public static void EmitVectorByScalarLongOpI32(ArmEmitterContext context, Func2I emit, bool signed)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
Operand m = ExtractElement(context, op.Vm, op.Size, signed);
if (op.Size == 2)
{
m = signed ? context.SignExtend32(OperandType.I64, m) : context.ZeroExtend32(OperandType.I64, m);
}
Operand res = context.VectorZero();
int elems = op.GetBytesCount() >> op.Size;
for (int index = 0; index < elems; index++)
{
Operand ne = EmitVectorExtract32(context, op.Qn, op.In + index, op.Size, signed);
if (op.Size == 2)
{
ne = signed ? context.SignExtend32(OperandType.I64, ne) : context.ZeroExtend32(OperandType.I64, ne);
}
res = EmitVectorInsert(context, res, emit(ne, m), index, op.Size + 1);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void EmitVectorsByScalarOpSimd32(ArmEmitterContext context, Func3I vectorFunc)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
Operand n = GetVecA32(op.Qn);
Operand d = GetVecA32(op.Qd);
Operand initialD = d;
int index = op.Vm & 3;
int dupeMask = (index << 6) | (index << 4) | (index << 2) | index;
Operand m = GetVecA32(op.Vm >> 2);
m = context.AddIntrinsic(Intrinsic.X86Shufps, m, m, Const(dupeMask));
if (!op.Q) // Register swap: move relevant doubleword to destination side.
{
n = EmitMoveDoubleWordToSide(context, n, op.Vn, op.Vd);
}
Operand res = vectorFunc(d, n, m);
if (!op.Q) // Register insert.
{
res = EmitDoubleWordInsert(context, initialD, res, op.Vd);
}
context.Copy(initialD, res);
}
public static void EmitVectorByScalarOpF32(ArmEmitterContext context, Intrinsic inst32, Intrinsic inst64)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
Intrinsic inst = (op.Size & 1) != 0 ? inst64 : inst32;
EmitVectorByScalarOpSimd32(context, (n, m) => context.AddIntrinsic(inst, n, m));
}
public static void EmitVectorsByScalarOpF32(ArmEmitterContext context, Intrinsic inst32pt1, Intrinsic inst64pt1, Intrinsic inst32pt2, Intrinsic inst64pt2)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
Intrinsic inst1 = (op.Size & 1) != 0 ? inst64pt1 : inst32pt1;
Intrinsic inst2 = (op.Size & 1) != 0 ? inst64pt2 : inst32pt2;
EmitVectorsByScalarOpSimd32(context, (d, n, m) =>
{
Operand res = context.AddIntrinsic(inst1, n, m);
return(res = context.AddIntrinsic(inst2, d, res));
});
}
public static void EmitVectorByScalarOpI32(ArmEmitterContext context, Func2I emit, bool signed)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
Operand m = ExtractElement(context, op.Vm, op.Size, signed);
Operand res = GetVecA32(op.Qd);
int elems = op.GetBytesCount() >> op.Size;
for (int index = 0; index < elems; index++)
{
Operand ne = EmitVectorExtract32(context, op.Qn, op.In + index, op.Size, signed);
res = EmitVectorInsert(context, res, emit(ne, m), op.Id + index, op.Size);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void Vmls_1(ArmEmitterContext context)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
if (op.F)
{
if (Optimizations.FastFP)
{
EmitVectorsByScalarOpF32(context, (op1, op2, op3) => context.Subtract(op1, context.Multiply(op2, op3)));
}
else
{
EmitVectorsByScalarOpF32(context, (op1, op2, op3) => EmitSoftFloatCallDefaultFpscr(context, SoftFloat32.FPMulSubFpscr, SoftFloat64.FPMulSubFpscr, op1, op2, op3));
}
}
else
{
EmitVectorsByScalarOpI32(context, (op1, op2, op3) => context.Subtract(op1, context.Multiply(op2, op3)), false);
}
}
// Vector by scalar
public static void EmitVectorByScalarOpF32(ArmEmitterContext context, Func2I emit)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
int sizeF = op.Size & 1;
OperandType type = sizeF != 0 ? OperandType.FP64 : OperandType.FP32;
int elems = op.GetBytesCount() >> sizeF + 2;
Operand m = ExtractScalar(context, type, op.Vm);
Operand res = GetVecA32(op.Qd);
for (int index = 0; index < elems; index++)
{
Operand ne = context.VectorExtract(type, GetVecA32(op.Qn), op.Fn + index);
res = context.VectorInsert(res, emit(ne, m), op.Fd + index);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void Vmul_1(ArmEmitterContext context)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
if (op.F)
{
if (Optimizations.FastFP && Optimizations.UseSse2)
{
EmitVectorByScalarOpF32(context, Intrinsic.X86Mulps, Intrinsic.X86Mulpd);
}
else if (Optimizations.FastFP)
{
EmitVectorByScalarOpF32(context, (op1, op2) => context.Multiply(op1, op2));
}
else
{
EmitVectorByScalarOpF32(context, (op1, op2) => EmitSoftFloatCallDefaultFpscr(context, nameof(SoftFloat32.FPMulFpscr), op1, op2));
}
}
else
{
EmitVectorByScalarOpI32(context, (op1, op2) => context.Multiply(op1, op2), false);
}
}
public static void Vmla_1(ArmEmitterContext context)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
if (op.F)
{
if (Optimizations.FastFP && Optimizations.UseSse2)
{
EmitVectorsByScalarOpF32(context, Intrinsic.X86Mulps, Intrinsic.X86Mulpd, Intrinsic.X86Addps, Intrinsic.X86Addpd);
}
else if (Optimizations.FastFP)
{
EmitVectorsByScalarOpF32(context, (op1, op2, op3) => context.Add(op1, context.Multiply(op2, op3)));
}
else
{
EmitVectorsByScalarOpF32(context, (op1, op2, op3) => EmitSoftFloatCallDefaultFpscr(context, SoftFloat32.FPMulAddFpscr, SoftFloat64.FPMulAddFpscr, op1, op2, op3));
}
}
else
{
EmitVectorsByScalarOpI32(context, (op1, op2, op3) => context.Add(op1, context.Multiply(op2, op3)), false);
}
}
public static void Vmull_1(ArmEmitterContext context)
{
OpCode32SimdRegElem op = (OpCode32SimdRegElem)context.CurrOp;
EmitVectorByScalarLongOpI32(context, (op1, op2) => context.Multiply(op1, op2), !op.U);
}
