diff --git a/gen/gen_code.cpp b/gen/gen_code.cpp
index fc62eb8..c50bb14 100644
--- a/gen/gen_code.cpp
+++ b/gen/gen_code.cpp
@@ -1061,7 +1061,7 @@ void put()
 			{ 0xDC, "paddusb", T_0F | T_66 | T_YMM, false, true },
 			{ 0xDD, "paddusw", T_0F | T_66 | T_YMM, false, true },
 
-			{ 0x0F, "palignr", T_0F3A | T_66 | T_YMM, true, true },
+			{ 0x0F, "palignr", T_0F3A | T_66 | T_YMM | T_EVEX, true, true },
 
 			{ 0xDB, "pand", T_0F | T_66 | T_YMM, false, true },
 			{ 0xDF, "pandn", T_0F | T_66 | T_YMM, false, true },
diff --git a/test/make_nm.cpp b/test/make_nm.cpp
index aeb3c45..006d7a5 100644
--- a/test/make_nm.cpp
+++ b/test/make_nm.cpp
@@ -2719,19 +2719,22 @@ public:
 			put(p.name, XMM_KZ, _XMM, _XMM|p.mem);
 		}
 	}
-	void put512_X_X_XM_I()
+	void put512_X3_I()
 	{
 		const struct Tbl {
 			const char *name;
-			uint64_t mem;
+			uint64_t x1;
+			uint64_t x2;
+			uint64_t xm;
 		} tbl[] = {
 #ifdef XBYAK64
-			{ "vinsertps", _XMM3 },
+			{ "vinsertps", _XMM, _XMM, _XMM3 },
 #endif
+			{ "vpalignr", ZMM_KZ, _ZMM, _ZMM },
 		};
 		for (size_t i = 0; i < NUM_OF_ARRAY(tbl); i++) {
 			const Tbl& p = tbl[i];
-			put(p.name, _XMM, _XMM, p.mem, IMM);
+			put(p.name, p.x1, p.x2, p.xm, IMM);
 		}
 	}
 	void putAVX512()
@@ -2744,7 +2747,7 @@ public:
 		put_vmov();
 		put512_X_MX();
 		put512_X_X_XM();
-		put512_X_X_XM_I();
+		put512_X3_I();
 	}
 #endif
 };
diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index 7d6b7a6..78f7280 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -801,7 +801,7 @@ void vpaddusb(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1
 void vpaddusb(const Xmm& x, const Operand& op) { vpaddusb(x, x, op); }
 void vpaddusw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xDD); }
 void vpaddusw(const Xmm& x, const Operand& op) { vpaddusw(x, x, op); }
-void vpalignr(const Xmm& x1, const Xmm& x2, const Operand& op, uint8 imm) { opAVX_X_X_XM(x1, x2, op, T_0F3A | T_66 | T_YMM, 0x0F, imm); }
+void vpalignr(const Xmm& x1, const Xmm& x2, const Operand& op, uint8 imm) { opAVX_X_X_XM(x1, x2, op, T_0F3A | T_66 | T_YMM | T_EVEX, 0x0F, imm); }
 void vpalignr(const Xmm& x, const Operand& op, uint8 imm) { vpalignr(x, x, op, imm); }
 void vpand(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xDB); }
 void vpand(const Xmm& x, const Operand& op) { vpand(x, x, op); }