add umwait
diff --git a/gen/gen_code.cpp b/gen/gen_code.cpp
index 069ae32..e23b552 100644
--- a/gen/gen_code.cpp
+++ b/gen/gen_code.cpp
@@ -1087,6 +1087,7 @@
 		puts("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)); }");
 		puts("void tpause(const Reg32& r) { int idx = r.getIdx(); if (idx > 7) XBYAK_THROW(ERR_BAD_PARAMETER) db(0x66); db(0x0F); db(0xAE); setModRM(3, 6, idx); }");
 		puts("void umonitor(const Reg& r) { int idx = r.getIdx(); if (idx > 7) XBYAK_THROW(ERR_BAD_PARAMETER) int bit = r.getBit(); if (BIT != bit) { if ((BIT == 32 && bit == 16) || (BIT == 64 && bit == 32)) { db(0x67); } else { XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER) } } db(0xF3); db(0x0F); db(0xAE); setModRM(3, 6, idx); }");
+		puts("void umwait(const Reg32& r) { int idx = r.getIdx(); if (idx > 7) XBYAK_THROW(ERR_BAD_PARAMETER) db(0xF2); db(0x0F); db(0xAE); setModRM(3, 6, idx); }");
 	}
 	{
 		const struct Tbl {
diff --git a/test/misc.cpp b/test/misc.cpp
index 0b664ef..f46239b 100644
--- a/test/misc.cpp
+++ b/test/misc.cpp
@@ -1891,7 +1891,7 @@
 }
 #endif
 
-CYBOZU_TEST_AUTO(misc)
+CYBOZU_TEST_AUTO(waitpkg)
 {
 	struct Code : Xbyak::CodeGenerator {
 		Code()
@@ -1905,6 +1905,8 @@
 			umonitor(ecx);
 			umonitor(rcx);
 #endif
+			umwait(eax);
+			umwait(ebx);
 		}
 	} c;
 	const uint8_t tbl[] = {
@@ -1914,6 +1916,9 @@
 		// umonitor
 		0x67, 0xf3, 0x0f, 0xae, 0xf1,
 		0xf3, 0x0f, 0xae, 0xf1,
+		// tpause
+		0xf2, 0x0f, 0xae, 0xf0,
+		0xf2, 0x0f, 0xae, 0xf3,
 	};
 	const size_t n = sizeof(tbl) / sizeof(tbl[0]);
 	CYBOZU_TEST_EQUAL(c.getSize(), n);
diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index e4e623c..5096c36 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -819,6 +819,7 @@
 void ucomiss(const Xmm& xmm, const Operand& op) { opGen(xmm, op, 0x2E, 0x100, isXMM_XMMorMEM); }
 void ud2() { db(0x0F); db(0x0B); }
 void umonitor(const Reg& r) { int idx = r.getIdx(); if (idx > 7) XBYAK_THROW(ERR_BAD_PARAMETER) int bit = r.getBit(); if (BIT != bit) { if ((BIT == 32 && bit == 16) || (BIT == 64 && bit == 32)) { db(0x67); } else { XBYAK_THROW(ERR_BAD_SIZE_OF_REGISTER) } } db(0xF3); db(0x0F); db(0xAE); setModRM(3, 6, idx); }
+void umwait(const Reg32& r) { int idx = r.getIdx(); if (idx > 7) XBYAK_THROW(ERR_BAD_PARAMETER) db(0xF2); db(0x0F); db(0xAE); setModRM(3, 6, idx); }
 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); }