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 20:56:22 +02:00
|
|
|
using ARMeilleure.IntermediateRepresentation;
|
|
|
|
using System;
|
|
|
|
|
|
|
|
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
|
|
|
|
|
|
|
|
namespace ARMeilleure.CodeGen.Optimizations
|
|
|
|
{
|
|
|
|
static class Simplification
|
|
|
|
{
|
|
|
|
public static void RunPass(Operation operation)
|
|
|
|
{
|
|
|
|
switch (operation.Instruction)
|
|
|
|
{
|
|
|
|
case Instruction.Add:
|
|
|
|
TryEliminateBinaryOpComutative(operation, 0);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.BitwiseAnd:
|
|
|
|
TryEliminateBitwiseAnd(operation);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.BitwiseOr:
|
|
|
|
TryEliminateBitwiseOr(operation);
|
|
|
|
break;
|
|
|
|
|
2020-04-09 01:36:19 +02:00
|
|
|
case Instruction.BitwiseExclusiveOr:
|
|
|
|
TryEliminateBitwiseExclusiveOr(operation);
|
|
|
|
break;
|
|
|
|
|
Add a new JIT compiler for CPU code (#693)
* Start of the ARMeilleure project
* Refactoring around the old IRAdapter, now renamed to PreAllocator
* Optimize the LowestBitSet method
* Add CLZ support and fix CLS implementation
* Add missing Equals and GetHashCode overrides on some structs, misc small tweaks
* Implement the ByteSwap IR instruction, and some refactoring on the assembler
* Implement the DivideUI IR instruction and fix 64-bits IDIV
* Correct constant operand type on CSINC
* Move division instructions implementation to InstEmitDiv
* Fix destination type for the ConditionalSelect IR instruction
* Implement UMULH and SMULH, with new IR instructions
* Fix some issues with shift instructions
* Fix constant types for BFM instructions
* Fix up new tests using the new V128 struct
* Update tests
* Move DIV tests to a separate file
* Add support for calls, and some instructions that depends on them
* Start adding support for SIMD & FP types, along with some of the related ARM instructions
* Fix some typos and the divide instruction with FP operands
* Fix wrong method call on Clz_V
* Implement ARM FP & SIMD move instructions, Saddlv_V, and misc. fixes
* Implement SIMD logical instructions and more misc. fixes
* Fix PSRAD x86 instruction encoding, TRN, UABD and UABDL implementations
* Implement float conversion instruction, merge in LDj3SNuD fixes, and some other misc. fixes
* Implement SIMD shift instruction and fix Dup_V
* Add SCVTF and UCVTF (vector, fixed-point) variants to the opcode table
* Fix check with tolerance on tester
* Implement FP & SIMD comparison instructions, and some fixes
* Update FCVT (Scalar) encoding on the table to support the Half-float variants
* Support passing V128 structs, some cleanup on the register allocator, merge LDj3SNuD fixes
* Use old memory access methods, made a start on SIMD memory insts support, some fixes
* Fix float constant passed to functions, save and restore non-volatile XMM registers, other fixes
* Fix arguments count with struct return values, other fixes
* More instructions
* Misc. fixes and integrate LDj3SNuD fixes
* Update tests
* Add a faster linear scan allocator, unwinding support on windows, and other changes
* Update Ryujinx.HLE
* Update Ryujinx.Graphics
* Fix V128 return pointer passing, RCX is clobbered
* Update Ryujinx.Tests
* Update ITimeZoneService
* Stop using GetFunctionPointer as that can't be called from native code, misc. fixes and tweaks
* Use generic GetFunctionPointerForDelegate method and other tweaks
* Some refactoring on the code generator, assert on invalid operations and use a separate enum for intrinsics
* Remove some unused code on the assembler
* Fix REX.W prefix regression on float conversion instructions, add some sort of profiler
* Add hardware capability detection
* Fix regression on Sha1h and revert Fcm** changes
* Add SSE2-only paths on vector extract and insert, some refactoring on the pre-allocator
* Fix silly mistake introduced on last commit on CpuId
* Generate inline stack probes when the stack allocation is too large
* Initial support for the System-V ABI
* Support multiple destination operands
* Fix SSE2 VectorInsert8 path, and other fixes
* Change placement of XMM callee save and restore code to match other compilers
* Rename Dest to Destination and Inst to Instruction
* Fix a regression related to calls and the V128 type
* Add an extra space on comments to match code style
* Some refactoring
* Fix vector insert FP32 SSE2 path
* Port over the ARM32 instructions
* Avoid memory protection races on JIT Cache
* Another fix on VectorInsert FP32 (thanks to LDj3SNuD
* Float operands don't need to use the same register when VEX is supported
* Add a new register allocator, higher quality code for hot code (tier up), and other tweaks
* Some nits, small improvements on the pre allocator
* CpuThreadState is gone
* Allow changing CPU emulators with a config entry
* Add runtime identifiers on the ARMeilleure project
* Allow switching between CPUs through a config entry (pt. 2)
* Change win10-x64 to win-x64 on projects
* Update the Ryujinx project to use ARMeilleure
* Ensure that the selected register is valid on the hybrid allocator
* Allow exiting on returns to 0 (should fix test regression)
* Remove register assignments for most used variables on the hybrid allocator
* Do not use fixed registers as spill temp
* Add missing namespace and remove unneeded using
* Address PR feedback
* Fix types, etc
* Enable AssumeStrictAbiCompliance by default
* Ensure that Spill and Fill don't load or store any more than necessary
2019-08-08 20:56:22 +02:00
|
|
|
case Instruction.ConditionalSelect:
|
|
|
|
TryEliminateConditionalSelect(operation);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.Divide:
|
|
|
|
TryEliminateBinaryOpY(operation, 1);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.Multiply:
|
|
|
|
TryEliminateBinaryOpComutative(operation, 1);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case Instruction.ShiftLeft:
|
|
|
|
case Instruction.ShiftRightSI:
|
|
|
|
case Instruction.ShiftRightUI:
|
|
|
|
case Instruction.Subtract:
|
|
|
|
TryEliminateBinaryOpY(operation, 0);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBitwiseAnd(Operation operation)
|
|
|
|
{
|
|
|
|
// Try to recognize and optimize those 3 patterns (in order):
|
|
|
|
// x & 0xFFFFFFFF == x, 0xFFFFFFFF & y == y,
|
|
|
|
// x & 0x00000000 == 0x00000000, 0x00000000 & y == 0x00000000
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, AllOnes(x.Type)))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, AllOnes(y.Type)))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(x, 0) || IsConstEqual(y, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(Const(0));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBitwiseOr(Operation operation)
|
|
|
|
{
|
|
|
|
// Try to recognize and optimize those 3 patterns (in order):
|
|
|
|
// x | 0x00000000 == x, 0x00000000 | y == y,
|
|
|
|
// x | 0xFFFFFFFF == 0xFFFFFFFF, 0xFFFFFFFF | y == 0xFFFFFFFF
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, 0))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(x, AllOnes(x.Type)) || IsConstEqual(y, AllOnes(y.Type)))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(Const(AllOnes(x.Type)));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-09 01:36:19 +02:00
|
|
|
private static void TryEliminateBitwiseExclusiveOr(Operation operation)
|
|
|
|
{
|
|
|
|
// Try to recognize and optimize those 2 patterns (in order):
|
|
|
|
// x ^ y == 0x00000000 when x == y
|
|
|
|
// 0x00000000 ^ y == y, x ^ 0x00000000 == x
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (x == y && x.Type.IsInteger())
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(Const(x.Type, 0));
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
TryEliminateBinaryOpComutative(operation, 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 20:56:22 +02:00
|
|
|
private static void TryEliminateBinaryOpY(Operation operation, ulong comparand)
|
|
|
|
{
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(y, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateBinaryOpComutative(Operation operation, ulong comparand)
|
|
|
|
{
|
|
|
|
Operand x = operation.GetSource(0);
|
|
|
|
Operand y = operation.GetSource(1);
|
|
|
|
|
|
|
|
if (IsConstEqual(x, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(y);
|
|
|
|
}
|
|
|
|
else if (IsConstEqual(y, comparand))
|
|
|
|
{
|
|
|
|
operation.TurnIntoCopy(x);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static void TryEliminateConditionalSelect(Operation operation)
|
|
|
|
{
|
|
|
|
Operand cond = operation.GetSource(0);
|
|
|
|
|
|
|
|
if (cond.Kind != OperandKind.Constant)
|
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// The condition is constant, we can turn it into a copy, and select
|
|
|
|
// the source based on the condition value.
|
|
|
|
int srcIndex = cond.Value != 0 ? 1 : 2;
|
|
|
|
|
|
|
|
Operand source = operation.GetSource(srcIndex);
|
|
|
|
|
|
|
|
operation.TurnIntoCopy(source);
|
|
|
|
}
|
|
|
|
|
|
|
|
private static bool IsConstEqual(Operand operand, ulong comparand)
|
|
|
|
{
|
|
|
|
if (operand.Kind != OperandKind.Constant || !operand.Type.IsInteger())
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
return operand.Value == comparand;
|
|
|
|
}
|
|
|
|
|
|
|
|
private static ulong AllOnes(OperandType type)
|
|
|
|
{
|
|
|
|
switch (type)
|
|
|
|
{
|
|
|
|
case OperandType.I32: return ~0U;
|
|
|
|
case OperandType.I64: return ~0UL;
|
|
|
|
}
|
|
|
|
|
|
|
|
throw new ArgumentException("Invalid operand type \"" + type + "\".");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|