forked from Mirror/Ryujinx
d904706fc0
* Implement Jump Table for Native Calls NOTE: this slows down rejit considerably! Not recommended to be used without codegen optimisation or AOT. - Does not work on Linux - A32 needs an additional commit. * A32 Support (WIP) * Actually write Direct Call pointers to the table That would help. * Direct Calls: Rather than returning to the translator, attempt to keep within the native stack frame. A return to the translator can still happen, but only by exceptionally bubbling up to it. Also: - Always translate lowCq as a function. Faster interop with the direct jumps, and this will be useful in future if we want to do speculative translation. - Tail Call Detection: after the decoding stage, detect if we do a tail call, and avoid translating into it. Detected if a jump is made to an address outwith the contiguous sequence of blocks surrounding the entry point. The goal is to reduce code touched by jit and rejit. * A32 Support * Use smaller max function size for lowCq, fix exceptional returns When a return has an unexpected value and there is no code block following this one, we now return the value rather than continuing. * CompareAndSwap (buggy) * Ensure CompareAndSwap does not get optimized away. * Use CompareAndSwap to make the dynamic table thread safe. * Tail call for linux, throw on too many arguments. * Combine CompareAndSwap 128 and 32/64. They emit different IR instructions since their PreAllocator behaviour is different, but now they just have one function on EmitterContext. * Fix issues separating from optimisations. * Use a stub to find and execute missing functions. This allows us to skip doing many runtime comparisons and branches, and reduces the amount of code we need to emit significantly. For the indirect call table, this stub also does the work of moving in the highCq address to the table when one is found. * Make Jump Tables and Jit Cache dynmically resize Reserve virtual memory, commit as needed. * Move TailCallRemover to its own class. * Multithreaded Translation (based on heuristic) A poor one, at that. Need to get core count for a better one, which means a lot of OS specific garbage. * Better priority management for background threads. * Bound core limit a bit more Past a certain point the load is not paralellizable and starts stealing from the main thread. Likely due to GC, memory, heap allocation thread contention. Reduce by one core til optimisations come to improve the situation. * Fix memory management on linux. * Temporary solution to some sync problems. This will make sure threads exit correctly, most of the time. There is a potential race where setting the sync counter to 0 does nothing (counter stays at what it was before, thread could take too long to exit), but we need to find a better way to do this anyways. Synchronization frequency has been tightened as we never enter blockwise segments of code. Essentially this means, check every x functions or loop iterations, before lowcq blocks existed and were worth just as much. Ideally it should be done in a better way, since functions can be anywhere from 1 to 5000 instructions. (maybe based on host timer, or an interrupt flag from a scheduler thread) * Address feedback minus CompareAndSwap change. * Use default ReservedRegion granularity. * Merge CompareAndSwap with its V128 variant. * We already got the source, no need to do it again. * Make sure all background translation threads exit. * Fix CompareAndSwap128 Detection criteria was a bit scuffed. * Address Comments.
94 lines
4.3 KiB
C#
94 lines
4.3 KiB
C#
using ARMeilleure.State;
|
|
using System;
|
|
|
|
namespace ARMeilleure.Instructions
|
|
{
|
|
delegate bool _Bool();
|
|
|
|
delegate double _F64_F64(double a1);
|
|
delegate double _F64_F64_Bool(double a1, bool a2);
|
|
delegate double _F64_F64_F64(double a1, double a2);
|
|
delegate double _F64_F64_F64_Bool(double a1, double a2, bool a3);
|
|
delegate double _F64_F64_F64_F64(double a1, double a2, double a3);
|
|
delegate double _F64_F64_F64_F64_Bool(double a1, double a2, double a3, bool a4);
|
|
delegate double _F64_F64_MidpointRounding(double a1, MidpointRounding a2);
|
|
|
|
delegate float _F32_F32(float a1);
|
|
delegate float _F32_F32_Bool(float a1, bool a2);
|
|
delegate float _F32_F32_F32(float a1, float a2);
|
|
delegate float _F32_F32_F32_Bool(float a1, float a2, bool a3);
|
|
delegate float _F32_F32_F32_F32(float a1, float a2, float a3);
|
|
delegate float _F32_F32_F32_F32_Bool(float a1, float a2, float a3, bool a4);
|
|
delegate float _F32_F32_MidpointRounding(float a1, MidpointRounding a2);
|
|
delegate float _F32_U16(ushort a1);
|
|
|
|
delegate int _S32_F32(float a1);
|
|
delegate int _S32_F32_F32_Bool(float a1, float a2, bool a3);
|
|
delegate int _S32_F64(double a1);
|
|
delegate int _S32_F64_F64_Bool(double a1, double a2, bool a3);
|
|
delegate int _S32_U64_U16(ulong a1, ushort a2);
|
|
delegate int _S32_U64_U32(ulong a1, uint a2);
|
|
delegate int _S32_U64_U64(ulong a1, ulong a2);
|
|
delegate int _S32_U64_U8(ulong a1, byte a2);
|
|
delegate int _S32_U64_V128(ulong a1, V128 a2);
|
|
|
|
delegate long _S64_F32(float a1);
|
|
delegate long _S64_F64(double a1);
|
|
delegate long _S64_S64(long a1);
|
|
delegate long _S64_S64_S32(long a1, int a2);
|
|
delegate long _S64_S64_S64(long a1, long a2);
|
|
delegate long _S64_S64_S64_Bool_S32(long a1, long a2, bool a3, int a4);
|
|
delegate long _S64_S64_S64_S32(long a1, long a2, int a3);
|
|
delegate long _S64_U64_S32(ulong a1, int a2);
|
|
delegate long _S64_U64_S64(ulong a1, long a2);
|
|
|
|
delegate ushort _U16_F32(float a1);
|
|
delegate ushort _U16_U64(ulong a1);
|
|
|
|
delegate uint _U32();
|
|
delegate uint _U32_F32(float a1);
|
|
delegate uint _U32_F64(double a1);
|
|
delegate uint _U32_U32(uint a1);
|
|
delegate uint _U32_U32_U16(uint a1, ushort a2);
|
|
delegate uint _U32_U32_U32(uint a1, uint a2);
|
|
delegate uint _U32_U32_U64(uint a1, ulong a2);
|
|
delegate uint _U32_U32_U8(uint a1, byte a2);
|
|
delegate uint _U32_U64(ulong a1);
|
|
|
|
delegate ulong _U64();
|
|
delegate ulong _U64_F32(float a1);
|
|
delegate ulong _U64_F64(double a1);
|
|
delegate ulong _U64_S64_S32(long a1, int a2);
|
|
delegate ulong _U64_S64_U64(long a1, ulong a2);
|
|
delegate ulong _U64_U64(ulong a1);
|
|
delegate ulong _U64_U64_S32(ulong a1, int a2);
|
|
delegate ulong _U64_U64_S64_S32(ulong a1, long a2, int a3);
|
|
delegate ulong _U64_U64_U64(ulong a1, ulong a2);
|
|
delegate ulong _U64_U64_U64_Bool_S32(ulong a1, ulong a2, bool a3, int a4);
|
|
|
|
delegate byte _U8_U64(ulong a1);
|
|
|
|
delegate V128 _V128_U64(ulong a1);
|
|
delegate V128 _V128_V128(V128 a1);
|
|
delegate V128 _V128_V128_S32_V128(V128 a1, int a2, V128 a3);
|
|
delegate V128 _V128_V128_S32_V128_V128(V128 a1, int a2, V128 a3, V128 a4);
|
|
delegate V128 _V128_V128_S32_V128_V128_V128(V128 a1, int a2, V128 a3, V128 a4, V128 a5);
|
|
delegate V128 _V128_V128_S32_V128_V128_V128_V128(V128 a1, int a2, V128 a3, V128 a4, V128 a5, V128 a6);
|
|
delegate V128 _V128_V128_U32_V128(V128 a1, uint a2, V128 a3);
|
|
delegate V128 _V128_V128_V128(V128 a1, V128 a2);
|
|
delegate V128 _V128_V128_V128_S32_V128(V128 a1, V128 a2, int a3, V128 a4);
|
|
delegate V128 _V128_V128_V128_S32_V128_V128(V128 a1, V128 a2, int a3, V128 a4, V128 a5);
|
|
delegate V128 _V128_V128_V128_S32_V128_V128_V128(V128 a1, V128 a2, int a3, V128 a4, V128 a5, V128 a6);
|
|
delegate V128 _V128_V128_V128_S32_V128_V128_V128_V128(V128 a1, V128 a2, int a3, V128 a4, V128 a5, V128 a6, V128 a7);
|
|
delegate V128 _V128_V128_V128_V128(V128 a1, V128 a2, V128 a3);
|
|
|
|
delegate void _Void();
|
|
delegate void _Void_U32(uint a1);
|
|
delegate void _Void_U64(ulong a1);
|
|
delegate void _Void_U64_S32(ulong a1, int a2);
|
|
delegate void _Void_U64_U16(ulong a1, ushort a2);
|
|
delegate void _Void_U64_U32(ulong a1, uint a2);
|
|
delegate void _Void_U64_U64(ulong a1, ulong a2);
|
|
delegate void _Void_U64_U8(ulong a1, byte a2);
|
|
delegate void _Void_U64_V128(ulong a1, V128 a2);
|
|
}
|