diff --git a/gen/gen_avx512.cpp b/gen/gen_avx512.cpp
index 85720d5..1b0d489 100644
--- a/gen/gen_avx512.cpp
+++ b/gen/gen_avx512.cpp
@@ -196,6 +196,8 @@ void putX_X_XM_IMM()
 
 		{ 0xEF, "vpxord", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_B32, false },
 		{ 0xEF, "vpxorq", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_B64, false },
+
+		{ 0x40, "vpmullq", T_66 | T_0F38 | T_MUST_EVEX | T_YMM | T_EW1 | T_B64, false },
 	};
 	for (size_t i = 0; i < NUM_OF_ARRAY(tbl); i++) {
 		const Tbl *p = &tbl[i];
diff --git a/gen/gen_code.cpp b/gen/gen_code.cpp
index d9cf45f..d07605d 100644
--- a/gen/gen_code.cpp
+++ b/gen/gen_code.cpp
@@ -1105,14 +1105,14 @@ void put()
 			{ 0x3A, "pminuw", T_0F38 | T_66 | T_YMM | T_EVEX, false, true },
 			{ 0x3B, "pminud", T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0 | T_B32, false, true },
 
-			{ 0xE4, "pmulhuw", T_0F | T_66 | T_YMM, false, true },
-			{ 0x0B, "pmulhrsw", T_0F38 | T_66 | T_YMM, false, true },
-			{ 0xE5, "pmulhw", T_0F | T_66 | T_YMM, false, true },
-			{ 0xD5, "pmullw", T_0F | T_66 | T_YMM, false, true },
-			{ 0x40, "pmulld", T_0F38 | T_66 | T_YMM, false, true },
+			{ 0xE4, "pmulhuw", T_0F | T_66 | T_YMM | T_EVEX, false, true },
+			{ 0x0B, "pmulhrsw", T_0F38 | T_66 | T_YMM | T_EVEX, false, true },
+			{ 0xE5, "pmulhw", T_0F | T_66 | T_YMM | T_EVEX, false, true },
+			{ 0xD5, "pmullw", T_0F | T_66 | T_YMM | T_EVEX, false, true },
+			{ 0x40, "pmulld", T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0 | T_B32, false, true },
 
-			{ 0xF4, "pmuludq", T_0F | T_66, false, true },
-			{ 0x28, "pmuldq", T_0F38 | T_66 | T_YMM, false, true },
+			{ 0xF4, "pmuludq", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_B64, false, true },
+			{ 0x28, "pmuldq", T_0F38 | T_66 | T_YMM | T_EVEX | T_EW1 | T_B64, false, true },
 
 			{ 0xEB, "por", T_0F | T_66 | T_YMM, false, true },
 			{ 0xF6, "psadbw", T_0F | T_66 | T_YMM | T_EVEX, false, true },
diff --git a/test/make_nm.cpp b/test/make_nm.cpp
index d878dfb..a27e53a 100644
--- a/test/make_nm.cpp
+++ b/test/make_nm.cpp
@@ -1537,7 +1537,7 @@ class Test {
 			{ "vpmullw", true },
 			{ "vpmulld", true },
 
-			{ "vpmuludq", false },
+			{ "vpmuludq", true },
 			{ "vpmuldq", true },
 
 			{ "vpor", true },
@@ -2921,7 +2921,31 @@ public:
 			{ "vpxorq", _ZMM | ZMM_KZ, _ZMM, M_1to8 },
 
 			{ "vpsadbw", _XMM3, _XMM, _XMM },
-			{ "vpsadbw", _ZMM, _ZMM, _MEM }
+			{ "vpsadbw", _ZMM, _ZMM, _MEM },
+
+			{ "vpmuldq", _XMM3, _XMM, _XMM | M_1to2 },
+			{ "vpmuldq", ZMM_KZ, _ZMM, M_1to8 },
+
+			{ "vpmulhrsw", _XMM3, _XMM, _XMM },
+			{ "vpmulhrsw", ZMM_KZ, _ZMM, _MEM },
+
+			{ "vpmulhuw", _XMM3, _XMM, _XMM },
+			{ "vpmulhuw", ZMM_KZ, _ZMM, _MEM },
+
+			{ "vpmulhw", _XMM3, _XMM, _XMM },
+			{ "vpmulhw", ZMM_KZ, _ZMM, _MEM },
+
+			{ "vpmullw", _XMM3, _XMM, _XMM },
+			{ "vpmullw", ZMM_KZ, _ZMM, _MEM },
+
+			{ "vpmulld", _XMM3, _XMM, M_1to4 },
+			{ "vpmulld", ZMM_KZ, _ZMM, M_1to16 },
+
+			{ "vpmullq", _XMM3, _XMM, M_1to2 },
+			{ "vpmullq", ZMM_KZ, _ZMM, M_1to8 },
+
+			{ "vpmuludq", _XMM3, _XMM, M_1to2 },
+			{ "vpmuludq", ZMM_KZ, _ZMM, M_1to8 },
 		};
 		for (size_t i = 0; i < NUM_OF_ARRAY(tbl); i++) {
 			const Tbl& p = tbl[i];
diff --git a/xbyak/xbyak_avx512.h b/xbyak/xbyak_avx512.h
index 0c16bba..d65cbb0 100644
--- a/xbyak/xbyak_avx512.h
+++ b/xbyak/xbyak_avx512.h
@@ -108,5 +108,6 @@ void vpord(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x
 void vporq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xEB); }
 void vpxord(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | 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_0F | T_66 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0xEF); }
+void vpmullq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x40); }
 void vpsraq(const Xmm& x, const Operand& op, uint8 imm) { opAVX_X_X_XM(x.copyAndSetIdx(4), x, op, T_0F | T_66 | T_EW1 | T_YMM | T_MUST_EVEX | T_B64, 0x72, imm); }
 #endif
diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index 9d0e9b5..50ef2ef 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -867,19 +867,19 @@ void vpminuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1,
 void vpminuw(const Xmm& x, const Operand& op) { vpminuw(x, x, op); }
 void vpminud(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x3B); }
 void vpminud(const Xmm& x, const Operand& op) { vpminud(x, x, op); }
-void vpmulhuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xE4); }
+void vpmulhuw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM | T_EVEX, 0xE4); }
 void vpmulhuw(const Xmm& x, const Operand& op) { vpmulhuw(x, x, op); }
-void vpmulhrsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_YMM, 0x0B); }
+void vpmulhrsw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_YMM | T_EVEX, 0x0B); }
 void vpmulhrsw(const Xmm& x, const Operand& op) { vpmulhrsw(x, x, op); }
-void vpmulhw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xE5); }
+void vpmulhw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM | T_EVEX, 0xE5); }
 void vpmulhw(const Xmm& x, const Operand& op) { vpmulhw(x, x, op); }
-void vpmullw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xD5); }
+void vpmullw(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM | T_EVEX, 0xD5); }
 void vpmullw(const Xmm& x, const Operand& op) { vpmullw(x, x, op); }
-void vpmulld(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_YMM, 0x40); }
+void vpmulld(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_EW0 | T_YMM | T_EVEX | T_B32, 0x40); }
 void vpmulld(const Xmm& x, const Operand& op) { vpmulld(x, x, op); }
-void vpmuludq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66, 0xF4); }
+void vpmuludq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_EW1 | T_YMM | T_EVEX | T_B64, 0xF4); }
 void vpmuludq(const Xmm& x, const Operand& op) { vpmuludq(x, x, op); }
-void vpmuldq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_YMM, 0x28); }
+void vpmuldq(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F38 | T_66 | T_EW1 | T_YMM | T_EVEX | T_B64, 0x28); }
 void vpmuldq(const Xmm& x, const Operand& op) { vpmuldq(x, x, op); }
 void vpor(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_0F | T_66 | T_YMM, 0xEB); }
 void vpor(const Xmm& x, const Operand& op) { vpor(x, x, op); }