diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td index cd10dde0e1e..5ef91ad0f05 100644 --- a/lib/Target/ARM/ARMInstrNEON.td +++ b/lib/Target/ARM/ARMInstrNEON.td @@ -174,7 +174,7 @@ def VecListOneDWordIndexed : Operand { let ParserMatchClass = VecListOneDWordIndexAsmOperand; let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx); } -// Register list of two D registers, with byte lane subscripting. +// Register list of two D registers with byte lane subscripting. def VecListTwoDByteIndexAsmOperand : AsmOperandClass { let Name = "VecListTwoDByteIndexed"; let ParserMethod = "parseVectorList"; @@ -204,6 +204,26 @@ def VecListTwoDWordIndexed : Operand { let ParserMatchClass = VecListTwoDWordIndexAsmOperand; let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx); } +// Register list of two Q registers with half-word lane subscripting. +def VecListTwoQHWordIndexAsmOperand : AsmOperandClass { + let Name = "VecListTwoQHWordIndexed"; + let ParserMethod = "parseVectorList"; + let RenderMethod = "addVecListIndexedOperands"; +} +def VecListTwoQHWordIndexed : Operand { + let ParserMatchClass = VecListTwoQHWordIndexAsmOperand; + let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx); +} +// ...with word lane subscripting. +def VecListTwoQWordIndexAsmOperand : AsmOperandClass { + let Name = "VecListTwoQWordIndexed"; + let ParserMethod = "parseVectorList"; + let RenderMethod = "addVecListIndexedOperands"; +} +def VecListTwoQWordIndexed : Operand { + let ParserMatchClass = VecListTwoQWordIndexAsmOperand; + let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx); +} //===----------------------------------------------------------------------===// // NEON-specific DAG Nodes. @@ -5735,6 +5755,10 @@ defm VLD2LNdAsm : NEONDT16AsmPseudoInst<"vld2${p}", "$list, $addr", (ins VecListTwoDHWordIndexed:$list, addrmode6:$addr, pred:$p)>; defm VLD2LNdAsm : NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr", (ins VecListTwoDWordIndexed:$list, addrmode6:$addr, pred:$p)>; +defm VLD2LNqAsm : NEONDT16AsmPseudoInst<"vld2${p}", "$list, $addr", + (ins VecListTwoQHWordIndexed:$list, addrmode6:$addr, pred:$p)>; +defm VLD2LNqAsm : NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr", + (ins VecListTwoQWordIndexed:$list, addrmode6:$addr, pred:$p)>; defm VLD2LNdWB_fixed_Asm : NEONDT8AsmPseudoInst<"vld2${p}", "$list, $addr!", (ins VecListTwoDByteIndexed:$list, addrmode6:$addr, pred:$p)>; @@ -5742,6 +5766,10 @@ defm VLD2LNdWB_fixed_Asm : NEONDT16AsmPseudoInst<"vld2${p}", "$list, $addr!", (ins VecListTwoDHWordIndexed:$list, addrmode6:$addr, pred:$p)>; defm VLD2LNdWB_fixed_Asm : NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr!", (ins VecListTwoDWordIndexed:$list, addrmode6:$addr, pred:$p)>; +defm VLD2LNqWB_fixed_Asm : NEONDT16AsmPseudoInst<"vld2${p}", "$list, $addr!", + (ins VecListTwoQHWordIndexed:$list, addrmode6:$addr, pred:$p)>; +defm VLD2LNqWB_fixed_Asm : NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr!", + (ins VecListTwoQWordIndexed:$list, addrmode6:$addr, pred:$p)>; defm VLD2LNdWB_register_Asm : NEONDT8AsmPseudoInst<"vld2${p}", "$list, $addr, $Rm", (ins VecListTwoDByteIndexed:$list, addrmode6:$addr, @@ -5754,6 +5782,14 @@ defm VLD2LNdWB_register_Asm : NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr, $Rm", (ins VecListTwoDWordIndexed:$list, addrmode6:$addr, rGPR:$Rm, pred:$p)>; +defm VLD2LNqWB_register_Asm : + NEONDT16AsmPseudoInst<"vld2${p}", "$list, $addr, $Rm", + (ins VecListTwoQHWordIndexed:$list, addrmode6:$addr, + rGPR:$Rm, pred:$p)>; +defm VLD2LNqWB_register_Asm : + NEONDT32AsmPseudoInst<"vld2${p}", "$list, $addr, $Rm", + (ins VecListTwoQWordIndexed:$list, addrmode6:$addr, + rGPR:$Rm, pred:$p)>; // VST2 single-lane pseudo-instructions. These need special handling for diff --git a/lib/Target/ARM/AsmParser/ARMAsmParser.cpp b/lib/Target/ARM/AsmParser/ARMAsmParser.cpp index 93e84040b7b..9bdd8fe2020 100644 --- a/lib/Target/ARM/AsmParser/ARMAsmParser.cpp +++ b/lib/Target/ARM/AsmParser/ARMAsmParser.cpp @@ -1128,33 +1128,49 @@ public: return VectorList.Count == 2; } + bool isSingleSpacedVectorIndexed() const { + return Kind == k_VectorListIndexed && !VectorList.isDoubleSpaced; + } + bool isDoubleSpacedVectorIndexed() const { + return Kind == k_VectorListIndexed && VectorList.isDoubleSpaced; + } bool isVecListOneDByteIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; return VectorList.Count == 1 && VectorList.LaneIndex <= 7; } bool isVecListOneDHWordIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; return VectorList.Count == 1 && VectorList.LaneIndex <= 3; } bool isVecListOneDWordIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; return VectorList.Count == 1 && VectorList.LaneIndex <= 1; } bool isVecListTwoDByteIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; return VectorList.Count == 2 && VectorList.LaneIndex <= 7; } bool isVecListTwoDHWordIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; + return VectorList.Count == 2 && VectorList.LaneIndex <= 3; + } + + bool isVecListTwoQWordIndexed() const { + if (!isDoubleSpacedVectorIndexed()) return false; + return VectorList.Count == 2 && VectorList.LaneIndex <= 1; + } + + bool isVecListTwoQHWordIndexed() const { + if (!isDoubleSpacedVectorIndexed()) return false; return VectorList.Count == 2 && VectorList.LaneIndex <= 3; } bool isVecListTwoDWordIndexed() const { - if (Kind != k_VectorListIndexed) return false; + if (!isSingleSpacedVectorIndexed()) return false; return VectorList.Count == 2 && VectorList.LaneIndex <= 1; } @@ -2035,11 +2051,14 @@ public: } static ARMOperand *CreateVectorListIndexed(unsigned RegNum, unsigned Count, - unsigned Index, SMLoc S, SMLoc E) { + unsigned Index, + bool isDoubleSpaced, + SMLoc S, SMLoc E) { ARMOperand *Op = new ARMOperand(k_VectorListIndexed); Op->VectorList.RegNum = RegNum; Op->VectorList.Count = Count; Op->VectorList.LaneIndex = Index; + Op->VectorList.isDoubleSpaced = isDoubleSpaced; Op->StartLoc = S; Op->EndLoc = E; return Op; @@ -2849,7 +2868,8 @@ parseVectorList(SmallVectorImpl &Operands) { break; case IndexedLane: Operands.push_back(ARMOperand::CreateVectorListIndexed(Reg, 1, - LaneIndex, S,E)); + LaneIndex, + false, S, E)); break; } return MatchOperand_Success; @@ -2872,7 +2892,8 @@ parseVectorList(SmallVectorImpl &Operands) { break; case IndexedLane: Operands.push_back(ARMOperand::CreateVectorListIndexed(Reg, 2, - LaneIndex, S,E)); + LaneIndex, + false, S, E)); break; } return MatchOperand_Success; @@ -3020,11 +3041,6 @@ parseVectorList(SmallVectorImpl &Operands) { Error(EndLoc, "mismatched lane index in register list"); return MatchOperand_ParseFail; } - if (Spacing == 2 && LaneKind != NoLanes) { - Error(EndLoc, - "lane index specfier invalid in double spaced register list"); - return MatchOperand_ParseFail; - } } SMLoc E = Parser.getTok().getLoc(); @@ -3047,7 +3063,9 @@ parseVectorList(SmallVectorImpl &Operands) { break; case IndexedLane: Operands.push_back(ARMOperand::CreateVectorListIndexed(FirstReg, Count, - LaneIndex, S, E)); + LaneIndex, + (Spacing == 2), + S, E)); break; } return MatchOperand_Success; @@ -5181,84 +5199,132 @@ static unsigned getRealVSTLNOpcode(unsigned Opc) { } } -static unsigned getRealVLDLNOpcode(unsigned Opc) { +static unsigned getRealVLDLNOpcode(unsigned Opc, unsigned &Spacing) { switch(Opc) { default: assert(0 && "unexpected opcode!"); // VLD1LN case ARM::VLD1LNdWB_fixed_Asm_8: case ARM::VLD1LNdWB_fixed_Asm_P8: case ARM::VLD1LNdWB_fixed_Asm_I8: case ARM::VLD1LNdWB_fixed_Asm_S8: case ARM::VLD1LNdWB_fixed_Asm_U8: + Spacing = 1; return ARM::VLD1LNd8_UPD; case ARM::VLD1LNdWB_fixed_Asm_16: case ARM::VLD1LNdWB_fixed_Asm_P16: case ARM::VLD1LNdWB_fixed_Asm_I16: case ARM::VLD1LNdWB_fixed_Asm_S16: case ARM::VLD1LNdWB_fixed_Asm_U16: + Spacing = 1; return ARM::VLD1LNd16_UPD; case ARM::VLD1LNdWB_fixed_Asm_32: case ARM::VLD1LNdWB_fixed_Asm_F: case ARM::VLD1LNdWB_fixed_Asm_F32: case ARM::VLD1LNdWB_fixed_Asm_I32: case ARM::VLD1LNdWB_fixed_Asm_S32: case ARM::VLD1LNdWB_fixed_Asm_U32: + Spacing = 1; return ARM::VLD1LNd32_UPD; case ARM::VLD1LNdWB_register_Asm_8: case ARM::VLD1LNdWB_register_Asm_P8: case ARM::VLD1LNdWB_register_Asm_I8: case ARM::VLD1LNdWB_register_Asm_S8: case ARM::VLD1LNdWB_register_Asm_U8: + Spacing = 1; return ARM::VLD1LNd8_UPD; case ARM::VLD1LNdWB_register_Asm_16: case ARM::VLD1LNdWB_register_Asm_P16: case ARM::VLD1LNdWB_register_Asm_I16: case ARM::VLD1LNdWB_register_Asm_S16: case ARM::VLD1LNdWB_register_Asm_U16: + Spacing = 1; return ARM::VLD1LNd16_UPD; case ARM::VLD1LNdWB_register_Asm_32: case ARM::VLD1LNdWB_register_Asm_F: case ARM::VLD1LNdWB_register_Asm_F32: case ARM::VLD1LNdWB_register_Asm_I32: case ARM::VLD1LNdWB_register_Asm_S32: case ARM::VLD1LNdWB_register_Asm_U32: + Spacing = 1; return ARM::VLD1LNd32_UPD; case ARM::VLD1LNdAsm_8: case ARM::VLD1LNdAsm_P8: case ARM::VLD1LNdAsm_I8: case ARM::VLD1LNdAsm_S8: case ARM::VLD1LNdAsm_U8: + Spacing = 1; return ARM::VLD1LNd8; case ARM::VLD1LNdAsm_16: case ARM::VLD1LNdAsm_P16: case ARM::VLD1LNdAsm_I16: case ARM::VLD1LNdAsm_S16: case ARM::VLD1LNdAsm_U16: + Spacing = 1; return ARM::VLD1LNd16; case ARM::VLD1LNdAsm_32: case ARM::VLD1LNdAsm_F: case ARM::VLD1LNdAsm_F32: case ARM::VLD1LNdAsm_I32: case ARM::VLD1LNdAsm_S32: case ARM::VLD1LNdAsm_U32: + Spacing = 1; return ARM::VLD1LNd32; // VLD2LN case ARM::VLD2LNdWB_fixed_Asm_8: case ARM::VLD2LNdWB_fixed_Asm_P8: case ARM::VLD2LNdWB_fixed_Asm_I8: case ARM::VLD2LNdWB_fixed_Asm_S8: case ARM::VLD2LNdWB_fixed_Asm_U8: + Spacing = 1; return ARM::VLD2LNd8_UPD; case ARM::VLD2LNdWB_fixed_Asm_16: case ARM::VLD2LNdWB_fixed_Asm_P16: case ARM::VLD2LNdWB_fixed_Asm_I16: case ARM::VLD2LNdWB_fixed_Asm_S16: case ARM::VLD2LNdWB_fixed_Asm_U16: + Spacing = 1; return ARM::VLD2LNd16_UPD; case ARM::VLD2LNdWB_fixed_Asm_32: case ARM::VLD2LNdWB_fixed_Asm_F: case ARM::VLD2LNdWB_fixed_Asm_F32: case ARM::VLD2LNdWB_fixed_Asm_I32: case ARM::VLD2LNdWB_fixed_Asm_S32: case ARM::VLD2LNdWB_fixed_Asm_U32: + Spacing = 1; return ARM::VLD2LNd32_UPD; + case ARM::VLD2LNqWB_fixed_Asm_16: case ARM::VLD2LNqWB_fixed_Asm_P16: + case ARM::VLD2LNqWB_fixed_Asm_I16: case ARM::VLD2LNqWB_fixed_Asm_S16: + case ARM::VLD2LNqWB_fixed_Asm_U16: + Spacing = 1; + return ARM::VLD2LNq16_UPD; + case ARM::VLD2LNqWB_fixed_Asm_32: case ARM::VLD2LNqWB_fixed_Asm_F: + case ARM::VLD2LNqWB_fixed_Asm_F32: case ARM::VLD2LNqWB_fixed_Asm_I32: + case ARM::VLD2LNqWB_fixed_Asm_S32: case ARM::VLD2LNqWB_fixed_Asm_U32: + Spacing = 2; + return ARM::VLD2LNq32_UPD; case ARM::VLD2LNdWB_register_Asm_8: case ARM::VLD2LNdWB_register_Asm_P8: case ARM::VLD2LNdWB_register_Asm_I8: case ARM::VLD2LNdWB_register_Asm_S8: case ARM::VLD2LNdWB_register_Asm_U8: + Spacing = 1; return ARM::VLD2LNd8_UPD; case ARM::VLD2LNdWB_register_Asm_16: case ARM::VLD2LNdWB_register_Asm_P16: case ARM::VLD2LNdWB_register_Asm_I16: case ARM::VLD2LNdWB_register_Asm_S16: case ARM::VLD2LNdWB_register_Asm_U16: + Spacing = 1; return ARM::VLD2LNd16_UPD; case ARM::VLD2LNdWB_register_Asm_32: case ARM::VLD2LNdWB_register_Asm_F: case ARM::VLD2LNdWB_register_Asm_F32: case ARM::VLD2LNdWB_register_Asm_I32: case ARM::VLD2LNdWB_register_Asm_S32: case ARM::VLD2LNdWB_register_Asm_U32: + Spacing = 1; return ARM::VLD2LNd32_UPD; + case ARM::VLD2LNqWB_register_Asm_16: case ARM::VLD2LNqWB_register_Asm_P16: + case ARM::VLD2LNqWB_register_Asm_I16: case ARM::VLD2LNqWB_register_Asm_S16: + case ARM::VLD2LNqWB_register_Asm_U16: + Spacing = 2; + return ARM::VLD2LNq16_UPD; + case ARM::VLD2LNqWB_register_Asm_32: case ARM::VLD2LNqWB_register_Asm_F: + case ARM::VLD2LNqWB_register_Asm_F32: case ARM::VLD2LNqWB_register_Asm_I32: + case ARM::VLD2LNqWB_register_Asm_S32: case ARM::VLD2LNqWB_register_Asm_U32: + Spacing = 2; + return ARM::VLD2LNq32_UPD; case ARM::VLD2LNdAsm_8: case ARM::VLD2LNdAsm_P8: case ARM::VLD2LNdAsm_I8: case ARM::VLD2LNdAsm_S8: case ARM::VLD2LNdAsm_U8: + Spacing = 1; return ARM::VLD2LNd8; case ARM::VLD2LNdAsm_16: case ARM::VLD2LNdAsm_P16: case ARM::VLD2LNdAsm_I16: case ARM::VLD2LNdAsm_S16: case ARM::VLD2LNdAsm_U16: + Spacing = 1; return ARM::VLD2LNd16; case ARM::VLD2LNdAsm_32: case ARM::VLD2LNdAsm_F: case ARM::VLD2LNdAsm_F32: case ARM::VLD2LNdAsm_I32: case ARM::VLD2LNdAsm_S32: case ARM::VLD2LNdAsm_U32: + Spacing = 1; return ARM::VLD2LNd32; + case ARM::VLD2LNqAsm_16: case ARM::VLD2LNqAsm_P16: + case ARM::VLD2LNqAsm_I16: case ARM::VLD2LNqAsm_S16: + case ARM::VLD2LNqAsm_U16: + Spacing = 2; + return ARM::VLD2LNq16; + case ARM::VLD2LNqAsm_32: case ARM::VLD2LNqAsm_F: + case ARM::VLD2LNqAsm_F32: case ARM::VLD2LNqAsm_I32: + case ARM::VLD2LNqAsm_S32: case ARM::VLD2LNqAsm_U32: + Spacing = 2; + return ARM::VLD2LNq32; } } @@ -5415,7 +5481,8 @@ processInstruction(MCInst &Inst, MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb TmpInst.addOperand(Inst.getOperand(2)); // Rn @@ -5429,26 +5496,34 @@ processInstruction(MCInst &Inst, return true; } - case ARM::VLD2LNdWB_register_Asm_8: case ARM::VLD2LNdWB_register_Asm_P8: - case ARM::VLD2LNdWB_register_Asm_I8: case ARM::VLD2LNdWB_register_Asm_S8: - case ARM::VLD2LNdWB_register_Asm_U8: case ARM::VLD2LNdWB_register_Asm_16: + case ARM::VLD2LNdWB_register_Asm_8: case ARM::VLD2LNdWB_register_Asm_P8: + case ARM::VLD2LNdWB_register_Asm_I8: case ARM::VLD2LNdWB_register_Asm_S8: + case ARM::VLD2LNdWB_register_Asm_U8: case ARM::VLD2LNdWB_register_Asm_16: case ARM::VLD2LNdWB_register_Asm_P16: case ARM::VLD2LNdWB_register_Asm_I16: case ARM::VLD2LNdWB_register_Asm_S16: case ARM::VLD2LNdWB_register_Asm_U16: - case ARM::VLD2LNdWB_register_Asm_32: case ARM::VLD2LNdWB_register_Asm_F: + case ARM::VLD2LNdWB_register_Asm_32: case ARM::VLD2LNdWB_register_Asm_F: case ARM::VLD2LNdWB_register_Asm_F32: case ARM::VLD2LNdWB_register_Asm_I32: - case ARM::VLD2LNdWB_register_Asm_S32: case ARM::VLD2LNdWB_register_Asm_U32: { + case ARM::VLD2LNdWB_register_Asm_S32: case ARM::VLD2LNdWB_register_Asm_U32: + case ARM::VLD2LNqWB_register_Asm_P16: case ARM::VLD2LNqWB_register_Asm_I16: + case ARM::VLD2LNqWB_register_Asm_S16: case ARM::VLD2LNqWB_register_Asm_U16: + case ARM::VLD2LNqWB_register_Asm_32: case ARM::VLD2LNqWB_register_Asm_F: + case ARM::VLD2LNqWB_register_Asm_F32: case ARM::VLD2LNqWB_register_Asm_I32: + case ARM::VLD2LNqWB_register_Asm_S32: case ARM::VLD2LNqWB_register_Asm_U32: { MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb TmpInst.addOperand(Inst.getOperand(2)); // Rn TmpInst.addOperand(Inst.getOperand(3)); // alignment TmpInst.addOperand(Inst.getOperand(4)); // Rm TmpInst.addOperand(Inst.getOperand(0)); // Tied operand src (== Vd) - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(1)); // lane TmpInst.addOperand(Inst.getOperand(5)); // CondCode TmpInst.addOperand(Inst.getOperand(6)); @@ -5467,7 +5542,8 @@ processInstruction(MCInst &Inst, MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb TmpInst.addOperand(Inst.getOperand(2)); // Rn @@ -5481,26 +5557,34 @@ processInstruction(MCInst &Inst, return true; } - case ARM::VLD2LNdWB_fixed_Asm_8: case ARM::VLD2LNdWB_fixed_Asm_P8: - case ARM::VLD2LNdWB_fixed_Asm_I8: case ARM::VLD2LNdWB_fixed_Asm_S8: - case ARM::VLD2LNdWB_fixed_Asm_U8: case ARM::VLD2LNdWB_fixed_Asm_16: + case ARM::VLD2LNdWB_fixed_Asm_8: case ARM::VLD2LNdWB_fixed_Asm_P8: + case ARM::VLD2LNdWB_fixed_Asm_I8: case ARM::VLD2LNdWB_fixed_Asm_S8: + case ARM::VLD2LNdWB_fixed_Asm_U8: case ARM::VLD2LNdWB_fixed_Asm_16: case ARM::VLD2LNdWB_fixed_Asm_P16: case ARM::VLD2LNdWB_fixed_Asm_I16: case ARM::VLD2LNdWB_fixed_Asm_S16: case ARM::VLD2LNdWB_fixed_Asm_U16: - case ARM::VLD2LNdWB_fixed_Asm_32: case ARM::VLD2LNdWB_fixed_Asm_F: + case ARM::VLD2LNdWB_fixed_Asm_32: case ARM::VLD2LNdWB_fixed_Asm_F: case ARM::VLD2LNdWB_fixed_Asm_F32: case ARM::VLD2LNdWB_fixed_Asm_I32: - case ARM::VLD2LNdWB_fixed_Asm_S32: case ARM::VLD2LNdWB_fixed_Asm_U32: { + case ARM::VLD2LNdWB_fixed_Asm_S32: case ARM::VLD2LNdWB_fixed_Asm_U32: + case ARM::VLD2LNqWB_fixed_Asm_P16: case ARM::VLD2LNqWB_fixed_Asm_I16: + case ARM::VLD2LNqWB_fixed_Asm_S16: case ARM::VLD2LNqWB_fixed_Asm_U16: + case ARM::VLD2LNqWB_fixed_Asm_32: case ARM::VLD2LNqWB_fixed_Asm_F: + case ARM::VLD2LNqWB_fixed_Asm_F32: case ARM::VLD2LNqWB_fixed_Asm_I32: + case ARM::VLD2LNqWB_fixed_Asm_S32: case ARM::VLD2LNqWB_fixed_Asm_U32: { MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb TmpInst.addOperand(Inst.getOperand(2)); // Rn TmpInst.addOperand(Inst.getOperand(3)); // alignment TmpInst.addOperand(MCOperand::CreateReg(0)); // Rm TmpInst.addOperand(Inst.getOperand(0)); // Tied operand src (== Vd) - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(1)); // lane TmpInst.addOperand(Inst.getOperand(4)); // CondCode TmpInst.addOperand(Inst.getOperand(5)); @@ -5517,7 +5601,8 @@ processInstruction(MCInst &Inst, MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd TmpInst.addOperand(Inst.getOperand(2)); // Rn TmpInst.addOperand(Inst.getOperand(3)); // alignment @@ -5529,22 +5614,29 @@ processInstruction(MCInst &Inst, return true; } - case ARM::VLD2LNdAsm_8: case ARM::VLD2LNdAsm_P8: case ARM::VLD2LNdAsm_I8: - case ARM::VLD2LNdAsm_S8: case ARM::VLD2LNdAsm_U8: case ARM::VLD2LNdAsm_16: + case ARM::VLD2LNdAsm_8: case ARM::VLD2LNdAsm_P8: case ARM::VLD2LNdAsm_I8: + case ARM::VLD2LNdAsm_S8: case ARM::VLD2LNdAsm_U8: case ARM::VLD2LNdAsm_16: case ARM::VLD2LNdAsm_P16: case ARM::VLD2LNdAsm_I16: case ARM::VLD2LNdAsm_S16: - case ARM::VLD2LNdAsm_U16: case ARM::VLD2LNdAsm_32: case ARM::VLD2LNdAsm_F: + case ARM::VLD2LNdAsm_U16: case ARM::VLD2LNdAsm_32: case ARM::VLD2LNdAsm_F: case ARM::VLD2LNdAsm_F32: case ARM::VLD2LNdAsm_I32: case ARM::VLD2LNdAsm_S32: - case ARM::VLD2LNdAsm_U32: { + case ARM::VLD2LNdAsm_U32: case ARM::VLD2LNqAsm_16: case ARM::VLD2LNqAsm_P16: + case ARM::VLD2LNqAsm_I16: case ARM::VLD2LNqAsm_S16: case ARM::VLD2LNqAsm_U16: + case ARM::VLD2LNqAsm_32: case ARM::VLD2LNqAsm_F: case ARM::VLD2LNqAsm_F32: + case ARM::VLD2LNqAsm_I32: case ARM::VLD2LNqAsm_S32: + case ARM::VLD2LNqAsm_U32: { MCInst TmpInst; // Shuffle the operands around so the lane index operand is in the // right place. - TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode())); + unsigned Spacing; + TmpInst.setOpcode(getRealVLDLNOpcode(Inst.getOpcode(), Spacing)); TmpInst.addOperand(Inst.getOperand(0)); // Vd - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(2)); // Rn TmpInst.addOperand(Inst.getOperand(3)); // alignment TmpInst.addOperand(Inst.getOperand(0)); // Tied operand src (== Vd) - TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg()+1)); + TmpInst.addOperand(MCOperand::CreateReg(Inst.getOperand(0).getReg() + + Spacing)); TmpInst.addOperand(Inst.getOperand(1)); // lane TmpInst.addOperand(Inst.getOperand(4)); // CondCode TmpInst.addOperand(Inst.getOperand(5)); diff --git a/test/MC/ARM/neon-vld-encoding.s b/test/MC/ARM/neon-vld-encoding.s index 62e35313918..6e6dda674ef 100644 --- a/test/MC/ARM/neon-vld-encoding.s +++ b/test/MC/ARM/neon-vld-encoding.s @@ -230,8 +230,9 @@ vld2.8 {d16[1], d17[1]}, [r0, :16] vld2.16 {d16[1], d17[1]}, [r0, :32] vld2.32 {d16[1], d17[1]}, [r0] -@ vld2.16 {d17[1], d19[1]}, [r0] -@ vld2.32 {d17[0], d19[0]}, [r0, :64] + vld2.16 {d17[1], d19[1]}, [r0] + vld2.32 {d17[0], d19[0]}, [r0, :64] + vld2.32 {d17[0], d19[0]}, [r0, :64]! vld2.8 {d2[4], d3[4]}, [r2], r3 vld2.8 {d2[4], d3[4]}, [r2]! vld2.8 {d2[4], d3[4]}, [r2] @@ -239,8 +240,9 @@ @ CHECK: vld2.8 {d16[1], d17[1]}, [r0, :16] @ encoding: [0x3f,0x01,0xe0,0xf4] @ CHECK: vld2.16 {d16[1], d17[1]}, [r0, :32] @ encoding: [0x5f,0x05,0xe0,0xf4] @ CHECK: vld2.32 {d16[1], d17[1]}, [r0] @ encoding: [0x8f,0x09,0xe0,0xf4] -@ FIXME: vld2.16 {d17[1], d19[1]}, [r0] @ encoding: [0x6f,0x15,0xe0,0xf4] -@ FIXME: vld2.32 {d17[0], d19[0]}, [r0, :64] @ encoding: [0x5f,0x19,0xe0,0xf4] +@ CHECK: vld2.16 {d17[1], d19[1]}, [r0] @ encoding: [0x6f,0x15,0xe0,0xf4] +@ CHECK: vld2.32 {d17[0], d19[0]}, [r0, :64] @ encoding: [0x5f,0x19,0xe0,0xf4] +@ CHECK: vld2.32 {d17[0], d19[0]}, [r0, :64]! @ encoding: [0x5d,0x19,0xe0,0xf4] @ CHECK: vld2.8 {d2[4], d3[4]}, [r2], r3 @ encoding: [0x83,0x21,0xa2,0xf4] @ CHECK: vld2.8 {d2[4], d3[4]}, [r2]! @ encoding: [0x8d,0x21,0xa2,0xf4] @ CHECK: vld2.8 {d2[4], d3[4]}, [r2] @ encoding: [0x8f,0x21,0xa2,0xf4]