[PATCH v4 3/9] Support APX GPR32 with extend evex prefix

["Cui, Lili" <lili.cui@intel.com>]

This patch adds non-ND, non-NF forms of EVEX promotion insn.

EVEX extension of legacy instructions:
  All promoted legacy instructions are placed in EVEX map 4, which is
  currently reserved.
EVEX extension of EVEX instructions:
  All existing EVEX instructions are extended by APX using the extended
  EVEX prefix, so that they can access all 32 GPRs.
EVEX extension of VEX instructions:
  Promoting a VEX instruction into the EVEX space does not change the map
  id, the opcode, or the operand encoding of the VEX instruction.

Note: The promoted versions of MOVBE will be extended to include the “MOVBE
  reg1, reg2”.

  gas/ChangeLog:

  2023-12-19  Lingling Kong <lingling.kong@intel.com>
	      H.J. Lu  <hongjiu.lu@intel.com>
	      Lili Cui <lili.cui@intel.com>
	      Lin Hu   <lin1.hu@intel.com>

	* config/tc-i386.c (APX_F): New define.
	(install_template): Handled APX combines.
	(is_apx_evex_encoding): Test apx evex encoding.
	(build_apx_evex_prefix): Enabe APX evex prefix.
	(md_assemble): Handle apx with evex encoding.
	(process_suffix): Handle apx map4 prefix.
	(check_register): Assign i.vec_encoding for APX evex instructions.
	* testsuite/gas/i386/x86-64-evex.d: Adjust test cases.
	* testsuite/gas/i386/x86-64.exp: Adjust x86-64-inval-movbe.

opcodes/ChangeLog:

	* i386-dis-evex-len.h: Handle EVEX_LEN_0F38F2, EVEX_LEN_0F38F3.
	* i386-dis-evex-prefix.h: Handle PREFIX_EVEX_0F38F2_L_0,
	PREFIX_EVEX_0F38F3_L_0, PREFIX_EVEX_MAP4_D8,
	PREFIX_EVEX_MAP4_DA, PREFIX_EVEX_MAP4_DB,
	PREFIX_EVEX_MAP4_DC, PREFIX_EVEX_MAP4_DD,
	PREFIX_EVEX_MAP4_DE, PREFIX_EVEX_MAP4_DF,
	PREFIX_EVEX_MAP4_F0, PREFIX_EVEX_MAP4_F1,
	PREFIX_EVEX_MAP4_F2, PREFIX_EVEX_MAP4_F8.
	* i386-dis-evex-reg.h: Handle REG_EVEX_0F38F3_L_0_P_0.
	* i386-dis-evex.h: Add EVEX_MAP4_ for legacy insn
	promote to apx to use gpr32
	* opcodes/i386-dis-evex-x86-64.h: Handle Add X86_64_EVEX_0F90,
	X86_64_EVEX_0F92, X86_64_EVEX_0F93, X86_64_EVEX_0F38F2,
	X86_64_EVEX_0F38F3, X86_64_EVEX_0F38F5, X86_64_EVEX_0F38F6,
	X86_64_EVEX_0F38F7, X86_64_EVEX_0F3AF0, X86_64_EVEX_0F91.
	* i386-dis.c
	(struct instr_info): Deleted bool r.
	(PREFIX_NP_OR_DATA): New.
	(NO_PREFIX): New.
	(putop): Ditto.
	(X86_64_EVEX_FROM_VEX_TABLE): Diito.
	(get_valid_dis386): Decode insn erex in extend evex prefix.
	Handle EVEX_MAP4
	(print_insn): Handle PREFIX_DATA_AND_NP_ONLY.
	(print_register): Handle apx instructions decode.
	(OP_E_memory): Diito.
	(OP_G): Diito.
	(OP_XMM): Diito.
	(DistinctDest_Fixup): Diito.
	* i386-gen.c (process_i386_opcode_modifier): Add EVEXMAP4.
	* i386-opc.h (SPACE_EVEXMAP4): Add legacy insn
	promote to evex.
	* i386-opc.tbl: Handle some legacy and vex insns don't
	support gpr32. And add some legacy insn (map2 / 3) promote
	to evex.
---
 gas/config/tc-i386.c                 |  65 ++++++++++-
 gas/testsuite/gas/i386/x86-64-evex.d |   2 +-
 gas/testsuite/gas/i386/x86-64.exp    |   2 +-
 opcodes/i386-dis-evex-len.h          |  10 ++
 opcodes/i386-dis-evex-prefix.h       |  66 +++++++++++
 opcodes/i386-dis-evex-reg.h          |   7 ++
 opcodes/i386-dis-evex-x86-64.h       |  50 ++++++++
 opcodes/i386-dis-evex.h              |  94 +++++++--------
 opcodes/i386-dis.c                   | 165 +++++++++++++++++++++++----
 opcodes/i386-gen.c                   |   2 +
 opcodes/i386-opc.h                   |   6 +
 opcodes/i386-opc.tbl                 | 109 ++++++++++++------
 12 files changed, 466 insertions(+), 112 deletions(-)
 create mode 100644 opcodes/i386-dis-evex-x86-64.h

diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index 051cdef2a3a..25cfacce138 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -89,6 +89,7 @@
 /* This matches the C -> StaticRounding alias in the opcode table.  */
 #define commutative staticrounding
 
+#define APX_F(cpuid) (maybe_cpu (t, CpuAPX_F) && maybe_cpu (t, cpuid))
 /*
   'templates' is for grouping together 'template' structures for opcodes
   of the same name.  This is only used for storing the insns in the grand
@@ -3673,7 +3674,7 @@ install_template (const insn_template *t)
 
   /* Dual VEX/EVEX templates need stripping one of the possible variants.  */
   if (t->opcode_modifier.vex && t->opcode_modifier.evex)
-  {
+    {
       if ((maybe_cpu (t, CpuAVX) || maybe_cpu (t, CpuAVX2)
 	   || maybe_cpu (t, CpuFMA))
 	  && (maybe_cpu (t, CpuAVX512F) || maybe_cpu (t, CpuAVX512VL)))
@@ -3695,7 +3696,15 @@ install_template (const insn_template *t)
 		gas_assert (i.tm.cpu.bitfield.isa == i.tm.cpu_any.bitfield.isa);
 	    }
 	}
-  }
+
+      if (APX_F(CpuCMPCCXADD) || APX_F(CpuAMX_TILE) || APX_F(CpuAVX512F)
+	  || APX_F(CpuAVX512DQ) || APX_F(CpuAVX512BW) || APX_F(CpuBMI)
+	  || APX_F(CpuBMI2))
+	if (need_evex_encoding ())
+	  i.tm.opcode_modifier.vex = 0;
+	else
+	  i.tm.opcode_modifier.evex = 0;
+    }
 
   /* Note that for pseudo prefixes this produces a length of 1. But for them
      the length isn't interesting at all.  */
@@ -3876,6 +3885,15 @@ is_any_vex_encoding (const insn_template *t)
   return t->opcode_modifier.vex || t->opcode_modifier.evex;
 }
 
+/* We can use this function only when the current encoding is evex.  */
+static INLINE bool
+is_apx_evex_encoding (void)
+{
+  return i.rex2 || i.tm.opcode_space == SPACE_EVEXMAP4
+    || (i.vex.register_specifier
+	&& i.vex.register_specifier->reg_flags & RegRex2);
+}
+
 static INLINE bool
 is_apx_rex2_encoding (void)
 {
@@ -4153,6 +4171,27 @@ build_rex2_prefix (void)
 		    | (i.rex2 << 4) | i.rex);
 }
 
+/* Build the EVEX prefix (4-byte) for evex insn
+   | 62h |
+   | `R`X`B`R' | B'mmm |
+   | W | v`v`v`v | `x' | pp |
+   | z| L'L | b | `v | aaa |
+*/
+static void
+build_apx_evex_prefix (void)
+{
+  build_evex_prefix ();
+  if (i.rex2 & REX_R)
+    i.vex.bytes[1] &= ~0x10;
+  if (i.rex2 & REX_B)
+    i.vex.bytes[1] |= 0x08;
+  if (i.rex2 & REX_X)
+    i.vex.bytes[2] &= ~0x04;
+  if (i.vex.register_specifier
+      && i.vex.register_specifier->reg_flags & RegRex2)
+    i.vex.bytes[3] &= ~0x08;
+}
+
 static void
 process_immext (void)
 {
@@ -5642,13 +5681,18 @@ md_assemble (char *line)
 	  return;
 	}
 
-      if (i.tm.opcode_modifier.vex)
+      if (is_apx_evex_encoding ())
+	build_apx_evex_prefix ();
+      else if (i.tm.opcode_modifier.vex)
 	build_vex_prefix (t);
       else
 	build_evex_prefix ();
 
       /* The individual REX.RXBW bits got consumed.  */
       i.rex &= REX_OPCODE;
+
+      /* The rex2 bits got consumed.  */
+      i.rex2 = 0;
     }
 
   /* Handle conversion of 'int $3' --> special int3 insn.  */
@@ -8087,7 +8131,8 @@ process_suffix (void)
       if (i.suffix != QWORD_MNEM_SUFFIX
 	  && i.tm.opcode_modifier.mnemonicsize != IGNORESIZE
 	  && !i.tm.opcode_modifier.floatmf
-	  && !is_any_vex_encoding (&i.tm)
+	  && (!is_any_vex_encoding (&i.tm)
+	      || i.tm.opcode_space == SPACE_EVEXMAP4)
 	  && ((i.suffix == LONG_MNEM_SUFFIX) == (flag_code == CODE_16BIT)
 	      || (flag_code == CODE_64BIT
 		  && i.tm.opcode_modifier.jump == JUMP_BYTE)))
@@ -8097,7 +8142,11 @@ process_suffix (void)
 	  if (i.tm.opcode_modifier.jump == JUMP_BYTE) /* jcxz, loop */
 	    prefix = ADDR_PREFIX_OPCODE;
 
-	  if (!add_prefix (prefix))
+	  /* The DATA PREFIX of EVEX promoted from legacy APX instructions
+	     needs to be adjusted.  */
+	  if (i.tm.opcode_space == SPACE_EVEXMAP4)
+	    i.tm.opcode_modifier.opcodeprefix = PREFIX_0X66;
+	  else if (!add_prefix (prefix))
 	    return 0;
 	}
 
@@ -14293,6 +14342,12 @@ static bool check_register (const reg_entry *r)
       if (!cpu_arch_flags.bitfield.cpuapx_f
 	  || flag_code != CODE_64BIT)
 	return false;
+
+      /* When using RegRex2, dual VEX/EVEX templates need to be marked as EVEX.
+	 For the later install_template function.  */
+      if (current_templates.start->opcode_modifier.vex
+	  && current_templates.start->opcode_modifier.evex)
+	i.vec_encoding = vex_encoding_evex;
     }
 
   if (((r->reg_flags & (RegRex64 | RegRex)) || r->reg_type.bitfield.qword)
diff --git a/gas/testsuite/gas/i386/x86-64-evex.d b/gas/testsuite/gas/i386/x86-64-evex.d
index 041747db892..5d974c312da 100644
--- a/gas/testsuite/gas/i386/x86-64-evex.d
+++ b/gas/testsuite/gas/i386/x86-64-evex.d
@@ -17,6 +17,6 @@ Disassembly of section .text:
  +[a-f0-9]+:	62 f1 d6 38 7b f0    	vcvtusi2ss %rax,\{rd-sae\},%xmm5,%xmm6
  +[a-f0-9]+:	62 f1 57 38 7b f0    	vcvtusi2sd %eax,\{rd-bad\},%xmm5,%xmm6
  +[a-f0-9]+:	62 f1 d7 38 7b f0    	vcvtusi2sd %rax,\{rd-sae\},%xmm5,%xmm6
- +[a-f0-9]+:	62 e1 7e 08 2d c0    	vcvtss2si %xmm0,\(bad\)
+ +[a-f0-9]+:	62 e1 7e 08 2d c0    	vcvtss2si %xmm0,%r16d
  +[a-f0-9]+:	62 e1 7c 08 c2 c0 00 	vcmpeqps %xmm0,%xmm0,\(bad\)
 #pass
diff --git a/gas/testsuite/gas/i386/x86-64.exp b/gas/testsuite/gas/i386/x86-64.exp
index 2be0df0e981..7a1fef58735 100644
--- a/gas/testsuite/gas/i386/x86-64.exp
+++ b/gas/testsuite/gas/i386/x86-64.exp
@@ -250,7 +250,7 @@ run_dump_test "x86-64-sse-noavx"
 run_dump_test "x86-64-movbe"
 run_dump_test "x86-64-movbe-intel"
 run_dump_test "x86-64-movbe-suffix"
-run_list_test "x86-64-inval-movbe" "-al"
+run_list_test "x86-64-inval-movbe" "-march=+noapx_f -al"
 run_dump_test "x86-64-ept"
 run_dump_test "x86-64-ept-intel"
 run_list_test "x86-64-inval-ept" "-al"
diff --git a/opcodes/i386-dis-evex-len.h b/opcodes/i386-dis-evex-len.h
index a02609c50f2..ad59a559e0d 100644
--- a/opcodes/i386-dis-evex-len.h
+++ b/opcodes/i386-dis-evex-len.h
@@ -62,6 +62,16 @@ static const struct dis386 evex_len_table[][3] = {
     { REG_TABLE (REG_EVEX_0F38C7_L_2) },
   },
 
+  /* EVEX_LEN_0F38F2 */
+  {
+    { PREFIX_TABLE (PREFIX_EVEX_0F38F2_L_0) },
+  },
+
+  /* EVEX_LEN_0F38F3 */
+  {
+    { PREFIX_TABLE (PREFIX_EVEX_0F38F3_L_0) },
+  },
+
   /* EVEX_LEN_0F3A00 */
   {
     { Bad_Opcode },
diff --git a/opcodes/i386-dis-evex-prefix.h b/opcodes/i386-dis-evex-prefix.h
index 28da54922c7..b11b7adb443 100644
--- a/opcodes/i386-dis-evex-prefix.h
+++ b/opcodes/i386-dis-evex-prefix.h
@@ -285,6 +285,14 @@
     { "%XEvfmsub213s%XW",	{ XMScalar, VexScalar, EXdq, EXxEVexR }, 0 },
     { "v4fnmadds%XS",	{ XMScalar, VexScalar, Mxmm }, 0 },
   },
+  /* PREFIX_EVEX_0F38F2_L_0 */
+  {
+    { "andnS",	{ Gdq, VexGdq, Edq }, 0 },
+  },
+  /* PREFIX_EVEX_0F38F3_L_0 */
+  {
+    { REG_TABLE (REG_EVEX_0F38F3_L_0_P_0) },
+  },
   /* PREFIX_EVEX_0F3A08 */
   {
     { "vrndscalep%XH",  { XM, EXxh, EXxEVexS, Ib }, 0 },
@@ -338,6 +346,64 @@
     { "vcmpp%XH", { MaskG, Vex, EXxh, EXxEVexS, CMP }, 0 },
     { "vcmps%XH", { MaskG, VexScalar, EXw, EXxEVexS, CMP }, 0 },
   },
+  /* PREFIX_EVEX_MAP4_D8 */
+  {
+    { "sha1nexte", { XM, EXxmm }, 0 },
+    { REG_TABLE (REG_0F38D8_PREFIX_1) },
+  },
+  /* PREFIX_EVEX_MAP4_DA */
+  {
+    { "sha1msg2", { XM, EXxmm }, 0 },
+    { "encodekey128", { Gd, Rd }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_DB */
+  {
+    { "sha256rnds2", { XM, EXxmm, XMM0 }, 0 },
+    { "encodekey256", { Gd, Rd }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_DC */
+  {
+    { "sha256msg1", { XM, EXxmm }, 0 },
+    { "aesenc128kl", { XM, M }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_DD */
+  {
+    { "sha256msg2", { XM, EXxmm }, 0 },
+    { "aesdec128kl", { XM, M }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_DE */
+  {
+    { Bad_Opcode },
+    { "aesenc256kl", { XM, M }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_DF */
+  {
+    { Bad_Opcode },
+    { "aesdec256kl", { XM, M }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_F0 */
+  {
+    { "crc32A", { Gdq, Eb }, 0 },
+    { "invept", { Gm, Mo }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_F1 */
+  {
+    { "crc32Q", { Gdq, Ev }, 0 },
+    { "invvpid", { Gm, Mo }, 0 },
+    { "crc32Q", { Gdq, Ev }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_F2 */
+  {
+    { Bad_Opcode },
+    { "invpcid", { Gm, M }, 0 },
+  },
+  /* PREFIX_EVEX_MAP4_F8 */
+  {
+    { Bad_Opcode },
+    { "enqcmds", { Gva, M },  0 },
+    { "movdir64b", { Gva, M }, 0 },
+    { "enqcmd", { Gva, M }, 0 },
+  },
   /* PREFIX_EVEX_MAP5_10 */
   {
     { Bad_Opcode },
diff --git a/opcodes/i386-dis-evex-reg.h b/opcodes/i386-dis-evex-reg.h
index 2885063628b..8374f0ea93a 100644
--- a/opcodes/i386-dis-evex-reg.h
+++ b/opcodes/i386-dis-evex-reg.h
@@ -49,3 +49,10 @@
     { "vscatterpf0qp%XW",  { MVexVSIBQWpX }, PREFIX_DATA },
     { "vscatterpf1qp%XW",  { MVexVSIBQWpX }, PREFIX_DATA },
   },
+  /* REG_EVEX_0F38F3_L_0_P_0 */
+  {
+    { Bad_Opcode },
+    { "blsrS",	{ VexGdq, Edq }, 0 },
+    { "blsmskS",	{ VexGdq, Edq }, 0 },
+    { "blsiS",	{ VexGdq, Edq }, 0 },
+  },
diff --git a/opcodes/i386-dis-evex-x86-64.h b/opcodes/i386-dis-evex-x86-64.h
new file mode 100644
index 00000000000..0d9d98a7691
--- /dev/null
+++ b/opcodes/i386-dis-evex-x86-64.h
@@ -0,0 +1,50 @@
+  /* X86_64_EVEX_0F90 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (VEX_W_0F90_L_0) },
+  },
+  /* X86_64_EVEX_0F91 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (VEX_W_0F91_L_0) },
+  },
+  /* X86_64_EVEX_0F92 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (VEX_W_0F92_L_0) },
+  },
+  /* X86_64_EVEX_0F93 */
+  {
+    { Bad_Opcode },
+    { VEX_W_TABLE (VEX_W_0F93_L_0) },
+  },
+  /* X86_64_EVEX_0F38F2 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_VEX_0F38F2_L_0) },
+  },
+  /* X86_64_EVEX_0F38F3 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_VEX_0F38F3_L_0) },
+  },
+  /* X86_64_EVEX_0F38F5 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_VEX_0F38F5_L_0) },
+  },
+  /* X86_64_EVEX_0F38F6 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE(PREFIX_VEX_0F38F6_L_0) },
+  },
+  /* X86_64_EVEX_0F38F7 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE(PREFIX_VEX_0F38F7_L_0) },
+  },
+  /* X86_64_EVEX_0F3AF0 */
+  {
+    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_VEX_0F3AF0_L_0) },
+  },
diff --git a/opcodes/i386-dis-evex.h b/opcodes/i386-dis-evex.h
index 7ad1edbe72d..90c063b2188 100644
--- a/opcodes/i386-dis-evex.h
+++ b/opcodes/i386-dis-evex.h
@@ -164,10 +164,10 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     /* 90 */
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F90) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F91) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F92) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F93) },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
@@ -375,9 +375,9 @@ static const struct dis386 evex_table[][256] = {
     { "vpsllv%DQ",	{ XM, Vex, EXx }, PREFIX_DATA },
     /* 48 */
     { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F3849) },
     { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F384B) },
     { "vrcp14p%XW",	{ XM, EXx }, PREFIX_DATA },
     { "vrcp14s%XW",	{ XMScalar, VexScalar, EXdq }, PREFIX_DATA },
     { "vrsqrt14p%XW",	{ XM, EXx }, 0 },
@@ -545,32 +545,32 @@ static const struct dis386 evex_table[][256] = {
     { "%XEvaesdecY",	{ XM, Vex, EXx }, PREFIX_DATA },
     { "%XEvaesdeclastY", { XM, Vex, EXx }, PREFIX_DATA },
     /* E0 */
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E0) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E1) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E2) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E3) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E4) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E5) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E6) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E7) },
     /* E8 */
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E8) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38E9) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38EA) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38EB) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38EC) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38ED) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38EE) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_VEX_0F38EF) },
     /* F0 */
     { Bad_Opcode },
     { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F38F2) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F38F3) },
     { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F38F5) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F38F6) },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F38F7) },
     /* F8 */
     { Bad_Opcode },
     { Bad_Opcode },
@@ -854,7 +854,7 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     /* F0 */
-    { Bad_Opcode },
+    { X86_64_EVEX_FROM_VEX_TABLE (X86_64_EVEX_0F3AF0) },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
@@ -983,13 +983,13 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     /* 60 */
+    { "movbeS",	{ Gv, Ev }, PREFIX_NP_OR_DATA },
+    { "movbeS",	{ Ev, Gv }, PREFIX_NP_OR_DATA },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { "wrussK",	{ M, Gdq }, PREFIX_DATA },
+    { PREFIX_TABLE (PREFIX_0F38F6) },
     { Bad_Opcode },
     /* 68 */
     { Bad_Opcode },
@@ -1113,19 +1113,19 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
-    { Bad_Opcode },
+    { "sha1rnds4",	{ XM, EXxmm, Ib }, NO_PREFIX },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
     /* D8 */
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_D8) },
+    { "sha1msg1",	{ XM, EXxmm }, NO_PREFIX },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DA) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DB) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DC) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DD) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DE) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_DF) },
     /* E0 */
     { Bad_Opcode },
     { Bad_Opcode },
@@ -1145,20 +1145,20 @@ static const struct dis386 evex_table[][256] = {
     { Bad_Opcode },
     { Bad_Opcode },
     /* F0 */
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_F0) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_F1) },
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_F2) },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
     /* F8 */
+    { PREFIX_TABLE (PREFIX_EVEX_MAP4_F8) },
+    { "movdiri",	{ Mdq, Gdq }, NO_PREFIX },
     { Bad_Opcode },
     { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
-    { Bad_Opcode },
+    { PREFIX_TABLE (PREFIX_0F38FC) },
     { Bad_Opcode },
     { Bad_Opcode },
     { Bad_Opcode },
diff --git a/opcodes/i386-dis.c b/opcodes/i386-dis.c
index 20fe7070b35..5b6f063d016 100644
--- a/opcodes/i386-dis.c
+++ b/opcodes/i386-dis.c
@@ -132,6 +132,13 @@ enum x86_64_isa
   intel64
 };
 
+enum evex_type
+{
+  evex_default = 0,
+  evex_from_legacy,
+  evex_from_vex,
+};
+
 struct instr_info
 {
   enum address_mode address_mode;
@@ -212,7 +219,6 @@ struct instr_info
     int ll;
     bool w;
     bool evex;
-    bool r;
     bool v;
     bool zeroing;
     bool b;
@@ -220,6 +226,8 @@ struct instr_info
   }
   vex;
 
+  enum evex_type evex_type;
+
   /* Remember if the current op is a jump instruction.  */
   bool op_is_jump;
 
@@ -305,6 +313,8 @@ struct dis_private {
 #define PREFIX_ADDR 0x400
 #define PREFIX_FWAIT 0x800
 #define PREFIX_REX2 0x1000
+#define PREFIX_NP_OR_DATA 0x2000
+#define NO_PREFIX   0x4000
 
 /* Make sure that bytes from INFO->PRIVATE_DATA->BUFFER (inclusive)
    to ADDR (exclusive) are valid.  Returns true for success, false
@@ -802,6 +812,7 @@ enum
   USE_RM_TABLE,
   USE_PREFIX_TABLE,
   USE_X86_64_TABLE,
+  USE_X86_64_EVEX_FROM_VEX_TABLE,
   USE_3BYTE_TABLE,
   USE_XOP_8F_TABLE,
   USE_VEX_C4_TABLE,
@@ -820,6 +831,8 @@ enum
 #define RM_TABLE(I)		DIS386 (USE_RM_TABLE, (I))
 #define PREFIX_TABLE(I)		DIS386 (USE_PREFIX_TABLE, (I))
 #define X86_64_TABLE(I)		DIS386 (USE_X86_64_TABLE, (I))
+#define X86_64_EVEX_FROM_VEX_TABLE(I) \
+  DIS386 (USE_X86_64_EVEX_FROM_VEX_TABLE, (I))
 #define THREE_BYTE_TABLE(I)	DIS386 (USE_3BYTE_TABLE, (I))
 #define XOP_8F_TABLE()		DIS386 (USE_XOP_8F_TABLE, 0)
 #define VEX_C4_TABLE()		DIS386 (USE_VEX_C4_TABLE, 0)
@@ -868,7 +881,7 @@ enum
   REG_VEX_0F73,
   REG_VEX_0FAE,
   REG_VEX_0F3849_X86_64_L_0_W_0_M_1_P_0,
-  REG_VEX_0F38F3_L_0,
+  REG_VEX_0F38F3_L_0_P_0,
   REG_VEX_MAP7_F8_L_0_W_0,
 
   REG_XOP_09_01_L_0,
@@ -880,7 +893,8 @@ enum
   REG_EVEX_0F72,
   REG_EVEX_0F73,
   REG_EVEX_0F38C6_L_2,
-  REG_EVEX_0F38C7_L_2
+  REG_EVEX_0F38C7_L_2,
+  REG_EVEX_0F38F3_L_0_P_0,
 };
 
 enum
@@ -1096,6 +1110,8 @@ enum
   PREFIX_VEX_0F38CC,
   PREFIX_VEX_0F38CD,
   PREFIX_VEX_0F38DA_W_0,
+  PREFIX_VEX_0F38F2_L_0,
+  PREFIX_VEX_0F38F3_L_0,
   PREFIX_VEX_0F38F5_L_0,
   PREFIX_VEX_0F38F6_L_0,
   PREFIX_VEX_0F38F7_L_0,
@@ -1147,6 +1163,8 @@ enum
   PREFIX_EVEX_0F389B,
   PREFIX_EVEX_0F38AA,
   PREFIX_EVEX_0F38AB,
+  PREFIX_EVEX_0F38F2_L_0,
+  PREFIX_EVEX_0F38F3_L_0,
 
   PREFIX_EVEX_0F3A08,
   PREFIX_EVEX_0F3A0A,
@@ -1158,6 +1176,18 @@ enum
   PREFIX_EVEX_0F3A67,
   PREFIX_EVEX_0F3AC2,
 
+  PREFIX_EVEX_MAP4_D8,
+  PREFIX_EVEX_MAP4_DA,
+  PREFIX_EVEX_MAP4_DB,
+  PREFIX_EVEX_MAP4_DC,
+  PREFIX_EVEX_MAP4_DD,
+  PREFIX_EVEX_MAP4_DE,
+  PREFIX_EVEX_MAP4_DF,
+  PREFIX_EVEX_MAP4_F0,
+  PREFIX_EVEX_MAP4_F1,
+  PREFIX_EVEX_MAP4_F2,
+  PREFIX_EVEX_MAP4_F8,
+
   PREFIX_EVEX_MAP5_10,
   PREFIX_EVEX_MAP5_11,
   PREFIX_EVEX_MAP5_1D,
@@ -1269,7 +1299,19 @@ enum
   X86_64_VEX_0F38ED,
   X86_64_VEX_0F38EE,
   X86_64_VEX_0F38EF,
+
   X86_64_VEX_MAP7_F8_L_0_W_0_R_0,
+
+  X86_64_EVEX_0F90,
+  X86_64_EVEX_0F91,
+  X86_64_EVEX_0F92,
+  X86_64_EVEX_0F93,
+  X86_64_EVEX_0F38F2,
+  X86_64_EVEX_0F38F3,
+  X86_64_EVEX_0F38F5,
+  X86_64_EVEX_0F38F6,
+  X86_64_EVEX_0F38F7,
+  X86_64_EVEX_0F3AF0,
 };
 
 enum
@@ -1454,6 +1496,8 @@ enum
   EVEX_LEN_0F385B,
   EVEX_LEN_0F38C6,
   EVEX_LEN_0F38C7,
+  EVEX_LEN_0F38F2,
+  EVEX_LEN_0F38F3,
   EVEX_LEN_0F3A00,
   EVEX_LEN_0F3A01,
   EVEX_LEN_0F3A18,
@@ -2884,12 +2928,12 @@ static const struct dis386 reg_table[][8] = {
   {
     { RM_TABLE (RM_VEX_0F3849_X86_64_L_0_W_0_M_1_P_0_R_0) },
   },
-  /* REG_VEX_0F38F3_L_0 */
+  /* REG_VEX_0F38F3_L_0_P_0 */
   {
     { Bad_Opcode },
-    { "blsrS",		{ VexGdq, Edq }, PREFIX_OPCODE },
-    { "blsmskS",	{ VexGdq, Edq }, PREFIX_OPCODE },
-    { "blsiS",		{ VexGdq, Edq }, PREFIX_OPCODE },
+    { "blsrS",		{ VexGdq, Edq }, 0 },
+    { "blsmskS",	{ VexGdq, Edq }, 0 },
+    { "blsiS",		{ VexGdq, Edq }, 0 },
   },
   /* REG_VEX_MAP7_F8_L_0_W_0 */
   {
@@ -4037,6 +4081,16 @@ static const struct dis386 prefix_table[][4] = {
     { "vsm4rnds4", { XM, Vex, EXx }, 0 },
   },
 
+  /* PREFIX_VEX_0F38F2_L_0 */
+  {
+    { "andnS",          { Gdq, VexGdq, Edq }, 0 },
+  },
+
+  /* PREFIX_VEX_0F38F3_L_0 */
+  {
+    { REG_TABLE (REG_VEX_0F38F3_L_0_P_0) },
+  },
+
   /* PREFIX_VEX_0F38F5_L_0 */
   {
     { "bzhiS",		{ Gdq, Edq, VexGdq }, 0 },
@@ -4529,6 +4583,7 @@ static const struct dis386 x86_64_table[][2] = {
     { PREFIX_TABLE (PREFIX_VEX_MAP7_F8_L_0_W_0_R_0_X86_64) },
   },
 
+#include "i386-dis-evex-x86-64.h"
 };
 
 static const struct dis386 three_byte_table[][256] = {
@@ -7115,12 +7170,12 @@ static const struct dis386 vex_len_table[][2] = {
 
   /* VEX_LEN_0F38F2 */
   {
-    { "andnS",		{ Gdq, VexGdq, Edq }, PREFIX_OPCODE },
+    { PREFIX_TABLE (PREFIX_VEX_0F38F2_L_0) },
   },
 
   /* VEX_LEN_0F38F3 */
   {
-    { REG_TABLE(REG_VEX_0F38F3_L_0) },
+    { PREFIX_TABLE (PREFIX_VEX_0F38F3_L_0) },
   },
 
   /* VEX_LEN_0F38F5 */
@@ -8734,6 +8789,17 @@ get_valid_dis386 (const struct dis386 *dp, instr_info *ins)
       dp = &prefix_table[dp->op[1].bytemode][vindex];
       break;
 
+    case USE_X86_64_EVEX_FROM_VEX_TABLE:
+      ins->evex_type = evex_from_vex;
+      /* EVEX from VEX instrucions require that EVEX.z, EVEX.L’L, EVEX.b and
+	 the lower 2 bits of EVEX.aaa must be 0.  */
+      if ((ins->vex.mask_register_specifier & 0x3) != 0
+	  || ins->vex.ll != 0
+	  || ins->vex.zeroing != 0
+	  || ins->vex.b)
+	return &bad_opcode;
+
+      /* Fall through.  */
     case USE_X86_64_TABLE:
       vindex = ins->address_mode == mode_64bit ? 1 : 0;
       dp = &x86_64_table[dp->op[1].bytemode][vindex];
@@ -8979,9 +9045,13 @@ get_valid_dis386 (const struct dis386 *dp, instr_info *ins)
       if (!fetch_code (ins->info, ins->codep + 4))
 	return &err_opcode;
       /* The first byte after 0x62.  */
+      if (*ins->codep & 0x8)
+	ins->rex2 |= REX_B;
+      if (!(*ins->codep & 0x10))
+	ins->rex2 |= REX_R;
+
       ins->rex = ~(*ins->codep >> 5) & 0x7;
-      ins->vex.r = *ins->codep & 0x10;
-      switch ((*ins->codep & 0xf))
+      switch (*ins->codep & 0x7)
 	{
 	default:
 	  return &bad_opcode;
@@ -8994,6 +9064,12 @@ get_valid_dis386 (const struct dis386 *dp, instr_info *ins)
 	case 0x3:
 	  vex_table_index = EVEX_0F3A;
 	  break;
+	case 0x4:
+	  vex_table_index = EVEX_MAP4;
+	  ins->evex_type = evex_from_legacy;
+	  if (ins->address_mode != mode_64bit)
+	    return &bad_opcode;
+	  break;
 	case 0x5:
 	  vex_table_index = EVEX_MAP5;
 	  break;
@@ -9010,9 +9086,8 @@ get_valid_dis386 (const struct dis386 *dp, instr_info *ins)
 
       ins->vex.register_specifier = (~(*ins->codep >> 3)) & 0xf;
 
-      /* The U bit.  */
       if (!(*ins->codep & 0x4))
-	return &bad_opcode;
+	ins->rex2 |= REX_X;
 
       switch ((*ins->codep & 0x3))
 	{
@@ -9042,12 +9117,26 @@ get_valid_dis386 (const struct dis386 *dp, instr_info *ins)
 
       if (ins->address_mode != mode_64bit)
 	{
+	  /* Report bad for !evex_default and when two fixed values of evex
+	     change..  */
+	  if (ins->evex_type != evex_default
+	      || (ins->rex2 & (REX_B | REX_X)))
+	    return &bad_opcode;
 	  /* In 16/32-bit mode silently ignore following bits.  */
 	  ins->rex &= ~REX_B;
-	  ins->vex.r = true;
+	  ins->rex2 &= ~REX_R;
 	}
 
       ins->need_vex = 4;
+
+      /* EVEX from legacy instructions require that EVEX.z, EVEX.L’L and the
+	 lower 2 bits of EVEX.aaa must be 0.  */
+      if (ins->evex_type == evex_from_legacy
+	  && ((ins->vex.mask_register_specifier & 0x3) != 0
+	      || ins->vex.ll != 0
+	      || ins->vex.zeroing != 0))
+	return &bad_opcode;
+
       ins->codep++;
       vindex = *ins->codep++;
       dp = &evex_table[vex_table_index][vindex];
@@ -9462,6 +9551,13 @@ print_insn (bfd_vma pc, disassemble_info *info, int intel_syntax)
       dp = get_valid_dis386 (dp, &ins);
       if (dp == &err_opcode)
 	goto fetch_error_out;
+
+      /* For APX instructions promoted from legacy maps 0/1, embedded prefix
+	 is interpreted as the operand size override.  */
+      if (ins.evex_type == evex_from_legacy
+	  && ins.vex.prefix == DATA_PREFIX_OPCODE)
+	sizeflag ^= DFLAG;
+
       if (dp != NULL && putop (&ins, dp->name, sizeflag) == 0)
 	{
 	  if (!get_sib (&ins, sizeflag))
@@ -9641,6 +9737,25 @@ print_insn (bfd_vma pc, disassemble_info *info, int intel_syntax)
       if (ins.last_repnz_prefix >= 0)
 	ins.all_prefixes[ins.last_repnz_prefix] = 0xf2;
       break;
+
+    case PREFIX_NP_OR_DATA:
+      if (ins.vex.prefix == REPE_PREFIX_OPCODE
+	  || ins.vex.prefix == REPNE_PREFIX_OPCODE)
+	{
+	  i386_dis_printf (info, dis_style_text, "(bad)");
+	  ret = ins.end_codep - priv.the_buffer;
+	  goto out;
+	}
+      break;
+
+    case NO_PREFIX:
+      if (ins.vex.prefix)
+	{
+	  i386_dis_printf (info, dis_style_text, "(bad)");
+	  ret = ins.end_codep - priv.the_buffer;
+	  goto out;
+	}
+      break;
     }
 
   /* Check if the REX prefix is used.  */
@@ -10350,7 +10465,7 @@ putop (instr_info *ins, const char *in_template, int sizeflag)
 		{
 		case 'X':
 		  if (!ins->vex.evex || ins->vex.b || ins->vex.ll >= 2
-		      || !ins->vex.r
+		      || (ins->rex2 & REX_R)
 		      || (ins->modrm.mod == 3 && (ins->rex & REX_X))
 		      || !ins->vex.v || ins->vex.mask_register_specifier)
 		    break;
@@ -11461,7 +11576,7 @@ OP_E_memory (instr_info *ins, int bytemode, int sizeflag)
 
   add += (ins->rex2 & REX_B) ? 16 : 0;
 
-  if (ins->vex.evex)
+  if (ins->vex.evex && ins->evex_type == evex_default)
     {
 
       /* Zeroing-masking is invalid for memory destinations. Set the flag
@@ -11605,6 +11720,13 @@ OP_E_memory (instr_info *ins, int bytemode, int sizeflag)
 		abort ();
 	      if (ins->vex.evex)
 		{
+		  /* S/G EVEX insns require EVEX.X4 not to be set.  */
+		  if (ins->rex2 & REX_X)
+		    {
+		      oappend (ins, "(bad)");
+		      return true;
+		    }
+
 		  if (!ins->vex.v)
 		    vindex += 16;
 		  check_gather = ins->obufp == ins->op_out[1];
@@ -11807,7 +11929,7 @@ OP_E_memory (instr_info *ins, int bytemode, int sizeflag)
 
 	      if (ins->rex & REX_R)
 	        modrm_reg += 8;
-	      if (!ins->vex.r)
+	      if (ins->rex2 & REX_R)
 	        modrm_reg += 16;
 	      if (vindex == modrm_reg)
 		oappend (ins, "/(bad)");
@@ -12013,10 +12135,7 @@ OP_indirE (instr_info *ins, int bytemode, int sizeflag)
 static bool
 OP_G (instr_info *ins, int bytemode, int sizeflag)
 {
-  if (ins->vex.evex && !ins->vex.r && ins->address_mode == mode_64bit)
-    oappend (ins, "(bad)");
-  else
-    print_register (ins, ins->modrm.reg, REX_R, bytemode, sizeflag);
+  print_register (ins, ins->modrm.reg, REX_R, bytemode, sizeflag);
   return true;
 }
 
@@ -12647,7 +12766,7 @@ OP_XMM (instr_info *ins, int bytemode, int sizeflag ATTRIBUTE_UNUSED)
     reg += 8;
   if (ins->vex.evex)
     {
-      if (!ins->vex.r)
+      if (ins->rex2 & REX_R)
 	reg += 16;
     }
 
@@ -13654,7 +13773,7 @@ DistinctDest_Fixup (instr_info *ins, int bytemode, int sizeflag)
   /* Calc destination register number.  */
   if (ins->rex & REX_R)
     modrm_reg += 8;
-  if (!ins->vex.r)
+  if (ins->rex2 & REX_R)
     modrm_reg += 16;
 
   /* Calc src1 register number.  */
diff --git a/opcodes/i386-gen.c b/opcodes/i386-gen.c
index fb5a4f81288..c42b05d6c9d 100644
--- a/opcodes/i386-gen.c
+++ b/opcodes/i386-gen.c
@@ -488,6 +488,7 @@ static bitfield opcode_modifiers[] =
   BITFIELD (Dialect),
   BITFIELD (ISA64),
   BITFIELD (NoEgpr),
+  BITFIELD (NF),
 };
 
 #define CLASS(n) #n, n
@@ -1121,6 +1122,7 @@ process_i386_opcode_modifier (FILE *table, char *mod, unsigned int space,
     SPACE(0F),
     SPACE(0F38),
     SPACE(0F3A),
+    SPACE(EVEXMAP4),
     SPACE(EVEXMAP5),
     SPACE(EVEXMAP6),
     SPACE(VEXMAP7),
diff --git a/opcodes/i386-opc.h b/opcodes/i386-opc.h
index 8b4a48c8c85..68dbeca343d 100644
--- a/opcodes/i386-opc.h
+++ b/opcodes/i386-opc.h
@@ -753,6 +753,9 @@ enum
      whether the instruction supports pseudo-prefix {rex2}.  */
   NoEgpr,
 
+  /* No CSPAZO flags update indication.  */
+  NF,
+
   /* The last bitfield in i386_opcode_modifier.  */
   Opcode_Modifier_Num
 };
@@ -799,6 +802,7 @@ typedef struct i386_opcode_modifier
   unsigned int dialect:2;
   unsigned int isa64:2;
   unsigned int noegpr:1;
+  unsigned int nf:1;
 } i386_opcode_modifier;
 
 /* Operand classes.  */
@@ -974,6 +978,7 @@ typedef struct insn_template
      1: 0F opcode prefix / space.
      2: 0F38 opcode prefix / space.
      3: 0F3A opcode prefix / space.
+     4: EVEXMAP4 opcode prefix / space.
      5: EVEXMAP5 opcode prefix / space.
      6: EVEXMAP6 opcode prefix / space.
      7: VEXMAP7 opcode prefix / space.
@@ -985,6 +990,7 @@ typedef struct insn_template
 #define SPACE_0F	1
 #define SPACE_0F38	2
 #define SPACE_0F3A	3
+#define SPACE_EVEXMAP4	4
 #define SPACE_EVEXMAP5	5
 #define SPACE_EVEXMAP6	6
 #define SPACE_VEXMAP7	7
diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl
index 8c8f6695d22..139ec8ce33a 100644
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -106,16 +106,6 @@
 #define HLEPrefixRelease PrefixOk=PrefixHLERelease
 #define NoTrackPrefixOk  PrefixOk=PrefixNoTrack
 
-#define Space0F    OpcodeSpace=SPACE_0F
-#define Space0F38  OpcodeSpace=SPACE_0F38
-#define Space0F3A  OpcodeSpace=SPACE_0F3A
-#define SpaceXOP08 OpcodeSpace=SPACE_XOP08
-#define SpaceXOP09 OpcodeSpace=SPACE_XOP09
-#define SpaceXOP0A OpcodeSpace=SPACE_XOP0A
-
-#define EVexMap5 OpcodeSpace=SPACE_EVEXMAP5
-#define EVexMap6 OpcodeSpace=SPACE_EVEXMAP6
-
 #define VexMap7 OpcodeSpace=SPACE_VEXMAP7
 
 #define VexW0 VexW=VEXW0
@@ -137,11 +127,25 @@
 #define EVexLIG EVex=EVEXLIG
 #define EVexDYN EVex=EVEXDYN
 
+#define Space0F    OpcodeSpace=SPACE_0F
+#define Space0F38  OpcodeSpace=SPACE_0F38
+#define Space0F3A  OpcodeSpace=SPACE_0F3A
+#define SpaceXOP08 OpcodeSpace=SPACE_XOP08
+#define SpaceXOP09 OpcodeSpace=SPACE_XOP09
+#define SpaceXOP0A OpcodeSpace=SPACE_XOP0A
+
+#define EVexMap4 OpcodeSpace=SPACE_EVEXMAP4|EVex128
+#define EVexMap5 OpcodeSpace=SPACE_EVEXMAP5
+#define EVexMap6 OpcodeSpace=SPACE_EVEXMAP6
+
 #define Disp8ShiftVL Disp8MemShift=DISP8_SHIFT_VL
 
 #define Vsz256 Vsz=VSZ256
 #define Vsz512 Vsz=VSZ512
 
+// The template supports VEX format for cpuid and EVEX format for cpuid & apx_f.
+#define APX_F(cpuid) cpuid&(cpuid|APX_F)
+
 // The EVEX purpose of StaticRounding appears only together with SAE. Re-use
 // the bit to mark commutative VEX encodings where swapping the source
 // operands may allow to switch from 3-byte to 2-byte VEX encoding.
@@ -197,6 +201,7 @@ mov, 0xf24, i386&No64, D|RegMem|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf, { Te
 
 // Move after swapping the bytes
 movbe, 0x0f38f0, Movbe, D|Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Word|Dword|Qword|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+movbe, 0x60, Movbe&APX_F, D|Modrm|CheckOperandSize|No_bSuf|No_sSuf|EVexMap4, { Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 
 // Move with sign extend.
 movsb, 0xfbe, i386, Modrm|No_bSuf|No_sSuf, { Reg8|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -1318,13 +1323,16 @@ getsec, 0xf37, SMX, NoSuf, {}
 
 invept, 0x660f3880, EPT&No64, Modrm|IgnoreSize|NoSuf, { Oword|Unspecified|BaseIndex, Reg32 }
 invept, 0x660f3880, EPT&x64, Modrm|NoSuf|NoRex64, { Oword|Unspecified|BaseIndex, Reg64 }
+invept, 0xf3f0, EPT&APX_F, Modrm|NoSuf|EVexMap4, { Oword|Unspecified|BaseIndex, Reg64 }
 invvpid, 0x660f3881, EPT&No64, Modrm|IgnoreSize|NoSuf, { Oword|Unspecified|BaseIndex, Reg32 }
 invvpid, 0x660f3881, EPT&x64, Modrm|NoSuf|NoRex64, { Oword|Unspecified|BaseIndex, Reg64 }
+invvpid, 0xf3f1, EPT&APX_F, Modrm|NoSuf|EVexMap4, { Oword|Unspecified|BaseIndex, Reg64 }
 
 // INVPCID instruction
 
 invpcid, 0x660f3882, INVPCID&No64, Modrm|IgnoreSize|NoSuf, { Oword|Unspecified|BaseIndex, Reg32 }
 invpcid, 0x660f3882, INVPCID&x64, Modrm|NoSuf|NoRex64, { Oword|Unspecified|BaseIndex, Reg64 }
+invpcid, 0xf3f2, INVPCID&APX_F, Modrm|NoSuf|EVexMap4, { Oword|Unspecified|BaseIndex, Reg64 }
 
 // SSSE3 instructions.
 
@@ -1425,6 +1433,8 @@ pcmpistri<sse42>, 0x660f3a63, <sse42:cpu>, Modrm|<sse42:attr>|NoSuf, { Imm8, Reg
 pcmpistrm<sse42>, 0x660f3a62, <sse42:cpu>, Modrm|<sse42:attr>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
 crc32, 0xf20f38f0, SSE4_2, W|Modrm|No_sSuf|No_qSuf, { Reg8|Reg16|Reg32|Unspecified|BaseIndex, Reg32 }
 crc32, 0xf20f38f0, SSE4_2&x64, W|Modrm|No_wSuf|No_lSuf|No_sSuf, { Reg8|Reg64|Unspecified|BaseIndex, Reg64 }
+crc32, 0xf0, APX_F, W|Modrm|No_sSuf|No_qSuf|EVexMap4, { Reg8|Reg16|Reg32|Unspecified|BaseIndex, Reg32 }
+crc32, 0xf0, APX_F, W|Modrm|No_wSuf|No_lSuf|No_sSuf|EVexMap4, { Reg8|Reg64|Unspecified|BaseIndex, Reg64 }
 
 // xsave/xrstor New Instructions.
 
@@ -1839,14 +1849,14 @@ xtest, 0xf01d6, HLE|RTM, NoSuf, {}
 
 // BMI2 instructions.
 
-bzhi, 0xf5, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-mulx, 0xf2f6, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-pdep, 0xf2f5, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-pext, 0xf3f5, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-rorx, 0xf2f0, BMI2, Modrm|CheckOperandSize|Vex128|Space0F3A|No_bSuf|No_wSuf|No_sSuf, { Imm8|Imm8S, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-sarx, 0xf3f7, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-shlx, 0x66f7, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-shrx, 0xf2f7, BMI2, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+bzhi, 0xf5, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+mulx, 0xf2f6, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
+pdep, 0xf2f5, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
+pext, 0xf3f5, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
+rorx, 0xf2f0, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F3A|No_bSuf|No_wSuf|No_sSuf, { Imm8|Imm8S, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+sarx, 0xf3f7, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+shlx, 0x66f7, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+shrx, 0xf2f7, APX_F(BMI2), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
 
 // FMA4 instructions
 
@@ -1916,11 +1926,11 @@ lwpins, 0x12/0, LWP, Modrm|SpaceXOP0A|NoSuf|VexVVVV|Vex, { Imm32|Imm32S, Reg32|U
 
 // BMI instructions
 
-andn, 0xf2, BMI, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
-bextr, 0xf7, BMI, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-blsi, 0xf3/3, BMI, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-blsmsk, 0xf3/2, BMI, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
-blsr, 0xf3/1, BMI, Modrm|CheckOperandSize|Vex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+andn, 0xf2, APX_F(BMI), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64, Reg32|Reg64 }
+bextr, 0xf7, APX_F(BMI), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|SwapSources|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64, Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+blsi, 0xf3/3, APX_F(BMI), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+blsmsk, 0xf3/2, APX_F(BMI), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
+blsr, 0xf3/1, APX_F(BMI), Modrm|CheckOperandSize|Vex128|EVex128|Space0F38|VexVVVV|No_bSuf|No_wSuf|No_sSuf|NF, { Reg32|Reg64|Unspecified|BaseIndex, Reg32|Reg64 }
 tzcnt, 0xf30fbc, BMI, Modrm|CheckOperandSize|No_bSuf|No_sSuf, { Reg16|Reg32|Reg64|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 
 // TBM instructions
@@ -2049,13 +2059,20 @@ bndldx, 0x0f1a, MPX, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex, RegBND }
 
 // SHA instructions.
 sha1rnds4, 0xf3acc, SHA, Modrm|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
+sha1rnds4, 0xd4, SHA&APX_F, Modrm|NoSuf|EVexMap4, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
 sha1nexte, 0xf38c8, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha1nexte, 0xd8, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 sha1msg1, 0xf38c9, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha1msg1, 0xd9, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 sha1msg2, 0xf38ca, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha1msg2, 0xda, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 sha256rnds2, 0xf38cb, SHA, Modrm|NoSuf, { Acc|Xmmword, RegXMM|Unspecified|BaseIndex, RegXMM }
 sha256rnds2, 0xf38cb, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha256rnds2, 0xdb, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 sha256msg1, 0xf38cc, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha256msg1, 0xdc, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 sha256msg2, 0xf38cd, SHA, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+sha256msg2, 0xdd, SHA&APX_F, Modrm|NoSuf|EVexMap4, { RegXMM|Unspecified|BaseIndex, RegXMM }
 
 // SHA512 instructions.
 
@@ -2117,9 +2134,9 @@ kor<bw>, 0x<bw:kpfx>45, <bw:kcpu>, Modrm|Vex256|Space0F|VexVVVV|VexW0|NoSuf, { R
 kxnor<bw>, 0x<bw:kpfx>46, <bw:kcpu>, Modrm|Vex256|Space0F|VexVVVV|VexW0|NoSuf, { RegMask, RegMask, RegMask }
 kxor<bw>, 0x<bw:kpfx>47, <bw:kcpu>, Modrm|Vex256|Space0F|VexVVVV|VexW0|NoSuf, { RegMask, RegMask, RegMask }
 
-kmov<bw>, 0x<bw:kpfx>90, <bw:kcpu>, Modrm|Vex128|Space0F|VexW0|NoSuf, { RegMask|<bw:elem>|Unspecified|BaseIndex, RegMask }
-kmov<bw>, 0x<bw:kpfx>91, <bw:kcpu>, Modrm|Vex128|Space0F|VexW0|NoSuf, { RegMask, <bw:elem>|Unspecified|BaseIndex }
-kmov<bw>, 0x<bw:kpfx>92, <bw:kcpu>, D|Modrm|Vex128|Space0F|VexW0|NoSuf, { Reg32, RegMask }
+kmov<bw>, 0x<bw:kpfx>90, APX_F(<bw:kcpu>), Modrm|Vex128|EVex128|Space0F|VexW0|NoSuf, { RegMask|<bw:elem>|Unspecified|BaseIndex, RegMask }
+kmov<bw>, 0x<bw:kpfx>91, APX_F(<bw:kcpu>), Modrm|Vex128|EVex128|Space0F|VexW0|NoSuf, { RegMask, <bw:elem>|Unspecified|BaseIndex }
+kmov<bw>, 0x<bw:kpfx>92, APX_F(<bw:kcpu>), D|Modrm|Vex128|EVex128|Space0F|VexW0|NoSuf, { Reg32, RegMask }
 
 knot<bw>, 0x<bw:kpfx>44, <bw:kcpu>, Modrm|Vex128|Space0F|VexW0|NoSuf, { RegMask, RegMask }
 kortest<bw>, 0x<bw:kpfx>98, <bw:kcpu>, Modrm|Vex128|Space0F|VexW0|NoSuf, { RegMask, RegMask }
@@ -2594,9 +2611,9 @@ vpmovzxdq, 0x6635, AVX512VL, Modrm|EVex=3|Masking|Space0F38|VexW=1|Disp8MemShift
 kadd<dq>, 0x<dq:kpfx>4a, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
 kand<dq>, 0x<dq:kpfx>41, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
 kandn<dq>, 0x<dq:kpfx>42, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf|Optimize, { RegMask, RegMask, RegMask }
-kmov<dq>, 0x<dq:kpfx>90, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask|<dq:elem>|Unspecified|BaseIndex, RegMask }
-kmov<dq>, 0x<dq:kpfx>91, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, <dq:elem>|Unspecified|BaseIndex }
-kmov<dq>, 0xf292, AVX512BW, D|Modrm|Vex128|Space0F|<dq:vexw64>|<dq:kvsz>|NoSuf, { <dq:gpr>, RegMask }
+kmov<dq>, 0x<dq:kpfx>90, APX_F(AVX512BW), Modrm|Vex128|EVex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask|<dq:elem>|Unspecified|BaseIndex, RegMask }
+kmov<dq>, 0x<dq:kpfx>91, APX_F(AVX512BW), Modrm|Vex128|EVex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, <dq:elem>|Unspecified|BaseIndex }
+kmov<dq>, 0xf292, APX_F(AVX512BW), D|Modrm|Vex128|EVex128|Space0F|<dq:vexw64>|<dq:kvsz>|NoSuf, { <dq:gpr>, RegMask }
 knot<dq>, 0x<dq:kpfx>44, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask }
 kor<dq>, 0x<dq:kpfx>45, AVX512BW, Modrm|Vex256|Space0F|VexVVVV|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask, RegMask }
 kortest<dq>, 0x<dq:kpfx>98, AVX512BW, Modrm|Vex128|Space0F|VexW1|<dq:kvsz>|NoSuf, { RegMask, RegMask }
@@ -2995,9 +3012,13 @@ rdsspq, 0xf30f1e/1, SHSTK&x64, Modrm|NoSuf, { Reg64 }
 saveprevssp, 0xf30f01ea, SHSTK, NoSuf, {}
 rstorssp, 0xf30f01/5, SHSTK, Modrm|NoSuf, { Qword|Unspecified|BaseIndex }
 wrssd, 0x0f38f6, SHSTK, Modrm|IgnoreSize|NoSuf, { Reg32, Dword|Unspecified|BaseIndex }
+wrssd, 0x66, SHSTK&APX_F, Modrm|IgnoreSize|NoSuf|EVexMap4, { Reg32, Dword|Unspecified|BaseIndex }
 wrssq, 0x0f38f6, SHSTK&x64, Modrm|NoSuf|Size64, { Reg64, Qword|Unspecified|BaseIndex }
+wrssq, 0x66, SHSTK&APX_F, Modrm|NoSuf|Size64|EVexMap4, { Reg64, Qword|Unspecified|BaseIndex }
 wrussd, 0x660f38f5, SHSTK, Modrm|IgnoreSize|NoSuf, { Reg32, Dword|Unspecified|BaseIndex }
+wrussd, 0x6665, SHSTK&APX_F, Modrm|IgnoreSize|NoSuf|EVexMap4, { Reg32, Dword|Unspecified|BaseIndex }
 wrussq, 0x660f38f5, SHSTK&x64, Modrm|NoSuf, { Reg64, Qword|Unspecified|BaseIndex }
+wrussq, 0x6665, SHSTK&APX_F, Modrm|NoSuf|EVexMap4, { Reg64, Qword|Unspecified|BaseIndex }
 setssbsy, 0xf30f01e8, SHSTK, NoSuf, {}
 clrssbsy, 0xf30fae/6, SHSTK, Modrm|NoSuf, { Qword|Unspecified|BaseIndex }
 endbr64, 0xf30f1efa, IBT, NoSuf, {}
@@ -3045,7 +3066,9 @@ cldemote, 0x0f1c/0, CLDEMOTE, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
 // MOVDIR[I,64B] instructions.
 
 movdiri, 0xf38f9, MOVDIRI, Modrm|CheckOperandSize|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+movdiri, 0xf9, MOVDIRI&APX_F, Modrm|CheckOperandSize|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 movdir64b, 0x660f38f8, MOVDIR64B, Modrm|AddrPrefixOpReg|NoSuf, { Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+movdir64b, 0x66f8, MOVDIR64B&APX_F, Modrm|AddrPrefixOpReg|NoSuf|EVexMap4, { Unspecified|BaseIndex, Reg32|Reg64 }
 
 // MOVEDIR instructions end.
 
@@ -3074,7 +3097,9 @@ vcvtneps2bf16<Vxy>, 0xf372, AVX_NE_CONVERT, Modrm|<Vxy:vex>|Space0F38|VexW0|NoSu
 // ENQCMD instructions.
 
 enqcmd, 0xf20f38f8, ENQCMD, Modrm|AddrPrefixOpReg|NoSuf, { Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+enqcmd, 0xf2f8, APX_F(ENQCMD), Modrm|AddrPrefixOpReg|NoSuf|EVexMap4, { Unspecified|BaseIndex, Reg32|Reg64 }
 enqcmds, 0xf30f38f8, ENQCMD, Modrm|AddrPrefixOpReg|NoSuf, { Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
+enqcmds, 0xf3f8, APX_F(ENQCMD), Modrm|AddrPrefixOpReg|NoSuf|EVexMap4, { Unspecified|BaseIndex, Reg32|Reg64 }
 
 // ENQCMD instructions end.
 
@@ -3135,8 +3160,8 @@ xresldtrk, 0xf20f01e9, TSXLDTRK, NoSuf, {}
 
 // AMX instructions.
 
-ldtilecfg, 0x49/0, AMX_TILE, Modrm|Vex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex }
-sttilecfg, 0x6649/0, AMX_TILE, Modrm|Vex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex }
+ldtilecfg, 0x49/0, APX_F(AMX_TILE), Modrm|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex }
+sttilecfg, 0x6649/0, APX_F(AMX_TILE), Modrm|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex }
 
 tcmmimfp16ps, 0x666c, AMX_COMPLEX, Modrm|Vex128|Space0F38|VexVVVV|VexW0|SwapSources|NoSuf, { RegTMM, RegTMM, RegTMM }
 tcmmrlfp16ps, 0x6c, AMX_COMPLEX, Modrm|Vex128|Space0F38|VexVVVV|VexW0|SwapSources|NoSuf, { RegTMM, RegTMM, RegTMM }
@@ -3148,9 +3173,9 @@ tdpbuud, 0x5e, AMX_INT8, Modrm|Vex128|Space0F38|VexVVVV|VexW0|SwapSources|NoSuf,
 tdpbusd, 0x665e, AMX_INT8, Modrm|Vex128|Space0F38|VexVVVV|VexW0|SwapSources|NoSuf, { RegTMM, RegTMM, RegTMM }
 tdpbsud, 0xf35e, AMX_INT8, Modrm|Vex128|Space0F38|VexVVVV|VexW0|SwapSources|NoSuf, { RegTMM, RegTMM, RegTMM }
 
-tileloadd, 0xf24b, AMX_TILE, Sibmem|Vex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
-tileloaddt1, 0x664b, AMX_TILE, Sibmem|Vex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
-tilestored, 0xf34b, AMX_TILE, Sibmem|Vex128|Space0F38|VexW0|NoSuf, { RegTMM, Unspecified|BaseIndex }
+tileloadd, 0xf24b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
+tileloaddt1, 0x664b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { Unspecified|BaseIndex, RegTMM }
+tilestored, 0xf34b, APX_F(AMX_TILE), Sibmem|Vex128|EVex128|Space0F38|VexW0|NoSuf, { RegTMM, Unspecified|BaseIndex }
 
 tilerelease, 0x49c0, AMX_TILE, Vex128|Space0F38|VexW0|NoSuf, {}
 
@@ -3162,15 +3187,25 @@ tilezero, 0xf249, AMX_TILE, Modrm|Vex128|Space0F38|VexW0|NoSuf, { RegTMM }
 
 loadiwkey, 0xf30f38dc, KL, Load|Modrm|NoSuf, { RegXMM, RegXMM }
 encodekey128, 0xf30f38fa, KL, Modrm|NoSuf, { Reg32, Reg32 }
+encodekey128, 0xf3da, KL&APX_F, Modrm|NoSuf|EVexMap4, { Reg32, Reg32 }
 encodekey256, 0xf30f38fb, KL, Modrm|NoSuf, { Reg32, Reg32 }
+encodekey256, 0xf3db, KL&APX_F, Modrm|NoSuf|EVexMap4, { Reg32, Reg32 }
 aesenc128kl, 0xf30f38dc, KL, Modrm|NoSuf, { Unspecified|BaseIndex, RegXMM }
+aesenc128kl, 0xf3dc, KL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex, RegXMM }
 aesdec128kl, 0xf30f38dd, KL, Modrm|NoSuf, { Unspecified|BaseIndex, RegXMM }
+aesdec128kl, 0xf3dd, KL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex, RegXMM }
 aesenc256kl, 0xf30f38de, KL, Modrm|NoSuf, { Unspecified|BaseIndex, RegXMM }
+aesenc256kl, 0xf3de, KL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex, RegXMM }
 aesdec256kl, 0xf30f38df, KL, Modrm|NoSuf, { Unspecified|BaseIndex, RegXMM }
+aesdec256kl, 0xf3df, KL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex, RegXMM }
 aesencwide128kl, 0xf30f38d8/0, WideKL, Modrm|NoSuf, { Unspecified|BaseIndex }
+aesencwide128kl, 0xf3d8/0, WideKL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex }
 aesdecwide128kl, 0xf30f38d8/1, WideKL, Modrm|NoSuf, { Unspecified|BaseIndex }
+aesdecwide128kl, 0xf3d8/1, WideKL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex }
 aesencwide256kl, 0xf30f38d8/2, WideKL, Modrm|NoSuf, { Unspecified|BaseIndex }
+aesencwide256kl, 0xf3d8/2, WideKL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex }
 aesdecwide256kl, 0xf30f38d8/3, WideKL, Modrm|NoSuf, { Unspecified|BaseIndex }
+aesdecwide256kl, 0xf3d8/3, WideKL&APX_F, Modrm|NoSuf|EVexMap4, { Unspecified|BaseIndex }
 
 // KEYLOCKER instructions end.
 
@@ -3318,7 +3353,7 @@ prefetchit1, 0xf18/6, PREFETCHI, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
 
 // CMPCCXADD instructions.
 
-cmp<cc>xadd, 0x66e<cc:opc>, CMPCCXADD, Modrm|Vex|Space0F38|VexVVVV|SwapSources|CheckOperandSize|NoSuf, { Reg32|Reg64, Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+cmp<cc>xadd, 0x66e<cc:opc>, APX_F(CMPCCXADD), Modrm|Vex|EVex128|Space0F38|VexVVVV|SwapSources|CheckOperandSize|NoSuf, { Reg32|Reg64, Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 
 // CMPCCXADD instructions end.
 
@@ -3338,9 +3373,13 @@ wrmsrlist, 0xf30f01c6, MSRLIST, NoSuf, {}
 // RAO-INT instructions.
 
 aadd, 0xf38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+aadd, 0xfc, RAO_INT&APX_F, Modrm|IgnoreSize|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 aand, 0x660f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+aand, 0x66fc, RAO_INT&APX_F, Modrm|IgnoreSize|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 aor, 0xf20f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+aor, 0xf2fc, RAO_INT&APX_F, Modrm|IgnoreSize|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 axor, 0xf30f38fc, RAO_INT, Modrm|IgnoreSize|CheckOperandSize|NoSuf, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
+axor, 0xf3fc, RAO_INT&APX_F, Modrm|IgnoreSize|CheckOperandSize|NoSuf|EVexMap4, { Reg32|Reg64, Dword|Qword|Unspecified|BaseIndex }
 
 // RAO-INT instructions end.
 
-- 
2.25.1