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/InstEmitMemory32.cs | 256 +++++++++++++++++++++++++++ 1 file changed, 256 insertions(+) create mode 100644 ARMeilleure/Instructions/InstEmitMemory32.cs (limited to 'ARMeilleure/Instructions/InstEmitMemory32.cs') diff --git a/ARMeilleure/Instructions/InstEmitMemory32.cs b/ARMeilleure/Instructions/InstEmitMemory32.cs new file mode 100644 index 00000000..002d2c5c --- /dev/null +++ b/ARMeilleure/Instructions/InstEmitMemory32.cs @@ -0,0 +1,256 @@ +using ARMeilleure.Decoders; +using ARMeilleure.IntermediateRepresentation; +using ARMeilleure.State; +using ARMeilleure.Translation; +using System; + +using static ARMeilleure.Instructions.InstEmitHelper; +using static ARMeilleure.Instructions.InstEmitMemoryHelper; +using static ARMeilleure.IntermediateRepresentation.OperandHelper; + +namespace ARMeilleure.Instructions +{ + static partial class InstEmit32 + { + private const int ByteSizeLog2 = 0; + private const int HWordSizeLog2 = 1; + private const int WordSizeLog2 = 2; + private const int DWordSizeLog2 = 3; + + [Flags] + enum AccessType + { + Store = 0, + Signed = 1, + Load = 2, + + LoadZx = Load, + LoadSx = Load | Signed, + } + + public static void Ldm(ArmEmitterContext context) + { + OpCode32MemMult op = (OpCode32MemMult)context.CurrOp; + + Operand n = GetIntA32(context, op.Rn); + + Operand baseAddress = context.Add(n, Const(op.Offset)); + + bool writesToPc = (op.RegisterMask & (1 << RegisterAlias.Aarch32Pc)) != 0; + + bool writeBack = op.PostOffset != 0 && (op.Rn != RegisterAlias.Aarch32Pc || !writesToPc); + + if (writeBack) + { + SetIntA32(context, op.Rn, context.Add(n, Const(op.PostOffset))); + } + + int mask = op.RegisterMask; + int offset = 0; + + for (int register = 0; mask != 0; mask >>= 1, register++) + { + if ((mask & 1) != 0) + { + Operand address = context.Add(baseAddress, Const(offset)); + + EmitLoadZx(context, address, register, WordSizeLog2); + + offset += 4; + } + } + } + + public static void Ldr(ArmEmitterContext context) + { + EmitLoadOrStore(context, WordSizeLog2, AccessType.LoadZx); + } + + public static void Ldrb(ArmEmitterContext context) + { + EmitLoadOrStore(context, ByteSizeLog2, AccessType.LoadZx); + } + + public static void Ldrd(ArmEmitterContext context) + { + EmitLoadOrStore(context, DWordSizeLog2, AccessType.LoadZx); + } + + public static void Ldrh(ArmEmitterContext context) + { + EmitLoadOrStore(context, HWordSizeLog2, AccessType.LoadZx); + } + + public static void Ldrsb(ArmEmitterContext context) + { + EmitLoadOrStore(context, ByteSizeLog2, AccessType.LoadSx); + } + + public static void Ldrsh(ArmEmitterContext context) + { + EmitLoadOrStore(context, HWordSizeLog2, AccessType.LoadSx); + } + + public static void Stm(ArmEmitterContext context) + { + OpCode32MemMult op = (OpCode32MemMult)context.CurrOp; + + Operand n = GetIntA32(context, op.Rn); + + Operand baseAddress = context.Add(n, Const(op.Offset)); + + int mask = op.RegisterMask; + int offset = 0; + + for (int register = 0; mask != 0; mask >>= 1, register++) + { + if ((mask & 1) != 0) + { + Operand address = context.Add(baseAddress, Const(offset)); + + EmitStore(context, address, register, WordSizeLog2); + + // Note: If Rn is also specified on the register list, + // and Rn is the first register on this list, then the + // value that is written to memory is the unmodified value, + // before the write back. If it is on the list, but it's + // not the first one, then the value written to memory + // varies between CPUs. + if (offset == 0 && op.PostOffset != 0) + { + // Emit write back after the first write. + SetIntA32(context, op.Rn, context.Add(n, Const(op.PostOffset))); + } + + offset += 4; + } + } + } + + public static void Str(ArmEmitterContext context) + { + EmitLoadOrStore(context, WordSizeLog2, AccessType.Store); + } + + public static void Strb(ArmEmitterContext context) + { + EmitLoadOrStore(context, ByteSizeLog2, AccessType.Store); + } + + public static void Strd(ArmEmitterContext context) + { + EmitLoadOrStore(context, DWordSizeLog2, AccessType.Store); + } + + public static void Strh(ArmEmitterContext context) + { + EmitLoadOrStore(context, HWordSizeLog2, AccessType.Store); + } + + private static void EmitLoadOrStore(ArmEmitterContext context, int size, AccessType accType) + { + OpCode32Mem op = (OpCode32Mem)context.CurrOp; + + Operand n = context.Copy(GetIntA32(context, op.Rn)); + + Operand temp = null; + + if (op.Index || op.WBack) + { + temp = op.Add + ? context.Add (n, Const(op.Immediate)) + : context.Subtract(n, Const(op.Immediate)); + } + + if (op.WBack) + { + SetIntA32(context, op.Rn, temp); + } + + Operand address; + + if (op.Index) + { + address = temp; + } + else + { + address = n; + } + + if ((accType & AccessType.Load) != 0) + { + void Load(int rt, int offs, int loadSize) + { + Operand addr = context.Add(address, Const(offs)); + + if ((accType & AccessType.Signed) != 0) + { + EmitLoadSx32(context, addr, rt, loadSize); + } + else + { + EmitLoadZx(context, addr, rt, loadSize); + } + } + + if (size == DWordSizeLog2) + { + Operand lblBigEndian = Label(); + Operand lblEnd = Label(); + + context.BranchIfTrue(lblBigEndian, GetFlag(PState.EFlag)); + + Load(op.Rt, 0, WordSizeLog2); + Load(op.Rt | 1, 4, WordSizeLog2); + + context.Branch(lblEnd); + + context.MarkLabel(lblBigEndian); + + Load(op.Rt | 1, 0, WordSizeLog2); + Load(op.Rt, 4, WordSizeLog2); + + context.MarkLabel(lblEnd); + } + else + { + Load(op.Rt, 0, size); + } + } + else + { + void Store(int rt, int offs, int storeSize) + { + Operand addr = context.Add(address, Const(offs)); + + EmitStore(context, addr, rt, storeSize); + } + + if (size == DWordSizeLog2) + { + Operand lblBigEndian = Label(); + Operand lblEnd = Label(); + + context.BranchIfTrue(lblBigEndian, GetFlag(PState.EFlag)); + + Store(op.Rt, 0, WordSizeLog2); + Store(op.Rt | 1, 4, WordSizeLog2); + + context.Branch(lblEnd); + + context.MarkLabel(lblBigEndian); + + Store(op.Rt | 1, 0, WordSizeLog2); + Store(op.Rt, 4, WordSizeLog2); + + context.MarkLabel(lblEnd); + } + else + { + Store(op.Rt, 0, size); + } + } + } + } +} \ No newline at end of file -- cgit v1.2.3