diff mbox series

[1/4] x86: fold certain VEX and EVEX templates

Message ID bb09df71-87f5-f88f-3c3f-60bb5b4b1209@suse.com
State New
Headers
Series x86: fold a number of VEX and EVEX templates |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_binutils_check--master-arm success Testing passed
linaro-tcwg-bot/tcwg_binutils_build--master-arm success Testing passed
linaro-tcwg-bot/tcwg_binutils_build--master-aarch64 success Testing passed
linaro-tcwg-bot/tcwg_binutils_check--master-aarch64 success Testing passed

Commit Message

Jan Beulich Sept. 15, 2023, 8:47 a.m. UTC 
  In anticipation of APX introduce logic to reduce the number of templates
we have now, allowing to limit some the number of ones we then need to
gain.

The fundamental requirements are that
- attributes be compatible, which specifically means VexW needs to be
  the same in the templates (which often isn't the case, for VEX
  encodings having far more WIG tha, EVEX ones),
- the EVEX form being AVX512F (with or without AVX512VL), not any of its
  extensions (the same will then be required for APX - it'll need to be
  APX_F).

Note that in check_register() there's now a redundant zmm check. Since
this logic will need revisiting for APX anyway, I'd like to keep it that
way for now. (Similarly a couple of if()-s which could be folded are
kept separate, to reduce code churn when adding APX support.)
---
RFC: Of course there are quite a few code changes, so there is the
     question of the savings being worth it.

The AVX512F constraint may be possible to relax, but the change is big
enough already.
diff mbox series

Patch

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -436,6 +436,7 @@  struct _i386_insn
 	vex_encoding_vex,
 	vex_encoding_vex3,
 	vex_encoding_evex,
+	vex_encoding_evex512,
 	vex_encoding_error
       } vec_encoding;
 
@@ -1872,6 +1873,13 @@  cpu_flags_and_not (i386_cpu_flags x, i38
 
 static const i386_cpu_flags avx512 = CPU_ANY_AVX512F_FLAGS;
 
+static INLINE bool need_evex_encoding (void)
+{
+  return i.vec_encoding == vex_encoding_evex
+	|| i.vec_encoding == vex_encoding_evex512
+	|| i.mask.reg;
+}
+
 #define CPU_FLAGS_ARCH_MATCH		0x1
 #define CPU_FLAGS_64BIT_MATCH		0x2
 
@@ -1899,6 +1907,27 @@  cpu_flags_match (const insn_template *t)
       /* This instruction is available only on some archs.  */
       i386_cpu_flags cpu = cpu_arch_flags;
 
+      /* Dual VEX/EVEX templates may need stripping of one of the flags.  */
+      if (t->opcode_modifier.vex && t->opcode_modifier.evex)
+	{
+	  /* Dual AVX/AVX512F templates need to retain AVX512F only if we already
+	     know that EVEX encoding will be needed.  */
+	  if ((x.bitfield.cpuavx || x.bitfield.cpuavx2)
+	      && x.bitfield.cpuavx512f)
+	    {
+	      if (need_evex_encoding ())
+		{
+		  x.bitfield.cpuavx = 0;
+		  x.bitfield.cpuavx2 = 0;
+		}
+	      else
+		{
+		  x.bitfield.cpuavx512f = 0;
+		  x.bitfield.cpuavx512vl = 0;
+		}
+	    }
+	}
+
       /* AVX512VL is no standalone feature - match it and then strip it.  */
       if (x.bitfield.cpuavx512vl && !cpu.bitfield.cpuavx512vl)
 	return match;
@@ -3646,6 +3675,27 @@  install_template (const insn_template *t
 
   i.tm = *t;
 
+  /* Dual VEX/EVEX templates need stripping one of the possible variants.  */
+  if (t->opcode_modifier.vex && t->opcode_modifier.evex)
+  {
+      if ((is_cpu (t, CpuAVX) || is_cpu (t, CpuAVX2))
+	  && is_cpu (t, CpuAVX512F))
+	{
+	  if (need_evex_encoding ())
+	    {
+	      i.tm.opcode_modifier.vex = 0;
+	      i.tm.cpu.bitfield.cpuavx = 0;
+	      if (is_cpu (&i.tm, CpuAVX2))
+	        i.tm.cpu.bitfield.isa = 0;
+	    }
+	  else
+	    {
+	      i.tm.opcode_modifier.evex = 0;
+	      i.tm.cpu.bitfield.cpuavx512f = 0;
+	    }
+	}
+  }
+
   /* Note that for pseudo prefixes this produces a length of 1. But for them
      the length isn't interesting at all.  */
   for (l = 1; l < 4; ++l)
@@ -4553,6 +4603,8 @@  optimize_encoding (void)
 	      i.tm.opcode_modifier.vex = VEX128;
 	      i.tm.opcode_modifier.vexw = VEXW0;
 	      i.tm.opcode_modifier.evex = 0;
+	      i.vec_encoding = vex_encoding_vex;
+	      i.mask.reg = NULL;
 	    }
 	  else if (optimize > 1)
 	    i.tm.opcode_modifier.evex = EVEX128;
@@ -5438,6 +5490,11 @@  md_assemble (char *line)
   if (optimize && !i.no_optimize && i.tm.opcode_modifier.optimize)
     optimize_encoding ();
 
+  /* Past optimization there's no need to distinguish vex_encoding_evex and
+     vex_encoding_evex512 anymore.  */
+  if (i.vec_encoding == vex_encoding_evex512)
+    i.vec_encoding = vex_encoding_evex;
+
   if (use_unaligned_vector_move)
     encode_with_unaligned_vector_move ();
 
@@ -5467,6 +5524,7 @@  md_assemble (char *line)
 	  if (i.tm.operand_types[j].bitfield.tmmword)
 	    i.xstate |= xstate_tmm;
 	  else if (i.tm.operand_types[j].bitfield.zmmword
+		   && !i.tm.opcode_modifier.vex
 		   && vector_size >= VSZ512)
 	    i.xstate |= xstate_zmm;
 	  else if (i.tm.operand_types[j].bitfield.ymmword
@@ -6468,7 +6526,8 @@  check_VecOperands (const insn_template *
   cpu = cpu_flags_and (cpu_flags_from_attr (t->cpu), avx512);
   if (!cpu_flags_all_zero (&cpu)
       && !is_cpu (t, CpuAVX512VL)
-      && !cpu_arch_flags.bitfield.cpuavx512vl)
+      && !cpu_arch_flags.bitfield.cpuavx512vl
+      && (!t->opcode_modifier.vex || need_evex_encoding()))
     {
       for (op = 0; op < t->operands; ++op)
 	{
@@ -6779,6 +6838,8 @@  check_VecOperands (const insn_template *
 
   /* Check vector Disp8 operand.  */
   if (t->opcode_modifier.disp8memshift
+      && (!t->opcode_modifier.vex
+          || need_evex_encoding ())
       && i.disp_encoding <= disp_encoding_8bit)
     {
       if (i.broadcast.type || i.broadcast.bytes)
@@ -6874,7 +6935,8 @@  VEX_check_encoding (const insn_template
       return 1;
     }
 
-  if (i.vec_encoding == vex_encoding_evex)
+  if (i.vec_encoding == vex_encoding_evex
+      || i.vec_encoding == vex_encoding_evex512)
     {
       /* This instruction must be encoded with EVEX prefix.  */
       if (!is_evex_encoding (t))
@@ -11211,6 +11273,10 @@  s_insn (int dummy ATTRIBUTE_UNUSED)
 	  goto done;
 	}
 
+      /* No need to distinguish vex_encoding_evex and vex_encoding_evex512.  */
+      if (i.vec_encoding == vex_encoding_evex512)
+	i.vec_encoding = vex_encoding_evex;
+
       /* Are we to emit ModR/M encoding?  */
       if (!i.short_form
 	  && (i.mem_operands
@@ -11633,6 +11699,12 @@  RC_SAE_specifier (const char *pstr)
 	      return NULL;
 	    }
 
+	  if (i.vec_encoding == vex_encoding_default)
+	    i.vec_encoding = vex_encoding_evex512;
+	  else if (i.vec_encoding != vex_encoding_evex
+		   && i.vec_encoding != vex_encoding_evex512)
+	    return NULL;
+
 	  i.rounding.type = RC_NamesTable[j].type;
 
 	  return (char *)(pstr + RC_NamesTable[j].len);
@@ -11692,6 +11764,12 @@  check_VecOperations (char *op_string)
 		}
 	      op_string++;
 
+	      if (i.vec_encoding == vex_encoding_default)
+		i.vec_encoding = vex_encoding_evex;
+	      else if (i.vec_encoding != vex_encoding_evex
+		       && i.vec_encoding != vex_encoding_evex512)
+		goto unknown_vec_op;
+
 	      i.broadcast.type = bcst_type;
 	      i.broadcast.operand = this_operand;
 
@@ -13953,8 +14031,17 @@  static bool check_register (const reg_en
 	}
     }
 
-  if (vector_size < VSZ512 && r->reg_type.bitfield.zmmword)
-    return false;
+  if (r->reg_type.bitfield.zmmword)
+    {
+      if (vector_size < VSZ512)
+	return false;
+
+      if (i.vec_encoding == vex_encoding_default)
+	i.vec_encoding = vex_encoding_evex512;
+      else if (i.vec_encoding != vex_encoding_evex
+	       && i.vec_encoding != vex_encoding_evex512)
+	i.vec_encoding = vex_encoding_error;
+    }
 
   if (vector_size < VSZ256 && r->reg_type.bitfield.ymmword)
     return false;
@@ -13979,7 +14066,8 @@  static bool check_register (const reg_en
 	  || flag_code != CODE_64BIT)
 	return false;
 
-      if (i.vec_encoding == vex_encoding_default)
+      if (i.vec_encoding == vex_encoding_default
+	  || i.vec_encoding == vex_encoding_evex512)
 	i.vec_encoding = vex_encoding_evex;
       else if (i.vec_encoding != vex_encoding_evex)
 	i.vec_encoding = vex_encoding_error;
--- a/gas/config/tc-i386-intel.c
+++ b/gas/config/tc-i386-intel.c
@@ -209,6 +209,11 @@  operatorT i386_operator (const char *nam
 	      || i386_types[j].sz[0] > 8
 	      || (i386_types[j].sz[0] & (i386_types[j].sz[0] - 1)))
 	    return O_illegal;
+	  if (i.vec_encoding == vex_encoding_default)
+	    i.vec_encoding = vex_encoding_evex;
+	  else if (i.vec_encoding != vex_encoding_evex
+		   && i.vec_encoding != vex_encoding_evex512)
+	    return O_illegal;
 	  if (!i.broadcast.bytes && !i.broadcast.type)
 	    {
 	      i.broadcast.bytes = i386_types[j].sz[0];
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -131,6 +131,8 @@ 
 #define EVexLIG EVex=EVEXLIG
 #define EVexDYN EVex=EVEXDYN
 
+#define Disp8ShiftVL Disp8MemShift=DISP8_SHIFT_VL
+
 #define Vsz256 Vsz=VSZ256
 #define Vsz512 Vsz=VSZ512
 
@@ -1518,8 +1520,8 @@  vdivs<sd>, 0x<sd:spfx>5e, AVX, Modrm|Vex
 vdppd, 0x6641, AVX, Modrm|Vex|Space0F3A|VexVVVV|VexWIG|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
 vdpps, 0x6640, AVX, Modrm|Vex|Space0F3A|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vextractf128, 0x6619, AVX, Modrm|Vex=2|Space0F3A|VexW=1|NoSuf, { Imm8, RegYMM, Unspecified|BaseIndex|RegXMM }
-vextractps, 0x6617, AVX, Modrm|Vex|Space0F3A|VexWIG|NoSuf, { Imm8, RegXMM, Reg32|Dword|Unspecified|BaseIndex }
-vextractps, 0x6617, AVX|x64, RegMem|Vex|Space0F3A|VexWIG|NoSuf, { Imm8, RegXMM, Reg64 }
+vextractps, 0x6617, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F3A|VexWIG|Disp8MemShift=2|NoSuf, { Imm8, RegXMM, Reg32|Dword|Unspecified|BaseIndex }
+vextractps, 0x6617, AVX|AVX512F|x64, RegMem|Vex128|EVex128|Space0F3A|VexWIG|NoSuf, { Imm8, RegXMM, Reg64 }
 vhaddpd, 0x667c, AVX, Modrm|Vex|Space0F|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vhaddps, 0xf27c, AVX, Modrm|Vex|Space0F|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vhsubpd, 0x667d, AVX, Modrm|Vex|Space0F|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
@@ -1541,7 +1543,7 @@  vmovap<sd>, 0x<sd:ppfx>28, AVX, D|Modrm|
 // by Intel AVX spec).  To avoid extra template in gcc x86 backend and
 // support assembler for AMD64, we accept 64bit operand on vmovd so
 // that we can use one template for both SSE and AVX instructions.
-vmovd, 0x666e, AVX, D|Modrm|Vex=1|Space0F|NoSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
+vmovd, 0x666e, AVX|AVX512F, D|Modrm|Vex128|EVex128|Space0F|Disp8MemShift=2|NoSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
 vmovd, 0x667e, AVX|x64, D|RegMem|Vex=1|Space0F|VexW=2|NoSuf|Size64, { RegXMM, Reg64 }
 vmovddup, 0xf212, AVX, Modrm|Vex|Space0F|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 vmovddup, 0xf212, AVX, Modrm|Vex=2|Space0F|VexWIG|NoSuf, { Unspecified|BaseIndex|RegYMM, RegYMM }
@@ -1559,7 +1561,7 @@  vmovntdqa, 0x662a, AVX|AVX2, Modrm|Vex|S
 vmovntp<sd>, 0x<sd:ppfx>2b, AVX, Modrm|Vex|Space0F|VexWIG|CheckOperandSize|NoSuf, { RegXMM|RegYMM, Xmmword|Ymmword|Unspecified|BaseIndex }
 vmovq, 0xf37e, AVX, Load|Modrm|Vex=1|Space0F|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 vmovq, 0x66d6, AVX, Modrm|Vex=1|Space0F|VexWIG|NoSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
-vmovq, 0x666e, AVX|x64, D|Modrm|Vex=1|Space0F|VexW=2|NoSuf, { Reg64|Unspecified|BaseIndex, RegXMM }
+vmovq, 0x666e, AVX|AVX512F|x64, D|Modrm|Vex128|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf, { Reg64|Unspecified|BaseIndex, RegXMM }
 vmovs<sd>, 0x<sd:spfx>10, AVX, D|Modrm|VexLIG|Space0F|VexWIG|NoSuf, { <sd:elem>|Unspecified|BaseIndex, RegXMM }
 vmovs<sd>, 0x<sd:spfx>10, AVX, D|Modrm|VexLIG|Space0F|VexVVVV|VexWIG|NoSuf, { RegXMM, RegXMM, RegXMM }
 vmovshdup, 0xf316, AVX, Modrm|Vex|Space0F|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM }
@@ -1599,8 +1601,10 @@  vpcmpgtq, 0x6637, AVX|AVX2, Modrm|Vex|Sp
 vpcmpistri, 0x6663, AVX, Modrm|Vex|Space0F3A|VexWIG|NoSuf, { Imm8, Unspecified|BaseIndex|RegXMM, RegXMM }
 vpcmpistrm, 0x6662, AVX, Modrm|Vex|Space0F3A|VexWIG|NoSuf, { Imm8, Unspecified|BaseIndex|RegXMM, RegXMM }
 vperm2f128, 0x6606, AVX, Modrm|Vex256|Space0F3A|VexVVVV|VexW0|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
-vpermilp<sd>, 0x660c | <sd:opc>, AVX, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpermilp<sd>, 0x6604 | <sd:opc>, AVX, Modrm|Vex|Space0F3A|VexW0|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM }
+vpermilps, 0x660c, AVX|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpermilps, 0x6604, AVX|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F3A|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
+vpermilpd, 0x660d, AVX, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
+vpermilpd, 0x6605, AVX, Modrm|Vex|Space0F3A|VexW0|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM }
 vpextr<dq>, 0x6616, AVX|<dq:cpu64>, Modrm|Vex|Space0F3A|<dq:vexw64>|NoSuf, { Imm8, RegXMM, <dq:gpr>|Unspecified|BaseIndex }
 vpextrw, 0x66c5, AVX, Load|Modrm|Vex|Space0F|VexWIG|No_bSuf|No_wSuf|No_sSuf, { Imm8, RegXMM, Reg32|Reg64 }
 vpextr<bw>, 0x6614 | <bw:opc>, AVX, RegMem|Vex|Space0F3A|VexWIG|NoSuf, { Imm8, RegXMM, Reg32|Reg64 }
@@ -1632,18 +1636,18 @@  vpminub, 0x66da, AVX|AVX2, Modrm|C|Vex|S
 vpminud, 0x663b, AVX|AVX2, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vpminuw, 0x663a, AVX|AVX2, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vpmovmskb, 0x66d7, AVX|AVX2, Modrm|Vex|Space0F|VexWIG|No_bSuf|No_wSuf|No_sSuf, { RegXMM|RegYMM, Reg32|Reg64 }
-vpmovsxbd, 0x6621, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovsxbq, 0x6622, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
+vpmovsxbd, 0x6621, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vpmovsxbq, 0x6622, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=1|NoSuf, { RegXMM|Word|Unspecified|BaseIndex, RegXMM }
 vpmovsxbw, 0x6620, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 vpmovsxdq, 0x6625, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovsxwd, 0x6623, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovsxwq, 0x6624, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovzxbd, 0x6631, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovzxbq, 0x6632, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
+vpmovsxwd, 0x6623, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vpmovsxwq, 0x6624, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vpmovzxbd, 0x6631, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vpmovzxbq, 0x6632, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=1|NoSuf, { RegXMM|Word|Unspecified|BaseIndex, RegXMM }
 vpmovzxbw, 0x6630, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 vpmovzxdq, 0x6635, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovzxwd, 0x6633, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-vpmovzxwq, 0x6634, AVX, Modrm|Vex|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
+vpmovzxwd, 0x6633, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vpmovzxwq, 0x6634, AVX|AVX512F|AVX512VL, Modrm|Vex128|EVex128|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
 vpmuldq, 0x6628, AVX|AVX2, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vpmulhrsw, 0x660b, AVX|AVX2, Modrm|Vex|Space0F38|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vpmulhuw, 0x66e4, AVX|AVX2, Modrm|C|Vex|Space0F|VexVVVV|VexWIG|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
@@ -1710,39 +1714,40 @@  vzeroupper, 0x77, AVX, Vex|Space0F|VexWI
 
 // 256bit integer AVX2 instructions.
 
-vpmovsxbd, 0x6621, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovsxbq, 0x6622, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegYMM }
+vpmovsxbd, 0x6621, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
+vpmovsxbq, 0x6622, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
 vpmovsxbw, 0x6620, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
 vpmovsxdq, 0x6625, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovsxwd, 0x6623, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovsxwq, 0x6624, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovzxbd, 0x6631, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovzxbq, 0x6632, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegYMM }
+vpmovsxwd, 0x6623, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
+vpmovsxwq, 0x6624, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
+vpmovzxbd, 0x6631, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
+vpmovzxbq, 0x6632, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
 vpmovzxbw, 0x6630, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
 vpmovzxdq, 0x6635, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovzxwd, 0x6633, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Unspecified|BaseIndex|RegXMM, RegYMM }
-vpmovzxwq, 0x6634, AVX2, Modrm|Vex=2|Space0F38|VexWIG|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegYMM }
+vpmovzxwd, 0x6633, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
+vpmovzxwq, 0x6634, AVX2|AVX512F|AVX512VL, Modrm|Vex256|EVex256|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
 
 // New AVX2 instructions.
 
 vbroadcasti128, 0x665A, AVX2, Modrm|Vex=2|Space0F38|VexW=1|NoSuf, { Xmmword|Unspecified|BaseIndex, RegYMM }
 vbroadcastsd, 0x6619, AVX2, Modrm|Vex=2|Space0F38|VexW=1|NoSuf, { RegXMM, RegYMM }
-vbroadcastss, 0x6618, AVX2, Modrm|Vex|Space0F38|VexW=1|NoSuf, { RegXMM, RegXMM|RegYMM }
+vbroadcastss, 0x6618, AVX2|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexW0|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
 vpblendd, 0x6602, AVX2, Modrm|Vex|Space0F3A|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vpbroadcast<bw>, 0x6678 | <bw:opc>, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf, { <bw:elem>|Unspecified|BaseIndex|RegXMM, RegXMM|RegYMM }
-vpbroadcast<dq>, 0x6658 | <dq:opc>, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf|Optimize, { <dq:elem>|Unspecified|BaseIndex|RegXMM, RegXMM|RegYMM }
+vpbroadcastd, 0x6658, AVX2|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexW0|Disp8MemShift|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
+vpbroadcastq, 0x6659, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf|Optimize, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM }
 vperm2i128, 0x6646, AVX2, Modrm|Vex=2|Space0F3A|VexVVVV|VexW0|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
-vpermd, 0x6636, AVX2, Modrm|Vex256|Space0F38|VexVVVV|VexW0|NoSuf, { Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
-vpermpd, 0x6601, AVX2, Modrm|Vex=2|Space0F3A|VexW1|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM }
-vpermps, 0x6616, AVX2, Modrm|Vex256|Space0F38|VexVVVV|VexW0|NoSuf, { Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
-vpermq, 0x6600, AVX2, Modrm|Vex=2|Space0F3A|VexW1|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM }
+vpermd, 0x6636, AVX2|AVX512F, Modrm|Vex256|EVexDYN|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
+vpermpd, 0x6601, AVX2|AVX512F, Modrm|Vex256|EVexDYN|Masking|Space0F3A|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM }
+vpermps, 0x6616, AVX2|AVX512F, Modrm|Vex256|EVexDYN|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
+vpermq, 0x6600, AVX2|AVX512F, Modrm|Vex256|EVexDYN|Masking|Space0F3A|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM }
 vextracti128, 0x6639, AVX2, Modrm|Vex=2|Space0F3A|VexW=1|NoSuf, { Imm8, RegYMM, Unspecified|BaseIndex|RegXMM }
 vinserti128, 0x6638, AVX2, Modrm|Vex256|Space0F3A|VexVVVV|VexW0|NoSuf, { Imm8, Unspecified|BaseIndex|RegXMM, RegYMM, RegYMM }
 vpmaskmov<dq>, 0x668e, AVX2, Modrm|Vex|Space0F38|VexVVVV|<dq:vexw>|CheckOperandSize|NoSuf, { RegXMM|RegYMM, RegXMM|RegYMM, Xmmword|Ymmword|Unspecified|BaseIndex }
 vpmaskmov<dq>, 0x668c, AVX2, Modrm|Vex|Space0F38|VexVVVV|<dq:vexw>|CheckOperandSize|NoSuf, { Xmmword|Ymmword|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
-vpsllv<dq>, 0x6647, AVX2, Modrm|Vex|Space0F38|VexVVVV|<dq:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpsravd, 0x6646, AVX2, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vpsrlv<dq>, 0x6645, AVX2, Modrm|Vex|Space0F38|VexVVVV|<dq:vexw>|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
+vpsllv<dq>, 0x6647, AVX2|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpsravd, 0x6646, AVX2|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpsrlv<dq>, 0x6645, AVX2|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 
 // AVX gather instructions
 vgatherdpd, 0x6692, AVX2, Modrm|Vex|Space0F38|VexVVVV|VexW1|SwapSources|CheckOperandSize|NoSuf|VecSIB128, { RegXMM|RegYMM, Qword|Unspecified|BaseIndex, RegXMM|RegYMM }
@@ -1779,7 +1784,7 @@  vpclmulhqhqdq, 0x6644/0x11, AVX|PCLMULQD
 
 vgf2p8affineinvqb, 0x66cf, AVX|GFNI, Modrm|Vex|Space0F3A|VexVVVV|VexW1|CheckOperandSize|NoSuf, { Imm8, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
 vgf2p8affineqb, 0x66ce, AVX|GFNI, Modrm|Vex|Space0F3A|VexVVVV|VexW1|CheckOperandSize|NoSuf, { Imm8, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
-vgf2p8mulb, 0x66cf, AVX|GFNI, Modrm|Vex|Space0F38|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
+vgf2p8mulb, 0x66cf, GFNI|AVX|AVX512F, Modrm|Vex|EVexDYN|Masking|Space0F38|VexVVVV|VexW0|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 
 // FSGSBASE, RDRND and F16C
 
@@ -2082,8 +2087,6 @@  vpclmulhqhqdq, 0x6644/0x11, VPCLMULQDQ,
 
 // AVX512F instructions.
 
-#define Disp8ShiftVL Disp8MemShift=DISP8_SHIFT_VL
-
 <sdh:cpu:cpudq:ppfx:spfx:pfx:spc1:spc2:opc:vexw:elem, +
     s:AVX512F:AVX512DQ::f3:66:Space0F:Space0F38:0:VexW0:Dword, +
     d:AVX512F:AVX512DQ:66:f2:66:Space0F:Space0F38:1:VexW1:Qword, +
@@ -2142,9 +2145,7 @@  vpmuldq, 0x6628, AVX512F, Modrm|Masking|
 vpmulld, 0x6640, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW=1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vprolv<dq>, 0x6615, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vprorv<dq>, 0x6614, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpsllv<dq>, 0x6647, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpsrav<dq>, 0x6646, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vpsrlv<dq>, 0x6645, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpsravq, 0x6646, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vpternlog<dq>, 0x6625, AVX512F, Modrm|Masking|Space0F3A|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 
 vbroadcastf32x4, 0x661A, AVX512F, Modrm|Masking|Space0F38|VexW=1|Disp8MemShift=4|NoSuf, { XMMword|Unspecified|BaseIndex, RegYMM|RegZMM }
@@ -2153,10 +2154,9 @@  vbroadcasti32x4, 0x665A, AVX512F, Modrm|
 vbroadcastf64x4, 0x661B, AVX512F, Modrm|EVex=1|Masking|Space0F38|VexW=2|Disp8MemShift=5|NoSuf, { YMMword|Unspecified|BaseIndex, RegZMM }
 vbroadcasti64x4, 0x665B, AVX512F, Modrm|EVex=1|Masking|Space0F38|VexW=2|Disp8MemShift=5|NoSuf, { YMMword|Unspecified|BaseIndex, RegZMM }
 
-vbroadcastss, 0x6618, AVX512F, Modrm|Masking|Space0F38|VexW0|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
 vbroadcastsd, 0x6619, AVX512F, Modrm|Masking|Space0F38|VexW1|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM }
 
-vpbroadcast<dq>, 0x6658 | <dq:opc>, AVX512F, Modrm|Masking|Space0F38|<dq:vexw>|Disp8MemShift|NoSuf, { RegXMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
+vpbroadcastq, 0x6659, AVX512F, Modrm|Masking|Space0F38|VexW1|Disp8MemShift|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
 vpbroadcast<dq>, 0x667c, AVX512F, Modrm|Masking|Space0F38|<dq:vexw64>|NoSuf, { <dq:gpr>, RegXMM|RegYMM|RegZMM }
 
 vcmp<frel>p<sd>, 0x<sd:ppfx>C2/0x<frel:imm>, AVX512F, Modrm|Masking|Space0F|VexVVVV|<sd:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|ImmExt|SAE, { RegXMM|RegYMM|RegZMM|<sd:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegMask }
@@ -2246,9 +2246,6 @@  vextracti32x4, 0x6639, AVX512F, Modrm|Ma
 vextractf64x4, 0x661B, AVX512F, Modrm|EVex=1|Masking|Space0F3A|VexW=2|Disp8MemShift=5|NoSuf, { Imm8, RegZMM, RegYMM|Unspecified|BaseIndex }
 vextracti64x4, 0x663B, AVX512F, Modrm|EVex=1|Masking|Space0F3A|VexW=2|Disp8MemShift=5|NoSuf, { Imm8, RegZMM, RegYMM|Unspecified|BaseIndex }
 
-vextractps, 0x6617, AVX512F, Modrm|EVex128|Space0F3A|VexWIG|Disp8MemShift=2|NoSuf, { Imm8, RegXMM, Reg32|Dword|Unspecified|BaseIndex }
-vextractps, 0x6617, AVX512F|x64, RegMem|EVex128|Space0F3A|VexWIG|NoSuf, { Imm8, RegXMM, Reg64 }
-
 vfixupimmp<sd>, 0x6654, AVX512F, Modrm|Masking|Space0F3A|VexVVVV|<sd:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf|SAE, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|<sd:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vfixupimms<sd>, 0x6655, AVX512F, Modrm|EVexLIG|Masking|Space0F3A|VexVVVV|<sd:vexw>|Disp8MemShift|NoSuf|SAE, { Imm8|Imm8S, RegXMM|<sd:elem>|Unspecified|BaseIndex, RegXMM, RegXMM }
 
@@ -2304,8 +2301,6 @@  vmovap<sd>, 0x<sd:ppfx>28, AVX512F, D|Mo
 vmovntp<sd>, 0x<sd:ppfx>2B, AVX512F, Modrm|Space0F|<sd:vexw>|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM, XMMword|YMMword|ZMMword|Unspecified|BaseIndex }
 vmovup<sd>, 0x<sd:ppfx>10, AVX512F, D|Modrm|Masking|Space0F|<sd:vexw>|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
 
-vmovd, 0x666E, AVX512F, D|Modrm|EVex=2|Space0F|Disp8MemShift=2|NoSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
-
 vmovddup, 0xF212, AVX512F, Modrm|Masking|Space0F|VexW=2|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Unspecified|BaseIndex, RegYMM|RegZMM }
 
 vmovdqa64, 0x666F, AVX512F, D|Modrm|Masking|Space0F|VexW=2|Disp8ShiftVL|CheckOperandSize|NoSuf|Optimize, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
@@ -2322,7 +2317,6 @@  vmovhp<sd>, 0x<sd:ppfx>17, AVX512F, Modr
 vmovlp<sd>, 0x<sd:ppfx>12, AVX512F, Modrm|EVexLIG|Space0F|VexVVVV|<sd:vexw>|Disp8MemShift=3|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM, RegXMM }
 vmovlp<sd>, 0x<sd:ppfx>13, AVX512F, Modrm|EVexLIG|Space0F|<sd:vexw>|Disp8MemShift=3|NoSuf, { RegXMM, Qword|Unspecified|BaseIndex }
 
-vmovq, 0x666E, AVX512F|x64, D|Modrm|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf, { Reg64|Unspecified|BaseIndex, RegXMM }
 vmovq, 0xF37E, AVX512F, Load|Modrm|EVex=2|Space0F|VexW1|Disp8MemShift=3|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 vmovq, 0x66D6, AVX512F, Modrm|EVex=2|Space0F|VexW1|Disp8MemShift=3|NoSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
 
@@ -2360,15 +2354,10 @@  vpcmp<irel>u<dq>, 0x661e/<irel:imm>, AVX
 vptestm<dq>, 0x6627, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegMask }
 vptestnm<dq>, 0xf327, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<dq:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<dq:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegMask }
 
-vpermd, 0x6636, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
-vpermps, 0x6616, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW0|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
-
-vpermilp<sd>, 0x6604 | <sd:opc>, AVX512F, Modrm|Masking|Space0F3A|<sd:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|<sd:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
-vpermilp<sd>, 0x660C | <sd:opc>, AVX512F, Modrm|Masking|Space0F38|VexVVVV|<sd:vexw>|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|<sd:elem>|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
+vpermilpd, 0x6605, AVX512F, Modrm|Masking|Space0F3A|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
+vpermilpd, 0x660d, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 
-vpermpd, 0x6601, AVX512F, Modrm|Masking|Space0F3A|VexW=2|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM }
 vpermpd, 0x6616, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
-vpermq, 0x6600, AVX512F, Modrm|Masking|Space0F3A|VexW=2|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8|Imm8S, RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM }
 vpermq, 0x6636, AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegYMM|RegZMM, RegYMM|RegZMM }
 
 vpmovdb, 0xF331, AVX512F, Modrm|EVex=1|Masking|Space0F38|VexW=1|Disp8MemShift=4|NoSuf, { RegZMM, RegXMM|Unspecified|BaseIndex }
@@ -2593,31 +2582,11 @@  vpmovsqw, 0xF324, AVX512F|AVX512VL, Modr
 vpmovusqw, 0xF314, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexW0|Disp8MemShift=2|NoSuf, { RegXMM, RegXMM|Dword|Unspecified|BaseIndex }
 vpmovusqw, 0xF314, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexW0|Disp8MemShift=3|NoSuf, { RegYMM, RegXMM|Qword|Unspecified|BaseIndex }
 
-vpmovsxbd, 0x6621, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
-vpmovsxbd, 0x6621, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
-vpmovzxbd, 0x6631, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
-vpmovzxbd, 0x6631, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
-
-vpmovsxbq, 0x6622, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=1|NoSuf, { RegXMM|Word|Unspecified|BaseIndex, RegXMM }
-vpmovsxbq, 0x6622, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
-vpmovzxbq, 0x6632, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=1|NoSuf, { RegXMM|Word|Unspecified|BaseIndex, RegXMM }
-vpmovzxbq, 0x6632, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegYMM }
-
 vpmovsxdq, 0x6625, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexW0|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
 vpmovsxdq, 0x6625, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexW=1|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
 vpmovzxdq, 0x6635, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexW0|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
 vpmovzxdq, 0x6635, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexW=1|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
 
-vpmovsxwd, 0x6623, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
-vpmovsxwd, 0x6623, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
-vpmovzxwd, 0x6633, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
-vpmovzxwd, 0x6633, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=4|NoSuf, { RegXMM|Unspecified|BaseIndex, RegYMM }
-
-vpmovsxwq, 0x6624, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
-vpmovsxwq, 0x6624, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
-vpmovzxwq, 0x6634, AVX512F|AVX512VL, Modrm|EVex=2|Masking|Space0F38|VexWIG|Disp8MemShift=2|NoSuf, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
-vpmovzxwq, 0x6634, AVX512F|AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexWIG|Disp8MemShift=3|NoSuf, { RegXMM|Qword|Unspecified|BaseIndex, RegYMM }
-
 // AVX512VL instructions end.
 
 // AVX512BW instructions.
@@ -2960,7 +2929,6 @@  vpshufbitqmb, 0x668f, AVX512_BITALG, Mod
 
 vgf2p8affineinvqb, 0x66cf, GFNI|AVX512F, Modrm|Masking|Space0F3A|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8, RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 vgf2p8affineqb, 0x66ce, GFNI|AVX512F, Modrm|Masking|Space0F3A|VexVVVV|VexW1|Broadcast|Disp8ShiftVL|CheckOperandSize|NoSuf, { Imm8, RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
-vgf2p8mulb, 0x66cf, GFNI|AVX512F, Modrm|Masking|Space0F38|VexVVVV|VexW0|Disp8ShiftVL|CheckOperandSize|NoSuf, { RegXMM|RegYMM|RegZMM|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
 
 // AVX512 + GFNI instructions end