[02/13] x86: drop ShortForm attribute

Message ID da5eab10-c2c1-9f05-2050-cab7e7b9d9e6@suse.com
State New
Headers show
Series
  • x86: further insn template compaction
Related show

Commit Message

Jan Beulich Oct. 30, 2019, 8:23 a.m.
It is very simple to derive from other template properties, and hence
there's little point wasting storage for it.

gas/
2019-10-XX  Jan Beulich  <jbeulich@suse.com>

	* config/tc-i386.c (process_immext): Also set i.tm.operands to
	zero.
	(optimize_encoding): Drop use of shortform field.
	(is_short_form): New.
	(process_suffix, process_operands): Use it to replace use of
	shortform field.

opcodes/
2019-10-XX  Jan Beulich  <jbeulich@suse.com>

	* i386-gen.c (opcode_modifiers): Remove ShortForm entry.
	* i386-opc.h (ShortForm): Delete.
	(struct i386_opcode_modifier): Remove shortform field.
	* i386-opc.tbl (mov, movabs, push, pop, xchg, inc, dec, fld,
	fst, fstp, fxch, fcom, fcomp, fucom, fucomp, fadd, faddp, fsub,
	fsubp, fsubr, fsubrp, fmul, fmulp, fdiv, fdivp, fdivr, fdivrp,
	ffreep, bswap, fcmov*, fcomi, fcomip, fucomi, fucomip, movq):
	Drop ShortForm.
	* i386-tbl.h: Re-generate.

Comments

H.J. Lu Oct. 31, 2019, 5:49 p.m. | #1
On Wed, Oct 30, 2019 at 1:23 AM Jan Beulich <jbeulich@suse.com> wrote:
>

> It is very simple to derive from other template properties, and hence

> there's little point wasting storage for it.

>

> gas/

> 2019-10-XX  Jan Beulich  <jbeulich@suse.com>

>

>         * config/tc-i386.c (process_immext): Also set i.tm.operands to

>         zero.

>         (optimize_encoding): Drop use of shortform field.

>         (is_short_form): New.

>         (process_suffix, process_operands): Use it to replace use of

>         shortform field.

>

> opcodes/

> 2019-10-XX  Jan Beulich  <jbeulich@suse.com>

>

>         * i386-gen.c (opcode_modifiers): Remove ShortForm entry.

>         * i386-opc.h (ShortForm): Delete.

>         (struct i386_opcode_modifier): Remove shortform field.

>         * i386-opc.tbl (mov, movabs, push, pop, xchg, inc, dec, fld,

>         fst, fstp, fxch, fcom, fcomp, fucom, fucomp, fadd, faddp, fsub,

>         fsubp, fsubr, fsubrp, fmul, fmulp, fdiv, fdivp, fdivr, fdivrp,

>         ffreep, bswap, fcmov*, fcomi, fcomip, fucomi, fucomip, movq):

>         Drop ShortForm.

>         * i386-tbl.h: Re-generate.

>

> --- a/gas/config/tc-i386.c

> +++ b/gas/config/tc-i386.c

> @@ -3842,6 +3842,7 @@ process_immext (void)

>                   i.tm.name);

>

>        i.operands = 0;

> +      i.tm.operands = 0;

>      }

>

>    if (i.tm.cpu_flags.bitfield.cpumwaitx && i.operands > 0)

> @@ -3870,6 +3871,7 @@ bad_register_operand:

>         }

>

>        i.operands = 0;

> +      i.tm.operands = 0;

>      }

>

>    /* These AMD 3DNow! and SSE2 instructions have an opcode suffix

> @@ -4034,7 +4036,6 @@ optimize_encoding (void)

>               i.tm.base_opcode = 0xb8;

>               i.tm.extension_opcode = None;

>               i.tm.opcode_modifier.w = 0;

> -             i.tm.opcode_modifier.shortform = 1;

>               i.tm.opcode_modifier.modrm = 0;

>             }

>         }

> @@ -6208,6 +6209,21 @@ check_string (void)

>    return 1;

>  }

>

> +static bfd_boolean

> +is_short_form (const insn_template *t)

> +{

> +  unsigned int op, num_reg;

> +

> +  if (t->opcode_modifier.modrm || t->operands > 2)

> +    return FALSE;

> +

> +  for (num_reg = op = 0; op < t->operands; ++op)

> +    if (t->operand_types[op].bitfield.reg)

> +      ++num_reg;

> +

> +  return num_reg == 1;

> +}

> +


So this replaces a bit check with a function.   What is the real advantage?

-- 
H.J.
Jan Beulich Nov. 4, 2019, 10:31 a.m. | #2
On 31.10.2019 18:49,  H.J. Lu  wrote:
> On Wed, Oct 30, 2019 at 1:23 AM Jan Beulich <jbeulich@suse.com> wrote:

>> @@ -6208,6 +6209,21 @@ check_string (void)

>>    return 1;

>>  }

>>

>> +static bfd_boolean

>> +is_short_form (const insn_template *t)

>> +{

>> +  unsigned int op, num_reg;

>> +

>> +  if (t->opcode_modifier.modrm || t->operands > 2)

>> +    return FALSE;

>> +

>> +  for (num_reg = op = 0; op < t->operands; ++op)

>> +    if (t->operand_types[op].bitfield.reg)

>> +      ++num_reg;

>> +

>> +  return num_reg == 1;

>> +}

>> +

> 

> So this replaces a bit check with a function.   What is the real advantage?


Space savings - one bit per template, which sums up with the large
number of templates there are.

Jan
H.J. Lu Nov. 4, 2019, 5:13 p.m. | #3
On Mon, Nov 4, 2019 at 2:31 AM Jan Beulich <jbeulich@suse.com> wrote:
>

> On 31.10.2019 18:49,  H.J. Lu  wrote:

> > On Wed, Oct 30, 2019 at 1:23 AM Jan Beulich <jbeulich@suse.com> wrote:

> >> @@ -6208,6 +6209,21 @@ check_string (void)

> >>    return 1;

> >>  }

> >>

> >> +static bfd_boolean

> >> +is_short_form (const insn_template *t)

> >> +{

> >> +  unsigned int op, num_reg;

> >> +

> >> +  if (t->opcode_modifier.modrm || t->operands > 2)

> >> +    return FALSE;

> >> +

> >> +  for (num_reg = op = 0; op < t->operands; ++op)

> >> +    if (t->operand_types[op].bitfield.reg)

> >> +      ++num_reg;

> >> +

> >> +  return num_reg == 1;

> >> +}

> >> +

> >

> > So this replaces a bit check with a function.   What is the real advantage?

>

> Space savings - one bit per template, which sums up with the large

> number of templates there are.

>


Is that really necessary?

-- 
H.J.
Jan Beulich Nov. 5, 2019, 7:55 a.m. | #4
On 04.11.2019 18:13, H.J. Lu wrote:
> On Mon, Nov 4, 2019 at 2:31 AM Jan Beulich <jbeulich@suse.com> wrote:

>>

>> On 31.10.2019 18:49,  H.J. Lu  wrote:

>>> On Wed, Oct 30, 2019 at 1:23 AM Jan Beulich <jbeulich@suse.com> wrote:

>>>> @@ -6208,6 +6209,21 @@ check_string (void)

>>>>    return 1;

>>>>  }

>>>>

>>>> +static bfd_boolean

>>>> +is_short_form (const insn_template *t)

>>>> +{

>>>> +  unsigned int op, num_reg;

>>>> +

>>>> +  if (t->opcode_modifier.modrm || t->operands > 2)

>>>> +    return FALSE;

>>>> +

>>>> +  for (num_reg = op = 0; op < t->operands; ++op)

>>>> +    if (t->operand_types[op].bitfield.reg)

>>>> +      ++num_reg;

>>>> +

>>>> +  return num_reg == 1;

>>>> +}

>>>> +

>>>

>>> So this replaces a bit check with a function.   What is the real advantage?

>>

>> Space savings - one bit per template, which sums up with the large

>> number of templates there are.

>>

> 

> Is that really necessary?


I think the rest of this series doesn't depend on this (yet I didn't
do a thorough check), but I think where easily possible and not
overly expensive, we should try to avoid having redundant information
in the templates. As to expensiveness: Note that patch 1 arranges for
the function to be called only at the tail of a long if/else-if chain
(which in particular filters out all insns using ModR/M encodings).
And the only other use is for templates with the W attribute set,
which are pretty common ones, but not very many.

If you continue to have severe reservations, I can try to re-order
the series, such that (if it works) the subsequent already approved
patches could go in independent of the decision here.

Jan
Michael Matz Nov. 5, 2019, 2:58 p.m. | #5
Hi,

On Mon, 4 Nov 2019, H.J. Lu wrote:

> > >> +static bfd_boolean

> > >> +is_short_form (const insn_template *t)

> > >> +{

> > >> +  unsigned int op, num_reg;

> > >> +

> > >> +  if (t->opcode_modifier.modrm || t->operands > 2)

> > >> +    return FALSE;

> > >> +

> > >> +  for (num_reg = op = 0; op < t->operands; ++op)

> > >> +    if (t->operand_types[op].bitfield.reg)

> > >> +      ++num_reg;

> > >> +

> > >> +  return num_reg == 1;

> > >> +}

> > >> +

> > >

> > > So this replaces a bit check with a function.   What is the real advantage?

> >

> > Space savings - one bit per template, which sums up with the large

> > number of templates there are.

> >

> 

> Is that really necessary?


If I may add an opinion: to me the memory space savings in the tables 
aren't the important part, but rather the savings in textual clutter in 
i386-opc.tbl.  The latter makes it so that it's very easy to overlook 
something (either the attribute missing, or invalidly there for certain 
instructions), so everything that can be instead computed (quickly) from 
other information should be computed.

FWIW, whenever I look at that file and see the usual marvel

  No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf

I cringe, and wonder why it isn't simply No_bwlsqldSuf (or, in this 
specific case 'No_Suf' as these are all No_?Suf flags).  Now, back to 
under my stone :)


Ciao,
Michael.
Jan Beulich Nov. 5, 2019, 3:15 p.m. | #6
On 05.11.2019 15:58, Michael Matz wrote:
> FWIW, whenever I look at that file and see the usual marvel

> 

>   No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf

> 

> I cringe, and wonder why it isn't simply No_bwlsqldSuf (or, in this 

> specific case 'No_Suf' as these are all No_?Suf flags).  Now, back to 

> under my stone :)


I mean to change this, but haven't got to that point yet.

Jan
Jan Beulich Nov. 7, 2019, 7:26 a.m. | #7
On 05.11.2019 15:58, Michael Matz wrote:
> Hi,

> 

> On Mon, 4 Nov 2019, H.J. Lu wrote:

> 

>>>>> +static bfd_boolean

>>>>> +is_short_form (const insn_template *t)

>>>>> +{

>>>>> +  unsigned int op, num_reg;

>>>>> +

>>>>> +  if (t->opcode_modifier.modrm || t->operands > 2)

>>>>> +    return FALSE;

>>>>> +

>>>>> +  for (num_reg = op = 0; op < t->operands; ++op)

>>>>> +    if (t->operand_types[op].bitfield.reg)

>>>>> +      ++num_reg;

>>>>> +

>>>>> +  return num_reg == 1;

>>>>> +}

>>>>> +

>>>>

>>>> So this replaces a bit check with a function.   What is the real advantage?

>>>

>>> Space savings - one bit per template, which sums up with the large

>>> number of templates there are.

>>>

>>

>> Is that really necessary?

> 

> If I may add an opinion: to me the memory space savings in the tables 

> aren't the important part, but rather the savings in textual clutter in 

> i386-opc.tbl.  The latter makes it so that it's very easy to overlook 

> something (either the attribute missing, or invalidly there for certain 

> instructions), so everything that can be instead computed (quickly) from 

> other information should be computed.


The memory space savings aren't the primary aspect when thinking of
space savings - it's rather the better cache utilization that I view
as relevant. (The memory size reduction is welcome to me nevertheless,
since I don't think software has to only ever grow in size.)

> FWIW, whenever I look at that file and see the usual marvel

> 

>   No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf

> 

> I cringe, and wonder why it isn't simply No_bwlsqldSuf (or, in this 

> specific case 'No_Suf' as these are all No_?Suf flags).  Now, back to 

> under my stone :)


I'd go a more radical (and sufficiently simple) step as a first move:
No instruction allowing for all suffixes, what about making i386-gen
simply set all 6 bits when it finds a template to not have any No_*Suf
at all? This would make for a significant readability improvement with
relatively little effort. Thoughts?

Jan
Michael Matz Nov. 7, 2019, 9:19 a.m. | #8
Hi,

On Thu, 7 Nov 2019, Jan Beulich wrote:

> > FWIW, whenever I look at that file and see the usual marvel

> > 

> >   No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf

> > 

> > I cringe, and wonder why it isn't simply No_bwlsqldSuf (or, in this 

> > specific case 'No_Suf' as these are all No_?Suf flags).  Now, back to 

> > under my stone :)

> 

> I'd go a more radical (and sufficiently simple) step as a first move:

> No instruction allowing for all suffixes, what about making i386-gen

> simply set all 6 bits when it finds a template to not have any No_*Suf

> at all? This would make for a significant readability improvement with

> relatively little effort. Thoughts?


I'd like that even more.


Ciao,
Michael.
H.J. Lu Nov. 7, 2019, 5:44 p.m. | #9
On Wed, Nov 6, 2019 at 11:26 PM Jan Beulich <jbeulich@suse.com> wrote:
>

> On 05.11.2019 15:58, Michael Matz wrote:

> > Hi,

> >

> > On Mon, 4 Nov 2019, H.J. Lu wrote:

> >

> >>>>> +static bfd_boolean

> >>>>> +is_short_form (const insn_template *t)

> >>>>> +{

> >>>>> +  unsigned int op, num_reg;

> >>>>> +

> >>>>> +  if (t->opcode_modifier.modrm || t->operands > 2)

> >>>>> +    return FALSE;

> >>>>> +

> >>>>> +  for (num_reg = op = 0; op < t->operands; ++op)

> >>>>> +    if (t->operand_types[op].bitfield.reg)

> >>>>> +      ++num_reg;

> >>>>> +

> >>>>> +  return num_reg == 1;

> >>>>> +}

> >>>>> +

> >>>>

> >>>> So this replaces a bit check with a function.   What is the real advantage?

> >>>

> >>> Space savings - one bit per template, which sums up with the large

> >>> number of templates there are.

> >>>

> >>

> >> Is that really necessary?

> >

> > If I may add an opinion: to me the memory space savings in the tables

> > aren't the important part, but rather the savings in textual clutter in

> > i386-opc.tbl.  The latter makes it so that it's very easy to overlook

> > something (either the attribute missing, or invalidly there for certain

> > instructions), so everything that can be instead computed (quickly) from

> > other information should be computed.

>

> The memory space savings aren't the primary aspect when thinking of

> space savings - it's rather the better cache utilization that I view

> as relevant. (The memory size reduction is welcome to me nevertheless,

> since I don't think software has to only ever grow in size.)


For this particular case, I prefer a bit over a function.

-- 
H.J.
Jan Beulich Nov. 8, 2019, 7:49 a.m. | #10
On 07.11.2019 18:44,  H.J. Lu  wrote:
> On Wed, Nov 6, 2019 at 11:26 PM Jan Beulich <jbeulich@suse.com> wrote:

>>

>> On 05.11.2019 15:58, Michael Matz wrote:

>>> Hi,

>>>

>>> On Mon, 4 Nov 2019, H.J. Lu wrote:

>>>

>>>>>>> +static bfd_boolean

>>>>>>> +is_short_form (const insn_template *t)

>>>>>>> +{

>>>>>>> +  unsigned int op, num_reg;

>>>>>>> +

>>>>>>> +  if (t->opcode_modifier.modrm || t->operands > 2)

>>>>>>> +    return FALSE;

>>>>>>> +

>>>>>>> +  for (num_reg = op = 0; op < t->operands; ++op)

>>>>>>> +    if (t->operand_types[op].bitfield.reg)

>>>>>>> +      ++num_reg;

>>>>>>> +

>>>>>>> +  return num_reg == 1;

>>>>>>> +}

>>>>>>> +

>>>>>>

>>>>>> So this replaces a bit check with a function.   What is the real advantage?

>>>>>

>>>>> Space savings - one bit per template, which sums up with the large

>>>>> number of templates there are.

>>>>>

>>>>

>>>> Is that really necessary?

>>>

>>> If I may add an opinion: to me the memory space savings in the tables

>>> aren't the important part, but rather the savings in textual clutter in

>>> i386-opc.tbl.  The latter makes it so that it's very easy to overlook

>>> something (either the attribute missing, or invalidly there for certain

>>> instructions), so everything that can be instead computed (quickly) from

>>> other information should be computed.

>>

>> The memory space savings aren't the primary aspect when thinking of

>> space savings - it's rather the better cache utilization that I view

>> as relevant. (The memory size reduction is welcome to me nevertheless,

>> since I don't think software has to only ever grow in size.)

> 

> For this particular case, I prefer a bit over a function.


Well, as the (sadly) only ix86 maintainer you have the final say here.
Yet I'd nevertheless like you to re-consider on the basis that both
Michael and I think differently. I'd also like to point out again the
fundamental goal of mine (with long term supportablity in mind): The
opcode table would preferably contain as little redundancy as
reasonably possible (and nothing at all that's plain unnecessary, like
stray attributes).

I guess I'll submit a v2 of this patch once swapped in order with the
already approved ones, and we'll further take it from there.

Jan

Patch

--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -3842,6 +3842,7 @@  process_immext (void)
 		  i.tm.name);
 
       i.operands = 0;
+      i.tm.operands = 0;
     }
 
   if (i.tm.cpu_flags.bitfield.cpumwaitx && i.operands > 0)
@@ -3870,6 +3871,7 @@  bad_register_operand:
 	}
 
       i.operands = 0;
+      i.tm.operands = 0;
     }
 
   /* These AMD 3DNow! and SSE2 instructions have an opcode suffix
@@ -4034,7 +4036,6 @@  optimize_encoding (void)
 	      i.tm.base_opcode = 0xb8;
 	      i.tm.extension_opcode = None;
 	      i.tm.opcode_modifier.w = 0;
-	      i.tm.opcode_modifier.shortform = 1;
 	      i.tm.opcode_modifier.modrm = 0;
 	    }
 	}
@@ -6208,6 +6209,21 @@  check_string (void)
   return 1;
 }
 
+static bfd_boolean
+is_short_form (const insn_template *t)
+{
+  unsigned int op, num_reg;
+
+  if (t->opcode_modifier.modrm || t->operands > 2)
+    return FALSE;
+
+  for (num_reg = op = 0; op < t->operands; ++op)
+    if (t->operand_types[op].bitfield.reg)
+      ++num_reg;
+
+  return num_reg == 1;
+}
+
 static int
 process_suffix (void)
 {
@@ -6511,7 +6527,7 @@  process_suffix (void)
       /* It's not a byte, select word/dword operation.  */
       if (i.tm.opcode_modifier.w)
 	{
-	  if (i.tm.opcode_modifier.shortform)
+	  if (is_short_form (&i.tm))
 	    i.tm.base_opcode |= 8;
 	  else
 	    i.tm.base_opcode |= 1;
@@ -7116,7 +7132,7 @@  duplicate:
 	 on one of their operands, the default segment is ds.  */
       default_seg = &ds;
     }
-  else if (i.tm.opcode_modifier.shortform)
+  else if (is_short_form(&i.tm))
     {
       /* The register or float register operand is in operand
 	 0 or 1.  */
--- a/opcodes/i386-gen.c
+++ b/opcodes/i386-gen.c
@@ -609,7 +609,6 @@  static bitfield opcode_modifiers[] =
   BITFIELD (W),
   BITFIELD (Load),
   BITFIELD (Modrm),
-  BITFIELD (ShortForm),
   BITFIELD (Jump),
   BITFIELD (JumpDword),
   BITFIELD (JumpByte),
--- a/opcodes/i386-opc.h
+++ b/opcodes/i386-opc.h
@@ -395,8 +395,6 @@  enum
   Load,
   /* insn has a modrm byte. */
   Modrm,
-  /* register is in low 3 bits of opcode */
-  ShortForm,
   /* special case for jump insns.  */
   Jump,
   /* call and jump */
@@ -637,7 +635,6 @@  typedef struct i386_opcode_modifier
   unsigned int w:1;
   unsigned int load:1;
   unsigned int modrm:1;
-  unsigned int shortform:1;
   unsigned int jump:1;
   unsigned int jumpdword:1;
   unsigned int jumpbyte:1;
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -70,9 +70,9 @@  mov, 2, 0xa0, None, 1, CpuNo64, D|W|No_s
 mov, 2, 0x88, None, 1, 0, D|W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|HLEPrefixOk=3, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 // In the 64bit mode the short form mov immediate is redefined to have
 // 64bit value.
-mov, 2, 0xb0, None, 1, 0, W|ShortForm|No_sSuf|No_qSuf|No_ldSuf, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32 }
+mov, 2, 0xb0, None, 1, 0, W|No_sSuf|No_qSuf|No_ldSuf, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32 }
 mov, 2, 0xc6, 0x0, 1, 0, W|Modrm|No_sSuf|No_ldSuf|HLEPrefixOk=3|Optimize, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
-mov, 2, 0xb8, None, 1, Cpu64, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
+mov, 2, 0xb8, None, 1, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
 // The segment register moves accept WordReg so that a segment register
 // can be copied to a 32 bit register, and vice versa, without using a
 // size prefix.  When moving to a 32 bit register, the upper 16 bits
@@ -89,7 +89,7 @@  mov, 2, 0xf21, None, 2, Cpu386|CpuNo64,
 mov, 2, 0xf21, None, 2, Cpu64, D|RegMem|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Debug, Reg64 }
 mov, 2, 0xf24, None, 2, Cpu386|CpuNo64, D|RegMem|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf, { Test, Reg32 }
 movabs, 2, 0xa0, None, 1, Cpu64, D|W|No_sSuf|No_ldSuf, { Disp64|Unspecified|Byte|Word|Dword|Qword, Acc|Byte|Word|Dword|Qword }
-movabs, 2, 0xb8, None, 1, Cpu64, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf, { Imm64, Reg64 }
+movabs, 2, 0xb8, None, 1, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf, { Imm64, Reg64 }
 
 // Move after swapping the bytes
 movbe, 2, 0x0f38f0, None, 3, CpuMovbe, Modrm|No_bSuf|No_sSuf|No_ldSuf, { Word|Dword|Qword|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -120,28 +120,28 @@  movzw, 2, 0xfb7, None, 2, Cpu386, Modrm|
 movzx, 2, 0xfb6, None, 2, Cpu386, W|Modrm|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg8|Reg16|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 
 // Push instructions.
-push, 1, 0x50, None, 1, CpuNo64, ShortForm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
+push, 1, 0x50, None, 1, CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
 push, 1, 0xff, 0x6, 1, CpuNo64, Modrm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32|Word|Dword|Unspecified|BaseIndex }
 push, 1, 0x6a, None, 1, Cpu186|CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8S }
 push, 1, 0x68, None, 1, Cpu186|CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm16|Imm32 }
-push, 1, 0x6, None, 1, CpuNo64, ShortForm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg }
+push, 1, 0x6, None, 1, CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg }
 // In 64bit mode, the operand size is implicitly 64bit.
-push, 1, 0x50, None, 1, Cpu64, ShortForm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64 }
+push, 1, 0x50, None, 1, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64 }
 push, 1, 0xff, 0x6, 1, Cpu64, Modrm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64|Word|Qword|Unspecified|BaseIndex }
 push, 1, 0x6a, None, 1, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Imm8S }
 push, 1, 0x68, None, 1, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Imm16|Imm32S }
-push, 1, 0xfa0, None, 2, Cpu64, ShortForm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { SReg }
+push, 1, 0xfa0, None, 2, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { SReg }
 
 pusha, 0, 0x60, None, 1, Cpu186|CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
 // Pop instructions.
-pop, 1, 0x58, None, 1, CpuNo64, ShortForm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
+pop, 1, 0x58, None, 1, CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
 pop, 1, 0x8f, 0x0, 1, CpuNo64, Modrm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32|Word|Dword|Unspecified|BaseIndex }
-pop, 1, 0x7, None, 1, CpuNo64, ShortForm|DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg }
+pop, 1, 0x7, None, 1, CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg }
 // In 64bit mode, the operand size is implicitly 64bit.
-pop, 1, 0x58, None, 1, Cpu64, ShortForm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64 }
+pop, 1, 0x58, None, 1, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64 }
 pop, 1, 0x8f, 0x0, 1, Cpu64, Modrm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Reg16|Reg64|Word|Qword|Unspecified|BaseIndex }
-pop, 1, 0xfa1, None, 2, Cpu64, ShortForm|DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { SReg }
+pop, 1, 0xfa1, None, 2, Cpu64, DefaultSize|No_bSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { SReg }
 
 popa, 0, 0x61, None, 1, Cpu186|CpuNo64, DefaultSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
@@ -149,8 +149,8 @@  popa, 0, 0x61, None, 1, Cpu186|CpuNo64,
 // xchg commutes:  we allow both operand orders.
 
 // In the 64bit code, xchg rax, rax is reused for new nop instruction.
-xchg, 2, 0x90, None, 1, 0, ShortForm|CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Reg16|Reg32|Reg64, Acc|Word|Dword|Qword }
-xchg, 2, 0x90, None, 1, 0, ShortForm|CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Acc|Word|Dword|Qword, Reg16|Reg32|Reg64 }
+xchg, 2, 0x90, None, 1, 0, CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Reg16|Reg32|Reg64, Acc|Word|Dword|Qword }
+xchg, 2, 0x90, None, 1, 0, CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Acc|Word|Dword|Qword, Reg16|Reg32|Reg64 }
 xchg, 2, 0x86, None, 1, 0, W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk=2, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 xchg, 2, 0x86, None, 1, 0, W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk=2, { Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex, Reg8|Reg16|Reg32|Reg64 }
 
@@ -196,7 +196,7 @@  add, 2, 0x83, 0x0, 1, 0, Modrm|No_bSuf|N
 add, 2, 0x4, None, 1, 0, W|No_sSuf|No_ldSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
 add, 2, 0x80, 0x0, 1, 0, W|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 
-inc, 1, 0x40, None, 1, CpuNo64, ShortForm|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
+inc, 1, 0x40, None, 1, CpuNo64, No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
 inc, 1, 0xfe, 0x0, 1, 0, W|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 
 sub, 2, 0x28, None, 1, 0, D|W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk|Optimize, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
@@ -204,7 +204,7 @@  sub, 2, 0x83, 0x5, 1, 0, Modrm|No_bSuf|N
 sub, 2, 0x2c, None, 1, 0, W|No_sSuf|No_ldSuf, { Imm8|Imm16|Imm32|Imm32S, Acc|Byte|Word|Dword|Qword }
 sub, 2, 0x80, 0x5, 1, 0, W|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 
-dec, 1, 0x48, None, 1, CpuNo64, ShortForm|No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
+dec, 1, 0x48, None, 1, CpuNo64, No_bSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg16|Reg32 }
 dec, 1, 0xfe, 0x1, 1, 0, W|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 
 sbb, 2, 0x18, None, 1, 0, D|W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
@@ -562,9 +562,9 @@  verw, 1, 0xf00, 0x5, 2, Cpu286, Modrm|Ig
 // Floating point instructions.
 
 // load
-fld, 1, 0xd9c0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fld, 1, 0xd9c0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 fld, 1, 0xd9, 0x0, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
-fld, 1, 0xd9c0, None, 2, CpuFP, ShortForm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
+fld, 1, 0xd9c0, None, 2, CpuFP, IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
 // Intel Syntax
 fld, 1, 0xdb, 0x5, 1, CpuFP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf, { Tbyte|Unspecified|BaseIndex }
 fild, 1, 0xdf, 0x0, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
@@ -574,15 +574,15 @@  fldt, 1, 0xdb, 0x5, 1, CpuFP, Modrm|No_b
 fbld, 1, 0xdf, 0x4, 1, CpuFP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf, { Tbyte|Unspecified|BaseIndex }
 
 // store (no pop)
-fst, 1, 0xddd0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fst, 1, 0xddd0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 fst, 1, 0xd9, 0x2, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
-fst, 1, 0xddd0, None, 2, CpuFP, ShortForm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
+fst, 1, 0xddd0, None, 2, CpuFP, IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
 fist, 1, 0xdf, 0x2, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
 // store (with pop)
-fstp, 1, 0xddd8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fstp, 1, 0xddd8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 fstp, 1, 0xd9, 0x3, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
-fstp, 1, 0xddd8, None, 2, CpuFP, ShortForm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
+fstp, 1, 0xddd8, None, 2, CpuFP, IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
 // Intel Syntax
 fstp, 1, 0xdb, 0x7, 1, CpuFP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf, { Tbyte|Unspecified|BaseIndex }
 fistp, 1, 0xdf, 0x3, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
@@ -592,32 +592,32 @@  fstpt, 1, 0xdb, 0x7, 1, CpuFP, Modrm|No_
 fbstp, 1, 0xdf, 0x6, 1, CpuFP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf, { Tbyte|Unspecified|BaseIndex }
 
 // exchange %st<n> with %st0
-fxch, 1, 0xd9c8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fxch, 1, 0xd9c8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fxch %st(1)
 fxch, 0, 0xd9c9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
 // comparison (without pop)
-fcom, 1, 0xd8d0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fcom, 1, 0xd8d0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fcom %st(1)
 fcom, 0, 0xd8d1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 fcom, 1, 0xd8, 0x2, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
-fcom, 1, 0xd8d0, None, 2, CpuFP, ShortForm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
+fcom, 1, 0xd8d0, None, 2, CpuFP, IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
 ficom, 1, 0xde, 0x2, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
 // comparison (with pop)
-fcomp, 1, 0xd8d8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fcomp, 1, 0xd8d8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fcomp %st(1)
 fcomp, 0, 0xd8d9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 fcomp, 1, 0xd8, 0x3, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
-fcomp, 1, 0xd8d8, None, 2, CpuFP, ShortForm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
+fcomp, 1, 0xd8d8, None, 2, CpuFP, IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg }
 ficomp, 1, 0xde, 0x3, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 fcompp, 0, 0xded9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
 // unordered comparison (with pop)
-fucom, 1, 0xdde0, None, 2, Cpu387, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fucom, 1, 0xdde0, None, 2, Cpu387, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fucom %st(1)
 fucom, 0, 0xdde1, None, 2, Cpu387, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fucomp, 1, 0xdde8, None, 2, Cpu387, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fucomp, 1, 0xdde8, None, 2, Cpu387, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fucomp %st(1)
 fucomp, 0, 0xdde9, None, 2, Cpu387, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 fucompp, 0, 0xdae9, None, 2, Cpu387, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
@@ -637,99 +637,99 @@  fldz, 0, 0xd9ee, None, 2, CpuFP, No_bSuf
 // Arithmetic.
 
 // add
-fadd, 2, 0xd8c0, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fadd, 2, 0xd8c0, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
 // alias for fadd %st(i), %st
-fadd, 1, 0xd8c0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fadd, 1, 0xd8c0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for faddp
 fadd, 0, 0xdec1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
 fadd, 1, 0xd8, 0x0, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fiadd, 1, 0xde, 0x0, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-faddp, 2, 0xdec0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatAcc, FloatReg }
-faddp, 1, 0xdec0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+faddp, 2, 0xdec0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatAcc, FloatReg }
+faddp, 1, 0xdec0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for faddp %st, %st(1)
 faddp, 0, 0xdec1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-faddp, 2, 0xdec0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg, FloatAcc }
+faddp, 2, 0xdec0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg, FloatAcc }
 
 // subtract
-fsub, 1, 0xd8e0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fsub, 2, 0xd8e0, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
+fsub, 1, 0xd8e0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fsub, 2, 0xd8e0, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
 // alias for fsubp
 fsub, 0, 0xdee1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic|ATTSyntax, { 0 }
 fsub, 0, 0xdee9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
-fsub, 2, 0xd8e0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm|D|FloatR, { FloatReg, FloatAcc }
+fsub, 2, 0xd8e0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|D|FloatR, { FloatReg, FloatAcc }
 fsub, 1, 0xd8, 0x4, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fisub, 1, 0xde, 0x4, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-fsubp, 2, 0xdee0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
-fsubp, 1, 0xdee0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
+fsubp, 2, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
+fsubp, 1, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
 fsubp, 0, 0xdee1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { 0 }
-fsubp, 2, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatAcc, FloatReg }
-fsubp, 1, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatReg }
+fsubp, 2, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatAcc, FloatReg }
+fsubp, 1, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatReg }
 fsubp, 0, 0xdee9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
 // subtract reverse
-fsubr, 1, 0xd8e8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fsubr, 2, 0xd8e8, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
+fsubr, 1, 0xd8e8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fsubr, 2, 0xd8e8, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
 // alias for fsubrp
 fsubr, 0, 0xdee9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic|ATTSyntax, { 0 }
 fsubr, 0, 0xdee1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
-fsubr, 2, 0xd8e8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm|D|FloatR, { FloatReg, FloatAcc }
+fsubr, 2, 0xd8e8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|D|FloatR, { FloatReg, FloatAcc }
 fsubr, 1, 0xd8, 0x5, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fisubr, 1, 0xde, 0x5, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-fsubrp, 2, 0xdee8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
-fsubrp, 1, 0xdee8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
+fsubrp, 2, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
+fsubrp, 1, 0xdee8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
 fsubrp, 0, 0xdee9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { 0 }
-fsubrp, 2, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatAcc, FloatReg }
-fsubrp, 1, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatReg }
+fsubrp, 2, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatAcc, FloatReg }
+fsubrp, 1, 0xdee0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatReg }
 fsubrp, 0, 0xdee1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { 0 }
 
 // multiply
-fmul, 2, 0xd8c8, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fmul, 1, 0xd8c8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fmul, 2, 0xd8c8, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fmul, 1, 0xd8c8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // alias for fmulp
 fmul, 0, 0xdec9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
 fmul, 1, 0xd8, 0x1, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fimul, 1, 0xde, 0x1, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-fmulp, 2, 0xdec8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatAcc, FloatReg }
-fmulp, 1, 0xdec8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fmulp, 2, 0xdec8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatAcc, FloatReg }
+fmulp, 1, 0xdec8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 fmulp, 0, 0xdec9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fmulp, 2, 0xdec8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg, FloatAcc }
+fmulp, 2, 0xdec8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh, { FloatReg, FloatAcc }
 
 // divide
-fdiv, 1, 0xd8f0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fdiv, 2, 0xd8f0, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
+fdiv, 1, 0xd8f0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fdiv, 2, 0xd8f0, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
 // alias for fdivp
 fdiv, 0, 0xdef1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic|ATTSyntax, { 0 }
 fdiv, 0, 0xdef9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
-fdiv, 2, 0xd8f0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm|D|FloatR, { FloatReg, FloatAcc }
+fdiv, 2, 0xd8f0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|D|FloatR, { FloatReg, FloatAcc }
 fdiv, 1, 0xd8, 0x6, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fidiv, 1, 0xde, 0x6, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-fdivp, 2, 0xdef0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
-fdivp, 1, 0xdef0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
+fdivp, 2, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
+fdivp, 1, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
 fdivp, 0, 0xdef1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { 0 }
-fdivp, 2, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatAcc, FloatReg }
-fdivp, 1, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatReg }
+fdivp, 2, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatAcc, FloatReg }
+fdivp, 1, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatReg }
 fdivp, 0, 0xdef9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { 0 }
 
 // divide reverse
-fdivr, 1, 0xd8f8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fdivr, 2, 0xd8f8, None, 2, CpuFP, ShortForm|D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
+fdivr, 1, 0xd8f8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fdivr, 2, 0xd8f8, None, 2, CpuFP, D|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg, FloatAcc }
 // alias for fdivrp
 fdivr, 0, 0xdef9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic|ATTSyntax, { 0 }
 fdivr, 0, 0xdef1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Ugh|ATTMnemonic, { 0 }
-fdivr, 2, 0xd8f8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm|D|FloatR, { FloatReg, FloatAcc }
+fdivr, 2, 0xd8f8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|D|FloatR, { FloatReg, FloatAcc }
 fdivr, 1, 0xd8, 0x7, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Dword|Qword|Unspecified|BaseIndex }
 fidivr, 1, 0xde, 0x7, 1, CpuFP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
 
-fdivrp, 2, 0xdef8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
-fdivrp, 1, 0xdef8, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
+fdivrp, 2, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatAcc, FloatReg }
+fdivrp, 1, 0xdef8, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { FloatReg }
 fdivrp, 0, 0xdef9, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTMnemonic|ATTSyntax, { 0 }
-fdivrp, 2, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatAcc, FloatReg }
-fdivrp, 1, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf|ShortForm, { FloatReg }
+fdivrp, 2, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatAcc, FloatReg }
+fdivrp, 1, 0xdef0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { FloatReg }
 fdivrp, 0, 0xdef1, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf,	{ 0 }
 
 f2xm1, 0, 0xd9f0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
@@ -782,9 +782,9 @@  fnsetpm, 0, 0xdbe4, None, 2, Cpu287, No_
 fsetpm, 0, 0xdbe4, None, 2, Cpu287, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|FWait, { 0 }
 frstpm, 0, 0xdbe5, None, 2, Cpu287, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
-ffree, 1, 0xddc0, None, 2, CpuFP, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+ffree, 1, 0xddc0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 // P6:free st(i), pop st
-ffreep, 1, 0xdfc0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+ffreep, 1, 0xdfc0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 fnop, 0, 0xd9d0, None, 2, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 fwait, 0, 0x9b, None, 1, CpuFP, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
 
@@ -859,7 +859,7 @@  rex.wrxb, 0, 0x4f, None, 1, Cpu64, No_bS
 
 // 486 extensions.
 
-bswap, 1, 0xfc8, None, 2, Cpu486, ShortForm|No_bSuf|No_wSuf|No_sSuf|No_ldSuf, { Reg32|Reg64 }
+bswap, 1, 0xfc8, None, 2, Cpu486, No_bSuf|No_wSuf|No_sSuf|No_ldSuf, { Reg32|Reg64 }
 xadd, 2, 0xfc0, None, 2, Cpu486, W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 cmpxchg, 2, 0xfb0, None, 2, Cpu486, W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|IsLockable|HLEPrefixOk, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 invd, 0, 0xf08, None, 2, Cpu486, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
@@ -925,37 +925,37 @@  cmovnle, 2, 0xf4f, None, 2, CpuCMOV, Mod
 cmovpe, 2, 0xf4a, None, 2, CpuCMOV, Modrm|CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Reg16|Reg32|Reg64|Word|Dword|Qword|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 cmovpo, 2, 0xf4b, None, 2, CpuCMOV, Modrm|CheckRegSize|No_bSuf|No_sSuf|No_ldSuf, { Reg16|Reg32|Reg64|Word|Dword|Qword|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
 
-fcmovb, 2, 0xdac0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovnae, 2, 0xdac0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmove, 2, 0xdac8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovbe, 2, 0xdad0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovna, 2, 0xdad0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovu, 2, 0xdad8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovae, 2, 0xdbc0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovnb, 2, 0xdbc0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovne, 2, 0xdbc8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmova, 2, 0xdbd0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovnbe, 2, 0xdbd0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcmovnu, 2, 0xdbd8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-
-fcomi, 2, 0xdbf0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcomi, 0, 0xdbf1, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fcomi, 1, 0xdbf0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fucomi, 2, 0xdbe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fucomi, 0, 0xdbe9, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fucomi, 1, 0xdbe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fcomip, 2, 0xdff0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcomip, 0, 0xdff1, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fcomip, 1, 0xdff0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fcompi, 2, 0xdff0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fcompi, 0, 0xdff1, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fcompi, 1, 0xdff0, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fucomip, 2, 0xdfe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fucomip, 0, 0xdfe9, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fucomip, 1, 0xdfe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
-fucompi, 2, 0xdfe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
-fucompi, 0, 0xdfe9, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
-fucompi, 1, 0xdfe8, None, 2, Cpu687, ShortForm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fcmovb, 2, 0xdac0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovnae, 2, 0xdac0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmove, 2, 0xdac8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovbe, 2, 0xdad0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovna, 2, 0xdad0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovu, 2, 0xdad8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovae, 2, 0xdbc0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovnb, 2, 0xdbc0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovne, 2, 0xdbc8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmova, 2, 0xdbd0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovnbe, 2, 0xdbd0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcmovnu, 2, 0xdbd8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+
+fcomi, 2, 0xdbf0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcomi, 0, 0xdbf1, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fcomi, 1, 0xdbf0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fucomi, 2, 0xdbe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fucomi, 0, 0xdbe9, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fucomi, 1, 0xdbe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fcomip, 2, 0xdff0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcomip, 0, 0xdff1, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fcomip, 1, 0xdff0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fcompi, 2, 0xdff0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fcompi, 0, 0xdff1, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fcompi, 1, 0xdff0, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fucomip, 2, 0xdfe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fucomip, 0, 0xdfe9, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fucomip, 1, 0xdfe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
+fucompi, 2, 0xdfe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg, FloatAcc }
+fucompi, 0, 0xdfe9, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { 0 }
+fucompi, 1, 0xdfe8, None, 2, Cpu687, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { FloatReg }
 
 // Pentium4 extensions.
 
@@ -985,7 +985,7 @@  movd, 2, 0xf6e, None, 2, CpuMMX|Cpu64, D
 movq, 2, 0xa1, None, 1, Cpu64, D|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Disp64|Unspecified|Qword, Acc|Qword }
 movq, 2, 0x89, None, 1, Cpu64, D|Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixOk=3, { Reg64, Reg64|Unspecified|Qword|BaseIndex }
 movq, 2, 0xc7, 0x0, 1, Cpu64, Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixOk=3|Optimize, { Imm32S, Reg64|Qword|Unspecified|BaseIndex }
-movq, 2, 0xb8, None, 1, Cpu64, ShortForm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
+movq, 2, 0xb8, None, 1, Cpu64, Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
 movq, 2, 0xf37e, None, 1, CpuAVX, Load|Modrm|Vex=1|VexOpcode=0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 movq, 2, 0x66d6, None, 1, CpuAVX, Modrm|Vex=1|VexOpcode=0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
 movq, 2, 0x666e, None, 1, CpuAVX|Cpu64, D|Modrm|Vex=1|VexOpcode=0|VexW=2|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64|SSE2AVX, { Reg64|Unspecified|BaseIndex, RegXMM }