public static void Vmin_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (op.U)
{
if (Optimizations.UseSse2)
{
EmitVectorBinaryOpSimd32(context, (op1, op2) => context.AddIntrinsic(X86PminuInstruction[op.Size], op1, op2));
}
else
{
EmitVectorBinaryOpZx32(context, (op1, op2) => context.ConditionalSelect(context.ICompareLessUI(op1, op2), op1, op2));
}
}
else
{
if (Optimizations.UseSse2)
{
EmitVectorBinaryOpSimd32(context, (op1, op2) => context.AddIntrinsic(X86PminsInstruction[op.Size], op1, op2));
}
else
{
EmitVectorBinaryOpSx32(context, (op1, op2) => context.ConditionalSelect(context.ICompareLess(op1, op2), op1, op2));
}
}
}
private static void EmitBifBit(ArmEmitterContext context, bool notRm)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (Optimizations.UseSse2)
{
EmitVectorTernaryOpSimd32(context, (d, n, m) =>
{
Operand res = context.AddIntrinsic(Intrinsic.X86Pxor, n, d);
res = context.AddIntrinsic((notRm) ? Intrinsic.X86Pandn : Intrinsic.X86Pand, m, res);
return(context.AddIntrinsic(Intrinsic.X86Pxor, d, res));
});
}
else
{
EmitVectorTernaryOpZx32(context, (d, n, m) =>
{
if (notRm)
{
m = context.BitwiseNot(m);
}
return(context.BitwiseExclusiveOr(
context.BitwiseAnd(m,
context.BitwiseExclusiveOr(d, n)), d));
});
}
}
public static void EmitVectorBinaryOpSimd32(ArmEmitterContext context, Func2I vectorFunc, int side = -1)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Operand n = GetVecA32(op.Qn);
Operand m = GetVecA32(op.Qm);
Operand d = GetVecA32(op.Qd);
if (side == -1)
{
side = op.Vd;
}
if (!op.Q) // Register swap: move relevant doubleword to destination side.
{
n = EmitMoveDoubleWordToSide(context, n, op.Vn, side);
m = EmitMoveDoubleWordToSide(context, m, op.Vm, side);
}
Operand res = vectorFunc(n, m);
if (!op.Q) // Register insert.
{
if (side != op.Vd)
{
res = EmitMoveDoubleWordToSide(context, res, side, op.Vd);
}
res = EmitDoubleWordInsert(context, d, res, op.Vd);
}
context.Copy(d, res);
}
public static void EmitVectorPairwiseTernaryLongOpI32(ArmEmitterContext context, Func3I emit, bool signed)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
int elems = op.GetBytesCount() >> op.Size;
int pairs = elems >> 1;
Operand res = GetVecA32(op.Qd);
for (int index = 0; index < pairs; index++)
{
int pairIndex = index * 2;
Operand m1 = EmitVectorExtract32(context, op.Qm, op.Im + pairIndex, op.Size, signed);
Operand m2 = EmitVectorExtract32(context, op.Qm, op.Im + pairIndex + 1, op.Size, signed);
if (op.Size == 2)
{
m1 = signed ? context.SignExtend32(OperandType.I64, m1) : context.ZeroExtend32(OperandType.I64, m1);
m2 = signed ? context.SignExtend32(OperandType.I64, m2) : context.ZeroExtend32(OperandType.I64, m2);
}
Operand d1 = EmitVectorExtract32(context, op.Qd, op.Id + index, op.Size + 1, signed);
res = EmitVectorInsert(context, res, emit(m1, m2, d1), op.Id + index, op.Size + 1);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void EmitVectorTernaryLongOpI32(ArmEmitterContext context, Func3I emit, bool signed)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Operand res = context.VectorZero();
int elems = op.GetBytesCount() >> op.Size;
for (int index = 0; index < elems; index++)
{
Operand de = EmitVectorExtract32(context, op.Qd, op.Id + index, op.Size + 1, signed);
Operand ne = EmitVectorExtract32(context, op.Qn, op.In + index, op.Size, signed);
Operand me = EmitVectorExtract32(context, op.Qm, op.Im + index, op.Size, signed);
if (op.Size == 2)
{
ne = signed ? context.SignExtend32(OperandType.I64, ne) : context.ZeroExtend32(OperandType.I64, ne);
me = signed ? context.SignExtend32(OperandType.I64, me) : context.ZeroExtend32(OperandType.I64, me);
}
res = EmitVectorInsert(context, res, emit(de, ne, me), index, op.Size + 1);
}
context.Copy(GetVecA32(op.Qd), res);
}
// Pairwise
public static void EmitVectorPairwiseOpF32(ArmEmitterContext context, Func2I emit)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
int sizeF = op.Size & 1;
OperandType type = sizeF != 0 ? OperandType.FP64 : OperandType.FP32;
int elems = op.GetBytesCount() >> (sizeF + 2);
int pairs = elems >> 1;
Operand res = GetVecA32(op.Qd);
Operand mvec = GetVecA32(op.Qm);
Operand nvec = GetVecA32(op.Qn);
for (int index = 0; index < pairs; index++)
{
int pairIndex = index << 1;
Operand n1 = context.VectorExtract(type, nvec, op.Fn + pairIndex);
Operand n2 = context.VectorExtract(type, nvec, op.Fn + pairIndex + 1);
res = context.VectorInsert(res, emit(n1, n2), op.Fd + index);
Operand m1 = context.VectorExtract(type, mvec, op.Fm + pairIndex);
Operand m2 = context.VectorExtract(type, mvec, op.Fm + pairIndex + 1);
res = context.VectorInsert(res, emit(m1, m2), op.Fd + index + pairs);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void EmitVectorBinaryOpF32(ArmEmitterContext context, Intrinsic inst32, Intrinsic inst64)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Intrinsic inst = (op.Size & 1) != 0 ? inst64 : inst32;
EmitVectorBinaryOpSimd32(context, (n, m) => context.AddIntrinsic(inst, n, m));
}
public static void EmitVectorTernaryOpF32(ArmEmitterContext context, Intrinsic inst32)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Debug.Assert((op.Size & 1) == 0);
EmitVectorTernaryOpSimd32(context, (d, n, m) =>
{
return(context.AddIntrinsic(inst32, d, n, m));
});
}
public static void Vadd_I(ArmEmitterContext context)
{
if (Optimizations.UseSse2)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorBinaryOpSimd32(context, (op1, op2) => context.AddIntrinsic(X86PaddInstruction[op.Size], op1, op2));
}
else
{
EmitVectorBinaryOpZx32(context, (op1, op2) => context.Add(op1, op2));
}
}
public static void Sha256su1_V(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Operand d = GetVecA32(op.Qd);
Operand n = GetVecA32(op.Qn);
Operand m = GetVecA32(op.Qm);
Operand res = InstEmitSimdHashHelper.EmitSha256su1(context, d, n, m);
context.Copy(GetVecA32(op.Qd), res);
}
public static void Vpadd_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (Optimizations.UseSsse3)
{
EmitSsse3VectorPairwiseOp32(context, X86PaddInstruction);
}
else
{
EmitVectorPairwiseOpI32(context, (op1, op2) => context.Add(op1, op2), !op.U);
}
}
public static void Vmul_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (op.U) // This instruction is always signed, U indicates polynomial mode.
{
EmitVectorBinaryOpZx32(context, (op1, op2) => EmitPolynomialMultiply(context, op1, op2, 8 << op.Size));
}
else
{
EmitVectorBinaryOpSx32(context, (op1, op2) => context.Multiply(op1, op2));
}
}
public static void EmitVectorTernaryOpF32(ArmEmitterContext context, Intrinsic inst32pt1, Intrinsic inst64pt1, Intrinsic inst32pt2, Intrinsic inst64pt2)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Intrinsic inst1 = (op.Size & 1) != 0 ? inst64pt1 : inst32pt1;
Intrinsic inst2 = (op.Size & 1) != 0 ? inst64pt2 : inst32pt2;
EmitVectorTernaryOpSimd32(context, (d, n, m) =>
{
Operand res = context.AddIntrinsic(inst1, n, m);
return(res = context.AddIntrinsic(inst2, d, res));
});
}
public static void Vshl_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (op.U)
{
EmitVectorBinaryOpZx32(context, (op1, op2) => EmitShlRegOp(context, op2, op1, op.Size, true));
}
else
{
EmitVectorBinaryOpSx32(context, (op1, op2) => EmitShlRegOp(context, op2, op1, op.Size, false));
}
}
public static void Vmin_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (op.U)
{
EmitVectorBinaryOpZx32(context, (op1, op2) => context.ConditionalSelect(context.ICompareLessUI(op1, op2), op1, op2));
}
else
{
EmitVectorBinaryOpSx32(context, (op1, op2) => context.ConditionalSelect(context.ICompareLess(op1, op2), op1, op2));
}
}
// Pairwise
public static void EmitSse2VectorPairwiseOpF32(ArmEmitterContext context, Intrinsic inst32)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorBinaryOpSimd32(context, (n, m) =>
{
Operand unpck = context.AddIntrinsic(Intrinsic.X86Unpcklps, n, m);
Operand part0 = unpck;
Operand part1 = context.AddIntrinsic(Intrinsic.X86Movhlps, unpck, unpck);
return(context.AddIntrinsic(inst32, part0, part1));
}, 0);
}
private static void EmitBifBit(ArmEmitterContext context, bool notRm)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorTernaryOpZx32(context, (d, n, m) =>
{
if (notRm)
{
m = context.BitwiseNot(m);
}
return(context.BitwiseExclusiveOr(
context.BitwiseAnd(m,
context.BitwiseExclusiveOr(d, n)), d));
});
}
public static void Vpmin_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
if (Optimizations.UseSsse3)
{
EmitSsse3VectorPairwiseOp32(context, op.U ? X86PminuInstruction : X86PminsInstruction);
}
else
{
EmitVectorPairwiseOpI32(context, (op1, op2) =>
{
Operand greater = op.U ? context.ICompareLessUI(op1, op2) : context.ICompareLess(op1, op2);
return(context.ConditionalSelect(greater, op1, op2));
}, !op.U);
}
}
public static void EmitVectorBinaryOpI32(ArmEmitterContext context, Func2I emit, bool signed)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
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);
Operand me = EmitVectorExtract32(context, op.Qm, op.Im + index, op.Size, signed);
res = EmitVectorInsert(context, res, emit(ne, me), op.Id + index, op.Size);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void EmitVectorBinaryOpF32(ArmEmitterContext context, Func2I emit)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
int sizeF = op.Size & 1;
OperandType type = sizeF != 0 ? OperandType.FP64 : OperandType.FP32;
int elems = op.GetBytesCount() >> (sizeF + 2);
Operand res = GetVecA32(op.Qd);
for (int index = 0; index < elems; index++)
{
Operand ne = context.VectorExtract(type, GetVecA32(op.Qn), op.Fn + index);
Operand me = context.VectorExtract(type, GetVecA32(op.Qm), op.Fm + index);
res = context.VectorInsert(res, emit(ne, me), op.Fd + index);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void EmitSsse3VectorPairwiseOp32(ArmEmitterContext context, Intrinsic[] inst)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorBinaryOpSimd32(context, (n, m) =>
{
if (op.RegisterSize == RegisterSize.Simd64)
{
Operand zeroEvenMask = X86GetElements(context, ZeroMask, EvenMasks[op.Size]);
Operand zeroOddMask = X86GetElements(context, ZeroMask, OddMasks[op.Size]);
Operand mN = context.AddIntrinsic(Intrinsic.X86Punpcklqdq, n, m); // m:n
Operand left = context.AddIntrinsic(Intrinsic.X86Pshufb, mN, zeroEvenMask); // 0:even from m:n
Operand right = context.AddIntrinsic(Intrinsic.X86Pshufb, mN, zeroOddMask); // 0:odd from m:n
return(context.AddIntrinsic(inst[op.Size], left, right));
}
else if (op.Size < 3)
{
Operand oddEvenMask = X86GetElements(context, OddMasks[op.Size], EvenMasks[op.Size]);
Operand oddEvenN = context.AddIntrinsic(Intrinsic.X86Pshufb, n, oddEvenMask); // odd:even from n
Operand oddEvenM = context.AddIntrinsic(Intrinsic.X86Pshufb, m, oddEvenMask); // odd:even from m
Operand left = context.AddIntrinsic(Intrinsic.X86Punpcklqdq, oddEvenN, oddEvenM);
Operand right = context.AddIntrinsic(Intrinsic.X86Punpckhqdq, oddEvenN, oddEvenM);
return(context.AddIntrinsic(inst[op.Size], left, right));
}
else
{
Operand left = context.AddIntrinsic(Intrinsic.X86Punpcklqdq, n, m);
Operand right = context.AddIntrinsic(Intrinsic.X86Punpckhqdq, n, m);
return(context.AddIntrinsic(inst[3], left, right));
}
}, 0);
}
public static void EmitVectorTernaryOpSimd32(ArmEmitterContext context, Func3I vectorFunc)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
Operand n = GetVecA32(op.Qn);
Operand m = GetVecA32(op.Qm);
Operand d = GetVecA32(op.Qd);
Operand initialD = d;
if (!op.Q) // Register swap: move relevant doubleword to destination side.
{
n = EmitMoveDoubleWordToSide(context, n, op.Vn, op.Vd);
m = EmitMoveDoubleWordToSide(context, m, op.Vm, 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 EmitVectorPairwiseOpI32(ArmEmitterContext context, Func2I emit, bool signed)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
int elems = op.GetBytesCount() >> op.Size;
int pairs = elems >> 1;
Operand res = GetVecA32(op.Qd);
for (int index = 0; index < pairs; index++)
{
int pairIndex = index << 1;
Operand n1 = EmitVectorExtract32(context, op.Qn, op.In + pairIndex, op.Size, signed);
Operand n2 = EmitVectorExtract32(context, op.Qn, op.In + pairIndex + 1, op.Size, signed);
Operand m1 = EmitVectorExtract32(context, op.Qm, op.Im + pairIndex, op.Size, signed);
Operand m2 = EmitVectorExtract32(context, op.Qm, op.Im + pairIndex + 1, op.Size, signed);
res = EmitVectorInsert(context, res, emit(n1, n2), op.Id + index, op.Size);
res = EmitVectorInsert(context, res, emit(m1, m2), op.Id + index + pairs, op.Size);
}
context.Copy(GetVecA32(op.Qd), res);
}
public static void Vmlsl_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorTernaryLongOpI32(context, (opD, op1, op2) => context.Subtract(opD, context.Multiply(op1, op2)), !op.U);
}
public static void Vcge_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitCmpOpI32(context, context.ICompareGreaterOrEqual, context.ICompareGreaterOrEqualUI, false, !op.U);
}
public static void Vpadd_I(ArmEmitterContext context)
{
OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
EmitVectorPairwiseOpI32(context, (op1, op2) => context.Add(op1, op2), !op.U);
}
