rjx-mirror/ARMeilleure/Decoders/Decoder.cs

366 lines
12 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.Instructions;
using ARMeilleure.Memory;
using ARMeilleure.State;
using System;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.Reflection.Emit;
namespace ARMeilleure.Decoders
{
static class Decoder
{
// We define a limit on the number of instructions that a function may have,
// this prevents functions being potentially too large, which would
// take too long to compile and use too much memory.
private const int MaxInstsPerFunction = 5000;
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
private delegate object MakeOp(InstDescriptor inst, ulong address, int opCode);
private static ConcurrentDictionary<Type, MakeOp> _opActivators;
static Decoder()
{
_opActivators = new ConcurrentDictionary<Type, MakeOp>();
}
public static Block[] DecodeBasicBlock(MemoryManager memory, ulong address, ExecutionMode mode)
{
Block block = new Block(address);
FillBlock(memory, mode, block, ulong.MaxValue);
return new Block[] { block };
}
public static Block[] DecodeFunction(MemoryManager memory, ulong address, ExecutionMode mode)
{
List<Block> blocks = new List<Block>();
Queue<Block> workQueue = new Queue<Block>();
Dictionary<ulong, Block> visited = new Dictionary<ulong, Block>();
int opsCount = 0;
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
Block GetBlock(ulong blkAddress)
{
if (!visited.TryGetValue(blkAddress, out Block block))
{
if (opsCount > MaxInstsPerFunction || !memory.IsMapped((long)blkAddress))
{
return null;
}
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
block = new Block(blkAddress);
workQueue.Enqueue(block);
visited.Add(blkAddress, block);
}
return block;
}
GetBlock(address);
while (workQueue.TryDequeue(out Block currBlock))
{
// Check if the current block is inside another block.
if (BinarySearch(blocks, currBlock.Address, out int nBlkIndex))
{
Block nBlock = blocks[nBlkIndex];
if (nBlock.Address == currBlock.Address)
{
throw new InvalidOperationException("Found duplicate block address on the list.");
}
nBlock.Split(currBlock);
blocks.Insert(nBlkIndex + 1, currBlock);
continue;
}
// If we have a block after the current one, set the limit address.
ulong limitAddress = ulong.MaxValue;
if (nBlkIndex != blocks.Count)
{
Block nBlock = blocks[nBlkIndex];
int nextIndex = nBlkIndex + 1;
if (nBlock.Address < currBlock.Address && nextIndex < blocks.Count)
{
limitAddress = blocks[nextIndex].Address;
}
else if (nBlock.Address > currBlock.Address)
{
limitAddress = blocks[nBlkIndex].Address;
}
}
FillBlock(memory, mode, currBlock, limitAddress);
opsCount += currBlock.OpCodes.Count;
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
if (currBlock.OpCodes.Count != 0)
{
// Set child blocks. "Branch" is the block the branch instruction
// points to (when taken), "Next" is the block at the next address,
// executed when the branch is not taken. For Unconditional Branches
// (except BL/BLR that are sub calls) or end of executable, Next is null.
OpCode lastOp = currBlock.GetLastOp();
bool isCall = IsCall(lastOp);
if (lastOp is IOpCodeBImm op && !isCall)
{
currBlock.Branch = GetBlock((ulong)op.Immediate);
}
if (!IsUnconditionalBranch(lastOp) /*|| isCall*/)
{
currBlock.Next = GetBlock(currBlock.EndAddress);
}
}
// Insert the new block on the list (sorted by address).
if (blocks.Count != 0)
{
Block nBlock = blocks[nBlkIndex];
blocks.Insert(nBlkIndex + (nBlock.Address < currBlock.Address ? 1 : 0), currBlock);
}
else
{
blocks.Add(currBlock);
}
}
return blocks.ToArray();
}
private static bool BinarySearch(List<Block> blocks, ulong address, out int index)
{
index = 0;
int left = 0;
int right = blocks.Count - 1;
while (left <= right)
{
int size = right - left;
int middle = left + (size >> 1);
Block block = blocks[middle];
index = middle;
if (address >= block.Address && address < block.EndAddress)
{
return true;
}
if (address < block.Address)
{
right = middle - 1;
}
else
{
left = middle + 1;
}
}
return false;
}
private static void FillBlock(
MemoryManager memory,
ExecutionMode mode,
Block block,
ulong limitAddress)
{
ulong address = block.Address;
OpCode opCode;
do
{
if (address >= limitAddress)
{
break;
}
opCode = DecodeOpCode(memory, address, mode);
block.OpCodes.Add(opCode);
address += (ulong)opCode.OpCodeSizeInBytes;
}
while (!(IsBranch(opCode) || IsException(opCode)));
block.EndAddress = address;
}
private static bool IsBranch(OpCode opCode)
{
return opCode is OpCodeBImm ||
opCode is OpCodeBReg || IsAarch32Branch(opCode);
}
private static bool IsUnconditionalBranch(OpCode opCode)
{
return opCode is OpCodeBImmAl ||
opCode is OpCodeBReg || IsAarch32UnconditionalBranch(opCode);
}
private static bool IsAarch32UnconditionalBranch(OpCode opCode)
{
if (!(opCode is OpCode32 op))
{
return false;
}
// Note: On ARM32, most instructions have conditional execution,
// so there's no "Always" (unconditional) branch like on ARM64.
// We need to check if the condition is "Always" instead.
return IsAarch32Branch(op) && op.Cond >= Condition.Al;
}
private static bool IsAarch32Branch(OpCode opCode)
{
// Note: On ARM32, most ALU operations can write to R15 (PC),
// so we must consider such operations as a branch in potential aswell.
if (opCode is IOpCode32Alu opAlu && opAlu.Rd == RegisterAlias.Aarch32Pc)
{
return true;
}
// Same thing for memory operations. We have the cases where PC is a target
// register (Rt == 15 or (mask & (1 << 15)) != 0), and cases where there is
// a write back to PC (wback == true && Rn == 15), however the later may
// be "undefined" depending on the CPU, so compilers should not produce that.
if (opCode is IOpCode32Mem || opCode is IOpCode32MemMult)
{
int rt, rn;
bool wBack, isLoad;
if (opCode is IOpCode32Mem opMem)
{
rt = opMem.Rt;
rn = opMem.Rn;
wBack = opMem.WBack;
isLoad = opMem.IsLoad;
// For the dual load, we also need to take into account the
// case were Rt2 == 15 (PC).
if (rt == 14 && opMem.Instruction.Name == InstName.Ldrd)
{
rt = RegisterAlias.Aarch32Pc;
}
}
else if (opCode is IOpCode32MemMult opMemMult)
{
const int pcMask = 1 << RegisterAlias.Aarch32Pc;
rt = (opMemMult.RegisterMask & pcMask) != 0 ? RegisterAlias.Aarch32Pc : 0;
rn = opMemMult.Rn;
wBack = opMemMult.PostOffset != 0;
isLoad = opMemMult.IsLoad;
}
else
{
throw new NotImplementedException($"The type \"{opCode.GetType().Name}\" is not implemented on the decoder.");
}
if ((rt == RegisterAlias.Aarch32Pc && isLoad) ||
(rn == RegisterAlias.Aarch32Pc && wBack))
{
return true;
}
}
// Explicit branch instructions.
return opCode is IOpCode32BImm ||
opCode is IOpCode32BReg;
}
private static bool IsCall(OpCode opCode)
{
return opCode.Instruction.Name == InstName.Bl ||
Add most of the A32 instruction set to ARMeilleure (#897) * Implement TEQ and MOV (Imm16) * Initial work on A32 instructions + SVC. No tests yet, hangs in rtld. * Implement CLZ, fix BFI and BFC Now stops on SIMD initialization. * Exclusive access instructions, fix to mul, system instructions. Now gets to a break after SignalProcessWideKey64. * Better impl of UBFX, add UDIV and SDIV Now boots way further - now stuck on VMOV instruction. * Many more instructions, start on SIMD and testing framework. * Fix build issues * svc: Rework 32 bit codepath Fixing once and for all argument ordering issues. * Fix 32 bits stacktrace * hle debug: Add 32 bits dynamic section parsing * Fix highCq mode, add many tests, fix some instruction bugs Still suffers from critical malloc failure :weary: * Fix incorrect opcode decoders and a few more instructions. * Add a few instructions and fix others. re-disable highCq for now. Disabled the svc memory clear since i'm not sure about it. * Fix build * Fix typo in ordered/exclusive stores. * Implement some more instructions, fix others. Uxtab16/Sxtab16 are untested. * Begin impl of pairwise, some other instructions. * Add a few more instructions, a quick hack to fix svcs for now. * Add tests and fix issues with VTRN, VZIP, VUZP * Add a few more instructions, fix Vmul_1 encoding. * Fix way too many instruction bugs, add tests for some of the more important ones. * Fix HighCq, enable FastFP paths for some floating point instructions (not entirely sure why these were disabled, so important to note this commit exists) Branching has been removed in A32 shifts until I figure out if it's worth it * Cleanup Part 1 There should be no functional change between these next few commits. Should is the key word. (except for removing break handler) * Implement 32 bits syscalls Co-authored-by: riperiperi <rhy3756547@hotmail.com> Implement all 32 bits counterparts of the 64 bits syscalls we currently have. * Refactor part 2: Move index/subindex logic to Operand May have inadvertently fixed one (1) bug * Add FlushProcessDataCache32 * Address jd's comments * Remove 16 bit encodings from OpCodeTable Still need to catch some edge cases (operands that use the "F" flag) and make Q encodings with non-even indexes undefined. * Correct Fpscr handling for FP vector slow paths WIP * Add StandardFPSCRValue behaviour for all Arithmetic instructions * Add StandardFPSCRValue behaviour to compare instructions. * Force passing of fpcr to FPProcessException and FPUnpack. Reduces potential for code error significantly * OpCode cleanup * Remove urgency from DMB comment in MRRC DMB is currently a no-op via the instruction, so it should likely still be a no-op here. * Test Cleanup * Fix FPDefaultNaN on Ryzen CPUs * Improve some tests, fix some shift instructions, add slow path for Vadd * Fix Typo * More test cleanup * Flip order of Fx and index, to indicate that the operand's is the "base" * Remove Simd32 register type, use Int32 and Int64 for scalars like A64 does. * Reintroduce alignment to DecoderHelper (removed by accident) * One more realign as reading diffs is hard * Use I32 registers in A32 (part 2) Swap default integer register type based on current execution mode. * FPSCR flags as Registers (part 1) Still need to change NativeContext and ExecutionContext to allow getting/setting with the flag values. * Use I32 registers in A32 (part 1) * FPSCR flags as registers (part 2) Only CMP flags are on the registers right now. It could be useful to use more of the space in non-fast-float when implementing A32 flags accurately in the fast path. * Address Feedback * Correct FP->Int behaviour (should saturate) * Make branches made by writing to PC eligible for Rejit Greatly improves performance in most games. * Remove unused branching for Vtbl * RejitRequest as a class rather than a tuple Makes a lot more sense than storing tuples on a dictionary. * Add VMOVN, VSHR (imm), VSHRN (imm) and related tests * Re-order InstEmitSystem32 Alphabetical sorting. * Address Feedback Feedback from Ac_K, remove and sort usings. * Address Feedback 2 * Address Feedback from LDj3SNuD Opcode table reordered to have alphabetical sorting within groups, Vmaxnm and Vminnm have split names to be less ambiguous, SoftFloat nits, Test nits and Test simplification with ValueSource. * Add Debug Asserts to A32 helpers Mainly to prevent the shift ones from being used on I64 operands, as they expect I32 input for most operations (eg. carry flag setting), and expect I32 input for shift and boolean amounts. Most other helper functions don't take Operands, throw on out of range values, and take specific types of OpCode, so didn't need any asserts. * Use ConstF rather than creating an operand. (useful for pooling in future) * Move exclusive load to helper, reference call flag rather than literal 1. * Address LDj feedback (minus table flatten) one final look before it's all gone. the world is so beautiful. * Flatten OpCodeTable oh no * Address more table ordering * Call Flag as int on A32 Co-authored-by: Natalie C. <cyuubiapps@gmail.com> Co-authored-by: Thog <thog@protonmail.com>
2020-02-23 21:20:40 +00:00
opCode.Instruction.Name == InstName.Blr ||
opCode.Instruction.Name == InstName.Blx;
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
}
private static bool IsException(OpCode opCode)
{
return opCode.Instruction.Name == InstName.Brk ||
opCode.Instruction.Name == InstName.Svc ||
Add most of the A32 instruction set to ARMeilleure (#897) * Implement TEQ and MOV (Imm16) * Initial work on A32 instructions + SVC. No tests yet, hangs in rtld. * Implement CLZ, fix BFI and BFC Now stops on SIMD initialization. * Exclusive access instructions, fix to mul, system instructions. Now gets to a break after SignalProcessWideKey64. * Better impl of UBFX, add UDIV and SDIV Now boots way further - now stuck on VMOV instruction. * Many more instructions, start on SIMD and testing framework. * Fix build issues * svc: Rework 32 bit codepath Fixing once and for all argument ordering issues. * Fix 32 bits stacktrace * hle debug: Add 32 bits dynamic section parsing * Fix highCq mode, add many tests, fix some instruction bugs Still suffers from critical malloc failure :weary: * Fix incorrect opcode decoders and a few more instructions. * Add a few instructions and fix others. re-disable highCq for now. Disabled the svc memory clear since i'm not sure about it. * Fix build * Fix typo in ordered/exclusive stores. * Implement some more instructions, fix others. Uxtab16/Sxtab16 are untested. * Begin impl of pairwise, some other instructions. * Add a few more instructions, a quick hack to fix svcs for now. * Add tests and fix issues with VTRN, VZIP, VUZP * Add a few more instructions, fix Vmul_1 encoding. * Fix way too many instruction bugs, add tests for some of the more important ones. * Fix HighCq, enable FastFP paths for some floating point instructions (not entirely sure why these were disabled, so important to note this commit exists) Branching has been removed in A32 shifts until I figure out if it's worth it * Cleanup Part 1 There should be no functional change between these next few commits. Should is the key word. (except for removing break handler) * Implement 32 bits syscalls Co-authored-by: riperiperi <rhy3756547@hotmail.com> Implement all 32 bits counterparts of the 64 bits syscalls we currently have. * Refactor part 2: Move index/subindex logic to Operand May have inadvertently fixed one (1) bug * Add FlushProcessDataCache32 * Address jd's comments * Remove 16 bit encodings from OpCodeTable Still need to catch some edge cases (operands that use the "F" flag) and make Q encodings with non-even indexes undefined. * Correct Fpscr handling for FP vector slow paths WIP * Add StandardFPSCRValue behaviour for all Arithmetic instructions * Add StandardFPSCRValue behaviour to compare instructions. * Force passing of fpcr to FPProcessException and FPUnpack. Reduces potential for code error significantly * OpCode cleanup * Remove urgency from DMB comment in MRRC DMB is currently a no-op via the instruction, so it should likely still be a no-op here. * Test Cleanup * Fix FPDefaultNaN on Ryzen CPUs * Improve some tests, fix some shift instructions, add slow path for Vadd * Fix Typo * More test cleanup * Flip order of Fx and index, to indicate that the operand's is the "base" * Remove Simd32 register type, use Int32 and Int64 for scalars like A64 does. * Reintroduce alignment to DecoderHelper (removed by accident) * One more realign as reading diffs is hard * Use I32 registers in A32 (part 2) Swap default integer register type based on current execution mode. * FPSCR flags as Registers (part 1) Still need to change NativeContext and ExecutionContext to allow getting/setting with the flag values. * Use I32 registers in A32 (part 1) * FPSCR flags as registers (part 2) Only CMP flags are on the registers right now. It could be useful to use more of the space in non-fast-float when implementing A32 flags accurately in the fast path. * Address Feedback * Correct FP->Int behaviour (should saturate) * Make branches made by writing to PC eligible for Rejit Greatly improves performance in most games. * Remove unused branching for Vtbl * RejitRequest as a class rather than a tuple Makes a lot more sense than storing tuples on a dictionary. * Add VMOVN, VSHR (imm), VSHRN (imm) and related tests * Re-order InstEmitSystem32 Alphabetical sorting. * Address Feedback Feedback from Ac_K, remove and sort usings. * Address Feedback 2 * Address Feedback from LDj3SNuD Opcode table reordered to have alphabetical sorting within groups, Vmaxnm and Vminnm have split names to be less ambiguous, SoftFloat nits, Test nits and Test simplification with ValueSource. * Add Debug Asserts to A32 helpers Mainly to prevent the shift ones from being used on I64 operands, as they expect I32 input for most operations (eg. carry flag setting), and expect I32 input for shift and boolean amounts. Most other helper functions don't take Operands, throw on out of range values, and take specific types of OpCode, so didn't need any asserts. * Use ConstF rather than creating an operand. (useful for pooling in future) * Move exclusive load to helper, reference call flag rather than literal 1. * Address LDj feedback (minus table flatten) one final look before it's all gone. the world is so beautiful. * Flatten OpCodeTable oh no * Address more table ordering * Call Flag as int on A32 Co-authored-by: Natalie C. <cyuubiapps@gmail.com> Co-authored-by: Thog <thog@protonmail.com>
2020-02-23 21:20:40 +00:00
opCode.Instruction.Name == InstName.Trap ||
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
opCode.Instruction.Name == InstName.Und;
}
public static OpCode DecodeOpCode(MemoryManager memory, ulong address, ExecutionMode mode)
{
int opCode = memory.ReadInt32((long)address);
InstDescriptor inst;
Type type;
if (mode == ExecutionMode.Aarch64)
{
(inst, type) = OpCodeTable.GetInstA64(opCode);
}
else
{
if (mode == ExecutionMode.Aarch32Arm)
{
(inst, type) = OpCodeTable.GetInstA32(opCode);
}
else /* if (mode == ExecutionMode.Aarch32Thumb) */
{
(inst, type) = OpCodeTable.GetInstT32(opCode);
}
}
if (type != null)
{
return MakeOpCode(inst, type, address, opCode);
}
else
{
return new OpCode(inst, address, opCode);
}
}
private static OpCode MakeOpCode(InstDescriptor inst, Type type, ulong address, int opCode)
{
MakeOp createInstance = _opActivators.GetOrAdd(type, CacheOpActivator);
return (OpCode)createInstance(inst, address, opCode);
}
private static MakeOp CacheOpActivator(Type type)
{
Type[] argTypes = new Type[] { typeof(InstDescriptor), typeof(ulong), typeof(int) };
DynamicMethod mthd = new DynamicMethod($"Make{type.Name}", type, argTypes);
ILGenerator generator = mthd.GetILGenerator();
generator.Emit(OpCodes.Ldarg_0);
generator.Emit(OpCodes.Ldarg_1);
generator.Emit(OpCodes.Ldarg_2);
generator.Emit(OpCodes.Newobj, type.GetConstructor(argTypes));
generator.Emit(OpCodes.Ret);
return (MakeOp)mthd.CreateDelegate(typeof(MakeOp));
}
}
}