2018-10-30 21:43:02 -04:00
|
|
|
using ChocolArm64.Decoders;
|
|
|
|
using ChocolArm64.State;
|
|
|
|
using ChocolArm64.Translation;
|
|
|
|
using System;
|
|
|
|
using System.Reflection;
|
|
|
|
using System.Reflection.Emit;
|
|
|
|
|
|
|
|
namespace ChocolArm64.Instructions
|
|
|
|
{
|
|
|
|
static partial class InstEmit
|
|
|
|
{
|
|
|
|
public static void Hint(ILEmitterCtx context)
|
|
|
|
{
|
2019-07-01 22:39:22 -04:00
|
|
|
// Execute as no-op.
|
2018-10-30 21:43:02 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
public static void Isb(ILEmitterCtx context)
|
|
|
|
{
|
2019-07-01 22:39:22 -04:00
|
|
|
// Execute as no-op.
|
2018-10-30 21:43:02 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
public static void Mrs(ILEmitterCtx context)
|
|
|
|
{
|
|
|
|
OpCodeSystem64 op = (OpCodeSystem64)context.CurrOp;
|
|
|
|
|
|
|
|
context.EmitLdarg(TranslatedSub.StateArgIdx);
|
|
|
|
|
|
|
|
string propName;
|
|
|
|
|
|
|
|
switch (GetPackedId(op))
|
|
|
|
{
|
|
|
|
case 0b11_011_0000_0000_001: propName = nameof(CpuThreadState.CtrEl0); break;
|
|
|
|
case 0b11_011_0000_0000_111: propName = nameof(CpuThreadState.DczidEl0); break;
|
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 14:56:22 -04:00
|
|
|
case 0b11_011_0100_0100_000: propName = nameof(CpuThreadState.CFpcr); break;
|
|
|
|
case 0b11_011_0100_0100_001: propName = nameof(CpuThreadState.CFpsr); break;
|
2018-10-30 21:43:02 -04:00
|
|
|
case 0b11_011_1101_0000_010: propName = nameof(CpuThreadState.TpidrEl0); break;
|
|
|
|
case 0b11_011_1101_0000_011: propName = nameof(CpuThreadState.Tpidr); break;
|
|
|
|
case 0b11_011_1110_0000_000: propName = nameof(CpuThreadState.CntfrqEl0); break;
|
|
|
|
case 0b11_011_1110_0000_001: propName = nameof(CpuThreadState.CntpctEl0); break;
|
|
|
|
|
|
|
|
default: throw new NotImplementedException($"Unknown MRS at {op.Position:x16}");
|
|
|
|
}
|
|
|
|
|
|
|
|
context.EmitCallPropGet(typeof(CpuThreadState), propName);
|
|
|
|
|
|
|
|
PropertyInfo propInfo = typeof(CpuThreadState).GetProperty(propName);
|
|
|
|
|
|
|
|
if (propInfo.PropertyType != typeof(long) &&
|
|
|
|
propInfo.PropertyType != typeof(ulong))
|
|
|
|
{
|
|
|
|
context.Emit(OpCodes.Conv_U8);
|
|
|
|
}
|
|
|
|
|
|
|
|
context.EmitStintzr(op.Rt);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static void Msr(ILEmitterCtx context)
|
|
|
|
{
|
|
|
|
OpCodeSystem64 op = (OpCodeSystem64)context.CurrOp;
|
|
|
|
|
|
|
|
context.EmitLdarg(TranslatedSub.StateArgIdx);
|
|
|
|
context.EmitLdintzr(op.Rt);
|
|
|
|
|
|
|
|
string propName;
|
|
|
|
|
|
|
|
switch (GetPackedId(op))
|
|
|
|
{
|
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 14:56:22 -04:00
|
|
|
case 0b11_011_0100_0100_000: propName = nameof(CpuThreadState.CFpcr); break;
|
|
|
|
case 0b11_011_0100_0100_001: propName = nameof(CpuThreadState.CFpsr); break;
|
2018-10-30 21:43:02 -04:00
|
|
|
case 0b11_011_1101_0000_010: propName = nameof(CpuThreadState.TpidrEl0); break;
|
|
|
|
|
|
|
|
default: throw new NotImplementedException($"Unknown MSR at {op.Position:x16}");
|
|
|
|
}
|
|
|
|
|
|
|
|
PropertyInfo propInfo = typeof(CpuThreadState).GetProperty(propName);
|
|
|
|
|
|
|
|
if (propInfo.PropertyType != typeof(long) &&
|
|
|
|
propInfo.PropertyType != typeof(ulong))
|
|
|
|
{
|
|
|
|
context.Emit(OpCodes.Conv_U4);
|
|
|
|
}
|
|
|
|
|
|
|
|
context.EmitCallPropSet(typeof(CpuThreadState), propName);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static void Nop(ILEmitterCtx context)
|
|
|
|
{
|
2019-07-01 22:39:22 -04:00
|
|
|
// Do nothing.
|
2018-10-30 21:43:02 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
public static void Sys(ILEmitterCtx context)
|
|
|
|
{
|
2019-07-01 22:39:22 -04:00
|
|
|
// This instruction is used to do some operations on the CPU like cache invalidation,
|
|
|
|
// address translation and the like.
|
|
|
|
// We treat it as no-op here since we don't have any cache being emulated anyway.
|
2018-10-30 21:43:02 -04:00
|
|
|
OpCodeSystem64 op = (OpCodeSystem64)context.CurrOp;
|
|
|
|
|
|
|
|
switch (GetPackedId(op))
|
|
|
|
{
|
|
|
|
case 0b11_011_0111_0100_001:
|
|
|
|
{
|
2019-07-01 22:39:22 -04:00
|
|
|
// DC ZVA
|
2018-10-30 21:43:02 -04:00
|
|
|
for (int offs = 0; offs < (4 << CpuThreadState.DczSizeLog2); offs += 8)
|
|
|
|
{
|
|
|
|
context.EmitLdintzr(op.Rt);
|
|
|
|
context.EmitLdc_I(offs);
|
|
|
|
|
|
|
|
context.Emit(OpCodes.Add);
|
|
|
|
|
|
|
|
context.EmitLdc_I8(0);
|
|
|
|
|
|
|
|
InstEmitMemoryHelper.EmitWriteCall(context, 3);
|
|
|
|
}
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2019-07-01 22:39:22 -04:00
|
|
|
// No-op
|
2018-10-30 21:43:02 -04:00
|
|
|
case 0b11_011_0111_1110_001: //DC CIVAC
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static int GetPackedId(OpCodeSystem64 op)
|
|
|
|
{
|
|
|
|
int id;
|
|
|
|
|
|
|
|
id = op.Op2 << 0;
|
|
|
|
id |= op.CRm << 3;
|
|
|
|
id |= op.CRn << 7;
|
|
|
|
id |= op.Op1 << 11;
|
|
|
|
id |= op.Op0 << 14;
|
|
|
|
|
|
|
|
return id;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|