diff options
Diffstat (limited to 'llvm/lib')
| -rw-r--r-- | llvm/lib/Target/AArch64/AArch64InstrInfo.td | 27 | ||||
| -rw-r--r-- | llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp | 8 |
2 files changed, 16 insertions, 19 deletions
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td index 6c46b18..9f8a257 100644 --- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td +++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td @@ -1053,13 +1053,6 @@ def AArch64umaxv : SDNode<"AArch64ISD::UMAXV", SDT_AArch64UnaryVec>; def AArch64uaddlv : SDNode<"AArch64ISD::UADDLV", SDT_AArch64uaddlp>; def AArch64saddlv : SDNode<"AArch64ISD::SADDLV", SDT_AArch64uaddlp>; -def AArch64uabd : PatFrags<(ops node:$lhs, node:$rhs), - [(abdu node:$lhs, node:$rhs), - (int_aarch64_neon_uabd node:$lhs, node:$rhs)]>; -def AArch64sabd : PatFrags<(ops node:$lhs, node:$rhs), - [(abds node:$lhs, node:$rhs), - (int_aarch64_neon_sabd node:$lhs, node:$rhs)]>; - // Add Pairwise of two vectors def AArch64addp_n : SDNode<"AArch64ISD::ADDP", SDT_AArch64Zip>; // Add Long Pairwise @@ -5667,8 +5660,7 @@ let Predicates = [HasFullFP16] in { // Advanced SIMD two vector instructions. //===----------------------------------------------------------------------===// -defm UABDL : SIMDLongThreeVectorBHSabdl<1, 0b0111, "uabdl", - AArch64uabd>; +defm UABDL : SIMDLongThreeVectorBHSabdl<1, 0b0111, "uabdl", abdu>; // Match UABDL in log2-shuffle patterns. def : Pat<(abs (v8i16 (sub (zext (v8i8 V64:$opA)), (zext (v8i8 V64:$opB))))), @@ -6018,8 +6010,8 @@ defm MLS : SIMDThreeSameVectorBHSTied<1, 0b10010, "mls", null_frag>; defm MUL : SIMDThreeSameVectorBHS<0, 0b10011, "mul", mul>; defm PMUL : SIMDThreeSameVectorB<1, 0b10011, "pmul", int_aarch64_neon_pmul>; defm SABA : SIMDThreeSameVectorBHSTied<0, 0b01111, "saba", - TriOpFrag<(add node:$LHS, (AArch64sabd node:$MHS, node:$RHS))> >; -defm SABD : SIMDThreeSameVectorBHS<0,0b01110,"sabd", AArch64sabd>; + TriOpFrag<(add node:$LHS, (abds node:$MHS, node:$RHS))> >; +defm SABD : SIMDThreeSameVectorBHS<0,0b01110,"sabd", abds>; defm SHADD : SIMDThreeSameVectorBHS<0,0b00000,"shadd", avgfloors>; defm SHSUB : SIMDThreeSameVectorBHS<0,0b00100,"shsub", int_aarch64_neon_shsub>; defm SMAXP : SIMDThreeSameVectorBHS<0,0b10100,"smaxp", int_aarch64_neon_smaxp>; @@ -6037,8 +6029,8 @@ defm SRSHL : SIMDThreeSameVector<0,0b01010,"srshl", int_aarch64_neon_srshl>; defm SSHL : SIMDThreeSameVector<0,0b01000,"sshl", int_aarch64_neon_sshl>; defm SUB : SIMDThreeSameVector<1,0b10000,"sub", sub>; defm UABA : SIMDThreeSameVectorBHSTied<1, 0b01111, "uaba", - TriOpFrag<(add node:$LHS, (AArch64uabd node:$MHS, node:$RHS))> >; -defm UABD : SIMDThreeSameVectorBHS<1,0b01110,"uabd", AArch64uabd>; + TriOpFrag<(add node:$LHS, (abdu node:$MHS, node:$RHS))> >; +defm UABD : SIMDThreeSameVectorBHS<1,0b01110,"uabd", abdu>; defm UHADD : SIMDThreeSameVectorBHS<1,0b00000,"uhadd", avgflooru>; defm UHSUB : SIMDThreeSameVectorBHS<1,0b00100,"uhsub", int_aarch64_neon_uhsub>; defm UMAXP : SIMDThreeSameVectorBHS<1,0b10100,"umaxp", int_aarch64_neon_umaxp>; @@ -6759,10 +6751,8 @@ defm SUBHN : SIMDNarrowThreeVectorBHS<0,0b0110,"subhn", int_aarch64_neon_subhn> defm RADDHN : SIMDNarrowThreeVectorBHS<1,0b0100,"raddhn",int_aarch64_neon_raddhn>; defm RSUBHN : SIMDNarrowThreeVectorBHS<1,0b0110,"rsubhn",int_aarch64_neon_rsubhn>; defm PMULL : SIMDDifferentThreeVectorBD<0,0b1110,"pmull", AArch64pmull>; -defm SABAL : SIMDLongThreeVectorTiedBHSabal<0,0b0101,"sabal", - AArch64sabd>; -defm SABDL : SIMDLongThreeVectorBHSabdl<0, 0b0111, "sabdl", - AArch64sabd>; +defm SABAL : SIMDLongThreeVectorTiedBHSabal<0,0b0101,"sabal", abds>; +defm SABDL : SIMDLongThreeVectorBHSabdl<0, 0b0111, "sabdl", abds>; defm SADDL : SIMDLongThreeVectorBHS< 0, 0b0000, "saddl", BinOpFrag<(add (sext node:$LHS), (sext node:$RHS))>>; defm SADDW : SIMDWideThreeVectorBHS< 0, 0b0001, "saddw", @@ -6780,8 +6770,7 @@ defm SSUBL : SIMDLongThreeVectorBHS<0, 0b0010, "ssubl", BinOpFrag<(sub (sext node:$LHS), (sext node:$RHS))>>; defm SSUBW : SIMDWideThreeVectorBHS<0, 0b0011, "ssubw", BinOpFrag<(sub node:$LHS, (sext node:$RHS))>>; -defm UABAL : SIMDLongThreeVectorTiedBHSabal<1, 0b0101, "uabal", - AArch64uabd>; +defm UABAL : SIMDLongThreeVectorTiedBHSabal<1, 0b0101, "uabal", abdu>; defm UADDL : SIMDLongThreeVectorBHS<1, 0b0000, "uaddl", BinOpFrag<(add (zanyext node:$LHS), (zanyext node:$RHS))>>; defm UADDW : SIMDWideThreeVectorBHS<1, 0b0001, "uaddw", diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp index 473ba5e..bb0f667b 100644 --- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp +++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp @@ -287,6 +287,10 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST) .moreElementsToNextPow2(0) .lower(); + getActionDefinitionsBuilder({G_ABDS, G_ABDU}) + .legalFor({v8s8, v16s8, v4s16, v8s16, v2s32, v4s32}) + .lower(); + getActionDefinitionsBuilder( {G_SADDE, G_SSUBE, G_UADDE, G_USUBE, G_SADDO, G_SSUBO, G_UADDO, G_USUBO}) .legalFor({{s32, s32}, {s64, s32}}) @@ -1794,6 +1798,10 @@ bool AArch64LegalizerInfo::legalizeIntrinsic(LegalizerHelper &Helper, return LowerBinOp(AArch64::G_SMULL); case Intrinsic::aarch64_neon_umull: return LowerBinOp(AArch64::G_UMULL); + case Intrinsic::aarch64_neon_sabd: + return LowerBinOp(TargetOpcode::G_ABDS); + case Intrinsic::aarch64_neon_uabd: + return LowerBinOp(TargetOpcode::G_ABDU); case Intrinsic::aarch64_neon_abs: { // Lower the intrinsic to G_ABS. MIB.buildInstr(TargetOpcode::G_ABS, {MI.getOperand(0)}, {MI.getOperand(2)}); |