public static void EmitScalarTernaryOpF32(
ArmEmitterContext context,
Intrinsic inst32pt1,
Intrinsic inst64pt1,
Intrinsic inst32pt2,
Intrinsic inst64pt2,
bool isNegD = false)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
bool doubleSize = (op.Size & 1) != 0;
Intrinsic inst1 = doubleSize ? inst64pt1 : inst32pt1;
Intrinsic inst2 = doubleSize ? inst64pt2 : inst32pt2;
EmitScalarTernaryOpSimd32(context, (d, n, m) =>
{
Operand res = context.AddIntrinsic(inst1, n, m);
if (isNegD)
{
Operand mask = doubleSize
? X86GetScalar(context, -0d)
: X86GetScalar(context, -0f);
d = doubleSize
? context.AddIntrinsic(Intrinsic.X86Xorpd, mask, d)
: context.AddIntrinsic(Intrinsic.X86Xorps, mask, d);
}
return(context.AddIntrinsic(inst2, d, res));
});
}
public static void Vnmul_S(ArmEmitterContext context)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
if (Optimizations.UseSse2)
{
EmitScalarBinaryOpSimd32(context, (n, m) =>
{
if ((op.Size & 1) == 0)
{
Operand res = context.AddIntrinsic(Intrinsic.X86Mulss, n, m);
Operand mask = X86GetScalar(context, -0f);
return(context.AddIntrinsic(Intrinsic.X86Xorps, mask, res));
}
else
{
Operand res = context.AddIntrinsic(Intrinsic.X86Mulsd, n, m);
Operand mask = X86GetScalar(context, -0d);
return(context.AddIntrinsic(Intrinsic.X86Xorpd, mask, res));
}
});
}
else
{
EmitScalarBinaryOpF32(context, (op1, op2) => context.Negate(context.Multiply(op1, op2)));
}
}
public static void EmitScalarBinaryOpF32(ArmEmitterContext context, Intrinsic inst32, Intrinsic inst64)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
Intrinsic inst = (op.Size & 1) != 0 ? inst64 : inst32;
EmitScalarBinaryOpSimd32(context, (n, m) => context.AddIntrinsic(inst, n, m));
}
public static void EmitScalarBinaryOpF32(ArmEmitterContext context, Func2I emit)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
OperandType type = (op.Size & 1) != 0 ? OperandType.FP64 : OperandType.FP32;
Operand n = ExtractScalar(context, type, op.Vn);
Operand m = ExtractScalar(context, type, op.Vm);
InsertScalar(context, op.Vd, emit(n, m));
}
public static void EmitScalarTernaryOpF32(ArmEmitterContext context, Intrinsic inst32, Intrinsic inst64)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
bool doubleSize = (op.Size & 1) != 0;
Intrinsic inst = doubleSize ? inst64 : inst32;
EmitScalarTernaryOpSimd32(context, (d, n, m) =>
{
return(context.AddIntrinsic(inst, d, n, m));
});
}
public static void EmitScalarTernaryOpF32(ArmEmitterContext context, Intrinsic inst32pt1, Intrinsic inst64pt1, Intrinsic inst32pt2, Intrinsic inst64pt2)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
bool doubleSize = (op.Size & 1) != 0;
Intrinsic inst1 = doubleSize ? inst64pt1 : inst32pt1;
Intrinsic inst2 = doubleSize ? inst64pt2 : inst32pt2;
EmitScalarTernaryOpSimd32(context, (d, n, m) =>
{
Operand res = context.AddIntrinsic(inst1, n, m);
return(context.AddIntrinsic(inst2, d, res));
});
}
public static void EmitScalarBinaryOpI32(ArmEmitterContext context, Func2I emit)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
OperandType type = (op.Size & 1) != 0 ? OperandType.I64 : OperandType.I32;
if (op.Size < 2)
{
throw new NotSupportedException("Cannot perform a scalar SIMD operation on integers smaller than 32 bits.");
}
Operand n = ExtractScalar(context, type, op.Vn);
Operand m = ExtractScalar(context, type, op.Vm);
InsertScalar(context, op.Vd, emit(n, m));
}
public static void EmitScalarBinaryOpSimd32(ArmEmitterContext context, Func2I scalarFunc)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
bool doubleSize = (op.Size & 1) != 0;
int shift = doubleSize ? 1 : 2;
Operand n = GetVecA32(op.Vn >> shift);
Operand m = GetVecA32(op.Vm >> shift);
Operand d = GetVecA32(op.Vd >> shift);
n = EmitSwapScalar(context, n, op.Vn, doubleSize);
m = EmitSwapScalar(context, m, op.Vm, doubleSize);
Operand res = scalarFunc(n, m);
// Insert scalar into vector.
res = EmitScalarInsert(context, d, res, op.Vd, doubleSize);
context.Copy(d, res);
}
public static void Vnmls_S(ArmEmitterContext context)
{
OpCode32SimdRegS op = (OpCode32SimdRegS)context.CurrOp;
if (Optimizations.FastFP && Optimizations.UseSse2)
{
EmitScalarTernaryOpSimd32(context, (d, n, m) =>
{
if ((op.Size & 1) == 0)
{
Operand res = context.AddIntrinsic(Intrinsic.X86Mulss, n, m);
Operand mask = X86GetScalar(context, -0f);
d = context.AddIntrinsic(Intrinsic.X86Xorps, mask, d);
return(context.AddIntrinsic(Intrinsic.X86Addss, d, res));
}
else
{
Operand res = context.AddIntrinsic(Intrinsic.X86Mulsd, n, m);
Operand mask = X86GetScalar(context, -0d);
d = context.AddIntrinsic(Intrinsic.X86Xorpd, mask, res);
return(context.AddIntrinsic(Intrinsic.X86Addsd, d, res));
}
});
}
else if (Optimizations.FastFP)
{
EmitScalarTernaryOpF32(context, (op1, op2, op3) =>
{
return(context.Add(context.Negate(op1), context.Multiply(op2, op3)));
});
}
else
{
EmitScalarTernaryOpF32(context, (op1, op2, op3) =>
{
return(EmitSoftFloatCall(context, nameof(SoftFloat32.FPNegMulSub), op1, op2, op3));
});
}
}
