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 19:56:22 +01:00
|
|
|
using ARMeilleure.IntermediateRepresentation;
|
|
|
|
using ARMeilleure.State;
|
|
|
|
using System;
|
|
|
|
|
|
|
|
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
|
|
|
|
|
|
|
|
namespace ARMeilleure.Translation
|
|
|
|
{
|
|
|
|
static class RegisterUsage
|
|
|
|
{
|
|
|
|
private const long CallerSavedIntRegistersMask = 0x7fL << 9;
|
|
|
|
private const long PStateNzcvFlagsMask = 0xfL << 60;
|
|
|
|
|
|
|
|
private const long CallerSavedVecRegistersMask = 0xffffL << 16;
|
|
|
|
|
|
|
|
private const int RegsCount = 32;
|
|
|
|
private const int RegsMask = RegsCount - 1;
|
|
|
|
|
|
|
|
private struct RegisterMask : IEquatable<RegisterMask>
|
|
|
|
{
|
|
|
|
public long IntMask { get; set; }
|
|
|
|
public long VecMask { get; set; }
|
|
|
|
|
|
|
|
public RegisterMask(long intMask, long vecMask)
|
|
|
|
{
|
|
|
|
IntMask = intMask;
|
|
|
|
VecMask = vecMask;
|
|
|
|
}
|
|
|
|
|
|
|
|
public static RegisterMask operator &(RegisterMask x, RegisterMask y)
|
|
|
|
{
|
|
|
|
return new RegisterMask(x.IntMask & y.IntMask, x.VecMask & y.VecMask);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static RegisterMask operator |(RegisterMask x, RegisterMask y)
|
|
|
|
{
|
|
|
|
return new RegisterMask(x.IntMask | y.IntMask, x.VecMask | y.VecMask);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static RegisterMask operator ~(RegisterMask x)
|
|
|
|
{
|
|
|
|
return new RegisterMask(~x.IntMask, ~x.VecMask);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static bool operator ==(RegisterMask x, RegisterMask y)
|
|
|
|
{
|
|
|
|
return x.Equals(y);
|
|
|
|
}
|
|
|
|
|
|
|
|
public static bool operator !=(RegisterMask x, RegisterMask y)
|
|
|
|
{
|
|
|
|
return !x.Equals(y);
|
|
|
|
}
|
|
|
|
|
|
|
|
public override bool Equals(object obj)
|
|
|
|
{
|
|
|
|
return obj is RegisterMask regMask && Equals(regMask);
|
|
|
|
}
|
|
|
|
|
|
|
|
public bool Equals(RegisterMask other)
|
|
|
|
{
|
|
|
|
return IntMask == other.IntMask && VecMask == other.VecMask;
|
|
|
|
}
|
|
|
|
|
|
|
|
public override int GetHashCode()
|
|
|
|
{
|
|
|
|
return HashCode.Combine(IntMask, VecMask);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
public static void RunPass(ControlFlowGraph cfg, bool isCompleteFunction)
|
|
|
|
{
|
|
|
|
// Compute local register inputs and outputs used inside blocks.
|
|
|
|
RegisterMask[] localInputs = new RegisterMask[cfg.Blocks.Count];
|
|
|
|
RegisterMask[] localOutputs = new RegisterMask[cfg.Blocks.Count];
|
|
|
|
|
2020-02-17 21:30:54 +00:00
|
|
|
for (BasicBlock block = cfg.Blocks.First; block != null; block = block.ListNext)
|
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 19:56:22 +01:00
|
|
|
{
|
2020-02-17 21:30:54 +00:00
|
|
|
for (Node node = block.Operations.First; node != null; node = node.ListNext)
|
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 19:56:22 +01:00
|
|
|
{
|
|
|
|
Operation operation = node as Operation;
|
|
|
|
|
|
|
|
for (int srcIndex = 0; srcIndex < operation.SourcesCount; srcIndex++)
|
|
|
|
{
|
|
|
|
Operand source = operation.GetSource(srcIndex);
|
|
|
|
|
|
|
|
if (source.Kind != OperandKind.Register)
|
|
|
|
{
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
Register register = source.GetRegister();
|
|
|
|
|
|
|
|
localInputs[block.Index] |= GetMask(register) & ~localOutputs[block.Index];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (operation.Destination != null && operation.Destination.Kind == OperandKind.Register)
|
|
|
|
{
|
|
|
|
localOutputs[block.Index] |= GetMask(operation.Destination.GetRegister());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Compute global register inputs and outputs used across blocks.
|
|
|
|
RegisterMask[] globalCmnOutputs = new RegisterMask[cfg.Blocks.Count];
|
|
|
|
|
|
|
|
RegisterMask[] globalInputs = new RegisterMask[cfg.Blocks.Count];
|
|
|
|
RegisterMask[] globalOutputs = new RegisterMask[cfg.Blocks.Count];
|
|
|
|
|
|
|
|
bool modified;
|
|
|
|
|
|
|
|
bool firstPass = true;
|
|
|
|
|
|
|
|
do
|
|
|
|
{
|
|
|
|
modified = false;
|
|
|
|
|
|
|
|
// Compute register outputs.
|
|
|
|
for (int index = cfg.PostOrderBlocks.Length - 1; index >= 0; index--)
|
|
|
|
{
|
|
|
|
BasicBlock block = cfg.PostOrderBlocks[index];
|
|
|
|
|
|
|
|
if (block.Predecessors.Count != 0 && !HasContextLoad(block))
|
|
|
|
{
|
|
|
|
BasicBlock predecessor = block.Predecessors[0];
|
|
|
|
|
|
|
|
RegisterMask cmnOutputs = localOutputs[predecessor.Index] | globalCmnOutputs[predecessor.Index];
|
|
|
|
|
|
|
|
RegisterMask outputs = globalOutputs[predecessor.Index];
|
|
|
|
|
|
|
|
for (int pIndex = 1; pIndex < block.Predecessors.Count; pIndex++)
|
|
|
|
{
|
|
|
|
predecessor = block.Predecessors[pIndex];
|
|
|
|
|
|
|
|
cmnOutputs &= localOutputs[predecessor.Index] | globalCmnOutputs[predecessor.Index];
|
|
|
|
|
|
|
|
outputs |= globalOutputs[predecessor.Index];
|
|
|
|
}
|
|
|
|
|
|
|
|
globalInputs[block.Index] |= outputs & ~cmnOutputs;
|
|
|
|
|
|
|
|
if (!firstPass)
|
|
|
|
{
|
|
|
|
cmnOutputs &= globalCmnOutputs[block.Index];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Exchange(globalCmnOutputs, block.Index, cmnOutputs))
|
|
|
|
{
|
|
|
|
modified = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
outputs |= localOutputs[block.Index];
|
|
|
|
|
|
|
|
if (Exchange(globalOutputs, block.Index, globalOutputs[block.Index] | outputs))
|
|
|
|
{
|
|
|
|
modified = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else if (Exchange(globalOutputs, block.Index, localOutputs[block.Index]))
|
|
|
|
{
|
|
|
|
modified = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Compute register inputs.
|
|
|
|
for (int index = 0; index < cfg.PostOrderBlocks.Length; index++)
|
|
|
|
{
|
|
|
|
BasicBlock block = cfg.PostOrderBlocks[index];
|
|
|
|
|
|
|
|
RegisterMask inputs = localInputs[block.Index];
|
|
|
|
|
|
|
|
if (block.Next != null)
|
|
|
|
{
|
|
|
|
inputs |= globalInputs[block.Next.Index];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (block.Branch != null)
|
|
|
|
{
|
|
|
|
inputs |= globalInputs[block.Branch.Index];
|
|
|
|
}
|
|
|
|
|
|
|
|
inputs &= ~globalCmnOutputs[block.Index];
|
|
|
|
|
|
|
|
if (Exchange(globalInputs, block.Index, globalInputs[block.Index] | inputs))
|
|
|
|
{
|
|
|
|
modified = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
firstPass = false;
|
|
|
|
}
|
|
|
|
while (modified);
|
|
|
|
|
|
|
|
// Insert load and store context instructions where needed.
|
2020-02-17 21:30:54 +00:00
|
|
|
for (BasicBlock block = cfg.Blocks.First; block != null; block = block.ListNext)
|
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 19:56:22 +01:00
|
|
|
{
|
|
|
|
bool hasContextLoad = HasContextLoad(block);
|
|
|
|
|
|
|
|
if (hasContextLoad)
|
|
|
|
{
|
2020-02-17 21:30:54 +00:00
|
|
|
block.Operations.Remove(block.Operations.First);
|
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 19:56:22 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
// The only block without any predecessor should be the entry block.
|
|
|
|
// It always needs a context load as it is the first block to run.
|
|
|
|
if (block.Predecessors.Count == 0 || hasContextLoad)
|
|
|
|
{
|
|
|
|
LoadLocals(block, globalInputs[block.Index].VecMask, RegisterType.Vector);
|
|
|
|
LoadLocals(block, globalInputs[block.Index].IntMask, RegisterType.Integer);
|
|
|
|
}
|
|
|
|
|
|
|
|
bool hasContextStore = HasContextStore(block);
|
|
|
|
|
|
|
|
if (hasContextStore)
|
|
|
|
{
|
2020-02-17 21:30:54 +00:00
|
|
|
block.Operations.Remove(block.Operations.Last);
|
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 19:56:22 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
if (EndsWithReturn(block) || hasContextStore)
|
|
|
|
{
|
|
|
|
StoreLocals(block, globalOutputs[block.Index].IntMask, RegisterType.Integer, isCompleteFunction);
|
|
|
|
StoreLocals(block, globalOutputs[block.Index].VecMask, RegisterType.Vector, isCompleteFunction);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool HasContextLoad(BasicBlock block)
|
|
|
|
{
|
2020-02-17 21:30:54 +00:00
|
|
|
return StartsWith(block, Instruction.LoadFromContext) && block.Operations.First.SourcesCount == 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 19:56:22 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
private static bool HasContextStore(BasicBlock block)
|
|
|
|
{
|
|
|
|
return EndsWith(block, Instruction.StoreToContext) && block.GetLastOp().SourcesCount == 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool StartsWith(BasicBlock block, Instruction inst)
|
|
|
|
{
|
|
|
|
if (block.Operations.Count == 0)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2020-02-17 21:30:54 +00:00
|
|
|
return block.Operations.First is Operation operation && operation.Instruction == inst;
|
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 19:56:22 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
private static bool EndsWith(BasicBlock block, Instruction inst)
|
|
|
|
{
|
|
|
|
if (block.Operations.Count == 0)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2020-02-17 21:30:54 +00:00
|
|
|
return block.Operations.Last is Operation operation && operation.Instruction == inst;
|
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 19:56:22 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
private static RegisterMask GetMask(Register register)
|
|
|
|
{
|
|
|
|
long intMask = 0;
|
|
|
|
long vecMask = 0;
|
|
|
|
|
|
|
|
switch (register.Type)
|
|
|
|
{
|
|
|
|
case RegisterType.Flag: intMask = (1L << RegsCount) << register.Index; break;
|
|
|
|
case RegisterType.Integer: intMask = 1L << register.Index; break;
|
|
|
|
case RegisterType.Vector: vecMask = 1L << register.Index; break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return new RegisterMask(intMask, vecMask);
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool Exchange(RegisterMask[] masks, int blkIndex, RegisterMask value)
|
|
|
|
{
|
|
|
|
RegisterMask oldValue = masks[blkIndex];
|
|
|
|
|
|
|
|
masks[blkIndex] = value;
|
|
|
|
|
|
|
|
return oldValue != value;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void LoadLocals(BasicBlock block, long inputs, RegisterType baseType)
|
|
|
|
{
|
|
|
|
Operand arg0 = Local(OperandType.I64);
|
|
|
|
|
|
|
|
for (int bit = 63; bit >= 0; bit--)
|
|
|
|
{
|
|
|
|
long mask = 1L << bit;
|
|
|
|
|
|
|
|
if ((inputs & mask) == 0)
|
|
|
|
{
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
Operand dest = GetRegFromBit(bit, baseType);
|
|
|
|
|
|
|
|
long offset = NativeContext.GetRegisterOffset(dest.GetRegister());
|
|
|
|
|
|
|
|
Operand addr = Local(OperandType.I64);
|
|
|
|
|
|
|
|
Operation loadOp = new Operation(Instruction.Load, dest, addr);
|
|
|
|
|
|
|
|
block.Operations.AddFirst(loadOp);
|
|
|
|
|
|
|
|
Operation calcOffsOp = new Operation(Instruction.Add, addr, arg0, Const(offset));
|
|
|
|
|
|
|
|
block.Operations.AddFirst(calcOffsOp);
|
|
|
|
}
|
|
|
|
|
|
|
|
Operation loadArg0 = new Operation(Instruction.LoadArgument, arg0, Const(0));
|
|
|
|
|
|
|
|
block.Operations.AddFirst(loadArg0);
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void StoreLocals(BasicBlock block, long outputs, RegisterType baseType, bool isCompleteFunction)
|
|
|
|
{
|
|
|
|
if (Optimizations.AssumeStrictAbiCompliance && isCompleteFunction)
|
|
|
|
{
|
|
|
|
if (baseType == RegisterType.Integer || baseType == RegisterType.Flag)
|
|
|
|
{
|
|
|
|
outputs = ClearCallerSavedIntRegs(outputs);
|
|
|
|
}
|
|
|
|
else /* if (baseType == RegisterType.Vector) */
|
|
|
|
{
|
|
|
|
outputs = ClearCallerSavedVecRegs(outputs);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
Operand arg0 = Local(OperandType.I64);
|
|
|
|
|
|
|
|
Operation loadArg0 = new Operation(Instruction.LoadArgument, arg0, Const(0));
|
|
|
|
|
|
|
|
block.Append(loadArg0);
|
|
|
|
|
|
|
|
for (int bit = 0; bit < 64; bit++)
|
|
|
|
{
|
|
|
|
long mask = 1L << bit;
|
|
|
|
|
|
|
|
if ((outputs & mask) == 0)
|
|
|
|
{
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
Operand source = GetRegFromBit(bit, baseType);
|
|
|
|
|
|
|
|
long offset = NativeContext.GetRegisterOffset(source.GetRegister());
|
|
|
|
|
|
|
|
Operand addr = Local(OperandType.I64);
|
|
|
|
|
|
|
|
Operation calcOffsOp = new Operation(Instruction.Add, addr, arg0, Const(offset));
|
|
|
|
|
|
|
|
block.Append(calcOffsOp);
|
|
|
|
|
|
|
|
Operation storeOp = new Operation(Instruction.Store, null, addr, source);
|
|
|
|
|
|
|
|
block.Append(storeOp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static Operand GetRegFromBit(int bit, RegisterType baseType)
|
|
|
|
{
|
|
|
|
if (bit < RegsCount)
|
|
|
|
{
|
|
|
|
return new Operand(bit, baseType, GetOperandType(baseType));
|
|
|
|
}
|
|
|
|
else if (baseType == RegisterType.Integer)
|
|
|
|
{
|
|
|
|
return new Operand(bit & RegsMask, RegisterType.Flag, OperandType.I32);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
throw new ArgumentOutOfRangeException(nameof(bit));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static OperandType GetOperandType(RegisterType type)
|
|
|
|
{
|
|
|
|
switch (type)
|
|
|
|
{
|
|
|
|
case RegisterType.Flag: return OperandType.I32;
|
|
|
|
case RegisterType.Integer: return OperandType.I64;
|
|
|
|
case RegisterType.Vector: return OperandType.V128;
|
|
|
|
}
|
|
|
|
|
|
|
|
throw new ArgumentException($"Invalid register type \"{type}\".");
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool EndsWithReturn(BasicBlock block)
|
|
|
|
{
|
|
|
|
if (!(block.GetLastOp() is Operation operation))
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return operation.Instruction == Instruction.Return;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static long ClearCallerSavedIntRegs(long mask)
|
|
|
|
{
|
|
|
|
// TODO: ARM32 support.
|
|
|
|
mask &= ~(CallerSavedIntRegistersMask | PStateNzcvFlagsMask);
|
|
|
|
|
|
|
|
return mask;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static long ClearCallerSavedVecRegs(long mask)
|
|
|
|
{
|
|
|
|
// TODO: ARM32 support.
|
|
|
|
mask &= ~CallerSavedVecRegistersMask;
|
|
|
|
|
|
|
|
return mask;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|