From a731ab3a2aad56e6ceb8b4e2444a61353246295c Mon Sep 17 00:00:00 2001 From: gdkchan Date: Thu, 8 Aug 2019 15:56:22 -0300 Subject: 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 --- ARMeilleure/Instructions/NativeInterface.cs | 367 ++++++++++++++++++++++++++++ 1 file changed, 367 insertions(+) create mode 100644 ARMeilleure/Instructions/NativeInterface.cs (limited to 'ARMeilleure/Instructions/NativeInterface.cs') diff --git a/ARMeilleure/Instructions/NativeInterface.cs b/ARMeilleure/Instructions/NativeInterface.cs new file mode 100644 index 00000000..3a1e91c8 --- /dev/null +++ b/ARMeilleure/Instructions/NativeInterface.cs @@ -0,0 +1,367 @@ +using ARMeilleure.Memory; +using ARMeilleure.State; +using System; + +namespace ARMeilleure.Instructions +{ + static class NativeInterface + { + private const int ErgSizeLog2 = 4; + + private class ThreadContext + { + public ExecutionContext Context { get; } + public MemoryManager Memory { get; } + + public ulong ExclusiveAddress { get; set; } + public ulong ExclusiveValueLow { get; set; } + public ulong ExclusiveValueHigh { get; set; } + + public ThreadContext(ExecutionContext context, MemoryManager memory) + { + Context = context; + Memory = memory; + + ExclusiveAddress = ulong.MaxValue; + } + } + + [ThreadStatic] + private static ThreadContext _context; + + public static void RegisterThread(ExecutionContext context, MemoryManager memory) + { + _context = new ThreadContext(context, memory); + } + + public static void UnregisterThread() + { + _context = null; + } + + public static void Break(ulong address, int imm) + { + Statistics.PauseTimer(); + + GetContext().OnBreak(address, imm); + + Statistics.ResumeTimer(); + } + + public static void SupervisorCall(ulong address, int imm) + { + Statistics.PauseTimer(); + + GetContext().OnSupervisorCall(address, imm); + + Statistics.ResumeTimer(); + } + + public static void Undefined(ulong address, int opCode) + { + Statistics.PauseTimer(); + + GetContext().OnUndefined(address, opCode); + + Statistics.ResumeTimer(); + } + +#region "System registers" + public static ulong GetCtrEl0() + { + return (ulong)GetContext().CtrEl0; + } + + public static ulong GetDczidEl0() + { + return (ulong)GetContext().DczidEl0; + } + + public static ulong GetFpcr() + { + return (ulong)GetContext().Fpcr; + } + + public static ulong GetFpsr() + { + return (ulong)GetContext().Fpsr; + } + + public static ulong GetTpidrEl0() + { + return (ulong)GetContext().TpidrEl0; + } + + public static ulong GetTpidr() + { + return (ulong)GetContext().Tpidr; + } + + public static ulong GetCntfrqEl0() + { + return GetContext().CntfrqEl0; + } + + public static ulong GetCntpctEl0() + { + return GetContext().CntpctEl0; + } + + public static void SetFpcr(ulong value) + { + GetContext().Fpcr = (FPCR)value; + } + + public static void SetFpsr(ulong value) + { + GetContext().Fpsr = (FPSR)value; + } + + public static void SetTpidrEl0(ulong value) + { + GetContext().TpidrEl0 = (long)value; + } +#endregion + +#region "Read" + public static byte ReadByte(ulong address) + { + return GetMemoryManager().ReadByte((long)address); + } + + public static ushort ReadUInt16(ulong address) + { + return GetMemoryManager().ReadUInt16((long)address); + } + + public static uint ReadUInt32(ulong address) + { + return GetMemoryManager().ReadUInt32((long)address); + } + + public static ulong ReadUInt64(ulong address) + { + return GetMemoryManager().ReadUInt64((long)address); + } + + public static V128 ReadVector128(ulong address) + { + return GetMemoryManager().ReadVector128((long)address); + } +#endregion + +#region "Read exclusive" + public static byte ReadByteExclusive(ulong address) + { + byte value = _context.Memory.ReadByte((long)address); + + _context.ExclusiveAddress = GetMaskedExclusiveAddress(address); + _context.ExclusiveValueLow = value; + _context.ExclusiveValueHigh = 0; + + return value; + } + + public static ushort ReadUInt16Exclusive(ulong address) + { + ushort value = _context.Memory.ReadUInt16((long)address); + + _context.ExclusiveAddress = GetMaskedExclusiveAddress(address); + _context.ExclusiveValueLow = value; + _context.ExclusiveValueHigh = 0; + + return value; + } + + public static uint ReadUInt32Exclusive(ulong address) + { + uint value = _context.Memory.ReadUInt32((long)address); + + _context.ExclusiveAddress = GetMaskedExclusiveAddress(address); + _context.ExclusiveValueLow = value; + _context.ExclusiveValueHigh = 0; + + return value; + } + + public static ulong ReadUInt64Exclusive(ulong address) + { + ulong value = _context.Memory.ReadUInt64((long)address); + + _context.ExclusiveAddress = GetMaskedExclusiveAddress(address); + _context.ExclusiveValueLow = value; + _context.ExclusiveValueHigh = 0; + + return value; + } + + public static V128 ReadVector128Exclusive(ulong address) + { + V128 value = _context.Memory.AtomicLoadInt128((long)address); + + _context.ExclusiveAddress = GetMaskedExclusiveAddress(address); + _context.ExclusiveValueLow = value.GetUInt64(0); + _context.ExclusiveValueHigh = value.GetUInt64(1); + + return value; + } +#endregion + +#region "Write" + public static void WriteByte(ulong address, byte value) + { + GetMemoryManager().WriteByte((long)address, value); + } + + public static void WriteUInt16(ulong address, ushort value) + { + GetMemoryManager().WriteUInt16((long)address, value); + } + + public static void WriteUInt32(ulong address, uint value) + { + GetMemoryManager().WriteUInt32((long)address, value); + } + + public static void WriteUInt64(ulong address, ulong value) + { + GetMemoryManager().WriteUInt64((long)address, value); + } + + public static void WriteVector128(ulong address, V128 value) + { + GetMemoryManager().WriteVector128((long)address, value); + } +#endregion + +#region "Write exclusive" + public static int WriteByteExclusive(ulong address, byte value) + { + bool success = _context.ExclusiveAddress == GetMaskedExclusiveAddress(address); + + if (success) + { + success = _context.Memory.AtomicCompareExchangeByte( + (long)address, + (byte)_context.ExclusiveValueLow, + (byte)value); + + if (success) + { + ClearExclusive(); + } + } + + return success ? 0 : 1; + } + + public static int WriteUInt16Exclusive(ulong address, ushort value) + { + bool success = _context.ExclusiveAddress == GetMaskedExclusiveAddress(address); + + if (success) + { + success = _context.Memory.AtomicCompareExchangeInt16( + (long)address, + (short)_context.ExclusiveValueLow, + (short)value); + + if (success) + { + ClearExclusive(); + } + } + + return success ? 0 : 1; + } + + public static int WriteUInt32Exclusive(ulong address, uint value) + { + bool success = _context.ExclusiveAddress == GetMaskedExclusiveAddress(address); + + if (success) + { + success = _context.Memory.AtomicCompareExchangeInt32( + (long)address, + (int)_context.ExclusiveValueLow, + (int)value); + + if (success) + { + ClearExclusive(); + } + } + + return success ? 0 : 1; + } + + public static int WriteUInt64Exclusive(ulong address, ulong value) + { + bool success = _context.ExclusiveAddress == GetMaskedExclusiveAddress(address); + + if (success) + { + success = _context.Memory.AtomicCompareExchangeInt64( + (long)address, + (long)_context.ExclusiveValueLow, + (long)value); + + if (success) + { + ClearExclusive(); + } + } + + return success ? 0 : 1; + } + + public static int WriteVector128Exclusive(ulong address, V128 value) + { + bool success = _context.ExclusiveAddress == GetMaskedExclusiveAddress(address); + + if (success) + { + V128 expected = new V128(_context.ExclusiveValueLow, _context.ExclusiveValueHigh); + + success = _context.Memory.AtomicCompareExchangeInt128((long)address, expected, value); + + if (success) + { + ClearExclusive(); + } + } + + return success ? 0 : 1; + } +#endregion + + private static ulong GetMaskedExclusiveAddress(ulong address) + { + return address & ~((4UL << ErgSizeLog2) - 1); + } + + public static void ClearExclusive() + { + _context.ExclusiveAddress = ulong.MaxValue; + } + + public static void CheckSynchronization() + { + Statistics.PauseTimer(); + + GetContext().CheckInterrupt(); + + Statistics.ResumeTimer(); + } + + public static ExecutionContext GetContext() + { + return _context.Context; + } + + public static MemoryManager GetMemoryManager() + { + return _context.Memory; + } + } +} \ No newline at end of file -- cgit v1.2.3