Ryujinx/ARMeilleure/IntermediateRepresentation/Intrinsic.cs
jduncanator 68e15c1a74
Implement Fast Paths for most A32 SIMD instructions (#952)
* Begin work on A32 SIMD Intrinsics

* More instructions, some cleanup.

* Intrinsics for Move instructions (zip etc)

These pass the existing tests.

* Intrinsics for some of Cvt

While doing this I noticed that the conversion for int/fp was incorrect
in the slow path. I'll fix this in the original repo.

* Intrinsics for more Arithmetic instructions.

* Intrinsics for Vext

* Fix VEXT Intrinsic for double words.

* Use InsertPs to move scalar values.

* Cleanup, fix VPADD.f32 and VMIN signed integer.

* Cleanup, add SSE2 support for scalar insert.

Works similarly to the IR scalar insert, but obviously this one works
directly on V128.

* Minor cleanup.

* Enable intrinsic for FP64 to integer conversion.

* Address feedback apart from splitting out intrinsic float abs

Also: bad VREV encodings as undefined rather than throwing in translation.

* Move float abs to helper, fix bug with cvt

* Rename opc2 & 3 to match A32 docs, use ArgumentOutOfRangeException appropriately.

* Get name of variable at compilation rather than string literal.

* Use correct double sign mask.
2020-03-05 11:41:33 +11:00

148 lines
No EOL
2.8 KiB
C#

namespace ARMeilleure.IntermediateRepresentation
{
enum Intrinsic
{
X86Addpd,
X86Addps,
X86Addsd,
X86Addss,
X86Andnpd,
X86Andnps,
X86Andpd,
X86Andps,
X86Blendvpd,
X86Blendvps,
X86Cmppd,
X86Cmpps,
X86Cmpsd,
X86Cmpss,
X86Comisdeq,
X86Comisdge,
X86Comisdlt,
X86Comisseq,
X86Comissge,
X86Comisslt,
X86Cvtdq2pd,
X86Cvtdq2ps,
X86Cvtpd2dq,
X86Cvtpd2ps,
X86Cvtps2dq,
X86Cvtps2pd,
X86Cvtsd2si,
X86Cvtsd2ss,
X86Cvtsi2sd,
X86Cvtsi2si,
X86Cvtsi2ss,
X86Cvtss2sd,
X86Cvtss2si,
X86Divpd,
X86Divps,
X86Divsd,
X86Divss,
X86Haddpd,
X86Haddps,
X86Insertps,
X86Maxpd,
X86Maxps,
X86Maxsd,
X86Maxss,
X86Minpd,
X86Minps,
X86Minsd,
X86Minss,
X86Movhlps,
X86Movlhps,
X86Movss,
X86Mulpd,
X86Mulps,
X86Mulsd,
X86Mulss,
X86Paddb,
X86Paddd,
X86Paddq,
X86Paddw,
X86Pand,
X86Pandn,
X86Pavgb,
X86Pavgw,
X86Pblendvb,
X86Pcmpeqb,
X86Pcmpeqd,
X86Pcmpeqq,
X86Pcmpeqw,
X86Pcmpgtb,
X86Pcmpgtd,
X86Pcmpgtq,
X86Pcmpgtw,
X86Pmaxsb,
X86Pmaxsd,
X86Pmaxsw,
X86Pmaxub,
X86Pmaxud,
X86Pmaxuw,
X86Pminsb,
X86Pminsd,
X86Pminsw,
X86Pminub,
X86Pminud,
X86Pminuw,
X86Pmovsxbw,
X86Pmovsxdq,
X86Pmovsxwd,
X86Pmovzxbw,
X86Pmovzxdq,
X86Pmovzxwd,
X86Pmulld,
X86Pmullw,
X86Popcnt,
X86Por,
X86Pshufb,
X86Pslld,
X86Pslldq,
X86Psllq,
X86Psllw,
X86Psrad,
X86Psraw,
X86Psrld,
X86Psrlq,
X86Psrldq,
X86Psrlw,
X86Psubb,
X86Psubd,
X86Psubq,
X86Psubw,
X86Punpckhbw,
X86Punpckhdq,
X86Punpckhqdq,
X86Punpckhwd,
X86Punpcklbw,
X86Punpckldq,
X86Punpcklqdq,
X86Punpcklwd,
X86Pxor,
X86Rcpps,
X86Rcpss,
X86Roundpd,
X86Roundps,
X86Roundsd,
X86Roundss,
X86Rsqrtps,
X86Rsqrtss,
X86Shufpd,
X86Shufps,
X86Sqrtpd,
X86Sqrtps,
X86Sqrtsd,
X86Sqrtss,
X86Subpd,
X86Subps,
X86Subsd,
X86Subss,
X86Unpckhpd,
X86Unpckhps,
X86Unpcklpd,
X86Unpcklps,
X86Xorpd,
X86Xorps
}
}