1
0
Fork 0
mirror of https://github.com/Ryujinx/Ryujinx.git synced 2024-12-22 16:02:03 +00:00
Ryujinx/ARMeilleure/CodeGen/X86/X86Instruction.cs
Wunk 45ce540b9b
ARMeilleure: Add gfni acceleration (#3669)
* ARMeilleure: Add `GFNI` detection

This is intended for utilizing the `gf2p8affineqb` instruction

* ARMeilleure: Add `gf2p8affineqb`

Not using the VEX or EVEX-form of this instruction is intentional. There
are `GFNI`-chips that do not support AVX(so no VEX encoding) such as
Tremont(Lakefield) chips as well as Jasper Lake.

13df339fe7/GenuineIntel/GenuineIntel00806A1_Lakefield_LC_InstLatX64.txt (L1297-L1299)

13df339fe7/GenuineIntel/GenuineIntel00906C0_JasperLake_InstLatX64.txt (L1252-L1254)

* ARMeilleure: Add `gfni` acceleration of `Rbit_V`

Passes all `Rbit_V*` unit tests on my `i9-11900k`

* ARMeilleure: Add `gfni` acceleration of `S{l,r}i_V`

Also added a fast-path for when the shift amount is greater than the
size of the element.

* ARMeilleure: Add `gfni` acceleration of `Shl_V` and `Sshr_V`

* ARMeilleure: Increment InternalVersion

* ARMeilleure: Fix Intrinsic and Assembler Table alignment

`gf2p8affineqb` is the longest instruction name I know of. It shouldn't
get any wider than this.

* ARMeilleure: Remove SSE2+SHA requirement for GFNI

* ARMeilleure Add `X86GetGf2p8LogicalShiftLeft`

Used to generate GF(2^8) 8x8 bit-matrices for bit-shifting for the `gf2p8affineqb` instruction.

* ARMeilleure: Append `FeatureInfo7Ecx` to `FeatureInfo`
2022-10-02 11:17:19 +02:00

228 lines
No EOL
3.6 KiB
C#

namespace ARMeilleure.CodeGen.X86
{
enum X86Instruction
{
None,
Add,
Addpd,
Addps,
Addsd,
Addss,
Aesdec,
Aesdeclast,
Aesenc,
Aesenclast,
Aesimc,
And,
Andnpd,
Andnps,
Andpd,
Andps,
Blendvpd,
Blendvps,
Bsr,
Bswap,
Call,
Cmovcc,
Cmp,
Cmppd,
Cmpps,
Cmpsd,
Cmpss,
Cmpxchg,
Cmpxchg16b,
Cmpxchg8,
Comisd,
Comiss,
Crc32,
Crc32_16,
Crc32_8,
Cvtdq2pd,
Cvtdq2ps,
Cvtpd2dq,
Cvtpd2ps,
Cvtps2dq,
Cvtps2pd,
Cvtsd2si,
Cvtsd2ss,
Cvtsi2sd,
Cvtsi2ss,
Cvtss2sd,
Cvtss2si,
Div,
Divpd,
Divps,
Divsd,
Divss,
Gf2p8affineqb,
Haddpd,
Haddps,
Idiv,
Imul,
Imul128,
Insertps,
Jmp,
Ldmxcsr,
Lea,
Maxpd,
Maxps,
Maxsd,
Maxss,
Minpd,
Minps,
Minsd,
Minss,
Mov,
Mov16,
Mov8,
Movd,
Movdqu,
Movhlps,
Movlhps,
Movq,
Movsd,
Movss,
Movsx16,
Movsx32,
Movsx8,
Movzx16,
Movzx8,
Mul128,
Mulpd,
Mulps,
Mulsd,
Mulss,
Neg,
Not,
Or,
Paddb,
Paddd,
Paddq,
Paddw,
Palignr,
Pand,
Pandn,
Pavgb,
Pavgw,
Pblendvb,
Pclmulqdq,
Pcmpeqb,
Pcmpeqd,
Pcmpeqq,
Pcmpeqw,
Pcmpgtb,
Pcmpgtd,
Pcmpgtq,
Pcmpgtw,
Pextrb,
Pextrd,
Pextrq,
Pextrw,
Pinsrb,
Pinsrd,
Pinsrq,
Pinsrw,
Pmaxsb,
Pmaxsd,
Pmaxsw,
Pmaxub,
Pmaxud,
Pmaxuw,
Pminsb,
Pminsd,
Pminsw,
Pminub,
Pminud,
Pminuw,
Pmovsxbw,
Pmovsxdq,
Pmovsxwd,
Pmovzxbw,
Pmovzxdq,
Pmovzxwd,
Pmulld,
Pmullw,
Pop,
Popcnt,
Por,
Pshufb,
Pshufd,
Pslld,
Pslldq,
Psllq,
Psllw,
Psrad,
Psraw,
Psrld,
Psrlq,
Psrldq,
Psrlw,
Psubb,
Psubd,
Psubq,
Psubw,
Punpckhbw,
Punpckhdq,
Punpckhqdq,
Punpckhwd,
Punpcklbw,
Punpckldq,
Punpcklqdq,
Punpcklwd,
Push,
Pxor,
Rcpps,
Rcpss,
Ror,
Roundpd,
Roundps,
Roundsd,
Roundss,
Rsqrtps,
Rsqrtss,
Sar,
Setcc,
Sha256Msg1,
Sha256Msg2,
Sha256Rnds2,
Shl,
Shr,
Shufpd,
Shufps,
Sqrtpd,
Sqrtps,
Sqrtsd,
Sqrtss,
Stmxcsr,
Sub,
Subpd,
Subps,
Subsd,
Subss,
Test,
Unpckhpd,
Unpckhps,
Unpcklpd,
Unpcklps,
Vblendvpd,
Vblendvps,
Vcvtph2ps,
Vcvtps2ph,
Vfmadd231ps,
Vfmadd231sd,
Vfmadd231ss,
Vfmsub231sd,
Vfmsub231ss,
Vfnmadd231ps,
Vfnmadd231sd,
Vfnmadd231ss,
Vfnmsub231sd,
Vfnmsub231ss,
Vpblendvb,
Xor,
Xorpd,
Xorps,
Count
}
}