32 NativeReg;
#endif
	// (XMM, XMM|MEM)
	static inline bool isXMM_XMMorMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isXMM() && (op2.isXMM() || op2.isMEM());
	}
	// (MMX, MMX|MEM) or (XMM, XMM|MEM)
	static inline bool isXMMorMMX_MEM(const Operand& op1, const Operand& op2)
	{
		return (op1.isMMX() && (op2.isMMX() || op2.isMEM())) || isXMM_XMMorMEM(op1, op2);
	}
	// (XMM, MMX|MEM)
	static inline bool isXMM_MMXorMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isXMM() && (op2.isMMX() || op2.isMEM());
	}
	// (MMX, XMM|MEM)
	static inline bool isMMX_XMMorMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isMMX() && (op2.isXMM() || op2.isMEM());
	}
	// (XMM, REG32|MEM)
	static inline bool isXMM_REG32orMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isXMM() && (op2.isREG(i32e) || op2.isMEM());
	}
	// (REG32, XMM|MEM)
	static inline bool isREG32_XMMorMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isREG(i32e) && (op2.isXMM() || op2.isMEM());
	}
	// (REG32, REG32|MEM)
	static inline bool isREG32_REG32orMEM(const Operand& op1, const Operand& op2)
	{
		return op1.isREG(i32e) && ((op2.isREG(i32e) && op1.getBit() == op2.getBit()) || op2.isMEM());
	}
	void rex(const Operand& op1, const Operand& op2 = Operand())
	{
		uint8_t rex = 0;
		const Operand *p1 = &op1, *p2 = &op2;
		if (p1->isMEM()) std::swap(p1, p2);
		if (p1->isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION)
		if (p2->isMEM()) {
			const Address& addr = p2->getAddress();
			if (BIT == 64 && addr.is32bit()) db(0x67);
			rex = addr.getRex() | p1->getReg().getRex();
		} else {
			// ModRM(reg, base);
			rex = op2.getReg().getRex(op1.getReg());
		}
		// except movsx(16bit, 32/64bit)
		if ((op1.isBit(16) && !op2.isBit(i32e)) || (op2.isBit(16) && !op1.isBit(i32e))) db(0x66);
		if (rex) db(rex);
	}
	enum AVXtype {
		// low 3 bit
		T_N1 = 1,
		T_N2 = 2,
		T_N4 = 3,
		T_N8 = 4,
		T_N16 = 5,
		T_N32 = 6,
		T_NX_MASK = 7,
		//
		T_N_VL = 1 << 3, // N * (1, 2, 4) for VL
		T_DUP = 1 << 4, // N = (8, 32, 64)
		T_66 = 1 << 5, // pp = 1
		T_F3 = 1 << 6, // pp = 2
		T_F2 = T_66 | T_F3, // pp = 3
		T_ER_R = 1 << 7, // reg{er}
		T_0F = 1 << 8,
		T_0F38 = 1 << 9,
		T_0F3A = 1 << 10,
		T_L0 = 1 << 11,
		T_L1 = 1 << 12,
		T_W0 = 1 << 13,
		T_W1 = 1 << 14,
		T_EW0 = 1 << 15,
		T_EW1 = 1 << 16,
		T_YMM = 1 << 17, // support YMM, ZMM
		T_EVEX = 1 << 18,
		T_ER_X = 1 << 19, // xmm{er}
		T_ER_Y = 1 << 20, // ymm{er}
		T_ER_Z = 1 << 21, // zmm{er}
		T_SAE_X = 1 << 22, // xmm{sae}
		T_SAE_Y = 1 << 23, // ymm{sae}
		T_SAE_Z = 1 << 24, // zmm{sae}
		T_MUST_EVEX = 1 << 25, // contains T_EVEX
		T_B32 = 1 << 26, // m32bcst
		T_B64 = 1 << 27, // m64bcst
		T_B16 = T_B32 | T_B64, // m16bcst (Be careful)
		T_M_K = 1 << 28, // mem{k}
		T_VSIB = 1 << 29,
		T_MEM_EVEX = 1 << 30, // use evex if mem
		T_FP16 = 1 << 31, // avx512-fp16
		T_MAP5 = T_FP16 | T_0F,
		T_MAP6 = T_FP16 | T_0F38,
		T_XXX
	};
	// T_66 = 1, T_F3 = 2, T_F2 = 3
	uint32_t getPP(int type) const { return (type >> 5) & 3; }
	void vex(const Reg& reg, const Reg& base, const Operand *v, int type, int code, bool x = false)
	{
		int w = (type & T_W1) ? 1 : 0;
		bool is256 = (type & T_L1) ? true : (type & T_L0) ? false : reg.isYMM();
		bool r = reg.isExtIdx();
		bool b = base.isExtIdx();
		int idx = v ? v->getIdx() : 0;
		if ((idx | reg.getIdx() | base.getIdx()) >= 16) XBYAK_THROW(ERR_BAD_COMBINATION)
		uint32_t pp = getPP(type);
		uint32_t vvvv = (((~idx) & 15) << 3) | (is256 ? 4 : 0) | pp;
		if (!b && !x && !w && (type & T_0F)) {
			db(0xC5); db((r ? 0 : 0x80) | vvvv);
		} else {
			uint32_t mmmm = (type & T_0F) ? 1 : (type & T_0F38) ? 2 : (type & T_0F3A) ? 3 : 0;
			db(0xC4); db((r ? 0 : 0x80) | (x ? 0 : 0x40) | (b ? 0 : 0x20) | mmmm); db((w << 7) | vvvv);
		}
		db(code);
	}
	void verifySAE(const Reg& r, int type) const
	{
		if (((type & T_SAE_X) && r.isXMM()) || ((type & T_SAE_Y) && r.isYMM()) || ((type & T_SAE_Z) && r.isZMM())) return;
		XBYAK_THROW(ERR_SAE_IS_INVALID)
	}
	void verifyER(const Reg& r, int type) const
	{
		if ((type & T_ER_R) && r.isREG(32|64)) return;
		if (((type & T_ER_X) && r.isXMM()) || ((type & T_ER_Y) && r.isYMM()) || ((type & T_ER_Z) && r.isZMM())) return;
		XBYAK_THROW(ERR_ER_IS_INVALID)
	}
	// (a, b, c) contains non zero two or three values then err
	int verifyDuplicate(int a, int b, int c, int err)
	{
		int v = a | b | c;
		if ((a > 0 && a != v) + (b > 0 && b != v) + (c > 0 && c != v) > 0) XBYAK_THROW_RET(err, 0)
		return v;
	}
	int evex(const Reg& reg, const Reg& base, const Operand *v, int type, int code, bool x = false, bool b = false, int aaa = 0, uint32_t VL = 0, bool Hi16Vidx = false)
	{
		if (!(type & (T_EVEX | T_MUST_EVEX))) XBYAK_THROW_RET(ERR_EVEX_IS_INVALID, 0)
		int w = (type & T_EW1) ? 1 : 0;
		uint32_t mmm = (type & T_0F) ? 1 : (type & T_0F38) ? 2 : (type & T_0F3A) ? 3 : 0;
		if (type & T_FP16) mmm |= 4;
		uint32_t pp = getPP(type);
		int idx = v ? v->getIdx() : 0;
		uint32_t vvvv = ~idx;

		bool R = !reg.isExtIdx();
		bool X = x ? false : !base.isExtIdx2();
		bool B = !base.isExtIdx();
		bool Rp = !reg.isExtIdx2();
		int LL;
		int rounding = verifyDuplicate(reg.getRounding(), base.getRounding(), v ? v->getRounding() : 0, ERR_ROUNDING_IS_ALREADY_SET);
		int disp8N = 1;
		if (rounding) {
			if (rounding == EvexModifierRounding::T_SAE) {
				verifySAE(base, type); LL = 0;
			} else {
				verifyER(base, type); LL = rounding - 1;
			}
			b = true;
		} else {
			if (v) VL = (std::max)(VL, v->getBit());
			VL = (std::max)((std::max)(reg.getBit(), base.getBit()), VL);
			LL = (VL == 512) ? 2 : (VL == 256) ? 1 : 0;
			if (b) {
				disp8N = ((type & T_B16) == T_B16) ? 2 : (type & T_B32) ? 4 : 8;
			} else if (type & T_DUP) {
				disp8N = VL == 128 ? 8 : VL == 256 ? 32 : 64;
			} else {
				if ((type & (T_NX_MASK | T_N_VL)) == 0) {
					type |= T_N16 | T_N_VL; // default
				}
				int low = type & T_NX_MASK;
				if (low > 0) {
					disp8N = 1 << (low - 1);
					if (type & T_N_VL) disp8N *= (VL == 512 ? 4 : VL == 256 ? 2 : 1);
				}
			}
		}
		bool Vp = !((v ? v->isExtIdx2() : 0) | Hi16Vidx);
		bool z = reg.hasZero() || base.hasZero() || (v ? v->hasZero() : false);
		if (aaa == 0) aaa = verifyDuplicate(base.getOpmaskIdx(), reg.getOpmaskIdx(), (v ? v->getOpmaskIdx() : 0), ERR_OPMASK_IS_ALREADY_SET);
		if (aaa == 0) z = 0; // clear T_z if mask is not set
		db(0x62);
		db((R ? 0x80 : 0) | (X ? 0x40 : 0) | (B ? 0x20 : 0) | (Rp ? 0x10 : 0) | mmm);
		db((w == 1 ? 0x80 : 0) | ((vvvv & 15) << 3) | 4 | (pp & 3));
		db((z ? 0x80 : 0) | ((LL & 3) << 5) | (b ? 0x10 : 0) | (Vp ? 8 : 0) | (aaa & 7));
		db(code);
		return disp8N;
	}
	void setModRM(int mod, int r1, int r2)
	{
		db(static_cast<uint8_t>((mod << 6) | ((r1 & 7) << 3) | (r2 & 7)));
	}
	void setSIB(const RegExp& e, int reg, int disp8N = 0)
	{
		uint64_t disp64 = e.getDisp();
#ifdef XBYAK64
		uint64_t high = disp64 >> 32;
		if (high != 0 && high != 0xFFFFFFFF) XBYAK_THROW(ERR_OFFSET_IS_TOO_BIG)
#endif
		uint32_t disp = static_cast<uint32_t>(disp64);
		const Reg& base = e.getBase();
		const Reg& index = e.getIndex();
		const int baseIdx = base.getIdx();
		const int baseBit = base.getBit();
		const int indexBit = index.getBit();
		enum {
			mod00 = 0, mod01 = 1, mod10 = 2
		};
		int mod = mod10; // disp32
		if (!baseBit || ((baseIdx & 7) != Operand::EBP && disp == 0)) {
			mod = mod00;
		} else {
			if (disp8N == 0) {
				if (inner::IsInDisp8(disp)) {
					mod = mod01;
				}
			} else {
				// disp must be casted to signed
				uint32_t t = static_cast<uint32_t>(static_cast<int>(disp) / disp8N);
				if ((disp % disp8N) == 0 && inner::IsInDisp8(t)) {
					disp = t;
					mod = mod01;
				}
			}
		}
		const int newBaseIdx = baseBit ? (baseIdx & 7) : Operand::EBP;
		/* ModR/M = [2:3:3] = [Mod:reg/code:R/M] */
		bool hasSIB = indexBit || (baseIdx & 7) == Operand::ESP;
#ifdef XBYAK64
		if (!baseBit && !indexBit) hasSIB = true;
#endif
		if (hasSIB) {
			setModRM(mod, reg, Operand::ESP);
			/* SIB = [2:3:3] = [SS:index:base(=rm)] */
			const int idx = indexBit ? (index.getIdx() & 7) : Operand::ESP;
			const int scale = e.getScale();
			const int SS = (scale == 8) ? 3 : (scale == 4) ? 2 : (scale == 2) ? 1 : 0;
			setModRM(SS, idx, newBaseIdx);
		} else {
			setModRM(mod, reg, newBaseIdx);
		}
		if (mod == mod01) {
			db(disp);
		} else if (mod == mod10 || (mod == mod00 && !baseBit)) {
			dd(disp);
		}
	}
	LabelManager labelMgr_;
	bool isInDisp16(uint32_t x) const { return 0xFFFF8000 <= x || x <= 0x7FFF; }
	void opModR(const Reg& reg1, const Reg& reg2, int code0, int code1 = NONE, int code2 = NONE)
	{
		rex(reg2, reg1);
		db(code0 | (reg1.isBit(8) ? 0 : 1)); if (code1 != NONE) db(code1); if (code2 != NONE) db(code2);
		setModRM(3, reg1.getIdx(), reg2.getIdx());
	}
	void opModM(const Address& addr, const Reg& reg, int code0, int code1 = NONE, int code2 = NONE, int immSize = 0)
	{
		if (addr.is64bitDisp()) XBYAK_THROW(ERR_CANT_USE_64BIT_DISP)
		rex(addr, reg);
		db(code0 | (reg.isBit(8) ? 0 : 1)); if (code1 != NONE) db(code1); if (code2 != NONE) db(code2);
		opAddr(addr, reg.getIdx(), immSize);
	}
	void opLoadSeg(const Address& addr, const Reg& reg, int code0, int code1 = NONE)
	{
		if (addr.is64bitDisp()) XBYAK_THROW(ERR_CANT_USE_64BIT_DISP)
		if (reg.isBit(8)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		rex(addr, reg);
		db(code0); if (code1 != NONE) db(code1);
		opAddr(addr, reg.getIdx());
	}
	void opMIB(const Address& addr, const Reg& reg, int code0, int code1)
	{
		if (addr.is64bitDisp()) XBYAK_THROW(ERR_CANT_USE_64BIT_DISP)
		if (addr.getMode() != Address::M_ModRM) XBYAK_THROW(ERR_INVALID_MIB_ADDRESS)
		if (BIT == 64 && addr.is32bit()) db(0x67);
		const RegExp& regExp = addr.getRegExp(false);
		uint8_t rex = regExp.getRex();
		if (rex) db(rex);
		db(code0); db(code1);
		setSIB(regExp, reg.getIdx());
	}
	void makeJmp(uint32_t disp, LabelType type, uint8_t shortCode, uint8_t longCode, uint8_t longPref)
	{
		const int shortJmpSize = 2;
		const int longHeaderSize = longPref ? 2 : 1;
		const int longJmpSize = longHeaderSize + 4;
		if (type != T_NEAR && inner::IsInDisp8(disp - shortJmpSize)) {
			db(shortCode); db(disp - shortJmpSize);
		} else {
			if (type == T_SHORT) XBYAK_THROW(ERR_LABEL_IS_TOO_FAR)
			if (longPref) db(longPref);
			db(longCode); dd(disp - longJmpSize);
		}
	}
	bool isNEAR(LabelType type) const { return type == T_NEAR || (type == T_AUTO && isDefaultJmpNEAR_); }
	template<class T>
	void opJmp(T& label, LabelType type, uint8_t shortCode, uint8_t longCode, uint8_t longPref)
	{
		if (type == T_FAR) XBYAK_THROW(ERR_NOT_SUPPORTED)
		if (isAutoGrow() && size_ + 16 >= maxSize_) growMemory(); /* avoid splitting code of jmp */
		size_t offset = 0;
		if (labelMgr_.getOffset(&offset, label)) { /* label exists */
			makeJmp(inner::VerifyInInt32(offset - size_), type, shortCode, longCode, longPref);
		} else {
			int jmpSize = 0;
			if (isNEAR(type)) {
				jmpSize = 4;
				if (longPref) db(longPref);
				db(longCode); dd(0);
			} else {
				jmpSize = 1;
				db(shortCode); db(0);
			}
			JmpLabel jmp(size_, jmpSize, inner::LasIs);
			labelMgr_.addUndefinedLabel(label, jmp);
		}
	}
	void opJmpAbs(const void *addr, LabelType type, uint8_t shortCode, uint8_t longCode, uint8_t longPref = 0)
	{
		if (type == T_FAR) XBYAK_THROW(ERR_NOT_SUPPORTED)
		if (isAutoGrow()) {
			if (!isNEAR(type)) XBYAK_THROW(ERR_ONLY_T_NEAR_IS_SUPPORTED_IN_AUTO_GROW)
			if (size_ + 16 >= maxSize_) growMemory();
			if (longPref) db(longPref);
			db(longCode);
			dd(0);
			save(size_ - 4, size_t(addr) - size_, 4, inner::Labs);
		} else {
			makeJmp(inner::VerifyInInt32(reinterpret_cast<const uint8_t*>(addr) - getCurr()), type, shortCode, longCode, longPref);
		}

	}
	void opJmpOp(const Operand& op, LabelType type, int ext)
	{
		const int bit = 16|i32e;
		if (type == T_FAR) {
			if (!op.isMEM(bit)) XBYAK_THROW(ERR_NOT_SUPPORTED)
			opR_ModM(op, bit, ext + 1, 0xFF, NONE, NONE, false);
		} else {
			opR_ModM(op, bit, ext, 0xFF, NONE, NONE, true);
		}
	}
	// reg is reg field of ModRM
	// immSize is the size for immediate value
	// disp8N = 0(normal), disp8N = 1(force disp32), disp8N = {2, 4, 8} ; compressed displacement
	void opAddr(const Address &addr, int reg, int immSize = 0, int disp8N = 0, bool permitVisb = false)
	{
		if (!permitVisb && addr.isVsib()) XBYAK_THROW(ERR_BAD_VSIB_ADDRESSING)
		if (addr.getMode() == Address::M_ModRM) {
			setSIB(addr.getRegExp(), reg, disp8N);
		} else if (addr.getMode() == Address::M_rip || addr.getMode() == Address::M_ripAddr) {
			setModRM(0, reg, 5);
			if (addr.getLabel()) { // [rip + Label]
				putL_inner(*addr.getLabel(), true, addr.getDisp() - immSize);
			} else {
				size_t disp = addr.getDisp();
				if (addr.getMode() == Address::M_ripAddr) {
					if (isAutoGrow()) XBYAK_THROW(ERR_INVALID_RIP_IN_AUTO_GROW)
					disp -= (size_t)getCurr() + 4 + immSize;
				}
				dd(inner::VerifyInInt32(disp));
			}
		}
	}
	/* preCode is for SSSE3/SSE4 */
	void opGen(const Operand& reg, const Operand& op, int code, int pref, bool isValid(const Operand&, const Operand&), int imm8 = NONE, int preCode = NONE)
	{
		if (isValid && !isValid(reg, op)) XBYAK_THROW(ERR_BAD_COMBINATION)
		if (pref != NONE) db(pref);
		if (op.isMEM()) {
			opModM(op.getAddress(), reg.getReg(), 0x0F, preCode, code, (imm8 != NONE) ? 1 : 0);
		} else {
			opModR(reg.getReg(), op.getReg(), 0x0F, preCode, code);
		}
		if (imm8 != NONE) db(imm8);
	}
	void opMMX_IMM(const Mmx& mmx, int imm8, int code, int ext)
	{
		if (mmx.isXMM()) db(0x66);
		opModR(Reg32(ext), mmx, 0x0F, code);
		db(imm8);
	}
	void opMMX(const Mmx& mmx, const Operand& op, int code, int pref = 0x66, int imm8 = NONE, int preCode = NONE)
	{
		opGen(mmx, op, code, mmx.isXMM() ? pref : NONE, isXMMorMMX_MEM, imm8, preCode);
	}
	void opMovXMM(const Operand& op1, const Operand& op2, int code, int pref)
	{
		if (pref != NONE) db(pref);
		if (op1.isXMM() && op2.isMEM()) {
			opModM(op2.getAddress(), op1.getReg(), 0x0F, code);
		} else if (op1.isMEM() && op2.isXMM()) {
			opModM(op1.getAddress(), op2.getReg(), 0x0F, code | 1);
		} else {
			XBYAK_THROW(ERR_BAD_COMBINATION)
		}
	}
	void opExt(const Operand& op, const Mmx& mmx, int code, int imm, bool hasMMX2 = false)
	{
		if (hasMMX2 && op.isREG(i32e)) { /* pextrw is special */
			if (mmx.isXMM()) db(0x66);
			opModR(op.getReg(), mmx, 0x0F, 0xC5); db(imm);
		} else {
			opGen(mmx, op, code, 0x66, isXMM_REG32orMEM, imm, 0x3A);
		}
	}
	void opR_ModM(const Operand& op, int bit, int ext, int code0, int code1 = NONE, int code2 = NONE, bool disableRex = false, int immSize = 0)
	{
		int opBit = op.getBit();
		if (disableRex && opBit == 64) opBit = 32;
		if (op.isREG(bit)) {
			opModR(Reg(ext, Operand::REG, opBit), op.getReg().changeBit(opBit), code0, code1, code2);
		} else if (op.isMEM()) {
			opModM(op.getAddress(), Reg(ext, Operand::REG, opBit), code0, code1, code2, immSize);
		} else {
			XBYAK_THROW(ERR_BAD_COMBINATION)
		}
	}
	void opShift(const Operand& op, int imm, int ext)
	{
		verifyMemHasSize(op);
		opR_ModM(op, 0, ext, (0xC0 | ((imm == 1 ? 1 : 0) << 4)), NONE, NONE, false, (imm != 1) ? 1 : 0);
		if (imm != 1) db(imm);
	}
	void opShift(const Operand& op, const Reg8& _cl, int ext)
	{
		if (_cl.getIdx() != Operand::CL) XBYAK_THROW(ERR_BAD_COMBINATION)
		opR_ModM(op, 0, ext, 0xD2);
	}
	void opModRM(const Operand& op1, const Operand& op2, bool condR, bool condM, int code0, int code1 = NONE, int code2 = NONE, int immSize = 0)
	{
		if (condR) {
			opModR(op1.getReg(), op2.getReg(), code0, code1, code2);
		} else if (condM) {
			opModM(op2.getAddress(), op1.getReg(), code0, code1, code2, immSize);
		} else {
			XBYAK_THROW(ERR_BAD_COMBINATION)
		}
	}
	void opShxd(const Operand& op, const Reg& reg, uint8_t imm, int code, const Reg8 *_cl = 0)
	{
		if (_cl && _cl->getIdx() != Operand::CL) XBYAK_THROW(ERR_BAD_COMBINATION)
		opModRM(reg, op, (op.isREG(16 | i32e) && op.getBit() == reg.getBit()), op.isMEM() && (reg.isREG(16 | i32e)), 0x0F, code | (_cl ? 1 : 0), NONE, _cl ? 0 : 1);
		if (!_cl) db(imm);
	}
	// (REG, REG|MEM), (MEM, REG)
	void opRM_RM(const Operand& op1, const Operand& op2, int code)
	{
		if (op1.isREG() && op2.isMEM()) {
			opModM(op2.getAddress(), op1.getReg(), code | 2);
		} else {
			opModRM(op2, op1, op1.isREG() && op1.getKind() == op2.getKind(), op1.isMEM() && op2.isREG(), code);
		}
	}
	// (REG|MEM, IMM)
	void opRM_I(const Operand& op, uint32_t imm, int code, int ext)
	{
		verifyMemHasSize(op);
		uint32_t immBit = inner::IsInDisp8(imm) ? 8 : isInDisp16(imm) ? 16 : 32;
		if (op.isBit(8)) immBit = 8;
		if (op.getBit() < immBit) XBYAK_THROW(ERR_IMM_IS_TOO_BIG)
		if (op.isBit(32|64) && immBit == 16) immBit = 32; /* don't use MEM16 if 32/64bit mode */
		if (op.isREG() && op.getIdx() == 0 && (op.getBit() == immBit || (op.isBit(64) && immBit == 32))) { // rax, eax, ax, al
			rex(op);
			db(code | 4 | (immBit == 8 ? 0 : 1));
		} else {
			int tmp = immBit < (std::min)(op.getBit(), 32U) ? 2 : 0;
			opR_ModM(op, 0, ext, 0x80 | tmp, NONE, NONE, false, immBit / 8);
		}
		db(imm, immBit / 8);
	}
	void opIncDec(const Operand& op, int code, int ext)
	{
		verifyMemHasSize(op);
#ifndef XBYAK64
		if (op.isREG() && !op.isBit(8)) {
			rex(op); db(code | op.getIdx());
			return;
		}
#endif
		code = 0xFE;
		if (op.isREG()) {
			opModR(Reg(ext, Operand::REG, op.getBit()), op.getReg(), code);
		} else {
			opModM(op.getAddress(), Reg(ext, Operand::REG, op.getBit()), code);
		}
	}
	void opPushPop(const Operand& op, int code, int ext, int alt)
	{
		int bit = op.getBit();
		if (bit == 16 || bit == BIT) {
			if (bit == 16) db(0x66);
			if (op.isREG()) {
				if (op.getReg().getIdx() >= 8) db(0x41);
				db(alt | (op.getIdx() & 7));
				return;
			}
			if (op.isMEM()) {
				opModM(op.getAddress(), Reg(ext, Operand::REG, 32), code);
				return;
			}
		}
		XBYAK_THROW(ERR_BAD_COMBINATION)
	}
	void verifyMemHasSize(const Operand& op) const
	{
		if (op.isMEM() && op.getBit() == 0) XBYAK_THROW(ERR_MEM_SIZE_IS_NOT_SPECIFIED)
	}
	/*
		mov(r, imm) = db(imm, mov_imm(r, imm))
	*/
	int mov_imm(const Reg& reg, uint64_t imm)
	{
		int bit = reg.getBit();
		const int idx = reg.getIdx();
		int code = 0xB0 | ((bit == 8 ? 0 : 1) << 3);
		if (bit == 64 && (imm & ~uint64_t(0xffffffffu)) == 0) {
			rex(Reg32(idx));
			bit = 32;
		} else {
			rex(reg);
			if (bit == 64 && inner::IsInInt32(imm)) {
				db(0xC7);
				code = 0xC0;
				bit = 32;
			}
		}
		db(code | (idx & 7));
		return bit / 8;
	}
	template<class T>
	void putL_inner(T& label, bool relative = false, size_t disp = 0)
	{
		const int jmpSize = relative ? 4 : (int)sizeof(size_t);
		if (isAutoGrow() && size_ + 16 >= maxSize_) growMemory();
		size_t offset = 0;
		if (labelMgr_.getOffset(&offset, label)) {
			if (relative) {
				db(inner::VerifyInInt32(offset + disp - size_ - jmpSize), jmpSize);
			} else if (isAutoGrow()) {
				db(uint64_t(0), jmpSize);
				save(size_ - jmpSize, offset, jmpSize, inner::LaddTop);
			} else {
				db(size_t(top_) + offset, jmpSize);
			}
			return;
		}
		db(uint64_t(0), jmpSize);
		JmpLabel jmp(size_, jmpSize, (relative ? inner::LasIs : isAutoGrow() ? inner::LaddTop : inner::Labs), disp);
		labelMgr_.addUndefinedLabel(label, jmp);
	}
	void opMovxx(const Reg& reg, const Operand& op, uint8_t code)
	{
		if (op.isBit(32)) XBYAK_THROW(ERR_BAD_COMBINATION)
		int w = op.isBit(16);
#ifdef XBYAK64
		if (op.isHigh8bit()) XBYAK_THROW(ERR_BAD_COMBINATION)
#endif
		bool cond = reg.isREG() && (reg.getBit() > op.getBit());
		opModRM(reg, op, cond && op.isREG(), cond && op.isMEM(), 0x0F, code | w);
	}
	void opFpuMem(const Address& addr, uint8_t m16, uint8_t m32, uint8_t m64, uint8_t ext, uint8_t m64ext)
	{
		if (addr.is64bitDisp()) XBYAK_THROW(ERR_CANT_USE_64BIT_DISP)
		uint8_t code = addr.isBit(16) ? m16 : addr.isBit(32) ? m32 : addr.isBit(64) ? m64 : 0;
		if (!code) XBYAK_THROW(ERR_BAD_MEM_SIZE)
		if (m64ext && addr.isBit(64)) ext = m64ext;

		rex(addr, st0);
		db(code);
		opAddr(addr, ext);
	}
	// use code1 if reg1 == st0
	// use code2 if reg1 != st0 && reg2 == st0
	void opFpuFpu(const Fpu& reg1, const Fpu& reg2, uint32_t code1, uint32_t code2)
	{
		uint32_t code = reg1.getIdx() == 0 ? code1 : reg2.getIdx() == 0 ? code2 : 0;
		if (!code) XBYAK_THROW(ERR_BAD_ST_COMBINATION)
		db(uint8_t(code >> 8));
		db(uint8_t(code | (reg1.getIdx() | reg2.getIdx())));
	}
	void opFpu(const Fpu& reg, uint8_t code1, uint8_t code2)
	{
		db(code1); db(code2 | reg.getIdx());
	}
	void opVex(const Reg& r, const Operand *p1, const Operand& op2, int type, int code, int imm8 = NONE)
	{
		if (op2.isMEM()) {
			const Address& addr = op2.getAddress();
			const RegExp& regExp = addr.getRegExp();
			const Reg& base = regExp.getBase();
			const Reg& index = regExp.getIndex();
			if (BIT == 64 && addr.is32bit()) db(0x67);
			int disp8N = 0;
			bool x = index.isExtIdx();
			if ((type & (T_MUST_EVEX|T_MEM_EVEX)) || r.hasEvex() || (p1 && p1->hasEvex()) || addr.isBroadcast() || addr.getOpmaskIdx()) {
				int aaa = addr.getOpmaskIdx();
				if (aaa && !(type & T_M_K)) XBYAK_THROW(ERR_INVALID_OPMASK_WITH_MEMORY)
				bool b = false;
				if (addr.isBroadcast()) {
					if (!(type & (T_B32 | T_B64))) XBYAK_THROW(ERR_INVALID_BROADCAST)
					b = true;
				}
				int VL = regExp.isVsib() ? index.getBit() : 0;
				disp8N = evex(r, base, p1, type, code, x, b, aaa, VL, index.isExtIdx2());
			} else {
				vex(r, base, p1, type, code, x);
			}
			opAddr(addr, r.getIdx(), (imm8 != NONE) ? 1 : 0, disp8N, (type & T_VSIB) != 0);
		} else {
			const Reg& base = op2.getReg();
			if ((type & T_MUST_EVEX) || r.hasEvex() || (p1 && p1->hasEvex()) || base.hasEvex()) {
				evex(r, base, p1, type, code);
			} else {
				vex(r, base, p1, type, code);
			}
			setModRM(3, r.getIdx(), base.getIdx());
		}
		if (imm8 != NONE) db(imm8);
	}
	// (r, r, r/m) if isR_R_RM
	// (r, r/m, r)
	void opGpr(const Reg32e& r, const Operand& op1, const Operand& op2, int type, uint8_t code, bool isR_R_RM, int imm8 = NONE)
	{
		const Operand *p1 = &op1;
		const Operand *p2 = &op2;
		if (!isR_R_RM) std::swap(p1, p2);
		const unsigned int bit = r.getBit();
		if (p1->getBit() != bit || (p2->isREG() && p2->getBit() != bit)) XBYAK_THROW(ERR_BAD_COMBINATION)
		type |= (bit == 64) ? T_W1 : T_W0;
		opVex(r, p1, *p2, type, code, imm8);
	}
	void opAVX_X_X_XM(const Xmm& x1, const Operand& op1, const Operand& op2, int type, int code0, int imm8 = NONE)
	{
		const Xmm *x2 = static_cast<const Xmm*>(&op1);
		const Operand *op = &op2;
		if (op2.isNone()) { // (x1, op1) -> (x1, x1, op1)
			x2 = &x1;
			op = &op1;
		}
		// (x1, x2, op)
		if (!((x1.isXMM() && x2->isXMM()) || ((type & T_YMM) && ((x1.isYMM() && x2->isYMM()) || (x1.isZMM() && x2->isZMM()))))) XBYAK_THROW(ERR_BAD_COMBINATION)
		opVex(x1, x2, *op, type, code0, imm8);
	}
	void opAVX_K_X_XM(const Opmask& k, const Xmm& x2, const Operand& op3, int type, int code0, int imm8 = NONE)
	{
		if (!op3.isMEM() && (x2.getKind() != op3.getKind())) XBYAK_THROW(ERR_BAD_COMBINATION)
		opVex(k, &x2, op3, type, code0, imm8);
	}
	// (x, x/m), (y, x/m256), (z, y/m)
	void checkCvt1(const Operand& x, const Operand& op) const
	{
		if (!op.isMEM() && !(x.is(Operand::XMM | Operand::YMM) && op.isXMM()) && !(x.isZMM() && op.isYMM())) XBYAK_THROW(ERR_BAD_COMBINATION)
	}
	// (x, x/m), (x, y/m256), (y, z/m)
	void checkCvt2(const Xmm& x, const Operand& op) const
	{
		if (!(x.isXMM() && op.is(Operand::XMM | Operand::YMM | Operand::MEM)) && !(x.isYMM() && op.is(Operand::ZMM | Operand::MEM))) XBYAK_THROW(ERR_BAD_COMBINATION)
	}
	void opCvt(const Xmm& x, const Operand& op, int type, int code)
	{
		Operand::Kind kind = x.isXMM() ? (op.isBit(256) ? Operand::YMM : Operand::XMM) : Operand::ZMM;
		opVex(x.copyAndSetKind(kind), &xm0, op, type, code);
	}
	void opCvt2(const Xmm& x, const Operand& op, int type, int code)
	{
		checkCvt2(x, op);
		opCvt(x, op, type, code);
	}
	void opCvt3(const Xmm& x1, const Xmm& x2, const Operand& op, int type, int type64, int type32, uint8_t code)
	{
		if (!(x1.isXMM() && x2.isXMM() && (op.isREG(i32e) || op.isMEM()))) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		Xmm x(op.getIdx());
		const Operand *p = op.isREG() ? &x : &op;
		opVex(x1, &x2, *p, type | (op.isBit(64) ? type64 : type32), code);
	}
	// (x, x/y/xword/yword), (y, z/m)
	void checkCvt4(const Xmm& x, const Operand& op) const
	{
		if (!(x.isXMM() && op.is(Operand::XMM | Operand::YMM | Operand::MEM) && op.isBit(128|256)) && !(x.isYMM() && op.is(Operand::ZMM | Operand::MEM))) XBYAK_THROW(ERR_BAD_COMBINATION)
	}
	// (x, x/y/z/xword/yword/zword)
	void opCvt5(const Xmm& x, const Operand& op, int type, int code)
	{
		if (!(x.isXMM() && op.isBit(128|256|512))) XBYAK_THROW(ERR_BAD_COMBINATION)
		Operand::Kind kind = op.isBit(128) ? Operand::XMM : op.isBit(256) ? Operand::YMM : Operand::ZMM;
		opVex(x.copyAndSetKind(kind), &xm0, op, type, code);
	}
	const Xmm& cvtIdx0(const Operand& x) const
	{
		return x.isZMM() ? zm0 : x.isYMM() ? ym0 : xm0;
	}
	// support (x, x/m, imm), (y, y/m, imm)
	void opAVX_X_XM_IMM(const Xmm& x, const Operand& op, int type, int code, int imm8 = NONE)
	{
		opAVX_X_X_XM(x, cvtIdx0(x), op, type, code, imm8);
	}
	// QQQ:need to refactor
	void opSp1(const Reg& reg, const Operand& op, uint8_t pref, uint8_t code0, uint8_t code1)
	{
		if (reg.isBit(8)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER)
		bool is16bit = reg.isREG(16) && (op.isREG(16) || op.isMEM());
		if (!is16bit && !(reg.isREG(i32e) && (op.isREG(reg.getBit()) || op.isMEM()))) XBYAK_THROW(ERR_BAD_COMBINATION)
		if (is16bit) db(0x66);
		db(pref); opModRM(reg.changeBit(i32e == 32 ? 32 : reg.getBit()), op, op.isREG(), true, code0, code1);
	}
	void opGather(const Xmm& x1, const Address& addr, const Xmm& x2, int type, uint8_t code, int mode)
	{
		const RegExp& regExp = addr.getRegExp();
		if (!regExp.isVsib(128 | 256)) XBYAK_THROW(ERR_BAD_VSIB_ADDRESSING)
		const int y_vx_y = 0;
		const int y_vy_y = 1;
//		const int x_vy_x = 2;
		const bool isAddrYMM = regExp.getIndex().getBit() == 256;
		if (!x1.isXMM() || isAddrYMM || !x2.isXMM()) {
			bool isOK = false;
			if (mode == y_vx_y) {
				isOK = x1.isYMM() && !isAddrYMM && x2.isYMM();
			} else if (mode == y_vy_y) {
				isOK = x1.isYMM() && isAddrYMM && x2.isYMM();
			} else { // x_vy_x
				isOK = !x1.isYMM() && isAddrYMM && !x2.isYMM();
			}
			if (!isOK) XBYAK_THROW(ERR_BAD_VSIB_ADDRESSING)
		}
		int i1 = x1.getIdx();
		int i2 = regExp.getIndex().getIdx();
		int i3 = x2.getIdx();
		if (i1 == i2 || i1 == i3 || i2 == i3) XBYAK_THROW(ERR_SAME_REGS_ARE_INVALID);
		opAVX_X_X_XM(isAddrYMM ? Ymm(i1) : x1, isAddrYMM ? Ymm(i3) : x2, addr, type, code);
	}
	enum {
		xx_yy_zz = 0,
		xx_yx_zy = 1,
		xx_xy_yz = 2
	};
	void checkGather2(const Xmm& x1, const Reg& x2, int mode) const
	{
		if (x1.isXMM() && x2.isXMM()) return;
		switch (mode) {
		case xx_yy_zz: if ((x1.isYMM() && x2.isYMM()) || (x1.isZMM() && x2.isZMM())) return;
			break;
		case xx_yx_zy: if ((x1.isYMM() && x2.isXMM()) || (x1.isZMM() && x2.isYMM())) return;
			break;
		case xx_xy_yz: if ((x1.isXMM() && x2.isYMM()) || (x1.isYMM() && x2.isZMM())) return;
			break;
		}
		XBYAK_THROW(ERR_BAD_VSIB_ADDRESSING)
	}
	void opGather2(const Xmm& x, const Address& addr, int type, uint8_t code, int mode)
	{
		if (x.hasZero()) XBYAK_THROW(ERR_INVALID_ZERO)
		const RegExp& regExp = addr.getRegExp();
		checkGather2(x, regExp.getIndex(), mode);
		int maskIdx = x.getOpmaskIdx();
		if ((type & T_M_K) && addr.getOpmaskIdx()) maskIdx = addr.getOpmaskIdx();
		if (maskIdx == 0) XBYAK_THROW(ERR_K0_IS_INVALID);
		if (!(type & T_M_K) && x.getIdx() == regExp.getIndex().getIdx()) XBYAK_THROW(ERR_SAME_REGS_ARE_INVALID);
		opVex(x, 0, addr, type, code);
	}
	/*
		xx_xy_yz ; mode = true
		xx_xy_xz ; mode = false
	*/
	void opVmov(const Operand& op, const Xmm& x, int type, uint8_t code, bool mode)
	{
		if (mode) {
			if (!op.isMEM() && !((op.isXMM() && x.isXMM()) || (op.isXMM() && x.isYMM()) || (op.isYMM() && x.isZMM()))) XBYAK_THROW(ERR_BAD_COMBINATION)
		} else {
			if (!op.isMEM() && !op.isXMM()) XBYAK_THROW(ERR_BAD_COMBINATION)
		}
		opVex(x, 0, op, type, code);
	}
	void opGatherFetch(const Address& addr, const Xmm& x, int type, uint8_t code, Operand::Kind kind)
	{
		if (addr.hasZero()) XBYAK_THROW(ERR_INVALID_ZERO)
		if (addr.getRegExp().getIndex().getKind() != kind) XBYAK_THROW(ERR_BAD_VSIB_ADDRESSING)
		opVex(x, 0, addr, type, code);
	}
	void opVnni(const Xmm& x1, const Xmm& x2, const Operand& op, int type, int code0, PreferredEncoding encoding)
	{
		if (encoding == DefaultEncoding) {
			encoding = EvexEncoding;
		}
		if (encoding == EvexEncoding) {
#ifdef XBYAK_DISABLE_AVX512
			XBYAK_THROW(ERR_EVEX_IS_INVALID)
#endif
			type |= T_MUST_EVEX;
		}
		opAVX_X_X_XM(x1, x2, op, type, code0);
	}
	void opInOut(const Reg& a, const Reg& d, uint8_t code)
	{
		if (a.getIdx() == Operand::AL && d.getIdx() == Operand::DX && d.getBit() == 16) {
			switch (a.getBit()) {
			case 8: db(code); return;
			case 16: db(0x66); db(code + 1); return;
			case 32: db(code + 1); return;
			}
		}
		XBYAK_THROW(ERR_BAD_COMBINATION)
	}
	void opInOut(const Reg& a, uint8_t code, uint8_t v)
	{
		if (a.getIdx() == Operand::AL) {
			switch (a.getBit()) {
			case 8: db(code); db(v); return;
			case 16: db(0x66); db(code + 1); db(v); return;
			case 32: db(code + 1); db(v); return;
			}
		}
		XBYAK_THROW(ERR_BAD_COMBINATION)
	}
#ifdef XBYAK64
	void opAMX(const Tmm& t1, const Address& addr, int type, int code0)
	{
		// require both base and index
		const RegExp exp = addr.getRegExp(false);
		if (exp.getBase().getBit() == 0 || exp.getIndex().getBit() == 0) XBYAK_THROW(ERR_NOT_SUPPORTED)
		opVex(t1, &tmm0, addr, type, code0);
	}
#endif
public:
	unsigned int getVersion() const { return VERSION; }
	using CodeArray::db;
	const Mmx mm0, mm1, mm2, mm3, mm4, mm5, mm6, mm7;
	const Xmm xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7;
	const Ymm ymm0, ymm1, ymm2, ymm3, ymm4, ymm5, ymm6, ymm7;
	const Zmm zmm0, zmm1, zmm2, zmm3, zmm4, zmm5, zmm6, zmm7;
	const Xmm &xm0, &xm1, &xm2, &xm3, &xm4, &xm5, &xm6, &xm7;
	const Ymm &ym0, &ym1, &ym2, &ym3, &ym4, &ym5, &ym6, &ym7;
	const Zmm &zm0, &zm1, &zm2, &zm3, &zm4, &zm5, &zm6, &zm7;
	const Reg32 eax, ecx, edx, ebx, esp, ebp, esi, edi;
	const Reg16 ax, cx, dx, bx, sp, bp, si, di;
	const Reg8 al, cl, dl, bl, ah, ch, dh, bh;
	const AddressFrame ptr, byte, word, dword, qword, xword, yword, zword; // xword is same as oword of NASM
	const AddressFrame ptr_b, xword_b, yword_b, zword_b; // broadcast such as {1to2}, {1to4}, {1to8}, {1to16}, {b}
	const Fpu st0, st1, st2, st3, st4, st5, st6, st7;
	const Opmask k0, k1, k2, k3, k4, k5, k6, k7;
	const BoundsReg bnd0, bnd1, bnd2, bnd3;
	const EvexModifierRounding T_sae, T_rn_sae, T_rd_sae, T_ru_sae, T_rz_sae; // {sae}, {rn-sae}, {rd-sae}, {ru-sae}, {rz-sae}
	const EvexModifierZero T_z; // {z}
#ifdef XBYAK64
	const Reg64 rax, rcx, rdx, rbx, rsp, rbp, rsi, rdi, r8, r9, r10, r11, r12, r13, r14, r15;
	const Reg32 r8d, r9d, r10d, r11d, r12d, r13d, r14d, r15d;
	const Reg16 r8w, r9w, r10w, r11w, r12w, r13w, r14w, r15w;
	const Reg8 r8b, r9b, r10b, r11b, r12b, r13b, r14b, r15b;
	const Reg8 spl, bpl, sil, dil;
	const Xmm xmm8, xmm9, xmm10, xmm11, xmm12, xmm13, xmm14, xmm15;
	const Xmm xmm16, xmm17, xmm18, xmm19, xmm20, xmm21, xmm22, xmm23;
	const Xmm xmm24, xmm25, xmm26, xmm27, xmm28, xmm29, xmm30, xmm31;
	const Ymm ymm8, ymm9, ymm10, ymm11, ymm12, ymm13, ymm14, ymm15;
	const Ymm ymm16, ymm17, ymm18, ymm19, ymm20, ymm21, ymm22, ymm23;
	const Ymm ymm24, ymm25, ymm26, ymm27, ymm28, ymm29, ymm30, ymm31;
	const Zmm zmm8, zmm9, zmm10, zmm11, zmm12, zmm13, zmm14, zmm15;
	const Zmm zmm16, zmm17, zmm18, zmm19, zmm20, zmm21, zmm22, zmm23;
	const Zmm zmm24, zmm25, zmm26, zmm27, zmm28, zmm29, zmm30, zmm31;
	const Tmm tmm0, tmm1, tmm2, tmm3, tmm4, tmm5, tmm6, tmm7;
	const Xmm &xm8, &xm9, &xm10, &xm11, &xm12, &xm13, &xm14, &xm15; // for my convenience
	const Xmm &xm16, &xm17, &xm18, &xm19, &xm20, &xm21, &xm22, &xm23;
	const Xmm &xm24, &xm25, &xm26, &xm27, &xm28, &xm29, &xm30, &xm31;
	const Ymm &ym8, &ym9, &ym10, &ym11, &ym12, &ym13, &ym14, &ym15;
	const Ymm &ym16, &ym17, &ym18, &ym19, &ym20, &ym21, &ym22, &ym23;
	const Ymm &ym24, &ym25, &ym26, &ym27, &ym28, &ym29, &ym30, &ym31;
	const Zmm &zm8, &zm9, &zm10, &zm11, &zm12, &zm13, &zm14, &zm15;
	const Zmm &zm16, &zm17, &zm18, &zm19, &zm20, &zm21, &zm22, &zm23;
	const Zmm &zm24, &zm25, &zm26, &zm27, &zm28, &zm29, &zm30, &zm31;
	const RegRip rip;
#endif
#ifndef XBYAK_DISABLE_SEGMENT
	const Segment es, cs, ss, ds, fs, gs;
#endif
private:
	bool isDefaultJmpNEAR_;
public:
	void L(const std::string& label) { labelMgr_.defineSlabel(label); }
	void L(Label& label) { labelMgr_.defineClabel(label); }
	Label L() { Label label; L(label); return label; }
	void inLocalLabel() { labelMgr_.enterLocal(); }
	void outLocalLabel() { labelMgr_.leaveLocal(); }
	/*
		assign src to dst
		require
		dst : does not used by L()
		src : used by L()
	*/
	void assignL(Label& dst, const Label& src) { labelMgr_.assign(dst, src); }
	/*
		put address of label to buffer
		@note the put size is 4(32-bit), 8(64-bit)
	*/
	void putL(std::string label) { putL_inner(label); }
	void putL(const Label& label) { putL_inner(label); }

	// set default type of `jmp` of undefined label to T_NEAR
	void setDefaultJmpNEAR(bool isNear) { isDefaultJmpNEAR_ = isNear; }
	void jmp(const Operand& op, LabelType type = T_AUTO) { opJmpOp(op, type, 4); }
	void jmp(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0xEB, 0xE9, 0); }
	void jmp(const char *label, LabelType type = T_AUTO) { jmp(std::string(label), type); }
	void jmp(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0xEB, 0xE9, 0); }
	void jmp(const void *addr, LabelType type = T_AUTO) { opJmpAbs(addr, type, 0xEB, 0xE9); }

	void call(const Operand& op, LabelType type = T_AUTO) { opJmpOp(op, type, 2); }
	// call(string label), not const std::string&
	void call(std::string label) { opJmp(label, T_NEAR, 0, 0xE8, 0); }
	void call(const char *label) { call(std::string(label)); }
	void call(const Label& label) { opJmp(label, T_NEAR, 0, 0xE8, 0); }
	// call(function pointer)
#ifdef XBYAK_VARIADIC_TEMPLATE
	template<class Ret, class... Params>
	void call(Ret(*func)(Params...)) { call(reinterpret_cast<const void*>(func)); }
#endif
	void call(const void *addr) { opJmpAbs(addr, T_NEAR, 0, 0xE8); }

	void test(const Operand& op, const Reg& reg)
	{
		opModRM(reg, op, op.isREG() && (op.getKind() == reg.getKind()), op.isMEM(), 0x84);
	}
	void test(const Operand& op, uint32_t imm)
	{
		verifyMemHasSize(op);
        int immSize = (std::min)(op.getBit() / 8, 4U);
		if (op.isREG() && op.getIdx() == 0) { // al, ax, eax
			rex(op);
			db(0xA8 | (op.isBit(8) ? 0 : 1));
		} else {
			opR_ModM(op, 0, 0, 0xF6, NONE, NONE, false, immSize);
		}
		db(imm, immSize);
	}
	void imul(const Reg& reg, const Operand& op)
	{
		opModRM(reg, op, op.isREG() && (reg.getKind() == op.getKind()), op.isMEM(), 0x0F, 0xAF);
	}
	void imul(const Reg& reg, const Operand& op, int imm)
	{
		int s = inner::IsInDisp8(imm) ? 1 : 0;
        int immSize = s ? 1 : reg.isREG(16) ? 2 : 4;
		opModRM(reg, op, op.isREG() && (reg.getKind() == op.getKind()), op.isMEM(), 0x69 | (s << 1), NONE, NONE, immSize);
		db(imm, immSize);
	}
	void push(const Operand& op) { opPushPop(op, 0xFF, 6, 0x50); }
	void pop(const Operand& op) { opPushPop(op, 0x8F, 0, 0x58); }
	void push(const AddressFrame& af, uint32_t imm)
	{
		if (af.bit_ == 8) {
			db(0x6A); db(imm);
		} else if (af.bit_ == 16) {
			db(0x66); db(0x68); dw(imm);
		} else {
			db(0x68); dd(imm);
		}
	}
	/* use "push(word, 4)" if you want "push word 4" */
	void push(uint32_t imm)
	{
		if (inner::IsInDisp8(imm)) {
			push(byte, imm);
		} else {
			push(dword, imm);
		}
	}
	void mov(const Operand& reg1, const Operand& reg2)
	{
		const Reg *reg = 0;
		const Address *addr = 0;
		uint8_t code = 0;
		if (reg1.isREG() && reg1.getIdx() == 0 && reg2.isMEM()) { // mov eax|ax|al, [disp]
			reg = &reg1.getReg();
			addr= &reg2.getAddress();
			code = 0xA0;
		} else
		if (reg1.isMEM() && reg2.isREG() && reg2.getIdx() == 0) { // mov [disp], eax|ax|al
			reg = &reg2.getReg();
			addr= &reg1.getAddress();
			code = 0xA2;
		}
#ifdef XBYAK64
		if (addr && addr->is64bitDisp()) {
			if (code) {
				rex(*reg);
				db(reg1.isREG(8) ? 0xA0 : reg1.isREG() ? 0xA1 : reg2.isREG(8) ? 0xA2 : 0xA3);
				db(addr->getDisp(), 8);
			} else {
				XBYAK_THROW(ERR_BAD_COMBINATION)
			}
		} else
#else
		if (code && addr->isOnlyDisp()) {
			rex(*reg, *addr);
			db(code | (reg->isBit(8) ? 0 : 1));
			dd(static_cast<uint32_t>(addr->getDisp()));
		} else
#endif
		{
			opRM_RM(reg1, reg2, 0x88);
		}
	}
	void mov(const Operand& op, uint64_t imm)
	{
		if (op.isREG()) {
			const int size = mov_imm(op.getReg(), imm);
			db(imm, size);
		} else if (op.isMEM()) {
			verifyMemHasSize(op);
			int immSize = op.getBit() / 8;
			if (immSize <= 4) {
				int64_t s = int64_t(imm) >> (immSize * 8);
				if (s != 0 && s != -1) XBYAK_THROW(ERR_IMM_IS_TOO_BIG)
			} else {
				if (!inner::IsInInt32(imm)) XBYAK_THROW(ERR_IMM_IS_TOO_BIG)
				immSize = 4;
			}
			opModM(op.getAddress(), Reg(0, Operand::REG, op.getBit()), 0xC6, NONE, NONE, immSize);
			db(static_cast<uint32_t>(imm), immSize);
		} else {
			XBYAK_THROW(ERR_BAD_COMBINATION)
		}
	}

	// The template is used to avoid ambiguity when the 2nd argument is 0.
	// When the 2nd argument is 0 the call goes to
	// `void mov(const Operand& op, uint64_t imm)`.
	template <typename T1, typename T2>
	void mov(const T1&, const T2 *) { T1::unexpected; }
	void mov(const NativeReg& reg, const Label& label)
	{
		mov_imm(reg, dummyAddr);
		putL(label);
	}
	void xchg(const Operand& op1, const Operand& op2)
	{
		const Operand *p1 = &op1, *p2 = &op2;
		if (p1->isMEM() || (p2->isREG(16 | i32e) && p2->getIdx() == 0)) {
			p1 = &op2; p2 = &op1;
		}
		if (p1->isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION)
		if (p2->isREG() && (p1->isREG(16 | i32e) && p1->getIdx() == 0)
#ifdef XBYAK64
			&& (p2->getIdx() != 0 || !p1->isREG(32))
#endif
		) {
			rex(*p2, *p1); db(0x90 | (p2->getIdx() & 7));
			return;
		}
		opModRM(*p1, *p2, (p1->isREG() && p2->isREG() && (p1->getBit() == p2->getBit())), p2->isMEM(), 0x86 | (p1->isBit(8) ? 0 : 1));
	}

#ifndef XBYAK_DISABLE_SEGMENT
	void push(const Segment& seg)
	{
		switch (seg.getIdx()) {
		case Segment::es: db(0x06); break;
		case Segment::cs: db(0x0E); break;
		case Segment::ss: db(0x16); break;
		case Segment::ds: db(0x1E); break;
		case Segment::fs: db(0x0F); db(0xA0); break;
		case Segment::gs: db(0x0F); db(0xA8); break;
		default:
			assert(0);
		}
	}
	void pop(const Segment& seg)
	{
		switch (seg.getIdx()) {
		case Segment::es: db(0x07); break;
		case Segment::cs: XBYAK_THROW(ERR_BAD_COMBINATION)
		case Segment::ss: db(0x17); break;
		case Segment::ds: db(0x1F); break;
		case Segment::fs: db(0x0F); db(0xA1); break;
		case Segment::gs: db(0x0F); db(0xA9); break;
		default:
			assert(0);
		}
	}
	void putSeg(const Segment& seg)
	{
		switch (seg.getIdx()) {
		case Segment::es: db(0x2E); break;
		case Segment::cs: db(0x36); break;
		case Segment::ss: db(0x3E); break;
		case Segment::ds: db(0x26); break;
		case Segment::fs: db(0x64); break;
		case Segment::gs: db(0x65); break;
		default:
			assert(0);
		}
	}
	void mov(const Operand& op, const Segment& seg)
	{
		opModRM(Reg8(seg.getIdx()), op, op.isREG(16|i32e), op.isMEM(), 0x8C);
	}
	void mov(const Segment& seg, const Operand& op)
	{
		opModRM(Reg8(seg.getIdx()), op.isREG(16|i32e) ? static_cast<const Operand&>(op.getReg().cvt32()) : op, op.isREG(16|i32e), op.isMEM(), 0x8E);
	}
#endif

	enum { NONE = 256 };
	// constructor
	CodeGenerator(size_t maxSize = DEFAULT_MAX_CODE_SIZE, void *userPtr = 0, Allocator *allocator = 0)
		: CodeArray(maxSize, userPtr, allocator)
		, mm0(0), mm1(1), mm2(2), mm3(3), mm4(4), mm5(5), mm6(6), mm7(7)
		, xmm0(0), xmm1(1), xmm2(2), xmm3(3), xmm4(4), xmm5(5), xmm6(6), xmm7(7)
		, ymm0(0), ymm1(1), ymm2(2), ymm3(3), ymm4(4), ymm5(5), ymm6(6), ymm7(7)
		, zmm0(0), zmm1(1), zmm2(2), zmm3(3), zmm4(4), zmm5(5), zmm6(6), zmm7(7)
		// for my convenience
		, xm0(xmm0), xm1(xmm1), xm2(xmm2), xm3(xmm3), xm4(xmm4), xm5(xmm5), xm6(xmm6), xm7(xmm7)
		, ym0(ymm0), ym1(ymm1), ym2(ymm2), ym3(ymm3), ym4(ymm4), ym5(ymm5), ym6(ymm6), ym7(ymm7)
		, zm0(zmm0), zm1(zmm1), zm2(zmm2), zm3(zmm3), zm4(zmm4), zm5(zmm5), zm6(zmm6), zm7(zmm7)

		, eax(Operand::EAX), ecx(Operand::ECX), edx(Operand::EDX), ebx(Operand::EBX), esp(Operand::ESP), ebp(Operand::EBP), esi(Operand::ESI), edi(Operand::EDI)
		, ax(Operand::AX), cx(Operand::CX), dx(Operand::DX), bx(Operand::BX), sp(Operand::SP), bp(Operand::BP), si(Operand::SI), di(Operand::DI)
		, al(Operand::AL), cl(Operand::CL), dl(Operand::DL), bl(Operand::BL), ah(Operand::AH), ch(Operand::CH), dh(Operand::DH), bh(Operand::BH)
		, ptr(0), byte(8), word(16), dword(32), qword(64), xword(128), yword(256), zword(512)
		, ptr_b(0, true), xword_b(128, true), yword_b(256, true), zword_b(512, true)
		, st0(0), st1(1), st2(2), st3(3), st4(4), st5(5), st6(6), st7(7)
		, k0(0), k1(1), k2(2), k3(3), k4(4), k5(5), k6(6), k7(7)
		, bnd0(0), bnd1(1), bnd2(2), bnd3(3)
		, T_sae(EvexModifierRounding::T_SAE), T_rn_sae(EvexModifierRounding::T_RN_SAE), T_rd_sae(EvexModifierRounding::T_RD_SAE), T_ru_sae(EvexModifierRounding::T_RU_SAE), T_rz_sae(EvexModifierRounding::T_RZ_SAE)
		, T_z()
#ifdef XBYAK64
		, rax(Operand::RAX), rcx(Operand::RCX), rdx(Operand::RDX), rbx(Operand::RBX), rsp(Operand::RSP), rbp(Operand::RBP), rsi(Operand::RSI), rdi(Operand::RDI), r8(Operand::R8), r9(Operand::R9), r10(Operand::R10), r11(Operand::R11), r12(Operand::R12), r13(Operand::R13), r14(Operand::R14), r15(Operand::R15)
		, r8d(8), r9d(9), r10d(10), r11d(11), r12d(12), r13d(13), r14d(14), r15d(15)
		, r8w(8), r9w(9), r10w(10), r11w(11), r12w(12), r13w(13), r14w(14), r15w(15)
		, r8b(8), r9b(9), r10b(10), r11b(11), r12b(12), r13b(13), r14b(14), r15b(15)
		, spl(Operand::SPL, true), bpl(Operand::BPL, true), sil(Operand::SIL, true), dil(Operand::DIL, true)
		, xmm8(8), xmm9(9), xmm10(10), xmm11(11), xmm12(12), xmm13(13), xmm14(14), xmm15(15)
		, xmm16(16), xmm17(17), xmm18(18), xmm19(19), xmm20(20), xmm21(21), xmm22(22), xmm23(23)
		, xmm24(24), xmm25(25), xmm26(26), xmm27(27), xmm28(28), xmm29(29), xmm30(30), xmm31(31)
		, ymm8(8), ymm9(9), ymm10(10), ymm11(11), ymm12(12), ymm13(13), ymm14(14), ymm15(15)
		, ymm16(16), ymm17(17), ymm18(18), ymm19(19), ymm20(20), ymm21(21), ymm22(22), ymm23(23)
		, ymm24(24), ymm25(25), ymm26(26), ymm27(27), ymm28(28), ymm29(29), ymm30(30), ymm31(31)
		, zmm8(8), zmm9(9), zmm10(10), zmm11(11), zmm12(12), zmm13(13), zmm14(14), zmm15(15)
		, zmm16(16), zmm17(17), zmm18(18), zmm19(19), zmm20(20), zmm21(21), zmm22(22), zmm23(23)
		, zmm24(24), zmm25(25), zmm26(26), zmm27(27), zmm28(28), zmm29(29), zmm30(30), zmm31(31)
		, tmm0(0), tmm1(1), tmm2(2), tmm3(3), tmm4(4), tmm5(5), tmm6(6), tmm7(7)
		// for my convenience
		, xm8(xmm8), xm9(xmm9), xm10(xmm10), xm11(xmm11), xm12(xmm12), xm13(xmm13), xm14(xmm14), xm15(xmm15)
		, xm16(xmm16), xm17(xmm17), xm18(xmm18), xm19(xmm19), xm20(xmm20), xm21(xmm21), xm22(xmm22), xm23(xmm23)
		, xm24(xmm24), xm25(xmm25), xm26(xmm26), xm27(xmm27), xm28(xmm28), xm29(xmm29), xm30(xmm30), xm31(xmm31)
		, ym8(ymm8), ym9(ymm9), ym10(ymm10), ym11(ymm11), ym12(ymm12), ym13(ymm13), ym14(ymm14), ym15(ymm15)
		, ym16(ymm16), ym17(ymm17), ym18(ymm18), ym19(ymm19), ym20(ymm20), ym21(ymm21), ym22(ymm22), ym23(ymm23)
		, ym24(ymm24), ym25(ymm25), ym26(ymm26), ym27(ymm27), ym28(ymm28), ym29(ymm29), ym30(ymm30), ym31(ymm31)
		, zm8(zmm8), zm9(zmm9), zm10(zmm10), zm11(zmm11), zm12(zmm12), zm13(zmm13), zm14(zmm14), zm15(zmm15)
		, zm16(zmm16), zm17(zmm17), zm18(zmm18), zm19(zmm19), zm20(zmm20), zm21(zmm21), zm22(zmm22), zm23(zmm23)
		, zm24(zmm24), zm25(zmm25), zm26(zmm26), zm27(zmm27), zm28(zmm28), zm29(zmm29), zm30(zmm30), zm31(zmm31)
		, rip()
#endif
#ifndef XBYAK_DISABLE_SEGMENT
		, es(Segment::es), cs(Segment::cs), ss(Segment::ss), ds(Segment::ds), fs(Segment::fs), gs(Segment::gs)
#endif
		, isDefaultJmpNEAR_(false)
	{
		labelMgr_.set(this);
	}
	void reset()
	{
		resetSize();
		labelMgr_.reset();
		labelMgr_.set(this);
	}
	bool hasUndefinedLabel() const { return labelMgr_.hasUndefSlabel() || labelMgr_.hasUndefClabel(); }
	/*
		MUST call ready() to complete generating code if you use AutoGrow mode.
		It is not necessary for the other mode if hasUndefinedLabel() is true.
	*/
	void ready(ProtectMode mode = PROTECT_RWE)
	{
		if (hasUndefinedLabel()) XBYAK_THROW(ERR_LABEL_IS_NOT_FOUND)
		if (isAutoGrow()) {
			calcJmpAddress();
			if (useProtect()) setProtectMode(mode);
		}
	}
	// set read/exec
	void readyRE() { return ready(PROTECT_RE); }
#ifdef XBYAK_TEST
	void dump(bool doClear = true)
	{
		CodeArray::dump();
		if (doClear) size_ = 0;
	}
#endif

#ifdef XBYAK_UNDEF_JNL
	#undef jnl
#endif

	/*
		use single byte nop if useMultiByteNop = false
	*/
	void nop(size_t size = 1, bool useMultiByteNop = true)
	{
		if (!useMultiByteNop) {
			for (size_t i = 0; i < size; i++) {
				db(0x90);
			}
			return;
		}
		/*
			Intel Architectures Software Developer's Manual Volume 2
			recommended multi-byte sequence of NOP instruction
			AMD and Intel seem to agree on the same sequences for up to 9 bytes:
			https://support.amd.com/TechDocs/55723_SOG_Fam_17h_Processors_3.00.pdf
		*/
		static const uint8_t nopTbl[9][9] = {
			{0x90},
			{0x66, 0x90},
			{0x0F, 0x1F, 0x00},
			{0x0F, 0x1F, 0x40, 0x00},
			{0x0F, 0x1F, 0x44, 0x00, 0x00},
			{0x66, 0x0F, 0x1F, 0x44, 0x00, 0x00},
			{0x0F, 0x1F, 0x80, 0x00, 0x00, 0x00, 0x00},
			{0x0F, 0x1F, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00},
			{0x66, 0x0F, 0x1F, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00},
		};
		const size_t n = sizeof(nopTbl) / sizeof(nopTbl[0]);
		while (size > 0) {
			size_t len = (std::min)(n, size);
			const uint8_t *seq = nopTbl[len - 1];
			db(seq, len);
			size -= len;
		}
	}

#ifndef XBYAK_DONT_READ_LIST
	const char* getVersionString() const { return "6.01"; }
	void adc(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x10, 2); }
	void adc(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x10); }
	void adcx(const Reg32e& reg, const Operand& op) { opGen(reg, op, 0xF6, 0x66, isREG32_REG32orMEM, NONE, 0x38); }
	void add(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x00, 0); }
	void add(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x00); }
	void addpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x58, 0x66, isXMM_XMMorMEM); }
	void addps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x58, 0x100, isXMM_XMMorMEM); }
	void addsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x58, 0xF2, isXMM_XMMorMEM); }
	void addss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x58, 0xF3, isXMM_XMMorMEM); }
	void addsubpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xD0, 0x66, isXMM_XMMorMEM); }
	void addsubps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xD0, 0xF2, isXMM_XMMorMEM); }
	void adox(const Reg32e& reg, const Operand& op) { opGen(reg, op, 0xF6, 0xF3, isREG32_REG32orMEM, NONE, 0x38); }
	void aesdec(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xDE, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void aesdeclast(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xDF, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void aesenc(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xDC, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void aesenclast(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xDD, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void aesimc(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xDB, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void aeskeygenassist(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0xDF, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void and_(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x20, 4); }
	void and_(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x20); }
	void andn(const Reg32e& r1, const Reg32e& r2, const Operand& op) { opGpr(r1, r2, op, T_0F38, 0xf2, true); }
	void andnpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x55, 0x66, isXMM_XMMorMEM); }
	void andnps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x55, 0x100, isXMM_XMMorMEM); }
	void andpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x54, 0x66, isXMM_XMMorMEM); }
	void andps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x54, 0x100, isXMM_XMMorMEM); }
	void bextr(const Reg32e& r1, const Operand& op, const Reg32e& r2) { opGpr(r1, op, r2, T_0F38, 0xf7, false); }
	void blendpd(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x0D, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void blendps(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x0C, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void blendvpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x15, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void blendvps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x14, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void blsi(const Reg32e& r, const Operand& op) { opGpr(Reg32e(3, r.getBit()), op, r, T_0F38, 0xf3, false); }
	void blsmsk(const Reg32e& r, const Operand& op) { opGpr(Reg32e(2, r.getBit()), op, r, T_0F38, 0xf3, false); }
	void blsr(const Reg32e& r, const Operand& op) { opGpr(Reg32e(1, r.getBit()), op, r, T_0F38, 0xf3, false); }
	void bnd() { db(0xF2); }
	void bndcl(const BoundsReg& bnd, const Operand& op) { db(0xF3); opR_ModM(op, i32e, bnd.getIdx(), 0x0F, 0x1A, NONE, !op.isMEM()); }
	void bndcn(const BoundsReg& bnd, const Operand& op) { db(0xF2); opR_ModM(op, i32e, bnd.getIdx(), 0x0F, 0x1B, NONE, !op.isMEM()); }
	void bndcu(const BoundsReg& bnd, const Operand& op) { db(0xF2); opR_ModM(op, i32e, bnd.getIdx(), 0x0F, 0x1A, NONE, !op.isMEM()); }
	void bndldx(const BoundsReg& bnd, const Address& addr) { opMIB(addr, bnd, 0x0F, 0x1A); }
	void bndmk(const BoundsReg& bnd, const Address& addr) { db(0xF3); opModM(addr, bnd, 0x0F, 0x1B); }
	void bndmov(const Address& addr, const BoundsReg& bnd) { db(0x66); opModM(addr, bnd, 0x0F, 0x1B); }
	void bndmov(const BoundsReg& bnd, const Operand& op) { db(0x66); opModRM(bnd, op, op.isBNDREG(), op.isMEM(), 0x0F, 0x1A); }
	void bndstx(const Address& addr, const BoundsReg& bnd) { opMIB(addr, bnd, 0x0F, 0x1B); }
	void bsf(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0xBC); }
	void bsr(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0xBD); }
	void bswap(const Reg32e& reg) { opModR(Reg32(1), reg, 0x0F); }
	void bt(const Operand& op, const Reg& reg) { opModRM(reg, op, op.isREG(16 | 32 | 64) && op.getBit() == reg.getBit(), op.isMEM(), 0x0f, 0xA3); }
	void bt(const Operand& op, uint8_t imm) { opR_ModM(op, 16 | 32 | 64, 4, 0x0f, 0xba, NONE, false, 1); db(imm); }
	void btc(const Operand& op, const Reg& reg) { opModRM(reg, op, op.isREG(16 | 32 | 64) && op.getBit() == reg.getBit(), op.isMEM(), 0x0f, 0xBB); }
	void btc(const Operand& op, uint8_t imm) { opR_ModM(op, 16 | 32 | 64, 7, 0x0f, 0xba, NONE, false, 1); db(imm); }
	void btr(const Operand& op, const Reg& reg) { opModRM(reg, op, op.isREG(16 | 32 | 64) && op.getBit() == reg.getBit(), op.isMEM(), 0x0f, 0xB3); }
	void btr(const Operand& op, uint8_t imm) { opR_ModM(op, 16 | 32 | 64, 6, 0x0f, 0xba, NONE, false, 1); db(imm); }
	void bts(const Operand& op, const Reg& reg) { opModRM(reg, op, op.isREG(16 | 32 | 64) && op.getBit() == reg.getBit(), op.isMEM(), 0x0f, 0xAB); }
	void bts(const Operand& op, uint8_t imm) { opR_ModM(op, 16 | 32 | 64, 5, 0x0f, 0xba, NONE, false, 1); db(imm); }
	void bzhi(const Reg32e& r1, const Operand& op, const Reg32e& r2) { opGpr(r1, op, r2, T_0F38, 0xf5, false); }
	void cbw() { db(0x66); db(0x98); }
	void cdq() { db(0x99); }
	void clc() { db(0xF8); }
	void cld() { db(0xFC); }
	void clflush(const Address& addr) { opModM(addr, Reg32(7), 0x0F, 0xAE); }
	void clflushopt(const Address& addr) { db(0x66); opModM(addr, Reg32(7), 0x0F, 0xAE); }
	void cli() { db(0xFA); }
	void clzero() { db(0x0F); db(0x01); db(0xFC); }
	void cmc() { db(0xF5); }
	void cmova(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 7); }//-V524
	void cmovae(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 3); }//-V524
	void cmovb(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 2); }//-V524
	void cmovbe(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 6); }//-V524
	void cmovc(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 2); }//-V524
	void cmove(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 4); }//-V524
	void cmovg(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 15); }//-V524
	void cmovge(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 13); }//-V524
	void cmovl(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 12); }//-V524
	void cmovle(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 14); }//-V524
	void cmovna(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 6); }//-V524
	void cmovnae(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 2); }//-V524
	void cmovnb(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 3); }//-V524
	void cmovnbe(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 7); }//-V524
	void cmovnc(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 3); }//-V524
	void cmovne(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 5); }//-V524
	void cmovng(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 14); }//-V524
	void cmovnge(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 12); }//-V524
	void cmovnl(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 13); }//-V524
	void cmovnle(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 15); }//-V524
	void cmovno(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 1); }//-V524
	void cmovnp(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 11); }//-V524
	void cmovns(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 9); }//-V524
	void cmovnz(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 5); }//-V524
	void cmovo(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 0); }//-V524
	void cmovp(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 10); }//-V524
	void cmovpe(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 10); }//-V524
	void cmovpo(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 11); }//-V524
	void cmovs(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 8); }//-V524
	void cmovz(const Reg& reg, const Operand& op) { opModRM(reg, op, op.isREG(16 | i32e), op.isMEM(), 0x0F, 0x40 | 4); }//-V524
	void cmp(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x38, 7); }
	void cmp(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x38); }
	void cmpeqpd(const Xmm& x, const Operand& op) { cmppd(x, op, 0); }
	void cmpeqps(const Xmm& x, const Operand& op) { cmpps(x, op, 0); }
	void cmpeqsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 0); }
	void cmpeqss(const Xmm& x, const Operand& op) { cmpss(x, op, 0); }
	void cmplepd(const Xmm& x, const Operand& op) { cmppd(x, op, 2); }
	void cmpleps(const Xmm& x, const Operand& op) { cmpps(x, op, 2); }
	void cmplesd(const Xmm& x, const Operand& op) { cmpsd(x, op, 2); }
	void cmpless(const Xmm& x, const Operand& op) { cmpss(x, op, 2); }
	void cmpltpd(const Xmm& x, const Operand& op) { cmppd(x, op, 1); }
	void cmpltps(const Xmm& x, const Operand& op) { cmpps(x, op, 1); }
	void cmpltsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 1); }
	void cmpltss(const Xmm& x, const Operand& op) { cmpss(x, op, 1); }
	void cmpneqpd(const Xmm& x, const Operand& op) { cmppd(x, op, 4); }
	void cmpneqps(const Xmm& x, const Operand& op) { cmpps(x, op, 4); }
	void cmpneqsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 4); }
	void cmpneqss(const Xmm& x, const Operand& op) { cmpss(x, op, 4); }
	void cmpnlepd(const Xmm& x, const Operand& op) { cmppd(x, op, 6); }
	void cmpnleps(const Xmm& x, const Operand& op) { cmpps(x, op, 6); }
	void cmpnlesd(const Xmm& x, const Operand& op) { cmpsd(x, op, 6); }
	void cmpnless(const Xmm& x, const Operand& op) { cmpss(x, op, 6); }
	void cmpnltpd(const Xmm& x, const Operand& op) { cmppd(x, op, 5); }
	void cmpnltps(const Xmm& x, const Operand& op) { cmpps(x, op, 5); }
	void cmpnltsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 5); }
	void cmpnltss(const Xmm& x, const Operand& op) { cmpss(x, op, 5); }
	void cmpordpd(const Xmm& x, const Operand& op) { cmppd(x, op, 7); }
	void cmpordps(const Xmm& x, const Operand& op) { cmpps(x, op, 7); }
	void cmpordsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 7); }
	void cmpordss(const Xmm& x, const Operand& op) { cmpss(x, op, 7); }
	void cmppd(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC2, 0x66, isXMM_XMMorMEM, imm8); }
	void cmpps(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC2, 0x100, isXMM_XMMorMEM, imm8); }
	void cmpsb() { db(0xA6); }
	void cmpsd() { db(0xA7); }
	void cmpsd(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC2, 0xF2, isXMM_XMMorMEM, imm8); }
	void cmpss(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC2, 0xF3, isXMM_XMMorMEM, imm8); }
	void cmpsw() { db(0x66); db(0xA7); }
	void cmpunordpd(const Xmm& x, const Operand& op) { cmppd(x, op, 3); }
	void cmpunordps(const Xmm& x, const Operand& op) { cmpps(x, op, 3); }
	void cmpunordsd(const Xmm& x, const Operand& op) { cmpsd(x, op, 3); }
	void cmpunordss(const Xmm& x, const Operand& op) { cmpss(x, op, 3); }
	void cmpxchg(const Operand& op, const Reg& reg) { opModRM(reg, op, (op.isREG() && reg.isREG() && op.getBit() == reg.getBit()), op.isMEM(), 0x0F, 0xB0 | (reg.isBit(8) ? 0 : 1)); }
	void cmpxchg8b(const Address& addr) { opModM(addr, Reg32(1), 0x0F, 0xC7); }
	void comisd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2F, 0x66, isXMM_XMMorMEM); }
	void comiss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2F, 0x100, isXMM_XMMorMEM); }
	void cpuid() { db(0x0F); db(0xA2); }
	void crc32(const Reg32e& reg, const Operand& op) { if (reg.isBit(32) && op.isBit(16)) db(0x66); db(0xF2); opModRM(reg, op, op.isREG(), op.isMEM(), 0x0F, 0x38, 0xF0 | (op.isBit(8) ? 0 : 1)); }
	void cvtdq2pd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xE6, 0xF3, isXMM_XMMorMEM); }
	void cvtdq2ps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5B, 0x100, isXMM_XMMorMEM); }
	void cvtpd2dq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xE6, 0xF2, isXMM_XMMorMEM); }
	void cvtpd2pi(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2D, 0x66, isMMX_XMMorMEM); }
	void cvtpd2ps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5A, 0x66, isXMM_XMMorMEM); }
	void cvtpi2pd(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2A, 0x66, isXMM_MMXorMEM); }
	void cvtpi2ps(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2A, 0x100, isXMM_MMXorMEM); }
	void cvtps2dq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5B, 0x66, isXMM_XMMorMEM); }
	void cvtps2pd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5A, 0x100, isXMM_XMMorMEM); }
	void cvtps2pi(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2D, 0x100, isMMX_XMMorMEM); }
	void cvtsd2si(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2D, 0xF2, isREG32_XMMorMEM); }
	void cvtsd2ss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5A, 0xF2, isXMM_XMMorMEM); }
	void cvtsi2sd(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2A, 0xF2, isXMM_REG32orMEM); }
	void cvtsi2ss(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2A, 0xF3, isXMM_REG32orMEM); }
	void cvtss2sd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5A, 0xF3, isXMM_XMMorMEM); }
	void cvtss2si(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2D, 0xF3, isREG32_XMMorMEM); }
	void cvttpd2dq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xE6, 0x66, isXMM_XMMorMEM); }
	void cvttpd2pi(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2C, 0x66, isMMX_XMMorMEM); }
	void cvttps2dq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5B, 0xF3, isXMM_XMMorMEM); }
	void cvttps2pi(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2C, 0x100, isMMX_XMMorMEM); }
	void cvttsd2si(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2C, 0xF2, isREG32_XMMorMEM); }
	void cvttss2si(const Operand& reg, const Operand& op) { opGen(reg, op, 0x2C, 0xF3, isREG32_XMMorMEM); }
	void cwd() { db(0x66); db(0x99); }
	void cwde() { db(0x98); }
	void dec(const Operand& op) { opIncDec(op, 0x48, 1); }
	void div(const Operand& op) { opR_ModM(op, 0, 6, 0xF6); }
	void divpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5E, 0x66, isXMM_XMMorMEM); }
	void divps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5E, 0x100, isXMM_XMMorMEM); }
	void divsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5E, 0xF2, isXMM_XMMorMEM); }
	void divss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5E, 0xF3, isXMM_XMMorMEM); }
	void dppd(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x41, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void dpps(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x40, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void emms() { db(0x0F); db(0x77); }
	void endbr32() { db(0xF3); db(0x0F); db(0x1E); db(0xFB); }
	void endbr64() { db(0xF3); db(0x0F); db(0x1E); db(0xFA); }
	void enter(uint16_t x, uint8_t y) { db(0xC8); dw(x); db(y); }
	void extractps(const Operand& op, const Xmm& xmm, uint8_t imm) { opExt(op, xmm, 0x17, imm); }
	void f2xm1() { db(0xD9); db(0xF0); }
	void fabs() { db(0xD9); db(0xE1); }
	void fadd(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 0, 0); }
	void fadd(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8C0, 0xDCC0); }
	void fadd(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8C0, 0xDCC0); }
	void faddp() { db(0xDE); db(0xC1); }
	void faddp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEC0); }
	void faddp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEC0); }
	void fbld(const Address& addr) { opModM(addr, Reg32(4), 0xDF, 0x100); }
	void fbstp(const Address& addr) { opModM(addr, Reg32(6), 0xDF, 0x100); }
	void fchs() { db(0xD9); db(0xE0); }
	void fclex() { db(0x9B); db(0xDB); db(0xE2); }
	void fcmovb(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDAC0, 0x00C0); }
	void fcmovb(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDAC0, 0x00C0); }
	void fcmovbe(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDAD0, 0x00D0); }
	void fcmovbe(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDAD0, 0x00D0); }
	void fcmove(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDAC8, 0x00C8); }
	void fcmove(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDAC8, 0x00C8); }
	void fcmovnb(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBC0, 0x00C0); }
	void fcmovnb(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBC0, 0x00C0); }
	void fcmovnbe(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBD0, 0x00D0); }
	void fcmovnbe(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBD0, 0x00D0); }
	void fcmovne(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBC8, 0x00C8); }
	void fcmovne(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBC8, 0x00C8); }
	void fcmovnu(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBD8, 0x00D8); }
	void fcmovnu(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBD8, 0x00D8); }
	void fcmovu(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDAD8, 0x00D8); }
	void fcmovu(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDAD8, 0x00D8); }
	void fcom() { db(0xD8); db(0xD1); }
	void fcom(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 2, 0); }
	void fcom(const Fpu& reg) { opFpu(reg, 0xD8, 0xD0); }
	void fcomi(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBF0, 0x00F0); }
	void fcomi(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBF0, 0x00F0); }
	void fcomip(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDFF0, 0x00F0); }
	void fcomip(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDFF0, 0x00F0); }
	void fcomp() { db(0xD8); db(0xD9); }
	void fcomp(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 3, 0); }
	void fcomp(const Fpu& reg) { opFpu(reg, 0xD8, 0xD8); }
	void fcompp() { db(0xDE); db(0xD9); }
	void fcos() { db(0xD9); db(0xFF); }
	void fdecstp() { db(0xD9); db(0xF6); }
	void fdiv(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 6, 0); }
	void fdiv(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8F0, 0xDCF8); }
	void fdiv(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8F0, 0xDCF8); }
	void fdivp() { db(0xDE); db(0xF9); }
	void fdivp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEF8); }
	void fdivp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEF8); }
	void fdivr(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 7, 0); }
	void fdivr(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8F8, 0xDCF0); }
	void fdivr(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8F8, 0xDCF0); }
	void fdivrp() { db(0xDE); db(0xF1); }
	void fdivrp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEF0); }
	void fdivrp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEF0); }
	void ffree(const Fpu& reg) { opFpu(reg, 0xDD, 0xC0); }
	void fiadd(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 0, 0); }
	void ficom(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 2, 0); }
	void ficomp(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 3, 0); }
	void fidiv(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 6, 0); }
	void fidivr(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 7, 0); }
	void fild(const Address& addr) { opFpuMem(addr, 0xDF, 0xDB, 0xDF, 0, 5); }
	void fimul(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 1, 0); }
	void fincstp() { db(0xD9); db(0xF7); }
	void finit() { db(0x9B); db(0xDB); db(0xE3); }
	void fist(const Address& addr) { opFpuMem(addr, 0xDF, 0xDB, 0x00, 2, 0); }
	void fistp(const Address& addr) { opFpuMem(addr, 0xDF, 0xDB, 0xDF, 3, 7); }
	void fisttp(const Address& addr) { opFpuMem(addr, 0xDF, 0xDB, 0xDD, 1, 0); }
	void fisub(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 4, 0); }
	void fisubr(const Address& addr) { opFpuMem(addr, 0xDE, 0xDA, 0x00, 5, 0); }
	void fld(const Address& addr) { opFpuMem(addr, 0x00, 0xD9, 0xDD, 0, 0); }
	void fld(const Fpu& reg) { opFpu(reg, 0xD9, 0xC0); }
	void fld1() { db(0xD9); db(0xE8); }
	void fldcw(const Address& addr) { opModM(addr, Reg32(5), 0xD9, 0x100); }
	void fldenv(const Address& addr) { opModM(addr, Reg32(4), 0xD9, 0x100); }
	void fldl2e() { db(0xD9); db(0xEA); }
	void fldl2t() { db(0xD9); db(0xE9); }
	void fldlg2() { db(0xD9); db(0xEC); }
	void fldln2() { db(0xD9); db(0xED); }
	void fldpi() { db(0xD9); db(0xEB); }
	void fldz() { db(0xD9); db(0xEE); }
	void fmul(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 1, 0); }
	void fmul(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8C8, 0xDCC8); }
	void fmul(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8C8, 0xDCC8); }
	void fmulp() { db(0xDE); db(0xC9); }
	void fmulp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEC8); }
	void fmulp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEC8); }
	void fnclex() { db(0xDB); db(0xE2); }
	void fninit() { db(0xDB); db(0xE3); }
	void fnop() { db(0xD9); db(0xD0); }
	void fnsave(const Address& addr) { opModM(addr, Reg32(6), 0xDD, 0x100); }
	void fnstcw(const Address& addr) { opModM(addr, Reg32(7), 0xD9, 0x100); }
	void fnstenv(const Address& addr) { opModM(addr, Reg32(6), 0xD9, 0x100); }
	void fnstsw(const Address& addr) { opModM(addr, Reg32(7), 0xDD, 0x100); }
	void fnstsw(const Reg16& r) { if (r.getIdx() != Operand::AX) XBYAK_THROW(ERR_BAD_PARAMETER) db(0xDF); db(0xE0); }
	void fpatan() { db(0xD9); db(0xF3); }
	void fprem() { db(0xD9); db(0xF8); }
	void fprem1() { db(0xD9); db(0xF5); }
	void fptan() { db(0xD9); db(0xF2); }
	void frndint() { db(0xD9); db(0xFC); }
	void frstor(const Address& addr) { opModM(addr, Reg32(4), 0xDD, 0x100); }
	void fsave(const Address& addr) { db(0x9B); opModM(addr, Reg32(6), 0xDD, 0x100); }
	void fscale() { db(0xD9); db(0xFD); }
	void fsin() { db(0xD9); db(0xFE); }
	void fsincos() { db(0xD9); db(0xFB); }
	void fsqrt() { db(0xD9); db(0xFA); }
	void fst(const Address& addr) { opFpuMem(addr, 0x00, 0xD9, 0xDD, 2, 0); }
	void fst(const Fpu& reg) { opFpu(reg, 0xDD, 0xD0); }
	void fstcw(const Address& addr) { db(0x9B); opModM(addr, Reg32(7), 0xD9, 0x100); }
	void fstenv(const Address& addr) { db(0x9B); opModM(addr, Reg32(6), 0xD9, 0x100); }
	void fstp(const Address& addr) { opFpuMem(addr, 0x00, 0xD9, 0xDD, 3, 0); }
	void fstp(const Fpu& reg) { opFpu(reg, 0xDD, 0xD8); }
	void fstsw(const Address& addr) { db(0x9B); opModM(addr, Reg32(7), 0xDD, 0x100); }
	void fstsw(const Reg16& r) { if (r.getIdx() != Operand::AX) XBYAK_THROW(ERR_BAD_PARAMETER) db(0x9B); db(0xDF); db(0xE0); }
	void fsub(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 4, 0); }
	void fsub(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8E0, 0xDCE8); }
	void fsub(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8E0, 0xDCE8); }
	void fsubp() { db(0xDE); db(0xE9); }
	void fsubp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEE8); }
	void fsubp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEE8); }
	void fsubr(const Address& addr) { opFpuMem(addr, 0x00, 0xD8, 0xDC, 5, 0); }
	void fsubr(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xD8E8, 0xDCE0); }
	void fsubr(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xD8E8, 0xDCE0); }
	void fsubrp() { db(0xDE); db(0xE1); }
	void fsubrp(const Fpu& reg1) { opFpuFpu(reg1, st0, 0x0000, 0xDEE0); }
	void fsubrp(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0x0000, 0xDEE0); }
	void ftst() { db(0xD9); db(0xE4); }
	void fucom() { db(0xDD); db(0xE1); }
	void fucom(const Fpu& reg) { opFpu(reg, 0xDD, 0xE0); }
	void fucomi(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDBE8, 0x00E8); }
	void fucomi(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDBE8, 0x00E8); }
	void fucomip(const Fpu& reg1) { opFpuFpu(st0, reg1, 0xDFE8, 0x00E8); }
	void fucomip(const Fpu& reg1, const Fpu& reg2) { opFpuFpu(reg1, reg2, 0xDFE8, 0x00E8); }
	void fucomp() { db(0xDD); db(0xE9); }
	void fucomp(const Fpu& reg) { opFpu(reg, 0xDD, 0xE8); }
	void fucompp() { db(0xDA); db(0xE9); }
	void fwait() { db(0x9B); }
	void fxam() { db(0xD9); db(0xE5); }
	void fxch() { db(0xD9); db(0xC9); }
	void fxch(const Fpu& reg) { opFpu(reg, 0xD9, 0xC8); }
	void fxrstor(const Address& addr) { opModM(addr, Reg32(1), 0x0F, 0xAE); }
	void fxtract() { db(0xD9); db(0xF4); }
	void fyl2x() { db(0xD9); db(0xF1); }
	void fyl2xp1() { db(0xD9); db(0xF9); }
	void gf2p8affineinvqb(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0xCF, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void gf2p8affineqb(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0xCE, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void gf2p8mulb(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xCF, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void haddpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x7C, 0x66, isXMM_XMMorMEM); }
	void haddps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x7C, 0xF2, isXMM_XMMorMEM); }
	void hlt() { db(0xF4); }
	void hsubpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x7D, 0x66, isXMM_XMMorMEM); }
	void hsubps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x7D, 0xF2, isXMM_XMMorMEM); }
	void idiv(const Operand& op) { opR_ModM(op, 0, 7, 0xF6); }
	void imul(const Operand& op) { opR_ModM(op, 0, 5, 0xF6); }
	void in_(const Reg& a, const Reg& d) { opInOut(a, d, 0xEC); }
	void in_(const Reg& a, uint8_t v) { opInOut(a, 0xE4, v); }
	void inc(const Operand& op) { opIncDec(op, 0x40, 0); }
	void insertps(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x21, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void int3() { db(0xCC); }
	void int_(uint8_t x) { db(0xCD); db(x); }
	void ja(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x77, 0x87, 0x0F); }//-V524
	void ja(const char* label, LabelType type = T_AUTO) { ja(std::string(label), type); }//-V524
	void ja(const void* addr) { opJmpAbs(addr, T_NEAR, 0x77, 0x87, 0x0F); }//-V524
	void ja(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x77, 0x87, 0x0F); }//-V524
	void jae(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jae(const char* label, LabelType type = T_AUTO) { jae(std::string(label), type); }//-V524
	void jae(const void* addr) { opJmpAbs(addr, T_NEAR, 0x73, 0x83, 0x0F); }//-V524
	void jae(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jb(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void jb(const char* label, LabelType type = T_AUTO) { jb(std::string(label), type); }//-V524
	void jb(const void* addr) { opJmpAbs(addr, T_NEAR, 0x72, 0x82, 0x0F); }//-V524
	void jb(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void jbe(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x76, 0x86, 0x0F); }//-V524
	void jbe(const char* label, LabelType type = T_AUTO) { jbe(std::string(label), type); }//-V524
	void jbe(const void* addr) { opJmpAbs(addr, T_NEAR, 0x76, 0x86, 0x0F); }//-V524
	void jbe(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x76, 0x86, 0x0F); }//-V524
	void jc(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void jc(const char* label, LabelType type = T_AUTO) { jc(std::string(label), type); }//-V524
	void jc(const void* addr) { opJmpAbs(addr, T_NEAR, 0x72, 0x82, 0x0F); }//-V524
	void jc(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void je(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x74, 0x84, 0x0F); }//-V524
	void je(const char* label, LabelType type = T_AUTO) { je(std::string(label), type); }//-V524
	void je(const void* addr) { opJmpAbs(addr, T_NEAR, 0x74, 0x84, 0x0F); }//-V524
	void je(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x74, 0x84, 0x0F); }//-V524
	void jg(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7F, 0x8F, 0x0F); }//-V524
	void jg(const char* label, LabelType type = T_AUTO) { jg(std::string(label), type); }//-V524
	void jg(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7F, 0x8F, 0x0F); }//-V524
	void jg(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7F, 0x8F, 0x0F); }//-V524
	void jge(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7D, 0x8D, 0x0F); }//-V524
	void jge(const char* label, LabelType type = T_AUTO) { jge(std::string(label), type); }//-V524
	void jge(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7D, 0x8D, 0x0F); }//-V524
	void jge(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7D, 0x8D, 0x0F); }//-V524
	void jl(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7C, 0x8C, 0x0F); }//-V524
	void jl(const char* label, LabelType type = T_AUTO) { jl(std::string(label), type); }//-V524
	void jl(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7C, 0x8C, 0x0F); }//-V524
	void jl(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7C, 0x8C, 0x0F); }//-V524
	void jle(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7E, 0x8E, 0x0F); }//-V524
	void jle(const char* label, LabelType type = T_AUTO) { jle(std::string(label), type); }//-V524
	void jle(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7E, 0x8E, 0x0F); }//-V524
	void jle(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7E, 0x8E, 0x0F); }//-V524
	void jna(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x76, 0x86, 0x0F); }//-V524
	void jna(const char* label, LabelType type = T_AUTO) { jna(std::string(label), type); }//-V524
	void jna(const void* addr) { opJmpAbs(addr, T_NEAR, 0x76, 0x86, 0x0F); }//-V524
	void jna(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x76, 0x86, 0x0F); }//-V524
	void jnae(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void jnae(const char* label, LabelType type = T_AUTO) { jnae(std::string(label), type); }//-V524
	void jnae(const void* addr) { opJmpAbs(addr, T_NEAR, 0x72, 0x82, 0x0F); }//-V524
	void jnae(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x72, 0x82, 0x0F); }//-V524
	void jnb(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jnb(const char* label, LabelType type = T_AUTO) { jnb(std::string(label), type); }//-V524
	void jnb(const void* addr) { opJmpAbs(addr, T_NEAR, 0x73, 0x83, 0x0F); }//-V524
	void jnb(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jnbe(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x77, 0x87, 0x0F); }//-V524
	void jnbe(const char* label, LabelType type = T_AUTO) { jnbe(std::string(label), type); }//-V524
	void jnbe(const void* addr) { opJmpAbs(addr, T_NEAR, 0x77, 0x87, 0x0F); }//-V524
	void jnbe(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x77, 0x87, 0x0F); }//-V524
	void jnc(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jnc(const char* label, LabelType type = T_AUTO) { jnc(std::string(label), type); }//-V524
	void jnc(const void* addr) { opJmpAbs(addr, T_NEAR, 0x73, 0x83, 0x0F); }//-V524
	void jnc(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x73, 0x83, 0x0F); }//-V524
	void jne(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x75, 0x85, 0x0F); }//-V524
	void jne(const char* label, LabelType type = T_AUTO) { jne(std::string(label), type); }//-V524
	void jne(const void* addr) { opJmpAbs(addr, T_NEAR, 0x75, 0x85, 0x0F); }//-V524
	void jne(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x75, 0x85, 0x0F); }//-V524
	void jng(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7E, 0x8E, 0x0F); }//-V524
	void jng(const char* label, LabelType type = T_AUTO) { jng(std::string(label), type); }//-V524
	void jng(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7E, 0x8E, 0x0F); }//-V524
	void jng(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7E, 0x8E, 0x0F); }//-V524
	void jnge(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7C, 0x8C, 0x0F); }//-V524
	void jnge(const char* label, LabelType type = T_AUTO) { jnge(std::string(label), type); }//-V524
	void jnge(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7C, 0x8C, 0x0F); }//-V524
	void jnge(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7C, 0x8C, 0x0F); }//-V524
	void jnl(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7D, 0x8D, 0x0F); }//-V524
	void jnl(const char* label, LabelType type = T_AUTO) { jnl(std::string(label), type); }//-V524
	void jnl(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7D, 0x8D, 0x0F); }//-V524
	void jnl(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7D, 0x8D, 0x0F); }//-V524
	void jnle(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7F, 0x8F, 0x0F); }//-V524
	void jnle(const char* label, LabelType type = T_AUTO) { jnle(std::string(label), type); }//-V524
	void jnle(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7F, 0x8F, 0x0F); }//-V524
	void jnle(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7F, 0x8F, 0x0F); }//-V524
	void jno(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x71, 0x81, 0x0F); }//-V524
	void jno(const char* label, LabelType type = T_AUTO) { jno(std::string(label), type); }//-V524
	void jno(const void* addr) { opJmpAbs(addr, T_NEAR, 0x71, 0x81, 0x0F); }//-V524
	void jno(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x71, 0x81, 0x0F); }//-V524
	void jnp(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7B, 0x8B, 0x0F); }//-V524
	void jnp(const char* label, LabelType type = T_AUTO) { jnp(std::string(label), type); }//-V524
	void jnp(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7B, 0x8B, 0x0F); }//-V524
	void jnp(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7B, 0x8B, 0x0F); }//-V524
	void jns(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x79, 0x89, 0x0F); }//-V524
	void jns(const char* label, LabelType type = T_AUTO) { jns(std::string(label), type); }//-V524
	void jns(const void* addr) { opJmpAbs(addr, T_NEAR, 0x79, 0x89, 0x0F); }//-V524
	void jns(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x79, 0x89, 0x0F); }//-V524
	void jnz(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x75, 0x85, 0x0F); }//-V524
	void jnz(const char* label, LabelType type = T_AUTO) { jnz(std::string(label), type); }//-V524
	void jnz(const void* addr) { opJmpAbs(addr, T_NEAR, 0x75, 0x85, 0x0F); }//-V524
	void jnz(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x75, 0x85, 0x0F); }//-V524
	void jo(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x70, 0x80, 0x0F); }//-V524
	void jo(const char* label, LabelType type = T_AUTO) { jo(std::string(label), type); }//-V524
	void jo(const void* addr) { opJmpAbs(addr, T_NEAR, 0x70, 0x80, 0x0F); }//-V524
	void jo(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x70, 0x80, 0x0F); }//-V524
	void jp(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7A, 0x8A, 0x0F); }//-V524
	void jp(const char* label, LabelType type = T_AUTO) { jp(std::string(label), type); }//-V524
	void jp(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7A, 0x8A, 0x0F); }//-V524
	void jp(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7A, 0x8A, 0x0F); }//-V524
	void jpe(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7A, 0x8A, 0x0F); }//-V524
	void jpe(const char* label, LabelType type = T_AUTO) { jpe(std::string(label), type); }//-V524
	void jpe(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7A, 0x8A, 0x0F); }//-V524
	void jpe(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7A, 0x8A, 0x0F); }//-V524
	void jpo(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x7B, 0x8B, 0x0F); }//-V524
	void jpo(const char* label, LabelType type = T_AUTO) { jpo(std::string(label), type); }//-V524
	void jpo(const void* addr) { opJmpAbs(addr, T_NEAR, 0x7B, 0x8B, 0x0F); }//-V524
	void jpo(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x7B, 0x8B, 0x0F); }//-V524
	void js(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x78, 0x88, 0x0F); }//-V524
	void js(const char* label, LabelType type = T_AUTO) { js(std::string(label), type); }//-V524
	void js(const void* addr) { opJmpAbs(addr, T_NEAR, 0x78, 0x88, 0x0F); }//-V524
	void js(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x78, 0x88, 0x0F); }//-V524
	void jz(const Label& label, LabelType type = T_AUTO) { opJmp(label, type, 0x74, 0x84, 0x0F); }//-V524
	void jz(const char* label, LabelType type = T_AUTO) { jz(std::string(label), type); }//-V524
	void jz(const void* addr) { opJmpAbs(addr, T_NEAR, 0x74, 0x84, 0x0F); }//-V524
	void jz(std::string label, LabelType type = T_AUTO) { opJmp(label, type, 0x74, 0x84, 0x0F); }//-V524
	void lahf() { db(0x9F); }
	void lddqu(const Xmm& xmm, const Address& addr) { db(0xF2); opModM(addr, xmm, 0x0F, 0xF0); }
	void ldmxcsr(const Address& addr) { opModM(addr, Reg32(2), 0x0F, 0xAE); }
	void lea(const Reg& reg, const Address& addr) { if (!reg.isBit(16 | i32e)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER) opModM(addr, reg, 0x8D); }
	void leave() { db(0xC9); }
	void lfence() { db(0x0F); db(0xAE); db(0xE8); }
	void lfs(const Reg& reg, const Address& addr) { opLoadSeg(addr, reg, 0x0F, 0xB4); }
	void lgs(const Reg& reg, const Address& addr) { opLoadSeg(addr, reg, 0x0F, 0xB5); }
	void lock() { db(0xF0); }
	void lodsb() { db(0xAC); }
	void lodsd() { db(0xAD); }
	void lodsw() { db(0x66); db(0xAD); }
	void loop(const Label& label) { opJmp(label, T_SHORT, 0xE2, 0, 0); }
	void loop(const char* label) { loop(std::string(label)); }
	void loop(std::string label) { opJmp(label, T_SHORT, 0xE2, 0, 0); }
	void loope(const Label& label) { opJmp(label, T_SHORT, 0xE1, 0, 0); }
	void loope(const char* label) { loope(std::string(label)); }
	void loope(std::string label) { opJmp(label, T_SHORT, 0xE1, 0, 0); }
	void loopne(const Label& label) { opJmp(label, T_SHORT, 0xE0, 0, 0); }
	void loopne(const char* label) { loopne(std::string(label)); }
	void loopne(std::string label) { opJmp(label, T_SHORT, 0xE0, 0, 0); }
	void lss(const Reg& reg, const Address& addr) { opLoadSeg(addr, reg, 0x0F, 0xB2); }
	void lzcnt(const Reg& reg, const Operand& op) { opSp1(reg, op, 0xF3, 0x0F, 0xBD); }
	void maskmovdqu(const Xmm& reg1, const Xmm& reg2) { db(0x66);  opModR(reg1, reg2, 0x0F, 0xF7); }
	void maskmovq(const Mmx& reg1, const Mmx& reg2) { if (!reg1.isMMX() || !reg2.isMMX()) XBYAK_THROW(ERR_BAD_COMBINATION) opModR(reg1, reg2, 0x0F, 0xF7); }
	void maxpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5F, 0x66, isXMM_XMMorMEM); }
	void maxps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5F, 0x100, isXMM_XMMorMEM); }
	void maxsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5F, 0xF2, isXMM_XMMorMEM); }
	void maxss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5F, 0xF3, isXMM_XMMorMEM); }
	void mfence() { db(0x0F); db(0xAE); db(0xF0); }
	void minpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5D, 0x66, isXMM_XMMorMEM); }
	void minps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5D, 0x100, isXMM_XMMorMEM); }
	void minsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5D, 0xF2, isXMM_XMMorMEM); }
	void minss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5D, 0xF3, isXMM_XMMorMEM); }
	void monitor() { db(0x0F); db(0x01); db(0xC8); }
	void monitorx() { db(0x0F); db(0x01); db(0xFA); }
	void movapd(const Address& addr, const Xmm& xmm) { db(0x66); opModM(addr, xmm, 0x0F, 0x29); }
	void movapd(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x28, 0x66); }
	void movaps(const Address& addr, const Xmm& xmm) { opModM(addr, xmm, 0x0F, 0x29); }
	void movaps(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x28, 0x100); }
	void movbe(const Address& addr, const Reg& reg) { opModM(addr, reg, 0x0F, 0x38, 0xF1); }
	void movbe(const Reg& reg, const Address& addr) { opModM(addr, reg, 0x0F, 0x38, 0xF0); }
	void movd(const Address& addr, const Mmx& mmx) { if (mmx.isXMM()) db(0x66); opModM(addr, mmx, 0x0F, 0x7E); }
	void movd(const Mmx& mmx, const Address& addr) { if (mmx.isXMM()) db(0x66); opModM(addr, mmx, 0x0F, 0x6E); }
	void movd(const Mmx& mmx, const Reg32& reg) { if (mmx.isXMM()) db(0x66); opModR(mmx, reg, 0x0F, 0x6E); }
	void movd(const Reg32& reg, const Mmx& mmx) { if (mmx.isXMM()) db(0x66); opModR(mmx, reg, 0x0F, 0x7E); }
	void movddup(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x12, 0xF2, isXMM_XMMorMEM, NONE, NONE); }
	void movdq2q(const Mmx& mmx, const Xmm& xmm) { db(0xF2); opModR(mmx, xmm, 0x0F, 0xD6); }
	void movdqa(const Address& addr, const Xmm& xmm) { db(0x66); opModM(addr, xmm, 0x0F, 0x7F); }
	void movdqa(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x6F, 0x66); }
	void movdqu(const Address& addr, const Xmm& xmm) { db(0xF3); opModM(addr, xmm, 0x0F, 0x7F); }
	void movdqu(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x6F, 0xF3); }
	void movhlps(const Xmm& reg1, const Xmm& reg2) { opModR(reg1, reg2, 0x0F, 0x12); }
	void movhpd(const Operand& op1, const Operand& op2) { opMovXMM(op1, op2, 0x16, 0x66); }
	void movhps(const Operand& op1, const Operand& op2) { opMovXMM(op1, op2, 0x16, 0x100); }
	void movlhps(const Xmm& reg1, const Xmm& reg2) { opModR(reg1, reg2, 0x0F, 0x16); }
	void movlpd(const Operand& op1, const Operand& op2) { opMovXMM(op1, op2, 0x12, 0x66); }
	void movlps(const Operand& op1, const Operand& op2) { opMovXMM(op1, op2, 0x12, 0x100); }
	void movmskpd(const Reg32e& reg, const Xmm& xmm) { db(0x66); movmskps(reg, xmm); }
	void movmskps(const Reg32e& reg, const Xmm& xmm) { opModR(reg, xmm, 0x0F, 0x50); }
	void movntdq(const Address& addr, const Xmm& reg) { opModM(addr, Reg16(reg.getIdx()), 0x0F, 0xE7); }
	void movntdqa(const Xmm& xmm, const Address& addr) { db(0x66); opModM(addr, xmm, 0x0F, 0x38, 0x2A); }
	void movnti(const Address& addr, const Reg32e& reg) { opModM(addr, reg, 0x0F, 0xC3); }
	void movntpd(const Address& addr, const Xmm& reg) { opModM(addr, Reg16(reg.getIdx()), 0x0F, 0x2B); }
	void movntps(const Address& addr, const Xmm& xmm) { opModM(addr, Mmx(xmm.getIdx()), 0x0F, 0x2B); }
	void movntq(const Address& addr, const Mmx& mmx) { if (!mmx.isMMX()) XBYAK_THROW(ERR_BAD_COMBINATION) opModM(addr, mmx, 0x0F, 0xE7); }
	void movq(const Address& addr, const Mmx& mmx) { if (mmx.isXMM()) db(0x66); opModM(addr, mmx, 0x0F, mmx.isXMM() ? 0xD6 : 0x7F); }
	void movq(const Mmx& mmx, const Operand& op) { if (mmx.isXMM()) db(0xF3); opModRM(mmx, op, (mmx.getKind() == op.getKind()), op.isMEM(), 0x0F, mmx.isXMM() ? 0x7E : 0x6F); }
	void movq2dq(const Xmm& xmm, const Mmx& mmx) { db(0xF3); opModR(xmm, mmx, 0x0F, 0xD6); }
	void movsb() { db(0xA4); }
	void movsd() { db(0xA5); }
	void movsd(const Address& addr, const Xmm& xmm) { db(0xF2); opModM(addr, xmm, 0x0F, 0x11); }
	void movsd(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x10, 0xF2); }
	void movshdup(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x16, 0xF3, isXMM_XMMorMEM, NONE, NONE); }
	void movsldup(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x12, 0xF3, isXMM_XMMorMEM, NONE, NONE); }
	void movss(const Address& addr, const Xmm& xmm) { db(0xF3); opModM(addr, xmm, 0x0F, 0x11); }
	void movss(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x10, 0xF3); }
	void movsw() { db(0x66); db(0xA5); }
	void movsx(const Reg& reg, const Operand& op) { opMovxx(reg, op, 0xBE); }
	void movupd(const Address& addr, const Xmm& xmm) { db(0x66); opModM(addr, xmm, 0x0F, 0x11); }
	void movupd(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x10, 0x66); }
	void movups(const Address& addr, const Xmm& xmm) { opModM(addr, xmm, 0x0F, 0x11); }
	void movups(const Xmm& xmm, const Operand& op) { opMMX(xmm, op, 0x10, 0x100); }
	void movzx(const Reg& reg, const Operand& op) { opMovxx(reg, op, 0xB6); }
	void mpsadbw(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x42, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void mul(const Operand& op) { opR_ModM(op, 0, 4, 0xF6); }
	void mulpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x59, 0x66, isXMM_XMMorMEM); }
	void mulps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x59, 0x100, isXMM_XMMorMEM); }
	void mulsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x59, 0xF2, isXMM_XMMorMEM); }
	void mulss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x59, 0xF3, isXMM_XMMorMEM); }
	void mulx(const Reg32e& r1, const Reg32e& r2, const Operand& op) { opGpr(r1, r2, op, T_F2 | T_0F38, 0xf6, true); }
	void mwait() { db(0x0F); db(0x01); db(0xC9); }
	void mwaitx() { db(0x0F); db(0x01); db(0xFB); }
	void neg(const Operand& op) { opR_ModM(op, 0, 3, 0xF6); }
	void not_(const Operand& op) { opR_ModM(op, 0, 2, 0xF6); }
	void or_(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x08, 1); }
	void or_(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x08); }
	void orpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x56, 0x66, isXMM_XMMorMEM); }
	void orps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x56, 0x100, isXMM_XMMorMEM); }
	void out_(const Reg& d, const Reg& a) { opInOut(a, d, 0xEE); }
	void out_(uint8_t v, const Reg& a) { opInOut(a, 0xE6, v); }
	void outsb() { db(0x6E); }
	void outsd() { db(0x6F); }
	void outsw() { db(0x66); db(0x6F); }
	void pabsb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x1C, 0x66, NONE, 0x38); }
	void pabsd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x1E, 0x66, NONE, 0x38); }
	void pabsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x1D, 0x66, NONE, 0x38); }
	void packssdw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x6B); }
	void packsswb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x63); }
	void packusdw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2B, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void packuswb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x67); }
	void paddb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xFC); }
	void paddd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xFE); }
	void paddq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD4); }
	void paddsb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xEC); }
	void paddsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xED); }
	void paddusb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDC); }
	void paddusw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDD); }
	void paddw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xFD); }
	void palignr(const Mmx& mmx, const Operand& op, int imm) { opMMX(mmx, op, 0x0f, 0x66, static_cast<uint8_t>(imm), 0x3a); }
	void pand(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDB); }
	void pandn(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDF); }
	void pause() { db(0xF3); db(0x90); }
	void pavgb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE0); }
	void pavgw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE3); }
	void pblendvb(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x10, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pblendw(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x0E, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void pclmulhqhdq(const Xmm& xmm, const Operand& op) { pclmulqdq(xmm, op, 0x11); }
	void pclmulhqlqdq(const Xmm& xmm, const Operand& op) { pclmulqdq(xmm, op, 0x01); }
	void pclmullqhdq(const Xmm& xmm, const Operand& op) { pclmulqdq(xmm, op, 0x10); }
	void pclmullqlqdq(const Xmm& xmm, const Operand& op) { pclmulqdq(xmm, op, 0x00); }
	void pclmulqdq(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x44, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void pcmpeqb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x74); }
	void pcmpeqd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x76); }
	void pcmpeqq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x29, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pcmpeqw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x75); }
	void pcmpestri(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x61, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void pcmpestrm(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x60, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void pcmpgtb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x64); }
	void pcmpgtd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x66); }
	void pcmpgtq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x37, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pcmpgtw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x65); }
	void pcmpistri(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x63, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void pcmpistrm(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x62, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void pdep(const Reg32e& r1, const Reg32e& r2, const Operand& op) { opGpr(r1, r2, op, T_F2 | T_0F38, 0xf5, true); }
	void pext(const Reg32e& r1, const Reg32e& r2, const Operand& op) { opGpr(r1, r2, op, T_F3 | T_0F38, 0xf5, true); }
	void pextrb(const Operand& op, const Xmm& xmm, uint8_t imm) { opExt(op, xmm, 0x14, imm); }
	void pextrd(const Operand& op, const Xmm& xmm, uint8_t imm) { opExt(op, xmm, 0x16, imm); }
	void pextrw(const Operand& op, const Mmx& xmm, uint8_t imm) { opExt(op, xmm, 0x15, imm, true); }
	void phaddd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x02, 0x66, NONE, 0x38); }
	void phaddsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x03, 0x66, NONE, 0x38); }
	void phaddw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x01, 0x66, NONE, 0x38); }
	void phminposuw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x41, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void phsubd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x06, 0x66, NONE, 0x38); }
	void phsubsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x07, 0x66, NONE, 0x38); }
	void phsubw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x05, 0x66, NONE, 0x38); }
	void pinsrb(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x20, 0x66, isXMM_REG32orMEM, imm, 0x3A); }
	void pinsrd(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x22, 0x66, isXMM_REG32orMEM, imm, 0x3A); }
	void pinsrw(const Mmx& mmx, const Operand& op, int imm) { if (!op.isREG(32) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opGen(mmx, op, 0xC4, mmx.isXMM() ? 0x66 : NONE, 0, imm); }
	void pmaddubsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x04, 0x66, NONE, 0x38); }
	void pmaddwd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF5); }
	void pmaxsb(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3C, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmaxsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3D, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmaxsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xEE); }
	void pmaxub(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDE); }
	void pmaxud(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3F, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmaxuw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3E, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pminsb(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x38, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pminsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x39, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pminsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xEA); }
	void pminub(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xDA); }
	void pminud(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3B, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pminuw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x3A, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovmskb(const Reg32e& reg, const Mmx& mmx) { if (mmx.isXMM()) db(0x66); opModR(reg, mmx, 0x0F, 0xD7); }
	void pmovsxbd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x21, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovsxbq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x22, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovsxbw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x20, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovsxdq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x25, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovsxwd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x23, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovsxwq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x24, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxbd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x31, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxbq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x32, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxbw(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x30, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxdq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x35, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxwd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x33, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmovzxwq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x34, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmuldq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x28, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmulhrsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x0B, 0x66, NONE, 0x38); }
	void pmulhuw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE4); }
	void pmulhw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE5); }
	void pmulld(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x40, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void pmullw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD5); }
	void pmuludq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF4); }
	void popcnt(const Reg& reg, const Operand& op) { opSp1(reg, op, 0xF3, 0x0F, 0xB8); }
	void popf() { db(0x9D); }
	void por(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xEB); }
	void prefetchnta(const Address& addr) { opModM(addr, Reg32(0), 0x0F, 0x18); }
	void prefetcht0(const Address& addr) { opModM(addr, Reg32(1), 0x0F, 0x18); }
	void prefetcht1(const Address& addr) { opModM(addr, Reg32(2), 0x0F, 0x18); }
	void prefetcht2(const Address& addr) { opModM(addr, Reg32(3), 0x0F, 0x18); }
	void prefetchw(const Address& addr) { opModM(addr, Reg32(1), 0x0F, 0x0D); }
	void prefetchwt1(const Address& addr) { opModM(addr, Reg32(2), 0x0F, 0x0D); }
	void psadbw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF6); }
	void pshufb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x00, 0x66, NONE, 0x38); }
	void pshufd(const Mmx& mmx, const Operand& op, uint8_t imm8) { opMMX(mmx, op, 0x70, 0x66, imm8); }
	void pshufhw(const Mmx& mmx, const Operand& op, uint8_t imm8) { opMMX(mmx, op, 0x70, 0xF3, imm8); }
	void pshuflw(const Mmx& mmx, const Operand& op, uint8_t imm8) { opMMX(mmx, op, 0x70, 0xF2, imm8); }
	void pshufw(const Mmx& mmx, const Operand& op, uint8_t imm8) { opMMX(mmx, op, 0x70, 0x00, imm8); }
	void psignb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x08, 0x66, NONE, 0x38); }
	void psignd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x0A, 0x66, NONE, 0x38); }
	void psignw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x09, 0x66, NONE, 0x38); }
	void pslld(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF2); }
	void pslld(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x72, 6); }
	void pslldq(const Xmm& xmm, int imm8) { opMMX_IMM(xmm, imm8, 0x73, 7); }
	void psllq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF3); }
	void psllq(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x73, 6); }
	void psllw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF1); }
	void psllw(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x71, 6); }
	void psrad(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE2); }
	void psrad(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x72, 4); }
	void psraw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE1); }
	void psraw(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x71, 4); }
	void psrld(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD2); }
	void psrld(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x72, 2); }
	void psrldq(const Xmm& xmm, int imm8) { opMMX_IMM(xmm, imm8, 0x73, 3); }
	void psrlq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD3); }
	void psrlq(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x73, 2); }
	void psrlw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD1); }
	void psrlw(const Mmx& mmx, int imm8) { opMMX_IMM(mmx, imm8, 0x71, 2); }
	void psubb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF8); }
	void psubd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xFA); }
	void psubq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xFB); }
	void psubsb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE8); }
	void psubsw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xE9); }
	void psubusb(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD8); }
	void psubusw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xD9); }
	void psubw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xF9); }
	void ptest(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x17, 0x66, isXMM_XMMorMEM, NONE, 0x38); }
	void punpckhbw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x68); }
	void punpckhdq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x6A); }
	void punpckhqdq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x6D, 0x66, isXMM_XMMorMEM); }
	void punpckhwd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x69); }
	void punpcklbw(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x60); }
	void punpckldq(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x62); }
	void punpcklqdq(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x6C, 0x66, isXMM_XMMorMEM); }
	void punpcklwd(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0x61); }
	void pushf() { db(0x9C); }
	void pxor(const Mmx& mmx, const Operand& op) { opMMX(mmx, op, 0xEF); }
	void rcl(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 2); }
	void rcl(const Operand& op, int imm) { opShift(op, imm, 2); }
	void rcpps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x53, 0x100, isXMM_XMMorMEM); }
	void rcpss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x53, 0xF3, isXMM_XMMorMEM); }
	void rcr(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 3); }
	void rcr(const Operand& op, int imm) { opShift(op, imm, 3); }
	void rdmsr() { db(0x0F); db(0x32); }
	void rdpmc() { db(0x0F); db(0x33); }
	void rdrand(const Reg& r) { if (r.isBit(8)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER) opModR(Reg(6, Operand::REG, r.getBit()), r, 0x0F, 0xC7); }
	void rdseed(const Reg& r) { if (r.isBit(8)) XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER) opModR(Reg(7, Operand::REG, r.getBit()), r, 0x0F, 0xC7); }
	void rdtsc() { db(0x0F); db(0x31); }
	void rdtscp() { db(0x0F); db(0x01); db(0xF9); }
	void rep() { db(0xF3); }
	void repe() { db(0xF3); }
	void repne() { db(0xF2); }
	void repnz() { db(0xF2); }
	void repz() { db(0xF3); }
	void ret(int imm = 0) { if (imm) { db(0xC2); dw(imm); } else { db(0xC3); } }
	void retf(int imm = 0) { if (imm) { db(0xCA); dw(imm); } else { db(0xCB); } }
	void rol(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 0); }
	void rol(const Operand& op, int imm) { opShift(op, imm, 0); }
	void ror(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 1); }
	void ror(const Operand& op, int imm) { opShift(op, imm, 1); }
	void rorx(const Reg32e& r, const Operand& op, uint8_t imm) { opGpr(r, op, Reg32e(0, r.getBit()), T_0F3A | T_F2, 0xF0, false, imm); }
	void roundpd(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x09, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void roundps(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0x08, 0x66, isXMM_XMMorMEM, imm, 0x3A); }
	void roundsd(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x0B, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void roundss(const Xmm& xmm, const Operand& op, int imm) { opGen(xmm, op, 0x0A, 0x66, isXMM_XMMorMEM, static_cast<uint8_t>(imm), 0x3A); }
	void rsqrtps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x52, 0x100, isXMM_XMMorMEM); }
	void rsqrtss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x52, 0xF3, isXMM_XMMorMEM); }
	void sahf() { db(0x9E); }
	void sal(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 4); }
	void sal(const Operand& op, int imm) { opShift(op, imm, 4); }
	void sar(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 7); }
	void sar(const Operand& op, int imm) { opShift(op, imm, 7); }
	void sarx(const Reg32e& r1, const Operand& op, const Reg32e& r2) { opGpr(r1, op, r2, T_F3 | T_0F38, 0xf7, false); }
	void sbb(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x18, 3); }
	void sbb(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x18); }
	void scasb() { db(0xAE); }
	void scasd() { db(0xAF); }
	void scasw() { db(0x66); db(0xAF); }
	void seta(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 7); }//-V524
	void setae(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 3); }//-V524
	void setb(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 2); }//-V524
	void setbe(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 6); }//-V524
	void setc(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 2); }//-V524
	void sete(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 4); }//-V524
	void setg(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 15); }//-V524
	void setge(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 13); }//-V524
	void setl(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 12); }//-V524
	void setle(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 14); }//-V524
	void setna(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 6); }//-V524
	void setnae(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 2); }//-V524
	void setnb(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 3); }//-V524
	void setnbe(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 7); }//-V524
	void setnc(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 3); }//-V524
	void setne(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 5); }//-V524
	void setng(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 14); }//-V524
	void setnge(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 12); }//-V524
	void setnl(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 13); }//-V524
	void setnle(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 15); }//-V524
	void setno(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 1); }//-V524
	void setnp(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 11); }//-V524
	void setns(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 9); }//-V524
	void setnz(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 5); }//-V524
	void seto(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 0); }//-V524
	void setp(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 10); }//-V524
	void setpe(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 10); }//-V524
	void setpo(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 11); }//-V524
	void sets(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 8); }//-V524
	void setz(const Operand& op) { opR_ModM(op, 8, 0, 0x0F, 0x90 | 4); }//-V524
	void sfence() { db(0x0F); db(0xAE); db(0xF8); }
	void sha1msg1(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xC9, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void sha1msg2(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xCA, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void sha1nexte(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xC8, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void sha1rnds4(const Xmm& xmm, const Operand& op, uint8_t imm) { opGen(xmm, op, 0xCC, NONE, isXMM_XMMorMEM, imm, 0x3A); }
	void sha256msg1(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xCC, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void sha256msg2(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xCD, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void sha256rnds2(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0xCB, NONE, isXMM_XMMorMEM, NONE, 0x38); }
	void shl(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 4); }
	void shl(const Operand& op, int imm) { opShift(op, imm, 4); }
	void shld(const Operand& op, const Reg& reg, const Reg8& _cl) { opShxd(op, reg, 0, 0xA4, &_cl); }
	void shld(const Operand& op, const Reg& reg, uint8_t imm) { opShxd(op, reg, imm, 0xA4); }
	void shlx(const Reg32e& r1, const Operand& op, const Reg32e& r2) { opGpr(r1, op, r2, T_66 | T_0F38, 0xf7, false); }
	void shr(const Operand& op, const Reg8& _cl) { opShift(op, _cl, 5); }
	void shr(const Operand& op, int imm) { opShift(op, imm, 5); }
	void shrd(const Operand& op, const Reg& reg, const Reg8& _cl) { opShxd(op, reg, 0, 0xAC, &_cl); }
	void shrd(const Operand& op, const Reg& reg, uint8_t imm) { opShxd(op, reg, imm, 0xAC); }
	void shrx(const Reg32e& r1, const Operand& op, const Reg32e& r2) { opGpr(r1, op, r2, T_F2 | T_0F38, 0xf7, false); }
	void shufpd(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC6, 0x66, isXMM_XMMorMEM, imm8); }
	void shufps(const Xmm& xmm, const Operand& op, uint8_t imm8) { opGen(xmm, op, 0xC6, 0x100, isXMM_XMMorMEM, imm8); }
	void sqrtpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x51, 0x66, isXMM_XMMorMEM); }
	void sqrtps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x51, 0x100, isXMM_XMMorMEM); }
	void sqrtsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x51, 0xF2, isXMM_XMMorMEM); }
	void sqrtss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x51, 0xF3, isXMM_XMMorMEM); }
	void stac() { db(0x0F); db(0x01); db(0xCB); }
	void stc() { db(0xF9); }
	void std() { db(0xFD); }
	void sti() { db(0xFB); }
	void stmxcsr(const Address& addr) { opModM(addr, Reg32(3), 0x0F, 0xAE); }
	void stosb() { db(0xAA); }
	void stosd() { db(0xAB); }
	void stosw() { db(0x66); db(0xAB); }
	void sub(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x28, 5); }
	void sub(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x28); }
	void subpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5C, 0x66, isXMM_XMMorMEM); }
	void subps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5C, 0x100, isXMM_XMMorMEM); }
	void subsd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5C, 0xF2, isXMM_XMMorMEM); }
	void subss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x5C, 0xF3, isXMM_XMMorMEM); }
	void sysenter() { db(0x0F); db(0x34); }
	void sysexit() { db(0x0F); db(0x35); }
	void tzcnt(const Reg& reg, const Operand& op) { opSp1(reg, op, 0xF3, 0x0F, 0xBC); }
	void ucomisd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2E, 0x66, isXMM_XMMorMEM); }
	void ucomiss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2E, 0x100, isXMM_XMMorMEM); }
	void ud2() { db(0x0F); db(0x0B); }
	void unpckhpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x15, 0x66, isXMM_XMMorMEM); }
	void unpckhps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x15, 0x100, isXMM_XMMorMEM); }
	void unpcklpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x14, 0x66, isXMM_XMMorMEM); }
	void unpcklps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x14, 0x100, isXMM_XMMorMEM); }
	void vaddpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x58); }
	void vaddps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x58); }
	void vaddsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x58); }
	void vaddss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x58); }
	void vaddsubpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F | T_YMM, 0xD0); }
	void vaddsubps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_F2 | T_0F | T_YMM, 0xD0); }
	void vaesdec(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F38 | T_YMM | T_EVEX, 0xDE); }
	void vaesdeclast(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F38 | T_YMM | T_EVEX, 0xDF); }
	void vaesenc(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F38 | T_YMM | T_EVEX, 0xDC); }
	void vaesenclast(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F38 | T_YMM | T_EVEX, 0xDD); }
	void vaesimc(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_W0, 0xDB); }
	void vaeskeygenassist(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A, 0xDF, imm); }
	void vandnpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x55); }
	void vandnps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x55); }
	void vandpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x54); }
	void vandps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x54); }
	void vblendpd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x0D, imm); }
	void vblendps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x0C, imm); }
	void vblendvpd(const Xmm& x1, const Xmm& x2, const Operand& op, const Xmm& x4) { opAVX_X_X_XM(x1, x2, op, T_0F3A | T_66 | T_YMM, 0x4B, x4.getIdx() << 4); }
	void vblendvps(const Xmm& x1, const Xmm& x2, const Operand& op, const Xmm& x4) { opAVX_X_X_XM(x1, x2, op, T_0F3A | T_66 | T_YMM, 0x4A, x4.getIdx() << 4); }
	void vbroadcastf128(const Ymm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x1A); }
	void vbroadcasti128(const Ymm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x5A); }
	void vbroadcastsd(const Ymm& y, const Operand& op) { if (!op.isMEM() && !(y.isYMM() && op.isXMM()) && !(y.isZMM() && op.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(y, op, T_0F38 | T_66 | T_W0 | T_YMM | T_EVEX | T_EW1 | T_N8, 0x19); }
	void vbroadcastss(const Xmm& x, const Operand& op) { if (!(op.isXMM() || op.isMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_W0 | T_YMM | T_EVEX, 0x18); }
	void vcmpeq_ospd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 16); }
	void vcmpeq_osps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 16); }
	void vcmpeq_ossd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 16); }
	void vcmpeq_osss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 16); }
	void vcmpeq_uqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 8); }
	void vcmpeq_uqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 8); }
	void vcmpeq_uqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 8); }
	void vcmpeq_uqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 8); }
	void vcmpeq_uspd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 24); }
	void vcmpeq_usps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 24); }
	void vcmpeq_ussd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 24); }
	void vcmpeq_usss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 24); }
	void vcmpeqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 0); }
	void vcmpeqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 0); }
	void vcmpeqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 0); }
	void vcmpeqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 0); }
	void vcmpfalse_ospd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 27); }
	void vcmpfalse_osps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 27); }
	void vcmpfalse_ossd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 27); }
	void vcmpfalse_osss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 27); }
	void vcmpfalsepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 11); }
	void vcmpfalseps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 11); }
	void vcmpfalsesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 11); }
	void vcmpfalsess(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 11); }
	void vcmpge_oqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 29); }
	void vcmpge_oqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 29); }
	void vcmpge_oqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 29); }
	void vcmpge_oqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 29); }
	void vcmpgepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 13); }
	void vcmpgeps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 13); }
	void vcmpgesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 13); }
	void vcmpgess(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 13); }
	void vcmpgt_oqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 30); }
	void vcmpgt_oqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 30); }
	void vcmpgt_oqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 30); }
	void vcmpgt_oqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 30); }
	void vcmpgtpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 14); }
	void vcmpgtps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 14); }
	void vcmpgtsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 14); }
	void vcmpgtss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 14); }
	void vcmple_oqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 18); }
	void vcmple_oqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 18); }
	void vcmple_oqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 18); }
	void vcmple_oqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 18); }
	void vcmplepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 2); }
	void vcmpleps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 2); }
	void vcmplesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 2); }
	void vcmpless(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 2); }
	void vcmplt_oqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 17); }
	void vcmplt_oqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 17); }
	void vcmplt_oqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 17); }
	void vcmplt_oqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 17); }
	void vcmpltpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 1); }
	void vcmpltps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 1); }
	void vcmpltsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 1); }
	void vcmpltss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 1); }
	void vcmpneq_oqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 12); }
	void vcmpneq_oqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 12); }
	void vcmpneq_oqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 12); }
	void vcmpneq_oqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 12); }
	void vcmpneq_ospd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 28); }
	void vcmpneq_osps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 28); }
	void vcmpneq_ossd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 28); }
	void vcmpneq_osss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 28); }
	void vcmpneq_uspd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 20); }
	void vcmpneq_usps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 20); }
	void vcmpneq_ussd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 20); }
	void vcmpneq_usss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 20); }
	void vcmpneqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 4); }
	void vcmpneqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 4); }
	void vcmpneqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 4); }
	void vcmpneqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 4); }
	void vcmpnge_uqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 25); }
	void vcmpnge_uqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 25); }
	void vcmpnge_uqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 25); }
	void vcmpnge_uqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 25); }
	void vcmpngepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 9); }
	void vcmpngeps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 9); }
	void vcmpngesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 9); }
	void vcmpngess(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 9); }
	void vcmpngt_uqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 26); }
	void vcmpngt_uqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 26); }
	void vcmpngt_uqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 26); }
	void vcmpngt_uqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 26); }
	void vcmpngtpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 10); }
	void vcmpngtps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 10); }
	void vcmpngtsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 10); }
	void vcmpngtss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 10); }
	void vcmpnle_uqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 22); }
	void vcmpnle_uqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 22); }
	void vcmpnle_uqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 22); }
	void vcmpnle_uqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 22); }
	void vcmpnlepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 6); }
	void vcmpnleps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 6); }
	void vcmpnlesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 6); }
	void vcmpnless(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 6); }
	void vcmpnlt_uqpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 21); }
	void vcmpnlt_uqps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 21); }
	void vcmpnlt_uqsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 21); }
	void vcmpnlt_uqss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 21); }
	void vcmpnltpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 5); }
	void vcmpnltps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 5); }
	void vcmpnltsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 5); }
	void vcmpnltss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 5); }
	void vcmpord_spd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 23); }
	void vcmpord_sps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 23); }
	void vcmpord_ssd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 23); }
	void vcmpord_sss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 23); }
	void vcmpordpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 7); }
	void vcmpordps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 7); }
	void vcmpordsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 7); }
	void vcmpordss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 7); }
	void vcmppd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0xC2, imm); }
	void vcmpps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_0F | T_YMM, 0xC2, imm); }
	void vcmpsd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_0F, 0xC2, imm); }
	void vcmpss(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_0F, 0xC2, imm); }
	void vcmptrue_uspd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 31); }
	void vcmptrue_usps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 31); }
	void vcmptrue_ussd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 31); }
	void vcmptrue_usss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 31); }
	void vcmptruepd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 15); }
	void vcmptrueps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 15); }
	void vcmptruesd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 15); }
	void vcmptruess(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 15); }
	void vcmpunord_spd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 19); }
	void vcmpunord_sps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 19); }
	void vcmpunord_ssd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 19); }
	void vcmpunord_sss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 19); }
	void vcmpunordpd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmppd(x1, x2, op, 3); }
	void vcmpunordps(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpps(x1, x2, op, 3); }
	void vcmpunordsd(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpsd(x1, x2, op, 3); }
	void vcmpunordss(const Xmm& x1, const Xmm& x2, const Operand& op) { vcmpss(x1, x2, op, 3); }
	void vcomisd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_66 | T_0F | T_EW1 | T_EVEX | T_SAE_X, 0x2F); }
	void vcomiss(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_0F | T_EW0 | T_EVEX | T_SAE_X, 0x2F); }
	void vcvtdq2pd(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_0F | T_F3 | T_YMM | T_EVEX | T_EW0 | T_B32 | T_N8 | T_N_VL, 0xE6); }
	void vcvtdq2ps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5B); }
	void vcvtpd2dq(const Xmm& x, const Operand& op) { opCvt2(x, op, T_0F | T_F2 | T_YMM | T_EVEX | T_EW1 | T_B64 | T_ER_Z, 0xE6); }
	void vcvtpd2ps(const Xmm& x, const Operand& op) { opCvt2(x, op, T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_B64 | T_ER_Z, 0x5A); }
	void vcvtph2ps(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_0F38 | T_66 | T_W0 | T_EVEX | T_EW0 | T_N8 | T_N_VL | T_SAE_Y, 0x13); }
	void vcvtps2dq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5B); }
	void vcvtps2pd(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_0F | T_YMM | T_EVEX | T_EW0 | T_B32 | T_N8 | T_N_VL | T_SAE_Y, 0x5A); }
	void vcvtps2ph(const Operand& op, const Xmm& x, uint8_t imm) { checkCvt1(x, op); opVex(x, 0, op, T_0F3A | T_66 | T_W0 | T_EVEX | T_EW0 | T_N8 | T_N_VL | T_SAE_Y | T_M_K, 0x1D, imm); }
	void vcvtsd2si(const Reg32& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F2 | T_W0 | T_EVEX | T_EW0 | T_N4 | T_ER_X, 0x2D); }
	void vcvtsd2ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_F2 | T_0F | T_EW1 | T_EVEX | T_ER_X, 0x5A); }
	void vcvtsi2sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opCvt3(x1, x2, op, T_0F | T_F2 | T_EVEX, T_W1 | T_EW1 | T_ER_X | T_N8, T_W0 | T_EW0 | T_N4, 0x2A); }
	void vcvtsi2ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opCvt3(x1, x2, op, T_0F | T_F3 | T_EVEX | T_ER_X, T_W1 | T_EW1 | T_N8, T_W0 | T_EW0 | T_N4, 0x2A); }
	void vcvtss2sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_F3 | T_0F | T_EW0 | T_EVEX | T_SAE_X, 0x5A); }
	void vcvtss2si(const Reg32& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F3 | T_W0 | T_EVEX | T_EW0 | T_ER_X | T_N8, 0x2D); }
	void vcvttpd2dq(const Xmm& x, const Operand& op) { opCvt2(x, op, T_66 | T_0F | T_YMM | T_EVEX | T_EW1 | T_B64 | T_ER_Z, 0xE6); }
	void vcvttps2dq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_EW0 | T_YMM | T_EVEX | T_SAE_Z | T_B32, 0x5B); }
	void vcvttsd2si(const Reg32& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F2 | T_W0 | T_EVEX | T_EW0 | T_N4 | T_SAE_X, 0x2C); }
	void vcvttss2si(const Reg32& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F3 | T_W0 | T_EVEX | T_EW0 | T_SAE_X | T_N8, 0x2C); }
	void vdivpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x5E); }
	void vdivps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5E); }
	void vdivsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x5E); }
	void vdivss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x5E); }
	void vdppd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0, 0x41, imm); }
	void vdpps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x40, imm); }
	void vextractf128(const Operand& op, const Ymm& y, uint8_t imm) { if (!(op.isXMEM() && y.isYMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y, 0, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x19, imm); }
	void vextracti128(const Operand& op, const Ymm& y, uint8_t imm) { if (!(op.isXMEM() && y.isYMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y, 0, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x39, imm); }
	void vextractps(const Operand& op, const Xmm& x, uint8_t imm) { if (!((op.isREG(32) || op.isMEM()) && x.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x, 0, op, T_0F3A | T_66 | T_W0 | T_EVEX | T_N4, 0x17, imm); }
	void vfmadd132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x98); }
	void vfmadd132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x98); }
	void vfmadd132sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0x99); }
	void vfmadd132ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0x99); }
	void vfmadd213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xA8); }
	void vfmadd213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xA8); }
	void vfmadd213sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xA9); }
	void vfmadd213ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xA9); }
	void vfmadd231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xB8); }
	void vfmadd231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xB8); }
	void vfmadd231sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xB9); }
	void vfmadd231ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xB9); }
	void vfmaddsub132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x96); }
	void vfmaddsub132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x96); }
	void vfmaddsub213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xA6); }
	void vfmaddsub213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xA6); }
	void vfmaddsub231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xB6); }
	void vfmaddsub231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xB6); }
	void vfmsub132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x9A); }
	void vfmsub132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x9A); }
	void vfmsub132sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0x9B); }
	void vfmsub132ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0x9B); }
	void vfmsub213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xAA); }
	void vfmsub213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xAA); }
	void vfmsub213sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xAB); }
	void vfmsub213ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xAB); }
	void vfmsub231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xBA); }
	void vfmsub231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xBA); }
	void vfmsub231sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xBB); }
	void vfmsub231ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xBB); }
	void vfmsubadd132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x97); }
	void vfmsubadd132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x97); }
	void vfmsubadd213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xA7); }
	void vfmsubadd213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xA7); }
	void vfmsubadd231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xB7); }
	void vfmsubadd231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xB7); }
	void vfnmadd132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x9C); }
	void vfnmadd132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x9C); }
	void vfnmadd132sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0x9D); }
	void vfnmadd132ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0x9D); }
	void vfnmadd213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xAC); }
	void vfnmadd213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xAC); }
	void vfnmadd213sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xAD); }
	void vfnmadd213ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xAD); }
	void vfnmadd231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xBC); }
	void vfnmadd231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xBC); }
	void vfnmadd231sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xBD); }
	void vfnmadd231ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xBD); }
	void vfnmsub132pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x9E); }
	void vfnmsub132ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x9E); }
	void vfnmsub132sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0x9F); }
	void vfnmsub132ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0x9F); }
	void vfnmsub213pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xAE); }
	void vfnmsub213ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xAE); }
	void vfnmsub213sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xAF); }
	void vfnmsub213ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xAF); }
	void vfnmsub231pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xBE); }
	void vfnmsub231ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0xBE); }
	void vfnmsub231sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_W1 | T_EW1 | T_EVEX | T_ER_X, 0xBF); }
	void vfnmsub231ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_W0 | T_EW0 | T_EVEX | T_ER_X, 0xBF); }
	void vgatherdpd(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W1, 0x92, 0); }
	void vgatherdps(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W0, 0x92, 1); }
	void vgatherqpd(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W1, 0x93, 1); }
	void vgatherqps(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W0, 0x93, 2); }
	void vgf2p8affineinvqb(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W1 | T_EW1 | T_YMM | T_EVEX | T_SAE_Z | T_B64, 0xCF, imm); }
	void vgf2p8affineqb(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W1 | T_EW1 | T_YMM | T_EVEX | T_SAE_Z | T_B64, 0xCE, imm); }
	void vgf2p8mulb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_SAE_Z, 0xCF); }
	void vhaddpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F | T_YMM, 0x7C); }
	void vhaddps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_F2 | T_0F | T_YMM, 0x7C); }
	void vhsubpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_66 | T_0F | T_YMM, 0x7D); }
	void vhsubps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_F2 | T_0F | T_YMM, 0x7D); }
	void vinsertf128(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { if (!(y1.isYMM() && y2.isYMM() && op.isXMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y1, &y2, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x18, imm); }
	void vinserti128(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { if (!(y1.isYMM() && y2.isYMM() && op.isXMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y1, &y2, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x38, imm); }
	void vinsertps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_W0 | T_EW0 | T_EVEX, 0x21, imm); }
	void vlddqu(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_F2 | T_W0 | T_YMM, 0xF0); }
	void vldmxcsr(const Address& addr) { opAVX_X_X_XM(xm2, xm0, addr, T_0F, 0xAE); }
	void vmaskmovdqu(const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x1, xm0, x2, T_0F | T_66, 0xF7); }
	void vmaskmovpd(const Address& addr, const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x2, x1, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x2F); }
	void vmaskmovpd(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x2D); }
	void vmaskmovps(const Address& addr, const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x2, x1, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x2E); }
	void vmaskmovps(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x2C); }
	void vmaxpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x5F); }
	void vmaxps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5F); }
	void vmaxsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x5F); }
	void vmaxss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x5F); }
	void vminpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x5D); }
	void vminps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5D); }
	void vminsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x5D); }
	void vminss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x5D); }
	void vmovapd(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_M_K, 0x29); }
	void vmovapd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX, 0x28); }
	void vmovaps(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_0F | T_EW0 | T_YMM | T_EVEX | T_M_K, 0x29); }
	void vmovaps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX, 0x28); }
	void vmovd(const Operand& op, const Xmm& x) { if (!op.isREG(32) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, xm0, op, T_0F | T_66 | T_W0 | T_EVEX | T_N4, 0x7E); }
	void vmovd(const Xmm& x, const Operand& op) { if (!op.isREG(32) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, xm0, op, T_0F | T_66 | T_W0 | T_EVEX | T_N4, 0x6E); }
	void vmovddup(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_DUP | T_F2 | T_0F | T_EW1 | T_YMM | T_EVEX | T_ER_X | T_ER_Y | T_ER_Z, 0x12); }
	void vmovdqa(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_66 | T_0F | T_YMM, 0x7F); }
	void vmovdqa(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_YMM, 0x6F); }
	void vmovdqu(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_F3 | T_0F | T_YMM, 0x7F); }
	void vmovdqu(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_YMM, 0x6F); }
	void vmovhlps(const Xmm& x1, const Xmm& x2, const Operand& op = Operand()) { if (!op.isNone() && !op.isXMM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x1, x2, op, T_0F | T_EVEX | T_EW0, 0x12); }
	void vmovhpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_0F | T_66 | T_EVEX | T_EW1 | T_N8, 0x17); }
	void vmovhpd(const Xmm& x, const Operand& op1, const Operand& op2 = Operand()) { if (!op2.isNone() && !op2.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, op1, op2, T_0F | T_66 | T_EVEX | T_EW1 | T_N8, 0x16); }
	void vmovhps(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_0F | T_EVEX | T_EW0 | T_N8, 0x17); }
	void vmovhps(const Xmm& x, const Operand& op1, const Operand& op2 = Operand()) { if (!op2.isNone() && !op2.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, op1, op2, T_0F | T_EVEX | T_EW0 | T_N8, 0x16); }
	void vmovlhps(const Xmm& x1, const Xmm& x2, const Operand& op = Operand()) { if (!op.isNone() && !op.isXMM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x1, x2, op, T_0F | T_EVEX | T_EW0, 0x16); }
	void vmovlpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_0F | T_66 | T_EVEX | T_EW1 | T_N8, 0x13); }
	void vmovlpd(const Xmm& x, const Operand& op1, const Operand& op2 = Operand()) { if (!op2.isNone() && !op2.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, op1, op2, T_0F | T_66 | T_EVEX | T_EW1 | T_N8, 0x12); }
	void vmovlps(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_0F | T_EVEX | T_EW0 | T_N8, 0x13); }
	void vmovlps(const Xmm& x, const Operand& op1, const Operand& op2 = Operand()) { if (!op2.isNone() && !op2.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, op1, op2, T_0F | T_EVEX | T_EW0 | T_N8, 0x12); }
	void vmovmskpd(const Reg& r, const Xmm& x) { if (!r.isBit(i32e)) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x.isXMM() ? Xmm(r.getIdx()) : Ymm(r.getIdx()), cvtIdx0(x), x, T_0F | T_66 | T_W0 | T_YMM, 0x50); }
	void vmovmskps(const Reg& r, const Xmm& x) { if (!r.isBit(i32e)) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x.isXMM() ? Xmm(r.getIdx()) : Ymm(r.getIdx()), cvtIdx0(x), x, T_0F | T_W0 | T_YMM, 0x50); }
	void vmovntdq(const Address& addr, const Xmm& x) { opVex(x, 0, addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW0, 0xE7); }
	void vmovntdqa(const Xmm& x, const Address& addr) { opVex(x, 0, addr, T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0, 0x2A); }
	void vmovntpd(const Address& addr, const Xmm& x) { opVex(x, 0, addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW1, 0x2B); }
	void vmovntps(const Address& addr, const Xmm& x) { opVex(x, 0, addr, T_0F | T_YMM | T_EVEX | T_EW0, 0x2B); }
	void vmovq(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_0F | T_66 | T_EVEX | T_EW1 | T_N8, x.getIdx() < 16 ? 0xD6 : 0x7E); }
	void vmovq(const Xmm& x, const Address& addr) { int type, code; if (x.getIdx() < 16) { type = T_0F | T_F3; code = 0x7E; } else { type = T_0F | T_66 | T_EVEX | T_EW1 | T_N8; code = 0x6E; } opAVX_X_X_XM(x, xm0, addr, type, code); }
	void vmovq(const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x1, xm0, x2, T_0F | T_F3 | T_EVEX | T_EW1 | T_N8, 0x7E); }
	void vmovsd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_N8 | T_F2 | T_0F | T_EW1 | T_EVEX | T_M_K, 0x11); }
	void vmovsd(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, xm0, addr, T_N8 | T_F2 | T_0F | T_EW1 | T_EVEX, 0x10); }
	void vmovsd(const Xmm& x1, const Xmm& x2, const Operand& op = Operand()) { if (!op.isNone() && !op.isXMM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x1, x2, op, T_N8 | T_F2 | T_0F | T_EW1 | T_EVEX, 0x10); }
	void vmovshdup(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_EW0 | T_YMM | T_EVEX, 0x16); }
	void vmovsldup(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_EW0 | T_YMM | T_EVEX, 0x12); }
	void vmovss(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, xm0, addr, T_N4 | T_F3 | T_0F | T_EW0 | T_EVEX | T_M_K, 0x11); }
	void vmovss(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, xm0, addr, T_N4 | T_F3 | T_0F | T_EW0 | T_EVEX, 0x10); }
	void vmovss(const Xmm& x1, const Xmm& x2, const Operand& op = Operand()) { if (!op.isNone() && !op.isXMM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x1, x2, op, T_N4 | T_F3 | T_0F | T_EW0 | T_EVEX, 0x10); }
	void vmovupd(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_M_K, 0x11); }
	void vmovupd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX, 0x10); }
	void vmovups(const Address& addr, const Xmm& xmm) { opAVX_X_XM_IMM(xmm, addr, T_0F | T_EW0 | T_YMM | T_EVEX | T_M_K, 0x11); }
	void vmovups(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX, 0x10); }
	void vmpsadbw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x42, imm); }
	void vmulpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x59); }
	void vmulps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x59); }
	void vmulsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x59); }
	void vmulss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x59); }
	void vorpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x56); }
	void vorps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x56); }
	void vpabsb(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x1C); }
	void vpabsd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x1E); }
	void vpabsw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x1D); }
	void vpackssdw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x6B); }
	void vpacksswb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x63); }
	void vpackusdw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x2B); }
	void vpackuswb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x67); }
	void vpaddb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xFC); }
	void vpaddd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0xFE); }
	void vpaddq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0xD4); }
	void vpaddsb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xEC); }
	void vpaddsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xED); }
	void vpaddusb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xDC); }
	void vpaddusw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xDD); }
	void vpaddw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xFD); }
	void vpalignr(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_YMM | T_EVEX, 0x0F, imm); }
	void vpand(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0xDB); }
	void vpandn(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0xDF); }
	void vpavgb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE0); }
	void vpavgw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE3); }
	void vpblendd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x02, imm); }
	void vpblendvb(const Xmm& x1, const Xmm& x2, const Operand& op, const Xmm& x4) { opAVX_X_X_XM(x1, x2, op, T_0F3A | T_66 | T_YMM, 0x4C, x4.getIdx() << 4); }
	void vpblendw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM, 0x0E, imm); }
	void vpbroadcastb(const Xmm& x, const Operand& op) { if (!(op.isXMM() || op.isMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(x, op, T_N1 | T_66 | T_0F38 | T_W0 | T_YMM | T_EVEX, 0x78); }
	void vpbroadcastd(const Xmm& x, const Operand& op) { if (!(op.isXMM() || op.isMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_W0 | T_YMM | T_EVEX, 0x58); }
	void vpbroadcastq(const Xmm& x, const Operand& op) { if (!(op.isXMM() || op.isMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_W0 | T_EW1 | T_YMM | T_EVEX, 0x59); }
	void vpbroadcastw(const Xmm& x, const Operand& op) { if (!(op.isXMM() || op.isMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_XM_IMM(x, op, T_N2 | T_66 | T_0F38 | T_W0 | T_YMM | T_EVEX, 0x79); }
	void vpclmulqdq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0 | T_YMM | T_EVEX, 0x44, imm); }
	void vpcmpeqb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x74); }
	void vpcmpeqd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x76); }
	void vpcmpeqq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x29); }
	void vpcmpeqw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x75); }
	void vpcmpestri(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A, 0x61, imm); }
	void vpcmpestrm(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A, 0x60, imm); }
	void vpcmpgtb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x64); }
	void vpcmpgtd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x66); }
	void vpcmpgtq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x37); }
	void vpcmpgtw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0x65); }
	void vpcmpistri(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A, 0x63, imm); }
	void vpcmpistrm(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A, 0x62, imm); }
	void vpdpbusd(const Xmm& x1, const Xmm& x2, const Operand& op, PreferredEncoding encoding = DefaultEncoding) { opVnni(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_B32, 0x50, encoding); }
	void vpdpbusds(const Xmm& x1, const Xmm& x2, const Operand& op, PreferredEncoding encoding = DefaultEncoding) { opVnni(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_B32, 0x51, encoding); }
	void vpdpwssd(const Xmm& x1, const Xmm& x2, const Operand& op, PreferredEncoding encoding = DefaultEncoding) { opVnni(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_B32, 0x52, encoding); }
	void vpdpwssds(const Xmm& x1, const Xmm& x2, const Operand& op, PreferredEncoding encoding = DefaultEncoding) { opVnni(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_B32, 0x53, encoding); }
	void vperm2f128(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { if (!(y1.isYMM() && y2.isYMM() && op.isYMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y1, &y2, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x06, imm); }
	void vperm2i128(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { if (!(y1.isYMM() && y2.isYMM() && op.isYMEM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(y1, &y2, op, T_0F3A | T_66 | T_W0 | T_YMM, 0x46, imm); }
	void vpermd(const Ymm& y1, const Ymm& y2, const Operand& op) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x36); }
	void vpermilpd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x0D); }
	void vpermilpd(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_EVEX | T_B64, 0x05, imm); }
	void vpermilps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x0C); }
	void vpermilps(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_EVEX | T_B32, 0x04, imm); }
	void vpermpd(const Ymm& y, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(y, op, T_66 | T_0F3A | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x01, imm); }
	void vpermpd(const Ymm& y1, const Ymm& y2, const Operand& op) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x16); }
	void vpermps(const Ymm& y1, const Ymm& y2, const Operand& op) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x16); }
	void vpermq(const Ymm& y, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(y, op, T_66 | T_0F3A | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x00, imm); }
	void vpermq(const Ymm& y1, const Ymm& y2, const Operand& op) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F38 | T_W0 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x36); }
	void vpextrb(const Operand& op, const Xmm& x, uint8_t imm) { if (!((op.isREG(8 | 16 | i32e) || op.isMEM()) && x.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x, 0, op, T_0F3A | T_66 | T_EVEX | T_N1, 0x14, imm); }
	void vpextrd(const Operand& op, const Xmm& x, uint8_t imm) { if (!((op.isREG(32) || op.isMEM()) && x.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x, 0, op, T_0F3A | T_66 | T_W0 | T_EVEX | T_EW0 | T_N4, 0x16, imm); }
	void vpextrq(const Operand& op, const Xmm& x, uint8_t imm) { if (!((op.isREG(64) || op.isMEM()) && x.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x, 0, op, T_0F3A | T_66 | T_W1 | T_EVEX | T_EW1 | T_N8, 0x16, imm); }
	void vpextrw(const Operand& op, const Xmm& x, uint8_t imm) { if (!((op.isREG(16 | i32e) || op.isMEM()) && x.isXMM())) XBYAK_THROW(ERR_BAD_COMBINATION) if (op.isREG() && x.getIdx() < 16) { opAVX_X_X_XM(Xmm(op.getIdx()), xm0, x, T_0F | T_66, 0xC5, imm); } else { opVex(x, 0, op, T_0F3A | T_66 | T_EVEX | T_N2, 0x15, imm); } }
	void vpgatherdd(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W0, 0x90, 1); }
	void vpgatherdq(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W1, 0x90, 0); }
	void vpgatherqd(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W0, 0x91, 2); }
	void vpgatherqq(const Xmm& x1, const Address& addr, const Xmm& x2) { opGather(x1, addr, x2, T_0F38 | T_66 | T_YMM | T_VSIB | T_W1, 0x91, 1); }
	void vphaddd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x02); }
	void vphaddsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x03); }
	void vphaddw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x01); }
	void vphminposuw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38, 0x41); }
	void vphsubd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x06); }
	void vphsubsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x07); }
	void vphsubw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x05); }
	void vpinsrb(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { if (!(x1.isXMM() && x2.isXMM() && (op.isREG(32) || op.isMEM()))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x1, &x2, op, T_0F3A | T_66 | T_EVEX | T_N1, 0x20, imm); }
	void vpinsrd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { if (!(x1.isXMM() && x2.isXMM() && (op.isREG(32) || op.isMEM()))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x1, &x2, op, T_0F3A | T_66 | T_W0 | T_EVEX | T_EW0 | T_N4, 0x22, imm); }
	void vpinsrq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { if (!(x1.isXMM() && x2.isXMM() && (op.isREG(64) || op.isMEM()))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x1, &x2, op, T_0F3A | T_66 | T_W1 | T_EVEX | T_EW1 | T_N8, 0x22, imm); }
	void vpinsrw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { if (!(x1.isXMM() && x2.isXMM() && (op.isREG(32) || op.isMEM()))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x1, &x2, op, T_0F | T_66 | T_EVEX | T_N2, 0xC4, imm); }
	void vpmaddubsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x04); }
	void vpmaddwd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xF5); }
	void vpmaskmovd(const Address& addr, const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x2, x1, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x8E); }
	void vpmaskmovd(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_66 | T_W0 | T_YMM, 0x8C); }
	void vpmaskmovq(const Address& addr, const Xmm& x1, const Xmm& x2) { opAVX_X_X_XM(x2, x1, addr, T_0F38 | T_66 | T_W1 | T_YMM, 0x8E); }
	void vpmaskmovq(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_66 | T_W1 | T_YMM, 0x8C); }
	void vpmaxsb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x3C); }
	void vpmaxsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x3D); }
	void vpmaxsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xEE); }
	void vpmaxub(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xDE); }
	void vpmaxud(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x3F); }
	void vpmaxuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x3E); }
	void vpminsb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x38); }
	void vpminsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x39); }
	void vpminsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xEA); }
	void vpminub(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xDA); }
	void vpminud(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x3B); }
	void vpminuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x3A); }
	void vpmovmskb(const Reg32e& r, const Xmm& x) { if (!x.is(Operand::XMM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(x.isYMM() ? Ymm(r.getIdx()) : Xmm(r.getIdx()), 0, x, T_0F | T_66 | T_YMM, 0xD7); }
	void vpmovsxbd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x21); }
	void vpmovsxbq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N2 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x22); }
	void vpmovsxbw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x20); }
	void vpmovsxdq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX, 0x25); }
	void vpmovsxwd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x23); }
	void vpmovsxwq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x24); }
	void vpmovzxbd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x31); }
	void vpmovzxbq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N2 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x32); }
	void vpmovzxbw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x30); }
	void vpmovzxdq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX, 0x35); }
	void vpmovzxwd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x33); }
	void vpmovzxwq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_N_VL | T_66 | T_0F38 | T_YMM | T_EVEX, 0x34); }
	void vpmuldq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x28); }
	void vpmulhrsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x0B); }
	void vpmulhuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE4); }
	void vpmulhw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE5); }
	void vpmulld(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x40); }
	void vpmullw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xD5); }
	void vpmuludq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0xF4); }
	void vpor(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0xEB); }
	void vpsadbw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xF6); }
	void vpshufb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x00); }
	void vpshufd(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x70, imm); }
	void vpshufhw(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_YMM | T_EVEX, 0x70, imm); }
	void vpshuflw(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_F2 | T_0F | T_YMM | T_EVEX, 0x70, imm); }
	void vpsignb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x08); }
	void vpsignd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x0A); }
	void vpsignw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_YMM, 0x09); }
	void vpslld(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 6), x, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32 | T_MEM_EVEX, 0x72, imm); }
	void vpslld(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW0 | T_YMM | T_EVEX, 0xF2); }
	void vpslldq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 7), x, op, T_66 | T_0F | T_YMM | T_EVEX | T_MEM_EVEX, 0x73, imm); }
	void vpsllq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 6), x, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64 | T_MEM_EVEX, 0x73, imm); }
	void vpsllq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW1 | T_YMM | T_EVEX, 0xF3); }
	void vpsllvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x47); }
	void vpsllvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x47); }
	void vpsllw(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 6), x, op, T_66 | T_0F | T_YMM | T_EVEX | T_MEM_EVEX, 0x71, imm); }
	void vpsllw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_YMM | T_EVEX, 0xF1); }
	void vpsrad(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 4), x, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32 | T_MEM_EVEX, 0x72, imm); }
	void vpsrad(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW0 | T_YMM | T_EVEX, 0xE2); }
	void vpsravd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x46); }
	void vpsraw(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 4), x, op, T_66 | T_0F | T_YMM | T_EVEX | T_MEM_EVEX, 0x71, imm); }
	void vpsraw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_YMM | T_EVEX, 0xE1); }
	void vpsrld(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 2), x, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32 | T_MEM_EVEX, 0x72, imm); }
	void vpsrld(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW0 | T_YMM | T_EVEX, 0xD2); }
	void vpsrldq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 3), x, op, T_66 | T_0F | T_YMM | T_EVEX | T_MEM_EVEX, 0x73, imm); }
	void vpsrlq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 2), x, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64 | T_MEM_EVEX, 0x73, imm); }
	void vpsrlq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW1 | T_YMM | T_EVEX, 0xD3); }
	void vpsrlvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W0 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x45); }
	void vpsrlvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_W1 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x45); }
	void vpsrlw(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 2), x, op, T_66 | T_0F | T_YMM | T_EVEX | T_MEM_EVEX, 0x71, imm); }
	void vpsrlw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_YMM | T_EVEX, 0xD1); }
	void vpsubb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xF8); }
	void vpsubd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0xFA); }
	void vpsubq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0xFB); }
	void vpsubsb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE8); }
	void vpsubsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xE9); }
	void vpsubusb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xD8); }
	void vpsubusw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xD9); }
	void vpsubw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0xF9); }
	void vptest(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM, 0x17); }
	void vpunpckhbw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x68); }
	void vpunpckhdq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x6A); }
	void vpunpckhqdq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0x6D); }
	void vpunpckhwd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x69); }
	void vpunpcklbw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x60); }
	void vpunpckldq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x62); }
	void vpunpcklqdq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0x6C); }
	void vpunpcklwd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM | T_EVEX, 0x61); }
	void vpxor(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_YMM, 0xEF); }
	void vrcpps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_YMM, 0x53); }
	void vrcpss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_0F, 0x53); }
	void vroundpd(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A | T_YMM, 0x09, imm); }
	void vroundps(const Xmm& xm, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F3A | T_YMM, 0x08, imm); }
	void vroundsd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0, 0x0B, imm); }
	void vroundss(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_W0, 0x0A, imm); }
	void vrsqrtps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_YMM, 0x52); }
	void vrsqrtss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_0F, 0x52); }
	void vshufpd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0xC6, imm); }
	void vshufps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0xC6, imm); }
	void vsqrtpd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x51); }
	void vsqrtps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x51); }
	void vsqrtsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_F2 | T_0F | T_EW1 | T_EVEX | T_ER_X, 0x51); }
	void vsqrtss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_F3 | T_0F | T_EW0 | T_EVEX | T_ER_X, 0x51); }
	void vstmxcsr(const Address& addr) { opAVX_X_X_XM(xm3, xm0, addr, T_0F, 0xAE); }
	void vsubpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x5C); }
	void vsubps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x5C); }
	void vsubsd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F2 | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x5C); }
	void vsubss(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_F3 | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x5C); }
	void vtestpd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM, 0x0F); }
	void vtestps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM, 0x0E); }
	void vucomisd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N8 | T_66 | T_0F | T_EW1 | T_EVEX | T_SAE_X, 0x2E); }
	void vucomiss(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_N4 | T_0F | T_EW0 | T_EVEX | T_SAE_X, 0x2E); }
	void vunpckhpd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0x15); }
	void vunpckhps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x15); }
	void vunpcklpd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_B64, 0x14); }
	void vunpcklps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0x14); }
	void vxorpd(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_ER_Z | T_B64, 0x57); }
	void vxorps(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_0F | T_EW0 | T_YMM | T_EVEX | T_ER_Z | T_B32, 0x57); }
	void vzeroall() { db(0xC5); db(0xFC); db(0x77); }
	void vzeroupper() { db(0xC5); db(0xF8); db(0x77); }
	void wait() { db(0x9B); }
	void wbinvd() { db(0x0F); db(0x09); }
	void wrmsr() { db(0x0F); db(0x30); }
	void xadd(const Operand& op, const Reg& reg) { opModRM(reg, op, (op.isREG() && reg.isREG() && op.getBit() == reg.getBit()), op.isMEM(), 0x0F, 0xC0 | (reg.isBit(8) ? 0 : 1)); }
	void xgetbv() { db(0x0F); db(0x01); db(0xD0); }
	void xlatb() { db(0xD7); }
	void xor_(const Operand& op, uint32_t imm) { opRM_I(op, imm, 0x30, 6); }
	void xor_(const Operand& op1, const Operand& op2) { opRM_RM(op1, op2, 0x30); }
	void xorpd(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x57, 0x66, isXMM_XMMorMEM); }
	void xorps(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x57, 0x100, isXMM_XMMorMEM); }
#ifdef XBYAK_ENABLE_OMITTED_OPERAND
	void vblendpd(const Xmm& x, const Operand& op, uint8_t imm) { vblendpd(x, x, op, imm); }
	void vblendps(const Xmm& x, const Operand& op, uint8_t imm) { vblendps(x, x, op, imm); }
	void vblendvpd(const Xmm& x1, const Operand& op, const Xmm& x4) { vblendvpd(x1, x1, op, x4); }
	void vblendvps(const Xmm& x1, const Operand& op, const Xmm& x4) { vblendvps(x1, x1, op, x4); }
	void vcmpeq_ospd(const Xmm& x, const Operand& op) { vcmpeq_ospd(x, x, op); }
	void vcmpeq_osps(const Xmm& x, const Operand& op) { vcmpeq_osps(x, x, op); }
	void vcmpeq_ossd(const Xmm& x, const Operand& op) { vcmpeq_ossd(x, x, op); }
	void vcmpeq_osss(const Xmm& x, const Operand& op) { vcmpeq_osss(x, x, op); }
	void vcmpeq_uqpd(const Xmm& x, const Operand& op) { vcmpeq_uqpd(x, x, op); }
	void vcmpeq_uqps(const Xmm& x, const Operand& op) { vcmpeq_uqps(x, x, op); }
	void vcmpeq_uqsd(const Xmm& x, const Operand& op) { vcmpeq_uqsd(x, x, op); }
	void vcmpeq_uqss(const Xmm& x, const Operand& op) { vcmpeq_uqss(x, x, op); }
	void vcmpeq_uspd(const Xmm& x, const Operand& op) { vcmpeq_uspd(x, x, op); }
	void vcmpeq_usps(const Xmm& x, const Operand& op) { vcmpeq_usps(x, x, op); }
	void vcmpeq_ussd(const Xmm& x, const Operand& op) { vcmpeq_ussd(x, x, op); }
	void vcmpeq_usss(const Xmm& x, const Operand& op) { vcmpeq_usss(x, x, op); }
	void vcmpeqpd(const Xmm& x, const Operand& op) { vcmpeqpd(x, x, op); }
	void vcmpeqps(const Xmm& x, const Operand& op) { vcmpeqps(x, x, op); }
	void vcmpeqsd(const Xmm& x, const Operand& op) { vcmpeqsd(x, x, op); }
	void vcmpeqss(const Xmm& x, const Operand& op) { vcmpeqss(x, x, op); }
	void vcmpfalse_ospd(const Xmm& x, const Operand& op) { vcmpfalse_ospd(x, x, op); }
	void vcmpfalse_osps(const Xmm& x, const Operand& op) { vcmpfalse_osps(x, x, op); }
	void vcmpfalse_ossd(const Xmm& x, const Operand& op) { vcmpfalse_ossd(x, x, op); }
	void vcmpfalse_osss(const Xmm& x, const Operand& op) { vcmpfalse_osss(x, x, op); }
	void vcmpfalsepd(const Xmm& x, const Operand& op) { vcmpfalsepd(x, x, op); }
	void vcmpfalseps(const Xmm& x, const Operand& op) { vcmpfalseps(x, x, op); }
	void vcmpfalsesd(const Xmm& x, const Operand& op) { vcmpfalsesd(x, x, op); }
	void vcmpfalsess(const Xmm& x, const Operand& op) { vcmpfalsess(x, x, op); }
	void vcmpge_oqpd(const Xmm& x, const Operand& op) { vcmpge_oqpd(x, x, op); }
	void vcmpge_oqps(const Xmm& x, const Operand& op) { vcmpge_oqps(x, x, op); }
	void vcmpge_oqsd(const Xmm& x, const Operand& op) { vcmpge_oqsd(x, x, op); }
	void vcmpge_oqss(const Xmm& x, const Operand& op) { vcmpge_oqss(x, x, op); }
	void vcmpgepd(const Xmm& x, const Operand& op) { vcmpgepd(x, x, op); }
	void vcmpgeps(const Xmm& x, const Operand& op) { vcmpgeps(x, x, op); }
	void vcmpgesd(const Xmm& x, const Operand& op) { vcmpgesd(x, x, op); }
	void vcmpgess(const Xmm& x, const Operand& op) { vcmpgess(x, x, op); }
	void vcmpgt_oqpd(const Xmm& x, const Operand& op) { vcmpgt_oqpd(x, x, op); }
	void vcmpgt_oqps(const Xmm& x, const Operand& op) { vcmpgt_oqps(x, x, op); }
	void vcmpgt_oqsd(const Xmm& x, const Operand& op) { vcmpgt_oqsd(x, x, op); }
	void vcmpgt_oqss(const Xmm& x, const Operand& op) { vcmpgt_oqss(x, x, op); }
	void vcmpgtpd(const Xmm& x, const Operand& op) { vcmpgtpd(x, x, op); }
	void vcmpgtps(const Xmm& x, const Operand& op) { vcmpgtps(x, x, op); }
	void vcmpgtsd(const Xmm& x, const Operand& op) { vcmpgtsd(x, x, op); }
	void vcmpgtss(const Xmm& x, const Operand& op) { vcmpgtss(x, x, op); }
	void vcmple_oqpd(const Xmm& x, const Operand& op) { vcmple_oqpd(x, x, op); }
	void vcmple_oqps(const Xmm& x, const Operand& op) { vcmple_oqps(x, x, op); }
	void vcmple_oqsd(const Xmm& x, const Operand& op) { vcmple_oqsd(x, x, op); }
	void vcmple_oqss(const Xmm& x, const Operand& op) { vcmple_oqss(x, x, op); }
	void vcmplepd(const Xmm& x, const Operand& op) { vcmplepd(x, x, op); }
	void vcmpleps(const Xmm& x, const Operand& op) { vcmpleps(x, x, op); }
	void vcmplesd(const Xmm& x, const Operand& op) { vcmplesd(x, x, op); }
	void vcmpless(const Xmm& x, const Operand& op) { vcmpless(x, x, op); }
	void vcmplt_oqpd(const Xmm& x, const Operand& op) { vcmplt_oqpd(x, x, op); }
	void vcmplt_oqps(const Xmm& x, const Operand& op) { vcmplt_oqps(x, x, op); }
	void vcmplt_oqsd(const Xmm& x, const Operand& op) { vcmplt_oqsd(x, x, op); }
	void vcmplt_oqss(const Xmm& x, const Operand& op) { vcmplt_oqss(x, x, op); }
	void vcmpltpd(const Xmm& x, const Operand& op) { vcmpltpd(x, x, op); }
	void vcmpltps(const Xmm& x, const Operand& op) { vcmpltps(x, x, op); }
	void vcmpltsd(const Xmm& x, const Operand& op) { vcmpltsd(x, x, op); }
	void vcmpltss(const Xmm& x, const Operand& op) { vcmpltss(x, x, op); }
	void vcmpneq_oqpd(const Xmm& x, const Operand& op) { vcmpneq_oqpd(x, x, op); }
	void vcmpneq_oqps(const Xmm& x, const Operand& op) { vcmpneq_oqps(x, x, op); }
	void vcmpneq_oqsd(const Xmm& x, const Operand& op) { vcmpneq_oqsd(x, x, op); }
	void vcmpneq_oqss(const Xmm& x, const Operand& op) { vcmpneq_oqss(x, x, op); }
	void vcmpneq_ospd(const Xmm& x, const Operand& op) { vcmpneq_ospd(x, x, op); }
	void vcmpneq_osps(const Xmm& x, const Operand& op) { vcmpneq_osps(x, x, op); }
	void vcmpneq_ossd(const Xmm& x, const Operand& op) { vcmpneq_ossd(x, x, op); }
	void vcmpneq_osss(const Xmm& x, const Operand& op) { vcmpneq_osss(x, x, op); }
	void vcmpneq_uspd(const Xmm& x, const Operand& op) { vcmpneq_uspd(x, x, op); }
	void vcmpneq_usps(const Xmm& x, const Operand& op) { vcmpneq_usps(x, x, op); }
	void vcmpneq_ussd(const Xmm& x, const Operand& op) { vcmpneq_ussd(x, x, op); }
	void vcmpneq_usss(const Xmm& x, const Operand& op) { vcmpneq_usss(x, x, op); }
	void vcmpneqpd(const Xmm& x, const Operand& op) { vcmpneqpd(x, x, op); }
	void vcmpneqps(const Xmm& x, const Operand& op) { vcmpneqps(x, x, op); }
	void vcmpneqsd(const Xmm& x, const Operand& op) { vcmpneqsd(x, x, op); }
	void vcmpneqss(const Xmm& x, const Operand& op) { vcmpneqss(x, x, op); }
	void vcmpnge_uqpd(const Xmm& x, const Operand& op) { vcmpnge_uqpd(x, x, op); }
	void vcmpnge_uqps(const Xmm& x, const Operand& op) { vcmpnge_uqps(x, x, op); }
	void vcmpnge_uqsd(const Xmm& x, const Operand& op) { vcmpnge_uqsd(x, x, op); }
	void vcmpnge_uqss(const Xmm& x, const Operand& op) { vcmpnge_uqss(x, x, op); }
	void vcmpngepd(const Xmm& x, const Operand& op) { vcmpngepd(x, x, op); }
	void vcmpngeps(const Xmm& x, const Operand& op) { vcmpngeps(x, x, op); }
	void vcmpngesd(const Xmm& x, const Operand& op) { vcmpngesd(x, x, op); }
	void vcmpngess(const Xmm& x, const Operand& op) { vcmpngess(x, x, op); }
	void vcmpngt_uqpd(const Xmm& x, const Operand& op) { vcmpngt_uqpd(x, x, op); }
	void vcmpngt_uqps(const Xmm& x, const Operand& op) { vcmpngt_uqps(x, x, op); }
	void vcmpngt_uqsd(const Xmm& x, const Operand& op) { vcmpngt_uqsd(x, x, op); }
	void vcmpngt_uqss(const Xmm& x, const Operand& op) { vcmpngt_uqss(x, x, op); }
	void vcmpngtpd(const Xmm& x, const Operand& op) { vcmpngtpd(x, x, op); }
	void vcmpngtps(const Xmm& x, const Operand& op) { vcmpngtps(x, x, op); }
	void vcmpngtsd(const Xmm& x, const Operand& op) { vcmpngtsd(x, x, op); }
	void vcmpngtss(const Xmm& x, const Operand& op) { vcmpngtss(x, x, op); }
	void vcmpnle_uqpd(const Xmm& x, const Operand& op) { vcmpnle_uqpd(x, x, op); }
	void vcmpnle_uqps(const Xmm& x, const Operand& op) { vcmpnle_uqps(x, x, op); }
	void vcmpnle_uqsd(const Xmm& x, const Operand& op) { vcmpnle_uqsd(x, x, op); }
	void vcmpnle_uqss(const Xmm& x, const Operand& op) { vcmpnle_uqss(x, x, op); }
	void vcmpnlepd(const Xmm& x, const Operand& op) { vcmpnlepd(x, x, op); }
	void vcmpnleps(const Xmm& x, const Operand& op) { vcmpnleps(x, x, op); }
	void vcmpnlesd(const Xmm& x, const Operand& op) { vcmpnlesd(x, x, op); }
	void vcmpnless(const Xmm& x, const Operand& op) { vcmpnless(x, x, op); }
	void vcmpnlt_uqpd(const Xmm& x, const Operand& op) { vcmpnlt_uqpd(x, x, op); }
	void vcmpnlt_uqps(const Xmm& x, const Operand& op) { vcmpnlt_uqps(x, x, op); }
	void vcmpnlt_uqsd(const Xmm& x, const Operand& op) { vcmpnlt_uqsd(x, x, op); }
	void vcmpnlt_uqss(const Xmm& x, const Operand& op) { vcmpnlt_uqss(x, x, op); }
	void vcmpnltpd(const Xmm& x, const Operand& op) { vcmpnltpd(x, x, op); }
	void vcmpnltps(const Xmm& x, const Operand& op) { vcmpnltps(x, x, op); }
	void vcmpnltsd(const Xmm& x, const Operand& op) { vcmpnltsd(x, x, op); }
	void vcmpnltss(const Xmm& x, const Operand& op) { vcmpnltss(x, x, op); }
	void vcmpord_spd(const Xmm& x, const Operand& op) { vcmpord_spd(x, x, op); }
	void vcmpord_sps(const Xmm& x, const Operand& op) { vcmpord_sps(x, x, op); }
	void vcmpord_ssd(const Xmm& x, const Operand& op) { vcmpord_ssd(x, x, op); }
	void vcmpord_sss(const Xmm& x, const Operand& op) { vcmpord_sss(x, x, op); }
	void vcmpordpd(const Xmm& x, const Operand& op) { vcmpordpd(x, x, op); }
	void vcmpordps(const Xmm& x, const Operand& op) { vcmpordps(x, x, op); }
	void vcmpordsd(const Xmm& x, const Operand& op) { vcmpordsd(x, x, op); }
	void vcmpordss(const Xmm& x, const Operand& op) { vcmpordss(x, x, op); }
	void vcmppd(const Xmm& x, const Operand& op, uint8_t imm) { vcmppd(x, x, op, imm); }
	void vcmpps(const Xmm& x, const Operand& op, uint8_t imm) { vcmpps(x, x, op, imm); }
	void vcmpsd(const Xmm& x, const Operand& op, uint8_t imm) { vcmpsd(x, x, op, imm); }
	void vcmpss(const Xmm& x, const Operand& op, uint8_t imm) { vcmpss(x, x, op, imm); }
	void vcmptrue_uspd(const Xmm& x, const Operand& op) { vcmptrue_uspd(x, x, op); }
	void vcmptrue_usps(const Xmm& x, const Operand& op) { vcmptrue_usps(x, x, op); }
	void vcmptrue_ussd(const Xmm& x, const Operand& op) { vcmptrue_ussd(x, x, op); }
	void vcmptrue_usss(const Xmm& x, const Operand& op) { vcmptrue_usss(x, x, op); }
	void vcmptruepd(const Xmm& x, const Operand& op) { vcmptruepd(x, x, op); }
	void vcmptrueps(const Xmm& x, const Operand& op) { vcmptrueps(x, x, op); }
	void vcmptruesd(const Xmm& x, const Operand& op) { vcmptruesd(x, x, op); }
	void vcmptruess(const Xmm& x, const Operand& op) { vcmptruess(x, x, op); }
	void vcmpunord_spd(const Xmm& x, const Operand& op) { vcmpunord_spd(x, x, op); }
	void vcmpunord_sps(const Xmm& x, const Operand& op) { vcmpunord_sps(x, x, op); }
	void vcmpunord_ssd(const Xmm& x, const Operand& op) { vcmpunord_ssd(x, x, op); }
	void vcmpunord_sss(const Xmm& x, const Operand& op) { vcmpunord_sss(x, x, op); }
	void vcmpunordpd(const Xmm& x, const Operand& op) { vcmpunordpd(x, x, op); }
	void vcmpunordps(const Xmm& x, const Operand& op) { vcmpunordps(x, x, op); }
	void vcmpunordsd(const Xmm& x, const Operand& op) { vcmpunordsd(x, x, op); }
	void vcmpunordss(const Xmm& x, const Operand& op) { vcmpunordss(x, x, op); }
	void vcvtsd2ss(const Xmm& x, const Operand& op) { vcvtsd2ss(x, x, op); }
	void vcvtsi2sd(const Xmm& x, const Operand& op) { vcvtsi2sd(x, x, op); }
	void vcvtsi2ss(const Xmm& x, const Operand& op) { vcvtsi2ss(x, x, op); }
	void vcvtss2sd(const Xmm& x, const Operand& op) { vcvtss2sd(x, x, op); }
	void vdppd(const Xmm& x, const Operand& op, uint8_t imm) { vdppd(x, x, op, imm); }
	void vdpps(const Xmm& x, const Operand& op, uint8_t imm) { vdpps(x, x, op, imm); }
	void vinsertps(const Xmm& x, const Operand& op, uint8_t imm) { vinsertps(x, x, op, imm); }
	void vmpsadbw(const Xmm& x, const Operand& op, uint8_t imm) { vmpsadbw(x, x, op, imm); }
	void vpackssdw(const Xmm& x, const Operand& op) { vpackssdw(x, x, op); }
	void vpacksswb(const Xmm& x, const Operand& op) { vpacksswb(x, x, op); }
	void vpackusdw(const Xmm& x, const Operand& op) { vpackusdw(x, x, op); }
	void vpackuswb(const Xmm& x, const Operand& op) { vpackuswb(x, x, op); }
	void vpaddb(const Xmm& x, const Operand& op) { vpaddb(x, x, op); }
	void vpaddd(const Xmm& x, const Operand& op) { vpaddd(x, x, op); }
	void vpaddq(const Xmm& x, const Operand& op) { vpaddq(x, x, op); }
	void vpaddsb(const Xmm& x, const Operand& op) { vpaddsb(x, x, op); }
	void vpaddsw(const Xmm& x, const Operand& op) { vpaddsw(x, x, op); }
	void vpaddusb(const Xmm& x, const Operand& op) { vpaddusb(x, x, op); }
	void vpaddusw(const Xmm& x, const Operand& op) { vpaddusw(x, x, op); }
	void vpaddw(const Xmm& x, const Operand& op) { vpaddw(x, x, op); }
	void vpalignr(const Xmm& x, const Operand& op, uint8_t imm) { vpalignr(x, x, op, imm); }
	void vpand(const Xmm& x, const Operand& op) { vpand(x, x, op); }
	void vpandn(const Xmm& x, const Operand& op) { vpandn(x, x, op); }
	void vpavgb(const Xmm& x, const Operand& op) { vpavgb(x, x, op); }
	void vpavgw(const Xmm& x, const Operand& op) { vpavgw(x, x, op); }
	void vpblendd(const Xmm& x, const Operand& op, uint8_t imm) { vpblendd(x, x, op, imm); }
	void vpblendvb(const Xmm& x1, const Operand& op, const Xmm& x4) { vpblendvb(x1, x1, op, x4); }
	void vpblendw(const Xmm& x, const Operand& op, uint8_t imm) { vpblendw(x, x, op, imm); }
	void vpclmulqdq(const Xmm& x, const Operand& op, uint8_t imm) { vpclmulqdq(x, x, op, imm); }
	void vpcmpeqb(const Xmm& x, const Operand& op) { vpcmpeqb(x, x, op); }
	void vpcmpeqd(const Xmm& x, const Operand& op) { vpcmpeqd(x, x, op); }
	void vpcmpeqq(const Xmm& x, const Operand& op) { vpcmpeqq(x, x, op); }
	void vpcmpeqw(const Xmm& x, const Operand& op) { vpcmpeqw(x, x, op); }
	void vpcmpgtb(const Xmm& x, const Operand& op) { vpcmpgtb(x, x, op); }
	void vpcmpgtd(const Xmm& x, const Operand& op) { vpcmpgtd(x, x, op); }
	void vpcmpgtq(const Xmm& x, const Operand& op) { vpcmpgtq(x, x, op); }
	void vpcmpgtw(const Xmm& x, const Operand& op) { vpcmpgtw(x, x, op); }
	void vphaddd(const Xmm& x, const Operand& op) { vphaddd(x, x, op); }
	void vphaddsw(const Xmm& x, const Operand& op) { vphaddsw(x, x, op); }
	void vphaddw(const Xmm& x, const Operand& op) { vphaddw(x, x, op); }
	void vphsubd(const Xmm& x, const Operand& op) { vphsubd(x, x, op); }
	void vphsubsw(const Xmm& x, const Operand& op) { vphsubsw(x, x, op); }
	void vphsubw(const Xmm& x, const Operand& op) { vphsubw(x, x, op); }
	void vpinsrb(const Xmm& x, const Operand& op, uint8_t imm) { vpinsrb(x, x, op, imm); }
	void vpinsrd(const Xmm& x, const Operand& op, uint8_t imm) { vpinsrd(x, x, op, imm); }
	void vpinsrq(const Xmm& x, const Operand& op, uint8_t imm) { vpinsrq(x, x, op, imm); }
	void vpinsrw(const Xmm& x, const Operand& op, uint8_t imm) { vpinsrw(x, x, op, imm); }
	void vpmaddubsw(const Xmm& x, const Operand& op) { vpmaddubsw(x, x, op); }
	void vpmaddwd(const Xmm& x, const Operand& op) { vpmaddwd(x, x, op); }
	void vpmaxsb(const Xmm& x, const Operand& op) { vpmaxsb(x, x, op); }
	void vpmaxsd(const Xmm& x, const Operand& op) { vpmaxsd(x, x, op); }
	void vpmaxsw(const Xmm& x, const Operand& op) { vpmaxsw(x, x, op); }
	void vpmaxub(const Xmm& x, const Operand& op) { vpmaxub(x, x, op); }
	void vpmaxud(const Xmm& x, const Operand& op) { vpmaxud(x, x, op); }
	void vpmaxuw(const Xmm& x, const Operand& op) { vpmaxuw(x, x, op); }
	void vpminsb(const Xmm& x, const Operand& op) { vpminsb(x, x, op); }
	void vpminsd(const Xmm& x, const Operand& op) { vpminsd(x, x, op); }
	void vpminsw(const Xmm& x, const Operand& op) { vpminsw(x, x, op); }
	void vpminub(const Xmm& x, const Operand& op) { vpminub(x, x, op); }
	void vpminud(const Xmm& x, const Operand& op) { vpminud(x, x, op); }
	void vpminuw(const Xmm& x, const Operand& op) { vpminuw(x, x, op); }
	void vpmuldq(const Xmm& x, const Operand& op) { vpmuldq(x, x, op); }
	void vpmulhrsw(const Xmm& x, const Operand& op) { vpmulhrsw(x, x, op); }
	void vpmulhuw(const Xmm& x, const Operand& op) { vpmulhuw(x, x, op); }
	void vpmulhw(const Xmm& x, const Operand& op) { vpmulhw(x, x, op); }
	void vpmulld(const Xmm& x, const Operand& op) { vpmulld(x, x, op); }
	void vpmullw(const Xmm& x, const Operand& op) { vpmullw(x, x, op); }
	void vpmuludq(const Xmm& x, const Operand& op) { vpmuludq(x, x, op); }
	void vpor(const Xmm& x, const Operand& op) { vpor(x, x, op); }
	void vpsadbw(const Xmm& x, const Operand& op) { vpsadbw(x, x, op); }
	void vpsignb(const Xmm& x, const Operand& op) { vpsignb(x, x, op); }
	void vpsignd(const Xmm& x, const Operand& op) { vpsignd(x, x, op); }
	void vpsignw(const Xmm& x, const Operand& op) { vpsignw(x, x, op); }
	void vpslld(const Xmm& x, const Operand& op) { vpslld(x, x, op); }
	void vpslld(const Xmm& x, uint8_t imm) { vpslld(x, x, imm); }
	void vpslldq(const Xmm& x, uint8_t imm) { vpslldq(x, x, imm); }
	void vpsllq(const Xmm& x, const Operand& op) { vpsllq(x, x, op); }
	void vpsllq(const Xmm& x, uint8_t imm) { vpsllq(x, x, imm); }
	void vpsllw(const Xmm& x, const Operand& op) { vpsllw(x, x, op); }
	void vpsllw(const Xmm& x, uint8_t imm) { vpsllw(x, x, imm); }
	void vpsrad(const Xmm& x, const Operand& op) { vpsrad(x, x, op); }
	void vpsrad(const Xmm& x, uint8_t imm) { vpsrad(x, x, imm); }
	void vpsraw(const Xmm& x, const Operand& op) { vpsraw(x, x, op); }
	void vpsraw(const Xmm& x, uint8_t imm) { vpsraw(x, x, imm); }
	void vpsrld(const Xmm& x, const Operand& op) { vpsrld(x, x, op); }
	void vpsrld(const Xmm& x, uint8_t imm) { vpsrld(x, x, imm); }
	void vpsrldq(const Xmm& x, uint8_t imm) { vpsrldq(x, x, imm); }
	void vpsrlq(const Xmm& x, const Operand& op) { vpsrlq(x, x, op); }
	void vpsrlq(const Xmm& x, uint8_t imm) { vpsrlq(x, x, imm); }
	void vpsrlw(const Xmm& x, const Operand& op) { vpsrlw(x, x, op); }
	void vpsrlw(const Xmm& x, uint8_t imm) { vpsrlw(x, x, imm); }
	void vpsubb(const Xmm& x, const Operand& op) { vpsubb(x, x, op); }
	void vpsubd(const Xmm& x, const Operand& op) { vpsubd(x, x, op); }
	void vpsubq(const Xmm& x, const Operand& op) { vpsubq(x, x, op); }
	void vpsubsb(const Xmm& x, const Operand& op) { vpsubsb(x, x, op); }
	void vpsubsw(const Xmm& x, const Operand& op) { vpsubsw(x, x, op); }
	void vpsubusb(const Xmm& x, const Operand& op) { vpsubusb(x, x, op); }
	void vpsubusw(const Xmm& x, const Operand& op) { vpsubusw(x, x, op); }
	void vpsubw(const Xmm& x, const Operand& op) { vpsubw(x, x, op); }
	void vpunpckhbw(const Xmm& x, const Operand& op) { vpunpckhbw(x, x, op); }
	void vpunpckhdq(const Xmm& x, const Operand& op) { vpunpckhdq(x, x, op); }
	void vpunpckhqdq(const Xmm& x, const Operand& op) { vpunpckhqdq(x, x, op); }
	void vpunpckhwd(const Xmm& x, const Operand& op) { vpunpckhwd(x, x, op); }
	void vpunpcklbw(const Xmm& x, const Operand& op) { vpunpcklbw(x, x, op); }
	void vpunpckldq(const Xmm& x, const Operand& op) { vpunpckldq(x, x, op); }
	void vpunpcklqdq(const Xmm& x, const Operand& op) { vpunpcklqdq(x, x, op); }
	void vpunpcklwd(const Xmm& x, const Operand& op) { vpunpcklwd(x, x, op); }
	void vpxor(const Xmm& x, const Operand& op) { vpxor(x, x, op); }
	void vrcpss(const Xmm& x, const Operand& op) { vrcpss(x, x, op); }
	void vroundsd(const Xmm& x, const Operand& op, uint8_t imm) { vroundsd(x, x, op, imm); }
	void vroundss(const Xmm& x, const Operand& op, uint8_t imm) { vroundss(x, x, op, imm); }
	void vrsqrtss(const Xmm& x, const Operand& op) { vrsqrtss(x, x, op); }
	void vshufpd(const Xmm& x, const Operand& op, uint8_t imm) { vshufpd(x, x, op, imm); }
	void vshufps(const Xmm& x, const Operand& op, uint8_t imm) { vshufps(x, x, op, imm); }
	void vsqrtsd(const Xmm& x, const Operand& op) { vsqrtsd(x, x, op); }
	void vsqrtss(const Xmm& x, const Operand& op) { vsqrtss(x, x, op); }
	void vunpckhpd(const Xmm& x, const Operand& op) { vunpckhpd(x, x, op); }
	void vunpckhps(const Xmm& x, const Operand& op) { vunpckhps(x, x, op); }
	void vunpcklpd(const Xmm& x, const Operand& op) { vunpcklpd(x, x, op); }
	void vunpcklps(const Xmm& x, const Operand& op) { vunpcklps(x, x, op); }
#endif
#ifdef XBYAK64
	void jecxz(std::string label) { db(0x67); opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jecxz(const Label& label) { db(0x67); opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jrcxz(std::string label) { opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jrcxz(const Label& label) { opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void cdqe() { db(0x48); db(0x98); }
	void cqo() { db(0x48); db(0x99); }
	void cmpsq() { db(0x48); db(0xA7); }
	void popfq() { db(0x9D); }
	void pushfq() { db(0x9C); }
	void lodsq() { db(0x48); db(0xAD); }
	void movsq() { db(0x48); db(0xA5); }
	void scasq() { db(0x48); db(0xAF); }
	void stosq() { db(0x48); db(0xAB); }
	void syscall() { db(0x0F); db(0x05); }
	void sysret() { db(0x0F); db(0x07); }
	void cmpxchg16b(const Address& addr) { opModM(addr, Reg64(1), 0x0F, 0xC7); }
	void fxrstor64(const Address& addr) { opModM(addr, Reg64(1), 0x0F, 0xAE); }
	void movq(const Reg64& reg, const Mmx& mmx) { if (mmx.isXMM()) db(0x66); opModR(mmx, reg, 0x0F, 0x7E); }
	void movq(const Mmx& mmx, const Reg64& reg) { if (mmx.isXMM()) db(0x66); opModR(mmx, reg, 0x0F, 0x6E); }
	void movsxd(const Reg64& reg, const Operand& op) { if (!op.isBit(32)) XBYAK_THROW(ERR_BAD_COMBINATION) opModRM(reg, op, op.isREG(), op.isMEM(), 0x63); }
	void pextrq(const Operand& op, const Xmm& xmm, uint8_t imm) { if (!op.isREG(64) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opGen(Reg64(xmm.getIdx()), op, 0x16, 0x66, 0, imm, 0x3A); }
	void pinsrq(const Xmm& xmm, const Operand& op, uint8_t imm) { if (!op.isREG(64) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opGen(Reg64(xmm.getIdx()), op, 0x22, 0x66, 0, imm, 0x3A); }
	void vcvtss2si(const Reg64& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F3 | T_W1 | T_EVEX | T_EW1 | T_ER_X | T_N8, 0x2D); }
	void vcvttss2si(const Reg64& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F3 | T_W1 | T_EVEX | T_EW1 | T_SAE_X | T_N8, 0x2C); }
	void vcvtsd2si(const Reg64& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F2 | T_W1 | T_EVEX | T_EW1 | T_N4 | T_ER_X, 0x2D); }
	void vcvttsd2si(const Reg64& r, const Operand& op) { opAVX_X_X_XM(Xmm(r.getIdx()), xm0, op, T_0F | T_F2 | T_W1 | T_EVEX | T_EW1 | T_N4 | T_SAE_X, 0x2C); }
	void vmovq(const Xmm& x, const Reg64& r) { opAVX_X_X_XM(x, xm0, Xmm(r.getIdx()), T_66 | T_0F | T_W1 | T_EVEX | T_EW1, 0x6E); }
	void vmovq(const Reg64& r, const Xmm& x) { opAVX_X_X_XM(x, xm0, Xmm(r.getIdx()), T_66 | T_0F | T_W1 | T_EVEX | T_EW1, 0x7E); }
	void ldtilecfg(const Address& addr) { opVex(tmm0, &tmm0, addr, T_0F38 | T_W0, 0x49); }
	void sttilecfg(const Address& addr) { opVex(tmm0, &tmm0, addr, T_66 | T_0F38 | T_W0, 0x49); }
	void tileloadd(const Tmm& tm, const Address& addr) { opAMX(tm, addr, T_F2 | T_0F38 | T_W0, 0x4b); }
	void tileloaddt1(const Tmm& tm, const Address& addr) { opAMX(tm, addr, T_66 | T_0F38 | T_W0, 0x4b); }
	void tilerelease() { db(0xc4); db(0xe2); db(0x78); db(0x49); db(0xc0); }
	void tilestored(const Address& addr, const Tmm& tm) { opVex(tm, &tmm0, addr, T_F3 | T_0F38 | T_W0, 0x4b); }
	void tilezero(const Tmm& Tmm) { opVex(Tmm, &tmm0, tmm0, T_F2 | T_0F38 | T_W0, 0x49); }
	void tdpbssd(const Tmm& x1, const Tmm& x2, const Tmm& x3) { opVex(x1, &x3, x2, T_F2 | T_0F38 | T_W0, 0x5e); }
	void tdpbsud(const Tmm& x1, const Tmm& x2, const Tmm& x3) { opVex(x1, &x3, x2, T_F3 | T_0F38 | T_W0, 0x5e); }
	void tdpbusd(const Tmm& x1, const Tmm& x2, const Tmm& x3) { opVex(x1, &x3, x2, T_66 | T_0F38 | T_W0, 0x5e); }
	void tdpbuud(const Tmm& x1, const Tmm& x2, const Tmm& x3) { opVex(x1, &x3, x2, T_0F38 | T_W0, 0x5e); }
	void tdpbf16ps(const Tmm& x1, const Tmm& x2, const Tmm& x3) { opVex(x1, &x3, x2, T_F3 | T_0F38 | T_W0, 0x5c); }
#else
	void jcxz(std::string label) { db(0x67); opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jcxz(const Label& label) { db(0x67); opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jecxz(std::string label) { opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void jecxz(const Label& label) { opJmp(label, T_SHORT, 0xe3, 0, 0); }
	void aaa() { db(0x37); }
	void aad() { db(0xD5); db(0x0A); }
	void aam() { db(0xD4); db(0x0A); }
	void aas() { db(0x3F); }
	void daa() { db(0x27); }
	void das() { db(0x2F); }
	void into() { db(0xCE); }
	void popad() { db(0x61); }
	void popfd() { db(0x9D); }
	void pusha() { db(0x60); }
	void pushad() { db(0x60); }
	void pushfd() { db(0x9C); }
	void popa() { db(0x61); }
	void lds(const Reg& reg, const Address& addr) { opLoadSeg(addr, reg, 0xC5, 0x100); }
	void les(const Reg& reg, const Address& addr) { opLoadSeg(addr, reg, 0xC4, 0x100); }
#endif
#ifndef XBYAK_NO_OP_NAMES
	void and (const Operand& op1, const Operand& op2) { and_(op1, op2); }
	void and (const Operand& op, uint32_t imm) { and_(op, imm); }
	void or (const Operand & op1, const Operand & op2) { or_(op1, op2); }
	void or (const Operand & op, uint32_t imm) { or_(op, imm); }
	void xor (const Operand& op1, const Operand& op2) { xor_(op1, op2); }
	void xor (const Operand& op, uint32_t imm) { xor_(op, imm); }
	void not(const Operand& op) { not_(op); }
#endif
#ifndef XBYAK_DISABLE_AVX512
	void kaddb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x4A); }
	void kaddd(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x4A); }
	void kaddq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x4A); }
	void kaddw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x4A); }
	void kandb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x41); }
	void kandd(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x41); }
	void kandnb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x42); }
	void kandnd(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x42); }
	void kandnq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x42); }
	void kandnw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x42); }
	void kandq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x41); }
	void kandw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x41); }
	void kmovb(const Address& addr, const Opmask& k) { opVex(k, 0, addr, T_L0 | T_0F | T_66 | T_W0, 0x91); }
	void kmovb(const Opmask& k, const Operand& op) { if (!op.isMEM() && !op.isOPMASK()) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(k, 0, op, T_L0 | T_0F | T_66 | T_W0, 0x90); }
	void kmovb(const Opmask& k, const Reg32& r) { opVex(k, 0, r, T_L0 | T_0F | T_66 | T_W0, 0x92); }
	void kmovb(const Reg32& r, const Opmask& k) { opVex(r, 0, k, T_L0 | T_0F | T_66 | T_W0, 0x93); }
	void kmovd(const Address& addr, const Opmask& k) { opVex(k, 0, addr, T_L0 | T_0F | T_66 | T_W1, 0x91); }
	void kmovd(const Opmask& k, const Operand& op) { if (!op.isMEM() && !op.isOPMASK()) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(k, 0, op, T_L0 | T_0F | T_66 | T_W1, 0x90); }
	void kmovd(const Opmask& k, const Reg32& r) { opVex(k, 0, r, T_L0 | T_0F | T_F2 | T_W0, 0x92); }
	void kmovd(const Reg32& r, const Opmask& k) { opVex(r, 0, k, T_L0 | T_0F | T_F2 | T_W0, 0x93); }
	void kmovq(const Address& addr, const Opmask& k) { opVex(k, 0, addr, T_L0 | T_0F | T_W1, 0x91); }
	void kmovq(const Opmask& k, const Operand& op) { if (!op.isMEM() && !op.isOPMASK()) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(k, 0, op, T_L0 | T_0F | T_W1, 0x90); }
	void kmovw(const Address& addr, const Opmask& k) { opVex(k, 0, addr, T_L0 | T_0F | T_W0, 0x91); }
	void kmovw(const Opmask& k, const Operand& op) { if (!op.isMEM() && !op.isOPMASK()) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(k, 0, op, T_L0 | T_0F | T_W0, 0x90); }
	void kmovw(const Opmask& k, const Reg32& r) { opVex(k, 0, r, T_L0 | T_0F | T_W0, 0x92); }
	void kmovw(const Reg32& r, const Opmask& k) { opVex(r, 0, k, T_L0 | T_0F | T_W0, 0x93); }
	void knotb(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W0, 0x44); }
	void knotd(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W1, 0x44); }
	void knotq(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W1, 0x44); }
	void knotw(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W0, 0x44); }
	void korb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x45); }
	void kord(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x45); }
	void korq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x45); }
	void kortestb(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W0, 0x98); }
	void kortestd(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W1, 0x98); }
	void kortestq(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W1, 0x98); }
	void kortestw(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W0, 0x98); }
	void korw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x45); }
	void kshiftlb(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W0, 0x32, imm); }
	void kshiftld(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W0, 0x33, imm); }
	void kshiftlq(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W1, 0x33, imm); }
	void kshiftlw(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W1, 0x32, imm); }
	void kshiftrb(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W0, 0x30, imm); }
	void kshiftrd(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W0, 0x31, imm); }
	void kshiftrq(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W1, 0x31, imm); }
	void kshiftrw(const Opmask& r1, const Opmask& r2, uint8_t imm) { opVex(r1, 0, r2, T_66 | T_0F3A | T_W1, 0x30, imm); }
	void ktestb(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W0, 0x99); }
	void ktestd(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_66 | T_W1, 0x99); }
	void ktestq(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W1, 0x99); }
	void ktestw(const Opmask& r1, const Opmask& r2) { opVex(r1, 0, r2, T_0F | T_W0, 0x99); }
	void kunpckbw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x4B); }
	void kunpckdq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x4B); }
	void kunpckwd(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x4B); }
	void kxnorb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x46); }
	void kxnord(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x46); }
	void kxnorq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x46); }
	void kxnorw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x46); }
	void kxorb(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W0, 0x47); }
	void kxord(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_66 | T_W1, 0x47); }
	void kxorq(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W1, 0x47); }
	void kxorw(const Opmask& r1, const Opmask& r2, const Opmask& r3) { opVex(r1, &r2, r3, T_L1 | T_0F | T_W0, 0x47); }
	void v4fmaddps(const Zmm& z1, const Zmm& z2, const Address& addr) { opAVX_X_X_XM(z1, z2, addr, T_0F38 | T_F2 | T_EW0 | T_YMM | T_MUST_EVEX | T_N16, 0x9A); }
	void v4fmaddss(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_F2 | T_EW0 | T_MUST_EVEX | T_N16, 0x9B); }
	void v4fnmaddps(const Zmm& z1, const Zmm& z2, const Address& addr) { opAVX_X_X_XM(z1, z2, addr, T_0F38 | T_F2 | T_EW0 | T_YMM | T_MUST_EVEX | T_N16, 0xAA); }
	void v4fnmaddss(const Xmm& x1, const Xmm& x2, const Address& addr) { opAVX_X_X_XM(x1, x2, addr, T_0F38 | T_F2 | T_EW0 | T_MUST_EVEX | T_N16, 0xAB); }
	void vaddph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x58); }
	void vaddsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x58); }
	void valignd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x03, imm); }
	void valignq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x03, imm); }
	void vblendmpd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x65); }
	void vblendmps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x65); }
	void vbroadcastf32x2(const Ymm& y, const Operand& op) { opAVX_X_XM_IMM(y, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N8, 0x19); }
	void vbroadcastf32x4(const Ymm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N16, 0x1A); }
	void vbroadcastf32x8(const Zmm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N32, 0x1B); }
	void vbroadcastf64x2(const Ymm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N16, 0x1A); }
	void vbroadcastf64x4(const Zmm& y, const Address& addr) { opAVX_X_XM_IMM(y, addr, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N32, 0x1B); }
	void vbroadcasti32x2(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N8, 0x59); }
	void vbroadcasti32x4(const Ymm& y, const Operand& op) { opAVX_X_XM_IMM(y, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N16, 0x5A); }
	void vbroadcasti32x8(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0 | T_N32, 0x5B); }
	void vbroadcasti64x2(const Ymm& y, const Operand& op) { opAVX_X_XM_IMM(y, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N16, 0x5A); }
	void vbroadcasti64x4(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1 | T_N32, 0x5B); }
	void vcmpeq_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 16); }
	void vcmpeq_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 16); }
	void vcmpeq_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 16); }
	void vcmpeq_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 16); }
	void vcmpeq_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 8); }
	void vcmpeq_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 8); }
	void vcmpeq_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 8); }
	void vcmpeq_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 8); }
	void vcmpeq_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 24); }
	void vcmpeq_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 24); }
	void vcmpeq_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 24); }
	void vcmpeq_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 24); }
	void vcmpeqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 0); }
	void vcmpeqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 0); }
	void vcmpeqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 0); }
	void vcmpeqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 0); }
	void vcmpfalse_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 27); }
	void vcmpfalse_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 27); }
	void vcmpfalse_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 27); }
	void vcmpfalse_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 27); }
	void vcmpfalsepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 11); }
	void vcmpfalseps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 11); }
	void vcmpfalsesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 11); }
	void vcmpfalsess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 11); }
	void vcmpge_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 29); }
	void vcmpge_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 29); }
	void vcmpge_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 29); }
	void vcmpge_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 29); }
	void vcmpgepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 13); }
	void vcmpgeps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 13); }
	void vcmpgesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 13); }
	void vcmpgess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 13); }
	void vcmpgt_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 30); }
	void vcmpgt_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 30); }
	void vcmpgt_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 30); }
	void vcmpgt_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 30); }
	void vcmpgtpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 14); }
	void vcmpgtps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 14); }
	void vcmpgtsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 14); }
	void vcmpgtss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 14); }
	void vcmple_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 18); }
	void vcmple_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 18); }
	void vcmple_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 18); }
	void vcmple_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 18); }
	void vcmplepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 2); }
	void vcmpleps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 2); }
	void vcmplesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 2); }
	void vcmpless(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 2); }
	void vcmplt_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 17); }
	void vcmplt_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 17); }
	void vcmplt_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 17); }
	void vcmplt_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 17); }
	void vcmpltpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 1); }
	void vcmpltps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 1); }
	void vcmpltsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 1); }
	void vcmpltss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 1); }
	void vcmpneq_oqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 12); }
	void vcmpneq_oqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 12); }
	void vcmpneq_oqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 12); }
	void vcmpneq_oqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 12); }
	void vcmpneq_ospd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 28); }
	void vcmpneq_osps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 28); }
	void vcmpneq_ossd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 28); }
	void vcmpneq_osss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 28); }
	void vcmpneq_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 20); }
	void vcmpneq_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 20); }
	void vcmpneq_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 20); }
	void vcmpneq_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 20); }
	void vcmpneqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 4); }
	void vcmpneqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 4); }
	void vcmpneqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 4); }
	void vcmpneqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 4); }
	void vcmpnge_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 25); }
	void vcmpnge_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 25); }
	void vcmpnge_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 25); }
	void vcmpnge_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 25); }
	void vcmpngepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 9); }
	void vcmpngeps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 9); }
	void vcmpngesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 9); }
	void vcmpngess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 9); }
	void vcmpngt_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 26); }
	void vcmpngt_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 26); }
	void vcmpngt_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 26); }
	void vcmpngt_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 26); }
	void vcmpngtpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 10); }
	void vcmpngtps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 10); }
	void vcmpngtsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 10); }
	void vcmpngtss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 10); }
	void vcmpnle_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 22); }
	void vcmpnle_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 22); }
	void vcmpnle_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 22); }
	void vcmpnle_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 22); }
	void vcmpnlepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 6); }
	void vcmpnleps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 6); }
	void vcmpnlesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 6); }
	void vcmpnless(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 6); }
	void vcmpnlt_uqpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 21); }
	void vcmpnlt_uqps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 21); }
	void vcmpnlt_uqsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 21); }
	void vcmpnlt_uqss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 21); }
	void vcmpnltpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 5); }
	void vcmpnltps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 5); }
	void vcmpnltsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 5); }
	void vcmpnltss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 5); }
	void vcmpord_spd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 23); }
	void vcmpord_sps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 23); }
	void vcmpord_ssd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 23); }
	void vcmpord_sss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 23); }
	void vcmpordpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 7); }
	void vcmpordps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 7); }
	void vcmpordsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 7); }
	void vcmpordss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 7); }
	void vcmppd(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0xC2, imm); }
	void vcmpph(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0xC2, imm); }
	void vcmpps(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_0F | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0xC2, imm); }
	void vcmpsd(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_N8 | T_F2 | T_0F | T_EW1 | T_SAE_Z | T_MUST_EVEX, 0xC2, imm); }
	void vcmpsh(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_N2 | T_F3 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0xC2, imm); }
	void vcmpss(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_N4 | T_F3 | T_0F | T_EW0 | T_SAE_Z | T_MUST_EVEX, 0xC2, imm); }
	void vcmptrue_uspd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 31); }
	void vcmptrue_usps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 31); }
	void vcmptrue_ussd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 31); }
	void vcmptrue_usss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 31); }
	void vcmptruepd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 15); }
	void vcmptrueps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 15); }
	void vcmptruesd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 15); }
	void vcmptruess(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 15); }
	void vcmpunord_spd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 19); }
	void vcmpunord_sps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 19); }
	void vcmpunord_ssd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 19); }
	void vcmpunord_sss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 19); }
	void vcmpunordpd(const Opmask& k, const Xmm& x, const Operand& op) { vcmppd(k, x, op, 3); }
	void vcmpunordps(const Opmask& k, const Xmm& x, const Operand& op) { vcmpps(k, x, op, 3); }
	void vcmpunordsd(const Opmask& k, const Xmm& x, const Operand& op) { vcmpsd(k, x, op, 3); }
	void vcmpunordss(const Opmask& k, const Xmm& x, const Operand& op) { vcmpss(k, x, op, 3); }
	void vcomish(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_MAP5 | T_MUST_EVEX | T_EW0 | T_SAE_X | T_N2, 0x2F); }
	void vcompressb(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N1 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x63); }
	void vcompresspd(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x8A); }
	void vcompressps(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x8A); }
	void vcompressw(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N2 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x63); }
	void vcvtdq2ph(const Xmm& x, const Operand& op) { checkCvt4(x, op); opCvt(x, op, T_N16 | T_N_VL | T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x5B); }
	void vcvtne2ps2bf16(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x72); }
	void vcvtneps2bf16(const Xmm& x, const Operand& op) { opCvt2(x, op, T_F3 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x72); }
	void vcvtpd2ph(const Xmm& x, const Operand& op) { opCvt5(x, op, T_N16 | T_N_VL | T_66 | T_MAP5 | T_EW1 | T_ER_Z | T_MUST_EVEX | T_B64, 0x5A); }
	void vcvtpd2qq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x7B); }
	void vcvtpd2udq(const Xmm& x, const Operand& op) { opCvt2(x, op, T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x79); }
	void vcvtpd2uqq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x79); }
	void vcvtph2dq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_YMM | T_ER_Y | T_MUST_EVEX | T_B16, 0x5B); }
	void vcvtph2pd(const Xmm& x, const Operand& op) { if (!op.isXMM() && !op.isMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(x, 0, op, T_N4 | T_N_VL | T_MAP5 | T_EW0 | T_YMM | T_SAE_X | T_MUST_EVEX | T_B16, 0x5A); }
	void vcvtph2psx(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_MAP6 | T_EW0 | T_YMM | T_SAE_Y | T_MUST_EVEX | T_B16, 0x13); }
	void vcvtph2qq(const Xmm& x, const Operand& op) { if (!op.isXMM() && !op.isMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(x, 0, op, T_N4 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_YMM | T_ER_X | T_MUST_EVEX | T_B16, 0x7B); }
	void vcvtph2udq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_MAP5 | T_EW0 | T_YMM | T_ER_Y | T_MUST_EVEX | T_B16, 0x79); }
	void vcvtph2uqq(const Xmm& x, const Operand& op) { if (!op.isXMM() && !op.isMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(x, 0, op, T_N4 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_YMM | T_ER_X | T_MUST_EVEX | T_B16, 0x79); }
	void vcvtph2uw(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x7D); }
	void vcvtph2w(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x7D); }
	void vcvtps2phx(const Xmm& x, const Operand& op) { checkCvt4(x, op); opCvt(x, op, T_N16 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_ER_Z | T_MUST_EVEX | T_B32, 0x1D); }
	void vcvtps2qq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_0F | T_EW0 | T_YMM | T_ER_Y | T_MUST_EVEX | T_B32, 0x7B); }
	void vcvtps2udq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_0F | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x79); }
	void vcvtps2uqq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_0F | T_EW0 | T_YMM | T_ER_Y | T_MUST_EVEX | T_B32, 0x79); }
	void vcvtqq2pd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F3 | T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0xE6); }
	void vcvtqq2ph(const Xmm& x, const Operand& op) { opCvt5(x, op, T_N16 | T_N_VL | T_MAP5 | T_EW1 | T_ER_Z | T_MUST_EVEX | T_B64, 0x5B); }
	void vcvtqq2ps(const Xmm& x, const Operand& op) { opCvt2(x, op, T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x5B); }
	void vcvtsd2sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_F2 | T_MAP5 | T_EW1 | T_ER_X | T_MUST_EVEX, 0x5A); }
	void vcvtsd2usi(const Reg32e& r, const Operand& op) { int type = (T_N8 | T_F2 | T_0F | T_ER_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x79); }
	void vcvtsh2sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_F3 | T_MAP5 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x5A); }
	void vcvtsh2si(const Reg32e& r, const Operand& op) { int type = (T_N2 | T_F3 | T_MAP5 | T_ER_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x2D); }
	void vcvtsh2ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_MAP6 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x13); }
	void vcvtsh2usi(const Reg32e& r, const Operand& op) { int type = (T_N2 | T_F3 | T_MAP5 | T_ER_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x79); }
	void vcvtsi2sh(const Xmm& x1, const Xmm& x2, const Operand& op) { if (!(x1.isXMM() && x2.isXMM() && op.isBit(32 | 64))) XBYAK_THROW(ERR_BAD_COMBINATION) int type = (T_F3 | T_MAP5 | T_ER_R | T_MUST_EVEX | T_M_K) | (op.isBit(32) ? (T_EW0 | T_N4) : (T_EW1 | T_N8)); opVex(x1, &x2, op, type, 0x2A); }
	void vcvtss2sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_MAP5 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x1D); }
	void vcvtss2usi(const Reg32e& r, const Operand& op) { int type = (T_N4 | T_F3 | T_0F | T_ER_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x79); }
	void vcvttpd2qq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x7A); }
	void vcvttpd2udq(const Xmm& x, const Operand& op) { opCvt2(x, op, T_0F | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x78); }
	void vcvttpd2uqq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x78); }
	void vcvttph2dq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_F3 | T_MAP5 | T_EW0 | T_YMM | T_SAE_Y | T_MUST_EVEX | T_B16, 0x5B); }
	void vcvttph2qq(const Xmm& x, const Operand& op) { if (!op.isXMM() && !op.isMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(x, 0, op, T_N4 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_YMM | T_SAE_X | T_MUST_EVEX | T_B16, 0x7A); }
	void vcvttph2udq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_MAP5 | T_EW0 | T_YMM | T_SAE_Y | T_MUST_EVEX | T_B16, 0x78); }
	void vcvttph2uqq(const Xmm& x, const Operand& op) { if (!op.isXMM() && !op.isMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(x, 0, op, T_N4 | T_N_VL | T_66 | T_MAP5 | T_EW0 | T_YMM | T_SAE_X | T_MUST_EVEX | T_B16, 0x78); }
	void vcvttph2uw(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_MAP5 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x7C); }
	void vcvttph2w(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_MAP5 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x7C); }
	void vcvttps2qq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_0F | T_EW0 | T_YMM | T_SAE_Y | T_MUST_EVEX | T_B32, 0x7A); }
	void vcvttps2udq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_0F | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x78); }
	void vcvttps2uqq(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_66 | T_0F | T_EW0 | T_YMM | T_SAE_Y | T_MUST_EVEX | T_B32, 0x78); }
	void vcvttsd2usi(const Reg32e& r, const Operand& op) { int type = (T_N8 | T_F2 | T_0F | T_SAE_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x78); }
	void vcvttsh2si(const Reg32e& r, const Operand& op) { int type = (T_N2 | T_F3 | T_MAP5 | T_EW0 | T_SAE_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x2C); }
	void vcvttsh2usi(const Reg32e& r, const Operand& op) { int type = (T_N2 | T_F3 | T_MAP5 | T_EW0 | T_SAE_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x78); }
	void vcvttss2usi(const Reg32e& r, const Operand& op) { int type = (T_N4 | T_F3 | T_0F | T_SAE_X | T_MUST_EVEX) | (r.isREG(64) ? T_EW1 : T_EW0); opVex(r, &xm0, op, type, 0x78); }
	void vcvtudq2pd(const Xmm& x, const Operand& op) { checkCvt1(x, op); opVex(x, 0, op, T_N8 | T_N_VL | T_F3 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x7A); }
	void vcvtudq2ph(const Xmm& x, const Operand& op) { checkCvt4(x, op); opCvt(x, op, T_N16 | T_N_VL | T_F2 | T_MAP5 | T_EW0 | T_ER_Z | T_MUST_EVEX | T_B32, 0x7A); }
	void vcvtudq2ps(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F2 | T_0F | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x7A); }
	void vcvtuqq2pd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F3 | T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x7A); }
	void vcvtuqq2ph(const Xmm& x, const Operand& op) { opCvt5(x, op, T_N16 | T_N_VL | T_F2 | T_MAP5 | T_EW1 | T_ER_Z | T_MUST_EVEX | T_B64, 0x7A); }
	void vcvtuqq2ps(const Xmm& x, const Operand& op) { opCvt2(x, op, T_F2 | T_0F | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x7A); }
	void vcvtusi2sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opCvt3(x1, x2, op, T_F2 | T_0F | T_MUST_EVEX, T_W1 | T_EW1 | T_ER_X | T_N8, T_W0 | T_EW0 | T_N4, 0x7B); }
	void vcvtusi2sh(const Xmm& x1, const Xmm& x2, const Operand& op) { if (!(x1.isXMM() && x2.isXMM() && op.isBit(32 | 64))) XBYAK_THROW(ERR_BAD_COMBINATION) int type = (T_F3 | T_MAP5 | T_ER_R | T_MUST_EVEX | T_M_K) | (op.isBit(32) ? (T_EW0 | T_N4) : (T_EW1 | T_N8)); opVex(x1, &x2, op, type, 0x7B); }
	void vcvtusi2ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opCvt3(x1, x2, op, T_F3 | T_0F | T_MUST_EVEX | T_ER_X, T_W1 | T_EW1 | T_N8, T_W0 | T_EW0 | T_N4, 0x7B); }
	void vcvtuw2ph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F2 | T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x7D); }
	void vcvtw2ph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F3 | T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x7D); }
	void vdbpsadbw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x42, imm); }
	void vdivph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x5E); }
	void vdivsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x5E); }
	void vdpbf16ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x52); }
	void vexp2pd(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1 | T_B64 | T_SAE_Z, 0xC8); }
	void vexp2ps(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0 | T_B32 | T_SAE_Z, 0xC8); }
	void vexpandpd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x88); }
	void vexpandps(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x88); }
	void vextractf32x4(const Operand& op, const Ymm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::XMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N16 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x19, imm); }
	void vextractf32x8(const Operand& op, const Zmm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N32 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x1B, imm); }
	void vextractf64x2(const Operand& op, const Ymm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::XMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N16 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x19, imm); }
	void vextractf64x4(const Operand& op, const Zmm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N32 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x1B, imm); }
	void vextracti32x4(const Operand& op, const Ymm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::XMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N16 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x39, imm); }
	void vextracti32x8(const Operand& op, const Zmm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N32 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x3B, imm); }
	void vextracti64x2(const Operand& op, const Ymm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::XMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N16 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x39, imm); }
	void vextracti64x4(const Operand& op, const Zmm& r, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r, 0, op, T_N32 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x3B, imm); }
	void vfcmaddcph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x56); }
	void vfcmulcph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0xD6); }
	void vfixupimmpd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x54, imm); }
	void vfixupimmps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x54, imm); }
	void vfixupimmsd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F3A | T_EW1 | T_SAE_Z | T_MUST_EVEX, 0x55, imm); }
	void vfixupimmss(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_EW0 | T_SAE_Z | T_MUST_EVEX, 0x55, imm); }
	void vfmadd132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x98); }
	void vfmadd132sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x99); }
	void vfmadd213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xA8); }
	void vfmadd213sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xA9); }
	void vfmadd231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xB8); }
	void vfmadd231sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xB9); }
	void vfmaddcph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x56); }
	void vfmaddsub132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x96); }
	void vfmaddsub213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xA6); }
	void vfmaddsub231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xB6); }
	void vfmsub132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x9A); }
	void vfmsub132sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x9B); }
	void vfmsub213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xAA); }
	void vfmsub213sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xAB); }
	void vfmsub231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xBA); }
	void vfmsub231sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xBB); }
	void vfmsubadd132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x97); }
	void vfmsubadd213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xA7); }
	void vfmsubadd231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xB7); }
	void vfmulcph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0xD6); }
	void vfnmadd132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x9C); }
	void vfnmadd132sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x9D); }
	void vfnmadd213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xAC); }
	void vfnmadd213sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xAD); }
	void vfnmadd231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xBC); }
	void vfnmadd231sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xBD); }
	void vfnmsub132ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x9E); }
	void vfnmsub132sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x9F); }
	void vfnmsub213ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xAE); }
	void vfnmsub213sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xAF); }
	void vfnmsub231ph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0xBE); }
	void vfnmsub231sh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0xBF); }
	void vfpclasspd(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isBit(128 | 256 | 512)) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k.changeBit(op.getBit()), 0, op, T_66 | T_0F3A | T_MUST_EVEX | T_YMM | T_EW1 | T_B64, 0x66, imm); }
	void vfpclassph(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isBit(128 | 256 | 512)) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k.changeBit(op.getBit()), 0, op, T_0F3A | T_MUST_EVEX | T_YMM | T_EW0 | T_B16, 0x66, imm); }
	void vfpclassps(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isBit(128 | 256 | 512)) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k.changeBit(op.getBit()), 0, op, T_66 | T_0F3A | T_MUST_EVEX | T_YMM | T_EW0 | T_B32, 0x66, imm); }
	void vfpclasssd(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isXMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k, 0, op, T_66 | T_0F3A | T_MUST_EVEX | T_EW1 | T_N8, 0x67, imm); }
	void vfpclasssh(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isXMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k, 0, op, T_0F3A | T_MUST_EVEX | T_EW0 | T_N2, 0x67, imm); }
	void vfpclassss(const Opmask& k, const Operand& op, uint8_t imm) { if (!op.isXMEM()) XBYAK_THROW(ERR_BAD_MEM_SIZE) opVex(k, 0, op, T_66 | T_0F3A | T_MUST_EVEX | T_EW0 | T_N4, 0x67, imm); }
	void vgatherdpd(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_VSIB, 0x92, 1); }
	void vgatherdps(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_VSIB, 0x92, 0); }
	void vgatherpf0dpd(const Address& addr) { opGatherFetch(addr, zm1, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::YMM); }
	void vgatherpf0dps(const Address& addr) { opGatherFetch(addr, zm1, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::ZMM); }
	void vgatherpf0qpd(const Address& addr) { opGatherFetch(addr, zm1, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vgatherpf0qps(const Address& addr) { opGatherFetch(addr, zm1, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vgatherpf1dpd(const Address& addr) { opGatherFetch(addr, zm2, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::YMM); }
	void vgatherpf1dps(const Address& addr) { opGatherFetch(addr, zm2, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::ZMM); }
	void vgatherpf1qpd(const Address& addr) { opGatherFetch(addr, zm2, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vgatherpf1qps(const Address& addr) { opGatherFetch(addr, zm2, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vgatherqpd(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_VSIB, 0x93, 0); }
	void vgatherqps(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_VSIB, 0x93, 2); }
	void vgetexppd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x42); }
	void vgetexpph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x42); }
	void vgetexpps(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x42); }
	void vgetexpsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_SAE_X | T_MUST_EVEX, 0x43); }
	void vgetexpsh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x43); }
	void vgetexpss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x43); }
	void vgetmantpd(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x26, imm); }
	void vgetmantph(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x26, imm); }
	void vgetmantps(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x26, imm); }
	void vgetmantsd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F3A | T_EW1 | T_SAE_X | T_MUST_EVEX, 0x27, imm); }
	void vgetmantsh(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x27, imm); }
	void vgetmantss(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x27, imm); }
	void vinsertf32x4(const Ymm& r1, const Ymm& r2, const Operand& op, uint8_t imm) { if (!(r1.getKind() == r2.getKind() && op.is(Operand::MEM | Operand::XMM))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N16 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x18, imm); }
	void vinsertf32x8(const Zmm& r1, const Zmm& r2, const Operand& op, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N32 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x1A, imm); }
	void vinsertf64x2(const Ymm& r1, const Ymm& r2, const Operand& op, uint8_t imm) { if (!(r1.getKind() == r2.getKind() && op.is(Operand::MEM | Operand::XMM))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N16 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x18, imm); }
	void vinsertf64x4(const Zmm& r1, const Zmm& r2, const Operand& op, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N32 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x1A, imm); }
	void vinserti32x4(const Ymm& r1, const Ymm& r2, const Operand& op, uint8_t imm) { if (!(r1.getKind() == r2.getKind() && op.is(Operand::MEM | Operand::XMM))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N16 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x38, imm); }
	void vinserti32x8(const Zmm& r1, const Zmm& r2, const Operand& op, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N32 | T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x3A, imm); }
	void vinserti64x2(const Ymm& r1, const Ymm& r2, const Operand& op, uint8_t imm) { if (!(r1.getKind() == r2.getKind() && op.is(Operand::MEM | Operand::XMM))) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N16 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x38, imm); }
	void vinserti64x4(const Zmm& r1, const Zmm& r2, const Operand& op, uint8_t imm) { if (!op.is(Operand::MEM | Operand::YMM)) XBYAK_THROW(ERR_BAD_COMBINATION) opVex(r1, &r2, op, T_N32 | T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x3A, imm); }
	void vmaxph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x5F); }
	void vmaxsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x5F); }
	void vminph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x5D); }
	void vminsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x5D); }
	void vmovdqa32(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_66 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqa32(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovdqa64(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_66 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqa64(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovdqu16(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_F2 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqu16(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F2 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovdqu32(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_F3 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqu32(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F3 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovdqu64(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_F3 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqu64(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F3 | T_0F | T_EW1 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovdqu8(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_F2 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX | T_M_K, 0x7F); }
	void vmovdqu8(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_F2 | T_0F | T_EW0 | T_YMM | T_ER_X | T_ER_Y | T_ER_Z | T_MUST_EVEX, 0x6F); }
	void vmovsh(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_N2 | T_F3 | T_MAP5 | T_EW0 | T_MUST_EVEX | T_M_K, 0x11); }
	void vmovsh(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, xm0, addr, T_N2 | T_F3 | T_MAP5 | T_EW0 | T_MUST_EVEX, 0x10); }
	void vmovsh(const Xmm& x1, const Xmm& x2, const Xmm& x3) { opAVX_X_X_XM(x1, x2, x3, T_N2 | T_F3 | T_MAP5 | T_EW0 | T_MUST_EVEX, 0x10); }
	void vmovw(const Address& addr, const Xmm& x) { opAVX_X_XM_IMM(x, addr, T_N2 | T_66 | T_MAP5 | T_MUST_EVEX, 0x7E); }
	void vmovw(const Reg32e& r, const Xmm& x) { opAVX_X_X_XM(x, xm0, r, T_N2 | T_66 | T_MAP5 | T_MUST_EVEX, 0x7E); }
	void vmovw(const Xmm& x, const Operand& op) { if (!op.isREG(32 | 64) && !op.isMEM()) XBYAK_THROW(ERR_BAD_COMBINATION) opAVX_X_X_XM(x, xm0, op, T_N2 | T_66 | T_MAP5 | T_MUST_EVEX, 0x6E); }
	void vmulph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x59); }
	void vmulsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x59); }
	void vp2intersectd(const Opmask& k, const Xmm& x, const Operand& op) { if (k.getOpmaskIdx() != 0) XBYAK_THROW(ERR_OPMASK_IS_ALREADY_SET) opAVX_K_X_XM(k, x, op, T_F2 | T_0F38 | T_YMM | T_EVEX | T_EW0 | T_B32, 0x68); }
	void vp2intersectq(const Opmask& k, const Xmm& x, const Operand& op) { if (k.getOpmaskIdx() != 0) XBYAK_THROW(ERR_OPMASK_IS_ALREADY_SET) opAVX_K_X_XM(k, x, op, T_F2 | T_0F38 | T_YMM | T_EVEX | T_EW1 | T_B64, 0x68); }
	void vp4dpwssd(const Zmm& z1, const Zmm& z2, const Address& addr) { opAVX_X_X_XM(z1, z2, addr, T_0F38 | T_F2 | T_EW0 | T_YMM | T_MUST_EVEX | T_N16, 0x52); }
	void vp4dpwssds(const Zmm& z1, const Zmm& z2, const Address& addr) { opAVX_X_X_XM(z1, z2, addr, T_0F38 | T_F2 | T_EW0 | T_YMM | T_MUST_EVEX | T_N16, 0x53); }
	void vpabsq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_MUST_EVEX | T_EW1 | T_B64 | T_YMM, 0x1F); }
	void vpandd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0xDB); }
	void vpandnd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0xDF); }
	void vpandnq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xDF); }
	void vpandq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xDB); }
	void vpblendmb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x66); }
	void vpblendmd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x64); }
	void vpblendmq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x64); }
	void vpblendmw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x66); }
	void vpbroadcastb(const Xmm& x, const Reg8& r) { opVex(x, 0, r, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x7A); }
	void vpbroadcastd(const Xmm& x, const Reg32& r) { opVex(x, 0, r, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x7C); }
	void vpbroadcastmb2q(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW1, 0x2A); }
	void vpbroadcastmw2d(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_YMM | T_MUST_EVEX | T_EW0, 0x3A); }
	void vpbroadcastw(const Xmm& x, const Reg16& r) { opVex(x, 0, r, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x7B); }
	void vpcmpb(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x3F, imm); }
	void vpcmpd(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x1F, imm); }
	void vpcmpeqb(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_YMM | T_MUST_EVEX, 0x74); }
	void vpcmpeqd(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_YMM | T_MUST_EVEX | T_B32, 0x76); }
	void vpcmpeqq(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x29); }
	void vpcmpeqw(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_YMM | T_MUST_EVEX, 0x75); }
	void vpcmpgtb(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_YMM | T_MUST_EVEX, 0x64); }
	void vpcmpgtd(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x66); }
	void vpcmpgtq(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x37); }
	void vpcmpgtw(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F | T_YMM | T_MUST_EVEX, 0x65); }
	void vpcmpq(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x1F, imm); }
	void vpcmpub(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX, 0x3E, imm); }
	void vpcmpud(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x1E, imm); }
	void vpcmpuq(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x1E, imm); }
	void vpcmpuw(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x3E, imm); }
	void vpcmpw(const Opmask& k, const Xmm& x, const Operand& op, uint8_t imm) { opAVX_K_X_XM(k, x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX, 0x3F, imm); }
	void vpcompressd(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x8B); }
	void vpcompressq(const Operand& op, const Xmm& x) { opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x8B); }
	void vpconflictd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0xC4); }
	void vpconflictq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xC4); }
	void vpermb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x8D); }
	void vpermi2b(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x75); }
	void vpermi2d(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x76); }
	void vpermi2pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x77); }
	void vpermi2ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x77); }
	void vpermi2q(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x76); }
	void vpermi2w(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x75); }
	void vpermt2b(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x7D); }
	void vpermt2d(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x7E); }
	void vpermt2pd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x7F); }
	void vpermt2ps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x7F); }
	void vpermt2q(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x7E); }
	void vpermt2w(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x7D); }
	void vpermw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x8D); }
	void vpexpandb(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N1 | T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x62); }
	void vpexpandd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x89); }
	void vpexpandq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x89); }
	void vpexpandw(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_N2 | T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x62); }
	void vpgatherdd(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_VSIB, 0x90, 0); }
	void vpgatherdq(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_VSIB, 0x90, 1); }
	void vpgatherqd(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_VSIB, 0x91, 2); }
	void vpgatherqq(const Xmm& x, const Address& addr) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_VSIB, 0x91, 0); }
	void vplzcntd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x44); }
	void vplzcntq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x44); }
	void vpmadd52huq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xB5); }
	void vpmadd52luq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xB4); }
	void vpmaxsq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x3D); }
	void vpmaxuq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x3F); }
	void vpminsq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x39); }
	void vpminuq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x3B); }
	void vpmovb2m(const Opmask& k, const Xmm& x) { opVex(k, 0, x, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0, 0x29); }
	void vpmovd2m(const Opmask& k, const Xmm& x) { opVex(k, 0, x, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0, 0x39); }
	void vpmovdb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x31, false); }
	void vpmovdw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x33, true); }
	void vpmovm2b(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0, 0x28); }
	void vpmovm2d(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0, 0x38); }
	void vpmovm2q(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1, 0x38); }
	void vpmovm2w(const Xmm& x, const Opmask& k) { opVex(x, 0, k, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1, 0x28); }
	void vpmovq2m(const Opmask& k, const Xmm& x) { opVex(k, 0, x, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1, 0x39); }
	void vpmovqb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N2 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x32, false); }
	void vpmovqd(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x35, true); }
	void vpmovqw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x34, false); }
	void vpmovsdb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x21, false); }
	void vpmovsdw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x23, true); }
	void vpmovsqb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N2 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x22, false); }
	void vpmovsqd(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x25, true); }
	void vpmovsqw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x24, false); }
	void vpmovswb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x20, true); }
	void vpmovusdb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x11, false); }
	void vpmovusdw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x13, true); }
	void vpmovusqb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N2 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x12, false); }
	void vpmovusqd(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x15, true); }
	void vpmovusqw(const Operand& op, const Xmm& x) { opVmov(op, x, T_N4 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x14, false); }
	void vpmovuswb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x10, true); }
	void vpmovw2m(const Opmask& k, const Xmm& x) { opVex(k, 0, x, T_F3 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1, 0x29); }
	void vpmovwb(const Operand& op, const Xmm& x) { opVmov(op, x, T_N8 | T_N_VL | T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x30, true); }
	void vpmullq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x40); }
	void vpmultishiftqb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x83); }
	void vpopcntb(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x54); }
	void vpopcntd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x55); }
	void vpopcntq(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x55); }
	void vpopcntw(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x54); }
	void vpord(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0xEB); }
	void vporq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xEB); }
	void vprold(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 1), x, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x72, imm); }
	void vprolq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 1), x, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x72, imm); }
	void vprolvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x15); }
	void vprolvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x15); }
	void vprord(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 0), x, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x72, imm); }
	void vprorq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 0), x, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x72, imm); }
	void vprorvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x14); }
	void vprorvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x14); }
	void vpscatterdd(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA0, 0); }
	void vpscatterdq(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA0, 1); }
	void vpscatterqd(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA1, 2); }
	void vpscatterqq(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA1, 0); }
	void vpshldd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x71, imm); }
	void vpshldq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x71, imm); }
	void vpshldvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x71); }
	void vpshldvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x71); }
	void vpshldvw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x70); }
	void vpshldw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x70, imm); }
	void vpshrdd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x73, imm); }
	void vpshrdq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x73, imm); }
	void vpshrdvd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x73); }
	void vpshrdvq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x73); }
	void vpshrdvw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x72); }
	void vpshrdw(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX, 0x72, imm); }
	void vpshufbitqmb(const Opmask& k, const Xmm& x, const Operand& op) { opVex(k, &x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x8F); }
	void vpsllvw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x12); }
	void vpsraq(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_X_XM(Xmm(x.getKind(), 4), x, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x72, imm); }
	void vpsraq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N16 | T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX, 0xE2); }
	void vpsravq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x46); }
	void vpsravw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x11); }
	void vpsrlvw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x10); }
	void vpternlogd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x25, imm); }
	void vpternlogq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x25, imm); }
	void vptestmb(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x26); }
	void vptestmd(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x27); }
	void vptestmq(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x27); }
	void vptestmw(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x26); }
	void vptestnmb(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x26); }
	void vptestnmd(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_F3 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x27); }
	void vptestnmq(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_F3 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x27); }
	void vptestnmw(const Opmask& k, const Xmm& x, const Operand& op) { opAVX_K_X_XM(k, x, op, T_F3 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x26); }
	void vpxord(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0xEF); }
	void vpxorq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xEF); }
	void vrangepd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x50, imm); }
	void vrangeps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x50, imm); }
	void vrangesd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F3A | T_EW1 | T_SAE_X | T_MUST_EVEX, 0x51, imm); }
	void vrangess(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x51, imm); }
	void vrcp14pd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x4C); }
	void vrcp14ps(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x4C); }
	void vrcp14sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX, 0x4D); }
	void vrcp14ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX, 0x4D); }
	void vrcp28pd(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1 | T_B64 | T_SAE_Z, 0xCA); }
	void vrcp28ps(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0 | T_B32 | T_SAE_Z, 0xCA); }
	void vrcp28sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_SAE_X | T_MUST_EVEX, 0xCB); }
	void vrcp28ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0xCB); }
	void vrcpph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_MUST_EVEX | T_B16, 0x4C); }
	void vrcpsh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_MUST_EVEX, 0x4D); }
	void vreducepd(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x56, imm); }
	void vreduceph(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x56, imm); }
	void vreduceps(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x56, imm); }
	void vreducesd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F3A | T_EW1 | T_SAE_X | T_MUST_EVEX, 0x57, imm); }
	void vreducesh(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x57, imm); }
	void vreducess(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x57, imm); }
	void vrndscalepd(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B64, 0x09, imm); }
	void vrndscaleph(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B16, 0x08, imm); }
	void vrndscaleps(const Xmm& x, const Operand& op, uint8_t imm) { opAVX_X_XM_IMM(x, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_SAE_Z | T_MUST_EVEX | T_B32, 0x08, imm); }
	void vrndscalesd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F3A | T_EW1 | T_SAE_X | T_MUST_EVEX, 0x0B, imm); }
	void vrndscalesh(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x0A, imm); }
	void vrndscaless(const Xmm& x1, const Xmm& x2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F3A | T_EW0 | T_SAE_X | T_MUST_EVEX, 0x0A, imm); }
	void vrsqrt14pd(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x4E); }
	void vrsqrt14ps(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_B32, 0x4E); }
	void vrsqrt14sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x4F); }
	void vrsqrt14ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX, 0x4F); }
	void vrsqrt28pd(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1 | T_B64 | T_SAE_Z, 0xCC); }
	void vrsqrt28ps(const Zmm& z, const Operand& op) { opAVX_X_XM_IMM(z, op, T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW0 | T_B32 | T_SAE_Z, 0xCC); }
	void vrsqrt28sd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_SAE_X | T_MUST_EVEX, 0xCD); }
	void vrsqrt28ss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_SAE_X | T_MUST_EVEX, 0xCD); }
	void vrsqrtph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_MUST_EVEX | T_B16, 0x4E); }
	void vrsqrtsh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_MUST_EVEX, 0x4F); }
	void vscalefpd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW1 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B64, 0x2C); }
	void vscalefph(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_MAP6 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x2C); }
	void vscalefps(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F38 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B32, 0x2C); }
	void vscalefsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N8 | T_66 | T_0F38 | T_EW1 | T_ER_X | T_MUST_EVEX, 0x2D); }
	void vscalefsh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_66 | T_MAP6 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x2D); }
	void vscalefss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N4 | T_66 | T_0F38 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x2D); }
	void vscatterdpd(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA2, 1); }
	void vscatterdps(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA2, 0); }
	void vscatterpf0dpd(const Address& addr) { opGatherFetch(addr, zm5, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::YMM); }
	void vscatterpf0dps(const Address& addr) { opGatherFetch(addr, zm5, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::ZMM); }
	void vscatterpf0qpd(const Address& addr) { opGatherFetch(addr, zm5, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vscatterpf0qps(const Address& addr) { opGatherFetch(addr, zm5, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vscatterpf1dpd(const Address& addr) { opGatherFetch(addr, zm6, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::YMM); }
	void vscatterpf1dps(const Address& addr) { opGatherFetch(addr, zm6, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC6, Operand::ZMM); }
	void vscatterpf1qpd(const Address& addr) { opGatherFetch(addr, zm6, T_N8 | T_66 | T_0F38 | T_EW1 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vscatterpf1qps(const Address& addr) { opGatherFetch(addr, zm6, T_N4 | T_66 | T_0F38 | T_EW0 | T_MUST_EVEX | T_M_K | T_VSIB, 0xC7, Operand::ZMM); }
	void vscatterqpd(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N8 | T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA3, 0); }
	void vscatterqps(const Address& addr, const Xmm& x) { opGather2(x, addr, T_N4 | T_66 | T_0F38 | T_EW0 | T_YMM | T_MUST_EVEX | T_M_K | T_VSIB, 0xA3, 2); }
	void vshuff32x4(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F3A | T_YMM | T_MUST_EVEX | T_EW0 | T_B32, 0x23, imm); }
	void vshuff64x2(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F3A | T_YMM | T_MUST_EVEX | T_EW1 | T_B64, 0x23, imm); }
	void vshufi32x4(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F3A | T_YMM | T_MUST_EVEX | T_EW0 | T_B32, 0x43, imm); }
	void vshufi64x2(const Ymm& y1, const Ymm& y2, const Operand& op, uint8_t imm) { opAVX_X_X_XM(y1, y2, op, T_66 | T_0F3A | T_YMM | T_MUST_EVEX | T_EW1 | T_B64, 0x43, imm); }
	void vsqrtph(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_MAP5 | T_EW0 | T_YMM | T_ER_Z | T_MUST_EVEX | T_B16, 0x51); }
	void vsqrtsh(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_N2 | T_F3 | T_MAP5 | T_EW0 | T_ER_X | T_MUST_EVEX, 0x51); }
	void vsubph(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_EW0 | T_YMM | T_MUST_EVEX | T_ER_Z | T_B16, 0x5C); }
	void vsubsh(const Xmm& xmm, const Operand& op1, const Operand& op2 = Operand()) { opAVX_X_X_XM(xmm, op1, op2, T_MAP5 | T_F3 | T_EW0 | T_MUST_EVEX | T_ER_X | T_N2, 0x5C); }
	void vucomish(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, T_MAP5 | T_MUST_EVEX | T_EW0 | T_SAE_X | T_N2, 0x2E); }
#ifdef XBYAK64
	void kmovq(const Opmask& k, const Reg64& r) { opVex(k, 0, r, T_L0 | T_0F | T_F2 | T_W1, 0x92); }
	void kmovq(const Reg64& r, const Opmask& k) { opVex(r, 0, k, T_L0 | T_0F | T_F2 | T_W1, 0x93); }
	void vpbroadcastq(const Xmm& x, const Reg64& r) { opVex(x, 0, r, T_66 | T_0F38 | T_EW1 | T_YMM | T_MUST_EVEX, 0x7C); }
#endif
#endif

	/*
		use single byte nop if useMultiByteNop = false
	*/
	void align(size_t x = 16, bool useMultiByteNop = true)
	{
		if (x == 1) return;
		if (x < 1 || (x & (x - 1))) XBYAK_THROW(ERR_BAD_ALIGN)
		if (isAutoGrow() && x > inner::ALIGN_PAGE_SIZE) fprintf(stderr, "warning:autoGrow mode does not support %d align\n", (int)x);
		size_t remain = size_t(getCurr()) % x;
		if (remain) {
			nop(x - remain, useMultiByteNop);
		}
	}
#endif
};

template <>
inline void CodeGenerator::mov(const NativeReg& reg, const char *label) // can't use std::string
{
	assert(label);
	mov_imm(reg, dummyAddr);
	putL(label);
}

namespace util {
static const XBYAK_CONSTEXPR Mmx mm0(0), mm1(1), mm2(2), mm3(3), mm4(4), mm5(5), mm6(6), mm7(7);
static const XBYAK_CONSTEXPR Xmm xmm0(0), xmm1(1), xmm2(2), xmm3(3), xmm4(4), xmm5(5), xmm6(6), xmm7(7);
static const XBYAK_CONSTEXPR Ymm ymm0(0), ymm1(1), ymm2(2), ymm3(3), ymm4(4), ymm5(5), ymm6(6), ymm7(7);
static const XBYAK_CONSTEXPR Zmm zmm0(0), zmm1(1), zmm2(2), zmm3(3), zmm4(4), zmm5(5), zmm6(6), zmm7(7);
static const XBYAK_CONSTEXPR Reg32 eax(Operand::EAX), ecx(Operand::ECX), edx(Operand::EDX), ebx(Operand::EBX), esp(Operand::ESP), ebp(Operand::EBP), esi(Operand::ESI), edi(Operand::EDI);
static const XBYAK_CONSTEXPR Reg16 ax(Operand::AX), cx(Operand::CX), dx(Operand::DX), bx(Operand::BX), sp(Operand::SP), bp(Operand::BP), si(Operand::SI), di(Operand::DI);
static const XBYAK_CONSTEXPR Reg8 al(Operand::AL), cl(Operand::CL), dl(Operand::DL), bl(Operand::BL), ah(Operand::AH), ch(Operand::CH), dh(Operand::DH), bh(Operand::BH);
static const XBYAK_CONSTEXPR AddressFrame ptr(0), byte(8), word(16), dword(32), qword(64), xword(128), yword(256), zword(512);
static const XBYAK_CONSTEXPR AddressFrame ptr_b(0, true), xword_b(128, true), yword_b(256, true), zword_b(512, true);
static const XBYAK_CONSTEXPR Fpu st0(0), st1(1), st2(2), st3(3), st4(4), st5(5), st6(6), st7(7);
static const XBYAK_CONSTEXPR Opmask k0(0), k1(1), k2(2), k3(3), k4(4), k5(5), k6(6), k7(7);
static const XBYAK_CONSTEXPR BoundsReg bnd0(0), bnd1(1), bnd2(2), bnd3(3);
static const XBYAK_CONSTEXPR EvexModifierRounding T_sae(EvexModifierRounding::T_SAE), T_rn_sae(EvexModifierRounding::T_RN_SAE), T_rd_sae(EvexModifierRounding::T_RD_SAE), T_ru_sae(EvexModifierRounding::T_RU_SAE), T_rz_sae(EvexModifierRounding::T_RZ_SAE);
static const XBYAK_CONSTEXPR EvexModifierZero T_z;
#ifdef XBYAK64
static const XBYAK_CONSTEXPR Reg64 rax(Operand::RAX), rcx(Operand::RCX), rdx(Operand::RDX), rbx(Operand::RBX), rsp(Operand::RSP), rbp(Operand::RBP), rsi(Operand::RSI), rdi(Operand::RDI), r8(Operand::R8), r9(Operand::R9), r10(Operand::R10), r11(Operand::R11), r12(Operand::R12), r13(Operand::R13), r14(Operand::R14), r15(Operand::R15);
static const XBYAK_CONSTEXPR Reg32 r8d(8), r9d(9), r10d(10), r11d(11), r12d(12), r13d(13), r14d(14), r15d(15);
static const XBYAK_CONSTEXPR Reg16 r8w(8), r9w(9), r10w(10), r11w(11), r12w(12), r13w(13), r14w(14), r15w(15);
static const XBYAK_CONSTEXPR Reg8 r8b(8), r9b(9), r10b(10), r11b(11), r12b(12), r13b(13), r14b(14), r15b(15), spl(Operand::SPL, true), bpl(Operand::BPL, true), sil(Operand::SIL, true), dil(Operand::DIL, true);
static const XBYAK_CONSTEXPR Xmm xmm8(8), xmm9(9), xmm10(10), xmm11(11), xmm12(12), xmm13(13), xmm14(14), xmm15(15);
static const XBYAK_CONSTEXPR Xmm xmm16(16), xmm17(17), xmm18(18), xmm19(19), xmm20(20), xmm21(21), xmm22(22), xmm23(23);
static const XBYAK_CONSTEXPR Xmm xmm24(24), xmm25(25), xmm26(26), xmm27(27), xmm28(28), xmm29(29), xmm30(30), xmm31(31);
static const XBYAK_CONSTEXPR Ymm ymm8(8), ymm9(9), ymm10(10), ymm11(11), ymm12(12), ymm13(13), ymm14(14), ymm15(15);
static const XBYAK_CONSTEXPR Ymm ymm16(16), ymm17(17), ymm18(18), ymm19(19), ymm20(20), ymm21(21), ymm22(22), ymm23(23);
static const XBYAK_CONSTEXPR Ymm ymm24(24), ymm25(25), ymm26(26), ymm27(27), ymm28(28), ymm29(29), ymm30(30), ymm31(31);
static const XBYAK_CONSTEXPR Zmm zmm8(8), zmm9(9), zmm10(10), zmm11(11), zmm12(12), zmm13(13), zmm14(14), zmm15(15);
static const XBYAK_CONSTEXPR Zmm zmm16(16), zmm17(17), zmm18(18), zmm19(19), zmm20(20), zmm21(21), zmm22(22), zmm23(23);
static const XBYAK_CONSTEXPR Zmm zmm24(24), zmm25(25), zmm26(26), zmm27(27), zmm28(28), zmm29(29), zmm30(30), zmm31(31);
static const XBYAK_CONSTEXPR Zmm tmm0(0), tmm1(1), tmm2(2), tmm3(3), tmm4(4), tmm5(5), tmm6(6), tmm7(7);
static const XBYAK_CONSTEXPR RegRip rip;
#endif
#ifndef XBYAK_DISABLE_SEGMENT
static const XBYAK_CONSTEXPR Segment es(Segment::es), cs(Segment::cs), ss(Segment::ss), ds(Segment::ds), fs(Segment::fs), gs(Segment::gs);
#endif
} // util

#ifdef _MSC_VER
	#pragma warning(pop)
#endif

} // end of namespace

#endif // XBYAK_XBYAK_H_