Add a new JIT compiler for CPU code (#693)

* Start of the ARMeilleure project

* Refactoring around the old IRAdapter, now renamed to PreAllocator

* Optimize the LowestBitSet method

* Add CLZ support and fix CLS implementation

* Add missing Equals and GetHashCode overrides on some structs, misc small tweaks

* Implement the ByteSwap IR instruction, and some refactoring on the assembler

* Implement the DivideUI IR instruction and fix 64-bits IDIV

* Correct constant operand type on CSINC

* Move division instructions implementation to InstEmitDiv

* Fix destination type for the ConditionalSelect IR instruction

* Implement UMULH and SMULH, with new IR instructions

* Fix some issues with shift instructions

* Fix constant types for BFM instructions

* Fix up new tests using the new V128 struct

* Update tests

* Move DIV tests to a separate file

* Add support for calls, and some instructions that depends on them

* Start adding support for SIMD & FP types, along with some of the related ARM instructions

* Fix some typos and the divide instruction with FP operands

* Fix wrong method call on Clz_V

* Implement ARM FP & SIMD move instructions, Saddlv_V, and misc. fixes

* Implement SIMD logical instructions and more misc. fixes

* Fix PSRAD x86 instruction encoding, TRN, UABD and UABDL implementations

* Implement float conversion instruction, merge in LDj3SNuD fixes, and some other misc. fixes

* Implement SIMD shift instruction and fix Dup_V

* Add SCVTF and UCVTF (vector, fixed-point) variants to the opcode table

* Fix check with tolerance on tester

* Implement FP & SIMD comparison instructions, and some fixes

* Update FCVT (Scalar) encoding on the table to support the Half-float variants

* Support passing V128 structs, some cleanup on the register allocator, merge LDj3SNuD fixes

* Use old memory access methods, made a start on SIMD memory insts support, some fixes

* Fix float constant passed to functions, save and restore non-volatile XMM registers, other fixes

* Fix arguments count with struct return values, other fixes

* More instructions

* Misc. fixes and integrate LDj3SNuD fixes

* Update tests

* Add a faster linear scan allocator, unwinding support on windows, and other changes

* Update Ryujinx.HLE

* Update Ryujinx.Graphics

* Fix V128 return pointer passing, RCX is clobbered

* Update Ryujinx.Tests

* Update ITimeZoneService

* Stop using GetFunctionPointer as that can't be called from native code, misc. fixes and tweaks

* Use generic GetFunctionPointerForDelegate method and other tweaks

* Some refactoring on the code generator, assert on invalid operations and use a separate enum for intrinsics

* Remove some unused code on the assembler

* Fix REX.W prefix regression on float conversion instructions, add some sort of profiler

* Add hardware capability detection

* Fix regression on Sha1h and revert Fcm** changes

* Add SSE2-only paths on vector extract and insert, some refactoring on the pre-allocator

* Fix silly mistake introduced on last commit on CpuId

* Generate inline stack probes when the stack allocation is too large

* Initial support for the System-V ABI

* Support multiple destination operands

* Fix SSE2 VectorInsert8 path, and other fixes

* Change placement of XMM callee save and restore code to match other compilers

* Rename Dest to Destination and Inst to Instruction

* Fix a regression related to calls and the V128 type

* Add an extra space on comments to match code style

* Some refactoring

* Fix vector insert FP32 SSE2 path

* Port over the ARM32 instructions

* Avoid memory protection races on JIT Cache

* Another fix on VectorInsert FP32 (thanks to LDj3SNuD

* Float operands don't need to use the same register when VEX is supported

* Add a new register allocator, higher quality code for hot code (tier up), and other tweaks

* Some nits, small improvements on the pre allocator

* CpuThreadState is gone

* Allow changing CPU emulators with a config entry

* Add runtime identifiers on the ARMeilleure project

* Allow switching between CPUs through a config entry (pt. 2)

* Change win10-x64 to win-x64 on projects

* Update the Ryujinx project to use ARMeilleure

* Ensure that the selected register is valid on the hybrid allocator

* Allow exiting on returns to 0 (should fix test regression)

* Remove register assignments for most used variables on the hybrid allocator

* Do not use fixed registers as spill temp

* Add missing namespace and remove unneeded using

* Address PR feedback

* Fix types, etc

* Enable AssumeStrictAbiCompliance by default

* Ensure that Spill and Fill don't load or store any more than necessary

5 files changed, 122 insertions, 113 deletions

diff --git a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcHandler.cs b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcHandler.cs
index cf881a79..7509ae04 100644
--- a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcHandler.cs
+++ b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcHandler.cs
@@ -1,5 +1,4 @@
-using ChocolArm64.Events;
-using ChocolArm64.State;
+using ARMeilleure.State;
 using Ryujinx.HLE.HOS.Kernel.Process;
 using System;
 
@@ -7,9 +6,9 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 {
     partial class SvcHandler
     {
-        private Switch        _device;
-        private KProcess      _process;
-        private Horizon       _system;
+        private Switch   _device;
+        private KProcess _process;
+        private Horizon  _system;
 
         public SvcHandler(Switch device, KProcess process)
         {
@@ -20,16 +19,16 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 
         public void SvcCall(object sender, InstExceptionEventArgs e)
         {
-            Action<SvcHandler, CpuThreadState> svcFunc = SvcTable.GetSvcFunc(e.Id);
+            Action<SvcHandler, IExecutionContext> svcFunc = SvcTable.GetSvcFunc(e.Id);
 
             if (svcFunc == null)
             {
                 throw new NotImplementedException($"SVC 0x{e.Id:X4} is not implemented.");
             }
 
-            CpuThreadState threadState = (CpuThreadState)sender;
+            IExecutionContext context = (IExecutionContext)sender;
 
-            svcFunc(this, threadState);
+            svcFunc(this, context);
         }
     }
 }
\ No newline at end of file
diff --git a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcIpc.cs b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcIpc.cs
index eb7595c0..7c1c981b 100644
--- a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcIpc.cs
+++ b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcIpc.cs
@@ -83,7 +83,7 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 
         public KernelResult SendSyncRequest64(int handle)
         {
-            return SendSyncRequest((ulong)_system.Scheduler.GetCurrentThread().Context.ThreadState.Tpidr, 0x100, handle);
+            return SendSyncRequest((ulong)_system.Scheduler.GetCurrentThread().Context.Tpidr, 0x100, handle);
         }
 
         public KernelResult SendSyncRequestWithUserBuffer64(ulong messagePtr, ulong size, int handle)
diff --git a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcSystem.cs b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcSystem.cs
index 5f971131..094e1935 100644
--- a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcSystem.cs
+++ b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcSystem.cs
@@ -1,4 +1,4 @@
-using ChocolArm64.Memory;
+using ARMeilleure.Memory;
 using Ryujinx.Common;
 using Ryujinx.Common.Logging;
 using Ryujinx.HLE.Exceptions;
@@ -138,7 +138,7 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 
         public ulong GetSystemTick64()
         {
-            return _system.Scheduler.GetCurrentThread().Context.ThreadState.CntpctEl0;
+            return _system.Scheduler.GetCurrentThread().Context.CntpctEl0;
         }
 
         public KernelResult GetProcessId64(int handle, out long pid)
diff --git a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcTable.cs b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcTable.cs
index 23934649..c1a31da9 100644
--- a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcTable.cs
+++ b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcTable.cs
@@ -1,4 +1,4 @@
-using ChocolArm64.State;
+using ARMeilleure.State;
 using Ryujinx.Common.Logging;
 using Ryujinx.HLE.HOS.Kernel.Common;
 using System;
@@ -14,7 +14,7 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 
         private static Dictionary<int, string> _svcFuncs64;
 
-        private static Action<SvcHandler, CpuThreadState>[] _svcTable64;
+        private static Action<SvcHandler, IExecutionContext>[] _svcTable64;
 
         static SvcTable()
         {
@@ -77,10 +77,10 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
                 { 0x78, nameof(SvcHandler.UnmapProcessCodeMemory64)        }
             };
 
-            _svcTable64 = new Action<SvcHandler, CpuThreadState>[0x80];
+            _svcTable64 = new Action<SvcHandler, IExecutionContext>[0x80];
         }
 
-        public static Action<SvcHandler, CpuThreadState> GetSvcFunc(int svcId)
+        public static Action<SvcHandler, IExecutionContext> GetSvcFunc(int svcId)
         {
             if (_svcTable64[svcId] != null)
             {
@@ -95,9 +95,9 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
             return null;
         }
 
-        private static Action<SvcHandler, CpuThreadState> GenerateMethod(string svcName)
+        private static Action<SvcHandler, IExecutionContext> GenerateMethod(string svcName)
         {
-            Type[] argTypes = new Type[] { typeof(SvcHandler), typeof(CpuThreadState) };
+            Type[] argTypes = new Type[] { typeof(SvcHandler), typeof(IExecutionContext) };
 
             DynamicMethod method = new DynamicMethod(svcName, null, argTypes);
 
@@ -183,7 +183,11 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
                 generator.Emit(OpCodes.Conv_I);
 
                 generator.Emit(OpCodes.Ldarg_1);
-                generator.Emit(OpCodes.Ldfld, GetStateFieldX(byRefArgsCount + index));
+                generator.Emit(OpCodes.Ldc_I4, byRefArgsCount + index);
+
+                MethodInfo info = typeof(IExecutionContext).GetMethod(nameof(IExecutionContext.GetX));
+
+                generator.Emit(OpCodes.Call, info);
 
                 generator.Emit(OpCodes.Box, typeof(ulong));
 
@@ -227,7 +231,11 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
                 else
                 {
                     generator.Emit(OpCodes.Ldarg_1);
-                    generator.Emit(OpCodes.Ldfld, GetStateFieldX(byRefArgsCount + index));
+                    generator.Emit(OpCodes.Ldc_I4, byRefArgsCount + index);
+
+                    MethodInfo info = typeof(IExecutionContext).GetMethod(nameof(IExecutionContext.GetX));
+
+                    generator.Emit(OpCodes.Call, info);
 
                     ConvertToArgType(argType);
                 }
@@ -258,51 +266,44 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
 
                 generator.Emit(OpCodes.Stloc, tempLocal);
                 generator.Emit(OpCodes.Ldarg_1);
+                generator.Emit(OpCodes.Ldc_I4, outRegIndex++);
                 generator.Emit(OpCodes.Ldloc, tempLocal);
 
                 ConvertToFieldType(retType);
 
-                generator.Emit(OpCodes.Stfld, GetStateFieldX(outRegIndex++));
+                MethodInfo info = typeof(IExecutionContext).GetMethod(nameof(IExecutionContext.SetX));
+
+                generator.Emit(OpCodes.Call, info);
             }
 
             for (int index = 0; index < locals.Count; index++)
             {
                 generator.Emit(OpCodes.Ldarg_1);
+                generator.Emit(OpCodes.Ldc_I4, outRegIndex++);
                 generator.Emit(OpCodes.Ldloc, locals[index]);
 
                 ConvertToFieldType(locals[index].LocalType);
 
-                generator.Emit(OpCodes.Stfld, GetStateFieldX(outRegIndex++));
+                MethodInfo info = typeof(IExecutionContext).GetMethod(nameof(IExecutionContext.SetX));
+
+                generator.Emit(OpCodes.Call, info);
             }
 
             // Zero out the remaining unused registers.
             while (outRegIndex < SvcFuncMaxArguments)
             {
                 generator.Emit(OpCodes.Ldarg_1);
+                generator.Emit(OpCodes.Ldc_I4, outRegIndex++);
                 generator.Emit(OpCodes.Ldc_I8, 0L);
-                generator.Emit(OpCodes.Stfld, GetStateFieldX(outRegIndex++));
-            }
 
-            generator.Emit(OpCodes.Ret);
-
-            return (Action<SvcHandler, CpuThreadState>)method.CreateDelegate(typeof(Action<SvcHandler, CpuThreadState>));
-        }
+                MethodInfo info = typeof(IExecutionContext).GetMethod(nameof(IExecutionContext.SetX));
 
-        private static FieldInfo GetStateFieldX(int index)
-        {
-            switch (index)
-            {
-                case 0: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X0));
-                case 1: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X1));
-                case 2: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X2));
-                case 3: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X3));
-                case 4: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X4));
-                case 5: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X5));
-                case 6: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X6));
-                case 7: return typeof(CpuThreadState).GetField(nameof(CpuThreadState.X7));
+                generator.Emit(OpCodes.Call, info);
             }
 
-            throw new ArgumentOutOfRangeException(nameof(index));
+            generator.Emit(OpCodes.Ret);
+
+            return (Action<SvcHandler, IExecutionContext>)method.CreateDelegate(typeof(Action<SvcHandler, IExecutionContext>));
         }
 
         private static void CheckIfTypeIsSupported(Type type, string svcName)
diff --git a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcThread.cs b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcThread.cs
index e1f018c1..e49da023 100644
--- a/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcThread.cs
+++ b/Ryujinx.HLE/HOS/Kernel/SupervisorCall/SvcThread.cs
@@ -1,4 +1,5 @@
-using ChocolArm64.Memory;
+using ARMeilleure.Memory;
+using ARMeilleure.State;
 using Ryujinx.HLE.HOS.Kernel.Common;
 using Ryujinx.HLE.HOS.Kernel.Process;
 using Ryujinx.HLE.HOS.Kernel.Threading;
@@ -347,83 +348,91 @@ namespace Ryujinx.HLE.HOS.Kernel.SupervisorCall
                 return KernelResult.InvalidThread;
             }
 
-            MemoryManager memory = currentProcess.CpuMemory;
-
-            memory.WriteUInt64((long)address + 0x0,  thread.Context.ThreadState.X0);
-            memory.WriteUInt64((long)address + 0x8,  thread.Context.ThreadState.X1);
-            memory.WriteUInt64((long)address + 0x10, thread.Context.ThreadState.X2);
-            memory.WriteUInt64((long)address + 0x18, thread.Context.ThreadState.X3);
-            memory.WriteUInt64((long)address + 0x20, thread.Context.ThreadState.X4);
-            memory.WriteUInt64((long)address + 0x28, thread.Context.ThreadState.X5);
-            memory.WriteUInt64((long)address + 0x30, thread.Context.ThreadState.X6);
-            memory.WriteUInt64((long)address + 0x38, thread.Context.ThreadState.X7);
-            memory.WriteUInt64((long)address + 0x40, thread.Context.ThreadState.X8);
-            memory.WriteUInt64((long)address + 0x48, thread.Context.ThreadState.X9);
-            memory.WriteUInt64((long)address + 0x50, thread.Context.ThreadState.X10);
-            memory.WriteUInt64((long)address + 0x58, thread.Context.ThreadState.X11);
-            memory.WriteUInt64((long)address + 0x60, thread.Context.ThreadState.X12);
-            memory.WriteUInt64((long)address + 0x68, thread.Context.ThreadState.X13);
-            memory.WriteUInt64((long)address + 0x70, thread.Context.ThreadState.X14);
-            memory.WriteUInt64((long)address + 0x78, thread.Context.ThreadState.X15);
-            memory.WriteUInt64((long)address + 0x80, thread.Context.ThreadState.X16);
-            memory.WriteUInt64((long)address + 0x88, thread.Context.ThreadState.X17);
-            memory.WriteUInt64((long)address + 0x90, thread.Context.ThreadState.X18);
-            memory.WriteUInt64((long)address + 0x98, thread.Context.ThreadState.X19);
-            memory.WriteUInt64((long)address + 0xa0, thread.Context.ThreadState.X20);
-            memory.WriteUInt64((long)address + 0xa8, thread.Context.ThreadState.X21);
-            memory.WriteUInt64((long)address + 0xb0, thread.Context.ThreadState.X22);
-            memory.WriteUInt64((long)address + 0xb8, thread.Context.ThreadState.X23);
-            memory.WriteUInt64((long)address + 0xc0, thread.Context.ThreadState.X24);
-            memory.WriteUInt64((long)address + 0xc8, thread.Context.ThreadState.X25);
-            memory.WriteUInt64((long)address + 0xd0, thread.Context.ThreadState.X26);
-            memory.WriteUInt64((long)address + 0xd8, thread.Context.ThreadState.X27);
-            memory.WriteUInt64((long)address + 0xe0, thread.Context.ThreadState.X28);
-            memory.WriteUInt64((long)address + 0xe8, thread.Context.ThreadState.X29);
-            memory.WriteUInt64((long)address + 0xf0, thread.Context.ThreadState.X30);
-            memory.WriteUInt64((long)address + 0xf8, thread.Context.ThreadState.X31);
+            IMemoryManager memory = currentProcess.CpuMemory;
+
+            memory.WriteUInt64((long)address + 0x0,  thread.Context.GetX(0));
+            memory.WriteUInt64((long)address + 0x8,  thread.Context.GetX(1));
+            memory.WriteUInt64((long)address + 0x10, thread.Context.GetX(2));
+            memory.WriteUInt64((long)address + 0x18, thread.Context.GetX(3));
+            memory.WriteUInt64((long)address + 0x20, thread.Context.GetX(4));
+            memory.WriteUInt64((long)address + 0x28, thread.Context.GetX(5));
+            memory.WriteUInt64((long)address + 0x30, thread.Context.GetX(6));
+            memory.WriteUInt64((long)address + 0x38, thread.Context.GetX(7));
+            memory.WriteUInt64((long)address + 0x40, thread.Context.GetX(8));
+            memory.WriteUInt64((long)address + 0x48, thread.Context.GetX(9));
+            memory.WriteUInt64((long)address + 0x50, thread.Context.GetX(10));
+            memory.WriteUInt64((long)address + 0x58, thread.Context.GetX(11));
+            memory.WriteUInt64((long)address + 0x60, thread.Context.GetX(12));
+            memory.WriteUInt64((long)address + 0x68, thread.Context.GetX(13));
+            memory.WriteUInt64((long)address + 0x70, thread.Context.GetX(14));
+            memory.WriteUInt64((long)address + 0x78, thread.Context.GetX(15));
+            memory.WriteUInt64((long)address + 0x80, thread.Context.GetX(16));
+            memory.WriteUInt64((long)address + 0x88, thread.Context.GetX(17));
+            memory.WriteUInt64((long)address + 0x90, thread.Context.GetX(18));
+            memory.WriteUInt64((long)address + 0x98, thread.Context.GetX(19));
+            memory.WriteUInt64((long)address + 0xa0, thread.Context.GetX(20));
+            memory.WriteUInt64((long)address + 0xa8, thread.Context.GetX(21));
+            memory.WriteUInt64((long)address + 0xb0, thread.Context.GetX(22));
+            memory.WriteUInt64((long)address + 0xb8, thread.Context.GetX(23));
+            memory.WriteUInt64((long)address + 0xc0, thread.Context.GetX(24));
+            memory.WriteUInt64((long)address + 0xc8, thread.Context.GetX(25));
+            memory.WriteUInt64((long)address + 0xd0, thread.Context.GetX(26));
+            memory.WriteUInt64((long)address + 0xd8, thread.Context.GetX(27));
+            memory.WriteUInt64((long)address + 0xe0, thread.Context.GetX(28));
+            memory.WriteUInt64((long)address + 0xe8, thread.Context.GetX(29));
+            memory.WriteUInt64((long)address + 0xf0, thread.Context.GetX(30));
+            memory.WriteUInt64((long)address + 0xf8, thread.Context.GetX(31));
 
             memory.WriteInt64((long)address + 0x100, thread.LastPc);
 
-            memory.WriteUInt64((long)address + 0x108, (ulong)thread.Context.ThreadState.Psr);
-
-            memory.WriteVector128((long)address + 0x110, thread.Context.ThreadState.V0);
-            memory.WriteVector128((long)address + 0x120, thread.Context.ThreadState.V1);
-            memory.WriteVector128((long)address + 0x130, thread.Context.ThreadState.V2);
-            memory.WriteVector128((long)address + 0x140, thread.Context.ThreadState.V3);
-            memory.WriteVector128((long)address + 0x150, thread.Context.ThreadState.V4);
-            memory.WriteVector128((long)address + 0x160, thread.Context.ThreadState.V5);
-            memory.WriteVector128((long)address + 0x170, thread.Context.ThreadState.V6);
-            memory.WriteVector128((long)address + 0x180, thread.Context.ThreadState.V7);
-            memory.WriteVector128((long)address + 0x190, thread.Context.ThreadState.V8);
-            memory.WriteVector128((long)address + 0x1a0, thread.Context.ThreadState.V9);
-            memory.WriteVector128((long)address + 0x1b0, thread.Context.ThreadState.V10);
-            memory.WriteVector128((long)address + 0x1c0, thread.Context.ThreadState.V11);
-            memory.WriteVector128((long)address + 0x1d0, thread.Context.ThreadState.V12);
-            memory.WriteVector128((long)address + 0x1e0, thread.Context.ThreadState.V13);
-            memory.WriteVector128((long)address + 0x1f0, thread.Context.ThreadState.V14);
-            memory.WriteVector128((long)address + 0x200, thread.Context.ThreadState.V15);
-            memory.WriteVector128((long)address + 0x210, thread.Context.ThreadState.V16);
-            memory.WriteVector128((long)address + 0x220, thread.Context.ThreadState.V17);
-            memory.WriteVector128((long)address + 0x230, thread.Context.ThreadState.V18);
-            memory.WriteVector128((long)address + 0x240, thread.Context.ThreadState.V19);
-            memory.WriteVector128((long)address + 0x250, thread.Context.ThreadState.V20);
-            memory.WriteVector128((long)address + 0x260, thread.Context.ThreadState.V21);
-            memory.WriteVector128((long)address + 0x270, thread.Context.ThreadState.V22);
-            memory.WriteVector128((long)address + 0x280, thread.Context.ThreadState.V23);
-            memory.WriteVector128((long)address + 0x290, thread.Context.ThreadState.V24);
-            memory.WriteVector128((long)address + 0x2a0, thread.Context.ThreadState.V25);
-            memory.WriteVector128((long)address + 0x2b0, thread.Context.ThreadState.V26);
-            memory.WriteVector128((long)address + 0x2c0, thread.Context.ThreadState.V27);
-            memory.WriteVector128((long)address + 0x2d0, thread.Context.ThreadState.V28);
-            memory.WriteVector128((long)address + 0x2e0, thread.Context.ThreadState.V29);
-            memory.WriteVector128((long)address + 0x2f0, thread.Context.ThreadState.V30);
-            memory.WriteVector128((long)address + 0x300, thread.Context.ThreadState.V31);
-
-            memory.WriteInt32((long)address + 0x310, thread.Context.ThreadState.Fpcr);
-            memory.WriteInt32((long)address + 0x314, thread.Context.ThreadState.Fpsr);
-            memory.WriteInt64((long)address + 0x318, thread.Context.ThreadState.Tpidr);
+            memory.WriteUInt64((long)address + 0x108, (ulong)GetPsr(thread.Context));
+
+            memory.WriteVector128((long)address + 0x110, thread.Context.GetV(0));
+            memory.WriteVector128((long)address + 0x120, thread.Context.GetV(1));
+            memory.WriteVector128((long)address + 0x130, thread.Context.GetV(2));
+            memory.WriteVector128((long)address + 0x140, thread.Context.GetV(3));
+            memory.WriteVector128((long)address + 0x150, thread.Context.GetV(4));
+            memory.WriteVector128((long)address + 0x160, thread.Context.GetV(5));
+            memory.WriteVector128((long)address + 0x170, thread.Context.GetV(6));
+            memory.WriteVector128((long)address + 0x180, thread.Context.GetV(7));
+            memory.WriteVector128((long)address + 0x190, thread.Context.GetV(8));
+            memory.WriteVector128((long)address + 0x1a0, thread.Context.GetV(9));
+            memory.WriteVector128((long)address + 0x1b0, thread.Context.GetV(10));
+            memory.WriteVector128((long)address + 0x1c0, thread.Context.GetV(11));
+            memory.WriteVector128((long)address + 0x1d0, thread.Context.GetV(12));
+            memory.WriteVector128((long)address + 0x1e0, thread.Context.GetV(13));
+            memory.WriteVector128((long)address + 0x1f0, thread.Context.GetV(14));
+            memory.WriteVector128((long)address + 0x200, thread.Context.GetV(15));
+            memory.WriteVector128((long)address + 0x210, thread.Context.GetV(16));
+            memory.WriteVector128((long)address + 0x220, thread.Context.GetV(17));
+            memory.WriteVector128((long)address + 0x230, thread.Context.GetV(18));
+            memory.WriteVector128((long)address + 0x240, thread.Context.GetV(19));
+            memory.WriteVector128((long)address + 0x250, thread.Context.GetV(20));
+            memory.WriteVector128((long)address + 0x260, thread.Context.GetV(21));
+            memory.WriteVector128((long)address + 0x270, thread.Context.GetV(22));
+            memory.WriteVector128((long)address + 0x280, thread.Context.GetV(23));
+            memory.WriteVector128((long)address + 0x290, thread.Context.GetV(24));
+            memory.WriteVector128((long)address + 0x2a0, thread.Context.GetV(25));
+            memory.WriteVector128((long)address + 0x2b0, thread.Context.GetV(26));
+            memory.WriteVector128((long)address + 0x2c0, thread.Context.GetV(27));
+            memory.WriteVector128((long)address + 0x2d0, thread.Context.GetV(28));
+            memory.WriteVector128((long)address + 0x2e0, thread.Context.GetV(29));
+            memory.WriteVector128((long)address + 0x2f0, thread.Context.GetV(30));
+            memory.WriteVector128((long)address + 0x300, thread.Context.GetV(31));
+
+            memory.WriteInt32((long)address + 0x310, (int)thread.Context.Fpcr);
+            memory.WriteInt32((long)address + 0x314, (int)thread.Context.Fpsr);
+            memory.WriteInt64((long)address + 0x318, thread.Context.Tpidr);
 
             return KernelResult.Success;
         }
+
+        private static int GetPsr(IExecutionContext context)
+        {
+            return (context.GetPstateFlag(PState.NFlag) ? (1 << 31) : 0) |
+                   (context.GetPstateFlag(PState.ZFlag) ? (1 << 30) : 0) |
+                   (context.GetPstateFlag(PState.CFlag) ? (1 << 29) : 0) |
+                   (context.GetPstateFlag(PState.VFlag) ? (1 << 28) : 0);
+        }
     }
 }
\ No newline at end of file