2015-08-13 14:14:55 +07:00
|
|
|
# x86 Opcode Maps
|
|
|
|
|
#
|
|
|
|
|
# This is (mostly) based on following documentations.
|
|
|
|
|
# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
|
|
|
|
|
# (#326018-047US, June 2013)
|
|
|
|
|
#
|
|
|
|
|
#<Opcode maps>
|
|
|
|
|
# Table: table-name
|
|
|
|
|
# Referrer: escaped-name
|
|
|
|
|
# AVXcode: avx-code
|
|
|
|
|
# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
|
|
|
|
|
# (or)
|
|
|
|
|
# opcode: escape # escaped-name
|
|
|
|
|
# EndTable
|
|
|
|
|
#
|
2016-07-20 15:30:36 +07:00
|
|
|
# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
|
|
|
|
|
# mnemonics that begin with lowercase 'k' accept a VEX prefix
|
|
|
|
|
#
|
2015-08-13 14:14:55 +07:00
|
|
|
#<group maps>
|
|
|
|
|
# GrpTable: GrpXXX
|
|
|
|
|
# reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
|
|
|
|
|
# EndTable
|
|
|
|
|
#
|
|
|
|
|
# AVX Superscripts
|
2016-07-20 15:30:36 +07:00
|
|
|
# (ev): this opcode requires EVEX prefix.
|
|
|
|
|
# (evo): this opcode is changed by EVEX prefix (EVEX opcode)
|
2015-08-13 14:14:55 +07:00
|
|
|
# (v): this opcode requires VEX prefix.
|
|
|
|
|
# (v1): this opcode only supports 128bit VEX.
|
|
|
|
|
#
|
|
|
|
|
# Last Prefix Superscripts
|
|
|
|
|
# - (66): the last prefix is 0x66
|
|
|
|
|
# - (F3): the last prefix is 0xF3
|
|
|
|
|
# - (F2): the last prefix is 0xF2
|
|
|
|
|
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
|
|
|
|
|
# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
|
|
|
|
|
|
|
|
|
|
Table: one byte opcode
|
|
|
|
|
Referrer:
|
|
|
|
|
AVXcode:
|
|
|
|
|
# 0x00 - 0x0f
|
|
|
|
|
00: ADD Eb,Gb
|
|
|
|
|
01: ADD Ev,Gv
|
|
|
|
|
02: ADD Gb,Eb
|
|
|
|
|
03: ADD Gv,Ev
|
|
|
|
|
04: ADD AL,Ib
|
|
|
|
|
05: ADD rAX,Iz
|
|
|
|
|
06: PUSH ES (i64)
|
|
|
|
|
07: POP ES (i64)
|
|
|
|
|
08: OR Eb,Gb
|
|
|
|
|
09: OR Ev,Gv
|
|
|
|
|
0a: OR Gb,Eb
|
|
|
|
|
0b: OR Gv,Ev
|
|
|
|
|
0c: OR AL,Ib
|
|
|
|
|
0d: OR rAX,Iz
|
|
|
|
|
0e: PUSH CS (i64)
|
|
|
|
|
0f: escape # 2-byte escape
|
|
|
|
|
# 0x10 - 0x1f
|
|
|
|
|
10: ADC Eb,Gb
|
|
|
|
|
11: ADC Ev,Gv
|
|
|
|
|
12: ADC Gb,Eb
|
|
|
|
|
13: ADC Gv,Ev
|
|
|
|
|
14: ADC AL,Ib
|
|
|
|
|
15: ADC rAX,Iz
|
|
|
|
|
16: PUSH SS (i64)
|
|
|
|
|
17: POP SS (i64)
|
|
|
|
|
18: SBB Eb,Gb
|
|
|
|
|
19: SBB Ev,Gv
|
|
|
|
|
1a: SBB Gb,Eb
|
|
|
|
|
1b: SBB Gv,Ev
|
|
|
|
|
1c: SBB AL,Ib
|
|
|
|
|
1d: SBB rAX,Iz
|
|
|
|
|
1e: PUSH DS (i64)
|
|
|
|
|
1f: POP DS (i64)
|
|
|
|
|
# 0x20 - 0x2f
|
|
|
|
|
20: AND Eb,Gb
|
|
|
|
|
21: AND Ev,Gv
|
|
|
|
|
22: AND Gb,Eb
|
|
|
|
|
23: AND Gv,Ev
|
|
|
|
|
24: AND AL,Ib
|
|
|
|
|
25: AND rAx,Iz
|
|
|
|
|
26: SEG=ES (Prefix)
|
|
|
|
|
27: DAA (i64)
|
|
|
|
|
28: SUB Eb,Gb
|
|
|
|
|
29: SUB Ev,Gv
|
|
|
|
|
2a: SUB Gb,Eb
|
|
|
|
|
2b: SUB Gv,Ev
|
|
|
|
|
2c: SUB AL,Ib
|
|
|
|
|
2d: SUB rAX,Iz
|
|
|
|
|
2e: SEG=CS (Prefix)
|
|
|
|
|
2f: DAS (i64)
|
|
|
|
|
# 0x30 - 0x3f
|
|
|
|
|
30: XOR Eb,Gb
|
|
|
|
|
31: XOR Ev,Gv
|
|
|
|
|
32: XOR Gb,Eb
|
|
|
|
|
33: XOR Gv,Ev
|
|
|
|
|
34: XOR AL,Ib
|
|
|
|
|
35: XOR rAX,Iz
|
|
|
|
|
36: SEG=SS (Prefix)
|
|
|
|
|
37: AAA (i64)
|
|
|
|
|
38: CMP Eb,Gb
|
|
|
|
|
39: CMP Ev,Gv
|
|
|
|
|
3a: CMP Gb,Eb
|
|
|
|
|
3b: CMP Gv,Ev
|
|
|
|
|
3c: CMP AL,Ib
|
|
|
|
|
3d: CMP rAX,Iz
|
|
|
|
|
3e: SEG=DS (Prefix)
|
|
|
|
|
3f: AAS (i64)
|
|
|
|
|
# 0x40 - 0x4f
|
|
|
|
|
40: INC eAX (i64) | REX (o64)
|
|
|
|
|
41: INC eCX (i64) | REX.B (o64)
|
|
|
|
|
42: INC eDX (i64) | REX.X (o64)
|
|
|
|
|
43: INC eBX (i64) | REX.XB (o64)
|
|
|
|
|
44: INC eSP (i64) | REX.R (o64)
|
|
|
|
|
45: INC eBP (i64) | REX.RB (o64)
|
|
|
|
|
46: INC eSI (i64) | REX.RX (o64)
|
|
|
|
|
47: INC eDI (i64) | REX.RXB (o64)
|
|
|
|
|
48: DEC eAX (i64) | REX.W (o64)
|
|
|
|
|
49: DEC eCX (i64) | REX.WB (o64)
|
|
|
|
|
4a: DEC eDX (i64) | REX.WX (o64)
|
|
|
|
|
4b: DEC eBX (i64) | REX.WXB (o64)
|
|
|
|
|
4c: DEC eSP (i64) | REX.WR (o64)
|
|
|
|
|
4d: DEC eBP (i64) | REX.WRB (o64)
|
|
|
|
|
4e: DEC eSI (i64) | REX.WRX (o64)
|
|
|
|
|
4f: DEC eDI (i64) | REX.WRXB (o64)
|
|
|
|
|
# 0x50 - 0x5f
|
|
|
|
|
50: PUSH rAX/r8 (d64)
|
|
|
|
|
51: PUSH rCX/r9 (d64)
|
|
|
|
|
52: PUSH rDX/r10 (d64)
|
|
|
|
|
53: PUSH rBX/r11 (d64)
|
|
|
|
|
54: PUSH rSP/r12 (d64)
|
|
|
|
|
55: PUSH rBP/r13 (d64)
|
|
|
|
|
56: PUSH rSI/r14 (d64)
|
|
|
|
|
57: PUSH rDI/r15 (d64)
|
|
|
|
|
58: POP rAX/r8 (d64)
|
|
|
|
|
59: POP rCX/r9 (d64)
|
|
|
|
|
5a: POP rDX/r10 (d64)
|
|
|
|
|
5b: POP rBX/r11 (d64)
|
|
|
|
|
5c: POP rSP/r12 (d64)
|
|
|
|
|
5d: POP rBP/r13 (d64)
|
|
|
|
|
5e: POP rSI/r14 (d64)
|
|
|
|
|
5f: POP rDI/r15 (d64)
|
|
|
|
|
# 0x60 - 0x6f
|
|
|
|
|
60: PUSHA/PUSHAD (i64)
|
|
|
|
|
61: POPA/POPAD (i64)
|
2016-07-20 15:30:36 +07:00
|
|
|
62: BOUND Gv,Ma (i64) | EVEX (Prefix)
|
2015-08-13 14:14:55 +07:00
|
|
|
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
|
|
|
|
|
64: SEG=FS (Prefix)
|
|
|
|
|
65: SEG=GS (Prefix)
|
|
|
|
|
66: Operand-Size (Prefix)
|
|
|
|
|
67: Address-Size (Prefix)
|
|
|
|
|
68: PUSH Iz (d64)
|
|
|
|
|
69: IMUL Gv,Ev,Iz
|
|
|
|
|
6a: PUSH Ib (d64)
|
|
|
|
|
6b: IMUL Gv,Ev,Ib
|
|
|
|
|
6c: INS/INSB Yb,DX
|
|
|
|
|
6d: INS/INSW/INSD Yz,DX
|
|
|
|
|
6e: OUTS/OUTSB DX,Xb
|
|
|
|
|
6f: OUTS/OUTSW/OUTSD DX,Xz
|
|
|
|
|
# 0x70 - 0x7f
|
|
|
|
|
70: JO Jb
|
|
|
|
|
71: JNO Jb
|
|
|
|
|
72: JB/JNAE/JC Jb
|
|
|
|
|
73: JNB/JAE/JNC Jb
|
|
|
|
|
74: JZ/JE Jb
|
|
|
|
|
75: JNZ/JNE Jb
|
|
|
|
|
76: JBE/JNA Jb
|
|
|
|
|
77: JNBE/JA Jb
|
|
|
|
|
78: JS Jb
|
|
|
|
|
79: JNS Jb
|
|
|
|
|
7a: JP/JPE Jb
|
|
|
|
|
7b: JNP/JPO Jb
|
|
|
|
|
7c: JL/JNGE Jb
|
|
|
|
|
7d: JNL/JGE Jb
|
|
|
|
|
7e: JLE/JNG Jb
|
|
|
|
|
7f: JNLE/JG Jb
|
|
|
|
|
# 0x80 - 0x8f
|
|
|
|
|
80: Grp1 Eb,Ib (1A)
|
|
|
|
|
81: Grp1 Ev,Iz (1A)
|
|
|
|
|
82: Grp1 Eb,Ib (1A),(i64)
|
|
|
|
|
83: Grp1 Ev,Ib (1A)
|
|
|
|
|
84: TEST Eb,Gb
|
|
|
|
|
85: TEST Ev,Gv
|
|
|
|
|
86: XCHG Eb,Gb
|
|
|
|
|
87: XCHG Ev,Gv
|
|
|
|
|
88: MOV Eb,Gb
|
|
|
|
|
89: MOV Ev,Gv
|
|
|
|
|
8a: MOV Gb,Eb
|
|
|
|
|
8b: MOV Gv,Ev
|
|
|
|
|
8c: MOV Ev,Sw
|
|
|
|
|
8d: LEA Gv,M
|
|
|
|
|
8e: MOV Sw,Ew
|
|
|
|
|
8f: Grp1A (1A) | POP Ev (d64)
|
|
|
|
|
# 0x90 - 0x9f
|
|
|
|
|
90: NOP | PAUSE (F3) | XCHG r8,rAX
|
|
|
|
|
91: XCHG rCX/r9,rAX
|
|
|
|
|
92: XCHG rDX/r10,rAX
|
|
|
|
|
93: XCHG rBX/r11,rAX
|
|
|
|
|
94: XCHG rSP/r12,rAX
|
|
|
|
|
95: XCHG rBP/r13,rAX
|
|
|
|
|
96: XCHG rSI/r14,rAX
|
|
|
|
|
97: XCHG rDI/r15,rAX
|
|
|
|
|
98: CBW/CWDE/CDQE
|
|
|
|
|
99: CWD/CDQ/CQO
|
|
|
|
|
9a: CALLF Ap (i64)
|
|
|
|
|
9b: FWAIT/WAIT
|
|
|
|
|
9c: PUSHF/D/Q Fv (d64)
|
|
|
|
|
9d: POPF/D/Q Fv (d64)
|
|
|
|
|
9e: SAHF
|
|
|
|
|
9f: LAHF
|
|
|
|
|
# 0xa0 - 0xaf
|
|
|
|
|
a0: MOV AL,Ob
|
|
|
|
|
a1: MOV rAX,Ov
|
|
|
|
|
a2: MOV Ob,AL
|
|
|
|
|
a3: MOV Ov,rAX
|
|
|
|
|
a4: MOVS/B Yb,Xb
|
|
|
|
|
a5: MOVS/W/D/Q Yv,Xv
|
|
|
|
|
a6: CMPS/B Xb,Yb
|
|
|
|
|
a7: CMPS/W/D Xv,Yv
|
|
|
|
|
a8: TEST AL,Ib
|
|
|
|
|
a9: TEST rAX,Iz
|
|
|
|
|
aa: STOS/B Yb,AL
|
|
|
|
|
ab: STOS/W/D/Q Yv,rAX
|
|
|
|
|
ac: LODS/B AL,Xb
|
|
|
|
|
ad: LODS/W/D/Q rAX,Xv
|
|
|
|
|
ae: SCAS/B AL,Yb
|
|
|
|
|
# Note: The May 2011 Intel manual shows Xv for the second parameter of the
|
|
|
|
|
# next instruction but Yv is correct
|
|
|
|
|
af: SCAS/W/D/Q rAX,Yv
|
|
|
|
|
# 0xb0 - 0xbf
|
|
|
|
|
b0: MOV AL/R8L,Ib
|
|
|
|
|
b1: MOV CL/R9L,Ib
|
|
|
|
|
b2: MOV DL/R10L,Ib
|
|
|
|
|
b3: MOV BL/R11L,Ib
|
|
|
|
|
b4: MOV AH/R12L,Ib
|
|
|
|
|
b5: MOV CH/R13L,Ib
|
|
|
|
|
b6: MOV DH/R14L,Ib
|
|
|
|
|
b7: MOV BH/R15L,Ib
|
|
|
|
|
b8: MOV rAX/r8,Iv
|
|
|
|
|
b9: MOV rCX/r9,Iv
|
|
|
|
|
ba: MOV rDX/r10,Iv
|
|
|
|
|
bb: MOV rBX/r11,Iv
|
|
|
|
|
bc: MOV rSP/r12,Iv
|
|
|
|
|
bd: MOV rBP/r13,Iv
|
|
|
|
|
be: MOV rSI/r14,Iv
|
|
|
|
|
bf: MOV rDI/r15,Iv
|
|
|
|
|
# 0xc0 - 0xcf
|
|
|
|
|
c0: Grp2 Eb,Ib (1A)
|
|
|
|
|
c1: Grp2 Ev,Ib (1A)
|
|
|
|
|
c2: RETN Iw (f64)
|
|
|
|
|
c3: RETN
|
|
|
|
|
c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
|
|
|
|
|
c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
|
|
|
|
|
c6: Grp11A Eb,Ib (1A)
|
|
|
|
|
c7: Grp11B Ev,Iz (1A)
|
|
|
|
|
c8: ENTER Iw,Ib
|
|
|
|
|
c9: LEAVE (d64)
|
|
|
|
|
ca: RETF Iw
|
|
|
|
|
cb: RETF
|
|
|
|
|
cc: INT3
|
|
|
|
|
cd: INT Ib
|
|
|
|
|
ce: INTO (i64)
|
|
|
|
|
cf: IRET/D/Q
|
|
|
|
|
# 0xd0 - 0xdf
|
|
|
|
|
d0: Grp2 Eb,1 (1A)
|
|
|
|
|
d1: Grp2 Ev,1 (1A)
|
|
|
|
|
d2: Grp2 Eb,CL (1A)
|
|
|
|
|
d3: Grp2 Ev,CL (1A)
|
|
|
|
|
d4: AAM Ib (i64)
|
|
|
|
|
d5: AAD Ib (i64)
|
|
|
|
|
d6:
|
|
|
|
|
d7: XLAT/XLATB
|
|
|
|
|
d8: ESC
|
|
|
|
|
d9: ESC
|
|
|
|
|
da: ESC
|
|
|
|
|
db: ESC
|
|
|
|
|
dc: ESC
|
|
|
|
|
dd: ESC
|
|
|
|
|
de: ESC
|
|
|
|
|
df: ESC
|
|
|
|
|
# 0xe0 - 0xef
|
|
|
|
|
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
|
|
|
|
|
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
|
|
|
|
|
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
|
|
|
|
|
e0: LOOPNE/LOOPNZ Jb (f64)
|
|
|
|
|
e1: LOOPE/LOOPZ Jb (f64)
|
|
|
|
|
e2: LOOP Jb (f64)
|
|
|
|
|
e3: JrCXZ Jb (f64)
|
|
|
|
|
e4: IN AL,Ib
|
|
|
|
|
e5: IN eAX,Ib
|
|
|
|
|
e6: OUT Ib,AL
|
|
|
|
|
e7: OUT Ib,eAX
|
|
|
|
|
# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
|
|
|
|
|
# in "near" jumps and calls is 16-bit. For CALL,
|
|
|
|
|
# push of return address is 16-bit wide, RSP is decremented by 2
|
|
|
|
|
# but is not truncated to 16 bits, unlike RIP.
|
|
|
|
|
e8: CALL Jz (f64)
|
|
|
|
|
e9: JMP-near Jz (f64)
|
|
|
|
|
ea: JMP-far Ap (i64)
|
|
|
|
|
eb: JMP-short Jb (f64)
|
|
|
|
|
ec: IN AL,DX
|
|
|
|
|
ed: IN eAX,DX
|
|
|
|
|
ee: OUT DX,AL
|
|
|
|
|
ef: OUT DX,eAX
|
|
|
|
|
# 0xf0 - 0xff
|
|
|
|
|
f0: LOCK (Prefix)
|
|
|
|
|
f1:
|
|
|
|
|
f2: REPNE (Prefix) | XACQUIRE (Prefix)
|
|
|
|
|
f3: REP/REPE (Prefix) | XRELEASE (Prefix)
|
|
|
|
|
f4: HLT
|
|
|
|
|
f5: CMC
|
|
|
|
|
f6: Grp3_1 Eb (1A)
|
|
|
|
|
f7: Grp3_2 Ev (1A)
|
|
|
|
|
f8: CLC
|
|
|
|
|
f9: STC
|
|
|
|
|
fa: CLI
|
|
|
|
|
fb: STI
|
|
|
|
|
fc: CLD
|
|
|
|
|
fd: STD
|
|
|
|
|
fe: Grp4 (1A)
|
|
|
|
|
ff: Grp5 (1A)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
Table: 2-byte opcode (0x0f)
|
|
|
|
|
Referrer: 2-byte escape
|
|
|
|
|
AVXcode: 1
|
|
|
|
|
# 0x0f 0x00-0x0f
|
|
|
|
|
00: Grp6 (1A)
|
|
|
|
|
01: Grp7 (1A)
|
|
|
|
|
02: LAR Gv,Ew
|
|
|
|
|
03: LSL Gv,Ew
|
|
|
|
|
04:
|
|
|
|
|
05: SYSCALL (o64)
|
|
|
|
|
06: CLTS
|
|
|
|
|
07: SYSRET (o64)
|
|
|
|
|
08: INVD
|
|
|
|
|
09: WBINVD
|
|
|
|
|
0a:
|
|
|
|
|
0b: UD2 (1B)
|
|
|
|
|
0c:
|
|
|
|
|
# AMD's prefetch group. Intel supports prefetchw(/1) only.
|
|
|
|
|
0d: GrpP
|
|
|
|
|
0e: FEMMS
|
|
|
|
|
# 3DNow! uses the last imm byte as opcode extension.
|
|
|
|
|
0f: 3DNow! Pq,Qq,Ib
|
|
|
|
|
# 0x0f 0x10-0x1f
|
|
|
|
|
# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
|
|
|
|
|
# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
|
|
|
|
|
# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
|
|
|
|
|
# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
|
|
|
|
|
# Reference A.1
|
|
|
|
|
10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
|
|
|
|
|
11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
|
|
|
|
|
12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
|
|
|
|
|
13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
|
|
|
|
|
14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
|
|
|
|
|
15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
|
|
|
|
|
16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
|
|
|
|
|
17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
|
|
|
|
|
18: Grp16 (1A)
|
|
|
|
|
19:
|
x86/insn: perf tools: Pedantically tweak opcode map for MPX instructions
The MPX instructions are presently not described in the SDM
opcode maps, and there are not encoding characters for bnd
registers, address method or operand type. So the kernel
opcode map is using 'Gv' for bnd registers and 'Ev' for
everything else. That is fine because the instruction
decoder does not use that information anyway, except as
an indication that there is a ModR/M byte.
Nevertheless, in some cases the 'Gv' and 'Ev' are the wrong
way around, BNDLDX and BNDSTX have 2 operands not 3, and it
wouldn't hurt to identify the mandatory prefixes.
This has no effect on the decoding of valid instructions,
but the addition of the mandatory prefixes will cause some
invalid instructions to error out that wouldn't have
previously.
Note that perf tools has a copy of the instruction decoder
and provides a test for new instructions which includes MPX
instructions e.g.
$ perf test "x86 ins"
39: Test x86 instruction decoder - new instructions : Ok
Or to see the details:
$ perf test -v "x86 ins"
Commiter notes:
And to see these MPX instructions specifically:
$ perf test -v "x86 ins" 2>&1 | grep bndldx | head -3
Decoded ok: 0f 1a 00 bndldx (%eax),%bnd0
Decoded ok: 0f 1a 05 78 56 34 12 bndldx 0x12345678,%bnd0
Decoded ok: 0f 1a 18 bndldx (%eax),%bnd3
$ perf test -v "x86 ins" 2>&1 | grep bndstx | head -3
Decoded ok: 0f 1b 00 bndstx %bnd0,(%eax)
Decoded ok: 0f 1b 05 78 56 34 12 bndstx %bnd0,0x12345678
Decoded ok: 0f 1b 18 bndstx %bnd3,(%eax)
$
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1441196131-20632-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-09-02 19:15:27 +07:00
|
|
|
# Intel SDM opcode map does not list MPX instructions. For now using Gv for
|
|
|
|
|
# bnd registers and Ev for everything else is OK because the instruction
|
|
|
|
|
# decoder does not use the information except as an indication that there is
|
|
|
|
|
# a ModR/M byte.
|
|
|
|
|
1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
|
|
|
|
|
1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
|
2015-08-13 14:14:55 +07:00
|
|
|
1c:
|
|
|
|
|
1d:
|
|
|
|
|
1e:
|
|
|
|
|
1f: NOP Ev
|
|
|
|
|
# 0x0f 0x20-0x2f
|
|
|
|
|
20: MOV Rd,Cd
|
|
|
|
|
21: MOV Rd,Dd
|
|
|
|
|
22: MOV Cd,Rd
|
|
|
|
|
23: MOV Dd,Rd
|
|
|
|
|
24:
|
|
|
|
|
25:
|
|
|
|
|
26:
|
|
|
|
|
27:
|
|
|
|
|
28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
|
|
|
|
|
29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
|
|
|
|
|
2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
|
|
|
|
|
2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
|
|
|
|
|
2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
|
|
|
|
|
2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
|
|
|
|
|
2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1)
|
|
|
|
|
2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1)
|
|
|
|
|
# 0x0f 0x30-0x3f
|
|
|
|
|
30: WRMSR
|
|
|
|
|
31: RDTSC
|
|
|
|
|
32: RDMSR
|
|
|
|
|
33: RDPMC
|
|
|
|
|
34: SYSENTER
|
|
|
|
|
35: SYSEXIT
|
|
|
|
|
36:
|
|
|
|
|
37: GETSEC
|
|
|
|
|
38: escape # 3-byte escape 1
|
|
|
|
|
39:
|
|
|
|
|
3a: escape # 3-byte escape 2
|
|
|
|
|
3b:
|
|
|
|
|
3c:
|
|
|
|
|
3d:
|
|
|
|
|
3e:
|
|
|
|
|
3f:
|
|
|
|
|
# 0x0f 0x40-0x4f
|
|
|
|
|
40: CMOVO Gv,Ev
|
2016-07-20 15:30:36 +07:00
|
|
|
41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
|
|
|
|
|
42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
|
2015-08-13 14:14:55 +07:00
|
|
|
43: CMOVAE/NB/NC Gv,Ev
|
2016-07-20 15:30:36 +07:00
|
|
|
44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
|
|
|
|
|
45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
|
|
|
|
|
46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
|
|
|
|
|
47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
|
2015-08-13 14:14:55 +07:00
|
|
|
48: CMOVS Gv,Ev
|
|
|
|
|
49: CMOVNS Gv,Ev
|
2016-07-20 15:30:36 +07:00
|
|
|
4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
|
|
|
|
|
4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
|
2015-08-13 14:14:55 +07:00
|
|
|
4c: CMOVL/NGE Gv,Ev
|
|
|
|
|
4d: CMOVNL/GE Gv,Ev
|
|
|
|
|
4e: CMOVLE/NG Gv,Ev
|
|
|
|
|
4f: CMOVNLE/G Gv,Ev
|
|
|
|
|
# 0x0f 0x50-0x5f
|
|
|
|
|
50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
|
|
|
|
|
51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
|
|
|
|
|
53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
|
|
|
|
|
54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
|
|
|
|
|
55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
|
|
|
|
|
56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
|
|
|
|
|
57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
|
|
|
|
|
58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
|
2015-08-13 14:14:55 +07:00
|
|
|
5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
|
|
|
|
|
# 0x0f 0x60-0x6f
|
|
|
|
|
60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0x70-0x7f
|
|
|
|
|
70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
|
|
|
|
|
71: Grp12 (1A)
|
|
|
|
|
72: Grp13 (1A)
|
|
|
|
|
73: Grp14 (1A)
|
|
|
|
|
74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
|
|
|
|
|
77: emms | vzeroupper | vzeroall
|
2016-07-20 15:30:36 +07:00
|
|
|
78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
|
|
|
|
|
79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
|
|
|
|
|
7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
|
|
|
|
|
7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
|
|
|
|
|
7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
|
|
|
|
|
7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0x80-0x8f
|
|
|
|
|
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
|
|
|
|
|
80: JO Jz (f64)
|
|
|
|
|
81: JNO Jz (f64)
|
|
|
|
|
82: JB/JC/JNAE Jz (f64)
|
|
|
|
|
83: JAE/JNB/JNC Jz (f64)
|
|
|
|
|
84: JE/JZ Jz (f64)
|
|
|
|
|
85: JNE/JNZ Jz (f64)
|
|
|
|
|
86: JBE/JNA Jz (f64)
|
|
|
|
|
87: JA/JNBE Jz (f64)
|
|
|
|
|
88: JS Jz (f64)
|
|
|
|
|
89: JNS Jz (f64)
|
|
|
|
|
8a: JP/JPE Jz (f64)
|
|
|
|
|
8b: JNP/JPO Jz (f64)
|
|
|
|
|
8c: JL/JNGE Jz (f64)
|
|
|
|
|
8d: JNL/JGE Jz (f64)
|
|
|
|
|
8e: JLE/JNG Jz (f64)
|
|
|
|
|
8f: JNLE/JG Jz (f64)
|
|
|
|
|
# 0x0f 0x90-0x9f
|
2016-07-20 15:30:36 +07:00
|
|
|
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
|
|
|
|
|
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
|
|
|
|
|
92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
|
|
|
|
|
93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
|
2015-08-13 14:14:55 +07:00
|
|
|
94: SETE/Z Eb
|
|
|
|
|
95: SETNE/NZ Eb
|
|
|
|
|
96: SETBE/NA Eb
|
|
|
|
|
97: SETA/NBE Eb
|
2016-07-20 15:30:36 +07:00
|
|
|
98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
|
|
|
|
|
99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
|
2015-08-13 14:14:55 +07:00
|
|
|
9a: SETP/PE Eb
|
|
|
|
|
9b: SETNP/PO Eb
|
|
|
|
|
9c: SETL/NGE Eb
|
|
|
|
|
9d: SETNL/GE Eb
|
|
|
|
|
9e: SETLE/NG Eb
|
|
|
|
|
9f: SETNLE/G Eb
|
|
|
|
|
# 0x0f 0xa0-0xaf
|
|
|
|
|
a0: PUSH FS (d64)
|
|
|
|
|
a1: POP FS (d64)
|
|
|
|
|
a2: CPUID
|
|
|
|
|
a3: BT Ev,Gv
|
|
|
|
|
a4: SHLD Ev,Gv,Ib
|
|
|
|
|
a5: SHLD Ev,Gv,CL
|
|
|
|
|
a6: GrpPDLK
|
|
|
|
|
a7: GrpRNG
|
|
|
|
|
a8: PUSH GS (d64)
|
|
|
|
|
a9: POP GS (d64)
|
|
|
|
|
aa: RSM
|
|
|
|
|
ab: BTS Ev,Gv
|
|
|
|
|
ac: SHRD Ev,Gv,Ib
|
|
|
|
|
ad: SHRD Ev,Gv,CL
|
|
|
|
|
ae: Grp15 (1A),(1C)
|
|
|
|
|
af: IMUL Gv,Ev
|
|
|
|
|
# 0x0f 0xb0-0xbf
|
|
|
|
|
b0: CMPXCHG Eb,Gb
|
|
|
|
|
b1: CMPXCHG Ev,Gv
|
|
|
|
|
b2: LSS Gv,Mp
|
|
|
|
|
b3: BTR Ev,Gv
|
|
|
|
|
b4: LFS Gv,Mp
|
|
|
|
|
b5: LGS Gv,Mp
|
|
|
|
|
b6: MOVZX Gv,Eb
|
|
|
|
|
b7: MOVZX Gv,Ew
|
|
|
|
|
b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
|
|
|
|
|
b9: Grp10 (1A)
|
|
|
|
|
ba: Grp8 Ev,Ib (1A)
|
|
|
|
|
bb: BTC Ev,Gv
|
|
|
|
|
bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
|
|
|
|
|
bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
|
|
|
|
|
be: MOVSX Gv,Eb
|
|
|
|
|
bf: MOVSX Gv,Ew
|
|
|
|
|
# 0x0f 0xc0-0xcf
|
|
|
|
|
c0: XADD Eb,Gb
|
|
|
|
|
c1: XADD Ev,Gv
|
|
|
|
|
c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
|
|
|
|
|
c3: movnti My,Gy
|
|
|
|
|
c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
|
|
|
|
|
c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
|
|
|
|
|
c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
|
|
|
|
|
c7: Grp9 (1A)
|
|
|
|
|
c8: BSWAP RAX/EAX/R8/R8D
|
|
|
|
|
c9: BSWAP RCX/ECX/R9/R9D
|
|
|
|
|
ca: BSWAP RDX/EDX/R10/R10D
|
|
|
|
|
cb: BSWAP RBX/EBX/R11/R11D
|
|
|
|
|
cc: BSWAP RSP/ESP/R12/R12D
|
|
|
|
|
cd: BSWAP RBP/EBP/R13/R13D
|
|
|
|
|
ce: BSWAP RSI/ESI/R14/R14D
|
|
|
|
|
cf: BSWAP RDI/EDI/R15/R15D
|
|
|
|
|
# 0x0f 0xd0-0xdf
|
|
|
|
|
d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
|
|
|
|
|
d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
|
|
|
|
|
d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
|
|
|
|
|
d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0xe0-0xef
|
|
|
|
|
e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
|
2015-08-13 14:14:55 +07:00
|
|
|
e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
|
|
|
|
|
e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0xf0-0xff
|
|
|
|
|
f0: vlddqu Vx,Mx (F2)
|
|
|
|
|
f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
|
|
|
|
|
f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
|
|
|
|
|
fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
ff:
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
Table: 3-byte opcode 1 (0x0f 0x38)
|
|
|
|
|
Referrer: 3-byte escape 1
|
|
|
|
|
AVXcode: 2
|
|
|
|
|
# 0x0f 0x38 0x00-0x0f
|
|
|
|
|
00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
|
|
|
|
|
09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
|
|
|
|
|
0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
|
|
|
|
|
0c: vpermilps Vx,Hx,Wx (66),(v)
|
|
|
|
|
0d: vpermilpd Vx,Hx,Wx (66),(v)
|
|
|
|
|
0e: vtestps Vx,Wx (66),(v)
|
|
|
|
|
0f: vtestpd Vx,Wx (66),(v)
|
|
|
|
|
# 0x0f 0x38 0x10-0x1f
|
2016-07-20 15:30:36 +07:00
|
|
|
10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
|
|
|
|
|
11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
|
|
|
|
|
12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
|
|
|
|
|
13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
|
|
|
|
|
14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
|
|
|
|
|
15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
|
|
|
|
|
16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
17: vptest Vx,Wx (66)
|
|
|
|
|
18: vbroadcastss Vx,Wd (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
|
|
|
|
|
1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
|
|
|
|
|
1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
|
|
|
|
|
1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
|
|
|
|
|
1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
1f: vpabsq Vx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0x38 0x20-0x2f
|
2016-07-20 15:30:36 +07:00
|
|
|
20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
|
|
|
|
|
21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
|
|
|
|
|
22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
|
|
|
|
|
23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
|
|
|
|
|
24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
|
|
|
|
|
25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
|
|
|
|
|
26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
|
|
|
|
|
27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
|
|
|
|
|
28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
|
|
|
|
|
29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
|
|
|
|
|
2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
2b: vpackusdw Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
|
|
|
|
|
2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
2e: vmaskmovps Mx,Hx,Vx (66),(v)
|
|
|
|
|
2f: vmaskmovpd Mx,Hx,Vx (66),(v)
|
|
|
|
|
# 0x0f 0x38 0x30-0x3f
|
2016-07-20 15:30:36 +07:00
|
|
|
30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
|
|
|
|
|
31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
|
|
|
|
|
32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
|
|
|
|
|
33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
|
|
|
|
|
34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
|
|
|
|
|
35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
|
|
|
|
|
36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
37: vpcmpgtq Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
|
|
|
|
|
39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
|
|
|
|
|
3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
|
|
|
|
|
3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
3c: vpmaxsb Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
3e: vpmaxuw Vx,Hx,Wx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
# 0x0f 0x38 0x40-0x8f
|
2016-07-20 15:30:36 +07:00
|
|
|
40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
41: vphminposuw Vdq,Wdq (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
42: vgetexpps/d Vx,Wx (66),(ev)
|
|
|
|
|
43: vgetexpss/d Vx,Hx,Wx (66),(ev)
|
|
|
|
|
44: vplzcntd/q Vx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
45: vpsrlvd/q Vx,Hx,Wx (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
47: vpsllvd/q Vx,Hx,Wx (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
# Skip 0x48-0x4b
|
|
|
|
|
4c: vrcp14ps/d Vpd,Wpd (66),(ev)
|
|
|
|
|
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
|
|
|
|
|
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
|
|
|
|
|
4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
|
|
|
|
|
# Skip 0x50-0x57
|
2015-08-13 14:14:55 +07:00
|
|
|
58: vpbroadcastd Vx,Wx (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
|
|
|
|
|
5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
|
|
|
|
|
5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
|
|
|
|
|
# Skip 0x5c-0x63
|
|
|
|
|
64: vpblendmd/q Vx,Hx,Wx (66),(ev)
|
|
|
|
|
65: vblendmps/d Vx,Hx,Wx (66),(ev)
|
|
|
|
|
66: vpblendmb/w Vx,Hx,Wx (66),(ev)
|
|
|
|
|
# Skip 0x67-0x74
|
|
|
|
|
75: vpermi2b/w Vx,Hx,Wx (66),(ev)
|
|
|
|
|
76: vpermi2d/q Vx,Hx,Wx (66),(ev)
|
|
|
|
|
77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
78: vpbroadcastb Vx,Wx (66),(v)
|
|
|
|
|
79: vpbroadcastw Vx,Wx (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
7a: vpbroadcastb Vx,Rv (66),(ev)
|
|
|
|
|
7b: vpbroadcastw Vx,Rv (66),(ev)
|
|
|
|
|
7c: vpbroadcastd/q Vx,Rv (66),(ev)
|
|
|
|
|
7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
|
|
|
|
|
7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
|
|
|
|
|
7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
80: INVEPT Gy,Mdq (66)
|
|
|
|
|
81: INVPID Gy,Mdq (66)
|
|
|
|
|
82: INVPCID Gy,Mdq (66)
|
2016-07-20 15:30:36 +07:00
|
|
|
83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
|
|
|
|
|
88: vexpandps/d Vpd,Wpd (66),(ev)
|
|
|
|
|
89: vpexpandd/q Vx,Wx (66),(ev)
|
|
|
|
|
8a: vcompressps/d Wx,Vx (66),(ev)
|
|
|
|
|
8b: vpcompressd/q Wx,Vx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
8d: vpermb/w Vx,Hx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
|
|
|
|
|
# 0x0f 0x38 0x90-0xbf (FMA)
|
2016-07-20 15:30:36 +07:00
|
|
|
90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
|
|
|
|
|
91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
92: vgatherdps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
93: vgatherqps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
94:
|
|
|
|
|
95:
|
|
|
|
|
96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
a0: vpscatterdd/q Wx,Vx (66),(ev)
|
|
|
|
|
a1: vpscatterqd/q Wx,Vx (66),(ev)
|
|
|
|
|
a2: vscatterdps/d Wx,Vx (66),(ev)
|
|
|
|
|
a3: vscatterqps/d Wx,Vx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
|
|
|
|
|
b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
|
|
|
|
|
bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
|
|
|
|
|
# 0x0f 0x38 0xc0-0xff
|
2016-07-20 15:30:36 +07:00
|
|
|
c4: vpconflictd/q Vx,Wx (66),(ev)
|
|
|
|
|
c6: Grp18 (1A)
|
|
|
|
|
c7: Grp19 (1A)
|
|
|
|
|
c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
|
x86/insn: perf tools: Add new SHA instructions
Intel SHA Extensions are explained in the Intel Architecture
Instruction Set Extensions Programing Reference (Oct 2014).
There are 7 new instructions. Add them to the op code map
and the perf tools new instructions test. e.g.
$ tools/perf/perf test "x86 ins"
39: Test x86 instruction decoder - new instructions : Ok
Or to see the details:
$ tools/perf/perf test -v "x86 ins" 2>&1 | grep sha
Committer note:
3 lines of details, for the curious:
$ perf test -v "x86 ins" 2>&1 | grep sha256msg1 | tail -3
Decoded ok: 0f 38 cc 84 08 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,1),%xmm0
Decoded ok: 0f 38 cc 84 c8 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,8),%xmm0
Decoded ok: 44 0f 38 cc bc c8 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,8),%xmm15
$
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1441196131-20632-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-09-02 19:15:28 +07:00
|
|
|
c9: sha1msg1 Vdq,Wdq
|
2016-07-20 15:30:36 +07:00
|
|
|
ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
|
|
|
|
|
cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
|
|
|
|
|
cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
|
|
|
|
|
cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
db: VAESIMC Vdq,Wdq (66),(v1)
|
|
|
|
|
dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
|
|
|
|
|
dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
|
|
|
|
|
de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
|
|
|
|
|
df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
|
|
|
|
|
f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
|
|
|
|
|
f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
|
|
|
|
|
f2: ANDN Gy,By,Ey (v)
|
|
|
|
|
f3: Grp17 (1A)
|
|
|
|
|
f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
|
|
|
|
|
f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
|
|
|
|
|
f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
Table: 3-byte opcode 2 (0x0f 0x3a)
|
|
|
|
|
Referrer: 3-byte escape 2
|
|
|
|
|
AVXcode: 3
|
|
|
|
|
# 0x0f 0x3a 0x00-0xff
|
|
|
|
|
00: vpermq Vqq,Wqq,Ib (66),(v)
|
|
|
|
|
01: vpermpd Vqq,Wqq,Ib (66),(v)
|
|
|
|
|
02: vpblendd Vx,Hx,Wx,Ib (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
04: vpermilps Vx,Wx,Ib (66),(v)
|
|
|
|
|
05: vpermilpd Vx,Wx,Ib (66),(v)
|
|
|
|
|
06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
|
|
|
|
|
07:
|
2016-07-20 15:30:36 +07:00
|
|
|
08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
|
|
|
|
|
09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
|
|
|
|
|
0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
|
|
|
|
|
0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
0c: vblendps Vx,Hx,Wx,Ib (66)
|
|
|
|
|
0d: vblendpd Vx,Hx,Wx,Ib (66)
|
|
|
|
|
0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
|
|
|
|
|
0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
|
|
|
|
|
14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
|
|
|
|
|
15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
|
|
|
|
|
16: vpextrd/q Ey,Vdq,Ib (66),(v1)
|
|
|
|
|
17: vextractps Ed,Vdq,Ib (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
|
|
|
|
|
19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
|
|
|
|
|
1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
|
|
|
|
|
1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
1d: vcvtps2ph Wx,Vx,Ib (66),(v)
|
2016-07-20 15:30:36 +07:00
|
|
|
1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
|
|
|
|
|
1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
|
|
|
|
|
21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
|
|
|
|
|
22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
26: vgetmantps/d Vx,Wx,Ib (66),(ev)
|
|
|
|
|
27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
30: kshiftrb/w Vk,Uk,Ib (66),(v)
|
|
|
|
|
31: kshiftrd/q Vk,Uk,Ib (66),(v)
|
|
|
|
|
32: kshiftlb/w Vk,Uk,Ib (66),(v)
|
|
|
|
|
33: kshiftld/q Vk,Uk,Ib (66),(v)
|
|
|
|
|
38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
|
|
|
|
|
39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
|
|
|
|
|
3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
|
|
|
|
|
3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
|
|
|
|
|
3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
|
|
|
|
|
3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
40: vdpps Vx,Hx,Wx,Ib (66)
|
|
|
|
|
41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
|
|
|
|
|
43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
|
|
|
|
|
46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
|
|
|
|
|
4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
|
|
|
|
|
4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
|
|
|
|
|
4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
|
|
|
|
|
56: vreduceps/d Vx,Wx,Ib (66),(ev)
|
|
|
|
|
57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
|
|
|
|
|
61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
|
|
|
|
|
62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
|
|
|
|
|
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
66: vfpclassps/d Vk,Wx,Ib (66),(ev)
|
|
|
|
|
67: vfpclassss/d Vk,Wx,Ib (66),(ev)
|
x86/insn: perf tools: Add new SHA instructions
Intel SHA Extensions are explained in the Intel Architecture
Instruction Set Extensions Programing Reference (Oct 2014).
There are 7 new instructions. Add them to the op code map
and the perf tools new instructions test. e.g.
$ tools/perf/perf test "x86 ins"
39: Test x86 instruction decoder - new instructions : Ok
Or to see the details:
$ tools/perf/perf test -v "x86 ins" 2>&1 | grep sha
Committer note:
3 lines of details, for the curious:
$ perf test -v "x86 ins" 2>&1 | grep sha256msg1 | tail -3
Decoded ok: 0f 38 cc 84 08 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,1),%xmm0
Decoded ok: 0f 38 cc 84 c8 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,8),%xmm0
Decoded ok: 44 0f 38 cc bc c8 78 56 34 12 sha256msg1 0x12345678(%rax,%rcx,8),%xmm15
$
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1441196131-20632-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-09-02 19:15:28 +07:00
|
|
|
cc: sha1rnds4 Vdq,Wdq,Ib
|
2015-08-13 14:14:55 +07:00
|
|
|
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
|
|
|
|
|
f0: RORX Gy,Ey,Ib (F2),(v)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp1
|
|
|
|
|
0: ADD
|
|
|
|
|
1: OR
|
|
|
|
|
2: ADC
|
|
|
|
|
3: SBB
|
|
|
|
|
4: AND
|
|
|
|
|
5: SUB
|
|
|
|
|
6: XOR
|
|
|
|
|
7: CMP
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp1A
|
|
|
|
|
0: POP
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp2
|
|
|
|
|
0: ROL
|
|
|
|
|
1: ROR
|
|
|
|
|
2: RCL
|
|
|
|
|
3: RCR
|
|
|
|
|
4: SHL/SAL
|
|
|
|
|
5: SHR
|
|
|
|
|
6:
|
|
|
|
|
7: SAR
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp3_1
|
|
|
|
|
0: TEST Eb,Ib
|
|
|
|
|
1:
|
|
|
|
|
2: NOT Eb
|
|
|
|
|
3: NEG Eb
|
|
|
|
|
4: MUL AL,Eb
|
|
|
|
|
5: IMUL AL,Eb
|
|
|
|
|
6: DIV AL,Eb
|
|
|
|
|
7: IDIV AL,Eb
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp3_2
|
|
|
|
|
0: TEST Ev,Iz
|
|
|
|
|
1:
|
|
|
|
|
2: NOT Ev
|
|
|
|
|
3: NEG Ev
|
|
|
|
|
4: MUL rAX,Ev
|
|
|
|
|
5: IMUL rAX,Ev
|
|
|
|
|
6: DIV rAX,Ev
|
|
|
|
|
7: IDIV rAX,Ev
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp4
|
|
|
|
|
0: INC Eb
|
|
|
|
|
1: DEC Eb
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp5
|
|
|
|
|
0: INC Ev
|
|
|
|
|
1: DEC Ev
|
|
|
|
|
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
|
|
|
|
|
2: CALLN Ev (f64)
|
|
|
|
|
3: CALLF Ep
|
|
|
|
|
4: JMPN Ev (f64)
|
|
|
|
|
5: JMPF Mp
|
|
|
|
|
6: PUSH Ev (d64)
|
|
|
|
|
7:
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp6
|
|
|
|
|
0: SLDT Rv/Mw
|
|
|
|
|
1: STR Rv/Mw
|
|
|
|
|
2: LLDT Ew
|
|
|
|
|
3: LTR Ew
|
|
|
|
|
4: VERR Ew
|
|
|
|
|
5: VERW Ew
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp7
|
|
|
|
|
0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
|
|
|
|
|
1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
|
|
|
|
|
2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
|
|
|
|
|
3: LIDT Ms
|
|
|
|
|
4: SMSW Mw/Rv
|
2015-09-02 19:15:30 +07:00
|
|
|
5: rdpkru (110),(11B) | wrpkru (111),(11B)
|
2015-08-13 14:14:55 +07:00
|
|
|
6: LMSW Ew
|
|
|
|
|
7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp8
|
|
|
|
|
4: BT
|
|
|
|
|
5: BTS
|
|
|
|
|
6: BTR
|
|
|
|
|
7: BTC
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp9
|
|
|
|
|
1: CMPXCHG8B/16B Mq/Mdq
|
2015-09-02 19:15:31 +07:00
|
|
|
3: xrstors
|
|
|
|
|
4: xsavec
|
|
|
|
|
5: xsaves
|
2015-08-13 14:14:55 +07:00
|
|
|
6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
|
|
|
|
|
7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp10
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
|
|
|
|
|
GrpTable: Grp11A
|
|
|
|
|
0: MOV Eb,Ib
|
|
|
|
|
7: XABORT Ib (000),(11B)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp11B
|
|
|
|
|
0: MOV Eb,Iz
|
|
|
|
|
7: XBEGIN Jz (000),(11B)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp12
|
|
|
|
|
2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp13
|
2016-07-20 15:30:36 +07:00
|
|
|
0: vprord/q Hx,Wx,Ib (66),(ev)
|
|
|
|
|
1: vprold/q Hx,Wx,Ib (66),(ev)
|
2015-08-13 14:14:55 +07:00
|
|
|
2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
|
2016-07-20 15:30:36 +07:00
|
|
|
4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
|
2015-08-13 14:14:55 +07:00
|
|
|
6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp14
|
|
|
|
|
2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp15
|
|
|
|
|
0: fxsave | RDFSBASE Ry (F3),(11B)
|
|
|
|
|
1: fxstor | RDGSBASE Ry (F3),(11B)
|
|
|
|
|
2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
|
|
|
|
|
3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
|
|
|
|
|
4: XSAVE
|
|
|
|
|
5: XRSTOR | lfence (11B)
|
2015-09-02 19:15:29 +07:00
|
|
|
6: XSAVEOPT | clwb (66) | mfence (11B)
|
2016-06-03 01:06:13 +07:00
|
|
|
7: clflush | clflushopt (66) | sfence (11B)
|
2015-08-13 14:14:55 +07:00
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp16
|
|
|
|
|
0: prefetch NTA
|
|
|
|
|
1: prefetch T0
|
|
|
|
|
2: prefetch T1
|
|
|
|
|
3: prefetch T2
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp17
|
|
|
|
|
1: BLSR By,Ey (v)
|
|
|
|
|
2: BLSMSK By,Ey (v)
|
|
|
|
|
3: BLSI By,Ey (v)
|
|
|
|
|
EndTable
|
|
|
|
|
|
2016-07-20 15:30:36 +07:00
|
|
|
GrpTable: Grp18
|
|
|
|
|
1: vgatherpf0dps/d Wx (66),(ev)
|
|
|
|
|
2: vgatherpf1dps/d Wx (66),(ev)
|
|
|
|
|
5: vscatterpf0dps/d Wx (66),(ev)
|
|
|
|
|
6: vscatterpf1dps/d Wx (66),(ev)
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: Grp19
|
|
|
|
|
1: vgatherpf0qps/d Wx (66),(ev)
|
|
|
|
|
2: vgatherpf1qps/d Wx (66),(ev)
|
|
|
|
|
5: vscatterpf0qps/d Wx (66),(ev)
|
|
|
|
|
6: vscatterpf1qps/d Wx (66),(ev)
|
|
|
|
|
EndTable
|
|
|
|
|
|
2015-08-13 14:14:55 +07:00
|
|
|
# AMD's Prefetch Group
|
|
|
|
|
GrpTable: GrpP
|
|
|
|
|
0: PREFETCH
|
|
|
|
|
1: PREFETCHW
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: GrpPDLK
|
|
|
|
|
0: MONTMUL
|
|
|
|
|
1: XSHA1
|
|
|
|
|
2: XSHA2
|
|
|
|
|
EndTable
|
|
|
|
|
|
|
|
|
|
GrpTable: GrpRNG
|
|
|
|
|
0: xstore-rng
|
|
|
|
|
1: xcrypt-ecb
|
|
|
|
|
2: xcrypt-cbc
|
|
|
|
|
4: xcrypt-cfb
|
|
|
|
|
5: xcrypt-ofb
|
|
|
|
|
EndTable
|