putX_XM is ok
diff --git a/gen/gen_avx512.cpp b/gen/gen_avx512.cpp
index 8739f5b..639b38b 100644
--- a/gen/gen_avx512.cpp
+++ b/gen/gen_avx512.cpp
@@ -132,19 +132,19 @@
const char *name;
int type;
} tbl[] = {
- { 0x6F, "vmovdqa32", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x6F, "vmovdqa64", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x6F, "vmovdqu8", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x6F, "vmovdqu16", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x6F, "vmovdqu32", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x6F, "vmovdqu64", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
+ { 0x6F, "vmovdqa32", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x6F, "vmovdqa64", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x6F, "vmovdqu8", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x6F, "vmovdqu16", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x6F, "vmovdqu32", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x6F, "vmovdqu64", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
};
for (size_t i = 0; i < NUM_OF_ARRAY(tbl); i++) {
const Tbl *p = &tbl[i];
std::string type = type2String(p->type);
printf("void %s(const Xmm& x, const Operand& op) { opAVX_X_XM_IMM(x, op, %s, 0x%02X); }\n", p->name, type.c_str(), p->code);
}
- puts("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); }");
+ puts("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 | T_N16 | T_N_VL, 0x1F); }");
}
void putM_X()
@@ -154,12 +154,12 @@
const char *name;
int type;
} tbl[] = {
- { 0x7F, "vmovdqa32", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x7F, "vmovdqa64", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x7F, "vmovdqu8", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x7F, "vmovdqu16", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x7F, "vmovdqu32", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z },
- { 0x7F, "vmovdqu64", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z },
+ { 0x7F, "vmovdqa32", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x7F, "vmovdqa64", T_66 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x7F, "vmovdqu8", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x7F, "vmovdqu16", T_F2 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x7F, "vmovdqu32", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW0 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
+ { 0x7F, "vmovdqu64", T_F3 | T_0F | T_MUST_EVEX | T_YMM | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_N16 | T_N_VL },
};
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 0bd53f7..4909da5 100644
--- a/gen/gen_code.cpp
+++ b/gen/gen_code.cpp
@@ -1162,8 +1162,8 @@
{ 0xC6, "shufpd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_B64, true, true },
{ 0xC6, "shufps", T_0F | T_YMM | T_EVEX | T_EW0 | T_B32, true, true },
- { 0x51, "sqrtsd", T_0F | T_F2 | T_EVEX | T_EW1 | T_ER_X, false, true },
- { 0x51, "sqrtss", T_0F | T_F3 | T_EVEX | T_EW0 | T_ER_X, false, true },
+ { 0x51, "sqrtsd", T_0F | T_F2 | T_EVEX | T_EW1 | T_ER_X | T_N8, false, true },
+ { 0x51, "sqrtss", T_0F | T_F3 | T_EVEX | T_EW0 | T_ER_X | T_N4, false, true },
{ 0x15, "unpckhpd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_B64, false, true },
{ 0x15, "unpckhps", T_0F | T_YMM | T_EVEX | T_EW0 | T_B32, false, true },
@@ -1206,17 +1206,17 @@
{ 0x5B, "cvttps2dq", T_0F | T_F3 | T_YMM, false },
{ 0x28, "movapd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_N16 | T_N_VL, false },
{ 0x28, "movaps", T_0F | T_YMM | T_EVEX | T_EW0 | T_N16 | T_N_VL, false },
- { 0x12, "movddup", T_0F | T_F2 | T_YMM | T_EVEX | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z, false },
- { 0x6F, "movdqa", T_0F | T_66 | T_YMM | T_N16 | T_N_VL | T_N16 | T_N_VL, false },
- { 0x6F, "movdqu", T_0F | T_F3 | T_YMM | T_N16 | T_N_VL | T_N16 | T_N_VL, false },
+ { 0x12, "movddup", T_0F | T_F2 | T_YMM | T_EVEX | T_EW1 | T_ER_X | T_ER_Y | T_ER_Z | T_DUP, false },
+ { 0x6F, "movdqa", T_0F | T_66 | T_YMM | T_N16 | T_N_VL, false },
+ { 0x6F, "movdqu", T_0F | T_F3 | T_YMM | T_N16 | T_N_VL, false },
{ 0x16, "movshdup", T_0F | T_F3 | T_YMM | T_EVEX | T_EW0, false },
{ 0x12, "movsldup", T_0F | T_F3 | T_YMM | T_EVEX | T_EW0, false },
{ 0x10, "movupd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_N16 | T_N_VL, false },
{ 0x10, "movups", T_0F | T_YMM | T_EVEX | T_EW0 | T_N16 | T_N_VL, false },
- { 0x1C, "pabsb", T_0F38 | T_66 | T_YMM | T_EVEX, false },
- { 0x1D, "pabsw", T_0F38 | T_66 | T_YMM | T_EVEX, false },
- { 0x1E, "pabsd", T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0 | T_B32, false },
+ { 0x1C, "pabsb", T_0F38 | T_66 | T_YMM | T_EVEX | T_N16 | T_N_VL, false },
+ { 0x1D, "pabsw", T_0F38 | T_66 | T_YMM | T_EVEX | T_N16 | T_N_VL, false },
+ { 0x1E, "pabsd", T_0F38 | T_66 | T_YMM | T_EVEX | T_EW0 | T_B32 | T_N16 | T_N_VL, false },
{ 0x41, "phminposuw", T_0F38 | T_66, false },
{ 0x20, "pmovsxbw", T_0F38 | T_66 | T_YMM | T_EVEX, false },
@@ -1241,8 +1241,8 @@
{ 0x53, "rcpps", T_0F | T_YMM, false },
{ 0x52, "rsqrtps", T_0F | T_YMM, false },
- { 0x51, "sqrtpd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_ER_Z | T_B64, false },
- { 0x51, "sqrtps", T_0F | T_YMM | T_EVEX | T_EW0 | T_ER_Z | T_B32, false },
+ { 0x51, "sqrtpd", T_0F | T_66 | T_YMM | T_EVEX | T_EW1 | T_ER_Z | T_B64 | T_N16 | T_N_VL, false },
+ { 0x51, "sqrtps", T_0F | T_YMM | T_EVEX | T_EW0 | T_ER_Z | T_B32 | T_N16 | T_N_VL, false },
{ 0x2E, "ucomisd", T_0F | T_66 | T_EVEX | T_EW1 | T_SAE_X | T_N8, false },
{ 0x2E, "ucomiss", T_0F | T_EVEX | T_EW0 | T_SAE_X | T_N4, false },
diff --git a/test/make_512.cpp b/test/make_512.cpp
index 90d14c9..e57b909 100644
--- a/test/make_512.cpp
+++ b/test/make_512.cpp
@@ -848,18 +848,18 @@
put(p.name, MEM, _YMM);
put(p.name, MEM, _ZMM);
}
- put("vsqrtpd", XMM_KZ, M_1to2);
- put("vsqrtpd", YMM_KZ, M_1to4);
- put("vsqrtpd", ZMM_KZ, M_1to8);
+ put("vsqrtpd", XMM_KZ, M_1to2 | _MEM);
+ put("vsqrtpd", YMM_KZ, M_1to4 | _MEM);
+ put("vsqrtpd", ZMM_KZ, M_1to8 | _MEM);
put("vsqrtpd", ZMM_KZ, ZMM_ER);
- put("vsqrtps", XMM_KZ, M_1to4);
- put("vsqrtps", YMM_KZ, M_1to8);
- put("vsqrtps", ZMM_KZ, M_1to16);
+ put("vsqrtps", XMM_KZ, M_1to4 | _MEM);
+ put("vsqrtps", YMM_KZ, M_1to8 | _MEM);
+ put("vsqrtps", ZMM_KZ, M_1to16 | _MEM);
put("vsqrtps", ZMM_KZ, ZMM_ER);
- put("vpabsd", ZMM_KZ, M_1to16);
- put("vpabsq", ZMM_KZ, M_1to8);
+ put("vpabsd", ZMM_KZ, M_1to16 | _MEM);
+ put("vpabsq", ZMM_KZ, M_1to8 | _MEM);
put("vbroadcastf32x2", YMM_KZ | ZMM_KZ, _XMM | _MEM);
put("vbroadcastf32x4", YMM_KZ | ZMM_KZ, _MEM);
@@ -1433,12 +1433,12 @@
separateFunc();
putAVX512_M_X();
separateFunc();
-#endif
put_vmov();
separateFunc();
-#if 0
+#endif
put512_X_XM();
separateFunc();
+#if 0
put512_X_X_XM();
separateFunc();
put512_X3();
diff --git a/xbyak/xbyak_avx512.h b/xbyak/xbyak_avx512.h
index 29c10c7..0462485 100644
--- a/xbyak/xbyak_avx512.h
+++ b/xbyak/xbyak_avx512.h
@@ -76,19 +76,19 @@
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 | T_N16 | T_N_VL, 0x65); }
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 | T_N16 | T_N_VL, 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 | T_N16 | T_N_VL, 0x37); }
-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 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 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 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 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 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 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 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, 0x7F); }
-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, 0x7F); }
-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, 0x7F); }
-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, 0x7F); }
-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, 0x7F); }
-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, 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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x6F); }
+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 | T_N16 | T_N_VL, 0x1F); }
+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_N16 | T_N_VL, 0x7F); }
+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_N16 | T_N_VL, 0x7F); }
+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_N16 | T_N_VL, 0x7F); }
+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_N16 | T_N_VL, 0x7F); }
+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_N16 | T_N_VL, 0x7F); }
+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_N16 | T_N_VL, 0x7F); }
void valignd(const Xmm& x1, const Xmm& x2, const Operand& op, uint8 imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW0 | T_YMM | T_MUST_EVEX | T_N16 | T_N_VL, 0x03, imm); }
void valignq(const Xmm& x1, const Xmm& x2, const Operand& op, uint8 imm) { opAVX_X_X_XM(x1, x2, op, T_66 | T_0F3A | T_EW1 | T_YMM | T_MUST_EVEX | T_N16 | T_N_VL, 0x03, imm); }
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); }
diff --git a/xbyak/xbyak_mnemonic.h b/xbyak/xbyak_mnemonic.h
index b826df8..013d0ca 100644
--- a/xbyak/xbyak_mnemonic.h
+++ b/xbyak/xbyak_mnemonic.h
@@ -950,9 +950,9 @@
void vshufpd(const Xmm& x, const Operand& op, uint8 imm) { vshufpd(x, x, op, imm); }
void vshufps(const Xmm& x1, const Xmm& x2, const Operand& op, uint8 imm) { opAVX_X_X_XM(x1, x2, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_B32, 0xC6, imm); }
void vshufps(const Xmm& x, const Operand& op, uint8 imm) { vshufps(x, x, op, imm); }
-void vsqrtsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_0F | T_EW1 | T_EVEX | T_ER_X, 0x51); }
+void vsqrtsd(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F2 | T_0F | T_EW1 | T_EVEX | T_ER_X | T_N8, 0x51); }
void vsqrtsd(const Xmm& x, const Operand& op) { vsqrtsd(x, x, op); }
-void vsqrtss(const Xmm& x1, const Xmm& x2, const Operand& op) { opAVX_X_X_XM(x1, x2, op, T_F3 | T_0F | T_EW0 | 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_F3 | T_0F | T_EW0 | T_EVEX | T_ER_X | T_N4, 0x51); }
void vsqrtss(const Xmm& x, const Operand& op) { vsqrtss(x, x, op); }
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 vunpckhpd(const Xmm& x, const Operand& op) { vunpckhpd(x, x, op); }
@@ -980,16 +980,16 @@
void vcvttps2dq(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_YMM, 0x5B); }
void vmovapd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x28); }
void vmovaps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x28); }
-void vmovddup(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F2 | T_0F | T_EW1 | T_YMM | T_EVEX | T_ER_X | T_ER_Y | T_ER_Z, 0x12); }
+void vmovddup(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F2 | T_0F | T_EW1 | T_YMM | T_EVEX | T_ER_X | T_ER_Y | T_ER_Z | T_DUP, 0x12); }
void vmovdqa(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_YMM | T_N16 | T_N_VL, 0x6F); }
void vmovdqu(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_F3 | T_0F | T_YMM | T_N16 | T_N_VL, 0x6F); }
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 vmovupd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x10); }
void vmovups(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x10); }
-void vpabsb(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x1C); }
-void vpabsw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x1D); }
-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 vpabsb(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x1C); }
+void vpabsw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX | T_N16 | T_N_VL, 0x1D); }
+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 | T_N16 | T_N_VL, 0x1E); }
void vphminposuw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38, 0x41); }
void vpmovsxbw(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x20); }
void vpmovsxbd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38 | T_YMM | T_EVEX, 0x21); }
@@ -1009,8 +1009,8 @@
void vptest(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F38, 0x17); }
void vrcpps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_YMM, 0x53); }
void vrsqrtps(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_YMM, 0x52); }
-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 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 | T_N16 | T_N_VL, 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 | T_N16 | T_N_VL, 0x51); }
void vucomisd(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_66 | T_0F | T_EW1 | T_EVEX | T_SAE_X | T_N8, 0x2E); }
void vucomiss(const Xmm& xm, const Operand& op) { opAVX_X_XM_IMM(xm, op, T_0F | T_EW0 | T_EVEX | T_SAE_X | T_N4, 0x2E); }
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_N16 | T_N_VL, 0x29); }
