x86: make D attribute usable for XOP and FMA4 insns

This once again allows to reduce redundancy in (and size of) the opcode
table.

Don't go as far as also making D work on the two 5-operand XOP insns:
This would significantly complicate the code, as there the first
(immediate) operand would need special treatment in several places.

Note that the .s suffix isn't being enabled to have any effect, for
being deprecated. Whereas neither {load} nor {store} pseudo prefixes
make sense here, as the respective operands are inputs (loads) only
anyway, regardless of order. Hence there is (as before) no way for the
programmer to request the alternative encoding to be used for register-
only insns.

Note further that it is always the first original template which is
retained (and altered), to make sure the same encoding as before is
used for register-only insns. This has the slightly odd (but pre-
existing) effect of XOP register-only insns having XOP.W clear, but FMA4
ones having VEX.W set.
This commit is contained in:
Jan Beulich
2022-07-06 15:40:04 +02:00
parent 3d0738af2a
commit 8bd915b770
4 changed files with 186 additions and 802 deletions

View File

@ -2087,12 +2087,18 @@ operand_size_match (const insn_template *t)
}
/* Check reverse. */
gas_assert (i.operands >= 2 && i.operands <= 3);
gas_assert ((i.operands >= 2 && i.operands <= 3)
|| t->opcode_modifier.vexsources);
for (j = 0; j < i.operands; j++)
{
unsigned int given = i.operands - j - 1;
/* For 4- and 5-operand insns VEX.W controls just the first two
register operands. */
if (t->opcode_modifier.vexsources)
given = j < 2 ? 1 - j : j;
if (t->operand_types[j].bitfield.class == Reg
&& !match_operand_size (t, j, given))
goto mismatch;
@ -6722,18 +6728,19 @@ match_template (char mnem_suffix)
if (!(size_match & MATCH_REVERSE))
continue;
/* Try reversing direction of operands. */
overlap0 = operand_type_and (i.types[0], operand_types[i.operands - 1]);
overlap1 = operand_type_and (i.types[i.operands - 1], operand_types[0]);
j = t->opcode_modifier.vexsources ? 1 : i.operands - 1;
overlap0 = operand_type_and (i.types[0], operand_types[j]);
overlap1 = operand_type_and (i.types[j], operand_types[0]);
overlap2 = operand_type_and (i.types[1], operand_types[1]);
gas_assert (t->operands != 3 || !check_register);
if (!operand_type_match (overlap0, i.types[0])
|| !operand_type_match (overlap1, i.types[i.operands - 1])
|| !operand_type_match (overlap1, i.types[j])
|| (t->operands == 3
&& !operand_type_match (overlap2, i.types[1]))
|| (check_register
&& !operand_type_register_match (i.types[0],
operand_types[i.operands - 1],
i.types[i.operands - 1],
operand_types[j],
i.types[j],
operand_types[0])))
{
/* Does not match either direction. */
@ -6745,6 +6752,11 @@ match_template (char mnem_suffix)
found_reverse_match = 0;
else if (operand_types[0].bitfield.tbyte)
found_reverse_match = Opcode_FloatD;
else if (t->opcode_modifier.vexsources)
{
found_reverse_match = Opcode_VexW;
goto check_operands_345;
}
else if (operand_types[0].bitfield.xmmword
|| operand_types[i.operands - 1].bitfield.xmmword
|| operand_types[0].bitfield.class == RegMMX
@ -6760,6 +6772,7 @@ match_template (char mnem_suffix)
else
{
/* Found a forward 2 operand match here. */
check_operands_345:
switch (t->operands)
{
case 5:
@ -6928,8 +6941,12 @@ match_template (char mnem_suffix)
i.tm.operand_types[addr_prefix_disp]
= operand_types[addr_prefix_disp];
if (found_reverse_match)
switch (found_reverse_match)
{
case 0:
break;
default:
/* If we found a reverse match we must alter the opcode direction
bit and clear/flip the regmem modifier one. found_reverse_match
holds bits to change (different for int & float insns). */
@ -6946,6 +6963,17 @@ match_template (char mnem_suffix)
= i.tm.opcode_modifier.modrm && i.tm.opcode_modifier.d
&& i.tm.operands > 2U - i.tm.opcode_modifier.sse2avx
&& !i.tm.opcode_modifier.regmem;
break;
case Opcode_VexW:
/* Only the first two register operands need reversing, alongside
flipping VEX.W. */
i.tm.opcode_modifier.vexw ^= VEXW0 ^ VEXW1;
j = i.tm.operand_types[0].bitfield.imm8;
i.tm.operand_types[j] = operand_types[j + 1];
i.tm.operand_types[j + 1] = operand_types[j];
break;
}
return t;

View File

@ -925,6 +925,9 @@ typedef struct insn_template
#define Opcode_FloatD 0x400 /* Direction bit for float insns. */
#define Opcode_SIMD_FloatD 0x1 /* Direction bit for SIMD fp insns. */
#define Opcode_SIMD_IntD 0x10 /* Direction bit for SIMD int insns. */
/* The next value is arbitrary, as long as it's non-zero and distinct
from all other values above. */
#define Opcode_VexW 0xf /* Operand order controlled by VEX.W. */
/* (Fake) base opcode value for pseudo prefixes. */
#define PSEUDO_PREFIX 0

View File

@ -1928,46 +1928,26 @@ shrx, 0xf2f7, None, CpuBMI2, Modrm|CheckRegSize|Vex128|Space0F38|VexVVVV=1|SwapS
// FMA4 instructions
vfmaddpd, 0x6669, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddpd, 0x6669, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddps, 0x6668, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddps, 0x6668, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsd, 0x666b, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmaddsd, 0x666b, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfmaddss, 0x666a, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmaddss, 0x666a, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfmaddsubpd, 0x665d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsubpd, 0x665d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsubps, 0x665c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsubps, 0x665c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddpd, 0x665f, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddpd, 0x665f, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddps, 0x665e, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddps, 0x665e, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubpd, 0x666d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubpd, 0x666d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubps, 0x666c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubps, 0x666c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubsd, 0x666f, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmsubsd, 0x666f, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfmsubss, 0x666e, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmsubss, 0x666e, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfnmaddpd, 0x6679, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddpd, 0x6679, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddps, 0x6678, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddps, 0x6678, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddsd, 0x667b, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmaddsd, 0x667b, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfnmaddss, 0x667a, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmaddss, 0x667a, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfnmsubpd, 0x667d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubpd, 0x667d, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubps, 0x667c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=2|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubps, 0x667c, None, CpuFMA4, Modrm|Vex|Space0F3A|VexVVVV=1|VexW=1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubsd, 0x667f, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmsubsd, 0x667f, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfnmsubss, 0x667e, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmsubss, 0x667e, None, CpuFMA4, Modrm|VexLIG|Space0F3A|VexVVVV|VexW0|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM }
vfmaddpd, 0x6669, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddps, 0x6668, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsd, 0x666b, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmaddss, 0x666a, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmaddsubpd, 0x665d, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmaddsubps, 0x665c, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddpd, 0x665f, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubaddps, 0x665e, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubpd, 0x666d, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubps, 0x666c, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfmsubsd, 0x666f, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfmsubss, 0x666e, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmaddpd, 0x6679, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddps, 0x6678, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmaddsd, 0x667b, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmaddss, 0x667a, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmsubpd, 0x667d, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubps, 0x667c, None, CpuFMA4, D|Modrm|Vex|Space0F3A|VexVVVV|VexW1|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, {Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vfnmsubsd, 0x667f, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
vfnmsubss, 0x667e, None, CpuFMA4, D|Modrm|VexLIG|Space0F3A|VexVVVV|VexW1|VexSources=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM, RegXMM, RegXMM }
// XOP instructions
@ -1979,8 +1959,7 @@ vfrczpd, 0x81, None, CpuXOP, Modrm|SpaceXOP09|VexW=1|CheckRegSize|No_bSuf|No_wSu
vfrczps, 0x80, None, CpuXOP, Modrm|SpaceXOP09|VexW=1|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM }
vfrczsd, 0x83, None, CpuXOP, Modrm|SpaceXOP09|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { Qword|RegXMM|Unspecified|BaseIndex, RegXMM }
vfrczss, 0x82, None, CpuXOP, Modrm|SpaceXOP09|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { Dword|RegXMM|Unspecified|BaseIndex, RegXMM }
vpcmov, 0xa2, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vpcmov, 0xa2, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vpcmov, 0xa2, None, CpuXOP, D|Modrm|SpaceXOP08|VexSources=2|VexVVVV|VexW0|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vpcom<xop_sign><xop_elem>, 0xcc | 0x<xop_sign:opc> | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP08|VexVVVV|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpcom<xop_irel><xop_sign><xop_elem>, 0xcc | 0x<xop_sign:opc> | <xop_elem:opc>, <xop_irel:imm>, CpuXOP, Modrm|Vex128|SpaceXOP08|VexVVVV|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpermil2pd, 0x6649, None, CpuXOP, Modrm|Space0F3A|VexVVVV=1|VexW=1|Vex|VexSources=2|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|RegYMM, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
@ -2014,15 +1993,11 @@ vpmacswd, 0x96, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|No_
vpmacsww, 0x95, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpmadcsswd, 0xa6, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpmadcswd, 0xb6, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpperm, 0xa3, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpperm, 0xa3, None, CpuXOP, Modrm|SpaceXOP08|VexSources=2|VexVVVV=1|VexW=2|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM, RegXMM }
vprot<xop_elem>, 0x90 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
vprot<xop_elem>, 0x90 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW1|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpperm, 0xa3, None, CpuXOP, D|Modrm|SpaceXOP08|VexSources=2|VexVVVV|VexW0|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Vex, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vprot<xop_elem>, 0x90 | <xop_elem:opc>, None, CpuXOP, D|Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
vprot<xop_elem>, 0xc0 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP08|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
vpsha<xop_elem>, 0x98 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
vpsha<xop_elem>, 0x98 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW1|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpshl<xop_elem>, 0x94 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
vpshl<xop_elem>, 0x94 | <xop_elem:opc>, None, CpuXOP, Modrm|Vex128|SpaceXOP09|VexW1|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM|Unspecified|BaseIndex, RegXMM, RegXMM }
vpsha<xop_elem>, 0x98 | <xop_elem:opc>, None, CpuXOP, D|Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
vpshl<xop_elem>, 0x94 | <xop_elem:opc>, None, CpuXOP, D|Modrm|Vex128|SpaceXOP09|VexW0|VexSources=1|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|No_qSuf, { RegXMM, RegXMM|Unspecified|BaseIndex, RegXMM }
// LWP instructions

File diff suppressed because it is too large Load Diff