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
This commit is contained in:
@ -1,8 +1,5 @@
|
||||
using Ryujinx.Tests.Unicorn.Native;
|
||||
using System;
|
||||
using System.Diagnostics.Contracts;
|
||||
using System.Runtime.Intrinsics;
|
||||
using System.Runtime.Intrinsics.X86;
|
||||
|
||||
namespace Ryujinx.Tests.Unicorn
|
||||
{
|
||||
@ -15,95 +12,96 @@ namespace Ryujinx.Tests.Unicorn
|
||||
get
|
||||
{
|
||||
return new IndexedProperty<int, ulong>(
|
||||
(int i) => GetX(i),
|
||||
(int i) => GetX(i),
|
||||
(int i, ulong value) => SetX(i, value));
|
||||
}
|
||||
}
|
||||
|
||||
public IndexedProperty<int, Vector128<float>> Q
|
||||
public IndexedProperty<int, SimdValue> Q
|
||||
{
|
||||
get
|
||||
{
|
||||
return new IndexedProperty<int, Vector128<float>>(
|
||||
(int i) => GetQ(i),
|
||||
(int i, Vector128<float> value) => SetQ(i, value));
|
||||
return new IndexedProperty<int, SimdValue>(
|
||||
(int i) => GetQ(i),
|
||||
(int i, SimdValue value) => SetQ(i, value));
|
||||
}
|
||||
}
|
||||
|
||||
public ulong LR
|
||||
{
|
||||
get { return GetRegister(ArmRegister.LR); }
|
||||
set { SetRegister(ArmRegister.LR, value); }
|
||||
get => GetRegister(ArmRegister.LR);
|
||||
set => SetRegister(ArmRegister.LR, value);
|
||||
}
|
||||
|
||||
public ulong SP
|
||||
{
|
||||
get { return GetRegister(ArmRegister.SP); }
|
||||
set { SetRegister(ArmRegister.SP, value); }
|
||||
get => GetRegister(ArmRegister.SP);
|
||||
set => SetRegister(ArmRegister.SP, value);
|
||||
}
|
||||
|
||||
public ulong PC
|
||||
{
|
||||
get { return GetRegister(ArmRegister.PC); }
|
||||
set { SetRegister(ArmRegister.PC, value); }
|
||||
get => GetRegister(ArmRegister.PC);
|
||||
set => SetRegister(ArmRegister.PC, value);
|
||||
}
|
||||
|
||||
public uint Pstate
|
||||
{
|
||||
get { return (uint)GetRegister(ArmRegister.PSTATE); }
|
||||
set { SetRegister(ArmRegister.PSTATE, (uint)value); }
|
||||
get => (uint)GetRegister(ArmRegister.PSTATE);
|
||||
set => SetRegister(ArmRegister.PSTATE, (uint)value);
|
||||
}
|
||||
|
||||
public int Fpcr
|
||||
{
|
||||
get { return (int)GetRegister(ArmRegister.FPCR); }
|
||||
set { SetRegister(ArmRegister.FPCR, (uint)value); }
|
||||
get => (int)GetRegister(ArmRegister.FPCR);
|
||||
set => SetRegister(ArmRegister.FPCR, (uint)value);
|
||||
}
|
||||
|
||||
public int Fpsr
|
||||
{
|
||||
get { return (int)GetRegister(ArmRegister.FPSR); }
|
||||
set { SetRegister(ArmRegister.FPSR, (uint)value); }
|
||||
get => (int)GetRegister(ArmRegister.FPSR);
|
||||
set => SetRegister(ArmRegister.FPSR, (uint)value);
|
||||
}
|
||||
|
||||
public bool OverflowFlag
|
||||
{
|
||||
get { return (Pstate & 0x10000000u) != 0; }
|
||||
set { Pstate = (Pstate & ~0x10000000u) | (value ? 0x10000000u : 0u); }
|
||||
get => (Pstate & 0x10000000u) != 0;
|
||||
set => Pstate = (Pstate & ~0x10000000u) | (value ? 0x10000000u : 0u);
|
||||
}
|
||||
|
||||
public bool CarryFlag
|
||||
{
|
||||
get { return (Pstate & 0x20000000u) != 0; }
|
||||
set { Pstate = (Pstate & ~0x20000000u) | (value ? 0x20000000u : 0u); }
|
||||
get => (Pstate & 0x20000000u) != 0;
|
||||
set => Pstate = (Pstate & ~0x20000000u) | (value ? 0x20000000u : 0u);
|
||||
}
|
||||
|
||||
public bool ZeroFlag
|
||||
{
|
||||
get { return (Pstate & 0x40000000u) != 0; }
|
||||
set { Pstate = (Pstate & ~0x40000000u) | (value ? 0x40000000u : 0u); }
|
||||
get => (Pstate & 0x40000000u) != 0;
|
||||
set => Pstate = (Pstate & ~0x40000000u) | (value ? 0x40000000u : 0u);
|
||||
}
|
||||
|
||||
public bool NegativeFlag
|
||||
{
|
||||
get { return (Pstate & 0x80000000u) != 0; }
|
||||
set { Pstate = (Pstate & ~0x80000000u) | (value ? 0x80000000u : 0u); }
|
||||
get => (Pstate & 0x80000000u) != 0;
|
||||
set => Pstate = (Pstate & ~0x80000000u) | (value ? 0x80000000u : 0u);
|
||||
}
|
||||
|
||||
public UnicornAArch64()
|
||||
{
|
||||
Interface.Checked(Interface.uc_open((uint)UnicornArch.UC_ARCH_ARM64, (uint)UnicornMode.UC_MODE_LITTLE_ENDIAN, out uc));
|
||||
Interface.Checked(Interface.uc_open(UnicornArch.UC_ARCH_ARM64, UnicornMode.UC_MODE_LITTLE_ENDIAN, out uc));
|
||||
|
||||
SetRegister(ArmRegister.CPACR_EL1, 0x00300000);
|
||||
}
|
||||
|
||||
~UnicornAArch64()
|
||||
{
|
||||
Interface.Checked(Interface.uc_close(uc));
|
||||
Interface.Checked(Native.Interface.uc_close(uc));
|
||||
}
|
||||
|
||||
public void RunForCount(ulong count)
|
||||
{
|
||||
Interface.Checked(Interface.uc_emu_start(uc, PC, 0xFFFFFFFFFFFFFFFFu, 0, count));
|
||||
Interface.Checked(Native.Interface.uc_emu_start(uc, this.PC, 0xFFFFFFFFFFFFFFFFu, 0, count));
|
||||
}
|
||||
|
||||
public void Step()
|
||||
@ -111,7 +109,7 @@ namespace Ryujinx.Tests.Unicorn
|
||||
RunForCount(1);
|
||||
}
|
||||
|
||||
internal static ArmRegister[] X_registers = new ArmRegister[31]
|
||||
private static ArmRegister[] XRegisters = new ArmRegister[31]
|
||||
{
|
||||
ArmRegister.X0,
|
||||
ArmRegister.X1,
|
||||
@ -146,7 +144,7 @@ namespace Ryujinx.Tests.Unicorn
|
||||
ArmRegister.X30,
|
||||
};
|
||||
|
||||
internal static ArmRegister[] Q_registers = new ArmRegister[32]
|
||||
private static ArmRegister[] QRegisters = new ArmRegister[32]
|
||||
{
|
||||
ArmRegister.Q0,
|
||||
ArmRegister.Q1,
|
||||
@ -182,97 +180,104 @@ namespace Ryujinx.Tests.Unicorn
|
||||
ArmRegister.Q31,
|
||||
};
|
||||
|
||||
internal ulong GetRegister(ArmRegister register)
|
||||
{
|
||||
byte[] value_bytes = new byte[8];
|
||||
Interface.Checked(Interface.uc_reg_read(uc, (int)register, value_bytes));
|
||||
return (ulong)BitConverter.ToInt64(value_bytes, 0);
|
||||
}
|
||||
|
||||
internal void SetRegister(ArmRegister register, ulong value)
|
||||
{
|
||||
byte[] value_bytes = BitConverter.GetBytes(value);
|
||||
Interface.Checked(Interface.uc_reg_write(uc, (int)register, value_bytes));
|
||||
}
|
||||
|
||||
internal Vector128<float> GetVector(ArmRegister register)
|
||||
{
|
||||
byte[] value_bytes = new byte[16];
|
||||
Interface.Checked(Interface.uc_reg_read(uc, (int)register, value_bytes));
|
||||
unsafe
|
||||
{
|
||||
fixed (byte* p = &value_bytes[0])
|
||||
{
|
||||
return Sse.LoadVector128((float*)p);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
internal void SetVector(ArmRegister register, Vector128<float> value)
|
||||
{
|
||||
byte[] value_bytes = new byte[16];
|
||||
unsafe
|
||||
{
|
||||
fixed (byte* p = &value_bytes[0])
|
||||
{
|
||||
Sse.Store((float*)p, value);
|
||||
}
|
||||
}
|
||||
Interface.Checked(Interface.uc_reg_write(uc, (int)register, value_bytes));
|
||||
}
|
||||
|
||||
public ulong GetX(int index)
|
||||
{
|
||||
Contract.Requires(index <= 30, "invalid register");
|
||||
if ((uint)index > 30)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(nameof(index));
|
||||
}
|
||||
|
||||
return GetRegister(X_registers[index]);
|
||||
return GetRegister(XRegisters[index]);
|
||||
}
|
||||
|
||||
public void SetX(int index, ulong value)
|
||||
{
|
||||
Contract.Requires(index <= 30, "invalid register");
|
||||
if ((uint)index > 30)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(nameof(index));
|
||||
}
|
||||
|
||||
SetRegister(X_registers[index], value);
|
||||
SetRegister(XRegisters[index], value);
|
||||
}
|
||||
|
||||
public Vector128<float> GetQ(int index)
|
||||
public SimdValue GetQ(int index)
|
||||
{
|
||||
Contract.Requires(index <= 31, "invalid vector");
|
||||
if ((uint)index > 31)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(nameof(index));
|
||||
}
|
||||
|
||||
return GetVector(Q_registers[index]);
|
||||
return GetVector(QRegisters[index]);
|
||||
}
|
||||
|
||||
public void SetQ(int index, Vector128<float> value)
|
||||
public void SetQ(int index, SimdValue value)
|
||||
{
|
||||
Contract.Requires(index <= 31, "invalid vector");
|
||||
if ((uint)index > 31)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(nameof(index));
|
||||
}
|
||||
|
||||
SetVector(Q_registers[index], value);
|
||||
SetVector(QRegisters[index], value);
|
||||
}
|
||||
|
||||
private ulong GetRegister(ArmRegister register)
|
||||
{
|
||||
byte[] data = new byte[8];
|
||||
|
||||
Interface.Checked(Native.Interface.uc_reg_read(uc, (int)register, data));
|
||||
|
||||
return (ulong)BitConverter.ToInt64(data, 0);
|
||||
}
|
||||
|
||||
private void SetRegister(ArmRegister register, ulong value)
|
||||
{
|
||||
byte[] data = BitConverter.GetBytes(value);
|
||||
|
||||
Interface.Checked(Interface.uc_reg_write(uc, (int)register, data));
|
||||
}
|
||||
|
||||
private SimdValue GetVector(ArmRegister register)
|
||||
{
|
||||
byte[] data = new byte[16];
|
||||
|
||||
Interface.Checked(Interface.uc_reg_read(uc, (int)register, data));
|
||||
|
||||
return new SimdValue(data);
|
||||
}
|
||||
|
||||
private void SetVector(ArmRegister register, SimdValue value)
|
||||
{
|
||||
byte[] data = value.ToArray();
|
||||
|
||||
Interface.Checked(Interface.uc_reg_write(uc, (int)register, data));
|
||||
}
|
||||
|
||||
public byte[] MemoryRead(ulong address, ulong size)
|
||||
{
|
||||
byte[] value = new byte[size];
|
||||
|
||||
Interface.Checked(Interface.uc_mem_read(uc, address, value, size));
|
||||
|
||||
return value;
|
||||
}
|
||||
|
||||
public byte MemoryRead8 (ulong address) { return MemoryRead(address, 1)[0]; }
|
||||
public UInt16 MemoryRead16(ulong address) { return (UInt16)BitConverter.ToInt16(MemoryRead(address, 2), 0); }
|
||||
public UInt32 MemoryRead32(ulong address) { return (UInt32)BitConverter.ToInt32(MemoryRead(address, 4), 0); }
|
||||
public UInt64 MemoryRead64(ulong address) { return (UInt64)BitConverter.ToInt64(MemoryRead(address, 8), 0); }
|
||||
public byte MemoryRead8 (ulong address) => MemoryRead(address, 1)[0];
|
||||
public UInt16 MemoryRead16(ulong address) => (UInt16)BitConverter.ToInt16(MemoryRead(address, 2), 0);
|
||||
public UInt32 MemoryRead32(ulong address) => (UInt32)BitConverter.ToInt32(MemoryRead(address, 4), 0);
|
||||
public UInt64 MemoryRead64(ulong address) => (UInt64)BitConverter.ToInt64(MemoryRead(address, 8), 0);
|
||||
|
||||
public void MemoryWrite(ulong address, byte[] value)
|
||||
{
|
||||
Interface.Checked(Interface.uc_mem_write(uc, address, value, (ulong)value.Length));
|
||||
}
|
||||
|
||||
public void MemoryWrite8 (ulong address, byte value) { MemoryWrite(address, new byte[]{value}); }
|
||||
public void MemoryWrite16(ulong address, Int16 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite16(ulong address, UInt16 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite32(ulong address, Int32 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite32(ulong address, UInt32 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite64(ulong address, Int64 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite64(ulong address, UInt64 value) { MemoryWrite(address, BitConverter.GetBytes(value)); }
|
||||
public void MemoryWrite8 (ulong address, byte value) => MemoryWrite(address, new byte[]{value});
|
||||
public void MemoryWrite16(ulong address, Int16 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
public void MemoryWrite16(ulong address, UInt16 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
public void MemoryWrite32(ulong address, Int32 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
public void MemoryWrite32(ulong address, UInt32 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
public void MemoryWrite64(ulong address, Int64 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
public void MemoryWrite64(ulong address, UInt64 value) => MemoryWrite(address, BitConverter.GetBytes(value));
|
||||
|
||||
public void MemoryMap(ulong address, ulong size, MemoryPermission permissions)
|
||||
{
|
||||
@ -289,21 +294,12 @@ namespace Ryujinx.Tests.Unicorn
|
||||
Interface.Checked(Interface.uc_mem_protect(uc, address, size, (uint)permissions));
|
||||
}
|
||||
|
||||
public void DumpMemoryInformation()
|
||||
{
|
||||
Interface.Checked(Interface.uc_mem_regions(uc, out IntPtr regions_raw, out uint length));
|
||||
Interface.MarshalArrayOf<UnicornMemoryRegion>(regions_raw, (int)length, out var regions);
|
||||
foreach (var region in regions)
|
||||
{
|
||||
Console.WriteLine("region: begin {0:X16} end {1:X16} perms {2:X8}", region.begin, region.end, region.perms);
|
||||
}
|
||||
}
|
||||
|
||||
public static bool IsAvailable()
|
||||
{
|
||||
try
|
||||
{
|
||||
Interface.uc_version(out uint major, out uint minor);
|
||||
Interface.uc_version(out _, out _);
|
||||
|
||||
return true;
|
||||
}
|
||||
catch (DllNotFoundException)
|
||||
|
Reference in New Issue
Block a user