Ryujinx/ARMeilleure/Instructions/InstEmitHelper.cs

219 lines
7.4 KiB
C#
Raw Normal View History

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
2019-08-08 12:56:22 -06:00
using ARMeilleure.Decoders;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.State;
using ARMeilleure.Translation;
using System;
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
namespace ARMeilleure.Instructions
{
static class InstEmitHelper
{
public static bool IsThumb(OpCode op)
{
return op is OpCodeT16;
}
public static Operand GetExtendedM(ArmEmitterContext context, int rm, IntType type)
{
Operand value = GetIntOrZR(context, rm);
switch (type)
{
case IntType.UInt8: value = context.ZeroExtend8 (value.Type, value); break;
case IntType.UInt16: value = context.ZeroExtend16(value.Type, value); break;
case IntType.UInt32: value = context.ZeroExtend32(value.Type, value); break;
case IntType.Int8: value = context.SignExtend8 (value.Type, value); break;
case IntType.Int16: value = context.SignExtend16(value.Type, value); break;
case IntType.Int32: value = context.SignExtend32(value.Type, value); break;
}
return value;
}
public static Operand GetIntA32(ArmEmitterContext context, int regIndex)
{
if (regIndex == RegisterAlias.Aarch32Pc)
{
OpCode32 op = (OpCode32)context.CurrOp;
return Const((int)op.GetPc());
}
else
{
return GetIntOrSP(context, GetRegisterAlias(context.Mode, regIndex));
}
}
public static void SetIntA32(ArmEmitterContext context, int regIndex, Operand value)
{
if (regIndex == RegisterAlias.Aarch32Pc)
{
context.StoreToContext();
EmitBxWritePc(context, value);
}
else
{
SetIntOrSP(context, GetRegisterAlias(context.Mode, regIndex), value);
}
}
public static int GetRegisterAlias(Aarch32Mode mode, int regIndex)
{
// Only registers >= 8 are banked,
// with registers in the range [8, 12] being
// banked for the FIQ mode, and registers
// 13 and 14 being banked for all modes.
if ((uint)regIndex < 8)
{
return regIndex;
}
return GetBankedRegisterAlias(mode, regIndex);
}
public static int GetBankedRegisterAlias(Aarch32Mode mode, int regIndex)
{
switch (regIndex)
{
case 8: return mode == Aarch32Mode.Fiq
? RegisterAlias.R8Fiq
: RegisterAlias.R8Usr;
case 9: return mode == Aarch32Mode.Fiq
? RegisterAlias.R9Fiq
: RegisterAlias.R9Usr;
case 10: return mode == Aarch32Mode.Fiq
? RegisterAlias.R10Fiq
: RegisterAlias.R10Usr;
case 11: return mode == Aarch32Mode.Fiq
? RegisterAlias.R11Fiq
: RegisterAlias.R11Usr;
case 12: return mode == Aarch32Mode.Fiq
? RegisterAlias.R12Fiq
: RegisterAlias.R12Usr;
case 13:
switch (mode)
{
case Aarch32Mode.User:
case Aarch32Mode.System: return RegisterAlias.SpUsr;
case Aarch32Mode.Fiq: return RegisterAlias.SpFiq;
case Aarch32Mode.Irq: return RegisterAlias.SpIrq;
case Aarch32Mode.Supervisor: return RegisterAlias.SpSvc;
case Aarch32Mode.Abort: return RegisterAlias.SpAbt;
case Aarch32Mode.Hypervisor: return RegisterAlias.SpHyp;
case Aarch32Mode.Undefined: return RegisterAlias.SpUnd;
default: throw new ArgumentException(nameof(mode));
}
case 14:
switch (mode)
{
case Aarch32Mode.User:
case Aarch32Mode.Hypervisor:
case Aarch32Mode.System: return RegisterAlias.LrUsr;
case Aarch32Mode.Fiq: return RegisterAlias.LrFiq;
case Aarch32Mode.Irq: return RegisterAlias.LrIrq;
case Aarch32Mode.Supervisor: return RegisterAlias.LrSvc;
case Aarch32Mode.Abort: return RegisterAlias.LrAbt;
case Aarch32Mode.Undefined: return RegisterAlias.LrUnd;
default: throw new ArgumentException(nameof(mode));
}
default: throw new ArgumentOutOfRangeException(nameof(regIndex));
}
}
public static void EmitBxWritePc(ArmEmitterContext context, Operand pc)
{
Operand mode = context.BitwiseAnd(pc, Const(1));
SetFlag(context, PState.TFlag, mode);
Operand lblArmMode = Label();
context.BranchIfTrue(lblArmMode, mode);
context.Return(context.ZeroExtend32(OperandType.I64, context.BitwiseAnd(pc, Const(~1))));
context.MarkLabel(lblArmMode);
context.Return(context.ZeroExtend32(OperandType.I64, context.BitwiseAnd(pc, Const(~3))));
}
public static Operand GetIntOrZR(ArmEmitterContext context, int regIndex)
{
if (regIndex == RegisterConsts.ZeroIndex)
{
OperandType type = context.CurrOp.GetOperandType();
return type == OperandType.I32 ? Const(0) : Const(0L);
}
else
{
return GetIntOrSP(context, regIndex);
}
}
public static void SetIntOrZR(ArmEmitterContext context, int regIndex, Operand value)
{
if (regIndex == RegisterConsts.ZeroIndex)
{
return;
}
SetIntOrSP(context, regIndex, value);
}
public static Operand GetIntOrSP(ArmEmitterContext context, int regIndex)
{
Operand value = Register(regIndex, RegisterType.Integer, OperandType.I64);
if (context.CurrOp.RegisterSize == RegisterSize.Int32)
{
value = context.ConvertI64ToI32(value);
}
return value;
}
public static void SetIntOrSP(ArmEmitterContext context, int regIndex, Operand value)
{
Operand reg = Register(regIndex, RegisterType.Integer, OperandType.I64);
if (value.Type == OperandType.I32)
{
value = context.ZeroExtend32(OperandType.I64, value);
}
context.Copy(reg, value);
}
public static Operand GetVec(int regIndex)
{
return Register(regIndex, RegisterType.Vector, OperandType.V128);
}
public static Operand GetFlag(PState stateFlag)
{
return Register((int)stateFlag, RegisterType.Flag, OperandType.I32);
}
public static void SetFlag(ArmEmitterContext context, PState stateFlag, Operand value)
{
context.Copy(GetFlag(stateFlag), value);
context.MarkFlagSet(stateFlag);
}
}
}