forked from OSchip/llvm-project
1520 lines
73 KiB
TableGen
1520 lines
73 KiB
TableGen
//===-- PPCInstrAltivec.td - The PowerPC Altivec Extension -*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the Altivec extension to the PowerPC instruction set.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// *********************************** NOTE ***********************************
|
|
// ** For POWER8 Little Endian, the VSX swap optimization relies on knowing **
|
|
// ** which VMX and VSX instructions are lane-sensitive and which are not. **
|
|
// ** A lane-sensitive instruction relies, implicitly or explicitly, on **
|
|
// ** whether lanes are numbered from left to right. An instruction like **
|
|
// ** VADDFP is not lane-sensitive, because each lane of the result vector **
|
|
// ** relies only on the corresponding lane of the source vectors. However, **
|
|
// ** an instruction like VMULESB is lane-sensitive, because "even" and **
|
|
// ** "odd" lanes are different for big-endian and little-endian numbering. **
|
|
// ** **
|
|
// ** When adding new VMX and VSX instructions, please consider whether they **
|
|
// ** are lane-sensitive. If so, they must be added to a switch statement **
|
|
// ** in PPCVSXSwapRemoval::gatherVectorInstructions(). **
|
|
// ****************************************************************************
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Altivec transformation functions and pattern fragments.
|
|
//
|
|
|
|
// Since we canonicalize buildvectors to v16i8, all vnots "-1" operands will be
|
|
// of that type.
|
|
def vnot_ppc : PatFrag<(ops node:$in),
|
|
(xor node:$in, (bitconvert (v16i8 immAllOnesV)))>;
|
|
|
|
def vpkuhum_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUHUMShuffleMask(cast<ShuffleVectorSDNode>(N), 0, *CurDAG);
|
|
}]>;
|
|
def vpkuwum_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUWUMShuffleMask(cast<ShuffleVectorSDNode>(N), 0, *CurDAG);
|
|
}]>;
|
|
def vpkudum_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUDUMShuffleMask(cast<ShuffleVectorSDNode>(N), 0, *CurDAG);
|
|
}]>;
|
|
def vpkuhum_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUHUMShuffleMask(cast<ShuffleVectorSDNode>(N), 1, *CurDAG);
|
|
}]>;
|
|
def vpkuwum_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUWUMShuffleMask(cast<ShuffleVectorSDNode>(N), 1, *CurDAG);
|
|
}]>;
|
|
def vpkudum_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUDUMShuffleMask(cast<ShuffleVectorSDNode>(N), 1, *CurDAG);
|
|
}]>;
|
|
|
|
// These fragments are provided for little-endian, where the inputs must be
|
|
// swapped for correct semantics.
|
|
def vpkuhum_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUHUMShuffleMask(cast<ShuffleVectorSDNode>(N), 2, *CurDAG);
|
|
}]>;
|
|
def vpkuwum_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUWUMShuffleMask(cast<ShuffleVectorSDNode>(N), 2, *CurDAG);
|
|
}]>;
|
|
def vpkudum_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVPKUDUMShuffleMask(cast<ShuffleVectorSDNode>(N), 2, *CurDAG);
|
|
}]>;
|
|
|
|
def vmrglb_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 0, *CurDAG);
|
|
}]>;
|
|
def vmrglh_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 0, *CurDAG);
|
|
}]>;
|
|
def vmrglw_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 0, *CurDAG);
|
|
}]>;
|
|
def vmrghb_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 0, *CurDAG);
|
|
}]>;
|
|
def vmrghh_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 0, *CurDAG);
|
|
}]>;
|
|
def vmrghw_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 0, *CurDAG);
|
|
}]>;
|
|
|
|
|
|
def vmrglb_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 1, *CurDAG);
|
|
}]>;
|
|
def vmrglh_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 1, *CurDAG);
|
|
}]>;
|
|
def vmrglw_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 1, *CurDAG);
|
|
}]>;
|
|
def vmrghb_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 1, *CurDAG);
|
|
}]>;
|
|
def vmrghh_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 1, *CurDAG);
|
|
}]>;
|
|
def vmrghw_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 1, *CurDAG);
|
|
}]>;
|
|
|
|
|
|
// These fragments are provided for little-endian, where the inputs must be
|
|
// swapped for correct semantics.
|
|
def vmrglb_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle (v16i8 node:$lhs), node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 2, *CurDAG);
|
|
}]>;
|
|
def vmrglh_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 2, *CurDAG);
|
|
}]>;
|
|
def vmrglw_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGLShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 2, *CurDAG);
|
|
}]>;
|
|
def vmrghb_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 1, 2, *CurDAG);
|
|
}]>;
|
|
def vmrghh_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 2, 2, *CurDAG);
|
|
}]>;
|
|
def vmrghw_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGHShuffleMask(cast<ShuffleVectorSDNode>(N), 4, 2, *CurDAG);
|
|
}]>;
|
|
|
|
|
|
def vmrgew_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), true, 0, *CurDAG);
|
|
}]>;
|
|
def vmrgow_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), false, 0, *CurDAG);
|
|
}]>;
|
|
def vmrgew_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), true, 1, *CurDAG);
|
|
}]>;
|
|
def vmrgow_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), false, 1, *CurDAG);
|
|
}]>;
|
|
def vmrgew_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), true, 2, *CurDAG);
|
|
}]>;
|
|
def vmrgow_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVMRGEOShuffleMask(cast<ShuffleVectorSDNode>(N), false, 2, *CurDAG);
|
|
}]>;
|
|
|
|
|
|
|
|
def VSLDOI_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::isVSLDOIShuffleMask(N, 0, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vsldoi_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVSLDOIShuffleMask(N, 0, *CurDAG) != -1;
|
|
}], VSLDOI_get_imm>;
|
|
|
|
|
|
/// VSLDOI_unary* - These are used to match vsldoi(X,X), which is turned into
|
|
/// vector_shuffle(X,undef,mask) by the dag combiner.
|
|
def VSLDOI_unary_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::isVSLDOIShuffleMask(N, 1, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vsldoi_unary_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVSLDOIShuffleMask(N, 1, *CurDAG) != -1;
|
|
}], VSLDOI_unary_get_imm>;
|
|
|
|
|
|
/// VSLDOI_swapped* - These fragments are provided for little-endian, where
|
|
/// the inputs must be swapped for correct semantics.
|
|
def VSLDOI_swapped_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::isVSLDOIShuffleMask(N, 2, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vsldoi_swapped_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isVSLDOIShuffleMask(N, 2, *CurDAG) != -1;
|
|
}], VSLDOI_get_imm>;
|
|
|
|
|
|
// VSPLT*_get_imm xform function: convert vector_shuffle mask to VSPLT* imm.
|
|
def VSPLTB_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::getVSPLTImmediate(N, 1, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vspltb_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isSplatShuffleMask(cast<ShuffleVectorSDNode>(N), 1);
|
|
}], VSPLTB_get_imm>;
|
|
def VSPLTH_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::getVSPLTImmediate(N, 2, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vsplth_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isSplatShuffleMask(cast<ShuffleVectorSDNode>(N), 2);
|
|
}], VSPLTH_get_imm>;
|
|
def VSPLTW_get_imm : SDNodeXForm<vector_shuffle, [{
|
|
return getI32Imm(PPC::getVSPLTImmediate(N, 4, *CurDAG), SDLoc(N));
|
|
}]>;
|
|
def vspltw_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(vector_shuffle node:$lhs, node:$rhs), [{
|
|
return PPC::isSplatShuffleMask(cast<ShuffleVectorSDNode>(N), 4);
|
|
}], VSPLTW_get_imm>;
|
|
|
|
|
|
// VSPLTISB_get_imm xform function: convert build_vector to VSPLTISB imm.
|
|
def VSPLTISB_get_imm : SDNodeXForm<build_vector, [{
|
|
return PPC::get_VSPLTI_elt(N, 1, *CurDAG);
|
|
}]>;
|
|
def vecspltisb : PatLeaf<(build_vector), [{
|
|
return PPC::get_VSPLTI_elt(N, 1, *CurDAG).getNode() != nullptr;
|
|
}], VSPLTISB_get_imm>;
|
|
|
|
// VSPLTISH_get_imm xform function: convert build_vector to VSPLTISH imm.
|
|
def VSPLTISH_get_imm : SDNodeXForm<build_vector, [{
|
|
return PPC::get_VSPLTI_elt(N, 2, *CurDAG);
|
|
}]>;
|
|
def vecspltish : PatLeaf<(build_vector), [{
|
|
return PPC::get_VSPLTI_elt(N, 2, *CurDAG).getNode() != nullptr;
|
|
}], VSPLTISH_get_imm>;
|
|
|
|
// VSPLTISW_get_imm xform function: convert build_vector to VSPLTISW imm.
|
|
def VSPLTISW_get_imm : SDNodeXForm<build_vector, [{
|
|
return PPC::get_VSPLTI_elt(N, 4, *CurDAG);
|
|
}]>;
|
|
def vecspltisw : PatLeaf<(build_vector), [{
|
|
return PPC::get_VSPLTI_elt(N, 4, *CurDAG).getNode() != nullptr;
|
|
}], VSPLTISW_get_imm>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Helpers for defining instructions that directly correspond to intrinsics.
|
|
|
|
// VA1a_Int_Ty - A VAForm_1a intrinsic definition of specific type.
|
|
class VA1a_Int_Ty<bits<6> xo, string opc, Intrinsic IntID, ValueType Ty>
|
|
: VAForm_1a<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vC),
|
|
!strconcat(opc, " $vD, $vA, $vB, $vC"), IIC_VecFP,
|
|
[(set Ty:$vD, (IntID Ty:$vA, Ty:$vB, Ty:$vC))]>;
|
|
|
|
// VA1a_Int_Ty2 - A VAForm_1a intrinsic definition where the type of the
|
|
// inputs doesn't match the type of the output.
|
|
class VA1a_Int_Ty2<bits<6> xo, string opc, Intrinsic IntID, ValueType OutTy,
|
|
ValueType InTy>
|
|
: VAForm_1a<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vC),
|
|
!strconcat(opc, " $vD, $vA, $vB, $vC"), IIC_VecFP,
|
|
[(set OutTy:$vD, (IntID InTy:$vA, InTy:$vB, InTy:$vC))]>;
|
|
|
|
// VA1a_Int_Ty3 - A VAForm_1a intrinsic definition where there are two
|
|
// input types and an output type.
|
|
class VA1a_Int_Ty3<bits<6> xo, string opc, Intrinsic IntID, ValueType OutTy,
|
|
ValueType In1Ty, ValueType In2Ty>
|
|
: VAForm_1a<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vC),
|
|
!strconcat(opc, " $vD, $vA, $vB, $vC"), IIC_VecFP,
|
|
[(set OutTy:$vD,
|
|
(IntID In1Ty:$vA, In1Ty:$vB, In2Ty:$vC))]>;
|
|
|
|
// VX1_Int_Ty - A VXForm_1 intrinsic definition of specific type.
|
|
class VX1_Int_Ty<bits<11> xo, string opc, Intrinsic IntID, ValueType Ty>
|
|
: VXForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vA, $vB"), IIC_VecFP,
|
|
[(set Ty:$vD, (IntID Ty:$vA, Ty:$vB))]>;
|
|
|
|
// VX1_Int_Ty2 - A VXForm_1 intrinsic definition where the type of the
|
|
// inputs doesn't match the type of the output.
|
|
class VX1_Int_Ty2<bits<11> xo, string opc, Intrinsic IntID, ValueType OutTy,
|
|
ValueType InTy>
|
|
: VXForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vA, $vB"), IIC_VecFP,
|
|
[(set OutTy:$vD, (IntID InTy:$vA, InTy:$vB))]>;
|
|
|
|
// VX1_Int_Ty3 - A VXForm_1 intrinsic definition where there are two
|
|
// input types and an output type.
|
|
class VX1_Int_Ty3<bits<11> xo, string opc, Intrinsic IntID, ValueType OutTy,
|
|
ValueType In1Ty, ValueType In2Ty>
|
|
: VXForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vA, $vB"), IIC_VecFP,
|
|
[(set OutTy:$vD, (IntID In1Ty:$vA, In2Ty:$vB))]>;
|
|
|
|
// VX2_Int_SP - A VXForm_2 intrinsic definition of vector single-precision type.
|
|
class VX2_Int_SP<bits<11> xo, string opc, Intrinsic IntID>
|
|
: VXForm_2<xo, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vB"), IIC_VecFP,
|
|
[(set v4f32:$vD, (IntID v4f32:$vB))]>;
|
|
|
|
// VX2_Int_Ty2 - A VXForm_2 intrinsic definition where the type of the
|
|
// inputs doesn't match the type of the output.
|
|
class VX2_Int_Ty2<bits<11> xo, string opc, Intrinsic IntID, ValueType OutTy,
|
|
ValueType InTy>
|
|
: VXForm_2<xo, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vB"), IIC_VecFP,
|
|
[(set OutTy:$vD, (IntID InTy:$vB))]>;
|
|
|
|
class VXBX_Int_Ty<bits<11> xo, string opc, Intrinsic IntID, ValueType Ty>
|
|
: VXForm_BX<xo, (outs vrrc:$vD), (ins vrrc:$vA),
|
|
!strconcat(opc, " $vD, $vA"), IIC_VecFP,
|
|
[(set Ty:$vD, (IntID Ty:$vA))]>;
|
|
|
|
class VXCR_Int_Ty<bits<11> xo, string opc, Intrinsic IntID, ValueType Ty>
|
|
: VXForm_CR<xo, (outs vrrc:$vD), (ins vrrc:$vA, u1imm:$ST, u4imm:$SIX),
|
|
!strconcat(opc, " $vD, $vA, $ST, $SIX"), IIC_VecFP,
|
|
[(set Ty:$vD, (IntID Ty:$vA, imm:$ST, imm:$SIX))]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Definitions.
|
|
|
|
def HasAltivec : Predicate<"PPCSubTarget->hasAltivec()">;
|
|
let Predicates = [HasAltivec] in {
|
|
|
|
def DSS : DSS_Form<0, 822, (outs), (ins u5imm:$STRM),
|
|
"dss $STRM", IIC_LdStLoad /*FIXME*/, [(int_ppc_altivec_dss imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST> {
|
|
let A = 0;
|
|
let B = 0;
|
|
}
|
|
|
|
def DSSALL : DSS_Form<1, 822, (outs), (ins),
|
|
"dssall", IIC_LdStLoad /*FIXME*/, [(int_ppc_altivec_dssall)]>,
|
|
Deprecated<DeprecatedDST> {
|
|
let STRM = 0;
|
|
let A = 0;
|
|
let B = 0;
|
|
}
|
|
|
|
def DST : DSS_Form<0, 342, (outs), (ins u5imm:$STRM, gprc:$rA, gprc:$rB),
|
|
"dst $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dst i32:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTT : DSS_Form<1, 342, (outs), (ins u5imm:$STRM, gprc:$rA, gprc:$rB),
|
|
"dstt $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dstt i32:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTST : DSS_Form<0, 374, (outs), (ins u5imm:$STRM, gprc:$rA, gprc:$rB),
|
|
"dstst $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dstst i32:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTSTT : DSS_Form<1, 374, (outs), (ins u5imm:$STRM, gprc:$rA, gprc:$rB),
|
|
"dststt $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dststt i32:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
let isCodeGenOnly = 1 in {
|
|
// The very same instructions as above, but formally matching 64bit registers.
|
|
def DST64 : DSS_Form<0, 342, (outs), (ins u5imm:$STRM, g8rc:$rA, gprc:$rB),
|
|
"dst $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dst i64:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTT64 : DSS_Form<1, 342, (outs), (ins u5imm:$STRM, g8rc:$rA, gprc:$rB),
|
|
"dstt $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dstt i64:$rA, i32:$rB, imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTST64 : DSS_Form<0, 374, (outs), (ins u5imm:$STRM, g8rc:$rA, gprc:$rB),
|
|
"dstst $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dstst i64:$rA, i32:$rB,
|
|
imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
|
|
def DSTSTT64 : DSS_Form<1, 374, (outs), (ins u5imm:$STRM, g8rc:$rA, gprc:$rB),
|
|
"dststt $rA, $rB, $STRM", IIC_LdStLoad /*FIXME*/,
|
|
[(int_ppc_altivec_dststt i64:$rA, i32:$rB,
|
|
imm:$STRM)]>,
|
|
Deprecated<DeprecatedDST>;
|
|
}
|
|
|
|
def MFVSCR : VXForm_4<1540, (outs vrrc:$vD), (ins),
|
|
"mfvscr $vD", IIC_LdStStore,
|
|
[(set v8i16:$vD, (int_ppc_altivec_mfvscr))]>;
|
|
def MTVSCR : VXForm_5<1604, (outs), (ins vrrc:$vB),
|
|
"mtvscr $vB", IIC_LdStLoad,
|
|
[(int_ppc_altivec_mtvscr v4i32:$vB)]>;
|
|
|
|
let PPC970_Unit = 2, mayLoad = 1, mayStore = 0 in { // Loads.
|
|
def LVEBX: XForm_1<31, 7, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvebx $vD, $src", IIC_LdStLoad,
|
|
[(set v16i8:$vD, (int_ppc_altivec_lvebx xoaddr:$src))]>;
|
|
def LVEHX: XForm_1<31, 39, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvehx $vD, $src", IIC_LdStLoad,
|
|
[(set v8i16:$vD, (int_ppc_altivec_lvehx xoaddr:$src))]>;
|
|
def LVEWX: XForm_1<31, 71, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvewx $vD, $src", IIC_LdStLoad,
|
|
[(set v4i32:$vD, (int_ppc_altivec_lvewx xoaddr:$src))]>;
|
|
def LVX : XForm_1<31, 103, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvx $vD, $src", IIC_LdStLoad,
|
|
[(set v4i32:$vD, (int_ppc_altivec_lvx xoaddr:$src))]>;
|
|
def LVXL : XForm_1<31, 359, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvxl $vD, $src", IIC_LdStLoad,
|
|
[(set v4i32:$vD, (int_ppc_altivec_lvxl xoaddr:$src))]>;
|
|
}
|
|
|
|
def LVSL : XForm_1<31, 6, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvsl $vD, $src", IIC_LdStLoad,
|
|
[(set v16i8:$vD, (int_ppc_altivec_lvsl xoaddr:$src))]>,
|
|
PPC970_Unit_LSU;
|
|
def LVSR : XForm_1<31, 38, (outs vrrc:$vD), (ins memrr:$src),
|
|
"lvsr $vD, $src", IIC_LdStLoad,
|
|
[(set v16i8:$vD, (int_ppc_altivec_lvsr xoaddr:$src))]>,
|
|
PPC970_Unit_LSU;
|
|
|
|
let PPC970_Unit = 2, mayStore = 1, mayLoad = 0 in { // Stores.
|
|
def STVEBX: XForm_8<31, 135, (outs), (ins vrrc:$rS, memrr:$dst),
|
|
"stvebx $rS, $dst", IIC_LdStStore,
|
|
[(int_ppc_altivec_stvebx v16i8:$rS, xoaddr:$dst)]>;
|
|
def STVEHX: XForm_8<31, 167, (outs), (ins vrrc:$rS, memrr:$dst),
|
|
"stvehx $rS, $dst", IIC_LdStStore,
|
|
[(int_ppc_altivec_stvehx v8i16:$rS, xoaddr:$dst)]>;
|
|
def STVEWX: XForm_8<31, 199, (outs), (ins vrrc:$rS, memrr:$dst),
|
|
"stvewx $rS, $dst", IIC_LdStStore,
|
|
[(int_ppc_altivec_stvewx v4i32:$rS, xoaddr:$dst)]>;
|
|
def STVX : XForm_8<31, 231, (outs), (ins vrrc:$rS, memrr:$dst),
|
|
"stvx $rS, $dst", IIC_LdStStore,
|
|
[(int_ppc_altivec_stvx v4i32:$rS, xoaddr:$dst)]>;
|
|
def STVXL : XForm_8<31, 487, (outs), (ins vrrc:$rS, memrr:$dst),
|
|
"stvxl $rS, $dst", IIC_LdStStore,
|
|
[(int_ppc_altivec_stvxl v4i32:$rS, xoaddr:$dst)]>;
|
|
}
|
|
|
|
let PPC970_Unit = 5 in { // VALU Operations.
|
|
// VA-Form instructions. 3-input AltiVec ops.
|
|
let isCommutable = 1 in {
|
|
def VMADDFP : VAForm_1<46, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vC, vrrc:$vB),
|
|
"vmaddfp $vD, $vA, $vC, $vB", IIC_VecFP,
|
|
[(set v4f32:$vD,
|
|
(fma v4f32:$vA, v4f32:$vC, v4f32:$vB))]>;
|
|
|
|
// FIXME: The fma+fneg pattern won't match because fneg is not legal.
|
|
def VNMSUBFP: VAForm_1<47, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vC, vrrc:$vB),
|
|
"vnmsubfp $vD, $vA, $vC, $vB", IIC_VecFP,
|
|
[(set v4f32:$vD, (fneg (fma v4f32:$vA, v4f32:$vC,
|
|
(fneg v4f32:$vB))))]>;
|
|
|
|
def VMHADDSHS : VA1a_Int_Ty<32, "vmhaddshs", int_ppc_altivec_vmhaddshs, v8i16>;
|
|
def VMHRADDSHS : VA1a_Int_Ty<33, "vmhraddshs", int_ppc_altivec_vmhraddshs,
|
|
v8i16>;
|
|
def VMLADDUHM : VA1a_Int_Ty<34, "vmladduhm", int_ppc_altivec_vmladduhm, v8i16>;
|
|
} // isCommutable
|
|
|
|
def VPERM : VA1a_Int_Ty3<43, "vperm", int_ppc_altivec_vperm,
|
|
v4i32, v4i32, v16i8>;
|
|
def VSEL : VA1a_Int_Ty<42, "vsel", int_ppc_altivec_vsel, v4i32>;
|
|
|
|
// Shuffles.
|
|
def VSLDOI : VAForm_2<44, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, u4imm:$SH),
|
|
"vsldoi $vD, $vA, $vB, $SH", IIC_VecFP,
|
|
[(set v16i8:$vD,
|
|
(PPCvecshl v16i8:$vA, v16i8:$vB, imm32SExt16:$SH))]>;
|
|
|
|
// VX-Form instructions. AltiVec arithmetic ops.
|
|
let isCommutable = 1 in {
|
|
def VADDFP : VXForm_1<10, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vaddfp $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4f32:$vD, (fadd v4f32:$vA, v4f32:$vB))]>;
|
|
|
|
def VADDUBM : VXForm_1<0, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vaddubm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (add v16i8:$vA, v16i8:$vB))]>;
|
|
def VADDUHM : VXForm_1<64, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vadduhm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (add v8i16:$vA, v8i16:$vB))]>;
|
|
def VADDUWM : VXForm_1<128, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vadduwm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (add v4i32:$vA, v4i32:$vB))]>;
|
|
|
|
def VADDCUW : VX1_Int_Ty<384, "vaddcuw", int_ppc_altivec_vaddcuw, v4i32>;
|
|
def VADDSBS : VX1_Int_Ty<768, "vaddsbs", int_ppc_altivec_vaddsbs, v16i8>;
|
|
def VADDSHS : VX1_Int_Ty<832, "vaddshs", int_ppc_altivec_vaddshs, v8i16>;
|
|
def VADDSWS : VX1_Int_Ty<896, "vaddsws", int_ppc_altivec_vaddsws, v4i32>;
|
|
def VADDUBS : VX1_Int_Ty<512, "vaddubs", int_ppc_altivec_vaddubs, v16i8>;
|
|
def VADDUHS : VX1_Int_Ty<576, "vadduhs", int_ppc_altivec_vadduhs, v8i16>;
|
|
def VADDUWS : VX1_Int_Ty<640, "vadduws", int_ppc_altivec_vadduws, v4i32>;
|
|
} // isCommutable
|
|
|
|
let isCommutable = 1 in
|
|
def VAND : VXForm_1<1028, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vand $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD, (and v4i32:$vA, v4i32:$vB))]>;
|
|
def VANDC : VXForm_1<1092, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vandc $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD, (and v4i32:$vA,
|
|
(vnot_ppc v4i32:$vB)))]>;
|
|
|
|
def VCFSX : VXForm_1<842, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vcfsx $vD, $vB, $UIMM", IIC_VecFP,
|
|
[(set v4f32:$vD,
|
|
(int_ppc_altivec_vcfsx v4i32:$vB, imm:$UIMM))]>;
|
|
def VCFUX : VXForm_1<778, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vcfux $vD, $vB, $UIMM", IIC_VecFP,
|
|
[(set v4f32:$vD,
|
|
(int_ppc_altivec_vcfux v4i32:$vB, imm:$UIMM))]>;
|
|
def VCTSXS : VXForm_1<970, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vctsxs $vD, $vB, $UIMM", IIC_VecFP,
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vctsxs v4f32:$vB, imm:$UIMM))]>;
|
|
def VCTUXS : VXForm_1<906, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vctuxs $vD, $vB, $UIMM", IIC_VecFP,
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vctuxs v4f32:$vB, imm:$UIMM))]>;
|
|
|
|
// Defines with the UIM field set to 0 for floating-point
|
|
// to integer (fp_to_sint/fp_to_uint) conversions and integer
|
|
// to floating-point (sint_to_fp/uint_to_fp) conversions.
|
|
let isCodeGenOnly = 1, VA = 0 in {
|
|
def VCFSX_0 : VXForm_1<842, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vcfsx $vD, $vB, 0", IIC_VecFP,
|
|
[(set v4f32:$vD,
|
|
(int_ppc_altivec_vcfsx v4i32:$vB, 0))]>;
|
|
def VCTUXS_0 : VXForm_1<906, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vctuxs $vD, $vB, 0", IIC_VecFP,
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vctuxs v4f32:$vB, 0))]>;
|
|
def VCFUX_0 : VXForm_1<778, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vcfux $vD, $vB, 0", IIC_VecFP,
|
|
[(set v4f32:$vD,
|
|
(int_ppc_altivec_vcfux v4i32:$vB, 0))]>;
|
|
def VCTSXS_0 : VXForm_1<970, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vctsxs $vD, $vB, 0", IIC_VecFP,
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vctsxs v4f32:$vB, 0))]>;
|
|
}
|
|
def VEXPTEFP : VX2_Int_SP<394, "vexptefp", int_ppc_altivec_vexptefp>;
|
|
def VLOGEFP : VX2_Int_SP<458, "vlogefp", int_ppc_altivec_vlogefp>;
|
|
|
|
let isCommutable = 1 in {
|
|
def VAVGSB : VX1_Int_Ty<1282, "vavgsb", int_ppc_altivec_vavgsb, v16i8>;
|
|
def VAVGSH : VX1_Int_Ty<1346, "vavgsh", int_ppc_altivec_vavgsh, v8i16>;
|
|
def VAVGSW : VX1_Int_Ty<1410, "vavgsw", int_ppc_altivec_vavgsw, v4i32>;
|
|
def VAVGUB : VX1_Int_Ty<1026, "vavgub", int_ppc_altivec_vavgub, v16i8>;
|
|
def VAVGUH : VX1_Int_Ty<1090, "vavguh", int_ppc_altivec_vavguh, v8i16>;
|
|
def VAVGUW : VX1_Int_Ty<1154, "vavguw", int_ppc_altivec_vavguw, v4i32>;
|
|
|
|
def VMAXFP : VX1_Int_Ty<1034, "vmaxfp", int_ppc_altivec_vmaxfp, v4f32>;
|
|
def VMAXSB : VX1_Int_Ty< 258, "vmaxsb", int_ppc_altivec_vmaxsb, v16i8>;
|
|
def VMAXSH : VX1_Int_Ty< 322, "vmaxsh", int_ppc_altivec_vmaxsh, v8i16>;
|
|
def VMAXSW : VX1_Int_Ty< 386, "vmaxsw", int_ppc_altivec_vmaxsw, v4i32>;
|
|
def VMAXUB : VX1_Int_Ty< 2, "vmaxub", int_ppc_altivec_vmaxub, v16i8>;
|
|
def VMAXUH : VX1_Int_Ty< 66, "vmaxuh", int_ppc_altivec_vmaxuh, v8i16>;
|
|
def VMAXUW : VX1_Int_Ty< 130, "vmaxuw", int_ppc_altivec_vmaxuw, v4i32>;
|
|
def VMINFP : VX1_Int_Ty<1098, "vminfp", int_ppc_altivec_vminfp, v4f32>;
|
|
def VMINSB : VX1_Int_Ty< 770, "vminsb", int_ppc_altivec_vminsb, v16i8>;
|
|
def VMINSH : VX1_Int_Ty< 834, "vminsh", int_ppc_altivec_vminsh, v8i16>;
|
|
def VMINSW : VX1_Int_Ty< 898, "vminsw", int_ppc_altivec_vminsw, v4i32>;
|
|
def VMINUB : VX1_Int_Ty< 514, "vminub", int_ppc_altivec_vminub, v16i8>;
|
|
def VMINUH : VX1_Int_Ty< 578, "vminuh", int_ppc_altivec_vminuh, v8i16>;
|
|
def VMINUW : VX1_Int_Ty< 642, "vminuw", int_ppc_altivec_vminuw, v4i32>;
|
|
} // isCommutable
|
|
|
|
def VMRGHB : VXForm_1< 12, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrghb $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrghb_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGHH : VXForm_1< 76, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrghh $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrghh_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGHW : VXForm_1<140, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrghw $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrghw_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGLB : VXForm_1<268, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrglb $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrglb_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGLH : VXForm_1<332, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrglh $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrglh_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGLW : VXForm_1<396, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrglw $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrglw_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
|
|
def VMSUMMBM : VA1a_Int_Ty3<37, "vmsummbm", int_ppc_altivec_vmsummbm,
|
|
v4i32, v16i8, v4i32>;
|
|
def VMSUMSHM : VA1a_Int_Ty3<40, "vmsumshm", int_ppc_altivec_vmsumshm,
|
|
v4i32, v8i16, v4i32>;
|
|
def VMSUMSHS : VA1a_Int_Ty3<41, "vmsumshs", int_ppc_altivec_vmsumshs,
|
|
v4i32, v8i16, v4i32>;
|
|
def VMSUMUBM : VA1a_Int_Ty3<36, "vmsumubm", int_ppc_altivec_vmsumubm,
|
|
v4i32, v16i8, v4i32>;
|
|
def VMSUMUHM : VA1a_Int_Ty3<38, "vmsumuhm", int_ppc_altivec_vmsumuhm,
|
|
v4i32, v8i16, v4i32>;
|
|
def VMSUMUHS : VA1a_Int_Ty3<39, "vmsumuhs", int_ppc_altivec_vmsumuhs,
|
|
v4i32, v8i16, v4i32>;
|
|
|
|
let isCommutable = 1 in {
|
|
def VMULESB : VX1_Int_Ty2<776, "vmulesb", int_ppc_altivec_vmulesb,
|
|
v8i16, v16i8>;
|
|
def VMULESH : VX1_Int_Ty2<840, "vmulesh", int_ppc_altivec_vmulesh,
|
|
v4i32, v8i16>;
|
|
def VMULEUB : VX1_Int_Ty2<520, "vmuleub", int_ppc_altivec_vmuleub,
|
|
v8i16, v16i8>;
|
|
def VMULEUH : VX1_Int_Ty2<584, "vmuleuh", int_ppc_altivec_vmuleuh,
|
|
v4i32, v8i16>;
|
|
def VMULOSB : VX1_Int_Ty2<264, "vmulosb", int_ppc_altivec_vmulosb,
|
|
v8i16, v16i8>;
|
|
def VMULOSH : VX1_Int_Ty2<328, "vmulosh", int_ppc_altivec_vmulosh,
|
|
v4i32, v8i16>;
|
|
def VMULOUB : VX1_Int_Ty2< 8, "vmuloub", int_ppc_altivec_vmuloub,
|
|
v8i16, v16i8>;
|
|
def VMULOUH : VX1_Int_Ty2< 72, "vmulouh", int_ppc_altivec_vmulouh,
|
|
v4i32, v8i16>;
|
|
} // isCommutable
|
|
|
|
def VREFP : VX2_Int_SP<266, "vrefp", int_ppc_altivec_vrefp>;
|
|
def VRFIM : VX2_Int_SP<714, "vrfim", int_ppc_altivec_vrfim>;
|
|
def VRFIN : VX2_Int_SP<522, "vrfin", int_ppc_altivec_vrfin>;
|
|
def VRFIP : VX2_Int_SP<650, "vrfip", int_ppc_altivec_vrfip>;
|
|
def VRFIZ : VX2_Int_SP<586, "vrfiz", int_ppc_altivec_vrfiz>;
|
|
def VRSQRTEFP : VX2_Int_SP<330, "vrsqrtefp", int_ppc_altivec_vrsqrtefp>;
|
|
|
|
def VSUBCUW : VX1_Int_Ty<1408, "vsubcuw", int_ppc_altivec_vsubcuw, v4i32>;
|
|
|
|
def VSUBFP : VXForm_1<74, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsubfp $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4f32:$vD, (fsub v4f32:$vA, v4f32:$vB))]>;
|
|
def VSUBUBM : VXForm_1<1024, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsububm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (sub v16i8:$vA, v16i8:$vB))]>;
|
|
def VSUBUHM : VXForm_1<1088, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsubuhm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (sub v8i16:$vA, v8i16:$vB))]>;
|
|
def VSUBUWM : VXForm_1<1152, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsubuwm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (sub v4i32:$vA, v4i32:$vB))]>;
|
|
|
|
def VSUBSBS : VX1_Int_Ty<1792, "vsubsbs" , int_ppc_altivec_vsubsbs, v16i8>;
|
|
def VSUBSHS : VX1_Int_Ty<1856, "vsubshs" , int_ppc_altivec_vsubshs, v8i16>;
|
|
def VSUBSWS : VX1_Int_Ty<1920, "vsubsws" , int_ppc_altivec_vsubsws, v4i32>;
|
|
def VSUBUBS : VX1_Int_Ty<1536, "vsububs" , int_ppc_altivec_vsububs, v16i8>;
|
|
def VSUBUHS : VX1_Int_Ty<1600, "vsubuhs" , int_ppc_altivec_vsubuhs, v8i16>;
|
|
def VSUBUWS : VX1_Int_Ty<1664, "vsubuws" , int_ppc_altivec_vsubuws, v4i32>;
|
|
|
|
def VSUMSWS : VX1_Int_Ty<1928, "vsumsws" , int_ppc_altivec_vsumsws, v4i32>;
|
|
def VSUM2SWS: VX1_Int_Ty<1672, "vsum2sws", int_ppc_altivec_vsum2sws, v4i32>;
|
|
|
|
def VSUM4SBS: VX1_Int_Ty3<1800, "vsum4sbs", int_ppc_altivec_vsum4sbs,
|
|
v4i32, v16i8, v4i32>;
|
|
def VSUM4SHS: VX1_Int_Ty3<1608, "vsum4shs", int_ppc_altivec_vsum4shs,
|
|
v4i32, v8i16, v4i32>;
|
|
def VSUM4UBS: VX1_Int_Ty3<1544, "vsum4ubs", int_ppc_altivec_vsum4ubs,
|
|
v4i32, v16i8, v4i32>;
|
|
|
|
def VNOR : VXForm_1<1284, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vnor $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD, (vnot_ppc (or v4i32:$vA,
|
|
v4i32:$vB)))]>;
|
|
let isCommutable = 1 in {
|
|
def VOR : VXForm_1<1156, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vor $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD, (or v4i32:$vA, v4i32:$vB))]>;
|
|
def VXOR : VXForm_1<1220, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vxor $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD, (xor v4i32:$vA, v4i32:$vB))]>;
|
|
} // isCommutable
|
|
|
|
def VRLB : VX1_Int_Ty< 4, "vrlb", int_ppc_altivec_vrlb, v16i8>;
|
|
def VRLH : VX1_Int_Ty< 68, "vrlh", int_ppc_altivec_vrlh, v8i16>;
|
|
def VRLW : VX1_Int_Ty< 132, "vrlw", int_ppc_altivec_vrlw, v4i32>;
|
|
|
|
def VSL : VX1_Int_Ty< 452, "vsl" , int_ppc_altivec_vsl, v4i32 >;
|
|
def VSLO : VX1_Int_Ty<1036, "vslo", int_ppc_altivec_vslo, v4i32>;
|
|
|
|
def VSLB : VX1_Int_Ty< 260, "vslb", int_ppc_altivec_vslb, v16i8>;
|
|
def VSLH : VX1_Int_Ty< 324, "vslh", int_ppc_altivec_vslh, v8i16>;
|
|
def VSLW : VX1_Int_Ty< 388, "vslw", int_ppc_altivec_vslw, v4i32>;
|
|
|
|
def VSPLTB : VXForm_1<524, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vspltb $vD, $vB, $UIMM", IIC_VecPerm,
|
|
[(set v16i8:$vD,
|
|
(vspltb_shuffle:$UIMM v16i8:$vB, (undef)))]>;
|
|
def VSPLTH : VXForm_1<588, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vsplth $vD, $vB, $UIMM", IIC_VecPerm,
|
|
[(set v16i8:$vD,
|
|
(vsplth_shuffle:$UIMM v16i8:$vB, (undef)))]>;
|
|
def VSPLTW : VXForm_1<652, (outs vrrc:$vD), (ins u5imm:$UIMM, vrrc:$vB),
|
|
"vspltw $vD, $vB, $UIMM", IIC_VecPerm,
|
|
[(set v16i8:$vD,
|
|
(vspltw_shuffle:$UIMM v16i8:$vB, (undef)))]>;
|
|
let isCodeGenOnly = 1 in {
|
|
def VSPLTBs : VXForm_1<524, (outs vrrc:$vD), (ins u5imm:$UIMM, vfrc:$vB),
|
|
"vspltb $vD, $vB, $UIMM", IIC_VecPerm, []>;
|
|
def VSPLTHs : VXForm_1<588, (outs vrrc:$vD), (ins u5imm:$UIMM, vfrc:$vB),
|
|
"vsplth $vD, $vB, $UIMM", IIC_VecPerm, []>;
|
|
}
|
|
|
|
def VSR : VX1_Int_Ty< 708, "vsr" , int_ppc_altivec_vsr, v4i32>;
|
|
def VSRO : VX1_Int_Ty<1100, "vsro" , int_ppc_altivec_vsro, v4i32>;
|
|
|
|
def VSRAB : VX1_Int_Ty< 772, "vsrab", int_ppc_altivec_vsrab, v16i8>;
|
|
def VSRAH : VX1_Int_Ty< 836, "vsrah", int_ppc_altivec_vsrah, v8i16>;
|
|
def VSRAW : VX1_Int_Ty< 900, "vsraw", int_ppc_altivec_vsraw, v4i32>;
|
|
def VSRB : VX1_Int_Ty< 516, "vsrb" , int_ppc_altivec_vsrb , v16i8>;
|
|
def VSRH : VX1_Int_Ty< 580, "vsrh" , int_ppc_altivec_vsrh , v8i16>;
|
|
def VSRW : VX1_Int_Ty< 644, "vsrw" , int_ppc_altivec_vsrw , v4i32>;
|
|
|
|
|
|
def VSPLTISB : VXForm_3<780, (outs vrrc:$vD), (ins s5imm:$SIMM),
|
|
"vspltisb $vD, $SIMM", IIC_VecPerm,
|
|
[(set v16i8:$vD, (v16i8 vecspltisb:$SIMM))]>;
|
|
def VSPLTISH : VXForm_3<844, (outs vrrc:$vD), (ins s5imm:$SIMM),
|
|
"vspltish $vD, $SIMM", IIC_VecPerm,
|
|
[(set v8i16:$vD, (v8i16 vecspltish:$SIMM))]>;
|
|
def VSPLTISW : VXForm_3<908, (outs vrrc:$vD), (ins s5imm:$SIMM),
|
|
"vspltisw $vD, $SIMM", IIC_VecPerm,
|
|
[(set v4i32:$vD, (v4i32 vecspltisw:$SIMM))]>;
|
|
|
|
// Vector Pack.
|
|
def VPKPX : VX1_Int_Ty2<782, "vpkpx", int_ppc_altivec_vpkpx,
|
|
v8i16, v4i32>;
|
|
def VPKSHSS : VX1_Int_Ty2<398, "vpkshss", int_ppc_altivec_vpkshss,
|
|
v16i8, v8i16>;
|
|
def VPKSHUS : VX1_Int_Ty2<270, "vpkshus", int_ppc_altivec_vpkshus,
|
|
v16i8, v8i16>;
|
|
def VPKSWSS : VX1_Int_Ty2<462, "vpkswss", int_ppc_altivec_vpkswss,
|
|
v8i16, v4i32>;
|
|
def VPKSWUS : VX1_Int_Ty2<334, "vpkswus", int_ppc_altivec_vpkswus,
|
|
v8i16, v4i32>;
|
|
def VPKUHUM : VXForm_1<14, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vpkuhum $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD,
|
|
(vpkuhum_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VPKUHUS : VX1_Int_Ty2<142, "vpkuhus", int_ppc_altivec_vpkuhus,
|
|
v16i8, v8i16>;
|
|
def VPKUWUM : VXForm_1<78, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vpkuwum $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD,
|
|
(vpkuwum_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VPKUWUS : VX1_Int_Ty2<206, "vpkuwus", int_ppc_altivec_vpkuwus,
|
|
v8i16, v4i32>;
|
|
|
|
// Vector Unpack.
|
|
def VUPKHPX : VX2_Int_Ty2<846, "vupkhpx", int_ppc_altivec_vupkhpx,
|
|
v4i32, v8i16>;
|
|
def VUPKHSB : VX2_Int_Ty2<526, "vupkhsb", int_ppc_altivec_vupkhsb,
|
|
v8i16, v16i8>;
|
|
def VUPKHSH : VX2_Int_Ty2<590, "vupkhsh", int_ppc_altivec_vupkhsh,
|
|
v4i32, v8i16>;
|
|
def VUPKLPX : VX2_Int_Ty2<974, "vupklpx", int_ppc_altivec_vupklpx,
|
|
v4i32, v8i16>;
|
|
def VUPKLSB : VX2_Int_Ty2<654, "vupklsb", int_ppc_altivec_vupklsb,
|
|
v8i16, v16i8>;
|
|
def VUPKLSH : VX2_Int_Ty2<718, "vupklsh", int_ppc_altivec_vupklsh,
|
|
v4i32, v8i16>;
|
|
|
|
|
|
// Altivec Comparisons.
|
|
|
|
class VCMP<bits<10> xo, string asmstr, ValueType Ty>
|
|
: VXRForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB), asmstr,
|
|
IIC_VecFPCompare,
|
|
[(set Ty:$vD, (Ty (PPCvcmp Ty:$vA, Ty:$vB, xo)))]>;
|
|
class VCMPo<bits<10> xo, string asmstr, ValueType Ty>
|
|
: VXRForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB), asmstr,
|
|
IIC_VecFPCompare,
|
|
[(set Ty:$vD, (Ty (PPCvcmp_o Ty:$vA, Ty:$vB, xo)))]> {
|
|
let Defs = [CR6];
|
|
let RC = 1;
|
|
}
|
|
|
|
// f32 element comparisons.0
|
|
def VCMPBFP : VCMP <966, "vcmpbfp $vD, $vA, $vB" , v4f32>;
|
|
def VCMPBFPo : VCMPo<966, "vcmpbfp. $vD, $vA, $vB" , v4f32>;
|
|
def VCMPEQFP : VCMP <198, "vcmpeqfp $vD, $vA, $vB" , v4f32>;
|
|
def VCMPEQFPo : VCMPo<198, "vcmpeqfp. $vD, $vA, $vB", v4f32>;
|
|
def VCMPGEFP : VCMP <454, "vcmpgefp $vD, $vA, $vB" , v4f32>;
|
|
def VCMPGEFPo : VCMPo<454, "vcmpgefp. $vD, $vA, $vB", v4f32>;
|
|
def VCMPGTFP : VCMP <710, "vcmpgtfp $vD, $vA, $vB" , v4f32>;
|
|
def VCMPGTFPo : VCMPo<710, "vcmpgtfp. $vD, $vA, $vB", v4f32>;
|
|
|
|
// i8 element comparisons.
|
|
def VCMPEQUB : VCMP < 6, "vcmpequb $vD, $vA, $vB" , v16i8>;
|
|
def VCMPEQUBo : VCMPo< 6, "vcmpequb. $vD, $vA, $vB", v16i8>;
|
|
def VCMPGTSB : VCMP <774, "vcmpgtsb $vD, $vA, $vB" , v16i8>;
|
|
def VCMPGTSBo : VCMPo<774, "vcmpgtsb. $vD, $vA, $vB", v16i8>;
|
|
def VCMPGTUB : VCMP <518, "vcmpgtub $vD, $vA, $vB" , v16i8>;
|
|
def VCMPGTUBo : VCMPo<518, "vcmpgtub. $vD, $vA, $vB", v16i8>;
|
|
|
|
// i16 element comparisons.
|
|
def VCMPEQUH : VCMP < 70, "vcmpequh $vD, $vA, $vB" , v8i16>;
|
|
def VCMPEQUHo : VCMPo< 70, "vcmpequh. $vD, $vA, $vB", v8i16>;
|
|
def VCMPGTSH : VCMP <838, "vcmpgtsh $vD, $vA, $vB" , v8i16>;
|
|
def VCMPGTSHo : VCMPo<838, "vcmpgtsh. $vD, $vA, $vB", v8i16>;
|
|
def VCMPGTUH : VCMP <582, "vcmpgtuh $vD, $vA, $vB" , v8i16>;
|
|
def VCMPGTUHo : VCMPo<582, "vcmpgtuh. $vD, $vA, $vB", v8i16>;
|
|
|
|
// i32 element comparisons.
|
|
def VCMPEQUW : VCMP <134, "vcmpequw $vD, $vA, $vB" , v4i32>;
|
|
def VCMPEQUWo : VCMPo<134, "vcmpequw. $vD, $vA, $vB", v4i32>;
|
|
def VCMPGTSW : VCMP <902, "vcmpgtsw $vD, $vA, $vB" , v4i32>;
|
|
def VCMPGTSWo : VCMPo<902, "vcmpgtsw. $vD, $vA, $vB", v4i32>;
|
|
def VCMPGTUW : VCMP <646, "vcmpgtuw $vD, $vA, $vB" , v4i32>;
|
|
def VCMPGTUWo : VCMPo<646, "vcmpgtuw. $vD, $vA, $vB", v4i32>;
|
|
|
|
let isCodeGenOnly = 1 in {
|
|
def V_SET0B : VXForm_setzero<1220, (outs vrrc:$vD), (ins),
|
|
"vxor $vD, $vD, $vD", IIC_VecFP,
|
|
[(set v16i8:$vD, (v16i8 immAllZerosV))]>;
|
|
def V_SET0H : VXForm_setzero<1220, (outs vrrc:$vD), (ins),
|
|
"vxor $vD, $vD, $vD", IIC_VecFP,
|
|
[(set v8i16:$vD, (v8i16 immAllZerosV))]>;
|
|
def V_SET0 : VXForm_setzero<1220, (outs vrrc:$vD), (ins),
|
|
"vxor $vD, $vD, $vD", IIC_VecFP,
|
|
[(set v4i32:$vD, (v4i32 immAllZerosV))]>;
|
|
|
|
let IMM=-1 in {
|
|
def V_SETALLONESB : VXForm_3<908, (outs vrrc:$vD), (ins),
|
|
"vspltisw $vD, -1", IIC_VecFP,
|
|
[(set v16i8:$vD, (v16i8 immAllOnesV))]>;
|
|
def V_SETALLONESH : VXForm_3<908, (outs vrrc:$vD), (ins),
|
|
"vspltisw $vD, -1", IIC_VecFP,
|
|
[(set v8i16:$vD, (v8i16 immAllOnesV))]>;
|
|
def V_SETALLONES : VXForm_3<908, (outs vrrc:$vD), (ins),
|
|
"vspltisw $vD, -1", IIC_VecFP,
|
|
[(set v4i32:$vD, (v4i32 immAllOnesV))]>;
|
|
}
|
|
}
|
|
} // VALU Operations.
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Additional Altivec Patterns
|
|
//
|
|
|
|
// Extended mnemonics
|
|
def : InstAlias<"vmr $vD, $vA", (VOR vrrc:$vD, vrrc:$vA, vrrc:$vA)>;
|
|
def : InstAlias<"vnot $vD, $vA", (VNOR vrrc:$vD, vrrc:$vA, vrrc:$vA)>;
|
|
|
|
// Loads.
|
|
def : Pat<(v4i32 (load xoaddr:$src)), (LVX xoaddr:$src)>;
|
|
|
|
// Stores.
|
|
def : Pat<(store v4i32:$rS, xoaddr:$dst),
|
|
(STVX $rS, xoaddr:$dst)>;
|
|
|
|
// Bit conversions.
|
|
def : Pat<(v16i8 (bitconvert (v8i16 VRRC:$src))), (v16i8 VRRC:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4i32 VRRC:$src))), (v16i8 VRRC:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4f32 VRRC:$src))), (v16i8 VRRC:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2i64 VRRC:$src))), (v16i8 VRRC:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v1i128 VRRC:$src))), (v16i8 VRRC:$src)>;
|
|
|
|
def : Pat<(v8i16 (bitconvert (v16i8 VRRC:$src))), (v8i16 VRRC:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4i32 VRRC:$src))), (v8i16 VRRC:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4f32 VRRC:$src))), (v8i16 VRRC:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2i64 VRRC:$src))), (v8i16 VRRC:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v1i128 VRRC:$src))), (v8i16 VRRC:$src)>;
|
|
|
|
def : Pat<(v4i32 (bitconvert (v16i8 VRRC:$src))), (v4i32 VRRC:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v8i16 VRRC:$src))), (v4i32 VRRC:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v4f32 VRRC:$src))), (v4i32 VRRC:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2i64 VRRC:$src))), (v4i32 VRRC:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v1i128 VRRC:$src))), (v4i32 VRRC:$src)>;
|
|
|
|
def : Pat<(v4f32 (bitconvert (v16i8 VRRC:$src))), (v4f32 VRRC:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v8i16 VRRC:$src))), (v4f32 VRRC:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v4i32 VRRC:$src))), (v4f32 VRRC:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2i64 VRRC:$src))), (v4f32 VRRC:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v1i128 VRRC:$src))), (v4f32 VRRC:$src)>;
|
|
|
|
def : Pat<(v2i64 (bitconvert (v16i8 VRRC:$src))), (v2i64 VRRC:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v8i16 VRRC:$src))), (v2i64 VRRC:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v4i32 VRRC:$src))), (v2i64 VRRC:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v4f32 VRRC:$src))), (v2i64 VRRC:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v1i128 VRRC:$src))), (v2i64 VRRC:$src)>;
|
|
|
|
def : Pat<(v1i128 (bitconvert (v16i8 VRRC:$src))), (v1i128 VRRC:$src)>;
|
|
def : Pat<(v1i128 (bitconvert (v8i16 VRRC:$src))), (v1i128 VRRC:$src)>;
|
|
def : Pat<(v1i128 (bitconvert (v4i32 VRRC:$src))), (v1i128 VRRC:$src)>;
|
|
def : Pat<(v1i128 (bitconvert (v4f32 VRRC:$src))), (v1i128 VRRC:$src)>;
|
|
def : Pat<(v1i128 (bitconvert (v2i64 VRRC:$src))), (v1i128 VRRC:$src)>;
|
|
|
|
// Shuffles.
|
|
|
|
// Match vsldoi(x,x), vpkuwum(x,x), vpkuhum(x,x)
|
|
def:Pat<(vsldoi_unary_shuffle:$in v16i8:$vA, undef),
|
|
(VSLDOI $vA, $vA, (VSLDOI_unary_get_imm $in))>;
|
|
def:Pat<(vpkuwum_unary_shuffle v16i8:$vA, undef),
|
|
(VPKUWUM $vA, $vA)>;
|
|
def:Pat<(vpkuhum_unary_shuffle v16i8:$vA, undef),
|
|
(VPKUHUM $vA, $vA)>;
|
|
def:Pat<(vsldoi_shuffle:$SH v16i8:$vA, v16i8:$vB),
|
|
(VSLDOI v16i8:$vA, v16i8:$vB, (VSLDOI_get_imm $SH))>;
|
|
|
|
|
|
// Match vsldoi(y,x), vpkuwum(y,x), vpkuhum(y,x), i.e., swapped operands.
|
|
// These fragments are matched for little-endian, where the inputs must
|
|
// be swapped for correct semantics.
|
|
def:Pat<(vsldoi_swapped_shuffle:$in v16i8:$vA, v16i8:$vB),
|
|
(VSLDOI $vB, $vA, (VSLDOI_swapped_get_imm $in))>;
|
|
def:Pat<(vpkuwum_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VPKUWUM $vB, $vA)>;
|
|
def:Pat<(vpkuhum_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VPKUHUM $vB, $vA)>;
|
|
|
|
// Match vmrg*(x,x)
|
|
def:Pat<(vmrglb_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGLB $vA, $vA)>;
|
|
def:Pat<(vmrglh_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGLH $vA, $vA)>;
|
|
def:Pat<(vmrglw_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGLW $vA, $vA)>;
|
|
def:Pat<(vmrghb_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGHB $vA, $vA)>;
|
|
def:Pat<(vmrghh_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGHH $vA, $vA)>;
|
|
def:Pat<(vmrghw_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGHW $vA, $vA)>;
|
|
|
|
// Match vmrg*(y,x), i.e., swapped operands. These fragments
|
|
// are matched for little-endian, where the inputs must be
|
|
// swapped for correct semantics.
|
|
def:Pat<(vmrglb_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGLB $vB, $vA)>;
|
|
def:Pat<(vmrglh_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGLH $vB, $vA)>;
|
|
def:Pat<(vmrglw_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGLW $vB, $vA)>;
|
|
def:Pat<(vmrghb_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGHB $vB, $vA)>;
|
|
def:Pat<(vmrghh_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGHH $vB, $vA)>;
|
|
def:Pat<(vmrghw_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGHW $vB, $vA)>;
|
|
|
|
// Logical Operations
|
|
def : Pat<(vnot_ppc v4i32:$vA), (VNOR $vA, $vA)>;
|
|
|
|
def : Pat<(vnot_ppc (or v4i32:$A, v4i32:$B)),
|
|
(VNOR $A, $B)>;
|
|
def : Pat<(and v4i32:$A, (vnot_ppc v4i32:$B)),
|
|
(VANDC $A, $B)>;
|
|
|
|
def : Pat<(fmul v4f32:$vA, v4f32:$vB),
|
|
(VMADDFP $vA, $vB,
|
|
(v4i32 (VSLW (V_SETALLONES), (V_SETALLONES))))>;
|
|
|
|
// Fused multiply add and multiply sub for packed float. These are represented
|
|
// separately from the real instructions above, for operations that must have
|
|
// the additional precision, such as Newton-Rhapson (used by divide, sqrt)
|
|
def : Pat<(PPCvmaddfp v4f32:$A, v4f32:$B, v4f32:$C),
|
|
(VMADDFP $A, $B, $C)>;
|
|
def : Pat<(PPCvnmsubfp v4f32:$A, v4f32:$B, v4f32:$C),
|
|
(VNMSUBFP $A, $B, $C)>;
|
|
|
|
def : Pat<(int_ppc_altivec_vmaddfp v4f32:$A, v4f32:$B, v4f32:$C),
|
|
(VMADDFP $A, $B, $C)>;
|
|
def : Pat<(int_ppc_altivec_vnmsubfp v4f32:$A, v4f32:$B, v4f32:$C),
|
|
(VNMSUBFP $A, $B, $C)>;
|
|
|
|
def : Pat<(PPCvperm v16i8:$vA, v16i8:$vB, v16i8:$vC),
|
|
(VPERM $vA, $vB, $vC)>;
|
|
|
|
def : Pat<(PPCfre v4f32:$A), (VREFP $A)>;
|
|
def : Pat<(PPCfrsqrte v4f32:$A), (VRSQRTEFP $A)>;
|
|
|
|
// Vector shifts
|
|
def : Pat<(v16i8 (shl v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSLB $vA, $vB))>;
|
|
def : Pat<(v8i16 (shl v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSLH $vA, $vB))>;
|
|
def : Pat<(v4i32 (shl v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSLW $vA, $vB))>;
|
|
def : Pat<(v1i128 (shl v1i128:$vA, v1i128:$vB)),
|
|
(v1i128 (VSL (VSLO $vA, $vB), (VSPLTB 15, $vB)))>;
|
|
def : Pat<(v16i8 (PPCshl v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSLB $vA, $vB))>;
|
|
def : Pat<(v8i16 (PPCshl v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSLH $vA, $vB))>;
|
|
def : Pat<(v4i32 (PPCshl v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSLW $vA, $vB))>;
|
|
def : Pat<(v1i128 (PPCshl v1i128:$vA, v1i128:$vB)),
|
|
(v1i128 (VSL (VSLO $vA, $vB), (VSPLTB 15, $vB)))>;
|
|
|
|
def : Pat<(v16i8 (srl v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSRB $vA, $vB))>;
|
|
def : Pat<(v8i16 (srl v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSRH $vA, $vB))>;
|
|
def : Pat<(v4i32 (srl v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSRW $vA, $vB))>;
|
|
def : Pat<(v1i128 (srl v1i128:$vA, v1i128:$vB)),
|
|
(v1i128 (VSR (VSRO $vA, $vB), (VSPLTB 15, $vB)))>;
|
|
def : Pat<(v16i8 (PPCsrl v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSRB $vA, $vB))>;
|
|
def : Pat<(v8i16 (PPCsrl v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSRH $vA, $vB))>;
|
|
def : Pat<(v4i32 (PPCsrl v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSRW $vA, $vB))>;
|
|
def : Pat<(v1i128 (PPCsrl v1i128:$vA, v1i128:$vB)),
|
|
(v1i128 (VSR (VSRO $vA, $vB), (VSPLTB 15, $vB)))>;
|
|
|
|
def : Pat<(v16i8 (sra v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSRAB $vA, $vB))>;
|
|
def : Pat<(v8i16 (sra v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSRAH $vA, $vB))>;
|
|
def : Pat<(v4i32 (sra v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSRAW $vA, $vB))>;
|
|
def : Pat<(v16i8 (PPCsra v16i8:$vA, v16i8:$vB)),
|
|
(v16i8 (VSRAB $vA, $vB))>;
|
|
def : Pat<(v8i16 (PPCsra v8i16:$vA, v8i16:$vB)),
|
|
(v8i16 (VSRAH $vA, $vB))>;
|
|
def : Pat<(v4i32 (PPCsra v4i32:$vA, v4i32:$vB)),
|
|
(v4i32 (VSRAW $vA, $vB))>;
|
|
|
|
// Float to integer and integer to float conversions
|
|
def : Pat<(v4i32 (fp_to_sint v4f32:$vA)),
|
|
(VCTSXS_0 $vA)>;
|
|
def : Pat<(v4i32 (fp_to_uint v4f32:$vA)),
|
|
(VCTUXS_0 $vA)>;
|
|
def : Pat<(v4f32 (sint_to_fp v4i32:$vA)),
|
|
(VCFSX_0 $vA)>;
|
|
def : Pat<(v4f32 (uint_to_fp v4i32:$vA)),
|
|
(VCFUX_0 $vA)>;
|
|
|
|
// Floating-point rounding
|
|
def : Pat<(v4f32 (ffloor v4f32:$vA)),
|
|
(VRFIM $vA)>;
|
|
def : Pat<(v4f32 (fceil v4f32:$vA)),
|
|
(VRFIP $vA)>;
|
|
def : Pat<(v4f32 (ftrunc v4f32:$vA)),
|
|
(VRFIZ $vA)>;
|
|
def : Pat<(v4f32 (fnearbyint v4f32:$vA)),
|
|
(VRFIN $vA)>;
|
|
|
|
} // end HasAltivec
|
|
|
|
def HasP8Altivec : Predicate<"PPCSubTarget->hasP8Altivec()">;
|
|
def HasP8Crypto : Predicate<"PPCSubTarget->hasP8Crypto()">;
|
|
let Predicates = [HasP8Altivec] in {
|
|
|
|
let isCommutable = 1 in {
|
|
def VMULESW : VX1_Int_Ty2<904, "vmulesw", int_ppc_altivec_vmulesw,
|
|
v2i64, v4i32>;
|
|
def VMULEUW : VX1_Int_Ty2<648, "vmuleuw", int_ppc_altivec_vmuleuw,
|
|
v2i64, v4i32>;
|
|
def VMULOSW : VX1_Int_Ty2<392, "vmulosw", int_ppc_altivec_vmulosw,
|
|
v2i64, v4i32>;
|
|
def VMULOUW : VX1_Int_Ty2<136, "vmulouw", int_ppc_altivec_vmulouw,
|
|
v2i64, v4i32>;
|
|
def VMULUWM : VXForm_1<137, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmuluwm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (mul v4i32:$vA, v4i32:$vB))]>;
|
|
def VMAXSD : VX1_Int_Ty<450, "vmaxsd", int_ppc_altivec_vmaxsd, v2i64>;
|
|
def VMAXUD : VX1_Int_Ty<194, "vmaxud", int_ppc_altivec_vmaxud, v2i64>;
|
|
def VMINSD : VX1_Int_Ty<962, "vminsd", int_ppc_altivec_vminsd, v2i64>;
|
|
def VMINUD : VX1_Int_Ty<706, "vminud", int_ppc_altivec_vminud, v2i64>;
|
|
} // isCommutable
|
|
|
|
// Vector merge
|
|
def VMRGEW : VXForm_1<1932, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrgew $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrgew_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VMRGOW : VXForm_1<1676, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vmrgow $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD, (vmrgow_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
|
|
// Match vmrgew(x,x) and vmrgow(x,x)
|
|
def:Pat<(vmrgew_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGEW $vA, $vA)>;
|
|
def:Pat<(vmrgow_unary_shuffle v16i8:$vA, undef),
|
|
(VMRGOW $vA, $vA)>;
|
|
|
|
// Match vmrgew(y,x) and vmrgow(y,x), i.e., swapped operands. These fragments
|
|
// are matched for little-endian, where the inputs must be swapped for correct
|
|
// semantics.w
|
|
def:Pat<(vmrgew_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGEW $vB, $vA)>;
|
|
def:Pat<(vmrgow_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VMRGOW $vB, $vA)>;
|
|
|
|
|
|
// Vector shifts
|
|
def VRLD : VX1_Int_Ty<196, "vrld", int_ppc_altivec_vrld, v2i64>;
|
|
def VSLD : VXForm_1<1476, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsld $vD, $vA, $vB", IIC_VecGeneral, []>;
|
|
def VSRD : VXForm_1<1732, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsrd $vD, $vA, $vB", IIC_VecGeneral, []>;
|
|
def VSRAD : VXForm_1<964, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsrad $vD, $vA, $vB", IIC_VecGeneral, []>;
|
|
|
|
def : Pat<(v2i64 (shl v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSLD $vA, $vB))>;
|
|
def : Pat<(v2i64 (PPCshl v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSLD $vA, $vB))>;
|
|
def : Pat<(v2i64 (srl v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSRD $vA, $vB))>;
|
|
def : Pat<(v2i64 (PPCsrl v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSRD $vA, $vB))>;
|
|
def : Pat<(v2i64 (sra v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSRAD $vA, $vB))>;
|
|
def : Pat<(v2i64 (PPCsra v2i64:$vA, v2i64:$vB)),
|
|
(v2i64 (VSRAD $vA, $vB))>;
|
|
|
|
// Vector Integer Arithmetic Instructions
|
|
let isCommutable = 1 in {
|
|
def VADDUDM : VXForm_1<192, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vaddudm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v2i64:$vD, (add v2i64:$vA, v2i64:$vB))]>;
|
|
def VADDUQM : VXForm_1<256, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vadduqm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v1i128:$vD, (add v1i128:$vA, v1i128:$vB))]>;
|
|
} // isCommutable
|
|
|
|
// Vector Quadword Add
|
|
def VADDEUQM : VA1a_Int_Ty<60, "vaddeuqm", int_ppc_altivec_vaddeuqm, v1i128>;
|
|
def VADDCUQ : VX1_Int_Ty<320, "vaddcuq", int_ppc_altivec_vaddcuq, v1i128>;
|
|
def VADDECUQ : VA1a_Int_Ty<61, "vaddecuq", int_ppc_altivec_vaddecuq, v1i128>;
|
|
|
|
// Vector Doubleword Subtract
|
|
def VSUBUDM : VXForm_1<1216, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsubudm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v2i64:$vD, (sub v2i64:$vA, v2i64:$vB))]>;
|
|
|
|
// Vector Quadword Subtract
|
|
def VSUBUQM : VXForm_1<1280, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vsubuqm $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v1i128:$vD, (sub v1i128:$vA, v1i128:$vB))]>;
|
|
def VSUBEUQM : VA1a_Int_Ty<62, "vsubeuqm", int_ppc_altivec_vsubeuqm, v1i128>;
|
|
def VSUBCUQ : VX1_Int_Ty<1344, "vsubcuq", int_ppc_altivec_vsubcuq, v1i128>;
|
|
def VSUBECUQ : VA1a_Int_Ty<63, "vsubecuq", int_ppc_altivec_vsubecuq, v1i128>;
|
|
|
|
// Count Leading Zeros
|
|
def VCLZB : VXForm_2<1794, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vclzb $vD, $vB", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (ctlz v16i8:$vB))]>;
|
|
def VCLZH : VXForm_2<1858, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vclzh $vD, $vB", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (ctlz v8i16:$vB))]>;
|
|
def VCLZW : VXForm_2<1922, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vclzw $vD, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (ctlz v4i32:$vB))]>;
|
|
def VCLZD : VXForm_2<1986, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vclzd $vD, $vB", IIC_VecGeneral,
|
|
[(set v2i64:$vD, (ctlz v2i64:$vB))]>;
|
|
|
|
// Population Count
|
|
def VPOPCNTB : VXForm_2<1795, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vpopcntb $vD, $vB", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (ctpop v16i8:$vB))]>;
|
|
def VPOPCNTH : VXForm_2<1859, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vpopcnth $vD, $vB", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (ctpop v8i16:$vB))]>;
|
|
def VPOPCNTW : VXForm_2<1923, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vpopcntw $vD, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (ctpop v4i32:$vB))]>;
|
|
def VPOPCNTD : VXForm_2<1987, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
"vpopcntd $vD, $vB", IIC_VecGeneral,
|
|
[(set v2i64:$vD, (ctpop v2i64:$vB))]>;
|
|
|
|
let isCommutable = 1 in {
|
|
// FIXME: Use AddedComplexity > 400 to ensure these patterns match before the
|
|
// VSX equivalents. We need to fix this up at some point. Two possible
|
|
// solutions for this problem:
|
|
// 1. Disable Altivec patterns that compete with VSX patterns using the
|
|
// !HasVSX predicate. This essentially favours VSX over Altivec, in
|
|
// hopes of reducing register pressure (larger register set using VSX
|
|
// instructions than VMX instructions)
|
|
// 2. Employ a more disciplined use of AddedComplexity, which would provide
|
|
// more fine-grained control than option 1. This would be beneficial
|
|
// if we find situations where Altivec is really preferred over VSX.
|
|
def VEQV : VXForm_1<1668, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"veqv $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (vnot_ppc (xor v4i32:$vA, v4i32:$vB)))]>;
|
|
def VNAND : VXForm_1<1412, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vnand $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (vnot_ppc (and v4i32:$vA, v4i32:$vB)))]>;
|
|
} // isCommutable
|
|
|
|
def VORC : VXForm_1<1348, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vorc $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (or v4i32:$vA,
|
|
(vnot_ppc v4i32:$vB)))]>;
|
|
|
|
// i64 element comparisons.
|
|
def VCMPEQUD : VCMP <199, "vcmpequd $vD, $vA, $vB" , v2i64>;
|
|
def VCMPEQUDo : VCMPo<199, "vcmpequd. $vD, $vA, $vB", v2i64>;
|
|
def VCMPGTSD : VCMP <967, "vcmpgtsd $vD, $vA, $vB" , v2i64>;
|
|
def VCMPGTSDo : VCMPo<967, "vcmpgtsd. $vD, $vA, $vB", v2i64>;
|
|
def VCMPGTUD : VCMP <711, "vcmpgtud $vD, $vA, $vB" , v2i64>;
|
|
def VCMPGTUDo : VCMPo<711, "vcmpgtud. $vD, $vA, $vB", v2i64>;
|
|
|
|
// The cryptography instructions that do not require Category:Vector.Crypto
|
|
def VPMSUMB : VX1_Int_Ty<1032, "vpmsumb",
|
|
int_ppc_altivec_crypto_vpmsumb, v16i8>;
|
|
def VPMSUMH : VX1_Int_Ty<1096, "vpmsumh",
|
|
int_ppc_altivec_crypto_vpmsumh, v8i16>;
|
|
def VPMSUMW : VX1_Int_Ty<1160, "vpmsumw",
|
|
int_ppc_altivec_crypto_vpmsumw, v4i32>;
|
|
def VPMSUMD : VX1_Int_Ty<1224, "vpmsumd",
|
|
int_ppc_altivec_crypto_vpmsumd, v2i64>;
|
|
def VPERMXOR : VA1a_Int_Ty<45, "vpermxor",
|
|
int_ppc_altivec_crypto_vpermxor, v16i8>;
|
|
|
|
// Vector doubleword integer pack and unpack.
|
|
def VPKSDSS : VX1_Int_Ty2<1486, "vpksdss", int_ppc_altivec_vpksdss,
|
|
v4i32, v2i64>;
|
|
def VPKSDUS : VX1_Int_Ty2<1358, "vpksdus", int_ppc_altivec_vpksdus,
|
|
v4i32, v2i64>;
|
|
def VPKUDUM : VXForm_1<1102, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vpkudum $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v16i8:$vD,
|
|
(vpkudum_shuffle v16i8:$vA, v16i8:$vB))]>;
|
|
def VPKUDUS : VX1_Int_Ty2<1230, "vpkudus", int_ppc_altivec_vpkudus,
|
|
v4i32, v2i64>;
|
|
def VUPKHSW : VX2_Int_Ty2<1614, "vupkhsw", int_ppc_altivec_vupkhsw,
|
|
v2i64, v4i32>;
|
|
def VUPKLSW : VX2_Int_Ty2<1742, "vupklsw", int_ppc_altivec_vupklsw,
|
|
v2i64, v4i32>;
|
|
|
|
// Shuffle patterns for unary and swapped (LE) vector pack modulo.
|
|
def:Pat<(vpkudum_unary_shuffle v16i8:$vA, undef),
|
|
(VPKUDUM $vA, $vA)>;
|
|
def:Pat<(vpkudum_swapped_shuffle v16i8:$vA, v16i8:$vB),
|
|
(VPKUDUM $vB, $vA)>;
|
|
|
|
def VGBBD : VX2_Int_Ty2<1292, "vgbbd", int_ppc_altivec_vgbbd, v16i8, v16i8>;
|
|
def VBPERMQ : VX1_Int_Ty2<1356, "vbpermq", int_ppc_altivec_vbpermq,
|
|
v2i64, v16i8>;
|
|
} // end HasP8Altivec
|
|
|
|
// Crypto instructions (from builtins)
|
|
let Predicates = [HasP8Crypto] in {
|
|
def VSHASIGMAW : VXCR_Int_Ty<1666, "vshasigmaw",
|
|
int_ppc_altivec_crypto_vshasigmaw, v4i32>;
|
|
def VSHASIGMAD : VXCR_Int_Ty<1730, "vshasigmad",
|
|
int_ppc_altivec_crypto_vshasigmad, v2i64>;
|
|
def VCIPHER : VX1_Int_Ty<1288, "vcipher", int_ppc_altivec_crypto_vcipher,
|
|
v2i64>;
|
|
def VCIPHERLAST : VX1_Int_Ty<1289, "vcipherlast",
|
|
int_ppc_altivec_crypto_vcipherlast, v2i64>;
|
|
def VNCIPHER : VX1_Int_Ty<1352, "vncipher",
|
|
int_ppc_altivec_crypto_vncipher, v2i64>;
|
|
def VNCIPHERLAST : VX1_Int_Ty<1353, "vncipherlast",
|
|
int_ppc_altivec_crypto_vncipherlast, v2i64>;
|
|
def VSBOX : VXBX_Int_Ty<1480, "vsbox", int_ppc_altivec_crypto_vsbox, v2i64>;
|
|
} // HasP8Crypto
|
|
|
|
// The following altivec instructions were introduced in Power ISA 3.0
|
|
def HasP9Altivec : Predicate<"PPCSubTarget->hasP9Altivec()">;
|
|
let Predicates = [HasP9Altivec] in {
|
|
|
|
// i8 element comparisons.
|
|
def VCMPNEB : VCMP < 7, "vcmpneb $vD, $vA, $vB" , v16i8>;
|
|
def VCMPNEBo : VCMPo < 7, "vcmpneb. $vD, $vA, $vB" , v16i8>;
|
|
def VCMPNEZB : VCMP <263, "vcmpnezb $vD, $vA, $vB" , v16i8>;
|
|
def VCMPNEZBo : VCMPo<263, "vcmpnezb. $vD, $vA, $vB", v16i8>;
|
|
|
|
// i16 element comparisons.
|
|
def VCMPNEH : VCMP < 71, "vcmpneh $vD, $vA, $vB" , v8i16>;
|
|
def VCMPNEHo : VCMPo< 71, "vcmpneh. $vD, $vA, $vB" , v8i16>;
|
|
def VCMPNEZH : VCMP <327, "vcmpnezh $vD, $vA, $vB" , v8i16>;
|
|
def VCMPNEZHo : VCMPo<327, "vcmpnezh. $vD, $vA, $vB", v8i16>;
|
|
|
|
// i32 element comparisons.
|
|
def VCMPNEW : VCMP <135, "vcmpnew $vD, $vA, $vB" , v4i32>;
|
|
def VCMPNEWo : VCMPo<135, "vcmpnew. $vD, $vA, $vB" , v4i32>;
|
|
def VCMPNEZW : VCMP <391, "vcmpnezw $vD, $vA, $vB" , v4i32>;
|
|
def VCMPNEZWo : VCMPo<391, "vcmpnezw. $vD, $vA, $vB", v4i32>;
|
|
|
|
// VX-Form: [PO VRT / UIM VRB XO].
|
|
// We use VXForm_1 to implement it, that is, we use "VRA" (5 bit) to represent
|
|
// "/ UIM" (1 + 4 bit)
|
|
class VX1_VT5_UIM5_VB5<bits<11> xo, string opc, list<dag> pattern>
|
|
: VXForm_1<xo, (outs vrrc:$vD), (ins u4imm:$UIMM, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vB, $UIMM"), IIC_VecGeneral, pattern>;
|
|
|
|
class VX1_RT5_RA5_VB5<bits<11> xo, string opc, list<dag> pattern>
|
|
: VXForm_1<xo, (outs g8rc:$rD), (ins g8rc:$rA, vrrc:$vB),
|
|
!strconcat(opc, " $rD, $rA, $vB"), IIC_VecGeneral, pattern>;
|
|
|
|
// Vector Extract Unsigned
|
|
def VEXTRACTUB : VX1_VT5_UIM5_VB5<525, "vextractub", []>;
|
|
def VEXTRACTUH : VX1_VT5_UIM5_VB5<589, "vextractuh", []>;
|
|
def VEXTRACTUW : VX1_VT5_UIM5_VB5<653, "vextractuw", []>;
|
|
def VEXTRACTD : VX1_VT5_UIM5_VB5<717, "vextractd" , []>;
|
|
|
|
// Vector Extract Unsigned Byte/Halfword/Word Left/Right-Indexed
|
|
def VEXTUBLX : VX1_RT5_RA5_VB5<1549, "vextublx", []>;
|
|
def VEXTUBRX : VX1_RT5_RA5_VB5<1805, "vextubrx", []>;
|
|
def VEXTUHLX : VX1_RT5_RA5_VB5<1613, "vextuhlx", []>;
|
|
def VEXTUHRX : VX1_RT5_RA5_VB5<1869, "vextuhrx", []>;
|
|
def VEXTUWLX : VX1_RT5_RA5_VB5<1677, "vextuwlx", []>;
|
|
def VEXTUWRX : VX1_RT5_RA5_VB5<1933, "vextuwrx", []>;
|
|
|
|
// Vector Insert Element Instructions
|
|
def VINSERTB : VXForm_1<781, (outs vrrc:$vD),
|
|
(ins vrrc:$vDi, u4imm:$UIM, vrrc:$vB),
|
|
"vinsertb $vD, $vB, $UIM", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (PPCvecinsert v16i8:$vDi, v16i8:$vB,
|
|
imm32SExt16:$UIM))]>,
|
|
RegConstraint<"$vDi = $vD">, NoEncode<"$vDi">;
|
|
def VINSERTH : VXForm_1<845, (outs vrrc:$vD),
|
|
(ins vrrc:$vDi, u4imm:$UIM, vrrc:$vB),
|
|
"vinserth $vD, $vB, $UIM", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (PPCvecinsert v8i16:$vDi, v8i16:$vB,
|
|
imm32SExt16:$UIM))]>,
|
|
RegConstraint<"$vDi = $vD">, NoEncode<"$vDi">;
|
|
def VINSERTW : VX1_VT5_UIM5_VB5<909, "vinsertw", []>;
|
|
def VINSERTD : VX1_VT5_UIM5_VB5<973, "vinsertd", []>;
|
|
|
|
class VX_VT5_EO5_VB5<bits<11> xo, bits<5> eo, string opc, list<dag> pattern>
|
|
: VXForm_RD5_XO5_RS5<xo, eo, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vB"), IIC_VecGeneral, pattern>;
|
|
class VX_VT5_EO5_VB5s<bits<11> xo, bits<5> eo, string opc, list<dag> pattern>
|
|
: VXForm_RD5_XO5_RS5<xo, eo, (outs vfrc:$vD), (ins vfrc:$vB),
|
|
!strconcat(opc, " $vD, $vB"), IIC_VecGeneral, pattern>;
|
|
|
|
// Vector Count Leading/Trailing Zero LSB. Result is placed into GPR[rD]
|
|
def VCLZLSBB : VXForm_RD5_XO5_RS5<1538, 0, (outs gprc:$rD), (ins vrrc:$vB),
|
|
"vclzlsbb $rD, $vB", IIC_VecGeneral,
|
|
[(set i32:$rD, (int_ppc_altivec_vclzlsbb
|
|
v16i8:$vB))]>;
|
|
def VCTZLSBB : VXForm_RD5_XO5_RS5<1538, 1, (outs gprc:$rD), (ins vrrc:$vB),
|
|
"vctzlsbb $rD, $vB", IIC_VecGeneral,
|
|
[(set i32:$rD, (int_ppc_altivec_vctzlsbb
|
|
v16i8:$vB))]>;
|
|
// Vector Count Trailing Zeros
|
|
def VCTZB : VX_VT5_EO5_VB5<1538, 28, "vctzb",
|
|
[(set v16i8:$vD, (cttz v16i8:$vB))]>;
|
|
def VCTZH : VX_VT5_EO5_VB5<1538, 29, "vctzh",
|
|
[(set v8i16:$vD, (cttz v8i16:$vB))]>;
|
|
def VCTZW : VX_VT5_EO5_VB5<1538, 30, "vctzw",
|
|
[(set v4i32:$vD, (cttz v4i32:$vB))]>;
|
|
def VCTZD : VX_VT5_EO5_VB5<1538, 31, "vctzd",
|
|
[(set v2i64:$vD, (cttz v2i64:$vB))]>;
|
|
|
|
// Vector Extend Sign
|
|
def VEXTSB2W : VX_VT5_EO5_VB5<1538, 16, "vextsb2w", []>;
|
|
def VEXTSH2W : VX_VT5_EO5_VB5<1538, 17, "vextsh2w", []>;
|
|
def VEXTSB2D : VX_VT5_EO5_VB5<1538, 24, "vextsb2d", []>;
|
|
def VEXTSH2D : VX_VT5_EO5_VB5<1538, 25, "vextsh2d", []>;
|
|
def VEXTSW2D : VX_VT5_EO5_VB5<1538, 26, "vextsw2d", []>;
|
|
let isCodeGenOnly = 1 in {
|
|
def VEXTSB2Ws : VX_VT5_EO5_VB5s<1538, 16, "vextsb2w", []>;
|
|
def VEXTSH2Ws : VX_VT5_EO5_VB5s<1538, 17, "vextsh2w", []>;
|
|
def VEXTSB2Ds : VX_VT5_EO5_VB5s<1538, 24, "vextsb2d", []>;
|
|
def VEXTSH2Ds : VX_VT5_EO5_VB5s<1538, 25, "vextsh2d", []>;
|
|
def VEXTSW2Ds : VX_VT5_EO5_VB5s<1538, 26, "vextsw2d", []>;
|
|
}
|
|
|
|
// Vector Integer Negate
|
|
def VNEGW : VX_VT5_EO5_VB5<1538, 6, "vnegw",
|
|
[(set v4i32:$vD,
|
|
(sub (v4i32 immAllZerosV), v4i32:$vB))]>;
|
|
|
|
def VNEGD : VX_VT5_EO5_VB5<1538, 7, "vnegd",
|
|
[(set v2i64:$vD,
|
|
(sub (v2i64 (bitconvert (v4i32 immAllZerosV))),
|
|
v2i64:$vB))]>;
|
|
|
|
// Vector Parity Byte
|
|
def VPRTYBW : VX_VT5_EO5_VB5<1538, 8, "vprtybw", [(set v4i32:$vD,
|
|
(int_ppc_altivec_vprtybw v4i32:$vB))]>;
|
|
def VPRTYBD : VX_VT5_EO5_VB5<1538, 9, "vprtybd", [(set v2i64:$vD,
|
|
(int_ppc_altivec_vprtybd v2i64:$vB))]>;
|
|
def VPRTYBQ : VX_VT5_EO5_VB5<1538, 10, "vprtybq", [(set v1i128:$vD,
|
|
(int_ppc_altivec_vprtybq v1i128:$vB))]>;
|
|
|
|
// Vector (Bit) Permute (Right-indexed)
|
|
def VBPERMD : VXForm_1<1484, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vbpermd $vD, $vA, $vB", IIC_VecFP, []>;
|
|
def VPERMR : VAForm_1a<59, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vC),
|
|
"vpermr $vD, $vA, $vB, $vC", IIC_VecFP, []>;
|
|
|
|
class VX1_VT5_VA5_VB5<bits<11> xo, string opc, list<dag> pattern>
|
|
: VXForm_1<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vA, $vB"), IIC_VecFP, pattern>;
|
|
|
|
// Vector Rotate Left Mask/Mask-Insert
|
|
def VRLWNM : VX1_VT5_VA5_VB5<389, "vrlwnm",
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vrlwnm v4i32:$vA,
|
|
v4i32:$vB))]>;
|
|
def VRLWMI : VXForm_1<133, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vDi),
|
|
"vrlwmi $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v4i32:$vD,
|
|
(int_ppc_altivec_vrlwmi v4i32:$vA, v4i32:$vB,
|
|
v4i32:$vDi))]>,
|
|
RegConstraint<"$vDi = $vD">, NoEncode<"$vDi">;
|
|
def VRLDNM : VX1_VT5_VA5_VB5<453, "vrldnm",
|
|
[(set v2i64:$vD,
|
|
(int_ppc_altivec_vrldnm v2i64:$vA,
|
|
v2i64:$vB))]>;
|
|
def VRLDMI : VXForm_1<197, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, vrrc:$vDi),
|
|
"vrldmi $vD, $vA, $vB", IIC_VecFP,
|
|
[(set v2i64:$vD,
|
|
(int_ppc_altivec_vrldmi v2i64:$vA, v2i64:$vB,
|
|
v2i64:$vDi))]>,
|
|
RegConstraint<"$vDi = $vD">, NoEncode<"$vDi">;
|
|
|
|
// Vector Shift Left/Right
|
|
def VSLV : VX1_VT5_VA5_VB5<1860, "vslv",
|
|
[(set v16i8 : $vD, (int_ppc_altivec_vslv v16i8 : $vA, v16i8 : $vB))]>;
|
|
def VSRV : VX1_VT5_VA5_VB5<1796, "vsrv",
|
|
[(set v16i8 : $vD, (int_ppc_altivec_vsrv v16i8 : $vA, v16i8 : $vB))]>;
|
|
|
|
// Vector Multiply-by-10 (& Write Carry) Unsigned Quadword
|
|
def VMUL10UQ : VXForm_BX<513, (outs vrrc:$vD), (ins vrrc:$vA),
|
|
"vmul10uq $vD, $vA", IIC_VecFP, []>;
|
|
def VMUL10CUQ : VXForm_BX< 1, (outs vrrc:$vD), (ins vrrc:$vA),
|
|
"vmul10cuq $vD, $vA", IIC_VecFP, []>;
|
|
|
|
// Vector Multiply-by-10 Extended (& Write Carry) Unsigned Quadword
|
|
def VMUL10EUQ : VX1_VT5_VA5_VB5<577, "vmul10euq" , []>;
|
|
def VMUL10ECUQ : VX1_VT5_VA5_VB5< 65, "vmul10ecuq", []>;
|
|
|
|
// Decimal Integer Format Conversion Instructions
|
|
|
|
// [PO VRT EO VRB 1 PS XO], "_o" means CR6 is set.
|
|
class VX_VT5_EO5_VB5_PS1_XO9_o<bits<5> eo, bits<9> xo, string opc,
|
|
list<dag> pattern>
|
|
: VX_RD5_EO5_RS5_PS1_XO9<eo, xo, (outs vrrc:$vD), (ins vrrc:$vB, u1imm:$PS),
|
|
!strconcat(opc, " $vD, $vB, $PS"), IIC_VecFP, pattern> {
|
|
let Defs = [CR6];
|
|
}
|
|
|
|
// [PO VRT EO VRB 1 / XO]
|
|
class VX_VT5_EO5_VB5_XO9_o<bits<5> eo, bits<9> xo, string opc,
|
|
list<dag> pattern>
|
|
: VX_RD5_EO5_RS5_PS1_XO9<eo, xo, (outs vrrc:$vD), (ins vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vB"), IIC_VecFP, pattern> {
|
|
let Defs = [CR6];
|
|
let PS = 0;
|
|
}
|
|
|
|
// Decimal Convert From/to National/Zoned/Signed-QWord
|
|
def BCDCFNo : VX_VT5_EO5_VB5_PS1_XO9_o<7, 385, "bcdcfn." , []>;
|
|
def BCDCFZo : VX_VT5_EO5_VB5_PS1_XO9_o<6, 385, "bcdcfz." , []>;
|
|
def BCDCTNo : VX_VT5_EO5_VB5_XO9_o <5, 385, "bcdctn." , []>;
|
|
def BCDCTZo : VX_VT5_EO5_VB5_PS1_XO9_o<4, 385, "bcdctz." , []>;
|
|
def BCDCFSQo : VX_VT5_EO5_VB5_PS1_XO9_o<2, 385, "bcdcfsq.", []>;
|
|
def BCDCTSQo : VX_VT5_EO5_VB5_XO9_o <0, 385, "bcdctsq.", []>;
|
|
|
|
// Decimal Copy-Sign/Set-Sign
|
|
let Defs = [CR6] in
|
|
def BCDCPSGNo : VX1_VT5_VA5_VB5<833, "bcdcpsgn.", []>;
|
|
|
|
def BCDSETSGNo : VX_VT5_EO5_VB5_PS1_XO9_o<31, 385, "bcdsetsgn.", []>;
|
|
|
|
// [PO VRT VRA VRB 1 PS XO], "_o" means CR6 is set.
|
|
class VX_VT5_VA5_VB5_PS1_XO9_o<bits<9> xo, string opc, list<dag> pattern>
|
|
: VX_RD5_RSp5_PS1_XO9<xo,
|
|
(outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB, u1imm:$PS),
|
|
!strconcat(opc, " $vD, $vA, $vB, $PS"), IIC_VecFP, pattern> {
|
|
let Defs = [CR6];
|
|
}
|
|
|
|
// [PO VRT VRA VRB 1 / XO]
|
|
class VX_VT5_VA5_VB5_XO9_o<bits<9> xo, string opc, list<dag> pattern>
|
|
: VX_RD5_RSp5_PS1_XO9<xo, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
!strconcat(opc, " $vD, $vA, $vB"), IIC_VecFP, pattern> {
|
|
let Defs = [CR6];
|
|
let PS = 0;
|
|
}
|
|
|
|
// Decimal Shift/Unsigned-Shift/Shift-and-Round
|
|
def BCDSo : VX_VT5_VA5_VB5_PS1_XO9_o<193, "bcds." , []>;
|
|
def BCDUSo : VX_VT5_VA5_VB5_XO9_o <129, "bcdus.", []>;
|
|
def BCDSRo : VX_VT5_VA5_VB5_PS1_XO9_o<449, "bcdsr.", []>;
|
|
|
|
// Decimal (Unsigned) Truncate
|
|
def BCDTRUNCo : VX_VT5_VA5_VB5_PS1_XO9_o<257, "bcdtrunc." , []>;
|
|
def BCDUTRUNCo : VX_VT5_VA5_VB5_XO9_o <321, "bcdutrunc.", []>;
|
|
|
|
// Absolute Difference
|
|
def VABSDUB : VXForm_1<1027, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vabsdub $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v16i8:$vD, (int_ppc_altivec_vabsdub v16i8:$vA, v16i8:$vB))]>;
|
|
def VABSDUH : VXForm_1<1091, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vabsduh $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v8i16:$vD, (int_ppc_altivec_vabsduh v8i16:$vA, v8i16:$vB))]>;
|
|
def VABSDUW : VXForm_1<1155, (outs vrrc:$vD), (ins vrrc:$vA, vrrc:$vB),
|
|
"vabsduw $vD, $vA, $vB", IIC_VecGeneral,
|
|
[(set v4i32:$vD, (int_ppc_altivec_vabsduw v4i32:$vA, v4i32:$vB))]>;
|
|
|
|
def : Pat<(v16i8:$vD (abs v16i8:$vA)),
|
|
(v16i8 (VABSDUB $vA, (V_SET0B)))>;
|
|
def : Pat<(v8i16:$vD (abs v8i16:$vA)),
|
|
(v8i16 (VABSDUH $vA, (V_SET0H)))>;
|
|
def : Pat<(v4i32:$vD (abs v4i32:$vA)),
|
|
(v4i32 (VABSDUW $vA, (V_SET0)))>;
|
|
|
|
def : Pat<(v16i8:$vD (abs (sub v16i8:$vA, v16i8:$vB))),
|
|
(v16i8 (VABSDUB $vA, $vB))>;
|
|
def : Pat<(v8i16:$vD (abs (sub v8i16:$vA, v8i16:$vB))),
|
|
(v8i16 (VABSDUH $vA, $vB))>;
|
|
def : Pat<(v4i32:$vD (abs (sub v4i32:$vA, v4i32:$vB))),
|
|
(v4i32 (VABSDUW $vA, $vB))>;
|
|
|
|
} // end HasP9Altivec
|