Archived
1
0
Fork 0
forked from Mirror/Ryujinx
This repository has been archived on 2024-10-11. You can view files and clone it, but cannot push or open issues or pull requests.
jinx/ARMeilleure/Instructions/InstEmitSystem.cs

115 lines
3.9 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 18:56:22 +00:00
using ARMeilleure.Decoders;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.Translation;
using System;
using static ARMeilleure.Instructions.InstEmitHelper;
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
namespace ARMeilleure.Instructions
{
static partial class InstEmit
{
private const int DczSizeLog2 = 4;
public static void Hint(ArmEmitterContext context)
{
// Execute as no-op.
}
public static void Isb(ArmEmitterContext context)
{
// Execute as no-op.
}
public static void Mrs(ArmEmitterContext context)
{
OpCodeSystem op = (OpCodeSystem)context.CurrOp;
Delegate dlg;
switch (GetPackedId(op))
{
case 0b11_011_0000_0000_001: dlg = new _U64(NativeInterface.GetCtrEl0); break;
case 0b11_011_0000_0000_111: dlg = new _U64(NativeInterface.GetDczidEl0); break;
case 0b11_011_0100_0100_000: dlg = new _U64(NativeInterface.GetFpcr); break;
case 0b11_011_0100_0100_001: dlg = new _U64(NativeInterface.GetFpsr); break;
case 0b11_011_1101_0000_010: dlg = new _U64(NativeInterface.GetTpidrEl0); break;
case 0b11_011_1101_0000_011: dlg = new _U64(NativeInterface.GetTpidr); break;
case 0b11_011_1110_0000_000: dlg = new _U64(NativeInterface.GetCntfrqEl0); break;
case 0b11_011_1110_0000_001: dlg = new _U64(NativeInterface.GetCntpctEl0); break;
default: throw new NotImplementedException($"Unknown MRS 0x{op.RawOpCode:X8} at 0x{op.Address:X16}.");
}
SetIntOrZR(context, op.Rt, context.Call(dlg));
}
public static void Msr(ArmEmitterContext context)
{
OpCodeSystem op = (OpCodeSystem)context.CurrOp;
Delegate dlg;
switch (GetPackedId(op))
{
case 0b11_011_0100_0100_000: dlg = new _Void_U64(NativeInterface.SetFpcr); break;
case 0b11_011_0100_0100_001: dlg = new _Void_U64(NativeInterface.SetFpsr); break;
case 0b11_011_1101_0000_010: dlg = new _Void_U64(NativeInterface.SetTpidrEl0); break;
default: throw new NotImplementedException($"Unknown MSR 0x{op.RawOpCode:X8} at 0x{op.Address:X16}.");
}
context.Call(dlg, GetIntOrZR(context, op.Rt));
}
public static void Nop(ArmEmitterContext context)
{
// Do nothing.
}
public static void Sys(ArmEmitterContext context)
{
// 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.
OpCodeSystem op = (OpCodeSystem)context.CurrOp;
switch (GetPackedId(op))
{
case 0b11_011_0111_0100_001:
{
// DC ZVA
Operand t = GetIntOrZR(context, op.Rt);
for (long offset = 0; offset < (4 << DczSizeLog2); offset += 8)
{
Operand address = context.Add(t, Const(offset));
context.Call(new _Void_U64_U64(NativeInterface.WriteUInt64), address, Const(0L));
}
break;
}
// No-op
case 0b11_011_0111_1110_001: //DC CIVAC
break;
}
}
private static int GetPackedId(OpCodeSystem 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;
}
}
}