Index: include/llvm/Target/TargetLowering.h =================================================================== --- include/llvm/Target/TargetLowering.h +++ include/llvm/Target/TargetLowering.h @@ -87,6 +87,7 @@ Legal, // The target natively supports this operation. Promote, // This operation should be executed in a larger type. Expand, // Try to expand this to other ops, otherwise use a libcall. + LibCall, // Don't try to expand this to other ops, always use a libcall. Custom // Use the LowerOperation hook to implement custom lowering. }; Index: lib/CodeGen/SelectionDAG/LegalizeDAG.cpp =================================================================== --- lib/CodeGen/SelectionDAG/LegalizeDAG.cpp +++ lib/CodeGen/SelectionDAG/LegalizeDAG.cpp @@ -147,9 +147,8 @@ SDValue ExpandConstantFP(ConstantFPSDNode *CFP, bool UseCP); - std::pair ExpandAtomic(SDNode *Node); - - void ExpandNode(SDNode *Node); + bool ExpandNode(SDNode *Node); + void ConvertNodeToLibcall(SDNode *Node); void PromoteNode(SDNode *Node); public: @@ -1390,7 +1389,11 @@ } // FALL THROUGH case TargetLowering::Expand: - ExpandNode(Node); + if (ExpandNode(Node)) + return; + // FALL THROUGH + case TargetLowering::LibCall: + ConvertNodeToLibcall(Node); return; case TargetLowering::Promote: PromoteNode(Node); @@ -2842,16 +2845,7 @@ } } -std::pair SelectionDAGLegalize::ExpandAtomic(SDNode *Node) { - unsigned Opc = Node->getOpcode(); - MVT VT = cast(Node)->getMemoryVT().getSimpleVT(); - RTLIB::Libcall LC = RTLIB::getATOMIC(Opc, VT); - assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unexpected atomic op or value type!"); - - return ExpandChainLibCall(LC, Node, false); -} - -void SelectionDAGLegalize::ExpandNode(SDNode *Node) { +bool SelectionDAGLegalize::ExpandNode(SDNode *Node) { SmallVector Results; SDLoc dl(Node); SDValue Tmp1, Tmp2, Tmp3, Tmp4; @@ -2898,24 +2892,6 @@ Results.push_back(DAG.getConstant(0, dl, MVT::i32)); Results.push_back(Node->getOperand(0)); break; - case ISD::ATOMIC_FENCE: { - // If the target didn't lower this, lower it to '__sync_synchronize()' call - // FIXME: handle "fence singlethread" more efficiently. - TargetLowering::ArgListTy Args; - - TargetLowering::CallLoweringInfo CLI(DAG); - CLI.setDebugLoc(dl) - .setChain(Node->getOperand(0)) - .setCallee(CallingConv::C, Type::getVoidTy(*DAG.getContext()), - DAG.getExternalSymbol("__sync_synchronize", - TLI.getPointerTy(DAG.getDataLayout())), - std::move(Args), 0); - - std::pair CallResult = TLI.LowerCallTo(CLI); - - Results.push_back(CallResult.second); - break; - } case ISD::ATOMIC_LOAD: { // There is no libcall for atomic load; fake it with ATOMIC_CMP_SWAP. SDValue Zero = DAG.getConstant(0, dl, Node->getValueType(0)); @@ -2943,26 +2919,6 @@ Results.push_back(Swap.getValue(1)); break; } - // By default, atomic intrinsics are marked Legal and lowered. Targets - // which don't support them directly, however, may want libcalls, in which - // case they mark them Expand, and we get here. - case ISD::ATOMIC_SWAP: - case ISD::ATOMIC_LOAD_ADD: - case ISD::ATOMIC_LOAD_SUB: - case ISD::ATOMIC_LOAD_AND: - case ISD::ATOMIC_LOAD_OR: - case ISD::ATOMIC_LOAD_XOR: - case ISD::ATOMIC_LOAD_NAND: - case ISD::ATOMIC_LOAD_MIN: - case ISD::ATOMIC_LOAD_MAX: - case ISD::ATOMIC_LOAD_UMIN: - case ISD::ATOMIC_LOAD_UMAX: - case ISD::ATOMIC_CMP_SWAP: { - std::pair Tmp = ExpandAtomic(Node); - Results.push_back(Tmp.first); - Results.push_back(Tmp.second); - break; - } case ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS: { // Expanding an ATOMIC_CMP_SWAP_WITH_SUCCESS produces an ATOMIC_CMP_SWAP and // splits out the success value as a comparison. Expanding the resulting @@ -3001,21 +2957,6 @@ } break; } - case ISD::TRAP: { - // If this operation is not supported, lower it to 'abort()' call - TargetLowering::ArgListTy Args; - TargetLowering::CallLoweringInfo CLI(DAG); - CLI.setDebugLoc(dl) - .setChain(Node->getOperand(0)) - .setCallee(CallingConv::C, Type::getVoidTy(*DAG.getContext()), - DAG.getExternalSymbol("abort", - TLI.getPointerTy(DAG.getDataLayout())), - std::move(Args), 0); - std::pair CallResult = TLI.LowerCallTo(CLI); - - Results.push_back(CallResult.second); - break; - } case ISD::FP_ROUND: case ISD::BITCAST: Tmp1 = EmitStackConvert(Node->getOperand(0), Node->getValueType(0), @@ -3286,25 +3227,9 @@ break; } - case ISD::FMINNUM: - Results.push_back(ExpandFPLibCall(Node, RTLIB::FMIN_F32, RTLIB::FMIN_F64, - RTLIB::FMIN_F80, RTLIB::FMIN_F128, - RTLIB::FMIN_PPCF128)); - break; - case ISD::FMAXNUM: - Results.push_back(ExpandFPLibCall(Node, RTLIB::FMAX_F32, RTLIB::FMAX_F64, - RTLIB::FMAX_F80, RTLIB::FMAX_F128, - RTLIB::FMAX_PPCF128)); - break; - case ISD::FSQRT: - Results.push_back(ExpandFPLibCall(Node, RTLIB::SQRT_F32, RTLIB::SQRT_F64, - RTLIB::SQRT_F80, RTLIB::SQRT_F128, - RTLIB::SQRT_PPCF128)); - break; case ISD::FSIN: case ISD::FCOS: { EVT VT = Node->getValueType(0); - bool isSIN = Node->getOpcode() == ISD::FSIN; // Turn fsin / fcos into ISD::FSINCOS node if there are a pair of fsin / // fcos which share the same operand and both are used. if ((TLI.isOperationLegalOrCustom(ISD::FSINCOS, VT) || @@ -3312,137 +3237,27 @@ && useSinCos(Node)) { SDVTList VTs = DAG.getVTList(VT, VT); Tmp1 = DAG.getNode(ISD::FSINCOS, dl, VTs, Node->getOperand(0)); - if (!isSIN) + if (Node->getOpcode() == ISD::FCOS) Tmp1 = Tmp1.getValue(1); Results.push_back(Tmp1); - } else if (isSIN) { - Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64, - RTLIB::SIN_F80, RTLIB::SIN_F128, - RTLIB::SIN_PPCF128)); - } else { - Results.push_back(ExpandFPLibCall(Node, RTLIB::COS_F32, RTLIB::COS_F64, - RTLIB::COS_F80, RTLIB::COS_F128, - RTLIB::COS_PPCF128)); } break; } - case ISD::FSINCOS: - // Expand into sincos libcall. - ExpandSinCosLibCall(Node, Results); - break; - case ISD::FLOG: - Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG_F32, RTLIB::LOG_F64, - RTLIB::LOG_F80, RTLIB::LOG_F128, - RTLIB::LOG_PPCF128)); - break; - case ISD::FLOG2: - Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG2_F32, RTLIB::LOG2_F64, - RTLIB::LOG2_F80, RTLIB::LOG2_F128, - RTLIB::LOG2_PPCF128)); - break; - case ISD::FLOG10: - Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG10_F32, RTLIB::LOG10_F64, - RTLIB::LOG10_F80, RTLIB::LOG10_F128, - RTLIB::LOG10_PPCF128)); - break; - case ISD::FEXP: - Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP_F32, RTLIB::EXP_F64, - RTLIB::EXP_F80, RTLIB::EXP_F128, - RTLIB::EXP_PPCF128)); - break; - case ISD::FEXP2: - Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP2_F32, RTLIB::EXP2_F64, - RTLIB::EXP2_F80, RTLIB::EXP2_F128, - RTLIB::EXP2_PPCF128)); - break; - case ISD::FTRUNC: - Results.push_back(ExpandFPLibCall(Node, RTLIB::TRUNC_F32, RTLIB::TRUNC_F64, - RTLIB::TRUNC_F80, RTLIB::TRUNC_F128, - RTLIB::TRUNC_PPCF128)); - break; - case ISD::FFLOOR: - Results.push_back(ExpandFPLibCall(Node, RTLIB::FLOOR_F32, RTLIB::FLOOR_F64, - RTLIB::FLOOR_F80, RTLIB::FLOOR_F128, - RTLIB::FLOOR_PPCF128)); - break; - case ISD::FCEIL: - Results.push_back(ExpandFPLibCall(Node, RTLIB::CEIL_F32, RTLIB::CEIL_F64, - RTLIB::CEIL_F80, RTLIB::CEIL_F128, - RTLIB::CEIL_PPCF128)); - break; - case ISD::FRINT: - Results.push_back(ExpandFPLibCall(Node, RTLIB::RINT_F32, RTLIB::RINT_F64, - RTLIB::RINT_F80, RTLIB::RINT_F128, - RTLIB::RINT_PPCF128)); - break; - case ISD::FNEARBYINT: - Results.push_back(ExpandFPLibCall(Node, RTLIB::NEARBYINT_F32, - RTLIB::NEARBYINT_F64, - RTLIB::NEARBYINT_F80, - RTLIB::NEARBYINT_F128, - RTLIB::NEARBYINT_PPCF128)); - break; - case ISD::FROUND: - Results.push_back(ExpandFPLibCall(Node, RTLIB::ROUND_F32, - RTLIB::ROUND_F64, - RTLIB::ROUND_F80, - RTLIB::ROUND_F128, - RTLIB::ROUND_PPCF128)); - break; - case ISD::FPOWI: - Results.push_back(ExpandFPLibCall(Node, RTLIB::POWI_F32, RTLIB::POWI_F64, - RTLIB::POWI_F80, RTLIB::POWI_F128, - RTLIB::POWI_PPCF128)); - break; - case ISD::FPOW: - Results.push_back(ExpandFPLibCall(Node, RTLIB::POW_F32, RTLIB::POW_F64, - RTLIB::POW_F80, RTLIB::POW_F128, - RTLIB::POW_PPCF128)); - break; - case ISD::FDIV: - Results.push_back(ExpandFPLibCall(Node, RTLIB::DIV_F32, RTLIB::DIV_F64, - RTLIB::DIV_F80, RTLIB::DIV_F128, - RTLIB::DIV_PPCF128)); - break; - case ISD::FREM: - Results.push_back(ExpandFPLibCall(Node, RTLIB::REM_F32, RTLIB::REM_F64, - RTLIB::REM_F80, RTLIB::REM_F128, - RTLIB::REM_PPCF128)); - break; - case ISD::FMA: - Results.push_back(ExpandFPLibCall(Node, RTLIB::FMA_F32, RTLIB::FMA_F64, - RTLIB::FMA_F80, RTLIB::FMA_F128, - RTLIB::FMA_PPCF128)); - break; case ISD::FMAD: llvm_unreachable("Illegal fmad should never be formed"); - case ISD::FADD: - Results.push_back(ExpandFPLibCall(Node, RTLIB::ADD_F32, RTLIB::ADD_F64, - RTLIB::ADD_F80, RTLIB::ADD_F128, - RTLIB::ADD_PPCF128)); - break; - case ISD::FMUL: - Results.push_back(ExpandFPLibCall(Node, RTLIB::MUL_F32, RTLIB::MUL_F64, - RTLIB::MUL_F80, RTLIB::MUL_F128, - RTLIB::MUL_PPCF128)); - break; - case ISD::FP16_TO_FP: { - if (Node->getValueType(0) == MVT::f32) { - Results.push_back(ExpandLibCall(RTLIB::FPEXT_F16_F32, Node, false)); - break; + case ISD::FP16_TO_FP: + if (Node->getValueType(0) != MVT::f32) { + // We can extend to types bigger than f32 in two steps without changing + // the result. Since "f16 -> f32" is much more commonly available, give + // CodeGen the option of emitting that before resorting to a libcall. + SDValue Res = + DAG.getNode(ISD::FP16_TO_FP, dl, MVT::f32, Node->getOperand(0)); + Results.push_back( + DAG.getNode(ISD::FP_EXTEND, dl, Node->getValueType(0), Res)); } - - // We can extend to types bigger than f32 in two steps without changing the - // result. Since "f16 -> f32" is much more commonly available, give CodeGen - // the option of emitting that before resorting to a libcall. - SDValue Res = - DAG.getNode(ISD::FP16_TO_FP, dl, MVT::f32, Node->getOperand(0)); - Results.push_back( - DAG.getNode(ISD::FP_EXTEND, dl, Node->getValueType(0), Res)); break; - } - case ISD::FP_TO_FP16: { + case ISD::FP_TO_FP16: if (!TLI.useSoftFloat() && TM.Options.UnsafeFPMath) { SDValue Op = Node->getOperand(0); MVT SVT = Op.getSimpleValueType(); @@ -3454,16 +3269,9 @@ DAG.getIntPtrConstant(0, dl)); Results.push_back( DAG.getNode(ISD::FP_TO_FP16, dl, MVT::i16, FloatVal)); - break; } } - - RTLIB::Libcall LC = - RTLIB::getFPROUND(Node->getOperand(0).getValueType(), MVT::f16); - assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unable to expand fp_to_fp16"); - Results.push_back(ExpandLibCall(LC, Node, false)); break; - } case ISD::ConstantFP: { ConstantFPSDNode *CFP = cast(Node); // Check to see if this FP immediate is already legal. @@ -3480,10 +3288,6 @@ Tmp1 = DAG.getNode(ISD::FNEG, dl, VT, Node->getOperand(1)); Tmp1 = DAG.getNode(ISD::FADD, dl, VT, Node->getOperand(0), Tmp1, Flags); Results.push_back(Tmp1); - } else { - Results.push_back(ExpandFPLibCall(Node, RTLIB::SUB_F32, RTLIB::SUB_F64, - RTLIB::SUB_F80, RTLIB::SUB_F128, - RTLIB::SUB_PPCF128)); } break; } @@ -3510,22 +3314,14 @@ if (TLI.isOperationLegalOrCustom(DivRemOpc, VT)) { SDVTList VTs = DAG.getVTList(VT, VT); Tmp1 = DAG.getNode(DivRemOpc, dl, VTs, Tmp2, Tmp3).getValue(1); + Results.push_back(Tmp1); } else if (TLI.isOperationLegalOrCustom(DivOpc, VT)) { // X % Y -> X-X/Y*Y Tmp1 = DAG.getNode(DivOpc, dl, VT, Tmp2, Tmp3); Tmp1 = DAG.getNode(ISD::MUL, dl, VT, Tmp1, Tmp3); Tmp1 = DAG.getNode(ISD::SUB, dl, VT, Tmp2, Tmp1); - } else if (isSigned) - Tmp1 = ExpandIntLibCall(Node, true, - RTLIB::SREM_I8, - RTLIB::SREM_I16, RTLIB::SREM_I32, - RTLIB::SREM_I64, RTLIB::SREM_I128); - else - Tmp1 = ExpandIntLibCall(Node, false, - RTLIB::UREM_I8, - RTLIB::UREM_I16, RTLIB::UREM_I32, - RTLIB::UREM_I64, RTLIB::UREM_I128); - Results.push_back(Tmp1); + Results.push_back(Tmp1); + } break; } case ISD::UDIV: @@ -3533,21 +3329,12 @@ bool isSigned = Node->getOpcode() == ISD::SDIV; unsigned DivRemOpc = isSigned ? ISD::SDIVREM : ISD::UDIVREM; EVT VT = Node->getValueType(0); - SDVTList VTs = DAG.getVTList(VT, VT); - if (TLI.isOperationLegalOrCustom(DivRemOpc, VT)) + if (TLI.isOperationLegalOrCustom(DivRemOpc, VT)) { + SDVTList VTs = DAG.getVTList(VT, VT); Tmp1 = DAG.getNode(DivRemOpc, dl, VTs, Node->getOperand(0), Node->getOperand(1)); - else if (isSigned) - Tmp1 = ExpandIntLibCall(Node, true, - RTLIB::SDIV_I8, - RTLIB::SDIV_I16, RTLIB::SDIV_I32, - RTLIB::SDIV_I64, RTLIB::SDIV_I128); - else - Tmp1 = ExpandIntLibCall(Node, false, - RTLIB::UDIV_I8, - RTLIB::UDIV_I16, RTLIB::UDIV_I32, - RTLIB::UDIV_I64, RTLIB::UDIV_I128); - Results.push_back(Tmp1); + Results.push_back(Tmp1); + } break; } case ISD::MULHU: @@ -3563,11 +3350,6 @@ Results.push_back(Tmp1.getValue(1)); break; } - case ISD::SDIVREM: - case ISD::UDIVREM: - // Expand into divrem libcall - ExpandDivRemLibCall(Node, Results); - break; case ISD::MUL: { EVT VT = Node->getValueType(0); SDVTList VTs = DAG.getVTList(VT, VT); @@ -3610,14 +3392,7 @@ TLI.getShiftAmountTy(HalfType, DAG.getDataLayout())); Hi = DAG.getNode(ISD::SHL, dl, VT, Hi, Shift); Results.push_back(DAG.getNode(ISD::OR, dl, VT, Lo, Hi)); - break; } - - Tmp1 = ExpandIntLibCall(Node, false, - RTLIB::MUL_I8, - RTLIB::MUL_I16, RTLIB::MUL_I32, - RTLIB::MUL_I64, RTLIB::MUL_I128); - Results.push_back(Tmp1); break; } case ISD::SADDO: @@ -4030,6 +3805,254 @@ } // Replace the original node with the legalized result. + if (Results.empty()) + return false; + + ReplaceNode(Node, Results.data()); + return true; +} + +void SelectionDAGLegalize::ConvertNodeToLibcall(SDNode *Node) { + SmallVector Results; + SDLoc dl(Node); + SDValue Tmp1, Tmp2, Tmp3, Tmp4; + unsigned Opc = Node->getOpcode(); + switch (Opc) { + case ISD::ATOMIC_FENCE: { + // If the target didn't lower this, lower it to '__sync_synchronize()' call + // FIXME: handle "fence singlethread" more efficiently. + TargetLowering::ArgListTy Args; + + TargetLowering::CallLoweringInfo CLI(DAG); + CLI.setDebugLoc(dl) + .setChain(Node->getOperand(0)) + .setCallee(CallingConv::C, Type::getVoidTy(*DAG.getContext()), + DAG.getExternalSymbol("__sync_synchronize", + TLI.getPointerTy(DAG.getDataLayout())), + std::move(Args), 0); + + std::pair CallResult = TLI.LowerCallTo(CLI); + + Results.push_back(CallResult.second); + break; + } + // By default, atomic intrinsics are marked Legal and lowered. Targets + // which don't support them directly, however, may want libcalls, in which + // case they mark them Expand, and we get here. + case ISD::ATOMIC_SWAP: + case ISD::ATOMIC_LOAD_ADD: + case ISD::ATOMIC_LOAD_SUB: + case ISD::ATOMIC_LOAD_AND: + case ISD::ATOMIC_LOAD_OR: + case ISD::ATOMIC_LOAD_XOR: + case ISD::ATOMIC_LOAD_NAND: + case ISD::ATOMIC_LOAD_MIN: + case ISD::ATOMIC_LOAD_MAX: + case ISD::ATOMIC_LOAD_UMIN: + case ISD::ATOMIC_LOAD_UMAX: + case ISD::ATOMIC_CMP_SWAP: { + MVT VT = cast(Node)->getMemoryVT().getSimpleVT(); + RTLIB::Libcall LC = RTLIB::getATOMIC(Opc, VT); + assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unexpected atomic op or value type!"); + + std::pair Tmp = ExpandChainLibCall(LC, Node, false); + Results.push_back(Tmp.first); + Results.push_back(Tmp.second); + break; + } + case ISD::TRAP: { + // If this operation is not supported, lower it to 'abort()' call + TargetLowering::ArgListTy Args; + TargetLowering::CallLoweringInfo CLI(DAG); + CLI.setDebugLoc(dl) + .setChain(Node->getOperand(0)) + .setCallee(CallingConv::C, Type::getVoidTy(*DAG.getContext()), + DAG.getExternalSymbol("abort", + TLI.getPointerTy(DAG.getDataLayout())), + std::move(Args), 0); + std::pair CallResult = TLI.LowerCallTo(CLI); + + Results.push_back(CallResult.second); + break; + } + case ISD::FMINNUM: + Results.push_back(ExpandFPLibCall(Node, RTLIB::FMIN_F32, RTLIB::FMIN_F64, + RTLIB::FMIN_F80, RTLIB::FMIN_F128, + RTLIB::FMIN_PPCF128)); + break; + case ISD::FMAXNUM: + Results.push_back(ExpandFPLibCall(Node, RTLIB::FMAX_F32, RTLIB::FMAX_F64, + RTLIB::FMAX_F80, RTLIB::FMAX_F128, + RTLIB::FMAX_PPCF128)); + break; + case ISD::FSQRT: + Results.push_back(ExpandFPLibCall(Node, RTLIB::SQRT_F32, RTLIB::SQRT_F64, + RTLIB::SQRT_F80, RTLIB::SQRT_F128, + RTLIB::SQRT_PPCF128)); + break; + case ISD::FSIN: + Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64, + RTLIB::SIN_F80, RTLIB::SIN_F128, + RTLIB::SIN_PPCF128)); + break; + case ISD::FCOS: + Results.push_back(ExpandFPLibCall(Node, RTLIB::COS_F32, RTLIB::COS_F64, + RTLIB::COS_F80, RTLIB::COS_F128, + RTLIB::COS_PPCF128)); + break; + case ISD::FSINCOS: + // Expand into sincos libcall. + ExpandSinCosLibCall(Node, Results); + break; + case ISD::FLOG: + Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG_F32, RTLIB::LOG_F64, + RTLIB::LOG_F80, RTLIB::LOG_F128, + RTLIB::LOG_PPCF128)); + break; + case ISD::FLOG2: + Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG2_F32, RTLIB::LOG2_F64, + RTLIB::LOG2_F80, RTLIB::LOG2_F128, + RTLIB::LOG2_PPCF128)); + break; + case ISD::FLOG10: + Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG10_F32, RTLIB::LOG10_F64, + RTLIB::LOG10_F80, RTLIB::LOG10_F128, + RTLIB::LOG10_PPCF128)); + break; + case ISD::FEXP: + Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP_F32, RTLIB::EXP_F64, + RTLIB::EXP_F80, RTLIB::EXP_F128, + RTLIB::EXP_PPCF128)); + break; + case ISD::FEXP2: + Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP2_F32, RTLIB::EXP2_F64, + RTLIB::EXP2_F80, RTLIB::EXP2_F128, + RTLIB::EXP2_PPCF128)); + break; + case ISD::FTRUNC: + Results.push_back(ExpandFPLibCall(Node, RTLIB::TRUNC_F32, RTLIB::TRUNC_F64, + RTLIB::TRUNC_F80, RTLIB::TRUNC_F128, + RTLIB::TRUNC_PPCF128)); + break; + case ISD::FFLOOR: + Results.push_back(ExpandFPLibCall(Node, RTLIB::FLOOR_F32, RTLIB::FLOOR_F64, + RTLIB::FLOOR_F80, RTLIB::FLOOR_F128, + RTLIB::FLOOR_PPCF128)); + break; + case ISD::FCEIL: + Results.push_back(ExpandFPLibCall(Node, RTLIB::CEIL_F32, RTLIB::CEIL_F64, + RTLIB::CEIL_F80, RTLIB::CEIL_F128, + RTLIB::CEIL_PPCF128)); + break; + case ISD::FRINT: + Results.push_back(ExpandFPLibCall(Node, RTLIB::RINT_F32, RTLIB::RINT_F64, + RTLIB::RINT_F80, RTLIB::RINT_F128, + RTLIB::RINT_PPCF128)); + break; + case ISD::FNEARBYINT: + Results.push_back(ExpandFPLibCall(Node, RTLIB::NEARBYINT_F32, + RTLIB::NEARBYINT_F64, + RTLIB::NEARBYINT_F80, + RTLIB::NEARBYINT_F128, + RTLIB::NEARBYINT_PPCF128)); + break; + case ISD::FROUND: + Results.push_back(ExpandFPLibCall(Node, RTLIB::ROUND_F32, + RTLIB::ROUND_F64, + RTLIB::ROUND_F80, + RTLIB::ROUND_F128, + RTLIB::ROUND_PPCF128)); + break; + case ISD::FPOWI: + Results.push_back(ExpandFPLibCall(Node, RTLIB::POWI_F32, RTLIB::POWI_F64, + RTLIB::POWI_F80, RTLIB::POWI_F128, + RTLIB::POWI_PPCF128)); + break; + case ISD::FPOW: + Results.push_back(ExpandFPLibCall(Node, RTLIB::POW_F32, RTLIB::POW_F64, + RTLIB::POW_F80, RTLIB::POW_F128, + RTLIB::POW_PPCF128)); + break; + case ISD::FDIV: + Results.push_back(ExpandFPLibCall(Node, RTLIB::DIV_F32, RTLIB::DIV_F64, + RTLIB::DIV_F80, RTLIB::DIV_F128, + RTLIB::DIV_PPCF128)); + break; + case ISD::FREM: + Results.push_back(ExpandFPLibCall(Node, RTLIB::REM_F32, RTLIB::REM_F64, + RTLIB::REM_F80, RTLIB::REM_F128, + RTLIB::REM_PPCF128)); + break; + case ISD::FMA: + Results.push_back(ExpandFPLibCall(Node, RTLIB::FMA_F32, RTLIB::FMA_F64, + RTLIB::FMA_F80, RTLIB::FMA_F128, + RTLIB::FMA_PPCF128)); + break; + case ISD::FADD: + Results.push_back(ExpandFPLibCall(Node, RTLIB::ADD_F32, RTLIB::ADD_F64, + RTLIB::ADD_F80, RTLIB::ADD_F128, + RTLIB::ADD_PPCF128)); + break; + case ISD::FMUL: + Results.push_back(ExpandFPLibCall(Node, RTLIB::MUL_F32, RTLIB::MUL_F64, + RTLIB::MUL_F80, RTLIB::MUL_F128, + RTLIB::MUL_PPCF128)); + break; + case ISD::FP16_TO_FP: + if (Node->getValueType(0) == MVT::f32) { + Results.push_back(ExpandLibCall(RTLIB::FPEXT_F16_F32, Node, false)); + } + break; + case ISD::FP_TO_FP16: { + RTLIB::Libcall LC = + RTLIB::getFPROUND(Node->getOperand(0).getValueType(), MVT::f16); + assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unable to expand fp_to_fp16"); + Results.push_back(ExpandLibCall(LC, Node, false)); + break; + } + case ISD::FSUB: + Results.push_back(ExpandFPLibCall(Node, RTLIB::SUB_F32, RTLIB::SUB_F64, + RTLIB::SUB_F80, RTLIB::SUB_F128, + RTLIB::SUB_PPCF128)); + break; + case ISD::SREM: + Results.push_back(ExpandIntLibCall(Node, true, + RTLIB::SREM_I8, + RTLIB::SREM_I16, RTLIB::SREM_I32, + RTLIB::SREM_I64, RTLIB::SREM_I128)); + break; + case ISD::UREM: + Results.push_back(ExpandIntLibCall(Node, false, + RTLIB::UREM_I8, + RTLIB::UREM_I16, RTLIB::UREM_I32, + RTLIB::UREM_I64, RTLIB::UREM_I128)); + break; + case ISD::SDIV: + Results.push_back(ExpandIntLibCall(Node, true, + RTLIB::SDIV_I8, + RTLIB::SDIV_I16, RTLIB::SDIV_I32, + RTLIB::SDIV_I64, RTLIB::SDIV_I128)); + break; + case ISD::UDIV: + Results.push_back(ExpandIntLibCall(Node, false, + RTLIB::UDIV_I8, + RTLIB::UDIV_I16, RTLIB::UDIV_I32, + RTLIB::UDIV_I64, RTLIB::UDIV_I128)); + break; + case ISD::SDIVREM: + case ISD::UDIVREM: + // Expand into divrem libcall + ExpandDivRemLibCall(Node, Results); + break; + case ISD::MUL: + Results.push_back(ExpandIntLibCall(Node, false, + RTLIB::MUL_I8, + RTLIB::MUL_I16, RTLIB::MUL_I32, + RTLIB::MUL_I64, RTLIB::MUL_I128)); + break; + } + + // Replace the original node with the legalized result. if (!Results.empty()) ReplaceNode(Node, Results.data()); } Index: lib/Target/ARM/ARMISelLowering.cpp =================================================================== --- lib/Target/ARM/ARMISelLowering.cpp +++ lib/Target/ARM/ARMISelLowering.cpp @@ -742,8 +742,8 @@ if (!(Subtarget->hasDivide() && Subtarget->isThumb2()) && !(Subtarget->hasDivideInARMMode() && !Subtarget->isThumb())) { // These are expanded into libcalls if the cpu doesn't have HW divider. - setOperationAction(ISD::SDIV, MVT::i32, Expand); - setOperationAction(ISD::UDIV, MVT::i32, Expand); + setOperationAction(ISD::SDIV, MVT::i32, LibCall); + setOperationAction(ISD::UDIV, MVT::i32, LibCall); } if (Subtarget->isTargetWindows() && !Subtarget->hasDivide()) { Index: test/CodeGen/ARM/divmod-eabi.ll =================================================================== --- test/CodeGen/ARM/divmod-eabi.ll +++ test/CodeGen/ARM/divmod-eabi.ll @@ -189,7 +189,7 @@ ; DARWIN-LABEL: g4: entry: %div = sdiv i32 %a, %b -; EABI: __aeabi_idivmod +; EABI: __aeabi_idiv{{$}} ; EABI: mov [[div:r[0-9]+]], r0 ; GNU: __aeabi_idiv ; GNU: mov [[sum:r[0-9]+]], r0