0
0
Fork 0
mirror of https://github.com/GreemDev/Ryujinx.git synced 2024-12-24 02:45:48 +00:00
Ryujinx/ARMeilleure/Optimizations.cs
FICTURE7 9d7627af64
Add multi-level function table (#2228)
* Add AddressTable<T>

* Use AddressTable<T> for dispatch

* Remove JumpTable & co.

* Add fallback for out of range addresses

* Add PPTC support

* Add documentation to `AddressTable<T>`

* Make AddressTable<T> configurable

* Fix table walk

* Fix IsMapped check

* Remove CountTableCapacity

* Add PPTC support for fast path

* Rename IsMapped to IsValid

* Remove stale comment

* Change format of address in exception message

* Add TranslatorStubs

* Split DispatchStub

Avoids recompilation of stubs during tests.

* Add hint for 64bit or 32bit

* Add documentation to `Symbol`

* Add documentation to `TranslatorStubs`

Make `TranslatorStubs` disposable as well.

* Add documentation to `SymbolType`

* Add `AddressTableEventSource` to monitor function table size

Add an EventSource which measures the amount of unmanaged bytes
allocated by AddressTable<T> instances.

 dotnet-counters monitor -n Ryujinx --counters ARMeilleure

* Add `AllowLcqInFunctionTable` optimization toggle

This is to reduce the impact this change has on the test duration.
Before everytime a test was ran, the FunctionTable would be initialized
and populated so that the newly compiled test would get registered to
it.

* Implement unmanaged dispatcher

Uses the DispatchStub to dispatch into the next translation, which
allows execution to stay in unmanaged for longer and skips a
ConcurrentDictionary look up when the target translation has been
registered to the FunctionTable.

* Remove redundant null check

* Tune levels of FunctionTable

Uses 5 levels instead of 4 and change unit of AddressTableEventSource
from KB to MB.

* Use 64-bit function table

Improves codegen for direct branches:

    mov qword [rax+0x408],0x10603560
 -  mov rcx,sub_10603560_OFFSET
 -  mov ecx,[rcx]
 -  mov ecx,ecx
 -  mov rdx,JIT_CACHE_BASE
 -  add rdx,rcx
 +  mov rcx,sub_10603560
 +  mov rdx,[rcx]
    mov rcx,rax

Improves codegen for dispatch stub:

    and rax,byte +0x1f
 -  mov eax,[rcx+rax*4]
 -  mov eax,eax
 -  mov rcx,JIT_CACHE_BASE
 -  lea rax,[rcx+rax]
 +  mov rax,[rcx+rax*8]
    mov rcx,rbx

* Remove `JitCacheSymbol` & `JitCache.Offset`

* Turn `Translator.Translate` into an instance method

We do not have to add more parameter to this method and related ones as
new structures are added & needed for translation.

* Add symbol only when PTC is enabled

Address LDj3SNuD's feedback

* Change `NativeContext.Running` to a 32-bit integer

* Fix PageTable symbol for host mapped
2021-05-29 18:06:28 -03:00

44 lines
No EOL
2.6 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 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;
}
}