x86: move some opcode table entries

For a long time there hasn't been a need anymore to keep together all
templates with identical mnemonics. Move the MOVQ and MOVABS ones next
to their MOV counterparts. Move the string forms of CMPSD and MOVSD next
to their CMPS / MOVS counterparts. Re-arrange what so fgar was the SSE3
section.

This makes reasonably obvious that MONITOR/MWAIT aren't suitable to
cover by CpuSSE3, but adjusting this is left for another time.

1 files changed, 31 insertions, 30 deletions

diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl
index 51f206c..0c35848 100644
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -125,12 +125,18 @@
 
 // Move instructions.
 mov, 0xa0, None, 0, D|W|No_sSuf|No_qSuf|No_ldSuf, { Disp16|Disp32|Disp64|Unspecified|Byte|Word|Dword|Qword, Acc|Byte|Word|Dword|Qword }
+movabs, 0xa0, None, Cpu64, D|W|No_sSuf|No_ldSuf, { Disp64|Unspecified|Byte|Word|Dword|Qword, Acc|Byte|Word|Dword|Qword }
+movq, 0xa1, None, Cpu64, D|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Disp64|Unspecified|Qword, Acc|Qword }
 mov, 0x88, None, 0, D|W|CheckRegSize|Modrm|No_sSuf|No_ldSuf|HLEPrefixRelease, { Reg8|Reg16|Reg32|Reg64, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
+movq, 0x89, None, Cpu64, D|Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixRelease, { Reg64, Reg64|Unspecified|Qword|BaseIndex }
 // In the 64bit mode the short form mov immediate is redefined to have
 // 64bit value.
 mov, 0xb0, None, 0, W|No_sSuf|No_qSuf|No_ldSuf, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32 }
 mov, 0xc6, 0, 0, W|Modrm|No_sSuf|No_ldSuf|HLEPrefixRelease|Optimize, { Imm8|Imm16|Imm32|Imm32S, Reg8|Reg16|Reg32|Reg64|Byte|Word|Dword|Qword|Unspecified|BaseIndex }
+movq, 0xc7, 0, Cpu64, Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixRelease|Optimize, { Imm32S, Reg64|Qword|Unspecified|BaseIndex }
 mov, 0xb8, None, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
+movabs, 0xb8, None, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf, { Imm64, Reg64 }
+movq, 0xb8, None, Cpu64, Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|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
@@ -138,16 +144,17 @@ mov, 0xb8, None, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|Optimize, { Imm
 // implementation defined value is zero).
 mov, 0x8c, None, 0, RegMem|No_bSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { SReg, Reg16|Reg32|Reg64 }
 mov, 0x8c, None, 0, D|Modrm|IgnoreSize|No_bSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg, Word|Unspecified|BaseIndex }
+movq, 0x8c, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg, Reg64 }
 mov, 0x8e, None, 0, Modrm|IgnoreSize|No_bSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Reg16|Reg32|Reg64, SReg }
 // Move to/from control debug registers.  In the 16 or 32bit modes
 // they are 32bit.  In the 64bit mode they are 64bit.
 mov, 0xf20, None, Cpu386|CpuNo64, D|RegMem|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf, { Control, Reg32 }
 mov, 0xf20, None, Cpu64, D|RegMem|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Control, Reg64 }
+movq, 0xf20, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Control, Reg64 }
 mov, 0xf21, None, Cpu386|CpuNo64, D|RegMem|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf, { Debug, Reg32 }
 mov, 0xf21, None, Cpu64, D|RegMem|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Debug, Reg64 }
+movq, 0xf21, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Debug, Reg64 }
 mov, 0xf24, None, Cpu386|CpuNo64, D|RegMem|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf|No_ldSuf, { Test, Reg32 }
-movabs, 0xa0, None, Cpu64, D|W|No_sSuf|No_ldSuf, { Disp64|Unspecified|Byte|Word|Dword|Qword, Acc|Byte|Word|Dword|Qword }
-movabs, 0xb8, None, Cpu64, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf, { Imm64, Reg64 }
 
 // Move after swapping the bytes
 movbe, 0x0f38f0, None, CpuMovbe, Modrm|No_bSuf|No_sSuf|No_ldSuf, { Word|Dword|Qword|Unspecified|BaseIndex, Reg16|Reg32|Reg64 }
@@ -477,6 +484,9 @@ set<cc>, 0xf9<cc:opc>, 0, Cpu386, Modrm|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf
 // String manipulation.
 cmps, 0xa6, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, {}
 cmps, 0xa6, None, 0, W|No_sSuf|No_ldSuf|IsStringEsOp0|RepPrefixOk, { Byte|Word|Dword|Qword|Unspecified|BaseIndex, Byte|Word|Dword|Qword|Unspecified|BaseIndex }
+// Intel mode string compare.
+cmpsd, 0xa7, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsString|RepPrefixOk, {}
+cmpsd, 0xa7, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsStringEsOp0|RepPrefixOk, { Dword|Unspecified|BaseIndex, Dword|Unspecified|BaseIndex }
 scmp, 0xa6, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, {}
 scmp, 0xa6, None, 0, W|No_sSuf|No_ldSuf|IsStringEsOp0|RepPrefixOk, { Byte|Word|Dword|Qword|Unspecified|BaseIndex, Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 ins, 0x6c, None, Cpu186, W|No_sSuf|No_qSuf|No_ldSuf|IsString|RepPrefixOk, {}
@@ -491,6 +501,9 @@ slod, 0xac, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, { Byte|Word|Dword|
 slod, 0xac, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, { Byte|Word|Dword|Qword|Unspecified|BaseIndex, Acc|Byte|Word|Dword|Qword }
 movs, 0xa4, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, {}
 movs, 0xa4, None, 0, W|No_sSuf|No_ldSuf|IsStringEsOp1|RepPrefixOk, { Byte|Word|Dword|Qword|Unspecified|BaseIndex, Byte|Word|Dword|Qword|Unspecified|BaseIndex }
+// Intel mode string move.
+movsd, 0xa5, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsString|RepPrefixOk, {}
+movsd, 0xa5, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsStringEsOp1|RepPrefixOk, { Dword|Unspecified|BaseIndex, Dword|Unspecified|BaseIndex }
 smov, 0xa4, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, {}
 smov, 0xa4, None, 0, W|No_sSuf|No_ldSuf|IsStringEsOp1|RepPrefixOk, { Byte|Word|Dword|Qword|Unspecified|BaseIndex, Byte|Word|Dword|Qword|Unspecified|BaseIndex }
 scas, 0xae, None, 0, W|No_sSuf|No_ldSuf|IsString|RepPrefixOk, {}
@@ -965,13 +978,6 @@ movd, 0x660f6e, None, CpuSSE2, D|Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSu
 movd, 0x660f6e, None, CpuSSE2|Cpu64, D|Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64, { Reg64|BaseIndex, RegXMM }
 movd, 0xf6e, None, CpuMMX, D|Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Reg32|Unspecified|BaseIndex, RegMMX }
 movd, 0xf6e, None, CpuMMX|Cpu64, D|Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64, { Reg64|BaseIndex, RegMMX }
-// In the 64bit mode the short form mov immediate is redefined to have
-// 64bit displacement value.  We put the 64bit displacement first and
-// we only mark constants larger than 32bit as Disp64.
-movq, 0xa1, None, Cpu64, D|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Disp64|Unspecified|Qword, Acc|Qword }
-movq, 0x89, None, Cpu64, D|Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixRelease, { Reg64, Reg64|Unspecified|Qword|BaseIndex }
-movq, 0xc7, 0, Cpu64, Modrm|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|HLEPrefixRelease|Optimize, { Imm32S, Reg64|Qword|Unspecified|BaseIndex }
-movq, 0xb8, None, Cpu64, Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Optimize, { Imm64, Reg64 }
 movq, 0xf37e, None, CpuAVX, Load|Modrm|Vex=1|Space0F|VexWIG|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 movq, 0x66d6, None, CpuAVX, Modrm|Vex=1|Space0F|VexWIG|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
 movq, 0x666e, None, CpuAVX|Cpu64, D|Modrm|Vex=1|Space0F|VexW1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64|SSE2AVX, { Reg64|Unspecified|BaseIndex, RegXMM }
@@ -980,14 +986,6 @@ movq, 0x660fd6, None, CpuSSE2, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_
 movq, 0x660f6e, None, CpuSSE2|Cpu64, D|Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64, { Reg64|Unspecified|BaseIndex, RegXMM }
 movq, 0xf6f, None, CpuMMX, D|Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Unspecified|Qword|BaseIndex|RegMMX, RegMMX }
 movq, 0xf6e, None, CpuMMX|Cpu64, D|Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64, { Reg64|Unspecified|BaseIndex, RegMMX }
-// The segment register moves accept Reg64 so that a segment register
-// can be copied to a 64 bit register, and vice versa.
-movq, 0x8c, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { SReg, Reg64 }
-// Move to/from control debug registers.  In the 16 or 32bit modes they
-// are 32bit.  In the 64bit mode they are 64bit.
-movq, 0xf20, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Control, Reg64 }
-movq, 0xf21, None, Cpu64, D|RegMem|Size64|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Debug, Reg64 }
-// Real MMX/SSE instructions.
 packssdw<mmx>, 0x<mmx:pfx>0f6b, None, <mmx:cpu>, Modrm|<mmx:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
 packsswb<mmx>, 0x<mmx:pfx>0f63, None, <mmx:cpu>, Modrm|<mmx:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
 packuswb<mmx>, 0x<mmx:pfx>0f67, None, <mmx:cpu>, Modrm|<mmx:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
@@ -1158,9 +1156,6 @@ andpd<sse2>, 0x660f54, None, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|<sse2:com
 cmp<sse_frel>pd<sse2>, 0x660fc2, <sse_frel:imm>, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|<sse_frel:comm>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
 cmp<sse_frel>sd<sse2>, 0xf20fc2, <sse_frel:imm>, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|<sse_frel:comm>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ImmExt, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
 cmppd<sse2>, 0x660fc2, None, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
-// Intel mode string compare.
-cmpsd, 0xa7, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsString|RepPrefixOk, {}
-cmpsd, 0xa7, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsStringEsOp0|RepPrefixOk, { Dword|Unspecified|BaseIndex, Dword|Unspecified|BaseIndex }
 cmpsd<sse2>, 0xf20fc2, None, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 comisd<sse2>, 0x660f2f, None, <sse2:cpu>, Modrm|<sse2:scal>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
 cvtpi2pd, 0x660f2a, None, CpuSSE2, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64|NoAVX, { RegMMX, RegXMM }
@@ -1186,9 +1181,6 @@ movlpd, 0x6613, None, CpuAVX, Modrm|Vex|Space0F|VexW=1|IgnoreSize|No_bSuf|No_wSu
 movlpd, 0x660f12, None, CpuSSE2, D|Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex, RegXMM }
 movmskpd<sse2>, 0x660f50, None, <sse2:cpu>, Modrm|<sse2:attr>|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_ldSuf|NoRex64, { RegXMM, Reg32|Reg64 }
 movntpd<sse2>, 0x660f2b, None, <sse2:cpu>, Modrm|<sse2:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
-// Intel mode string move.
-movsd, 0xa5, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsString|RepPrefixOk, {}
-movsd, 0xa5, None, 0, Size32|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IsStringEsOp1|RepPrefixOk, { Dword|Unspecified|BaseIndex, Dword|Unspecified|BaseIndex }
 movsd, 0xf210, None, CpuAVX, D|Modrm|Vex=3|Space0F|VexW=1|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
 movsd, 0xf210, None, CpuAVX, D|Modrm|Vex=3|Space0F|VexVVVV=1|VexW=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SSE2AVX, { RegXMM, RegXMM }
 movsd, 0xf20f10, None, CpuSSE2, D|Modrm|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
@@ -1243,15 +1235,27 @@ punpcklqdq<sse2>, 0x660f6c, None, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|No_b
 
 addsubpd<sse3>, 0x660fd0, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 addsubps<sse3>, 0xf20fd0, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
-cmpxchg16b, 0xfc7, 1, CpuCX16|Cpu64, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64|LockPrefixOk, { Oword|Unspecified|BaseIndex }
-fisttp, 0xdf, 1, CpuFISTTP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
-fisttp, 0xdd, 1, CpuFISTTP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Qword|Unspecified|BaseIndex }
-fisttpll, 0xdd, 1, CpuFISTTP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Unspecified|BaseIndex }
 haddpd<sse3>, 0x660f7c, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 haddps<sse3>, 0xf20f7c, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 hsubpd<sse3>, 0x660f7d, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 hsubps<sse3>, 0xf20f7d, None, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 lddqu<sse3>, 0xf20ff0, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
+movddup<sse3>, 0xf20f12, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
+movshdup<sse3>, 0xf30f16, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+movsldup<sse3>, 0xf30f12, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
+
+// FPU instructions also covered by SSE3 CPUID flag.
+
+fisttp, 0xdf, 1, CpuFISTTP, Modrm|FloatMF|No_bSuf|No_wSuf|No_qSuf|No_ldSuf, { Word|Dword|Unspecified|BaseIndex }
+fisttp, 0xdd, 1, CpuFISTTP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_ldSuf|NoRex64, { Qword|Unspecified|BaseIndex }
+fisttpll, 0xdd, 1, CpuFISTTP, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Unspecified|BaseIndex }
+
+// CMPXCHG16B instruction.
+
+cmpxchg16b, 0xfc7, 1, CpuCX16|Cpu64, Modrm|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|Size64|LockPrefixOk, { Oword|Unspecified|BaseIndex }
+
+// MONITOR instructions.
+
 monitor, 0xf01c8, None, CpuSSE3, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoAVX, {}
 // monitor is very special. CX and DX are always 32 bits. The
 // address size override prefix can be used to overrride the AX size in
@@ -1259,9 +1263,6 @@ monitor, 0xf01c8, None, CpuSSE3, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSu
 monitor, 0xf01c8, None, CpuSSE3, AddrPrefixOpReg|NoAVX, { Acc|Word|Dword|Qword, RegC|Dword, RegD|Dword }
 // The 64-bit form exists only for compatibility with older gas.
 monitor, 0xf01c8, None, CpuSSE3|Cpu64, AddrPrefixOpReg|NoAVX, { Acc|Dword|Qword, RegC|Qword, RegD|Qword }
-movddup<sse3>, 0xf20f12, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoRex64, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
-movshdup<sse3>, 0xf30f16, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
-movsldup<sse3>, 0xf30f12, None, <sse3:cpu>, Modrm|<sse3:attr>|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
 mwait, 0xf01c9, None, CpuSSE3, No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|NoAVX, {}
 // mwait is very special. AX and CX are always 32 bits.
 // The 64-bit form exists only for compatibility with older gas.