maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/PowerPC/PPCInstrVSX.td

2937 lines
138 KiB
TableGen
Raw Blame History

//===- PPCInstrVSX.td - The PowerPC VSX 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 VSX 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(). **
// ****************************************************************************
def PPCRegVSRCAsmOperand : AsmOperandClass {
let Name = "RegVSRC"; let PredicateMethod = "isVSRegNumber";
}
def vsrc : RegisterOperand<VSRC> {
let ParserMatchClass = PPCRegVSRCAsmOperand;
}
def PPCRegVSFRCAsmOperand : AsmOperandClass {
let Name = "RegVSFRC"; let PredicateMethod = "isVSRegNumber";
}
def vsfrc : RegisterOperand<VSFRC> {
let ParserMatchClass = PPCRegVSFRCAsmOperand;
}
def PPCRegVSSRCAsmOperand : AsmOperandClass {
let Name = "RegVSSRC"; let PredicateMethod = "isVSRegNumber";
}
def vssrc : RegisterOperand<VSSRC> {
let ParserMatchClass = PPCRegVSSRCAsmOperand;
}
// Little-endian-specific nodes.
def SDT_PPClxvd2x : SDTypeProfile<1, 1, [
SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
]>;
def SDT_PPCstxvd2x : SDTypeProfile<0, 2, [
SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
]>;
def SDT_PPCxxswapd : SDTypeProfile<1, 1, [
SDTCisSameAs<0, 1>
]>;
def SDTVecConv : SDTypeProfile<1, 2, [
SDTCisVec<0>, SDTCisVec<1>, SDTCisPtrTy<2>
]>;
def PPClxvd2x : SDNode<"PPCISD::LXVD2X", SDT_PPClxvd2x,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def PPCstxvd2x : SDNode<"PPCISD::STXVD2X", SDT_PPCstxvd2x,
[SDNPHasChain, SDNPMayStore]>;
def PPCxxswapd : SDNode<"PPCISD::XXSWAPD", SDT_PPCxxswapd, [SDNPHasChain]>;
def PPCmfvsr : SDNode<"PPCISD::MFVSR", SDTUnaryOp, []>;
def PPCmtvsra : SDNode<"PPCISD::MTVSRA", SDTUnaryOp, []>;
def PPCmtvsrz : SDNode<"PPCISD::MTVSRZ", SDTUnaryOp, []>;
def PPCsvec2fp : SDNode<"PPCISD::SINT_VEC_TO_FP", SDTVecConv, []>;
def PPCuvec2fp: SDNode<"PPCISD::UINT_VEC_TO_FP", SDTVecConv, []>;
def PPCswapNoChain : SDNode<"PPCISD::SWAP_NO_CHAIN", SDT_PPCxxswapd>;
multiclass XX3Form_Rcr<bits<6> opcode, bits<7> xo, string asmbase,
string asmstr, InstrItinClass itin, Intrinsic Int,
ValueType OutTy, ValueType InTy> {
let BaseName = asmbase in {
def NAME : XX3Form_Rc<opcode, xo, (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
!strconcat(asmbase, !strconcat(" ", asmstr)), itin,
[(set OutTy:$XT, (Int InTy:$XA, InTy:$XB))]>;
let Defs = [CR6] in
def o : XX3Form_Rc<opcode, xo, (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
!strconcat(asmbase, !strconcat(". ", asmstr)), itin,
[(set InTy:$XT,
(InTy (PPCvcmp_o InTy:$XA, InTy:$XB, xo)))]>,
isDOT;
}
}
// Instruction form with a single input register for instructions such as
// XXPERMDI. The reason for defining this is that specifying multiple chained
// operands (such as loads) to an instruction will perform both chained
// operations rather than coalescing them into a single register - even though
// the source memory location is the same. This simply forces the instruction
// to use the same register for both inputs.
// For example, an output DAG such as this:
// (XXPERMDI (LXSIBZX xoaddr:$src), (LXSIBZX xoaddr:$src ), 0))
// would result in two load instructions emitted and used as separate inputs
// to the XXPERMDI instruction.
class XX3Form_2s<bits<6> opcode, bits<5> xo, dag OOL, dag IOL, string asmstr,
InstrItinClass itin, list<dag> pattern>
: XX3Form_2<opcode, xo, OOL, IOL, asmstr, itin, pattern> {
let XB = XA;
}
def HasVSX : Predicate<"PPCSubTarget->hasVSX()">;
def IsLittleEndian : Predicate<"PPCSubTarget->isLittleEndian()">;
def IsBigEndian : Predicate<"!PPCSubTarget->isLittleEndian()">;
def HasOnlySwappingMemOps : Predicate<"!PPCSubTarget->hasP9Vector()">;
let Predicates = [HasVSX] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let UseVSXReg = 1 in {
let hasSideEffects = 0 in { // VSX instructions don't have side effects.
let Uses = [RM] in {
// Load indexed instructions
let mayLoad = 1, mayStore = 0 in {
let CodeSize = 3 in
def LXSDX : XX1Form<31, 588,
(outs vsfrc:$XT), (ins memrr:$src),
"lxsdx $XT, $src", IIC_LdStLFD,
[(set f64:$XT, (load xoaddr:$src))]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in
def LXVD2X : XX1Form<31, 844,
(outs vsrc:$XT), (ins memrr:$src),
"lxvd2x $XT, $src", IIC_LdStLFD,
[(set v2f64:$XT, (int_ppc_vsx_lxvd2x xoaddr:$src))]>;
def LXVDSX : XX1Form<31, 332,
(outs vsrc:$XT), (ins memrr:$src),
"lxvdsx $XT, $src", IIC_LdStLFD, []>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in
def LXVW4X : XX1Form<31, 780,
(outs vsrc:$XT), (ins memrr:$src),
"lxvw4x $XT, $src", IIC_LdStLFD,
[(set v4i32:$XT, (int_ppc_vsx_lxvw4x xoaddr:$src))]>;
} // mayLoad
// Store indexed instructions
let mayStore = 1, mayLoad = 0 in {
let CodeSize = 3 in
def STXSDX : XX1Form<31, 716,
(outs), (ins vsfrc:$XT, memrr:$dst),
"stxsdx $XT, $dst", IIC_LdStSTFD,
[(store f64:$XT, xoaddr:$dst)]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
// The behaviour of this instruction is endianness-specific so we provide no
// pattern to match it without considering endianness.
def STXVD2X : XX1Form<31, 972,
(outs), (ins vsrc:$XT, memrr:$dst),
"stxvd2x $XT, $dst", IIC_LdStSTFD,
[]>;
def STXVW4X : XX1Form<31, 908,
(outs), (ins vsrc:$XT, memrr:$dst),
"stxvw4x $XT, $dst", IIC_LdStSTFD,
[(store v4i32:$XT, xoaddr:$dst)]>;
}
} // mayStore
// Add/Mul Instructions
let isCommutable = 1 in {
def XSADDDP : XX3Form<60, 32,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsadddp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fadd f64:$XA, f64:$XB))]>;
def XSMULDP : XX3Form<60, 48,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmuldp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fmul f64:$XA, f64:$XB))]>;
def XVADDDP : XX3Form<60, 96,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvadddp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fadd v2f64:$XA, v2f64:$XB))]>;
def XVADDSP : XX3Form<60, 64,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvaddsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fadd v4f32:$XA, v4f32:$XB))]>;
def XVMULDP : XX3Form<60, 112,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmuldp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fmul v2f64:$XA, v2f64:$XB))]>;
def XVMULSP : XX3Form<60, 80,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmulsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fmul v4f32:$XA, v4f32:$XB))]>;
}
// Subtract Instructions
def XSSUBDP : XX3Form<60, 40,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xssubdp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fsub f64:$XA, f64:$XB))]>;
def XVSUBDP : XX3Form<60, 104,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvsubdp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fsub v2f64:$XA, v2f64:$XB))]>;
def XVSUBSP : XX3Form<60, 72,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvsubsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fsub v4f32:$XA, v4f32:$XB))]>;
// FMA Instructions
let BaseName = "XSMADDADP" in {
let isCommutable = 1 in
def XSMADDADP : XX3Form<60, 33,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fma f64:$XA, f64:$XB, f64:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMADDMDP : XX3Form<60, 41,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSMSUBADP" in {
let isCommutable = 1 in
def XSMSUBADP : XX3Form<60, 49,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fma f64:$XA, f64:$XB, (fneg f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMSUBMDP : XX3Form<60, 57,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMADDADP" in {
let isCommutable = 1 in
def XSNMADDADP : XX3Form<60, 161,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fma f64:$XA, f64:$XB, f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMADDMDP : XX3Form<60, 169,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMSUBADP" in {
let isCommutable = 1 in
def XSNMSUBADP : XX3Form<60, 177,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fma f64:$XA, f64:$XB, (fneg f64:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMSUBMDP : XX3Form<60, 185,
(outs vsfrc:$XT), (ins vsfrc:$XTi, vsfrc:$XA, vsfrc:$XB),
"xsnmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMADDADP" in {
let isCommutable = 1 in
def XVMADDADP : XX3Form<60, 97,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fma v2f64:$XA, v2f64:$XB, v2f64:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMADDMDP : XX3Form<60, 105,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMADDASP" in {
let isCommutable = 1 in
def XVMADDASP : XX3Form<60, 65,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fma v4f32:$XA, v4f32:$XB, v4f32:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMADDMSP : XX3Form<60, 73,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMSUBADP" in {
let isCommutable = 1 in
def XVMSUBADP : XX3Form<60, 113,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fma v2f64:$XA, v2f64:$XB, (fneg v2f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMSUBMDP : XX3Form<60, 121,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVMSUBASP" in {
let isCommutable = 1 in
def XVMSUBASP : XX3Form<60, 81,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fma v4f32:$XA, v4f32:$XB, (fneg v4f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVMSUBMSP : XX3Form<60, 89,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMADDADP" in {
let isCommutable = 1 in
def XVNMADDADP : XX3Form<60, 225,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fma v2f64:$XA, v2f64:$XB, v2f64:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMADDMDP : XX3Form<60, 233,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMADDASP" in {
let isCommutable = 1 in
def XVNMADDASP : XX3Form<60, 193,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fma v4f32:$XA, v4f32:$XB, v4f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMADDMSP : XX3Form<60, 201,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMSUBADP" in {
let isCommutable = 1 in
def XVNMSUBADP : XX3Form<60, 241,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubadp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fma v2f64:$XA, v2f64:$XB, (fneg v2f64:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMSUBMDP : XX3Form<60, 249,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubmdp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XVNMSUBASP" in {
let isCommutable = 1 in
def XVNMSUBASP : XX3Form<60, 209,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fma v4f32:$XA, v4f32:$XB, (fneg v4f32:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XVNMSUBMSP : XX3Form<60, 217,
(outs vsrc:$XT), (ins vsrc:$XTi, vsrc:$XA, vsrc:$XB),
"xvnmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
// Division Instructions
def XSDIVDP : XX3Form<60, 56,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsdivdp $XT, $XA, $XB", IIC_FPDivD,
[(set f64:$XT, (fdiv f64:$XA, f64:$XB))]>;
def XSSQRTDP : XX2Form<60, 75,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xssqrtdp $XT, $XB", IIC_FPSqrtD,
[(set f64:$XT, (fsqrt f64:$XB))]>;
def XSREDP : XX2Form<60, 90,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsredp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfre f64:$XB))]>;
def XSRSQRTEDP : XX2Form<60, 74,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrsqrtedp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfrsqrte f64:$XB))]>;
def XSTDIVDP : XX3Form_1<60, 61,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xstdivdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSTSQRTDP : XX2Form_1<60, 106,
(outs crrc:$crD), (ins vsfrc:$XB),
"xstsqrtdp $crD, $XB", IIC_FPCompare, []>;
def XVDIVDP : XX3Form<60, 120,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvdivdp $XT, $XA, $XB", IIC_FPDivD,
[(set v2f64:$XT, (fdiv v2f64:$XA, v2f64:$XB))]>;
def XVDIVSP : XX3Form<60, 88,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvdivsp $XT, $XA, $XB", IIC_FPDivS,
[(set v4f32:$XT, (fdiv v4f32:$XA, v4f32:$XB))]>;
def XVSQRTDP : XX2Form<60, 203,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvsqrtdp $XT, $XB", IIC_FPSqrtD,
[(set v2f64:$XT, (fsqrt v2f64:$XB))]>;
def XVSQRTSP : XX2Form<60, 139,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvsqrtsp $XT, $XB", IIC_FPSqrtS,
[(set v4f32:$XT, (fsqrt v4f32:$XB))]>;
def XVTDIVDP : XX3Form_1<60, 125,
(outs crrc:$crD), (ins vsrc:$XA, vsrc:$XB),
"xvtdivdp $crD, $XA, $XB", IIC_FPCompare, []>;
def XVTDIVSP : XX3Form_1<60, 93,
(outs crrc:$crD), (ins vsrc:$XA, vsrc:$XB),
"xvtdivsp $crD, $XA, $XB", IIC_FPCompare, []>;
def XVTSQRTDP : XX2Form_1<60, 234,
(outs crrc:$crD), (ins vsrc:$XB),
"xvtsqrtdp $crD, $XB", IIC_FPCompare, []>;
def XVTSQRTSP : XX2Form_1<60, 170,
(outs crrc:$crD), (ins vsrc:$XB),
"xvtsqrtsp $crD, $XB", IIC_FPCompare, []>;
def XVREDP : XX2Form<60, 218,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvredp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (PPCfre v2f64:$XB))]>;
def XVRESP : XX2Form<60, 154,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvresp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (PPCfre v4f32:$XB))]>;
def XVRSQRTEDP : XX2Form<60, 202,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrsqrtedp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (PPCfrsqrte v2f64:$XB))]>;
def XVRSQRTESP : XX2Form<60, 138,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrsqrtesp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (PPCfrsqrte v4f32:$XB))]>;
// Compare Instructions
def XSCMPODP : XX3Form_1<60, 43,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpodp $crD, $XA, $XB", IIC_FPCompare, []>;
def XSCMPUDP : XX3Form_1<60, 35,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpudp $crD, $XA, $XB", IIC_FPCompare, []>;
defm XVCMPEQDP : XX3Form_Rcr<60, 99,
"xvcmpeqdp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpeqdp, v2i64, v2f64>;
defm XVCMPEQSP : XX3Form_Rcr<60, 67,
"xvcmpeqsp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpeqsp, v4i32, v4f32>;
defm XVCMPGEDP : XX3Form_Rcr<60, 115,
"xvcmpgedp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgedp, v2i64, v2f64>;
defm XVCMPGESP : XX3Form_Rcr<60, 83,
"xvcmpgesp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgesp, v4i32, v4f32>;
defm XVCMPGTDP : XX3Form_Rcr<60, 107,
"xvcmpgtdp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgtdp, v2i64, v2f64>;
defm XVCMPGTSP : XX3Form_Rcr<60, 75,
"xvcmpgtsp", "$XT, $XA, $XB", IIC_VecFPCompare,
int_ppc_vsx_xvcmpgtsp, v4i32, v4f32>;
// Move Instructions
def XSABSDP : XX2Form<60, 345,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsabsdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fabs f64:$XB))]>;
def XSNABSDP : XX2Form<60, 361,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsnabsdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fneg (fabs f64:$XB)))]>;
def XSNEGDP : XX2Form<60, 377,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsnegdp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fneg f64:$XB))]>;
def XSCPSGNDP : XX3Form<60, 176,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xscpsgndp $XT, $XA, $XB", IIC_VecFP,
[(set f64:$XT, (fcopysign f64:$XB, f64:$XA))]>;
def XVABSDP : XX2Form<60, 473,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvabsdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fabs v2f64:$XB))]>;
def XVABSSP : XX2Form<60, 409,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvabssp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fabs v4f32:$XB))]>;
def XVCPSGNDP : XX3Form<60, 240,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcpsgndp $XT, $XA, $XB", IIC_VecFP,
[(set v2f64:$XT, (fcopysign v2f64:$XB, v2f64:$XA))]>;
def XVCPSGNSP : XX3Form<60, 208,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcpsgnsp $XT, $XA, $XB", IIC_VecFP,
[(set v4f32:$XT, (fcopysign v4f32:$XB, v4f32:$XA))]>;
def XVNABSDP : XX2Form<60, 489,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnabsdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg (fabs v2f64:$XB)))]>;
def XVNABSSP : XX2Form<60, 425,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnabssp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg (fabs v4f32:$XB)))]>;
def XVNEGDP : XX2Form<60, 505,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnegdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fneg v2f64:$XB))]>;
def XVNEGSP : XX2Form<60, 441,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvnegsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fneg v4f32:$XB))]>;
// Conversion Instructions
def XSCVDPSP : XX2Form<60, 265,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsp $XT, $XB", IIC_VecFP, []>;
def XSCVDPSXDS : XX2Form<60, 344,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsxds $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctidz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPSXDSs : XX2Form<60, 344,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpsxds $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctidz f32:$XB))]>;
def XSCVDPSXWS : XX2Form<60, 88,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpsxws $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiwz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPSXWSs : XX2Form<60, 88,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpsxws $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiwz f32:$XB))]>;
def XSCVDPUXDS : XX2Form<60, 328,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpuxds $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiduz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPUXDSs : XX2Form<60, 328,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpuxds $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiduz f32:$XB))]>;
def XSCVDPUXWS : XX2Form<60, 72,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvdpuxws $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfctiwuz f64:$XB))]>;
let isCodeGenOnly = 1 in
def XSCVDPUXWSs : XX2Form<60, 72,
(outs vssrc:$XT), (ins vssrc:$XB),
"xscvdpuxws $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfctiwuz f32:$XB))]>;
def XSCVSPDP : XX2Form<60, 329,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvspdp $XT, $XB", IIC_VecFP, []>;
def XSCVSXDDP : XX2Form<60, 376,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvsxddp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfcfid f64:$XB))]>;
def XSCVUXDDP : XX2Form<60, 360,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xscvuxddp $XT, $XB", IIC_VecFP,
[(set f64:$XT, (PPCfcfidu f64:$XB))]>;
def XVCVDPSP : XX2Form<60, 393,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvdpsp v2f64:$XB))]>;
def XVCVDPSXDS : XX2Form<60, 472,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsxds $XT, $XB", IIC_VecFP,
[(set v2i64:$XT, (fp_to_sint v2f64:$XB))]>;
def XVCVDPSXWS : XX2Form<60, 216,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpsxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (int_ppc_vsx_xvcvdpsxws v2f64:$XB))]>;
def XVCVDPUXDS : XX2Form<60, 456,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpuxds $XT, $XB", IIC_VecFP,
[(set v2i64:$XT, (fp_to_uint v2f64:$XB))]>;
def XVCVDPUXWS : XX2Form<60, 200,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvdpuxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (int_ppc_vsx_xvcvdpuxws v2f64:$XB))]>;
def XVCVSPDP : XX2Form<60, 457,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvspdp v4f32:$XB))]>;
def XVCVSPSXDS : XX2Form<60, 408,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspsxds $XT, $XB", IIC_VecFP, []>;
def XVCVSPSXWS : XX2Form<60, 152,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspsxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (fp_to_sint v4f32:$XB))]>;
def XVCVSPUXDS : XX2Form<60, 392,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspuxds $XT, $XB", IIC_VecFP, []>;
def XVCVSPUXWS : XX2Form<60, 136,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvspuxws $XT, $XB", IIC_VecFP,
[(set v4i32:$XT, (fp_to_uint v4f32:$XB))]>;
def XVCVSXDDP : XX2Form<60, 504,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxddp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (sint_to_fp v2i64:$XB))]>;
def XVCVSXDSP : XX2Form<60, 440,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxdsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvsxdsp v2i64:$XB))]>;
def XVCVSXWDP : XX2Form<60, 248,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxwdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvsxwdp v4i32:$XB))]>;
def XVCVSXWSP : XX2Form<60, 184,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvsxwsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (sint_to_fp v4i32:$XB))]>;
def XVCVUXDDP : XX2Form<60, 488,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxddp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (uint_to_fp v2i64:$XB))]>;
def XVCVUXDSP : XX2Form<60, 424,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxdsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (int_ppc_vsx_xvcvuxdsp v2i64:$XB))]>;
def XVCVUXWDP : XX2Form<60, 232,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxwdp $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (int_ppc_vsx_xvcvuxwdp v4i32:$XB))]>;
def XVCVUXWSP : XX2Form<60, 168,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvcvuxwsp $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (uint_to_fp v4i32:$XB))]>;
// Rounding Instructions
def XSRDPI : XX2Form<60, 73,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpi $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fround f64:$XB))]>;
def XSRDPIC : XX2Form<60, 107,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpic $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fnearbyint f64:$XB))]>;
def XSRDPIM : XX2Form<60, 121,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpim $XT, $XB", IIC_VecFP,
[(set f64:$XT, (ffloor f64:$XB))]>;
def XSRDPIP : XX2Form<60, 105,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpip $XT, $XB", IIC_VecFP,
[(set f64:$XT, (fceil f64:$XB))]>;
def XSRDPIZ : XX2Form<60, 89,
(outs vsfrc:$XT), (ins vsfrc:$XB),
"xsrdpiz $XT, $XB", IIC_VecFP,
[(set f64:$XT, (ftrunc f64:$XB))]>;
def XVRDPI : XX2Form<60, 201,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpi $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fround v2f64:$XB))]>;
def XVRDPIC : XX2Form<60, 235,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpic $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fnearbyint v2f64:$XB))]>;
def XVRDPIM : XX2Form<60, 249,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpim $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (ffloor v2f64:$XB))]>;
def XVRDPIP : XX2Form<60, 233,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpip $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (fceil v2f64:$XB))]>;
def XVRDPIZ : XX2Form<60, 217,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrdpiz $XT, $XB", IIC_VecFP,
[(set v2f64:$XT, (ftrunc v2f64:$XB))]>;
def XVRSPI : XX2Form<60, 137,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspi $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fround v4f32:$XB))]>;
def XVRSPIC : XX2Form<60, 171,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspic $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fnearbyint v4f32:$XB))]>;
def XVRSPIM : XX2Form<60, 185,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspim $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (ffloor v4f32:$XB))]>;
def XVRSPIP : XX2Form<60, 169,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspip $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (fceil v4f32:$XB))]>;
def XVRSPIZ : XX2Form<60, 153,
(outs vsrc:$XT), (ins vsrc:$XB),
"xvrspiz $XT, $XB", IIC_VecFP,
[(set v4f32:$XT, (ftrunc v4f32:$XB))]>;
// Max/Min Instructions
let isCommutable = 1 in {
def XSMAXDP : XX3Form<60, 160,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmaxdp $XT, $XA, $XB", IIC_VecFP,
[(set vsfrc:$XT,
(int_ppc_vsx_xsmaxdp vsfrc:$XA, vsfrc:$XB))]>;
def XSMINDP : XX3Form<60, 168,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xsmindp $XT, $XA, $XB", IIC_VecFP,
[(set vsfrc:$XT,
(int_ppc_vsx_xsmindp vsfrc:$XA, vsfrc:$XB))]>;
def XVMAXDP : XX3Form<60, 224,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmaxdp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmaxdp vsrc:$XA, vsrc:$XB))]>;
def XVMINDP : XX3Form<60, 232,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmindp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmindp vsrc:$XA, vsrc:$XB))]>;
def XVMAXSP : XX3Form<60, 192,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvmaxsp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvmaxsp vsrc:$XA, vsrc:$XB))]>;
def XVMINSP : XX3Form<60, 200,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvminsp $XT, $XA, $XB", IIC_VecFP,
[(set vsrc:$XT,
(int_ppc_vsx_xvminsp vsrc:$XA, vsrc:$XB))]>;
} // isCommutable
} // Uses = [RM]
// Logical Instructions
let isCommutable = 1 in
def XXLAND : XX3Form<60, 130,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxland $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (and v4i32:$XA, v4i32:$XB))]>;
def XXLANDC : XX3Form<60, 138,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlandc $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (and v4i32:$XA,
(vnot_ppc v4i32:$XB)))]>;
let isCommutable = 1 in {
def XXLNOR : XX3Form<60, 162,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlnor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (or v4i32:$XA,
v4i32:$XB)))]>;
def XXLOR : XX3Form<60, 146,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (or v4i32:$XA, v4i32:$XB))]>;
let isCodeGenOnly = 1 in
def XXLORf: XX3Form<60, 146,
(outs vsfrc:$XT), (ins vsfrc:$XA, vsfrc:$XB),
"xxlor $XT, $XA, $XB", IIC_VecGeneral, []>;
def XXLXOR : XX3Form<60, 154,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlxor $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (xor v4i32:$XA, v4i32:$XB))]>;
} // isCommutable
let isCodeGenOnly = 1 in
def XXLXORz : XX3Form_Zero<60, 154, (outs vsrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set v4i32:$XT, (v4i32 immAllZerosV))]>;
let isCodeGenOnly = 1 in {
def XXLXORdpz : XX3Form_SetZero<60, 154,
(outs vsfrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set f64:$XT, (fpimm0))]>;
def XXLXORspz : XX3Form_SetZero<60, 154,
(outs vssrc:$XT), (ins),
"xxlxor $XT, $XT, $XT", IIC_VecGeneral,
[(set f32:$XT, (fpimm0))]>;
}
// Permutation Instructions
def XXMRGHW : XX3Form<60, 18,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxmrghw $XT, $XA, $XB", IIC_VecPerm, []>;
def XXMRGLW : XX3Form<60, 50,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxmrglw $XT, $XA, $XB", IIC_VecPerm, []>;
def XXPERMDI : XX3Form_2<60, 10,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, u2imm:$DM),
"xxpermdi $XT, $XA, $XB, $DM", IIC_VecPerm, []>;
let isCodeGenOnly = 1 in
def XXPERMDIs : XX3Form_2s<60, 10, (outs vsrc:$XT), (ins vsfrc:$XA, u2imm:$DM),
"xxpermdi $XT, $XA, $XA, $DM", IIC_VecPerm, []>;
def XXSEL : XX4Form<60, 3,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, vsrc:$XC),
"xxsel $XT, $XA, $XB, $XC", IIC_VecPerm, []>;
def XXSLDWI : XX3Form_2<60, 2,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB, u2imm:$SHW),
"xxsldwi $XT, $XA, $XB, $SHW", IIC_VecPerm,
[(set v4i32:$XT, (PPCvecshl v4i32:$XA, v4i32:$XB,
imm32SExt16:$SHW))]>;
def XXSPLTW : XX2Form_2<60, 164,
(outs vsrc:$XT), (ins vsrc:$XB, u2imm:$UIM),
"xxspltw $XT, $XB, $UIM", IIC_VecPerm,
[(set v4i32:$XT,
(PPCxxsplt v4i32:$XB, imm32SExt16:$UIM))]>;
let isCodeGenOnly = 1 in
def XXSPLTWs : XX2Form_2<60, 164,
(outs vsrc:$XT), (ins vfrc:$XB, u2imm:$UIM),
"xxspltw $XT, $XB, $UIM", IIC_VecPerm, []>;
} // hasSideEffects
} // UseVSXReg = 1
// SELECT_CC_* - Used to implement the SELECT_CC DAG operation. Expanded after
// instruction selection into a branch sequence.
let usesCustomInserter = 1, // Expanded after instruction selection.
PPC970_Single = 1 in {
def SELECT_CC_VSRC: Pseudo<(outs vsrc:$dst),
(ins crrc:$cond, vsrc:$T, vsrc:$F, i32imm:$BROPC),
"#SELECT_CC_VSRC",
[]>;
def SELECT_VSRC: Pseudo<(outs vsrc:$dst),
(ins crbitrc:$cond, vsrc:$T, vsrc:$F),
"#SELECT_VSRC",
[(set v2f64:$dst,
(select i1:$cond, v2f64:$T, v2f64:$F))]>;
def SELECT_CC_VSFRC: Pseudo<(outs f8rc:$dst),
(ins crrc:$cond, f8rc:$T, f8rc:$F,
i32imm:$BROPC), "#SELECT_CC_VSFRC",
[]>;
def SELECT_VSFRC: Pseudo<(outs f8rc:$dst),
(ins crbitrc:$cond, f8rc:$T, f8rc:$F),
"#SELECT_VSFRC",
[(set f64:$dst,
(select i1:$cond, f64:$T, f64:$F))]>;
def SELECT_CC_VSSRC: Pseudo<(outs f4rc:$dst),
(ins crrc:$cond, f4rc:$T, f4rc:$F,
i32imm:$BROPC), "#SELECT_CC_VSSRC",
[]>;
def SELECT_VSSRC: Pseudo<(outs f4rc:$dst),
(ins crbitrc:$cond, f4rc:$T, f4rc:$F),
"#SELECT_VSSRC",
[(set f32:$dst,
(select i1:$cond, f32:$T, f32:$F))]>;
} // usesCustomInserter
} // AddedComplexity
def : InstAlias<"xvmovdp $XT, $XB",
(XVCPSGNDP vsrc:$XT, vsrc:$XB, vsrc:$XB)>;
def : InstAlias<"xvmovsp $XT, $XB",
(XVCPSGNSP vsrc:$XT, vsrc:$XB, vsrc:$XB)>;
def : InstAlias<"xxspltd $XT, $XB, 0",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 0)>;
def : InstAlias<"xxspltd $XT, $XB, 1",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 3)>;
def : InstAlias<"xxmrghd $XT, $XA, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XA, vsrc:$XB, 0)>;
def : InstAlias<"xxmrgld $XT, $XA, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XA, vsrc:$XB, 3)>;
def : InstAlias<"xxswapd $XT, $XB",
(XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 2)>;
def : InstAlias<"xxspltd $XT, $XB, 0",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 0)>;
def : InstAlias<"xxspltd $XT, $XB, 1",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 3)>;
def : InstAlias<"xxswapd $XT, $XB",
(XXPERMDIs vsrc:$XT, vsfrc:$XB, 2)>;
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
def : Pat<(v4i32 (vnot_ppc v4i32:$A)),
(v4i32 (XXLNOR $A, $A))>;
let Predicates = [IsBigEndian] in {
def : Pat<(v2f64 (scalar_to_vector f64:$A)),
(v2f64 (SUBREG_TO_REG (i64 1), $A, sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 0)),
(f64 (EXTRACT_SUBREG $S, sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 1)),
(f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
}
let Predicates = [IsLittleEndian] in {
def : Pat<(v2f64 (scalar_to_vector f64:$A)),
(v2f64 (XXPERMDI (SUBREG_TO_REG (i64 1), $A, sub_64),
(SUBREG_TO_REG (i64 1), $A, sub_64), 0))>;
def : Pat<(f64 (extractelt v2f64:$S, 0)),
(f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
def : Pat<(f64 (extractelt v2f64:$S, 1)),
(f64 (EXTRACT_SUBREG $S, sub_64))>;
}
// Additional fnmsub patterns: -a*c + b == -(a*c - b)
def : Pat<(fma (fneg f64:$A), f64:$C, f64:$B),
(XSNMSUBADP $B, $C, $A)>;
def : Pat<(fma f64:$A, (fneg f64:$C), f64:$B),
(XSNMSUBADP $B, $C, $A)>;
def : Pat<(fma (fneg v2f64:$A), v2f64:$C, v2f64:$B),
(XVNMSUBADP $B, $C, $A)>;
def : Pat<(fma v2f64:$A, (fneg v2f64:$C), v2f64:$B),
(XVNMSUBADP $B, $C, $A)>;
def : Pat<(fma (fneg v4f32:$A), v4f32:$C, v4f32:$B),
(XVNMSUBASP $B, $C, $A)>;
def : Pat<(fma v4f32:$A, (fneg v4f32:$C), v4f32:$B),
(XVNMSUBASP $B, $C, $A)>;
def : Pat<(v2f64 (bitconvert v4f32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v4i32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v8i16:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2f64 (bitconvert v16i8:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v4f32 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v4i32 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v8i16 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v16i8 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2i64 (bitconvert v4f32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v4i32:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v8i16:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v2i64 (bitconvert v16i8:$A)),
(COPY_TO_REGCLASS $A, VSRC)>;
def : Pat<(v4f32 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v4i32 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v8i16 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v16i8 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2f64 (bitconvert v2i64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2i64 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v2f64 (bitconvert v1i128:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
def : Pat<(v1i128 (bitconvert v2f64:$A)),
(COPY_TO_REGCLASS $A, VRRC)>;
// sign extension patterns
// To extend "in place" from v2i32 to v2i64, we have input data like:
// | undef | i32 | undef | i32 |
// but xvcvsxwdp expects the input in big-Endian format:
// | i32 | undef | i32 | undef |
// so we need to shift everything to the left by one i32 (word) before
// the conversion.
def : Pat<(sext_inreg v2i64:$C, v2i32),
(XVCVDPSXDS (XVCVSXWDP (XXSLDWI $C, $C, 1)))>;
def : Pat<(v2f64 (sint_to_fp (sext_inreg v2i64:$C, v2i32))),
(XVCVSXWDP (XXSLDWI $C, $C, 1))>;
def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 0)),
(v2f64 (XVCVSXWDP (v2i64 (XXMRGHW $C, $C))))>;
def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 1)),
(v2f64 (XVCVSXWDP (v2i64 (XXMRGLW $C, $C))))>;
def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 0)),
(v2f64 (XVCVUXWDP (v2i64 (XXMRGHW $C, $C))))>;
def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 1)),
(v2f64 (XVCVUXWDP (v2i64 (XXMRGLW $C, $C))))>;
// Loads.
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
def : Pat<(v2f64 (PPClxvd2x xoaddr:$src)), (LXVD2X xoaddr:$src)>;
// Stores.
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, xoaddr:$dst),
(STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, xoaddr:$dst),
(STXVW4X $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x_be v2f64:$rS, xoaddr:$dst),
(STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x_be v4i32:$rS, xoaddr:$dst),
(STXVW4X $rS, xoaddr:$dst)>;
def : Pat<(PPCstxvd2x v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
}
let Predicates = [IsBigEndian, HasVSX, HasOnlySwappingMemOps] in {
def : Pat<(v2f64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(v2i64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
def : Pat<(v4i32 (load xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(store v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
def : Pat<(store v2i64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
}
// Permutes.
def : Pat<(v2f64 (PPCxxswapd v2f64:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v2i64 (PPCxxswapd v2i64:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v4f32 (PPCxxswapd v4f32:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v4i32 (PPCxxswapd v4i32:$src)), (XXPERMDI $src, $src, 2)>;
def : Pat<(v2f64 (PPCswapNoChain v2f64:$src)), (XXPERMDI $src, $src, 2)>;
// Selects.
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETLT)),
(SELECT_VSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETULT)),
(SELECT_VSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETLE)),
(SELECT_VSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETULE)),
(SELECT_VSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETEQ)),
(SELECT_VSRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETGE)),
(SELECT_VSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETUGE)),
(SELECT_VSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETGT)),
(SELECT_VSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETUGT)),
(SELECT_VSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETNE)),
(SELECT_VSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETLT)),
(SELECT_VSFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETULT)),
(SELECT_VSFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETLE)),
(SELECT_VSFRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETULE)),
(SELECT_VSFRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETEQ)),
(SELECT_VSFRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETGE)),
(SELECT_VSFRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETUGE)),
(SELECT_VSFRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETGT)),
(SELECT_VSFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETUGT)),
(SELECT_VSFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETNE)),
(SELECT_VSFRC (CRXOR $lhs, $rhs), $tval, $fval)>;
// Divides.
def : Pat<(int_ppc_vsx_xvdivsp v4f32:$A, v4f32:$B),
(XVDIVSP $A, $B)>;
def : Pat<(int_ppc_vsx_xvdivdp v2f64:$A, v2f64:$B),
(XVDIVDP $A, $B)>;
// Reciprocal estimate
def : Pat<(int_ppc_vsx_xvresp v4f32:$A),
(XVRESP $A)>;
def : Pat<(int_ppc_vsx_xvredp v2f64:$A),
(XVREDP $A)>;
// Recip. square root estimate
def : Pat<(int_ppc_vsx_xvrsqrtesp v4f32:$A),
(XVRSQRTESP $A)>;
def : Pat<(int_ppc_vsx_xvrsqrtedp v2f64:$A),
(XVRSQRTEDP $A)>;
let Predicates = [IsLittleEndian] in {
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
} // IsLittleEndian
let Predicates = [IsBigEndian] in {
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f64 (PPCfcfid (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVSXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f64 (PPCfcfidu (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f64 (XSCVUXDDP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
} // IsBigEndian
} // AddedComplexity
} // HasVSX
def ScalarLoads {
dag Li8 = (i32 (extloadi8 xoaddr:$src));
dag ZELi8 = (i32 (zextloadi8 xoaddr:$src));
dag ZELi8i64 = (i64 (zextloadi8 xoaddr:$src));
dag SELi8 = (i32 (sext_inreg (extloadi8 xoaddr:$src), i8));
dag SELi8i64 = (i64 (sext_inreg (extloadi8 xoaddr:$src), i8));
dag Li16 = (i32 (extloadi16 xoaddr:$src));
dag ZELi16 = (i32 (zextloadi16 xoaddr:$src));
dag ZELi16i64 = (i64 (zextloadi16 xoaddr:$src));
dag SELi16 = (i32 (sextloadi16 xoaddr:$src));
dag SELi16i64 = (i64 (sextloadi16 xoaddr:$src));
dag Li32 = (i32 (load xoaddr:$src));
}
// The following VSX instructions were introduced in Power ISA 2.07
/* FIXME: if the operands are v2i64, these patterns will not match.
we should define new patterns or otherwise match the same patterns
when the elements are larger than i32.
*/
def HasP8Vector : Predicate<"PPCSubTarget->hasP8Vector()">;
def HasDirectMove : Predicate<"PPCSubTarget->hasDirectMove()">;
let Predicates = [HasP8Vector] in {
let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
let isCommutable = 1, UseVSXReg = 1 in {
def XXLEQV : XX3Form<60, 186,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxleqv $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (xor v4i32:$XA, v4i32:$XB)))]>;
def XXLNAND : XX3Form<60, 178,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlnand $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (vnot_ppc (and v4i32:$XA,
v4i32:$XB)))]>;
} // isCommutable, UseVSXReg
def : Pat<(int_ppc_vsx_xxleqv v4i32:$A, v4i32:$B),
(XXLEQV $A, $B)>;
let UseVSXReg = 1 in {
def XXLORC : XX3Form<60, 170,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xxlorc $XT, $XA, $XB", IIC_VecGeneral,
[(set v4i32:$XT, (or v4i32:$XA, (vnot_ppc v4i32:$XB)))]>;
// VSX scalar loads introduced in ISA 2.07
let mayLoad = 1, mayStore = 0 in {
let CodeSize = 3 in
def LXSSPX : XX1Form<31, 524, (outs vssrc:$XT), (ins memrr:$src),
"lxsspx $XT, $src", IIC_LdStLFD,
[(set f32:$XT, (load xoaddr:$src))]>;
def LXSIWAX : XX1Form<31, 76, (outs vsfrc:$XT), (ins memrr:$src),
"lxsiwax $XT, $src", IIC_LdStLFD,
[(set f64:$XT, (PPClfiwax xoaddr:$src))]>;
def LXSIWZX : XX1Form<31, 12, (outs vsfrc:$XT), (ins memrr:$src),
"lxsiwzx $XT, $src", IIC_LdStLFD,
[(set f64:$XT, (PPClfiwzx xoaddr:$src))]>;
} // mayLoad
// VSX scalar stores introduced in ISA 2.07
let mayStore = 1, mayLoad = 0 in {
let CodeSize = 3 in
def STXSSPX : XX1Form<31, 652, (outs), (ins vssrc:$XT, memrr:$dst),
"stxsspx $XT, $dst", IIC_LdStSTFD,
[(store f32:$XT, xoaddr:$dst)]>;
def STXSIWX : XX1Form<31, 140, (outs), (ins vsfrc:$XT, memrr:$dst),
"stxsiwx $XT, $dst", IIC_LdStSTFD,
[(PPCstfiwx f64:$XT, xoaddr:$dst)]>;
} // mayStore
} // UseVSXReg = 1
def : Pat<(f64 (extloadf32 xoaddr:$src)),
(COPY_TO_REGCLASS (LXSSPX xoaddr:$src), VSFRC)>;
def : Pat<(f32 (fpround (extloadf32 xoaddr:$src))),
(f32 (LXSSPX xoaddr:$src))>;
def : Pat<(f64 (fpextend f32:$src)),
(COPY_TO_REGCLASS $src, VSFRC)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLT)),
(SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETULT)),
(SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLE)),
(SELECT_VSSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETULE)),
(SELECT_VSSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETEQ)),
(SELECT_VSSRC (CREQV $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGE)),
(SELECT_VSSRC (CRORC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETUGE)),
(SELECT_VSSRC (CRORC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGT)),
(SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETUGT)),
(SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETNE)),
(SELECT_VSSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
let UseVSXReg = 1 in {
// VSX Elementary Scalar FP arithmetic (SP)
let isCommutable = 1 in {
def XSADDSP : XX3Form<60, 0,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsaddsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fadd f32:$XA, f32:$XB))]>;
def XSMULSP : XX3Form<60, 16,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsmulsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fmul f32:$XA, f32:$XB))]>;
} // isCommutable
def XSDIVSP : XX3Form<60, 24,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xsdivsp $XT, $XA, $XB", IIC_FPDivS,
[(set f32:$XT, (fdiv f32:$XA, f32:$XB))]>;
def XSRESP : XX2Form<60, 26,
(outs vssrc:$XT), (ins vssrc:$XB),
"xsresp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfre f32:$XB))]>;
def XSSQRTSP : XX2Form<60, 11,
(outs vssrc:$XT), (ins vssrc:$XB),
"xssqrtsp $XT, $XB", IIC_FPSqrtS,
[(set f32:$XT, (fsqrt f32:$XB))]>;
def XSRSQRTESP : XX2Form<60, 10,
(outs vssrc:$XT), (ins vssrc:$XB),
"xsrsqrtesp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfrsqrte f32:$XB))]>;
def XSSUBSP : XX3Form<60, 8,
(outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
"xssubsp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fsub f32:$XA, f32:$XB))]>;
// FMA Instructions
let BaseName = "XSMADDASP" in {
let isCommutable = 1 in
def XSMADDASP : XX3Form<60, 1,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fma f32:$XA, f32:$XB, f32:$XTi))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMADDMSP : XX3Form<60, 9,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSMSUBASP" in {
let isCommutable = 1 in
def XSMSUBASP : XX3Form<60, 17,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fma f32:$XA, f32:$XB,
(fneg f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSMSUBMSP : XX3Form<60, 25,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMADDASP" in {
let isCommutable = 1 in
def XSNMADDASP : XX3Form<60, 129,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmaddasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fneg (fma f32:$XA, f32:$XB,
f32:$XTi)))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMADDMSP : XX3Form<60, 137,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmaddmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
let BaseName = "XSNMSUBASP" in {
let isCommutable = 1 in
def XSNMSUBASP : XX3Form<60, 145,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmsubasp $XT, $XA, $XB", IIC_VecFP,
[(set f32:$XT, (fneg (fma f32:$XA, f32:$XB,
(fneg f32:$XTi))))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
let IsVSXFMAAlt = 1 in
def XSNMSUBMSP : XX3Form<60, 153,
(outs vssrc:$XT),
(ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
"xsnmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
AltVSXFMARel;
}
// Single Precision Conversions (FP <-> INT)
def XSCVSXDSP : XX2Form<60, 312,
(outs vssrc:$XT), (ins vsfrc:$XB),
"xscvsxdsp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfcfids f64:$XB))]>;
def XSCVUXDSP : XX2Form<60, 296,
(outs vssrc:$XT), (ins vsfrc:$XB),
"xscvuxdsp $XT, $XB", IIC_VecFP,
[(set f32:$XT, (PPCfcfidus f64:$XB))]>;
// Conversions between vector and scalar single precision
def XSCVDPSPN : XX2Form<60, 267, (outs vsrc:$XT), (ins vssrc:$XB),
"xscvdpspn $XT, $XB", IIC_VecFP, []>;
def XSCVSPDPN : XX2Form<60, 331, (outs vssrc:$XT), (ins vsrc:$XB),
"xscvspdpn $XT, $XB", IIC_VecFP, []>;
} // UseVSXReg = 1
let Predicates = [IsLittleEndian] in {
def : Pat<(f32 (PPCfcfids (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f32 (PPCfcfids (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f32 (XSCVSXDSP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f32 (XSCVUXDSP (COPY_TO_REGCLASS (f64 (COPY_TO_REGCLASS $S, VSRC)), VSFRC)))>;
}
let Predicates = [IsBigEndian] in {
def : Pat<(f32 (PPCfcfids (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f32 (XSCVSXDSP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f32 (PPCfcfids (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f32 (XSCVSXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsra (i64 (vector_extract v2i64:$S, 0))))),
(f32 (XSCVUXDSP (COPY_TO_REGCLASS $S, VSFRC)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsra (i64 (vector_extract v2i64:$S, 1))))),
(f32 (XSCVUXDSP (COPY_TO_REGCLASS (XXPERMDI $S, $S, 2), VSFRC)))>;
}
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.Li32)),
(v4i32 (XXSPLTWs (LXSIWAX xoaddr:$src), 1))>;
} // AddedComplexity = 400
} // HasP8Vector
let UseVSXReg = 1, AddedComplexity = 400 in {
let Predicates = [HasDirectMove] in {
// VSX direct move instructions
def MFVSRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsfrc:$XT),
"mfvsrd $rA, $XT", IIC_VecGeneral,
[(set i64:$rA, (PPCmfvsr f64:$XT))]>,
Requires<[In64BitMode]>;
let isCodeGenOnly = 1 in
def MFVRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vrrc:$XT),
"mfvsrd $rA, $XT", IIC_VecGeneral,
[]>,
Requires<[In64BitMode]>;
def MFVSRWZ : XX1_RS6_RD5_XO<31, 115, (outs gprc:$rA), (ins vsfrc:$XT),
"mfvsrwz $rA, $XT", IIC_VecGeneral,
[(set i32:$rA, (PPCmfvsr f64:$XT))]>;
def MTVSRD : XX1_RS6_RD5_XO<31, 179, (outs vsfrc:$XT), (ins g8rc:$rA),
"mtvsrd $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsra i64:$rA))]>,
Requires<[In64BitMode]>;
def MTVSRWA : XX1_RS6_RD5_XO<31, 211, (outs vsfrc:$XT), (ins gprc:$rA),
"mtvsrwa $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsra i32:$rA))]>;
def MTVSRWZ : XX1_RS6_RD5_XO<31, 243, (outs vsfrc:$XT), (ins gprc:$rA),
"mtvsrwz $XT, $rA", IIC_VecGeneral,
[(set f64:$XT, (PPCmtvsrz i32:$rA))]>;
} // HasDirectMove
let Predicates = [IsISA3_0, HasDirectMove] in {
def MTVSRWS: XX1_RS6_RD5_XO<31, 403, (outs vsrc:$XT), (ins gprc:$rA),
"mtvsrws $XT, $rA", IIC_VecGeneral, []>;
def MTVSRDD: XX1Form<31, 435, (outs vsrc:$XT), (ins g8rc:$rA, g8rc:$rB),
"mtvsrdd $XT, $rA, $rB", IIC_VecGeneral,
[]>, Requires<[In64BitMode]>;
def MFVSRLD: XX1_RS6_RD5_XO<31, 307, (outs g8rc:$rA), (ins vsrc:$XT),
"mfvsrld $rA, $XT", IIC_VecGeneral,
[]>, Requires<[In64BitMode]>;
} // IsISA3_0, HasDirectMove
} // UseVSXReg = 1
// We want to parse this from asm, but we don't want to emit this as it would
// be emitted with a VSX reg. So leave Emit = 0 here.
def : InstAlias<"mfvrd $rA, $XT",
(MFVRD g8rc:$rA, vrrc:$XT), 0>;
def : InstAlias<"mffprd $rA, $src",
(MFVSRD g8rc:$rA, f8rc:$src)>;
/* Direct moves of various widths from GPR's into VSR's. Each move lines
the value up into element 0 (both BE and LE). Namely, entities smaller than
a doubleword are shifted left and moved for BE. For LE, they're moved, then
swapped to go into the least significant element of the VSR.
*/
def MovesToVSR {
dag BE_BYTE_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 56, 7));
dag BE_HALF_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 48, 15));
dag BE_WORD_0 =
(MTVSRD
(RLDICR
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 32, 31));
dag BE_DWORD_0 = (MTVSRD $A);
dag LE_MTVSRW = (MTVSRD (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32));
dag LE_WORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
LE_MTVSRW, sub_64));
dag LE_WORD_0 = (XXPERMDI LE_WORD_1, LE_WORD_1, 2);
dag LE_DWORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
BE_DWORD_0, sub_64));
dag LE_DWORD_0 = (XXPERMDI LE_DWORD_1, LE_DWORD_1, 2);
}
/* Patterns for extracting elements out of vectors. Integer elements are
extracted using direct move operations. Patterns for extracting elements
whose indices are not available at compile time are also provided with
various _VARIABLE_ patterns.
The numbering for the DAG's is for LE, but when used on BE, the correct
LE element can just be used (i.e. LE_BYTE_2 == BE_BYTE_13).
*/
def VectorExtractions {
// Doubleword extraction
dag LE_DWORD_0 =
(MFVSRD
(EXTRACT_SUBREG
(XXPERMDI (COPY_TO_REGCLASS $S, VSRC),
(COPY_TO_REGCLASS $S, VSRC), 2), sub_64));
dag LE_DWORD_1 = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
// Word extraction
dag LE_WORD_0 = (MFVSRWZ (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64));
dag LE_WORD_1 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 1), sub_64));
dag LE_WORD_2 = (MFVSRWZ (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
dag LE_WORD_3 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 3), sub_64));
// Halfword extraction
dag LE_HALF_0 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 0, 48), sub_32));
dag LE_HALF_1 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 48, 48), sub_32));
dag LE_HALF_2 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 32, 48), sub_32));
dag LE_HALF_3 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 16, 48), sub_32));
dag LE_HALF_4 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 0, 48), sub_32));
dag LE_HALF_5 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 48, 48), sub_32));
dag LE_HALF_6 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 32, 48), sub_32));
dag LE_HALF_7 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 16, 48), sub_32));
// Byte extraction
dag LE_BYTE_0 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 0, 56), sub_32));
dag LE_BYTE_1 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 56, 56), sub_32));
dag LE_BYTE_2 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 48, 56), sub_32));
dag LE_BYTE_3 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 40, 56), sub_32));
dag LE_BYTE_4 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 32, 56), sub_32));
dag LE_BYTE_5 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 24, 56), sub_32));
dag LE_BYTE_6 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 16, 56), sub_32));
dag LE_BYTE_7 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 8, 56), sub_32));
dag LE_BYTE_8 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 0, 56), sub_32));
dag LE_BYTE_9 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 56, 56), sub_32));
dag LE_BYTE_10 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 48, 56), sub_32));
dag LE_BYTE_11 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 40, 56), sub_32));
dag LE_BYTE_12 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 32, 56), sub_32));
dag LE_BYTE_13 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 24, 56), sub_32));
dag LE_BYTE_14 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 16, 56), sub_32));
dag LE_BYTE_15 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 8, 56), sub_32));
/* Variable element number (BE and LE patterns must be specified separately)
This is a rather involved process.
Conceptually, this is how the move is accomplished:
1. Identify which doubleword contains the element
2. Shift in the VMX register so that the correct doubleword is correctly
lined up for the MFVSRD
3. Perform the move so that the element (along with some extra stuff)
is in the GPR
4. Right shift within the GPR so that the element is right-justified
Of course, the index is an element number which has a different meaning
on LE/BE so the patterns have to be specified separately.
Note: The final result will be the element right-justified with high
order bits being arbitrarily defined (namely, whatever was in the
vector register to the left of the value originally).
*/
/* LE variable byte
Number 1. above:
- For elements 0-7, we shift left by 8 bytes since they're on the right
- For elements 8-15, we need not shift (shift left by zero bytes)
This is accomplished by inverting the bits of the index and AND-ing
with 0x8 (i.e. clearing all bits of the index and inverting bit 60).
*/
dag LE_VBYTE_PERM_VEC = (LVSL ZERO8, (ANDC8 (LI8 8), $Idx));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VBYTE_PERMUTE = (VPERM $S, $S, LE_VBYTE_PERM_VEC);
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VBYTE = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VBYTE_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-7 (8-15 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 8 as we need to shift right by the number of bits, not bytes
- Shift right in the GPR by the calculated value
*/
dag LE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 7), $Idx), 3, 60),
sub_32);
dag LE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD LE_MV_VBYTE, LE_VBYTE_SHIFT),
sub_32);
/* LE variable halfword
Number 1. above:
- For elements 0-3, we shift left by 8 since they're on the right
- For elements 4-7, we need not shift (shift left by zero bytes)
Similarly to the byte pattern, we invert the bits of the index, but we
AND with 0x4 (i.e. clear all bits of the index and invert bit 61).
Of course, the shift is still by 8 bytes, so we must multiply by 2.
*/
dag LE_VHALF_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDC8 (LI8 4), $Idx), 1, 62));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VHALF_PERMUTE = (VPERM $S, $S, LE_VHALF_PERM_VEC);
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VHALF = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VHALF_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-3 (4-7 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 16 as we need to shift right by the number of bits
- Shift right in the GPR by the calculated value
*/
dag LE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 3), $Idx), 4, 59),
sub_32);
dag LE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD LE_MV_VHALF, LE_VHALF_SHIFT),
sub_32);
/* LE variable word
Number 1. above:
- For elements 0-1, we shift left by 8 since they're on the right
- For elements 2-3, we need not shift
*/
dag LE_VWORD_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDC8 (LI8 2), $Idx), 2, 61));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VWORD_PERMUTE = (VPERM $S, $S, LE_VWORD_PERM_VEC);
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
dag LE_MV_VWORD = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VWORD_PERMUTE, VSRC)),
sub_64));
/* Number 4. above:
- Truncate the element number to the range 0-1 (2-3 are symmetrical
and out of range values are truncated accordingly)
- Multiply by 32 as we need to shift right by the number of bits
- Shift right in the GPR by the calculated value
*/
dag LE_VWORD_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 1), $Idx), 5, 58),
sub_32);
dag LE_VARIABLE_WORD = (EXTRACT_SUBREG (SRD LE_MV_VWORD, LE_VWORD_SHIFT),
sub_32);
/* LE variable doubleword
Number 1. above:
- For element 0, we shift left by 8 since it's on the right
- For element 1, we need not shift
*/
dag LE_VDWORD_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDC8 (LI8 1), $Idx), 3, 60));
// Number 2. above:
// - Now that we set up the shift amount, we shift in the VMX register
dag LE_VDWORD_PERMUTE = (VPERM $S, $S, LE_VDWORD_PERM_VEC);
// Number 3. above:
// - The doubleword containing our element is moved to a GPR
// - Number 4. is not needed for the doubleword as the value is 64-bits
dag LE_VARIABLE_DWORD =
(MFVSRD (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS LE_VDWORD_PERMUTE, VSRC)),
sub_64));
/* LE variable float
- Shift the vector to line up the desired element to BE Word 0
- Convert 32-bit float to a 64-bit single precision float
*/
dag LE_VFLOAT_PERM_VEC = (LVSL ZERO8, (RLDICR (XOR8 (LI8 3), $Idx), 2, 61));
dag LE_VFLOAT_PERMUTE = (VPERM $S, $S, LE_VFLOAT_PERM_VEC);
dag LE_VARIABLE_FLOAT = (XSCVSPDPN LE_VFLOAT_PERMUTE);
/* LE variable double
Same as the LE doubleword except there is no move.
*/
dag LE_VDOUBLE_PERMUTE = (VPERM (COPY_TO_REGCLASS $S, VRRC),
(COPY_TO_REGCLASS $S, VRRC),
LE_VDWORD_PERM_VEC);
dag LE_VARIABLE_DOUBLE = (COPY_TO_REGCLASS LE_VDOUBLE_PERMUTE, VSRC);
/* BE variable byte
The algorithm here is the same as the LE variable byte except:
- The shift in the VMX register is by 0/8 for opposite element numbers so
we simply AND the element number with 0x8
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-7
*/
dag BE_VBYTE_PERM_VEC = (LVSL ZERO8, (ANDIo8 $Idx, 8));
dag BE_VBYTE_PERMUTE = (VPERM $S, $S, BE_VBYTE_PERM_VEC);
dag BE_MV_VBYTE = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VBYTE_PERMUTE, VSRC)),
sub_64));
dag BE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 7), $Idx), 3, 60),
sub_32);
dag BE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD BE_MV_VBYTE, BE_VBYTE_SHIFT),
sub_32);
/* BE variable halfword
The algorithm here is the same as the LE variable halfword except:
- The shift in the VMX register is by 0/8 for opposite element numbers so
we simply AND the element number with 0x4 and multiply by 2
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-3
*/
dag BE_VHALF_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDIo8 $Idx, 4), 1, 62));
dag BE_VHALF_PERMUTE = (VPERM $S, $S, BE_VHALF_PERM_VEC);
dag BE_MV_VHALF = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VHALF_PERMUTE, VSRC)),
sub_64));
dag BE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 3), $Idx), 4, 59),
sub_32);
dag BE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD BE_MV_VHALF, BE_VHALF_SHIFT),
sub_32);
/* BE variable word
The algorithm is the same as the LE variable word except:
- The shift in the VMX register happens for opposite element numbers
- The order of elements after the move to GPR is reversed, so we invert
the bits of the index prior to truncating to the range 0-1
*/
dag BE_VWORD_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDIo8 $Idx, 2), 2, 61));
dag BE_VWORD_PERMUTE = (VPERM $S, $S, BE_VWORD_PERM_VEC);
dag BE_MV_VWORD = (MFVSRD
(EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VWORD_PERMUTE, VSRC)),
sub_64));
dag BE_VWORD_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 1), $Idx), 5, 58),
sub_32);
dag BE_VARIABLE_WORD = (EXTRACT_SUBREG (SRD BE_MV_VWORD, BE_VWORD_SHIFT),
sub_32);
/* BE variable doubleword
Same as the LE doubleword except we shift in the VMX register for opposite
element indices.
*/
dag BE_VDWORD_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDIo8 $Idx, 1), 3, 60));
dag BE_VDWORD_PERMUTE = (VPERM $S, $S, BE_VDWORD_PERM_VEC);
dag BE_VARIABLE_DWORD =
(MFVSRD (EXTRACT_SUBREG
(v2i64 (COPY_TO_REGCLASS BE_VDWORD_PERMUTE, VSRC)),
sub_64));
/* BE variable float
- Shift the vector to line up the desired element to BE Word 0
- Convert 32-bit float to a 64-bit single precision float
*/
dag BE_VFLOAT_PERM_VEC = (LVSL ZERO8, (RLDICR $Idx, 2, 61));
dag BE_VFLOAT_PERMUTE = (VPERM $S, $S, BE_VFLOAT_PERM_VEC);
dag BE_VARIABLE_FLOAT = (XSCVSPDPN BE_VFLOAT_PERMUTE);
/* BE variable double
Same as the BE doubleword except there is no move.
*/
dag BE_VDOUBLE_PERMUTE = (VPERM (COPY_TO_REGCLASS $S, VRRC),
(COPY_TO_REGCLASS $S, VRRC),
BE_VDWORD_PERM_VEC);
dag BE_VARIABLE_DOUBLE = (COPY_TO_REGCLASS BE_VDOUBLE_PERMUTE, VSRC);
}
let AddedComplexity = 400 in {
// v4f32 scalar <-> vector conversions (BE)
let Predicates = [IsBigEndian, HasP8Vector] in {
def : Pat<(v4f32 (scalar_to_vector f32:$A)),
(v4f32 (XSCVDPSPN $A))>;
def : Pat<(f32 (vector_extract v4f32:$S, 0)),
(f32 (XSCVSPDPN $S))>;
def : Pat<(f32 (vector_extract v4f32:$S, 1)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 2)),
(f32 (XSCVSPDPN (XXPERMDI $S, $S, 2)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 3)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
def : Pat<(f32 (vector_extract v4f32:$S, i64:$Idx)),
(f32 VectorExtractions.BE_VARIABLE_FLOAT)>;
} // IsBigEndian, HasP8Vector
// Variable index vector_extract for v2f64 does not require P8Vector
let Predicates = [IsBigEndian, HasVSX] in
def : Pat<(f64 (vector_extract v2f64:$S, i64:$Idx)),
(f64 VectorExtractions.BE_VARIABLE_DOUBLE)>;
let Predicates = [IsBigEndian, HasDirectMove] in {
// v16i8 scalar <-> vector conversions (BE)
def : Pat<(v16i8 (scalar_to_vector i32:$A)),
(v16i8 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_BYTE_0, sub_64))>;
def : Pat<(v8i16 (scalar_to_vector i32:$A)),
(v8i16 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_HALF_0, sub_64))>;
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_WORD_0, sub_64))>;
def : Pat<(v2i64 (scalar_to_vector i64:$A)),
(v2i64 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_DWORD_0, sub_64))>;
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 VectorExtractions.LE_BYTE_15)>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 VectorExtractions.LE_BYTE_14)>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 VectorExtractions.LE_BYTE_13)>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 VectorExtractions.LE_BYTE_12)>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 VectorExtractions.LE_BYTE_11)>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 VectorExtractions.LE_BYTE_10)>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 VectorExtractions.LE_BYTE_9)>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 VectorExtractions.LE_BYTE_8)>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 VectorExtractions.LE_BYTE_7)>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 VectorExtractions.LE_BYTE_6)>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 VectorExtractions.LE_BYTE_5)>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 VectorExtractions.LE_BYTE_4)>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 VectorExtractions.LE_BYTE_3)>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 VectorExtractions.LE_BYTE_2)>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 VectorExtractions.LE_BYTE_1)>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 VectorExtractions.LE_BYTE_0)>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_BYTE)>;
// v8i16 scalar <-> vector conversions (BE)
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 VectorExtractions.LE_HALF_7)>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 VectorExtractions.LE_HALF_6)>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 VectorExtractions.LE_HALF_5)>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 VectorExtractions.LE_HALF_4)>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 VectorExtractions.LE_HALF_3)>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 VectorExtractions.LE_HALF_2)>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 VectorExtractions.LE_HALF_1)>;
def : Pat<(i32 (vector_extract v8i16:$S, 7)),
(i32 VectorExtractions.LE_HALF_0)>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_HALF)>;
// v4i32 scalar <-> vector conversions (BE)
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 VectorExtractions.LE_WORD_3)>;
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 VectorExtractions.LE_WORD_1)>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 VectorExtractions.LE_WORD_0)>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 VectorExtractions.BE_VARIABLE_WORD)>;
// v2i64 scalar <-> vector conversions (BE)
def : Pat<(i64 (vector_extract v2i64:$S, 0)),
(i64 VectorExtractions.LE_DWORD_1)>;
def : Pat<(i64 (vector_extract v2i64:$S, 1)),
(i64 VectorExtractions.LE_DWORD_0)>;
def : Pat<(i64 (vector_extract v2i64:$S, i64:$Idx)),
(i64 VectorExtractions.BE_VARIABLE_DWORD)>;
} // IsBigEndian, HasDirectMove
// v4f32 scalar <-> vector conversions (LE)
let Predicates = [IsLittleEndian, HasP8Vector] in {
def : Pat<(v4f32 (scalar_to_vector f32:$A)),
(v4f32 (XXSLDWI (XSCVDPSPN $A), (XSCVDPSPN $A), 1))>;
def : Pat<(f32 (vector_extract v4f32:$S, 0)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 1)),
(f32 (XSCVSPDPN (XXPERMDI $S, $S, 2)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 2)),
(f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
def : Pat<(f32 (vector_extract v4f32:$S, 3)),
(f32 (XSCVSPDPN $S))>;
def : Pat<(f32 (vector_extract v4f32:$S, i64:$Idx)),
(f32 VectorExtractions.LE_VARIABLE_FLOAT)>;
} // IsLittleEndian, HasP8Vector
// Variable index vector_extract for v2f64 does not require P8Vector
let Predicates = [IsLittleEndian, HasVSX] in
def : Pat<(f64 (vector_extract v2f64:$S, i64:$Idx)),
(f64 VectorExtractions.LE_VARIABLE_DOUBLE)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x_be xoaddr:$src)), (LXVW4X xoaddr:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x_be xoaddr:$src)), (LXVD2X xoaddr:$src)>;
let Predicates = [IsLittleEndian, HasDirectMove] in {
// v16i8 scalar <-> vector conversions (LE)
def : Pat<(v16i8 (scalar_to_vector i32:$A)),
(v16i8 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
def : Pat<(v8i16 (scalar_to_vector i32:$A)),
(v8i16 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 MovesToVSR.LE_WORD_0)>;
def : Pat<(v2i64 (scalar_to_vector i64:$A)),
(v2i64 MovesToVSR.LE_DWORD_0)>;
def : Pat<(i32 (vector_extract v16i8:$S, 0)),
(i32 VectorExtractions.LE_BYTE_0)>;
def : Pat<(i32 (vector_extract v16i8:$S, 1)),
(i32 VectorExtractions.LE_BYTE_1)>;
def : Pat<(i32 (vector_extract v16i8:$S, 2)),
(i32 VectorExtractions.LE_BYTE_2)>;
def : Pat<(i32 (vector_extract v16i8:$S, 3)),
(i32 VectorExtractions.LE_BYTE_3)>;
def : Pat<(i32 (vector_extract v16i8:$S, 4)),
(i32 VectorExtractions.LE_BYTE_4)>;
def : Pat<(i32 (vector_extract v16i8:$S, 5)),
(i32 VectorExtractions.LE_BYTE_5)>;
def : Pat<(i32 (vector_extract v16i8:$S, 6)),
(i32 VectorExtractions.LE_BYTE_6)>;
def : Pat<(i32 (vector_extract v16i8:$S, 7)),
(i32 VectorExtractions.LE_BYTE_7)>;
def : Pat<(i32 (vector_extract v16i8:$S, 8)),
(i32 VectorExtractions.LE_BYTE_8)>;
def : Pat<(i32 (vector_extract v16i8:$S, 9)),
(i32 VectorExtractions.LE_BYTE_9)>;
def : Pat<(i32 (vector_extract v16i8:$S, 10)),
(i32 VectorExtractions.LE_BYTE_10)>;
def : Pat<(i32 (vector_extract v16i8:$S, 11)),
(i32 VectorExtractions.LE_BYTE_11)>;
def : Pat<(i32 (vector_extract v16i8:$S, 12)),
(i32 VectorExtractions.LE_BYTE_12)>;
def : Pat<(i32 (vector_extract v16i8:$S, 13)),
(i32 VectorExtractions.LE_BYTE_13)>;
def : Pat<(i32 (vector_extract v16i8:$S, 14)),
(i32 VectorExtractions.LE_BYTE_14)>;
def : Pat<(i32 (vector_extract v16i8:$S, 15)),
(i32 VectorExtractions.LE_BYTE_15)>;
def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_BYTE)>;
// v8i16 scalar <-> vector conversions (LE)
def : Pat<(i32 (vector_extract v8i16:$S, 0)),
(i32 VectorExtractions.LE_HALF_0)>;
def : Pat<(i32 (vector_extract v8i16:$S, 1)),
(i32 VectorExtractions.LE_HALF_1)>;
def : Pat<(i32 (vector_extract v8i16:$S, 2)),
(i32 VectorExtractions.LE_HALF_2)>;
def : Pat<(i32 (vector_extract v8i16:$S, 3)),
(i32 VectorExtractions.LE_HALF_3)>;
def : Pat<(i32 (vector_extract v8i16:$S, 4)),
(i32 VectorExtractions.LE_HALF_4)>;
def : Pat<(i32 (vector_extract v8i16:$S, 5)),
(i32 VectorExtractions.LE_HALF_5)>;
def : Pat<(i32 (vector_extract v8i16:$S, 6)),
(i32 VectorExtractions.LE_HALF_6)>;
def : Pat<(i32 (vector_extract v8i16:$S, 7)),
(i32 VectorExtractions.LE_HALF_7)>;
def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_HALF)>;
// v4i32 scalar <-> vector conversions (LE)
def : Pat<(i32 (vector_extract v4i32:$S, 0)),
(i32 VectorExtractions.LE_WORD_0)>;
def : Pat<(i32 (vector_extract v4i32:$S, 1)),
(i32 VectorExtractions.LE_WORD_1)>;
def : Pat<(i32 (vector_extract v4i32:$S, 2)),
(i32 VectorExtractions.LE_WORD_2)>;
def : Pat<(i32 (vector_extract v4i32:$S, 3)),
(i32 VectorExtractions.LE_WORD_3)>;
def : Pat<(i32 (vector_extract v4i32:$S, i64:$Idx)),
(i32 VectorExtractions.LE_VARIABLE_WORD)>;
// v2i64 scalar <-> vector conversions (LE)
def : Pat<(i64 (vector_extract v2i64:$S, 0)),
(i64 VectorExtractions.LE_DWORD_0)>;
def : Pat<(i64 (vector_extract v2i64:$S, 1)),
(i64 VectorExtractions.LE_DWORD_1)>;
def : Pat<(i64 (vector_extract v2i64:$S, i64:$Idx)),
(i64 VectorExtractions.LE_VARIABLE_DWORD)>;
} // IsLittleEndian, HasDirectMove
let Predicates = [HasDirectMove, HasVSX] in {
// bitconvert f32 -> i32
// (convert to 32-bit fp single, shift right 1 word, move to GPR)
def : Pat<(i32 (bitconvert f32:$S)),
(i32 (MFVSRWZ (EXTRACT_SUBREG
(XXSLDWI (XSCVDPSPN $S),(XSCVDPSPN $S), 3),
sub_64)))>;
// bitconvert i32 -> f32
// (move to FPR, shift left 1 word, convert to 64-bit fp single)
def : Pat<(f32 (bitconvert i32:$A)),
(f32 (XSCVSPDPN
(XXSLDWI MovesToVSR.LE_WORD_1, MovesToVSR.LE_WORD_1, 1)))>;
// bitconvert f64 -> i64
// (move to GPR, nothing else needed)
def : Pat<(i64 (bitconvert f64:$S)),
(i64 (MFVSRD $S))>;
// bitconvert i64 -> f64
// (move to FPR, nothing else needed)
def : Pat<(f64 (bitconvert i64:$S)),
(f64 (MTVSRD $S))>;
}
// Materialize a zero-vector of long long
def : Pat<(v2i64 immAllZerosV),
(v2i64 (XXLXORz))>;
}
def AlignValues {
dag F32_TO_BE_WORD1 = (v4f32 (XXSLDWI (XSCVDPSPN $B), (XSCVDPSPN $B), 3));
dag I32_TO_BE_WORD1 = (COPY_TO_REGCLASS (MTVSRWZ $B), VSRC);
}
// The following VSX instructions were introduced in Power ISA 3.0
def HasP9Vector : Predicate<"PPCSubTarget->hasP9Vector()">;
let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vrrc:$vB),
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
// [PO VRT XO VRB XO RO], Round to Odd version of [PO VRT XO VRB XO /]
class X_VT5_XO5_VB5_Ro<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_XO5_VB5<opcode, xo2, xo, opc, pattern>, isDOT;
// [PO VRT XO VRB XO /], but the VRB is only used the left 64 bits (or less),
// So we use different operand class for VRB
class X_VT5_XO5_VB5_TyVB<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
RegisterOperand vbtype, list<dag> pattern>
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vbtype:$vB),
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
let UseVSXReg = 1 in {
// [PO T XO B XO BX /]
class XX2_RT5_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
list<dag> pattern>
: XX2_RD5_XO5_RS6<opcode, xo2, xo, (outs g8rc:$rT), (ins vsfrc:$XB),
!strconcat(opc, " $rT, $XB"), IIC_VecFP, pattern>;
// [PO T XO B XO BX TX]
class XX2_XT6_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX2_RD6_XO5_RS6<opcode, xo2, xo, (outs vtype:$XT), (ins vtype:$XB),
!strconcat(opc, " $XT, $XB"), IIC_VecFP, pattern>;
// [PO T A B XO AX BX TX], src and dest register use different operand class
class XX3_XT5_XA5_XB5<bits<6> opcode, bits<8> xo, string opc,
RegisterOperand xty, RegisterOperand aty, RegisterOperand bty,
InstrItinClass itin, list<dag> pattern>
: XX3Form<opcode, xo, (outs xty:$XT), (ins aty:$XA, bty:$XB),
!strconcat(opc, " $XT, $XA, $XB"), itin, pattern>;
} // UseVSXReg = 1
// [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: XForm_1<opcode, xo, (outs vrrc:$vT), (ins vrrc:$vA, vrrc:$vB),
!strconcat(opc, " $vT, $vA, $vB"), IIC_VecFP, pattern>;
// [PO VRT VRA VRB XO RO], Round to Odd version of [PO VRT VRA VRB XO /]
class X_VT5_VA5_VB5_Ro<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: X_VT5_VA5_VB5<opcode, xo, opc, pattern>, isDOT;
//===--------------------------------------------------------------------===//
// Quad-Precision Scalar Move Instructions:
// Copy Sign
def XSCPSGNQP : X_VT5_VA5_VB5<63, 100, "xscpsgnqp", []>;
// Absolute/Negative-Absolute/Negate
def XSABSQP : X_VT5_XO5_VB5<63, 0, 804, "xsabsqp" , []>;
def XSNABSQP : X_VT5_XO5_VB5<63, 8, 804, "xsnabsqp", []>;
def XSNEGQP : X_VT5_XO5_VB5<63, 16, 804, "xsnegqp" , []>;
//===--------------------------------------------------------------------===//
// Quad-Precision Scalar Floating-Point Arithmetic Instructions:
// Add/Divide/Multiply/Subtract
def XSADDQP : X_VT5_VA5_VB5 <63, 4, "xsaddqp" , []>;
def XSADDQPO : X_VT5_VA5_VB5_Ro<63, 4, "xsaddqpo", []>;
def XSDIVQP : X_VT5_VA5_VB5 <63, 548, "xsdivqp" , []>;
def XSDIVQPO : X_VT5_VA5_VB5_Ro<63, 548, "xsdivqpo", []>;
def XSMULQP : X_VT5_VA5_VB5 <63, 36, "xsmulqp" , []>;
def XSMULQPO : X_VT5_VA5_VB5_Ro<63, 36, "xsmulqpo", []>;
def XSSUBQP : X_VT5_VA5_VB5 <63, 516, "xssubqp" , []>;
def XSSUBQPO : X_VT5_VA5_VB5_Ro<63, 516, "xssubqpo", []>;
// Square-Root
def XSSQRTQP : X_VT5_XO5_VB5 <63, 27, 804, "xssqrtqp" , []>;
def XSSQRTQPO : X_VT5_XO5_VB5_Ro<63, 27, 804, "xssqrtqpo", []>;
// (Negative) Multiply-{Add/Subtract}
def XSMADDQP : X_VT5_VA5_VB5 <63, 388, "xsmaddqp" , []>;
def XSMADDQPO : X_VT5_VA5_VB5_Ro<63, 388, "xsmaddqpo" , []>;
def XSMSUBQP : X_VT5_VA5_VB5 <63, 420, "xsmsubqp" , []>;
def XSMSUBQPO : X_VT5_VA5_VB5_Ro<63, 420, "xsmsubqpo" , []>;
def XSNMADDQP : X_VT5_VA5_VB5 <63, 452, "xsnmaddqp" , []>;
def XSNMADDQPO: X_VT5_VA5_VB5_Ro<63, 452, "xsnmaddqpo", []>;
def XSNMSUBQP : X_VT5_VA5_VB5 <63, 484, "xsnmsubqp" , []>;
def XSNMSUBQPO: X_VT5_VA5_VB5_Ro<63, 484, "xsnmsubqpo", []>;
//===--------------------------------------------------------------------===//
// Quad/Double-Precision Compare Instructions:
// [PO BF // VRA VRB XO /]
class X_BF3_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
list<dag> pattern>
: XForm_17<opcode, xo, (outs crrc:$crD), (ins vrrc:$VA, vrrc:$VB),
!strconcat(opc, " $crD, $VA, $VB"), IIC_FPCompare> {
let Pattern = pattern;
}
// QP Compare Ordered/Unordered
def XSCMPOQP : X_BF3_VA5_VB5<63, 132, "xscmpoqp", []>;
def XSCMPUQP : X_BF3_VA5_VB5<63, 644, "xscmpuqp", []>;
// DP/QP Compare Exponents
def XSCMPEXPDP : XX3Form_1<60, 59,
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
"xscmpexpdp $crD, $XA, $XB", IIC_FPCompare, []>,
UseVSXReg;
def XSCMPEXPQP : X_BF3_VA5_VB5<63, 164, "xscmpexpqp", []>;
// DP Compare ==, >=, >, !=
// Use vsrc for XT, because the entire register of XT is set.
// XT.dword[1] = 0x0000_0000_0000_0000
def XSCMPEQDP : XX3_XT5_XA5_XB5<60, 3, "xscmpeqdp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
def XSCMPGEDP : XX3_XT5_XA5_XB5<60, 19, "xscmpgedp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
def XSCMPGTDP : XX3_XT5_XA5_XB5<60, 11, "xscmpgtdp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
def XSCMPNEDP : XX3_XT5_XA5_XB5<60, 27, "xscmpnedp", vsrc, vsfrc, vsfrc,
IIC_FPCompare, []>;
let UseVSXReg = 1 in {
// Vector Compare Not Equal
def XVCMPNEDP : XX3Form_Rc<60, 123,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcmpnedp $XT, $XA, $XB", IIC_VecFPCompare, []>;
let Defs = [CR6] in
def XVCMPNEDPo : XX3Form_Rc<60, 123,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcmpnedp. $XT, $XA, $XB", IIC_VecFPCompare, []>,
isDOT;
def XVCMPNESP : XX3Form_Rc<60, 91,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcmpnesp $XT, $XA, $XB", IIC_VecFPCompare, []>;
let Defs = [CR6] in
def XVCMPNESPo : XX3Form_Rc<60, 91,
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
"xvcmpnesp. $XT, $XA, $XB", IIC_VecFPCompare, []>,
isDOT;
} // UseVSXReg = 1
//===--------------------------------------------------------------------===//
// Quad-Precision Floating-Point Conversion Instructions:
// Convert DP -> QP
def XSCVDPQP : X_VT5_XO5_VB5_TyVB<63, 22, 836, "xscvdpqp", vfrc, []>;
// Round & Convert QP -> DP (dword[1] is set to zero)
def XSCVQPDP : X_VT5_XO5_VB5 <63, 20, 836, "xscvqpdp" , []>;
def XSCVQPDPO : X_VT5_XO5_VB5_Ro<63, 20, 836, "xscvqpdpo", []>;
// Truncate & Convert QP -> (Un)Signed (D)Word (dword[1] is set to zero)
def XSCVQPSDZ : X_VT5_XO5_VB5<63, 25, 836, "xscvqpsdz", []>;
def XSCVQPSWZ : X_VT5_XO5_VB5<63, 9, 836, "xscvqpswz", []>;
def XSCVQPUDZ : X_VT5_XO5_VB5<63, 17, 836, "xscvqpudz", []>;
def XSCVQPUWZ : X_VT5_XO5_VB5<63, 1, 836, "xscvqpuwz", []>;
// Convert (Un)Signed DWord -> QP
def XSCVSDQP : X_VT5_XO5_VB5_TyVB<63, 10, 836, "xscvsdqp", vfrc, []>;
def XSCVUDQP : X_VT5_XO5_VB5_TyVB<63, 2, 836, "xscvudqp", vfrc, []>;
let UseVSXReg = 1 in {
//===--------------------------------------------------------------------===//
// Round to Floating-Point Integer Instructions
// (Round &) Convert DP <-> HP
// Note! xscvdphp's src and dest register both use the left 64 bits, so we use
// vsfrc for src and dest register. xscvhpdp's src only use the left 16 bits,
// but we still use vsfrc for it.
def XSCVDPHP : XX2_XT6_XO5_XB6<60, 17, 347, "xscvdphp", vsfrc, []>;
def XSCVHPDP : XX2_XT6_XO5_XB6<60, 16, 347, "xscvhpdp", vsfrc, []>;
// Vector HP -> SP
def XVCVHPSP : XX2_XT6_XO5_XB6<60, 24, 475, "xvcvhpsp", vsrc, []>;
def XVCVSPHP : XX2_XT6_XO5_XB6<60, 25, 475, "xvcvsphp", vsrc,
[(set v4f32:$XT,
(int_ppc_vsx_xvcvsphp v4f32:$XB))]>;
} // UseVSXReg = 1
// Pattern for matching Vector HP -> Vector SP intrinsic. Defined as a
// seperate pattern so that it can convert the input register class from
// VRRC(v8i16) to VSRC.
def : Pat<(v4f32 (int_ppc_vsx_xvcvhpsp v8i16:$A)),
(v4f32 (XVCVHPSP (COPY_TO_REGCLASS $A, VSRC)))>;
class Z23_VT5_R1_VB5_RMC2_EX1<bits<6> opcode, bits<8> xo, bit ex, string opc,
list<dag> pattern>
: Z23Form_1<opcode, xo,
(outs vrrc:$vT), (ins u1imm:$r, vrrc:$vB, u2imm:$rmc),
!strconcat(opc, " $r, $vT, $vB, $rmc"), IIC_VecFP, pattern> {
let RC = ex;
}
// Round to Quad-Precision Integer [with Inexact]
def XSRQPI : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 0, "xsrqpi" , []>;
def XSRQPIX : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 1, "xsrqpix", []>;
// Round Quad-Precision to Double-Extended Precision (fp80)
def XSRQPXP : Z23_VT5_R1_VB5_RMC2_EX1<63, 37, 0, "xsrqpxp", []>;
//===--------------------------------------------------------------------===//
// Insert/Extract Instructions
// Insert Exponent DP/QP
// XT NOTE: XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU
def XSIEXPDP : XX1Form <60, 918, (outs vsrc:$XT), (ins g8rc:$rA, g8rc:$rB),
"xsiexpdp $XT, $rA, $rB", IIC_VecFP, []>, UseVSXReg;
// vB NOTE: only vB.dword[0] is used, that's why we don't use
// X_VT5_VA5_VB5 form
def XSIEXPQP : XForm_18<63, 868, (outs vrrc:$vT), (ins vrrc:$vA, vsfrc:$vB),
"xsiexpqp $vT, $vA, $vB", IIC_VecFP, []>;
// Extract Exponent/Significand DP/QP
def XSXEXPDP : XX2_RT5_XO5_XB6<60, 0, 347, "xsxexpdp", []>;
def XSXSIGDP : XX2_RT5_XO5_XB6<60, 1, 347, "xsxsigdp", []>;
def XSXEXPQP : X_VT5_XO5_VB5 <63, 2, 804, "xsxexpqp", []>;
def XSXSIGQP : X_VT5_XO5_VB5 <63, 18, 804, "xsxsigqp", []>;
// Vector Insert Word
let UseVSXReg = 1 in {
// XB NOTE: Only XB.dword[1] is used, but we use vsrc on XB.
def XXINSERTW :
XX2_RD6_UIM5_RS6<60, 181, (outs vsrc:$XT),
(ins vsrc:$XTi, vsrc:$XB, u4imm:$UIM),
"xxinsertw $XT, $XB, $UIM", IIC_VecFP,
[(set v4i32:$XT, (PPCxxinsert v4i32:$XTi, v4i32:$XB,
imm32SExt16:$UIM))]>,
RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">;
// Vector Extract Unsigned Word
def XXEXTRACTUW : XX2_RD6_UIM5_RS6<60, 165,
(outs vsfrc:$XT), (ins vsrc:$XB, u4imm:$UIMM),
"xxextractuw $XT, $XB, $UIMM", IIC_VecFP, []>;
} // UseVSXReg = 1
// Vector Insert Exponent DP/SP
def XVIEXPDP : XX3_XT5_XA5_XB5<60, 248, "xviexpdp", vsrc, vsrc, vsrc,
IIC_VecFP, [(set v2f64: $XT,(int_ppc_vsx_xviexpdp v2i64:$XA, v2i64:$XB))]>;
def XVIEXPSP : XX3_XT5_XA5_XB5<60, 216, "xviexpsp", vsrc, vsrc, vsrc,
IIC_VecFP, [(set v4f32: $XT,(int_ppc_vsx_xviexpsp v4i32:$XA, v4i32:$XB))]>;
// Vector Extract Exponent/Significand DP/SP
def XVXEXPDP : XX2_XT6_XO5_XB6<60, 0, 475, "xvxexpdp", vsrc,
[(set v2i64: $XT,
(int_ppc_vsx_xvxexpdp v2f64:$XB))]>;
def XVXEXPSP : XX2_XT6_XO5_XB6<60, 8, 475, "xvxexpsp", vsrc,
[(set v4i32: $XT,
(int_ppc_vsx_xvxexpsp v4f32:$XB))]>;
def XVXSIGDP : XX2_XT6_XO5_XB6<60, 1, 475, "xvxsigdp", vsrc,
[(set v2i64: $XT,
(int_ppc_vsx_xvxsigdp v2f64:$XB))]>;
def XVXSIGSP : XX2_XT6_XO5_XB6<60, 9, 475, "xvxsigsp", vsrc,
[(set v4i32: $XT,
(int_ppc_vsx_xvxsigsp v4f32:$XB))]>;
let AddedComplexity = 400, Predicates = [HasP9Vector] in {
// Extra patterns expanding to vector Extract Word/Insert Word
def : Pat<(v4i32 (int_ppc_vsx_xxinsertw v4i32:$A, v2i64:$B, imm:$IMM)),
(v4i32 (XXINSERTW $A, $B, imm:$IMM))>;
def : Pat<(v2i64 (int_ppc_vsx_xxextractuw v2i64:$A, imm:$IMM)),
(v2i64 (COPY_TO_REGCLASS (XXEXTRACTUW $A, imm:$IMM), VSRC))>;
} // AddedComplexity = 400, HasP9Vector
//===--------------------------------------------------------------------===//
// Test Data Class SP/DP/QP
let UseVSXReg = 1 in {
def XSTSTDCSP : XX2_BF3_DCMX7_RS6<60, 298,
(outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
"xststdcsp $BF, $XB, $DCMX", IIC_VecFP, []>;
def XSTSTDCDP : XX2_BF3_DCMX7_RS6<60, 362,
(outs crrc:$BF), (ins u7imm:$DCMX, vsfrc:$XB),
"xststdcdp $BF, $XB, $DCMX", IIC_VecFP, []>;
} // UseVSXReg = 1
def XSTSTDCQP : X_BF3_DCMX7_RS5 <63, 708,
(outs crrc:$BF), (ins u7imm:$DCMX, vrrc:$vB),
"xststdcqp $BF, $vB, $DCMX", IIC_VecFP, []>;
// Vector Test Data Class SP/DP
let UseVSXReg = 1 in {
def XVTSTDCSP : XX2_RD6_DCMX7_RS6<60, 13, 5,
(outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
"xvtstdcsp $XT, $XB, $DCMX", IIC_VecFP,
[(set v4i32: $XT,
(int_ppc_vsx_xvtstdcsp v4f32:$XB, imm:$DCMX))]>;
def XVTSTDCDP : XX2_RD6_DCMX7_RS6<60, 15, 5,
(outs vsrc:$XT), (ins u7imm:$DCMX, vsrc:$XB),
"xvtstdcdp $XT, $XB, $DCMX", IIC_VecFP,
[(set v2i64: $XT,
(int_ppc_vsx_xvtstdcdp v2f64:$XB, imm:$DCMX))]>;
} // UseVSXReg = 1
//===--------------------------------------------------------------------===//
// Maximum/Minimum Type-C/Type-J DP
// XT.dword[1] = 0xUUUU_UUUU_UUUU_UUUU, so we use vsrc for XT
def XSMAXCDP : XX3_XT5_XA5_XB5<60, 128, "xsmaxcdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
def XSMAXJDP : XX3_XT5_XA5_XB5<60, 144, "xsmaxjdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
def XSMINCDP : XX3_XT5_XA5_XB5<60, 136, "xsmincdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
def XSMINJDP : XX3_XT5_XA5_XB5<60, 152, "xsminjdp", vsrc, vsfrc, vsfrc,
IIC_VecFP, []>;
//===--------------------------------------------------------------------===//
// Vector Byte-Reverse H/W/D/Q Word
def XXBRH : XX2_XT6_XO5_XB6<60, 7, 475, "xxbrh", vsrc, []>;
def XXBRW : XX2_XT6_XO5_XB6<60, 15, 475, "xxbrw", vsrc, []>;
def XXBRD : XX2_XT6_XO5_XB6<60, 23, 475, "xxbrd", vsrc, []>;
def XXBRQ : XX2_XT6_XO5_XB6<60, 31, 475, "xxbrq", vsrc, []>;
// Vector Permute
def XXPERM : XX3_XT5_XA5_XB5<60, 26, "xxperm" , vsrc, vsrc, vsrc,
IIC_VecPerm, []>;
def XXPERMR : XX3_XT5_XA5_XB5<60, 58, "xxpermr", vsrc, vsrc, vsrc,
IIC_VecPerm, []>;
// Vector Splat Immediate Byte
def XXSPLTIB : X_RD6_IMM8<60, 360, (outs vsrc:$XT), (ins u8imm:$IMM8),
"xxspltib $XT, $IMM8", IIC_VecPerm, []>, UseVSXReg;
//===--------------------------------------------------------------------===//
// Vector/Scalar Load/Store Instructions
// When adding new D-Form loads/stores, be sure to update the ImmToIdxMap in
// PPCRegisterInfo::PPCRegisterInfo and maybe save yourself some debugging.
let mayLoad = 1, mayStore = 0 in {
// Load Vector
def LXV : DQ_RD6_RS5_DQ12<61, 1, (outs vsrc:$XT), (ins memrix16:$src),
"lxv $XT, $src", IIC_LdStLFD, []>, UseVSXReg;
// Load DWord
def LXSD : DSForm_1<57, 2, (outs vfrc:$vD), (ins memrix:$src),
"lxsd $vD, $src", IIC_LdStLFD, []>;
// Load SP from src, convert it to DP, and place in dword[0]
def LXSSP : DSForm_1<57, 3, (outs vfrc:$vD), (ins memrix:$src),
"lxssp $vD, $src", IIC_LdStLFD, []>;
// [PO T RA RB XO TX] almost equal to [PO S RA RB XO SX], but has different
// "out" and "in" dag
class X_XT6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form<opcode, xo, (outs vtype:$XT), (ins memrr:$src),
!strconcat(opc, " $XT, $src"), IIC_LdStLFD, pattern>, UseVSXReg;
// Load as Integer Byte/Halfword & Zero Indexed
def LXSIBZX : X_XT6_RA5_RB5<31, 781, "lxsibzx", vsfrc,
[(set f64:$XT, (PPClxsizx xoaddr:$src, 1))]>;
def LXSIHZX : X_XT6_RA5_RB5<31, 813, "lxsihzx", vsfrc,
[(set f64:$XT, (PPClxsizx xoaddr:$src, 2))]>;
// Load Vector Halfword*8/Byte*16 Indexed
def LXVH8X : X_XT6_RA5_RB5<31, 812, "lxvh8x" , vsrc, []>;
def LXVB16X : X_XT6_RA5_RB5<31, 876, "lxvb16x", vsrc, []>;
// Load Vector Indexed
def LXVX : X_XT6_RA5_RB5<31, 268, "lxvx" , vsrc,
[(set v2f64:$XT, (load xoaddr:$src))]>;
// Load Vector (Left-justified) with Length
def LXVL : XX1Form<31, 269, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvl $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvl addr:$src, i64:$rB))]>,
UseVSXReg;
def LXVLL : XX1Form<31,301, (outs vsrc:$XT), (ins memr:$src, g8rc:$rB),
"lxvll $XT, $src, $rB", IIC_LdStLoad,
[(set v4i32:$XT, (int_ppc_vsx_lxvll addr:$src, i64:$rB))]>,
UseVSXReg;
// Load Vector Word & Splat Indexed
def LXVWSX : X_XT6_RA5_RB5<31, 364, "lxvwsx" , vsrc, []>;
} // mayLoad
// When adding new D-Form loads/stores, be sure to update the ImmToIdxMap in
// PPCRegisterInfo::PPCRegisterInfo and maybe save yourself some debugging.
let mayStore = 1, mayLoad = 0 in {
// Store Vector
def STXV : DQ_RD6_RS5_DQ12<61, 5, (outs), (ins vsrc:$XT, memrix16:$dst),
"stxv $XT, $dst", IIC_LdStSTFD, []>, UseVSXReg;
// Store DWord
def STXSD : DSForm_1<61, 2, (outs), (ins vfrc:$vS, memrix:$dst),
"stxsd $vS, $dst", IIC_LdStSTFD, []>;
// Convert DP of dword[0] to SP, and Store to dst
def STXSSP : DSForm_1<61, 3, (outs), (ins vfrc:$vS, memrix:$dst),
"stxssp $vS, $dst", IIC_LdStSTFD, []>;
// [PO S RA RB XO SX]
class X_XS6_RA5_RB5<bits<6> opcode, bits<10> xo, string opc,
RegisterOperand vtype, list<dag> pattern>
: XX1Form<opcode, xo, (outs), (ins vtype:$XT, memrr:$dst),
!strconcat(opc, " $XT, $dst"), IIC_LdStSTFD, pattern>, UseVSXReg;
// Store as Integer Byte/Halfword Indexed
def STXSIBX : X_XS6_RA5_RB5<31, 909, "stxsibx" , vsfrc,
[(PPCstxsix f64:$XT, xoaddr:$dst, 1)]>;
def STXSIHX : X_XS6_RA5_RB5<31, 941, "stxsihx" , vsfrc,
[(PPCstxsix f64:$XT, xoaddr:$dst, 2)]>;
let isCodeGenOnly = 1 in {
def STXSIBXv : X_XS6_RA5_RB5<31, 909, "stxsibx" , vrrc, []>;
def STXSIHXv : X_XS6_RA5_RB5<31, 941, "stxsihx" , vrrc, []>;
}
// Store Vector Halfword*8/Byte*16 Indexed
def STXVH8X : X_XS6_RA5_RB5<31, 940, "stxvh8x" , vsrc, []>;
def STXVB16X : X_XS6_RA5_RB5<31, 1004, "stxvb16x", vsrc, []>;
// Store Vector Indexed
def STXVX : X_XS6_RA5_RB5<31, 396, "stxvx" , vsrc,
[(store v2f64:$XT, xoaddr:$dst)]>;
// Store Vector (Left-justified) with Length
def STXVL : XX1Form<31, 397, (outs), (ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvl $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvl v4i32:$XT, addr:$dst, i64:$rB)]>,
UseVSXReg;
def STXVLL : XX1Form<31, 429, (outs), (ins vsrc:$XT, memr:$dst, g8rc:$rB),
"stxvll $XT, $dst, $rB", IIC_LdStLoad,
[(int_ppc_vsx_stxvll v4i32:$XT, addr:$dst, i64:$rB)]>,
UseVSXReg;
} // mayStore
// Patterns for which instructions from ISA 3.0 are a better match
let Predicates = [IsLittleEndian, HasP9Vector] in {
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 0))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 12)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 1))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 2))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 3))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 0)))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 0)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 12))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 1)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 8))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 2)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 4))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 3)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 0))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 0)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 12))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 1)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 8))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 2)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 4))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 3)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 0))>;
} // IsLittleEndian, HasP9Vector
let Predicates = [IsBigEndian, HasP9Vector] in {
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 0))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 0)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 1))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 4)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 2))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 8)))>;
def : Pat<(f32 (PPCfcfidus (PPCmtvsrz (i32 (extractelt v4i32:$A, 3))))),
(f32 (XSCVUXDSP (XXEXTRACTUW $A, 12)))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 0)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 0))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 1)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 4))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 2)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 8))>;
def : Pat<(v4i32 (insertelt v4i32:$A, i32:$B, 3)),
(v4i32 (XXINSERTW v4i32:$A, AlignValues.I32_TO_BE_WORD1, 12))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 0)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 0))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 1)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 4))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 2)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 8))>;
def : Pat<(v4f32 (insertelt v4f32:$A, f32:$B, 3)),
(v4f32 (XXINSERTW v4f32:$A, AlignValues.F32_TO_BE_WORD1, 12))>;
} // IsLittleEndian, HasP9Vector
def : Pat<(v2f64 (load xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v2i64 (load xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4f32 (load xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4i32 (load xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x xoaddr:$src)), (LXVX xoaddr:$src)>;
def : Pat<(store v2f64:$rS, xoaddr:$dst), (STXVX $rS, xoaddr:$dst)>;
def : Pat<(store v2i64:$rS, xoaddr:$dst), (STXVX $rS, xoaddr:$dst)>;
def : Pat<(store v4f32:$rS, xoaddr:$dst), (STXVX $rS, xoaddr:$dst)>;
def : Pat<(store v4i32:$rS, xoaddr:$dst), (STXVX $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, xoaddr:$dst),
(STXVX $rS, xoaddr:$dst)>;
def : Pat<(v4i32 (scalar_to_vector (i32 (load xoaddr:$src)))),
(v4i32 (LXVWSX xoaddr:$src))>;
def : Pat<(v4f32 (scalar_to_vector (f32 (load xoaddr:$src)))),
(v4f32 (LXVWSX xoaddr:$src))>;
def : Pat<(v4f32 (scalar_to_vector (f32 (fpround (extloadf32 xoaddr:$src))))),
(v4f32 (LXVWSX xoaddr:$src))>;
// Build vectors from i8 loads
def : Pat<(v16i8 (scalar_to_vector ScalarLoads.Li8)),
(v16i8 (VSPLTBs 7, (LXSIBZX xoaddr:$src)))>;
def : Pat<(v8i16 (scalar_to_vector ScalarLoads.ZELi8)),
(v8i16 (VSPLTHs 3, (LXSIBZX xoaddr:$src)))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.ZELi8)),
(v4i32 (XXSPLTWs (LXSIBZX xoaddr:$src), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.ZELi8i64)),
(v2i64 (XXPERMDIs (LXSIBZX xoaddr:$src), 0))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.SELi8)),
(v4i32 (XXSPLTWs (VEXTSB2Ws (LXSIBZX xoaddr:$src)), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.SELi8i64)),
(v2i64 (XXPERMDIs (VEXTSB2Ds (LXSIBZX xoaddr:$src)), 0))>;
// Build vectors from i16 loads
def : Pat<(v8i16 (scalar_to_vector ScalarLoads.Li16)),
(v8i16 (VSPLTHs 3, (LXSIHZX xoaddr:$src)))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.ZELi16)),
(v4i32 (XXSPLTWs (LXSIHZX xoaddr:$src), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.ZELi16i64)),
(v2i64 (XXPERMDIs (LXSIHZX xoaddr:$src), 0))>;
def : Pat<(v4i32 (scalar_to_vector ScalarLoads.SELi16)),
(v4i32 (XXSPLTWs (VEXTSH2Ws (LXSIHZX xoaddr:$src)), 1))>;
def : Pat<(v2i64 (scalar_to_vector ScalarLoads.SELi16i64)),
(v2i64 (XXPERMDIs (VEXTSH2Ds (LXSIHZX xoaddr:$src)), 0))>;
let Predicates = [IsBigEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 9), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 10), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 11), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 12), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 13), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 14), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 15), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv $S, xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 1), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 2), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 3), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 4), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 5), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 6), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 7), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 8), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 10), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 12), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 14), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv $S, xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 2), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 4), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 6), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 8), xoaddr:$dst)>;
} // IsBigEndian, HasP9Vector
let Predicates = [IsLittleEndian, HasP9Vector] in {
// Scalar stores of i8
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 0)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 8), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 1)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 7), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 2)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 6), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 3)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 5), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 4)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 4), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 5)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 3), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 6)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 2), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 7)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 1), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 8)), xoaddr:$dst),
(STXSIBXv $S, xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 9)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 15), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 10)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 14), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 11)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 13), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 12)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 12), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 13)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 11), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 14)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 10), xoaddr:$dst)>;
def : Pat<(truncstorei8 (i32 (vector_extract v16i8:$S, 15)), xoaddr:$dst),
(STXSIBXv (VSLDOI $S, $S, 9), xoaddr:$dst)>;
// Scalar stores of i16
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 0)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 8), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 1)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 6), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 2)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 4), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 3)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 2), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 4)), xoaddr:$dst),
(STXSIHXv $S, xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 5)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 14), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 6)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 12), xoaddr:$dst)>;
def : Pat<(truncstorei16 (i32 (vector_extract v8i16:$S, 7)), xoaddr:$dst),
(STXSIHXv (VSLDOI $S, $S, 10), xoaddr:$dst)>;
} // IsLittleEndian, HasP9Vector
// Vector sign extensions
def : Pat<(f64 (PPCVexts f64:$A, 1)),
(f64 (COPY_TO_REGCLASS (VEXTSB2Ds $A), VSFRC))>;
def : Pat<(f64 (PPCVexts f64:$A, 2)),
(f64 (COPY_TO_REGCLASS (VEXTSH2Ds $A), VSFRC))>;
let isPseudo = 1 in {
def DFLOADf32 : Pseudo<(outs vssrc:$XT), (ins memrix:$src),
"#DFLOADf32",
[(set f32:$XT, (load iaddr:$src))]>;
def DFLOADf64 : Pseudo<(outs vsfrc:$XT), (ins memrix:$src),
"#DFLOADf64",
[(set f64:$XT, (load iaddr:$src))]>;
def DFSTOREf32 : Pseudo<(outs), (ins vssrc:$XT, memrix:$dst),
"#DFSTOREf32",
[(store f32:$XT, iaddr:$dst)]>;
def DFSTOREf64 : Pseudo<(outs), (ins vsfrc:$XT, memrix:$dst),
"#DFSTOREf64",
[(store f64:$XT, iaddr:$dst)]>;
}
def : Pat<(f64 (extloadf32 iaddr:$src)),
(COPY_TO_REGCLASS (DFLOADf32 iaddr:$src), VSFRC)>;
def : Pat<(f32 (fpround (extloadf32 iaddr:$src))),
(f32 (DFLOADf32 iaddr:$src))>;
} // end HasP9Vector, AddedComplexity
// Integer extend helper dags 32 -> 64
def AnyExts {
dag A = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32);
dag B = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $B, sub_32);
dag C = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $C, sub_32);
dag D = (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $D, sub_32);
}
def DblToFlt {
dag A0 = (f32 (fpround (f64 (extractelt v2f64:$A, 0))));
dag A1 = (f32 (fpround (f64 (extractelt v2f64:$A, 1))));
dag B0 = (f32 (fpround (f64 (extractelt v2f64:$B, 0))));
dag B1 = (f32 (fpround (f64 (extractelt v2f64:$B, 1))));
}
def FltToIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToUIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToLongLoad {
dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToULongLoad {
dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (extloadf32 xoaddr:$A)))));
}
def FltToLong {
dag A = (i64 (PPCmfvsr (PPCfctidz (fpextend f32:$A))));
}
def FltToULong {
dag A = (i64 (PPCmfvsr (PPCfctiduz (fpextend f32:$A))));
}
def DblToInt {
dag A = (i32 (PPCmfvsr (f64 (PPCfctiwz f64:$A))));
}
def DblToUInt {
dag A = (i32 (PPCmfvsr (f64 (PPCfctiwuz f64:$A))));
}
def DblToLong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctidz f64:$A))));
}
def DblToULong {
dag A = (i64 (PPCmfvsr (f64 (PPCfctiduz f64:$A))));
}
def DblToIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (load xoaddr:$A)))));
}
def DblToUIntLoad {
dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (load xoaddr:$A)))));
}
def DblToLongLoad {
dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (load xoaddr:$A)))));
}
def DblToULongLoad {
dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (load xoaddr:$A)))));
}
// FP merge dags (for f32 -> v4f32)
def MrgFP {
dag AC = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $A, VSRC),
(COPY_TO_REGCLASS $C, VSRC), 0));
dag BD = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $B, VSRC),
(COPY_TO_REGCLASS $D, VSRC), 0));
dag ABhToFlt = (XVCVDPSP (XXPERMDI $A, $B, 0));
dag ABlToFlt = (XVCVDPSP (XXPERMDI $A, $B, 3));
dag BAhToFlt = (XVCVDPSP (XXPERMDI $B, $A, 0));
dag BAlToFlt = (XVCVDPSP (XXPERMDI $B, $A, 3));
}
// Patterns for BUILD_VECTOR nodes.
def NoP9Vector : Predicate<"!PPCSubTarget->hasP9Vector()">;
let AddedComplexity = 400 in {
let Predicates = [HasVSX] in {
// Build vectors of floating point converted to i32.
def : Pat<(v4i32 (build_vector DblToInt.A, DblToInt.A,
DblToInt.A, DblToInt.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS (XSCVDPSXWS $A), VSRC), 1))>;
def : Pat<(v4i32 (build_vector DblToUInt.A, DblToUInt.A,
DblToUInt.A, DblToUInt.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS (XSCVDPUXWS $A), VSRC), 1))>;
def : Pat<(v2i64 (build_vector DblToLong.A, DblToLong.A)),
(v2i64 (XXPERMDI (COPY_TO_REGCLASS (XSCVDPSXDS $A), VSRC),
(COPY_TO_REGCLASS (XSCVDPSXDS $A), VSRC), 0))>;
def : Pat<(v2i64 (build_vector DblToULong.A, DblToULong.A)),
(v2i64 (XXPERMDI (COPY_TO_REGCLASS (XSCVDPUXDS $A), VSRC),
(COPY_TO_REGCLASS (XSCVDPUXDS $A), VSRC), 0))>;
def : Pat<(v4i32 (scalar_to_vector FltToIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWSs (LXSSPX xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector FltToUIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWSs (LXSSPX xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4f32 (build_vector f32:$A, f32:$A, f32:$A, f32:$A)),
(v4f32 (XXSPLTW (v4f32 (XSCVDPSPN $A)), 0))>;
// Build vectors of floating point converted to i64.
def : Pat<(v2i64 (build_vector FltToLong.A, FltToLong.A)),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (XSCVDPSXDSs $A), VSFRC), 0))>;
def : Pat<(v2i64 (build_vector FltToULong.A, FltToULong.A)),
(v2i64 (XXPERMDIs
(COPY_TO_REGCLASS (XSCVDPUXDSs $A), VSFRC), 0))>;
def : Pat<(v2i64 (scalar_to_vector DblToLongLoad.A)),
(v2i64 (XVCVDPSXDS (LXVDSX xoaddr:$A)))>;
def : Pat<(v2i64 (scalar_to_vector DblToULongLoad.A)),
(v2i64 (XVCVDPUXDS (LXVDSX xoaddr:$A)))>;
}
let Predicates = [HasVSX, NoP9Vector] in {
// Load-and-splat with fp-to-int conversion (using X-Form VSX loads).
def : Pat<(v4i32 (scalar_to_vector DblToIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWS (LXSDX xoaddr:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector DblToUIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWS (LXSDX xoaddr:$A)), VSRC), 1))>;
def : Pat<(v2i64 (scalar_to_vector FltToLongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPSXDS (COPY_TO_REGCLASS
(LXSSPX xoaddr:$A), VSFRC)), 0))>;
def : Pat<(v2i64 (scalar_to_vector FltToULongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPUXDS (COPY_TO_REGCLASS
(LXSSPX xoaddr:$A), VSFRC)), 0))>;
}
// Big endian, available on all targets with VSX
let Predicates = [IsBigEndian, HasVSX] in {
def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),
(v2f64 (XXPERMDI
(COPY_TO_REGCLASS $A, VSRC),
(COPY_TO_REGCLASS $B, VSRC), 0))>;
def : Pat<(v4f32 (build_vector f32:$A, f32:$B, f32:$C, f32:$D)),
(VMRGEW MrgFP.AC, MrgFP.BD)>;
def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1,
DblToFlt.B0, DblToFlt.B1)),
(v4f32 (VMRGEW MrgFP.ABhToFlt, MrgFP.ABlToFlt))>;
}
let Predicates = [IsLittleEndian, HasVSX] in {
// Little endian, available on all targets with VSX
def : Pat<(v2f64 (build_vector f64:$A, f64:$B)),
(v2f64 (XXPERMDI
(COPY_TO_REGCLASS $B, VSRC),
(COPY_TO_REGCLASS $A, VSRC), 0))>;
def : Pat<(v4f32 (build_vector f32:$D, f32:$C, f32:$B, f32:$A)),
(VMRGEW MrgFP.AC, MrgFP.BD)>;
def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1,
DblToFlt.B0, DblToFlt.B1)),
(v4f32 (VMRGEW MrgFP.BAhToFlt, MrgFP.BAlToFlt))>;
}
let Predicates = [HasDirectMove] in {
// Endianness-neutral constant splat on P8 and newer targets. The reason
// for this pattern is that on targets with direct moves, we don't expand
// BUILD_VECTOR nodes for v4i32.
def : Pat<(v4i32 (build_vector immSExt5NonZero:$A, immSExt5NonZero:$A,
immSExt5NonZero:$A, immSExt5NonZero:$A)),
(v4i32 (VSPLTISW imm:$A))>;
}
let Predicates = [IsBigEndian, HasDirectMove, NoP9Vector] in {
// Big endian integer vectors using direct moves.
def : Pat<(v2i64 (build_vector i64:$A, i64:$B)),
(v2i64 (XXPERMDI
(COPY_TO_REGCLASS (MTVSRD $A), VSRC),
(COPY_TO_REGCLASS (MTVSRD $B), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(VMRGOW (XXPERMDI (COPY_TO_REGCLASS (MTVSRWZ $A), VSRC),
(COPY_TO_REGCLASS (MTVSRWZ $C), VSRC), 0),
(XXPERMDI (COPY_TO_REGCLASS (MTVSRWZ $B), VSRC),
(COPY_TO_REGCLASS (MTVSRWZ $D), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(XXSPLTW (COPY_TO_REGCLASS (MTVSRWZ $A), VSRC), 1)>;
}
let Predicates = [IsLittleEndian, HasDirectMove, NoP9Vector] in {
// Little endian integer vectors using direct moves.
def : Pat<(v2i64 (build_vector i64:$A, i64:$B)),
(v2i64 (XXPERMDI
(COPY_TO_REGCLASS (MTVSRD $B), VSRC),
(COPY_TO_REGCLASS (MTVSRD $A), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(VMRGOW (XXPERMDI (COPY_TO_REGCLASS (MTVSRWZ $D), VSRC),
(COPY_TO_REGCLASS (MTVSRWZ $B), VSRC), 0),
(XXPERMDI (COPY_TO_REGCLASS (MTVSRWZ $C), VSRC),
(COPY_TO_REGCLASS (MTVSRWZ $A), VSRC), 0))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(XXSPLTW (COPY_TO_REGCLASS (MTVSRWZ $A), VSRC), 1)>;
}
let Predicates = [HasP9Vector] in {
// Endianness-neutral patterns for const splats with ISA 3.0 instructions.
def : Pat<(v4i32 (scalar_to_vector i32:$A)),
(v4i32 (MTVSRWS $A))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$A, i32:$A, i32:$A)),
(v4i32 (MTVSRWS $A))>;
def : Pat<(v16i8 (build_vector immAnyExt8:$A, immAnyExt8:$A, immAnyExt8:$A,
immAnyExt8:$A, immAnyExt8:$A, immAnyExt8:$A,
immAnyExt8:$A, immAnyExt8:$A, immAnyExt8:$A,
immAnyExt8:$A, immAnyExt8:$A, immAnyExt8:$A,
immAnyExt8:$A, immAnyExt8:$A, immAnyExt8:$A,
immAnyExt8:$A)),
(v16i8 (COPY_TO_REGCLASS (XXSPLTIB imm:$A), VSRC))>;
def : Pat<(v16i8 immAllOnesV),
(v16i8 (COPY_TO_REGCLASS (XXSPLTIB 255), VSRC))>;
def : Pat<(v8i16 immAllOnesV),
(v8i16 (COPY_TO_REGCLASS (XXSPLTIB 255), VSRC))>;
def : Pat<(v4i32 immAllOnesV),
(v4i32 (XXSPLTIB 255))>;
def : Pat<(v2i64 immAllOnesV),
(v2i64 (XXSPLTIB 255))>;
def : Pat<(v4i32 (scalar_to_vector FltToIntLoad.A)),
(v4i32 (XVCVSPSXWS (LXVWSX xoaddr:$A)))>;
def : Pat<(v4i32 (scalar_to_vector FltToUIntLoad.A)),
(v4i32 (XVCVSPUXWS (LXVWSX xoaddr:$A)))>;
def : Pat<(v4i32 (scalar_to_vector DblToIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPSXWS (DFLOADf64 iaddr:$A)), VSRC), 1))>;
def : Pat<(v4i32 (scalar_to_vector DblToUIntLoad.A)),
(v4i32 (XXSPLTW (COPY_TO_REGCLASS
(XSCVDPUXWS (DFLOADf64 iaddr:$A)), VSRC), 1))>;
def : Pat<(v2i64 (scalar_to_vector FltToLongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPSXDS (COPY_TO_REGCLASS
(DFLOADf32 iaddr:$A),
VSFRC)), 0))>;
def : Pat<(v2i64 (scalar_to_vector FltToULongLoad.A)),
(v2i64 (XXPERMDIs (XSCVDPUXDS (COPY_TO_REGCLASS
(DFLOADf32 iaddr:$A),
VSFRC)), 0))>;
}
let Predicates = [IsISA3_0, HasDirectMove, IsBigEndian] in {
def : Pat<(i64 (extractelt v2i64:$A, 1)),
(i64 (MFVSRLD $A))>;
// Better way to build integer vectors if we have MTVSRDD. Big endian.
def : Pat<(v2i64 (build_vector i64:$rB, i64:$rA)),
(v2i64 (MTVSRDD $rB, $rA))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(VMRGOW (COPY_TO_REGCLASS (MTVSRDD AnyExts.A, AnyExts.C), VSRC),
(COPY_TO_REGCLASS (MTVSRDD AnyExts.B, AnyExts.D), VSRC))>;
}
let Predicates = [IsISA3_0, HasDirectMove, IsLittleEndian] in {
def : Pat<(i64 (extractelt v2i64:$A, 0)),
(i64 (MFVSRLD $A))>;
// Better way to build integer vectors if we have MTVSRDD. Little endian.
def : Pat<(v2i64 (build_vector i64:$rA, i64:$rB)),
(v2i64 (MTVSRDD $rB, $rA))>;
def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
(VMRGOW (COPY_TO_REGCLASS (MTVSRDD AnyExts.D, AnyExts.B), VSRC),
(COPY_TO_REGCLASS (MTVSRDD AnyExts.C, AnyExts.A), VSRC))>;
}
}
Reference in New Issue View Git Blame Copy Permalink