diff options
author | Artyom Skrobov <Artyom.Skrobov@arm.com> | 2017-03-22 23:35:51 +0000 |
---|---|---|
committer | Artyom Skrobov <Artyom.Skrobov@arm.com> | 2017-03-22 23:35:51 +0000 |
commit | 92c0653095f5db544ff52cfb72cc1726b2cdf345 (patch) | |
tree | 0ecabedbc90af3633442fca1f2e425630fa85373 /llvm/lib/Target | |
parent | 3eb2b44d31ff921041eb5b55333c77d6fb16eb61 (diff) | |
download | bcm5719-llvm-92c0653095f5db544ff52cfb72cc1726b2cdf345.tar.gz bcm5719-llvm-92c0653095f5db544ff52cfb72cc1726b2cdf345.zip |
Reapply r298417 "[ARM] Recommit the glueless lowering of addc/adde in Thumb1"
The UB in t2_so_imm_neg conversion has been addressed under D31242 / r298512
This reverts commit r298482.
llvm-svn: 298562
Diffstat (limited to 'llvm/lib/Target')
-rw-r--r-- | llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp | 10 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMISelLowering.cpp | 96 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMInstrThumb.td | 92 |
3 files changed, 167 insertions, 31 deletions
diff --git a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp index 72868828596..4f5711ca9a7 100644 --- a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp +++ b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp @@ -2028,6 +2028,16 @@ static const AddSubFlagsOpcodePair AddSubFlagsOpcodeMap[] = { {ARM::RSBSrsi, ARM::RSBrsi}, {ARM::RSBSrsr, ARM::RSBrsr}, + {ARM::tADDSi3, ARM::tADDi3}, + {ARM::tADDSi8, ARM::tADDi8}, + {ARM::tADDSrr, ARM::tADDrr}, + {ARM::tADCS, ARM::tADC}, + + {ARM::tSUBSi3, ARM::tSUBi3}, + {ARM::tSUBSi8, ARM::tSUBi8}, + {ARM::tSUBSrr, ARM::tSUBrr}, + {ARM::tSBCS, ARM::tSBC}, + {ARM::t2ADDSri, ARM::t2ADDri}, {ARM::t2ADDSrr, ARM::t2ADDrr}, {ARM::t2ADDSrs, ARM::t2ADDrs}, diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp index e3723788223..0c17211cce3 100644 --- a/llvm/lib/Target/ARM/ARMISelLowering.cpp +++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp @@ -822,13 +822,10 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM, setOperationAction(ISD::SRL, MVT::i64, Custom); setOperationAction(ISD::SRA, MVT::i64, Custom); - if (!Subtarget->isThumb1Only()) { - // FIXME: We should do this for Thumb1 as well. - setOperationAction(ISD::ADDC, MVT::i32, Custom); - setOperationAction(ISD::ADDE, MVT::i32, Custom); - setOperationAction(ISD::SUBC, MVT::i32, Custom); - setOperationAction(ISD::SUBE, MVT::i32, Custom); - } + setOperationAction(ISD::ADDC, MVT::i32, Custom); + setOperationAction(ISD::ADDE, MVT::i32, Custom); + setOperationAction(ISD::SUBC, MVT::i32, Custom); + setOperationAction(ISD::SUBE, MVT::i32, Custom); if (!Subtarget->isThumb1Only() && Subtarget->hasV6T2Ops()) setOperationAction(ISD::BITREVERSE, MVT::i32, Legal); @@ -9096,19 +9093,45 @@ void ARMTargetLowering::AdjustInstrPostInstrSelection(MachineInstr &MI, // Rename pseudo opcodes. unsigned NewOpc = convertAddSubFlagsOpcode(MI.getOpcode()); + unsigned ccOutIdx; if (NewOpc) { const ARMBaseInstrInfo *TII = Subtarget->getInstrInfo(); MCID = &TII->get(NewOpc); - assert(MCID->getNumOperands() == MI.getDesc().getNumOperands() + 1 && - "converted opcode should be the same except for cc_out"); + assert(MCID->getNumOperands() == + MI.getDesc().getNumOperands() + 5 - MI.getDesc().getSize() + && "converted opcode should be the same except for cc_out" + " (and, on Thumb1, pred)"); MI.setDesc(*MCID); // Add the optional cc_out operand MI.addOperand(MachineOperand::CreateReg(0, /*isDef=*/true)); - } - unsigned ccOutIdx = MCID->getNumOperands() - 1; + + // On Thumb1, move all input operands to the end, then add the predicate + if (Subtarget->isThumb1Only()) { + for (unsigned c = MCID->getNumOperands() - 4; c--;) { + MI.addOperand(MI.getOperand(1)); + MI.RemoveOperand(1); + } + + // Restore the ties + for (unsigned i = MI.getNumOperands(); i--;) { + const MachineOperand& op = MI.getOperand(i); + if (op.isReg() && op.isUse()) { + int DefIdx = MCID->getOperandConstraint(i, MCOI::TIED_TO); + if (DefIdx != -1) + MI.tieOperands(DefIdx, i); + } + } + + MI.addOperand(MachineOperand::CreateImm(ARMCC::AL)); + MI.addOperand(MachineOperand::CreateReg(0, /*isDef=*/false)); + ccOutIdx = 1; + } else + ccOutIdx = MCID->getNumOperands() - 1; + } else + ccOutIdx = MCID->getNumOperands() - 1; // Any ARM instruction that sets the 's' bit should specify an optional // "cc_out" operand in the last operand position. @@ -9139,7 +9162,9 @@ void ARMTargetLowering::AdjustInstrPostInstrSelection(MachineInstr &MI, if (deadCPSR) { assert(!MI.getOperand(ccOutIdx).getReg() && "expect uninitialized optional cc_out operand"); - return; + // Thumb1 instructions must have the S bit even if the CPSR is dead. + if (!Subtarget->isThumb1Only()) + return; } // If this instruction was defined with an optional CPSR def and its dag node @@ -9759,6 +9784,48 @@ static SDValue PerformUMLALCombine(SDNode *N, SelectionDAG &DAG, return SDValue(); } +static SDValue PerformAddcSubcCombine(SDNode *N, SelectionDAG &DAG, + const ARMSubtarget *Subtarget) { + if (Subtarget->isThumb1Only()) { + SDValue RHS = N->getOperand(1); + if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(RHS)) { + int32_t imm = C->getSExtValue(); + if (imm < 0 && imm > INT_MIN) { + SDLoc DL(N); + RHS = DAG.getConstant(-imm, DL, MVT::i32); + unsigned Opcode = (N->getOpcode() == ARMISD::ADDC) ? ARMISD::SUBC + : ARMISD::ADDC; + return DAG.getNode(Opcode, DL, N->getVTList(), N->getOperand(0), RHS); + } + } + } + return SDValue(); +} + +static SDValue PerformAddeSubeCombine(SDNode *N, SelectionDAG &DAG, + const ARMSubtarget *Subtarget) { + if (Subtarget->isThumb1Only()) { + SDValue RHS = N->getOperand(1); + if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(RHS)) { + int64_t imm = C->getSExtValue(); + if (imm < 0) { + SDLoc DL(N); + + // The with-carry-in form matches bitwise not instead of the negation. + // Effectively, the inverse interpretation of the carry flag already + // accounts for part of the negation. + RHS = DAG.getConstant(~imm, DL, MVT::i32); + + unsigned Opcode = (N->getOpcode() == ARMISD::ADDE) ? ARMISD::SUBE + : ARMISD::ADDE; + return DAG.getNode(Opcode, DL, N->getVTList(), + N->getOperand(0), RHS, N->getOperand(2)); + } + } + } + return SDValue(); +} + /// PerformADDECombine - Target-specific dag combine transform from /// ARMISD::ADDC, ARMISD::ADDE, and ISD::MUL_LOHI to MLAL or /// ARMISD::ADDC, ARMISD::ADDE and ARMISD::UMLAL to ARMISD::UMAAL @@ -9767,7 +9834,7 @@ static SDValue PerformADDECombine(SDNode *N, const ARMSubtarget *Subtarget) { // Only ARM and Thumb2 support UMLAL/SMLAL. if (Subtarget->isThumb1Only()) - return SDValue(); + return PerformAddeSubeCombine(N, DCI.DAG, Subtarget); // Only perform the checks after legalize when the pattern is available. if (DCI.isBeforeLegalize()) return SDValue(); @@ -11867,6 +11934,9 @@ SDValue ARMTargetLowering::PerformDAGCombine(SDNode *N, case ISD::OR: return PerformORCombine(N, DCI, Subtarget); case ISD::XOR: return PerformXORCombine(N, DCI, Subtarget); case ISD::AND: return PerformANDCombine(N, DCI, Subtarget); + case ARMISD::ADDC: + case ARMISD::SUBC: return PerformAddcSubcCombine(N, DCI.DAG, Subtarget); + case ARMISD::SUBE: return PerformAddeSubeCombine(N, DCI.DAG, Subtarget); case ARMISD::BFI: return PerformBFICombine(N, DCI); case ARMISD::VMOVRRD: return PerformVMOVRRDCombine(N, DCI, Subtarget); case ARMISD::VMOVDRR: return PerformVMOVDRRCombine(N, DCI.DAG); diff --git a/llvm/lib/Target/ARM/ARMInstrThumb.td b/llvm/lib/Target/ARM/ARMInstrThumb.td index e6934cb04ef..c372bcdc262 100644 --- a/llvm/lib/Target/ARM/ARMInstrThumb.td +++ b/llvm/lib/Target/ARM/ARMInstrThumb.td @@ -922,7 +922,7 @@ let isAdd = 1 in { def tADC : // A8.6.2 T1sItDPEncode<0b0101, (outs tGPR:$Rdn), (ins tGPR:$Rn, tGPR:$Rm), IIC_iALUr, "adc", "\t$Rdn, $Rm", - [(set tGPR:$Rdn, (adde tGPR:$Rn, tGPR:$Rm))]>, Sched<[WriteALU]>; + []>, Sched<[WriteALU]>; // Add immediate def tADDi3 : // A8.6.4 T1 @@ -950,6 +950,43 @@ let isAdd = 1 in { "add", "\t$Rd, $Rn, $Rm", [(set tGPR:$Rd, (add tGPR:$Rn, tGPR:$Rm))]>, Sched<[WriteALU]>; + /// Similar to the above except these set the 's' bit so the + /// instruction modifies the CPSR register. + /// + /// These opcodes will be converted to the real non-S opcodes by + /// AdjustInstrPostInstrSelection after giving then an optional CPSR operand. + let hasPostISelHook = 1, Defs = [CPSR] in { + let isCommutable = 1 in + def tADCS : tPseudoInst<(outs tGPR:$Rdn), (ins tGPR:$Rn, tGPR:$Rm), + 2, IIC_iALUr, + [(set tGPR:$Rdn, CPSR, (ARMadde tGPR:$Rn, tGPR:$Rm, + CPSR))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + def tADDSi3 : tPseudoInst<(outs tGPR:$Rd), (ins tGPR:$Rm, imm0_7:$imm3), + 2, IIC_iALUi, + [(set tGPR:$Rd, CPSR, (ARMaddc tGPR:$Rm, + imm0_7:$imm3))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + def tADDSi8 : tPseudoInst<(outs tGPR:$Rdn), (ins tGPR:$Rn, imm0_255:$imm8), + 2, IIC_iALUi, + [(set tGPR:$Rdn, CPSR, (ARMaddc tGPR:$Rn, + imm8_255:$imm8))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + let isCommutable = 1 in + def tADDSrr : tPseudoInst<(outs tGPR:$Rd), (ins tGPR:$Rn, tGPR:$Rm), + 2, IIC_iALUr, + [(set tGPR:$Rd, CPSR, (ARMaddc tGPR:$Rn, + tGPR:$Rm))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + } + let hasSideEffects = 0 in def tADDhirr : T1pIt<(outs GPR:$Rdn), (ins GPR:$Rn, GPR:$Rm), IIC_iALUr, "add", "\t$Rdn, $Rm", []>, @@ -1215,7 +1252,7 @@ def tSBC : // A8.6.151 T1sItDPEncode<0b0110, (outs tGPR:$Rdn), (ins tGPR:$Rn, tGPR:$Rm), IIC_iALUr, "sbc", "\t$Rdn, $Rm", - [(set tGPR:$Rdn, (sube tGPR:$Rn, tGPR:$Rm))]>, + []>, Sched<[WriteALU]>; // Subtract immediate @@ -1252,6 +1289,41 @@ def tSUBrr : // A8.6.212 [(set tGPR:$Rd, (sub tGPR:$Rn, tGPR:$Rm))]>, Sched<[WriteALU]>; +/// Similar to the above except these set the 's' bit so the +/// instruction modifies the CPSR register. +/// +/// These opcodes will be converted to the real non-S opcodes by +/// AdjustInstrPostInstrSelection after giving then an optional CPSR operand. +let hasPostISelHook = 1, Defs = [CPSR] in { + def tSBCS : tPseudoInst<(outs tGPR:$Rdn), (ins tGPR:$Rn, tGPR:$Rm), + 2, IIC_iALUr, + [(set tGPR:$Rdn, CPSR, (ARMsube tGPR:$Rn, tGPR:$Rm, + CPSR))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + def tSUBSi3 : tPseudoInst<(outs tGPR:$Rd), (ins tGPR:$Rm, imm0_7:$imm3), + 2, IIC_iALUi, + [(set tGPR:$Rd, CPSR, (ARMsubc tGPR:$Rm, + imm0_7:$imm3))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + def tSUBSi8 : tPseudoInst<(outs tGPR:$Rdn), (ins tGPR:$Rn, imm0_255:$imm8), + 2, IIC_iALUi, + [(set tGPR:$Rdn, CPSR, (ARMsubc tGPR:$Rn, + imm8_255:$imm8))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; + + def tSUBSrr : tPseudoInst<(outs tGPR:$Rd), (ins tGPR:$Rn, tGPR:$Rm), + 2, IIC_iALUr, + [(set tGPR:$Rd, CPSR, (ARMsubc tGPR:$Rn, + tGPR:$Rm))]>, + Requires<[IsThumb1Only]>, + Sched<[WriteALU]>; +} + // Sign-extend byte def tSXTB : // A8.6.222 T1pIMiscEncode<{0,0,1,0,0,1,?}, (outs tGPR:$Rd), (ins tGPR:$Rm), @@ -1412,22 +1484,6 @@ def : T1Pat<(ARMcmpZ tGPR:$Rn, imm0_255:$imm8), def : T1Pat<(ARMcmpZ tGPR:$Rn, tGPR:$Rm), (tCMPr tGPR:$Rn, tGPR:$Rm)>; -// Add with carry -def : T1Pat<(addc tGPR:$lhs, imm0_7:$rhs), - (tADDi3 tGPR:$lhs, imm0_7:$rhs)>; -def : T1Pat<(addc tGPR:$lhs, imm8_255:$rhs), - (tADDi8 tGPR:$lhs, imm8_255:$rhs)>; -def : T1Pat<(addc tGPR:$lhs, tGPR:$rhs), - (tADDrr tGPR:$lhs, tGPR:$rhs)>; - -// Subtract with carry -def : T1Pat<(addc tGPR:$lhs, imm0_7_neg:$rhs), - (tSUBi3 tGPR:$lhs, imm0_7_neg:$rhs)>; -def : T1Pat<(addc tGPR:$lhs, imm8_255_neg:$rhs), - (tSUBi8 tGPR:$lhs, imm8_255_neg:$rhs)>; -def : T1Pat<(subc tGPR:$lhs, tGPR:$rhs), - (tSUBrr tGPR:$lhs, tGPR:$rhs)>; - // Bswap 16 with load/store def : T1Pat<(srl (bswap (extloadi16 t_addrmode_is2:$addr)), (i32 16)), (tREV16 (tLDRHi t_addrmode_is2:$addr))>; |