llvm-project/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td

1109 lines
55 KiB
TableGen

//===-- X86InstrFragmentsSIMD.td - x86 SIMD ISA ------------*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file provides pattern fragments useful for SIMD instructions.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// MMX specific DAG Nodes.
//===----------------------------------------------------------------------===//
// Low word of MMX to GPR.
def MMX_X86movd2w : SDNode<"X86ISD::MMX_MOVD2W", SDTypeProfile<1, 1,
[SDTCisVT<0, i32>, SDTCisVT<1, x86mmx>]>>;
// GPR to low word of MMX.
def MMX_X86movw2d : SDNode<"X86ISD::MMX_MOVW2D", SDTypeProfile<1, 1,
[SDTCisVT<0, x86mmx>, SDTCisVT<1, i32>]>>;
//===----------------------------------------------------------------------===//
// MMX Pattern Fragments
//===----------------------------------------------------------------------===//
def load_mmx : PatFrag<(ops node:$ptr), (x86mmx (load node:$ptr))>;
//===----------------------------------------------------------------------===//
// SSE specific DAG Nodes.
//===----------------------------------------------------------------------===//
def SDTX86VFCMP : SDTypeProfile<1, 3, [SDTCisFP<0>, SDTCisVec<0>,
SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>,
SDTCisVT<3, i8>]>;
def X86fmin : SDNode<"X86ISD::FMIN", SDTFPBinOp>;
def X86fmax : SDNode<"X86ISD::FMAX", SDTFPBinOp>;
def X86fmins : SDNode<"X86ISD::FMINS", SDTFPBinOp>;
def X86fmaxs : SDNode<"X86ISD::FMAXS", SDTFPBinOp>;
// Commutative and Associative FMIN and FMAX.
def X86fminc : SDNode<"X86ISD::FMINC", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86fmaxc : SDNode<"X86ISD::FMAXC", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86fand : SDNode<"X86ISD::FAND", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86for : SDNode<"X86ISD::FOR", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86fxor : SDNode<"X86ISD::FXOR", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86fandn : SDNode<"X86ISD::FANDN", SDTFPBinOp>;
def X86frsqrt : SDNode<"X86ISD::FRSQRT", SDTFPUnaryOp>;
def X86frcp : SDNode<"X86ISD::FRCP", SDTFPUnaryOp>;
def X86fhadd : SDNode<"X86ISD::FHADD", SDTFPBinOp>;
def X86fhsub : SDNode<"X86ISD::FHSUB", SDTFPBinOp>;
def X86hadd : SDNode<"X86ISD::HADD", SDTIntBinOp>;
def X86hsub : SDNode<"X86ISD::HSUB", SDTIntBinOp>;
def X86comi : SDNode<"X86ISD::COMI", SDTX86CmpTest>;
def X86ucomi : SDNode<"X86ISD::UCOMI", SDTX86CmpTest>;
def X86cmps : SDNode<"X86ISD::FSETCC", SDTX86Cmps>;
def X86pshufb : SDNode<"X86ISD::PSHUFB",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i8>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
def X86psadbw : SDNode<"X86ISD::PSADBW",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i64>,
SDTCVecEltisVT<1, i8>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<1,2>]>, [SDNPCommutative]>;
def X86dbpsadbw : SDNode<"X86ISD::DBPSADBW",
SDTypeProfile<1, 3, [SDTCVecEltisVT<0, i16>,
SDTCVecEltisVT<1, i8>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<1,2>, SDTCisInt<3>]>>;
def X86andnp : SDNode<"X86ISD::ANDNP",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
def X86multishift : SDNode<"X86ISD::MULTISHIFT",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisSameAs<1,2>]>>;
def X86pextrb : SDNode<"X86ISD::PEXTRB",
SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisVT<1, v16i8>,
SDTCisPtrTy<2>]>>;
def X86pextrw : SDNode<"X86ISD::PEXTRW",
SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisVT<1, v8i16>,
SDTCisPtrTy<2>]>>;
def X86pinsrb : SDNode<"X86ISD::PINSRB",
SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
def X86pinsrw : SDNode<"X86ISD::PINSRW",
SDTypeProfile<1, 3, [SDTCisVT<0, v8i16>, SDTCisSameAs<0,1>,
SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
def X86insertps : SDNode<"X86ISD::INSERTPS",
SDTypeProfile<1, 3, [SDTCisVT<0, v4f32>, SDTCisSameAs<0,1>,
SDTCisVT<2, v4f32>, SDTCisVT<3, i8>]>>;
def X86vzmovl : SDNode<"X86ISD::VZEXT_MOVL",
SDTypeProfile<1, 1, [SDTCisSameAs<0,1>]>>;
def X86vzload : SDNode<"X86ISD::VZEXT_LOAD", SDTLoad,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def X86vzext : SDNode<"X86ISD::VZEXT",
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisInt<0>, SDTCisInt<1>,
SDTCisOpSmallerThanOp<1, 0>]>>;
def X86vsext : SDNode<"X86ISD::VSEXT",
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisInt<0>, SDTCisInt<1>,
SDTCisOpSmallerThanOp<1, 0>]>>;
def SDTVtrunc : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisInt<0>, SDTCisInt<1>,
SDTCisOpSmallerThanOp<0, 1>]>;
def X86vtrunc : SDNode<"X86ISD::VTRUNC", SDTVtrunc>;
def X86vtruncs : SDNode<"X86ISD::VTRUNCS", SDTVtrunc>;
def X86vtruncus : SDNode<"X86ISD::VTRUNCUS", SDTVtrunc>;
def X86vfpext : SDNode<"X86ISD::VFPEXT",
SDTypeProfile<1, 1, [SDTCVecEltisVT<0, f64>,
SDTCVecEltisVT<1, f32>,
SDTCisSameSizeAs<0, 1>]>>;
def X86vfpround: SDNode<"X86ISD::VFPROUND",
SDTypeProfile<1, 1, [SDTCVecEltisVT<0, f32>,
SDTCVecEltisVT<1, f64>,
SDTCisSameSizeAs<0, 1>]>>;
def X86froundRnd: SDNode<"X86ISD::VFPROUNDS_RND",
SDTypeProfile<1, 3, [SDTCVecEltisVT<0, f32>,
SDTCisSameAs<0, 1>,
SDTCVecEltisVT<2, f64>,
SDTCisSameSizeAs<0, 2>,
SDTCisVT<3, i32>]>>;
def X86fpextRnd : SDNode<"X86ISD::VFPEXTS_RND",
SDTypeProfile<1, 3, [SDTCVecEltisVT<0, f64>,
SDTCisSameAs<0, 1>,
SDTCVecEltisVT<2, f32>,
SDTCisSameSizeAs<0, 2>,
SDTCisVT<3, i32>]>>;
def X86vshiftimm : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisVT<2, i8>, SDTCisInt<0>]>;
def X86vshldq : SDNode<"X86ISD::VSHLDQ", X86vshiftimm>;
def X86vshrdq : SDNode<"X86ISD::VSRLDQ", X86vshiftimm>;
def X86cmpp : SDNode<"X86ISD::CMPP", SDTX86VFCMP>;
def X86pcmpeq : SDNode<"X86ISD::PCMPEQ", SDTIntBinOp, [SDNPCommutative]>;
def X86pcmpgt : SDNode<"X86ISD::PCMPGT", SDTIntBinOp>;
def X86CmpMaskCC :
SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCVecEltisVT<0, i1>,
SDTCisVec<1>, SDTCisSameAs<2, 1>,
SDTCisSameNumEltsAs<0, 1>, SDTCisVT<3, i8>]>;
def X86CmpMaskCCRound :
SDTypeProfile<1, 4, [SDTCisVec<0>,SDTCVecEltisVT<0, i1>,
SDTCisVec<1>, SDTCisFP<1>, SDTCisSameAs<2, 1>,
SDTCisSameNumEltsAs<0, 1>, SDTCisVT<3, i8>,
SDTCisVT<4, i32>]>;
def X86CmpMaskCCScalar :
SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisFP<1>, SDTCisSameAs<1, 2>,
SDTCisVT<3, i8>]>;
def X86CmpMaskCCScalarRound :
SDTypeProfile<1, 4, [SDTCisInt<0>, SDTCisFP<1>, SDTCisSameAs<1, 2>,
SDTCisVT<3, i8>, SDTCisVT<4, i32>]>;
def X86cmpm : SDNode<"X86ISD::CMPM", X86CmpMaskCC>;
// Hack to make CMPM commutable in tablegen patterns for load folding.
def X86cmpm_c : SDNode<"X86ISD::CMPM", X86CmpMaskCC, [SDNPCommutative]>;
def X86cmpmRnd : SDNode<"X86ISD::CMPM_RND", X86CmpMaskCCRound>;
def X86cmpms : SDNode<"X86ISD::FSETCCM", X86CmpMaskCCScalar>;
def X86cmpmsRnd : SDNode<"X86ISD::FSETCCM_RND", X86CmpMaskCCScalarRound>;
def X86phminpos: SDNode<"X86ISD::PHMINPOS",
SDTypeProfile<1, 1, [SDTCisVT<0, v8i16>, SDTCisVT<1, v8i16>]>>;
def X86vshiftuniform : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisVec<2>, SDTCisInt<0>,
SDTCisInt<1>]>;
def X86vshl : SDNode<"X86ISD::VSHL", X86vshiftuniform>;
def X86vsrl : SDNode<"X86ISD::VSRL", X86vshiftuniform>;
def X86vsra : SDNode<"X86ISD::VSRA", X86vshiftuniform>;
def X86vshiftvariable : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>, SDTCisInt<0>]>;
def X86vsrav : SDNode<"X86ISD::VSRAV", X86vshiftvariable>;
def X86vshli : SDNode<"X86ISD::VSHLI", X86vshiftimm>;
def X86vsrli : SDNode<"X86ISD::VSRLI", X86vshiftimm>;
def X86vsrai : SDNode<"X86ISD::VSRAI", X86vshiftimm>;
def X86kshiftl : SDNode<"X86ISD::KSHIFTL",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i1>,
SDTCisSameAs<0, 1>,
SDTCisVT<2, i8>]>>;
def X86kshiftr : SDNode<"X86ISD::KSHIFTR",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i1>,
SDTCisSameAs<0, 1>,
SDTCisVT<2, i8>]>>;
def X86kadd : SDNode<"X86ISD::KADD", SDTIntBinOp, [SDNPCommutative]>;
def X86vrotli : SDNode<"X86ISD::VROTLI", X86vshiftimm>;
def X86vrotri : SDNode<"X86ISD::VROTRI", X86vshiftimm>;
def X86vpshl : SDNode<"X86ISD::VPSHL", X86vshiftvariable>;
def X86vpsha : SDNode<"X86ISD::VPSHA", X86vshiftvariable>;
def X86vpcom : SDNode<"X86ISD::VPCOM",
SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisVT<3, i8>, SDTCisInt<0>]>>;
def X86vpcomu : SDNode<"X86ISD::VPCOMU",
SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisVT<3, i8>, SDTCisInt<0>]>>;
def X86vpermil2 : SDNode<"X86ISD::VPERMIL2",
SDTypeProfile<1, 4, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisFP<0>, SDTCisInt<3>,
SDTCisSameNumEltsAs<0, 3>,
SDTCisSameSizeAs<0,3>,
SDTCisVT<4, i8>]>>;
def X86vpperm : SDNode<"X86ISD::VPPERM",
SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>, SDTCisSameAs<0, 3>]>>;
def SDTX86CmpPTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
SDTCisVec<1>,
SDTCisSameAs<2, 1>]>;
def X86addus : SDNode<"X86ISD::ADDUS", SDTIntBinOp, [SDNPCommutative]>;
def X86subus : SDNode<"X86ISD::SUBUS", SDTIntBinOp>;
def X86adds : SDNode<"X86ISD::ADDS", SDTIntBinOp, [SDNPCommutative]>;
def X86subs : SDNode<"X86ISD::SUBS", SDTIntBinOp>;
def X86mulhrs : SDNode<"X86ISD::MULHRS", SDTIntBinOp, [SDNPCommutative]>;
def X86avg : SDNode<"X86ISD::AVG" , SDTIntBinOp, [SDNPCommutative]>;
def X86ptest : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
def X86testp : SDNode<"X86ISD::TESTP", SDTX86CmpPTest>;
def X86kortest : SDNode<"X86ISD::KORTEST", SDTX86CmpPTest>;
def X86ktest : SDNode<"X86ISD::KTEST", SDTX86CmpPTest>;
def X86movmsk : SDNode<"X86ISD::MOVMSK",
SDTypeProfile<1, 1, [SDTCisVT<0, i32>, SDTCisVec<1>]>>;
def X86selects : SDNode<"X86ISD::SELECTS",
SDTypeProfile<1, 3, [SDTCisVT<1, v1i1>,
SDTCisSameAs<0, 2>,
SDTCisSameAs<2, 3>]>>;
def X86pmuludq : SDNode<"X86ISD::PMULUDQ",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i64>,
SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>]>,
[SDNPCommutative]>;
def X86pmuldq : SDNode<"X86ISD::PMULDQ",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i64>,
SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>]>,
[SDNPCommutative]>;
def X86extrqi : SDNode<"X86ISD::EXTRQI",
SDTypeProfile<1, 3, [SDTCisVT<0, v2i64>, SDTCisSameAs<0,1>,
SDTCisVT<2, i8>, SDTCisVT<3, i8>]>>;
def X86insertqi : SDNode<"X86ISD::INSERTQI",
SDTypeProfile<1, 4, [SDTCisVT<0, v2i64>, SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>, SDTCisVT<3, i8>,
SDTCisVT<4, i8>]>>;
// Specific shuffle nodes - At some point ISD::VECTOR_SHUFFLE will always get
// translated into one of the target nodes below during lowering.
// Note: this is a work in progress...
def SDTShuff1Op : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDTShuff2Op : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>;
def SDTShuff2OpM : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisFP<0>, SDTCisInt<2>,
SDTCisSameNumEltsAs<0,2>,
SDTCisSameSizeAs<0,2>]>;
def SDTShuff2OpI : SDTypeProfile<1, 2, [SDTCisVec<0>,
SDTCisSameAs<0,1>, SDTCisVT<2, i8>]>;
def SDTShuff3OpI : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>, SDTCisVT<3, i8>]>;
def SDTFPBinOpImm: SDTypeProfile<1, 3, [SDTCisFP<0>, SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisVT<3, i32>]>;
def SDTFPBinOpImmRound: SDTypeProfile<1, 4, [SDTCisFP<0>, SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>]>;
def SDTFPTernaryOpImmRound: SDTypeProfile<1, 5, [SDTCisFP<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisInt<3>,
SDTCisSameSizeAs<0, 3>,
SDTCisSameNumEltsAs<0, 3>,
SDTCisVT<4, i32>,
SDTCisVT<5, i32>]>;
def SDTFPUnaryOpImm: SDTypeProfile<1, 2, [SDTCisFP<0>, SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisVT<2, i32>]>;
def SDTFPUnaryOpImmRound: SDTypeProfile<1, 3, [SDTCisFP<0>, SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisVT<2, i32>,
SDTCisVT<3, i32>]>;
def SDTVBroadcast : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
def SDTVBroadcastm : SDTypeProfile<1, 1, [SDTCisVec<0>,
SDTCisInt<0>, SDTCisInt<1>]>;
def SDTBlend : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>, SDTCisVT<3, i8>]>;
def SDTTernlog : SDTypeProfile<1, 4, [SDTCisInt<0>, SDTCisVec<0>,
SDTCisSameAs<0,1>, SDTCisSameAs<0,2>,
SDTCisSameAs<0,3>, SDTCisVT<4, i8>]>;
def SDTFPBinOpRound : SDTypeProfile<1, 3, [ // fadd_round, fmul_round, etc.
SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisFP<0>, SDTCisVT<3, i32>]>;
def SDTFPUnaryOpRound : SDTypeProfile<1, 2, [ // fsqrt_round, fgetexp_round, etc.
SDTCisSameAs<0, 1>, SDTCisFP<0>, SDTCisVT<2, i32>]>;
def SDTFmaRound : SDTypeProfile<1, 4, [SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>, SDTCisSameAs<1,3>,
SDTCisFP<0>, SDTCisVT<4, i32>]>;
def X86PAlignr : SDNode<"X86ISD::PALIGNR",
SDTypeProfile<1, 3, [SDTCVecEltisVT<0, i8>,
SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisVT<3, i8>]>>;
def X86VAlign : SDNode<"X86ISD::VALIGN", SDTShuff3OpI>;
def X86VShld : SDNode<"X86ISD::VSHLD", SDTShuff3OpI>;
def X86VShrd : SDNode<"X86ISD::VSHRD", SDTShuff3OpI>;
def X86VShldv : SDNode<"X86ISD::VSHLDV",
SDTypeProfile<1, 3, [SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisSameAs<0,3>]>>;
def X86VShrdv : SDNode<"X86ISD::VSHRDV",
SDTypeProfile<1, 3, [SDTCisVec<0>,
SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>,
SDTCisSameAs<0,3>]>>;
def X86Conflict : SDNode<"X86ISD::CONFLICT", SDTIntUnaryOp>;
def X86PShufd : SDNode<"X86ISD::PSHUFD", SDTShuff2OpI>;
def X86PShufhw : SDNode<"X86ISD::PSHUFHW", SDTShuff2OpI>;
def X86PShuflw : SDNode<"X86ISD::PSHUFLW", SDTShuff2OpI>;
def X86Shufp : SDNode<"X86ISD::SHUFP", SDTShuff3OpI>;
def X86Shuf128 : SDNode<"X86ISD::SHUF128", SDTShuff3OpI>;
def X86Movddup : SDNode<"X86ISD::MOVDDUP", SDTShuff1Op>;
def X86Movshdup : SDNode<"X86ISD::MOVSHDUP", SDTShuff1Op>;
def X86Movsldup : SDNode<"X86ISD::MOVSLDUP", SDTShuff1Op>;
def X86Movsd : SDNode<"X86ISD::MOVSD", SDTShuff2Op>;
def X86Movss : SDNode<"X86ISD::MOVSS", SDTShuff2Op>;
def X86Movlhps : SDNode<"X86ISD::MOVLHPS", SDTShuff2Op>;
def X86Movlhpd : SDNode<"X86ISD::MOVLHPD", SDTShuff2Op>;
def X86Movhlps : SDNode<"X86ISD::MOVHLPS", SDTShuff2Op>;
def X86Movlps : SDNode<"X86ISD::MOVLPS", SDTShuff2Op>;
def X86Movlpd : SDNode<"X86ISD::MOVLPD", SDTShuff2Op>;
def SDTPack : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisInt<0>,
SDTCisVec<1>, SDTCisInt<1>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<1,2>,
SDTCisOpSmallerThanOp<0, 1>]>;
def X86Packss : SDNode<"X86ISD::PACKSS", SDTPack>;
def X86Packus : SDNode<"X86ISD::PACKUS", SDTPack>;
def X86Unpckl : SDNode<"X86ISD::UNPCKL", SDTShuff2Op>;
def X86Unpckh : SDNode<"X86ISD::UNPCKH", SDTShuff2Op>;
def X86vpmaddubsw : SDNode<"X86ISD::VPMADDUBSW",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i16>,
SDTCVecEltisVT<1, i8>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<1,2>]>>;
def X86vpmaddwd : SDNode<"X86ISD::VPMADDWD",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i32>,
SDTCVecEltisVT<1, i16>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<1,2>]>,
[SDNPCommutative]>;
def X86VPermilpv : SDNode<"X86ISD::VPERMILPV", SDTShuff2OpM>;
def X86VPermilpi : SDNode<"X86ISD::VPERMILPI", SDTShuff2OpI>;
def X86VPermv : SDNode<"X86ISD::VPERMV",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisInt<1>,
SDTCisSameNumEltsAs<0,1>,
SDTCisSameSizeAs<0,1>,
SDTCisSameAs<0,2>]>>;
def X86VPermi : SDNode<"X86ISD::VPERMI", SDTShuff2OpI>;
def X86VPermt2 : SDNode<"X86ISD::VPERMV3",
SDTypeProfile<1, 3, [SDTCisVec<0>,
SDTCisSameAs<0,1>, SDTCisInt<2>,
SDTCisVec<2>, SDTCisSameNumEltsAs<0, 2>,
SDTCisSameSizeAs<0,2>,
SDTCisSameAs<0,3>]>, []>;
def X86vpternlog : SDNode<"X86ISD::VPTERNLOG", SDTTernlog>;
def X86VPerm2x128 : SDNode<"X86ISD::VPERM2X128", SDTShuff3OpI>;
def X86VFixupimm : SDNode<"X86ISD::VFIXUPIMM", SDTFPTernaryOpImmRound>;
def X86VFixupimmScalar : SDNode<"X86ISD::VFIXUPIMMS", SDTFPTernaryOpImmRound>;
def X86VRange : SDNode<"X86ISD::VRANGE", SDTFPBinOpImm>;
def X86VRangeRnd : SDNode<"X86ISD::VRANGE_RND", SDTFPBinOpImmRound>;
def X86VReduce : SDNode<"X86ISD::VREDUCE", SDTFPUnaryOpImm>;
def X86VReduceRnd : SDNode<"X86ISD::VREDUCE_RND", SDTFPUnaryOpImmRound>;
def X86VRndScale : SDNode<"X86ISD::VRNDSCALE", SDTFPUnaryOpImm>;
def X86VRndScaleRnd: SDNode<"X86ISD::VRNDSCALE_RND", SDTFPUnaryOpImmRound>;
def X86VGetMant : SDNode<"X86ISD::VGETMANT", SDTFPUnaryOpImm>;
def X86VGetMantRnd : SDNode<"X86ISD::VGETMANT_RND", SDTFPUnaryOpImmRound>;
def X86Vfpclass : SDNode<"X86ISD::VFPCLASS",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i1>,
SDTCisFP<1>,
SDTCisSameNumEltsAs<0,1>,
SDTCisVT<2, i32>]>, []>;
def X86Vfpclasss : SDNode<"X86ISD::VFPCLASSS",
SDTypeProfile<1, 2, [SDTCisVT<0, v1i1>,
SDTCisFP<1>, SDTCisVT<2, i32>]>,[]>;
def X86SubVBroadcast : SDNode<"X86ISD::SUBV_BROADCAST",
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisSubVecOfVec<1, 0>]>, []>;
def X86VBroadcast : SDNode<"X86ISD::VBROADCAST", SDTVBroadcast>;
def X86VBroadcastm : SDNode<"X86ISD::VBROADCASTM", SDTVBroadcastm>;
def X86Blendi : SDNode<"X86ISD::BLENDI", SDTBlend>;
def X86Addsub : SDNode<"X86ISD::ADDSUB", SDTFPBinOp>;
def X86faddRnd : SDNode<"X86ISD::FADD_RND", SDTFPBinOpRound>;
def X86faddRnds : SDNode<"X86ISD::FADDS_RND", SDTFPBinOpRound>;
def X86fsubRnd : SDNode<"X86ISD::FSUB_RND", SDTFPBinOpRound>;
def X86fsubRnds : SDNode<"X86ISD::FSUBS_RND", SDTFPBinOpRound>;
def X86fmulRnd : SDNode<"X86ISD::FMUL_RND", SDTFPBinOpRound>;
def X86fmulRnds : SDNode<"X86ISD::FMULS_RND", SDTFPBinOpRound>;
def X86fdivRnd : SDNode<"X86ISD::FDIV_RND", SDTFPBinOpRound>;
def X86fdivRnds : SDNode<"X86ISD::FDIVS_RND", SDTFPBinOpRound>;
def X86fmaxRnd : SDNode<"X86ISD::FMAX_RND", SDTFPBinOpRound>;
def X86fmaxRnds : SDNode<"X86ISD::FMAXS_RND", SDTFPBinOpRound>;
def X86fminRnd : SDNode<"X86ISD::FMIN_RND", SDTFPBinOpRound>;
def X86fminRnds : SDNode<"X86ISD::FMINS_RND", SDTFPBinOpRound>;
def X86scalef : SDNode<"X86ISD::SCALEF", SDTFPBinOpRound>;
def X86scalefs : SDNode<"X86ISD::SCALEFS", SDTFPBinOpRound>;
def X86fsqrtRnd : SDNode<"X86ISD::FSQRT_RND", SDTFPUnaryOpRound>;
def X86fsqrtRnds : SDNode<"X86ISD::FSQRTS_RND", SDTFPBinOpRound>;
def X86fgetexpRnd : SDNode<"X86ISD::FGETEXP_RND", SDTFPUnaryOpRound>;
def X86fgetexpRnds : SDNode<"X86ISD::FGETEXPS_RND", SDTFPBinOpRound>;
def X86Fmadd : SDNode<"ISD::FMA", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmadd : SDNode<"X86ISD::FNMADD", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fmsub : SDNode<"X86ISD::FMSUB", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmsub : SDNode<"X86ISD::FNMSUB", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fmaddsub : SDNode<"X86ISD::FMADDSUB", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fmsubadd : SDNode<"X86ISD::FMSUBADD", SDTFPTernaryOp, [SDNPCommutative]>;
def X86FmaddRnd : SDNode<"X86ISD::FMADD_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FnmaddRnd : SDNode<"X86ISD::FNMADD_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FmsubRnd : SDNode<"X86ISD::FMSUB_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FnmsubRnd : SDNode<"X86ISD::FNMSUB_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FmaddsubRnd : SDNode<"X86ISD::FMADDSUB_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FmsubaddRnd : SDNode<"X86ISD::FMSUBADD_RND", SDTFmaRound, [SDNPCommutative]>;
// Scalar FMA4 intrinsics which zero the non-scalar bits.
def X86Fmadd4s : SDNode<"X86ISD::FMADD4S", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmadd4s : SDNode<"X86ISD::FNMADD4S", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fmsub4s : SDNode<"X86ISD::FMSUB4S", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmsub4s : SDNode<"X86ISD::FNMSUB4S", SDTFPTernaryOp, [SDNPCommutative]>;
// Scalar FMA intrinsics with passthru bits in operand 1.
def X86Fmadds1 : SDNode<"X86ISD::FMADDS1", SDTFPTernaryOp>;
def X86Fnmadds1 : SDNode<"X86ISD::FNMADDS1", SDTFPTernaryOp>;
def X86Fmsubs1 : SDNode<"X86ISD::FMSUBS1", SDTFPTernaryOp>;
def X86Fnmsubs1 : SDNode<"X86ISD::FNMSUBS1", SDTFPTernaryOp>;
// Scalar FMA intrinsics with passthru bits in operand 1.
def X86FmaddRnds1 : SDNode<"X86ISD::FMADDS1_RND", SDTFmaRound>;
def X86FnmaddRnds1 : SDNode<"X86ISD::FNMADDS1_RND", SDTFmaRound>;
def X86FmsubRnds1 : SDNode<"X86ISD::FMSUBS1_RND", SDTFmaRound>;
def X86FnmsubRnds1 : SDNode<"X86ISD::FNMSUBS1_RND", SDTFmaRound>;
def X86Fmadds3 : SDNode<"X86ISD::FMADDS3", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmadds3 : SDNode<"X86ISD::FNMADDS3", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fmsubs3 : SDNode<"X86ISD::FMSUBS3", SDTFPTernaryOp, [SDNPCommutative]>;
def X86Fnmsubs3 : SDNode<"X86ISD::FNMSUBS3", SDTFPTernaryOp, [SDNPCommutative]>;
// Scalar FMA intrinsics with passthru bits in operand 3.
def X86FmaddRnds3 : SDNode<"X86ISD::FMADDS3_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FnmaddRnds3 : SDNode<"X86ISD::FNMADDS3_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FmsubRnds3 : SDNode<"X86ISD::FMSUBS3_RND", SDTFmaRound, [SDNPCommutative]>;
def X86FnmsubRnds3 : SDNode<"X86ISD::FNMSUBS3_RND", SDTFmaRound, [SDNPCommutative]>;
def SDTIFma : SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;
def x86vpmadd52l : SDNode<"X86ISD::VPMADD52L", SDTIFma, [SDNPCommutative]>;
def x86vpmadd52h : SDNode<"X86ISD::VPMADD52H", SDTIFma, [SDNPCommutative]>;
def X86rsqrt14 : SDNode<"X86ISD::RSQRT14", SDTFPUnaryOp>;
def X86rcp14 : SDNode<"X86ISD::RCP14", SDTFPUnaryOp>;
// VNNI
def SDTVnni : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;
def X86Vpdpbusd : SDNode<"X86ISD::VPDPBUSD", SDTVnni>;
def X86Vpdpbusds : SDNode<"X86ISD::VPDPBUSDS", SDTVnni>;
def X86Vpdpwssd : SDNode<"X86ISD::VPDPWSSD", SDTVnni>;
def X86Vpdpwssds : SDNode<"X86ISD::VPDPWSSDS", SDTVnni>;
def X86rsqrt28 : SDNode<"X86ISD::RSQRT28", SDTFPUnaryOpRound>;
def X86rcp28 : SDNode<"X86ISD::RCP28", SDTFPUnaryOpRound>;
def X86exp2 : SDNode<"X86ISD::EXP2", SDTFPUnaryOpRound>;
def X86rsqrt14s : SDNode<"X86ISD::RSQRT14S", SDTFPBinOp>;
def X86rcp14s : SDNode<"X86ISD::RCP14S", SDTFPBinOp>;
def X86rsqrt28s : SDNode<"X86ISD::RSQRT28S", SDTFPBinOpRound>;
def X86rcp28s : SDNode<"X86ISD::RCP28S", SDTFPBinOpRound>;
def X86Ranges : SDNode<"X86ISD::VRANGES", SDTFPBinOpImm>;
def X86RndScales : SDNode<"X86ISD::VRNDSCALES", SDTFPBinOpImm>;
def X86Reduces : SDNode<"X86ISD::VREDUCES", SDTFPBinOpImm>;
def X86GetMants : SDNode<"X86ISD::VGETMANTS", SDTFPBinOpImm>;
def X86RangesRnd : SDNode<"X86ISD::VRANGES_RND", SDTFPBinOpImmRound>;
def X86RndScalesRnd : SDNode<"X86ISD::VRNDSCALES_RND", SDTFPBinOpImmRound>;
def X86ReducesRnd : SDNode<"X86ISD::VREDUCES_RND", SDTFPBinOpImmRound>;
def X86GetMantsRnd : SDNode<"X86ISD::VGETMANTS_RND", SDTFPBinOpImmRound>;
def X86compress: SDNode<"X86ISD::COMPRESS", SDTypeProfile<1, 1,
[SDTCisSameAs<0, 1>, SDTCisVec<1>]>, []>;
def X86expand : SDNode<"X86ISD::EXPAND", SDTypeProfile<1, 1,
[SDTCisSameAs<0, 1>, SDTCisVec<1>]>, []>;
// vpshufbitqmb
def X86Vpshufbitqmb : SDNode<"X86ISD::VPSHUFBITQMB",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisSameAs<1,2>,
SDTCVecEltisVT<0,i1>,
SDTCisSameNumEltsAs<0,1>]>>;
def SDTintToFPRound: SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisFP<0>,
SDTCisSameAs<0,1>, SDTCisInt<2>,
SDTCisVT<3, i32>]>;
def SDTFloatToInt: SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisInt<0>, SDTCisFP<1>]>;
def SDTFloatToIntRnd: SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisInt<0>, SDTCisFP<1>,
SDTCisVT<2, i32>]>;
def SDTSFloatToIntRnd: SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisFP<1>,
SDTCisVec<1>, SDTCisVT<2, i32>]>;
def SDTVintToFP: SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisFP<0>, SDTCisInt<1>]>;
def SDTVintToFPRound: SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisFP<0>, SDTCisInt<1>,
SDTCisVT<2, i32>]>;
// Scalar
def X86SintToFpRnd : SDNode<"X86ISD::SCALAR_SINT_TO_FP_RND", SDTintToFPRound>;
def X86UintToFpRnd : SDNode<"X86ISD::SCALAR_UINT_TO_FP_RND", SDTintToFPRound>;
def X86cvtts2IntRnd : SDNode<"X86ISD::CVTTS2SI_RND", SDTSFloatToIntRnd>;
def X86cvtts2UIntRnd : SDNode<"X86ISD::CVTTS2UI_RND", SDTSFloatToIntRnd>;
def X86cvts2si : SDNode<"X86ISD::CVTS2SI_RND", SDTSFloatToIntRnd>;
def X86cvts2usi : SDNode<"X86ISD::CVTS2UI_RND", SDTSFloatToIntRnd>;
// Vector with rounding mode
// cvtt fp-to-int staff
def X86cvttp2siRnd : SDNode<"X86ISD::CVTTP2SI_RND", SDTFloatToIntRnd>;
def X86cvttp2uiRnd : SDNode<"X86ISD::CVTTP2UI_RND", SDTFloatToIntRnd>;
def X86VSintToFpRnd : SDNode<"X86ISD::SINT_TO_FP_RND", SDTVintToFPRound>;
def X86VUintToFpRnd : SDNode<"X86ISD::UINT_TO_FP_RND", SDTVintToFPRound>;
// cvt fp-to-int staff
def X86cvtp2IntRnd : SDNode<"X86ISD::CVTP2SI_RND", SDTFloatToIntRnd>;
def X86cvtp2UIntRnd : SDNode<"X86ISD::CVTP2UI_RND", SDTFloatToIntRnd>;
// Vector without rounding mode
// cvtt fp-to-int staff
def X86cvttp2si : SDNode<"X86ISD::CVTTP2SI", SDTFloatToInt>;
def X86cvttp2ui : SDNode<"X86ISD::CVTTP2UI", SDTFloatToInt>;
def X86VSintToFP : SDNode<"X86ISD::CVTSI2P", SDTVintToFP>;
def X86VUintToFP : SDNode<"X86ISD::CVTUI2P", SDTVintToFP>;
// cvt int-to-fp staff
def X86cvtp2Int : SDNode<"X86ISD::CVTP2SI", SDTFloatToInt>;
def X86cvtp2UInt : SDNode<"X86ISD::CVTP2UI", SDTFloatToInt>;
def X86cvtph2ps : SDNode<"X86ISD::CVTPH2PS",
SDTypeProfile<1, 1, [SDTCVecEltisVT<0, f32>,
SDTCVecEltisVT<1, i16>]> >;
def X86cvtph2psRnd : SDNode<"X86ISD::CVTPH2PS_RND",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, f32>,
SDTCVecEltisVT<1, i16>,
SDTCisVT<2, i32>]> >;
def X86cvtps2ph : SDNode<"X86ISD::CVTPS2PH",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, i16>,
SDTCVecEltisVT<1, f32>,
SDTCisVT<2, i32>]> >;
def X86vfpextRnd : SDNode<"X86ISD::VFPEXT_RND",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, f64>,
SDTCVecEltisVT<1, f32>,
SDTCisOpSmallerThanOp<1, 0>,
SDTCisVT<2, i32>]>>;
def X86vfproundRnd: SDNode<"X86ISD::VFPROUND_RND",
SDTypeProfile<1, 2, [SDTCVecEltisVT<0, f32>,
SDTCVecEltisVT<1, f64>,
SDTCisOpSmallerThanOp<0, 1>,
SDTCisVT<2, i32>]>>;
// galois field arithmetic
def X86GF2P8affineinvqb : SDNode<"X86ISD::GF2P8AFFINEINVQB", SDTBlend>;
def X86GF2P8affineqb : SDNode<"X86ISD::GF2P8AFFINEQB", SDTBlend>;
def X86GF2P8mulb : SDNode<"X86ISD::GF2P8MULB", SDTIntBinOp>;
//===----------------------------------------------------------------------===//
// SSE Complex Patterns
//===----------------------------------------------------------------------===//
// These are 'extloads' from a scalar to the low element of a vector, zeroing
// the top elements. These are used for the SSE 'ss' and 'sd' instruction
// forms.
def sse_load_f32 : ComplexPattern<v4f32, 5, "selectScalarSSELoad", [],
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
SDNPWantRoot, SDNPWantParent]>;
def sse_load_f64 : ComplexPattern<v2f64, 5, "selectScalarSSELoad", [],
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
SDNPWantRoot, SDNPWantParent]>;
def ssmem : Operand<v4f32> {
let PrintMethod = "printf32mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, SEGMENT_REG);
let ParserMatchClass = X86Mem32AsmOperand;
let OperandType = "OPERAND_MEMORY";
}
def sdmem : Operand<v2f64> {
let PrintMethod = "printf64mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, SEGMENT_REG);
let ParserMatchClass = X86Mem64AsmOperand;
let OperandType = "OPERAND_MEMORY";
}
//===----------------------------------------------------------------------===//
// SSE pattern fragments
//===----------------------------------------------------------------------===//
// Vector load wrappers to prevent folding of non-temporal aligned loads on
// supporting targets.
def vecload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
return !useNonTemporalLoad(cast<LoadSDNode>(N));
}]>;
// 128-bit load pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def loadv4f32 : PatFrag<(ops node:$ptr), (v4f32 (vecload node:$ptr))>;
def loadv2f64 : PatFrag<(ops node:$ptr), (v2f64 (vecload node:$ptr))>;
def loadv2i64 : PatFrag<(ops node:$ptr), (v2i64 (vecload node:$ptr))>;
// 256-bit load pattern fragments
// NOTE: all 256-bit integer vector loads are promoted to v4i64
def loadv8f32 : PatFrag<(ops node:$ptr), (v8f32 (vecload node:$ptr))>;
def loadv4f64 : PatFrag<(ops node:$ptr), (v4f64 (vecload node:$ptr))>;
def loadv4i64 : PatFrag<(ops node:$ptr), (v4i64 (vecload node:$ptr))>;
// 512-bit load pattern fragments
def loadv16f32 : PatFrag<(ops node:$ptr), (v16f32 (vecload node:$ptr))>;
def loadv8f64 : PatFrag<(ops node:$ptr), (v8f64 (vecload node:$ptr))>;
def loadv8i64 : PatFrag<(ops node:$ptr), (v8i64 (vecload node:$ptr))>;
// 128-/256-/512-bit extload pattern fragments
def extloadv2f32 : PatFrag<(ops node:$ptr), (v2f64 (extloadvf32 node:$ptr))>;
def extloadv4f32 : PatFrag<(ops node:$ptr), (v4f64 (extloadvf32 node:$ptr))>;
def extloadv8f32 : PatFrag<(ops node:$ptr), (v8f64 (extloadvf32 node:$ptr))>;
// Like 'store', but always requires vector size alignment.
def alignedstore : PatFrag<(ops node:$val, node:$ptr),
(store node:$val, node:$ptr), [{
auto *St = cast<StoreSDNode>(N);
return St->getAlignment() >= St->getMemoryVT().getStoreSize();
}]>;
// Like 'load', but always requires 128-bit vector alignment.
def alignedvecload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
auto *Ld = cast<LoadSDNode>(N);
return Ld->getAlignment() >= Ld->getMemoryVT().getStoreSize() &&
!useNonTemporalLoad(cast<LoadSDNode>(N));
}]>;
// 128-bit aligned load pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def alignedloadv4f32 : PatFrag<(ops node:$ptr),
(v4f32 (alignedvecload node:$ptr))>;
def alignedloadv2f64 : PatFrag<(ops node:$ptr),
(v2f64 (alignedvecload node:$ptr))>;
def alignedloadv2i64 : PatFrag<(ops node:$ptr),
(v2i64 (alignedvecload node:$ptr))>;
// 256-bit aligned load pattern fragments
// NOTE: all 256-bit integer vector loads are promoted to v4i64
def alignedloadv8f32 : PatFrag<(ops node:$ptr),
(v8f32 (alignedvecload node:$ptr))>;
def alignedloadv4f64 : PatFrag<(ops node:$ptr),
(v4f64 (alignedvecload node:$ptr))>;
def alignedloadv4i64 : PatFrag<(ops node:$ptr),
(v4i64 (alignedvecload node:$ptr))>;
// 512-bit aligned load pattern fragments
def alignedloadv16f32 : PatFrag<(ops node:$ptr),
(v16f32 (alignedvecload node:$ptr))>;
def alignedloadv8f64 : PatFrag<(ops node:$ptr),
(v8f64 (alignedvecload node:$ptr))>;
def alignedloadv8i64 : PatFrag<(ops node:$ptr),
(v8i64 (alignedvecload node:$ptr))>;
// Like 'vecload', but uses special alignment checks suitable for use in
// memory operands in most SSE instructions, which are required to
// be naturally aligned on some targets but not on others. If the subtarget
// allows unaligned accesses, match any load, though this may require
// setting a feature bit in the processor (on startup, for example).
// Opteron 10h and later implement such a feature.
def memop : PatFrag<(ops node:$ptr), (vecload node:$ptr), [{
auto *Ld = cast<LoadSDNode>(N);
return Subtarget->hasSSEUnalignedMem() ||
Ld->getAlignment() >= Ld->getMemoryVT().getStoreSize();
}]>;
// 128-bit memop pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def memopv4f32 : PatFrag<(ops node:$ptr), (v4f32 (memop node:$ptr))>;
def memopv2f64 : PatFrag<(ops node:$ptr), (v2f64 (memop node:$ptr))>;
def memopv2i64 : PatFrag<(ops node:$ptr), (v2i64 (memop node:$ptr))>;
def X86masked_gather : SDNode<"X86ISD::MGATHER",
SDTypeProfile<2, 3, [SDTCisVec<0>,
SDTCisVec<1>, SDTCisInt<1>,
SDTCisSameAs<0, 2>,
SDTCisSameAs<1, 3>,
SDTCisPtrTy<4>]>,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def X86masked_scatter : SDNode<"X86ISD::MSCATTER",
SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisVec<1>,
SDTCisSameAs<0, 2>,
SDTCVecEltisVT<0, i1>,
SDTCisPtrTy<3>]>,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def mgatherv4i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v4i32;
}]>;
def mgatherv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v8i32;
}]>;
def mgatherv2i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v2i64;
}]>;
def mgatherv4i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v4i64;
}]>;
def mgatherv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v8i64;
}]>;
def mgatherv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_gather node:$src1, node:$src2, node:$src3) , [{
X86MaskedGatherSDNode *Mgt = cast<X86MaskedGatherSDNode>(N);
return Mgt->getIndex().getValueType() == MVT::v16i32;
}]>;
def mscatterv2i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v2i64;
}]>;
def mscatterv4i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v4i32;
}]>;
def mscatterv4i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v4i64;
}]>;
def mscatterv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v8i32;
}]>;
def mscatterv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v8i64;
}]>;
def mscatterv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86masked_scatter node:$src1, node:$src2, node:$src3) , [{
X86MaskedScatterSDNode *Sc = cast<X86MaskedScatterSDNode>(N);
return Sc->getIndex().getValueType() == MVT::v16i32;
}]>;
// 128-bit bitconvert pattern fragments
def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>;
def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>;
def bc_v16i8 : PatFrag<(ops node:$in), (v16i8 (bitconvert node:$in))>;
def bc_v8i16 : PatFrag<(ops node:$in), (v8i16 (bitconvert node:$in))>;
def bc_v4i32 : PatFrag<(ops node:$in), (v4i32 (bitconvert node:$in))>;
def bc_v2i64 : PatFrag<(ops node:$in), (v2i64 (bitconvert node:$in))>;
// 256-bit bitconvert pattern fragments
def bc_v32i8 : PatFrag<(ops node:$in), (v32i8 (bitconvert node:$in))>;
def bc_v16i16 : PatFrag<(ops node:$in), (v16i16 (bitconvert node:$in))>;
def bc_v8i32 : PatFrag<(ops node:$in), (v8i32 (bitconvert node:$in))>;
def bc_v4i64 : PatFrag<(ops node:$in), (v4i64 (bitconvert node:$in))>;
def bc_v8f32 : PatFrag<(ops node:$in), (v8f32 (bitconvert node:$in))>;
def bc_v4f64 : PatFrag<(ops node:$in), (v4f64 (bitconvert node:$in))>;
// 512-bit bitconvert pattern fragments
def bc_v64i8 : PatFrag<(ops node:$in), (v64i8 (bitconvert node:$in))>;
def bc_v16i32 : PatFrag<(ops node:$in), (v16i32 (bitconvert node:$in))>;
def bc_v8i64 : PatFrag<(ops node:$in), (v8i64 (bitconvert node:$in))>;
def bc_v8f64 : PatFrag<(ops node:$in), (v8f64 (bitconvert node:$in))>;
def bc_v16f32 : PatFrag<(ops node:$in), (v16f32 (bitconvert node:$in))>;
def vzmovl_v2i64 : PatFrag<(ops node:$src),
(bitconvert (v2i64 (X86vzmovl
(v2i64 (scalar_to_vector (loadi64 node:$src))))))>;
def vzmovl_v4i32 : PatFrag<(ops node:$src),
(bitconvert (v4i32 (X86vzmovl
(v4i32 (scalar_to_vector (loadi32 node:$src))))))>;
def vzload_v2i64 : PatFrag<(ops node:$src),
(bitconvert (v2i64 (X86vzload node:$src)))>;
def fp32imm0 : PatLeaf<(f32 fpimm), [{
return N->isExactlyValue(+0.0);
}]>;
def fp64imm0 : PatLeaf<(f64 fpimm), [{
return N->isExactlyValue(+0.0);
}]>;
def I8Imm : SDNodeXForm<imm, [{
// Transformation function: get the low 8 bits.
return getI8Imm((uint8_t)N->getZExtValue(), SDLoc(N));
}]>;
def FROUND_NO_EXC : ImmLeaf<i32, [{ return Imm == 8; }]>;
def FROUND_CURRENT : ImmLeaf<i32, [{
return Imm == X86::STATIC_ROUNDING::CUR_DIRECTION;
}]>;
// BYTE_imm - Transform bit immediates into byte immediates.
def BYTE_imm : SDNodeXForm<imm, [{
// Transformation function: imm >> 3
return getI32Imm(N->getZExtValue() >> 3, SDLoc(N));
}]>;
// EXTRACT_get_vextract128_imm xform function: convert extract_subvector index
// to VEXTRACTF128/VEXTRACTI128 imm.
def EXTRACT_get_vextract128_imm : SDNodeXForm<extract_subvector, [{
return getExtractVEXTRACTImmediate(N, 128, SDLoc(N));
}]>;
// INSERT_get_vinsert128_imm xform function: convert insert_subvector index to
// VINSERTF128/VINSERTI128 imm.
def INSERT_get_vinsert128_imm : SDNodeXForm<insert_subvector, [{
return getInsertVINSERTImmediate(N, 128, SDLoc(N));
}]>;
// EXTRACT_get_vextract256_imm xform function: convert extract_subvector index
// to VEXTRACTF64x4 imm.
def EXTRACT_get_vextract256_imm : SDNodeXForm<extract_subvector, [{
return getExtractVEXTRACTImmediate(N, 256, SDLoc(N));
}]>;
// INSERT_get_vinsert256_imm xform function: convert insert_subvector index to
// VINSERTF64x4 imm.
def INSERT_get_vinsert256_imm : SDNodeXForm<insert_subvector, [{
return getInsertVINSERTImmediate(N, 256, SDLoc(N));
}]>;
def vextract128_extract : PatFrag<(ops node:$bigvec, node:$index),
(extract_subvector node:$bigvec,
node:$index), [{}],
EXTRACT_get_vextract128_imm>;
def vinsert128_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
node:$index),
(insert_subvector node:$bigvec, node:$smallvec,
node:$index), [{}],
INSERT_get_vinsert128_imm>;
def vextract256_extract : PatFrag<(ops node:$bigvec, node:$index),
(extract_subvector node:$bigvec,
node:$index), [{}],
EXTRACT_get_vextract256_imm>;
def vinsert256_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
node:$index),
(insert_subvector node:$bigvec, node:$smallvec,
node:$index), [{}],
INSERT_get_vinsert256_imm>;
def X86mload : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_load node:$src1, node:$src2, node:$src3), [{
return !cast<MaskedLoadSDNode>(N)->isExpandingLoad() &&
cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::NON_EXTLOAD;
}]>;
def masked_load_aligned128 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mload node:$src1, node:$src2, node:$src3), [{
return cast<MaskedLoadSDNode>(N)->getAlignment() >= 16;
}]>;
def masked_load_aligned256 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mload node:$src1, node:$src2, node:$src3), [{
return cast<MaskedLoadSDNode>(N)->getAlignment() >= 32;
}]>;
def masked_load_aligned512 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mload node:$src1, node:$src2, node:$src3), [{
return cast<MaskedLoadSDNode>(N)->getAlignment() >= 64;
}]>;
def masked_load_unaligned : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_load node:$src1, node:$src2, node:$src3), [{
return !cast<MaskedLoadSDNode>(N)->isExpandingLoad() &&
cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::NON_EXTLOAD;
}]>;
def X86mExpandingLoad : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_load node:$src1, node:$src2, node:$src3), [{
return cast<MaskedLoadSDNode>(N)->isExpandingLoad();
}]>;
// Masked store fragments.
// X86mstore can't be implemented in core DAG files because some targets
// do not support vector types (llvm-tblgen will fail).
def X86mstore : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_store node:$src1, node:$src2, node:$src3), [{
return (!cast<MaskedStoreSDNode>(N)->isTruncatingStore()) &&
(!cast<MaskedStoreSDNode>(N)->isCompressingStore());
}]>;
def masked_store_aligned128 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getAlignment() >= 16;
}]>;
def masked_store_aligned256 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getAlignment() >= 32;
}]>;
def masked_store_aligned512 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getAlignment() >= 64;
}]>;
def masked_store_unaligned : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_store node:$src1, node:$src2, node:$src3), [{
return (!cast<MaskedStoreSDNode>(N)->isTruncatingStore()) &&
(!cast<MaskedStoreSDNode>(N)->isCompressingStore());
}]>;
def X86mCompressingStore : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_store node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->isCompressingStore();
}]>;
// masked truncstore fragments
// X86mtruncstore can't be implemented in core DAG files because some targets
// doesn't support vector type ( llvm-tblgen will fail)
def X86mtruncstore : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(masked_store node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->isTruncatingStore();
}]>;
def masked_truncstorevi8 :
PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mtruncstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def masked_truncstorevi16 :
PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mtruncstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def masked_truncstorevi32 :
PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86mtruncstore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;
def X86TruncSStore : SDNode<"X86ISD::VTRUNCSTORES", SDTStore,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def X86TruncUSStore : SDNode<"X86ISD::VTRUNCSTOREUS", SDTStore,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def X86MTruncSStore : SDNode<"X86ISD::VMTRUNCSTORES", SDTMaskedStore,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def X86MTruncUSStore : SDNode<"X86ISD::VMTRUNCSTOREUS", SDTMaskedStore,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def truncstore_s_vi8 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncSStore node:$val, node:$ptr), [{
return cast<TruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def truncstore_us_vi8 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncUSStore node:$val, node:$ptr), [{
return cast<TruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def truncstore_s_vi16 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncSStore node:$val, node:$ptr), [{
return cast<TruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def truncstore_us_vi16 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncUSStore node:$val, node:$ptr), [{
return cast<TruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def truncstore_s_vi32 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncSStore node:$val, node:$ptr), [{
return cast<TruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;
def truncstore_us_vi32 : PatFrag<(ops node:$val, node:$ptr),
(X86TruncUSStore node:$val, node:$ptr), [{
return cast<TruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;
def masked_truncstore_s_vi8 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def masked_truncstore_us_vi8 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncUSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def masked_truncstore_s_vi16 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def masked_truncstore_us_vi16 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncUSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def masked_truncstore_s_vi32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;
def masked_truncstore_us_vi32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(X86MTruncUSStore node:$src1, node:$src2, node:$src3), [{
return cast<MaskedTruncUSStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;