add vmovntpd
diff --git a/gen/gen_code.cpp b/gen/gen_code.cpp
index 35272e6..1d2752c 100644
--- a/gen/gen_code.cpp
+++ b/gen/gen_code.cpp
@@ -1534,7 +1534,7 @@
 		printf("void vmovmskps(const Reg& r, const Xmm& x) { if (!r.isBit(i32e)) throw Error(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); }\n");
 
 		printf("void vmovntdq(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW0, 0xE7); }\n");
-		printf("void vmovntpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM, 0x2B); }\n");
+		printf("void vmovntpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW1, 0x2B); }\n");
 		printf("void vmovntps(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_YMM, 0x2B); }\n");
 		printf("void vmovntdqa(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0, 0x2A); }\n");
 
diff --git a/test/make_nm.cpp b/test/make_nm.cpp
index 00b73d5..6db238c 100644
--- a/test/make_nm.cpp
+++ b/test/make_nm.cpp
@@ -2614,6 +2614,7 @@
 		put("vmovlhps", _XMM3, _XMM3, _XMM3);
 		put("vmovntdqa", _XMM3|_YMM3|ZMM, MEM);
 		put("vmovntdq", MEM, _XMM3 | _YMM3 | ZMM);
+		put("vmovntpd", MEM, _XMM3 | _YMM3 | ZMM);
 		{
 			const char tbl[][16] = {
 				"vmovhpd",
diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index 033ebba..bac8a4d 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -1464,7 +1464,7 @@
 void vmovmskpd(const Reg& r, const Xmm& x) { if (!r.isBit(i32e)) throw Error(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)) throw Error(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) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW0, 0xE7); }
-void vmovntpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM, 0x2B); }
+void vmovntpd(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_66 | T_YMM | T_EVEX | T_EW1, 0x2B); }
 void vmovntps(const Address& addr, const Xmm& x) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F | T_YMM, 0x2B); }
 void vmovntdqa(const Xmm& x, const Address& addr) { opAVX_X_X_XM(x, cvtIdx0(x), addr, T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0, 0x2A); }
 void vmovsd(const Xmm& x1, const Xmm& x2, const Operand& op = Operand()) { if (!op.isNone() && !op.isXMM()) throw Error(ERR_BAD_COMBINATION); opAVX_X_X_XM(x1, x2, op, T_0F | T_F2, 0x10); }