a731ab3a2a
* 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
196 lines
6.0 KiB
C#
196 lines
6.0 KiB
C#
using ARMeilleure.Decoders;
|
|
using ARMeilleure.IntermediateRepresentation;
|
|
using ARMeilleure.Translation;
|
|
|
|
using static ARMeilleure.Instructions.InstEmitHelper;
|
|
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
|
|
|
|
namespace ARMeilleure.Instructions
|
|
{
|
|
static partial class InstEmit
|
|
{
|
|
public static void Bfm(ArmEmitterContext context)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
Operand d = GetIntOrZR(context, op.Rd);
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
Operand res;
|
|
|
|
if (op.Pos < op.Shift)
|
|
{
|
|
// BFI.
|
|
int shift = op.GetBitsCount() - op.Shift;
|
|
|
|
int width = op.Pos + 1;
|
|
|
|
long mask = (long)(ulong.MaxValue >> (64 - width));
|
|
|
|
res = context.ShiftLeft(context.BitwiseAnd(n, Const(n.Type, mask)), Const(shift));
|
|
|
|
res = context.BitwiseOr(res, context.BitwiseAnd(d, Const(d.Type, ~(mask << shift))));
|
|
}
|
|
else
|
|
{
|
|
// BFXIL.
|
|
int shift = op.Shift;
|
|
|
|
int width = op.Pos - shift + 1;
|
|
|
|
long mask = (long)(ulong.MaxValue >> (64 - width));
|
|
|
|
res = context.BitwiseAnd(context.ShiftRightUI(n, Const(shift)), Const(n.Type, mask));
|
|
|
|
res = context.BitwiseOr(res, context.BitwiseAnd(d, Const(d.Type, ~mask)));
|
|
}
|
|
|
|
SetIntOrZR(context, op.Rd, res);
|
|
}
|
|
|
|
public static void Sbfm(ArmEmitterContext context)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
int bitsCount = op.GetBitsCount();
|
|
|
|
if (op.Pos + 1 == bitsCount)
|
|
{
|
|
EmitSbfmShift(context);
|
|
}
|
|
else if (op.Pos < op.Shift)
|
|
{
|
|
EmitSbfiz(context);
|
|
}
|
|
else if (op.Pos == 7 && op.Shift == 0)
|
|
{
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
SetIntOrZR(context, op.Rd, context.SignExtend8(n.Type, n));
|
|
}
|
|
else if (op.Pos == 15 && op.Shift == 0)
|
|
{
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
SetIntOrZR(context, op.Rd, context.SignExtend16(n.Type, n));
|
|
}
|
|
else if (op.Pos == 31 && op.Shift == 0)
|
|
{
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
SetIntOrZR(context, op.Rd, context.SignExtend32(n.Type, n));
|
|
}
|
|
else
|
|
{
|
|
Operand res = GetIntOrZR(context, op.Rn);
|
|
|
|
res = context.ShiftLeft (res, Const(bitsCount - 1 - op.Pos));
|
|
res = context.ShiftRightSI(res, Const(bitsCount - 1));
|
|
res = context.BitwiseAnd (res, Const(res.Type, ~op.TMask));
|
|
|
|
Operand n2 = GetBfmN(context);
|
|
|
|
SetIntOrZR(context, op.Rd, context.BitwiseOr(res, n2));
|
|
}
|
|
}
|
|
|
|
public static void Ubfm(ArmEmitterContext context)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
if (op.Pos + 1 == op.GetBitsCount())
|
|
{
|
|
EmitUbfmShift(context);
|
|
}
|
|
else if (op.Pos < op.Shift)
|
|
{
|
|
EmitUbfiz(context);
|
|
}
|
|
else if (op.Pos + 1 == op.Shift)
|
|
{
|
|
EmitBfmLsl(context);
|
|
}
|
|
else if (op.Pos == 7 && op.Shift == 0)
|
|
{
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
SetIntOrZR(context, op.Rd, context.BitwiseAnd(n, Const(n.Type, 0xff)));
|
|
}
|
|
else if (op.Pos == 15 && op.Shift == 0)
|
|
{
|
|
Operand n = GetIntOrZR(context, op.Rn);
|
|
|
|
SetIntOrZR(context, op.Rd, context.BitwiseAnd(n, Const(n.Type, 0xffff)));
|
|
}
|
|
else
|
|
{
|
|
SetIntOrZR(context, op.Rd, GetBfmN(context));
|
|
}
|
|
}
|
|
|
|
private static void EmitSbfiz(ArmEmitterContext context) => EmitBfiz(context, signed: true);
|
|
private static void EmitUbfiz(ArmEmitterContext context) => EmitBfiz(context, signed: false);
|
|
|
|
private static void EmitBfiz(ArmEmitterContext context, bool signed)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
int width = op.Pos + 1;
|
|
|
|
Operand res = GetIntOrZR(context, op.Rn);
|
|
|
|
res = context.ShiftLeft(res, Const(op.GetBitsCount() - width));
|
|
|
|
res = signed
|
|
? context.ShiftRightSI(res, Const(op.Shift - width))
|
|
: context.ShiftRightUI(res, Const(op.Shift - width));
|
|
|
|
SetIntOrZR(context, op.Rd, res);
|
|
}
|
|
|
|
private static void EmitSbfmShift(ArmEmitterContext context)
|
|
{
|
|
EmitBfmShift(context, signed: true);
|
|
}
|
|
|
|
private static void EmitUbfmShift(ArmEmitterContext context)
|
|
{
|
|
EmitBfmShift(context, signed: false);
|
|
}
|
|
|
|
private static void EmitBfmShift(ArmEmitterContext context, bool signed)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
Operand res = GetIntOrZR(context, op.Rn);
|
|
|
|
res = signed
|
|
? context.ShiftRightSI(res, Const(op.Shift))
|
|
: context.ShiftRightUI(res, Const(op.Shift));
|
|
|
|
SetIntOrZR(context, op.Rd, res);
|
|
}
|
|
|
|
private static void EmitBfmLsl(ArmEmitterContext context)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
Operand res = GetIntOrZR(context, op.Rn);
|
|
|
|
int shift = op.GetBitsCount() - op.Shift;
|
|
|
|
SetIntOrZR(context, op.Rd, context.ShiftLeft(res, Const(shift)));
|
|
}
|
|
|
|
private static Operand GetBfmN(ArmEmitterContext context)
|
|
{
|
|
OpCodeBfm op = (OpCodeBfm)context.CurrOp;
|
|
|
|
Operand res = GetIntOrZR(context, op.Rn);
|
|
|
|
long mask = op.WMask & op.TMask;
|
|
|
|
return context.BitwiseAnd(context.RotateRight(res, Const(op.Shift)), Const(res.Type, mask));
|
|
}
|
|
}
|
|
} |