Ryujinx/ARMeilleure/Optimizations.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

48 lines
3 KiB
C#

using ARMeilleure.CodeGen.X86;
namespace ARMeilleure
{
public static class Optimizations
{
public static bool FastFP { get; set; } = true;
public static bool AllowLcqInFunctionTable { get; set; } = true;
public static bool UseUnmanagedDispatchLoop { get; set; } = true;
public static bool UseSseIfAvailable { get; set; } = true;
public static bool UseSse2IfAvailable { get; set; } = true;
public static bool UseSse3IfAvailable { get; set; } = true;
public static bool UseSsse3IfAvailable { get; set; } = true;
public static bool UseSse41IfAvailable { get; set; } = true;
public static bool UseSse42IfAvailable { get; set; } = true;
public static bool UsePopCntIfAvailable { get; set; } = true;
public static bool UseAvxIfAvailable { get; set; } = true;
public static bool UseF16cIfAvailable { get; set; } = true;
public static bool UseFmaIfAvailable { get; set; } = true;
public static bool UseAesniIfAvailable { get; set; } = true;
public static bool UsePclmulqdqIfAvailable { get; set; } = true;
public static bool UseShaIfAvailable { get; set; } = true;
public static bool UseGfniIfAvailable { get; set; } = true;
public static bool ForceLegacySse
{
get => HardwareCapabilities.ForceLegacySse;
set => HardwareCapabilities.ForceLegacySse = value;
}
internal static bool UseSse => UseSseIfAvailable && HardwareCapabilities.SupportsSse;
internal static bool UseSse2 => UseSse2IfAvailable && HardwareCapabilities.SupportsSse2;
internal static bool UseSse3 => UseSse3IfAvailable && HardwareCapabilities.SupportsSse3;
internal static bool UseSsse3 => UseSsse3IfAvailable && HardwareCapabilities.SupportsSsse3;
internal static bool UseSse41 => UseSse41IfAvailable && HardwareCapabilities.SupportsSse41;
internal static bool UseSse42 => UseSse42IfAvailable && HardwareCapabilities.SupportsSse42;
internal static bool UsePopCnt => UsePopCntIfAvailable && HardwareCapabilities.SupportsPopcnt;
internal static bool UseAvx => UseAvxIfAvailable && HardwareCapabilities.SupportsAvx && !ForceLegacySse;
internal static bool UseF16c => UseF16cIfAvailable && HardwareCapabilities.SupportsF16c;
internal static bool UseFma => UseFmaIfAvailable && HardwareCapabilities.SupportsFma;
internal static bool UseAesni => UseAesniIfAvailable && HardwareCapabilities.SupportsAesni;
internal static bool UsePclmulqdq => UsePclmulqdqIfAvailable && HardwareCapabilities.SupportsPclmulqdq;
internal static bool UseSha => UseShaIfAvailable && HardwareCapabilities.SupportsSha;
internal static bool UseGfni => UseGfniIfAvailable && HardwareCapabilities.SupportsGfni;
}
}