Ryujinx/ARMeilleure/Translation/DirectCallStubs.cs
LDj3SNuD 5e724cf24e
Add Profiled Persistent Translation Cache. (#769)
* Delete DelegateTypes.cs

* Delete DelegateCache.cs

* Add files via upload

* Update Horizon.cs

* Update Program.cs

* Update MainWindow.cs

* Update Aot.cs

* Update RelocEntry.cs

* Update Translator.cs

* Update MemoryManager.cs

* Update InstEmitMemoryHelper.cs

* Update Delegates.cs

* Nit.

* Nit.

* Nit.

* 10 fewer MSIL bytes for us

* Add comment. Nits.

* Update Translator.cs

* Update Aot.cs

* Nits.

* Opt..

* Opt..

* Opt..

* Opt..

* Allow to change compression level.

* Update MemoryManager.cs

* Update Translator.cs

* Manage corner cases during the save phase. Nits.

* Update Aot.cs

* Translator response tweak for Aot disabled. Nit.

* Nit.

* Nits.

* Create DelegateHelpers.cs

* Update Delegates.cs

* Nit.

* Nit.

* Nits.

* Fix due to #784.

* Fixes due to #757 & #841.

* Fix due to #846.

* Fix due to #847.

* Use MethodInfo for managed method calls.

Use IR methods instead of managed methods about Max/Min (S/U).
Follow-ups & Nits.

* Add missing exception messages.

Reintroduce slow path for Fmov_Vi.
Implement slow path for Fmov_Si.

* Switch to the new folder structure.

Nits.

* Impl. index-based relocation information. Impl. cache file version field.

* Nit.

* Address gdkchan comments.

Mainly:
- fixed cache file corruption issue on exit; - exposed a way to disable AOT on the GUI.

* Address AcK77 comment.

* Address Thealexbarney, jduncanator & emmauss comments.

Header magic, CpuId (FI) & Aot -> Ptc.

* Adaptation to the new application reloading system.

Improvements to the call system of managed methods.
Follow-ups.
Nits.

* Get the same boot times as on master when PTC is disabled.

* Profiled Aot.

* A32 support (#897).

* #975 support (1 of 2).

* #975 support (2 of 2).

* Rebase fix & nits.

* Some fixes and nits (still one bug left).

* One fix & nits.

* Tests fix (by gdk) & nits.

* Support translations not only in high quality and rejit.

Nits.

* Added possibility to skip translations and continue execution, using `ESC` key.

* Update SettingsWindow.cs

* Update GLRenderer.cs

* Update Ptc.cs

* Disabled Profiled PTC by default as requested in the past by gdk.

* Fix rejit bug. Increased number of parallel translations. Add stack unwinding stuffs support (1 of 2).

Nits.

* Add stack unwinding stuffs support (2 of 2). Tuned number of parallel translations.

* Restored the ability to assemble jumps with 8-bit offset when Profiled PTC is disabled or during profiling.

Modifications due to rebase.
Nits.

* Limited profiling of the functions to be translated to the addresses belonging to the range of static objects only.

* Nits.

* Nits.

* Update Delegates.cs

* Nit.

* Update InstEmitSimdArithmetic.cs

* Address riperiperi comments.

* Fixed the issue of unjustifiably longer boot times at the second boot than at the first boot, measured at the same time or reference point and with the same number of translated functions.

* Implemented a simple redundant load/save mechanism.

Halved the value of Decoder.MaxInstsPerFunction more appropriate for the current performance of the Translator.
Replaced by Logger.PrintError to Logger.PrintDebug in TexturePool.cs about the supposed invalid texture format to avoid the spawn of the log.
Nits.

* Nit.

Improved Logger.PrintError in TexturePool.cs to avoid log spawn.
Added missing code for FZ handling (in output) for fp max/min instructions (slow paths).

* Add configuration migration for PTC

Co-authored-by: Thog <me@thog.eu>
2020-06-16 20:28:02 +02:00

121 lines
5.2 KiB
C#

using ARMeilleure.Instructions;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.State;
using System;
using System.Diagnostics;
using System.Runtime.InteropServices;
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
namespace ARMeilleure.Translation
{
static class DirectCallStubs
{
private delegate long GuestFunction(IntPtr nativeContextPtr);
private static IntPtr _directCallStubPtr;
private static IntPtr _directTailCallStubPtr;
private static IntPtr _indirectCallStubPtr;
private static IntPtr _indirectTailCallStubPtr;
private static readonly object _lock = new object();
private static bool _initialized;
public static void InitializeStubs()
{
if (_initialized) return;
lock (_lock)
{
if (_initialized) return;
_directCallStubPtr = Marshal.GetFunctionPointerForDelegate<GuestFunction>(GenerateDirectCallStub(false));
_directTailCallStubPtr = Marshal.GetFunctionPointerForDelegate<GuestFunction>(GenerateDirectCallStub(true));
_indirectCallStubPtr = Marshal.GetFunctionPointerForDelegate<GuestFunction>(GenerateIndirectCallStub(false));
_indirectTailCallStubPtr = Marshal.GetFunctionPointerForDelegate<GuestFunction>(GenerateIndirectCallStub(true));
_initialized = true;
}
}
public static IntPtr DirectCallStub(bool tailCall)
{
Debug.Assert(_initialized);
return tailCall ? _directTailCallStubPtr : _directCallStubPtr;
}
public static IntPtr IndirectCallStub(bool tailCall)
{
Debug.Assert(_initialized);
return tailCall ? _indirectTailCallStubPtr : _indirectCallStubPtr;
}
private static void EmitCall(EmitterContext context, Operand address, bool tailCall)
{
if (tailCall)
{
context.Tailcall(address, context.LoadArgument(OperandType.I64, 0));
}
else
{
context.Return(context.Call(address, OperandType.I64, context.LoadArgument(OperandType.I64, 0)));
}
}
/// <summary>
/// Generates a stub that is used to find function addresses. Used for direct calls when their jump table does not have the host address yet.
/// Takes a NativeContext like a translated guest function, and extracts the target address from the NativeContext.
/// When the target function is compiled in highCq, all table entries are updated to point to that function instead of this stub by the translator.
/// </summary>
private static GuestFunction GenerateDirectCallStub(bool tailCall)
{
EmitterContext context = new EmitterContext();
Operand nativeContextPtr = context.LoadArgument(OperandType.I64, 0);
Operand address = context.Load(OperandType.I64, context.Add(nativeContextPtr, Const((long)NativeContext.GetCallAddressOffset())));
address = context.BitwiseOr(address, Const(address.Type, 1)); // Set call flag.
Operand functionAddr = context.Call(typeof(NativeInterface).GetMethod(nameof(NativeInterface.GetFunctionAddress)), address);
EmitCall(context, functionAddr, tailCall);
ControlFlowGraph cfg = context.GetControlFlowGraph();
OperandType[] argTypes = new OperandType[] { OperandType.I64 };
return Compiler.Compile<GuestFunction>(cfg, argTypes, OperandType.I64, CompilerOptions.HighCq);
}
/// <summary>
/// Generates a stub that is used to find function addresses and add them to an indirect table.
/// Used for indirect calls entries (already claimed) when their jump table does not have the host address yet.
/// Takes a NativeContext like a translated guest function, and extracts the target indirect table entry from the NativeContext.
/// If the function we find is highCq, the entry in the table is updated to point to that function rather than this stub.
/// </summary>
private static GuestFunction GenerateIndirectCallStub(bool tailCall)
{
EmitterContext context = new EmitterContext();
Operand nativeContextPtr = context.LoadArgument(OperandType.I64, 0);
Operand entryAddress = context.Load(OperandType.I64, context.Add(nativeContextPtr, Const((long)NativeContext.GetCallAddressOffset())));
Operand address = context.Load(OperandType.I64, entryAddress);
// We need to find the missing function. If the function is HighCq, then it replaces this stub in the indirect table.
// Either way, we call it afterwards.
Operand functionAddr = context.Call(typeof(NativeInterface).GetMethod(nameof(NativeInterface.GetIndirectFunctionAddress)), address, entryAddress);
// Call and save the function.
EmitCall(context, functionAddr, tailCall);
ControlFlowGraph cfg = context.GetControlFlowGraph();
OperandType[] argTypes = new OperandType[] { OperandType.I64 };
return Compiler.Compile<GuestFunction>(cfg, argTypes, OperandType.I64, CompilerOptions.HighCq);
}
}
}