| //===--- arm_neon.td - ARM NEON compiler interface ------------------------===// |
| // |
| // The LLVM Compiler Infrastructure |
| // |
| // This file is distributed under the University of Illinois Open Source |
| // License. See LICENSE.TXT for details. |
| // |
| //===----------------------------------------------------------------------===// |
| // |
| // This file defines the TableGen definitions from which the ARM NEON header |
| // file will be generated. See ARM document DUI0348B. |
| // |
| //===----------------------------------------------------------------------===// |
| |
| class Op; |
| |
| def OP_NONE : Op; |
| def OP_UNAVAILABLE : Op; |
| def OP_ADD : Op; |
| def OP_ADDL : Op; |
| def OP_ADDLHi : Op; |
| def OP_ADDW : Op; |
| def OP_ADDWHi : Op; |
| def OP_SUB : Op; |
| def OP_SUBL : Op; |
| def OP_SUBLHi : Op; |
| def OP_SUBW : Op; |
| def OP_SUBWHi : Op; |
| def OP_MUL : Op; |
| def OP_MLA : Op; |
| def OP_MLAL : Op; |
| def OP_MULLHi : Op; |
| def OP_MLALHi : Op; |
| def OP_MLS : Op; |
| def OP_MLSL : Op; |
| def OP_MLSLHi : Op; |
| def OP_MUL_N : Op; |
| def OP_MLA_N : Op; |
| def OP_MLS_N : Op; |
| def OP_MLAL_N : Op; |
| def OP_MLSL_N : Op; |
| def OP_MUL_LN: Op; |
| def OP_MULX_LN: Op; |
| def OP_MULL_LN : Op; |
| def OP_MULLHi_LN : Op; |
| def OP_MLA_LN: Op; |
| def OP_MLS_LN: Op; |
| def OP_MLAL_LN : Op; |
| def OP_MLALHi_LN : Op; |
| def OP_MLSL_LN : Op; |
| def OP_MLSLHi_LN : Op; |
| def OP_QDMULL_LN : Op; |
| def OP_QDMULLHi_LN : Op; |
| def OP_QDMLAL_LN : Op; |
| def OP_QDMLALHi_LN : Op; |
| def OP_QDMLSL_LN : Op; |
| def OP_QDMLSLHi_LN : Op; |
| def OP_QDMULH_LN : Op; |
| def OP_QRDMULH_LN : Op; |
| def OP_FMS_LN : Op; |
| def OP_FMS_LNQ : Op; |
| def OP_TRN1 : Op; |
| def OP_ZIP1 : Op; |
| def OP_UZP1 : Op; |
| def OP_TRN2 : Op; |
| def OP_ZIP2 : Op; |
| def OP_UZP2 : Op; |
| def OP_EQ : Op; |
| def OP_GE : Op; |
| def OP_LE : Op; |
| def OP_GT : Op; |
| def OP_LT : Op; |
| def OP_NEG : Op; |
| def OP_NOT : Op; |
| def OP_AND : Op; |
| def OP_OR : Op; |
| def OP_XOR : Op; |
| def OP_ANDN : Op; |
| def OP_ORN : Op; |
| def OP_CAST : Op; |
| def OP_HI : Op; |
| def OP_LO : Op; |
| def OP_CONC : Op; |
| def OP_DUP : Op; |
| def OP_DUP_LN: Op; |
| def OP_SEL : Op; |
| def OP_REV64 : Op; |
| def OP_REV32 : Op; |
| def OP_REV16 : Op; |
| def OP_REINT : Op; |
| def OP_ADDHNHi : Op; |
| def OP_RADDHNHi : Op; |
| def OP_SUBHNHi : Op; |
| def OP_RSUBHNHi : Op; |
| def OP_ABDL : Op; |
| def OP_ABDLHi : Op; |
| def OP_ABA : Op; |
| def OP_ABAL : Op; |
| def OP_ABALHi : Op; |
| def OP_QDMULLHi : Op; |
| def OP_QDMLALHi : Op; |
| def OP_QDMLSLHi : Op; |
| def OP_DIV : Op; |
| def OP_LONG_HI : Op; |
| def OP_NARROW_HI : Op; |
| def OP_MOVL_HI : Op; |
| def OP_COPY_LN : Op; |
| def OP_COPYQ_LN : Op; |
| def OP_COPY_LNQ : Op; |
| |
| class Inst <string n, string p, string t, Op o> { |
| string Name = n; |
| string Prototype = p; |
| string Types = t; |
| Op Operand = o; |
| bit isShift = 0; |
| bit isScalarShift = 0; |
| bit isVCVT_N = 0; |
| bit isA64 = 0; |
| |
| // Certain intrinsics have different names than their representative |
| // instructions. This field allows us to handle this correctly when we |
| // are generating tests. |
| string InstName = ""; |
| |
| // Certain intrinsics even though they are not a WOpInst or LOpInst, |
| // generate a WOpInst/LOpInst instruction (see below for definition |
| // of a WOpInst/LOpInst). For testing purposes we need to know |
| // this. Ex: vset_lane which outputs vmov instructions. |
| bit isHiddenWInst = 0; |
| bit isHiddenLInst = 0; |
| } |
| |
| // The following instruction classes are implemented via builtins. |
| // These declarations are used to generate Builtins.def: |
| // |
| // SInst: Instruction with signed/unsigned suffix (e.g., "s8", "u8", "p8") |
| // IInst: Instruction with generic integer suffix (e.g., "i8") |
| // WInst: Instruction with only bit size suffix (e.g., "8") |
| class SInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
| class IInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
| class WInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
| |
| // The following instruction classes are implemented via operators |
| // instead of builtins. As such these declarations are only used for |
| // the purpose of generating tests. |
| // |
| // SOpInst: Instruction with signed/unsigned suffix (e.g., "s8", |
| // "u8", "p8"). |
| // IOpInst: Instruction with generic integer suffix (e.g., "i8"). |
| // WOpInst: Instruction with bit size only suffix (e.g., "8"). |
| // LOpInst: Logical instruction with no bit size suffix. |
| // NoTestOpInst: Intrinsic that has no corresponding instruction. |
| class SOpInst<string n, string p, string t, Op o> : Inst<n, p, t, o> {} |
| class IOpInst<string n, string p, string t, Op o> : Inst<n, p, t, o> {} |
| class WOpInst<string n, string p, string t, Op o> : Inst<n, p, t, o> {} |
| class LOpInst<string n, string p, string t, Op o> : Inst<n, p, t, o> {} |
| class NoTestOpInst<string n, string p, string t, Op o> : Inst<n, p, t, o> {} |
| |
| // prototype: return (arg, arg, ...) |
| // v: void |
| // t: best-fit integer (int/poly args) |
| // x: signed integer (int/float args) |
| // u: unsigned integer (int/float args) |
| // f: float (int args) |
| // d: default |
| // g: default, ignore 'Q' size modifier. |
| // j: default, force 'Q' size modifier. |
| // w: double width elements, same num elts |
| // n: double width elements, half num elts |
| // h: half width elements, double num elts |
| // q: half width elements, quad num elts |
| // e: half width elements, double num elts, unsigned |
| // m: half width elements, same num elts |
| // i: constant int |
| // l: constant uint64 |
| // s: scalar of element type |
| // z: scalar of half width element type, signed |
| // r: scalar of double width element type, signed |
| // a: scalar of element type (splat to vector type) |
| // b: scalar of unsigned integer/long type (int/float args) |
| // y: scalar of float |
| // o: scalar of double |
| // k: default elt width, double num elts |
| // #: array of default vectors |
| // p: pointer type |
| // c: const pointer type |
| |
| // sizes: |
| // c: char |
| // s: short |
| // i: int |
| // l: long |
| // f: float |
| // h: half-float |
| // d: double |
| |
| // size modifiers: |
| // S: scalar, only used for function mangling. |
| // U: unsigned |
| // Q: 128b |
| // H: 128b without mangling 'q' |
| // P: polynomial |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.1 Addition |
| def VADD : IOpInst<"vadd", "ddd", |
| "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_ADD>; |
| def VADDL : SOpInst<"vaddl", "wdd", "csiUcUsUi", OP_ADDL>; |
| def VADDW : SOpInst<"vaddw", "wwd", "csiUcUsUi", OP_ADDW>; |
| def VHADD : SInst<"vhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VRHADD : SInst<"vrhadd", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VQADD : SInst<"vqadd", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VADDHN : IInst<"vaddhn", "hkk", "silUsUiUl">; |
| def VRADDHN : IInst<"vraddhn", "hkk", "silUsUiUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.2 Multiplication |
| def VMUL : IOpInst<"vmul", "ddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MUL>; |
| def VMULP : SInst<"vmul", "ddd", "PcQPc">; |
| def VMLA : IOpInst<"vmla", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLA>; |
| def VMLAL : SOpInst<"vmlal", "wwdd", "csiUcUsUi", OP_MLAL>; |
| def VMLS : IOpInst<"vmls", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_MLS>; |
| def VMLSL : SOpInst<"vmlsl", "wwdd", "csiUcUsUi", OP_MLSL>; |
| def VQDMULH : SInst<"vqdmulh", "ddd", "siQsQi">; |
| def VQRDMULH : SInst<"vqrdmulh", "ddd", "siQsQi">; |
| def VQDMLAL : SInst<"vqdmlal", "wwdd", "si">; |
| def VQDMLSL : SInst<"vqdmlsl", "wwdd", "si">; |
| def VMULL : SInst<"vmull", "wdd", "csiUcUsUiPc">; |
| def VQDMULL : SInst<"vqdmull", "wdd", "si">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.3 Subtraction |
| def VSUB : IOpInst<"vsub", "ddd", |
| "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUl", OP_SUB>; |
| def VSUBL : SOpInst<"vsubl", "wdd", "csiUcUsUi", OP_SUBL>; |
| def VSUBW : SOpInst<"vsubw", "wwd", "csiUcUsUi", OP_SUBW>; |
| def VQSUB : SInst<"vqsub", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VHSUB : SInst<"vhsub", "ddd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VSUBHN : IInst<"vsubhn", "hkk", "silUsUiUl">; |
| def VRSUBHN : IInst<"vrsubhn", "hkk", "silUsUiUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.4 Comparison |
| def VCEQ : IOpInst<"vceq", "udd", "csifUcUsUiPcQcQsQiQfQUcQUsQUiQPc", OP_EQ>; |
| def VCGE : SOpInst<"vcge", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GE>; |
| let InstName = "vcge" in |
| def VCLE : SOpInst<"vcle", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LE>; |
| def VCGT : SOpInst<"vcgt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_GT>; |
| let InstName = "vcgt" in |
| def VCLT : SOpInst<"vclt", "udd", "csifUcUsUiQcQsQiQfQUcQUsQUi", OP_LT>; |
| let InstName = "vacge" in { |
| def VCAGE : IInst<"vcage", "udd", "fQf">; |
| def VCALE : IInst<"vcale", "udd", "fQf">; |
| } |
| let InstName = "vacgt" in { |
| def VCAGT : IInst<"vcagt", "udd", "fQf">; |
| def VCALT : IInst<"vcalt", "udd", "fQf">; |
| } |
| def VTST : WInst<"vtst", "udd", "csiUcUsUiPcPsQcQsQiQUcQUsQUiQPcQPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.5 Absolute Difference |
| def VABD : SInst<"vabd", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">; |
| def VABDL : SOpInst<"vabdl", "wdd", "csiUcUsUi", OP_ABDL>; |
| def VABA : SOpInst<"vaba", "dddd", "csiUcUsUiQcQsQiQUcQUsQUi", OP_ABA>; |
| def VABAL : SOpInst<"vabal", "wwdd", "csiUcUsUi", OP_ABAL>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.6 Max/Min |
| def VMAX : SInst<"vmax", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">; |
| def VMIN : SInst<"vmin", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQf">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.7 Pairwise Addition |
| def VPADD : IInst<"vpadd", "ddd", "csiUcUsUif">; |
| def VPADDL : SInst<"vpaddl", "nd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VPADAL : SInst<"vpadal", "nnd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.8-9 Folding Max/Min |
| def VPMAX : SInst<"vpmax", "ddd", "csiUcUsUif">; |
| def VPMIN : SInst<"vpmin", "ddd", "csiUcUsUif">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.10 Reciprocal/Sqrt |
| def VRECPS : IInst<"vrecps", "ddd", "fQf">; |
| def VRSQRTS : IInst<"vrsqrts", "ddd", "fQf">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.11 Shifts by signed variable |
| def VSHL : SInst<"vshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VQSHL : SInst<"vqshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VRSHL : SInst<"vrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VQRSHL : SInst<"vqrshl", "ddx", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.12 Shifts by constant |
| let isShift = 1 in { |
| def VSHR_N : SInst<"vshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VSHL_N : IInst<"vshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VRSHR_N : SInst<"vrshr_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VSRA_N : SInst<"vsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VRSRA_N : SInst<"vrsra_n", "dddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VQSHL_N : SInst<"vqshl_n", "ddi", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl">; |
| def VQSHLU_N : SInst<"vqshlu_n", "udi", "csilQcQsQiQl">; |
| def VSHRN_N : IInst<"vshrn_n", "hki", "silUsUiUl">; |
| def VQSHRUN_N : SInst<"vqshrun_n", "eki", "sil">; |
| def VQRSHRUN_N : SInst<"vqrshrun_n", "eki", "sil">; |
| def VQSHRN_N : SInst<"vqshrn_n", "hki", "silUsUiUl">; |
| def VRSHRN_N : IInst<"vrshrn_n", "hki", "silUsUiUl">; |
| def VQRSHRN_N : SInst<"vqrshrn_n", "hki", "silUsUiUl">; |
| def VSHLL_N : SInst<"vshll_n", "wdi", "csiUcUsUi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.13 Shifts with insert |
| def VSRI_N : WInst<"vsri_n", "dddi", |
| "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">; |
| def VSLI_N : WInst<"vsli_n", "dddi", |
| "csilUcUsUiUlPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.14 Loads and stores of a single vector |
| def VLD1 : WInst<"vld1", "dc", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VLD1_LANE : WInst<"vld1_lane", "dcdi", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VLD1_DUP : WInst<"vld1_dup", "dc", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VST1 : WInst<"vst1", "vpd", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VST1_LANE : WInst<"vst1_lane", "vpdi", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.15 Loads and stores of an N-element structure |
| def VLD2 : WInst<"vld2", "2c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VLD3 : WInst<"vld3", "3c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VLD4 : WInst<"vld4", "4c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VLD2_DUP : WInst<"vld2_dup", "2c", "UcUsUiUlcsilhfPcPs">; |
| def VLD3_DUP : WInst<"vld3_dup", "3c", "UcUsUiUlcsilhfPcPs">; |
| def VLD4_DUP : WInst<"vld4_dup", "4c", "UcUsUiUlcsilhfPcPs">; |
| def VLD2_LANE : WInst<"vld2_lane", "2c2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| def VLD3_LANE : WInst<"vld3_lane", "3c3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| def VLD4_LANE : WInst<"vld4_lane", "4c4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| def VST2 : WInst<"vst2", "vp2", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VST3 : WInst<"vst3", "vp3", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VST4 : WInst<"vst4", "vp4", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; |
| def VST2_LANE : WInst<"vst2_lane", "vp2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| def VST3_LANE : WInst<"vst3_lane", "vp3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| def VST4_LANE : WInst<"vst4_lane", "vp4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.16 Extract lanes from a vector |
| let InstName = "vmov" in |
| def VGET_LANE : IInst<"vget_lane", "sdi", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.17 Set lanes within a vector |
| let InstName = "vmov" in |
| def VSET_LANE : IInst<"vset_lane", "dsdi", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.18 Initialize a vector from bit pattern |
| def VCREATE : NoTestOpInst<"vcreate", "dl", "csihfUcUsUiUlPcPsl", OP_CAST>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.19 Set all lanes to same value |
| let InstName = "vmov" in { |
| def VDUP_N : WOpInst<"vdup_n", "ds", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl", OP_DUP>; |
| def VMOV_N : WOpInst<"vmov_n", "ds", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl", OP_DUP>; |
| } |
| let InstName = "" in |
| def VDUP_LANE: WOpInst<"vdup_lane", "dgi", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUl", |
| OP_DUP_LN>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.20 Combining vectors |
| def VCOMBINE : NoTestOpInst<"vcombine", "kdd", "csilhfUcUsUiUlPcPs", OP_CONC>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.21 Splitting vectors |
| let InstName = "vmov" in { |
| def VGET_HIGH : NoTestOpInst<"vget_high", "dk", "csilhfUcUsUiUlPcPs", OP_HI>; |
| def VGET_LOW : NoTestOpInst<"vget_low", "dk", "csilhfUcUsUiUlPcPs", OP_LO>; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.22 Converting vectors |
| def VCVT_S32 : SInst<"vcvt_s32", "xd", "fQf">; |
| def VCVT_U32 : SInst<"vcvt_u32", "ud", "fQf">; |
| def VCVT_F16 : SInst<"vcvt_f16", "hk", "f">; |
| def VCVT_F32 : SInst<"vcvt_f32", "fd", "iUiQiQUi">; |
| def VCVT_F32_F16 : SInst<"vcvt_f32_f16", "fd", "h">; |
| let isVCVT_N = 1 in { |
| def VCVT_N_S32 : SInst<"vcvt_n_s32", "xdi", "fQf">; |
| def VCVT_N_U32 : SInst<"vcvt_n_u32", "udi", "fQf">; |
| def VCVT_N_F32 : SInst<"vcvt_n_f32", "fdi", "iUiQiQUi">; |
| } |
| def VMOVN : IInst<"vmovn", "hk", "silUsUiUl">; |
| def VMOVL : SInst<"vmovl", "wd", "csiUcUsUi">; |
| def VQMOVN : SInst<"vqmovn", "hk", "silUsUiUl">; |
| def VQMOVUN : SInst<"vqmovun", "ek", "sil">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.23-24 Table lookup, Extended table lookup |
| let InstName = "vtbl" in { |
| def VTBL1 : WInst<"vtbl1", "ddt", "UccPc">; |
| def VTBL2 : WInst<"vtbl2", "d2t", "UccPc">; |
| def VTBL3 : WInst<"vtbl3", "d3t", "UccPc">; |
| def VTBL4 : WInst<"vtbl4", "d4t", "UccPc">; |
| } |
| let InstName = "vtbx" in { |
| def VTBX1 : WInst<"vtbx1", "dddt", "UccPc">; |
| def VTBX2 : WInst<"vtbx2", "dd2t", "UccPc">; |
| def VTBX3 : WInst<"vtbx3", "dd3t", "UccPc">; |
| def VTBX4 : WInst<"vtbx4", "dd4t", "UccPc">; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.25 Operations with a scalar value |
| def VMLA_LANE : IOpInst<"vmla_lane", "dddgi", |
| "siUsUifQsQiQUsQUiQf", OP_MLA_LN>; |
| def VMLAL_LANE : SOpInst<"vmlal_lane", "wwddi", "siUsUi", OP_MLAL_LN>; |
| def VQDMLAL_LANE : SOpInst<"vqdmlal_lane", "wwddi", "si", OP_QDMLAL_LN>; |
| def VMLS_LANE : IOpInst<"vmls_lane", "dddgi", |
| "siUsUifQsQiQUsQUiQf", OP_MLS_LN>; |
| def VMLSL_LANE : SOpInst<"vmlsl_lane", "wwddi", "siUsUi", OP_MLSL_LN>; |
| def VQDMLSL_LANE : SOpInst<"vqdmlsl_lane", "wwddi", "si", OP_QDMLSL_LN>; |
| def VMUL_N : IOpInst<"vmul_n", "dds", "sifUsUiQsQiQfQUsQUi", OP_MUL_N>; |
| def VMUL_LANE : IOpInst<"vmul_lane", "ddgi", |
| "sifUsUiQsQiQfQUsQUi", OP_MUL_LN>; |
| def VMULL_N : SInst<"vmull_n", "wda", "siUsUi">; |
| def VMULL_LANE : SOpInst<"vmull_lane", "wddi", "siUsUi", OP_MULL_LN>; |
| def VQDMULL_N : SInst<"vqdmull_n", "wda", "si">; |
| def VQDMULL_LANE : SOpInst<"vqdmull_lane", "wddi", "si", OP_QDMULL_LN>; |
| def VQDMULH_N : SInst<"vqdmulh_n", "dda", "siQsQi">; |
| def VQDMULH_LANE : SOpInst<"vqdmulh_lane", "ddgi", "siQsQi", OP_QDMULH_LN>; |
| def VQRDMULH_N : SInst<"vqrdmulh_n", "dda", "siQsQi">; |
| def VQRDMULH_LANE : SOpInst<"vqrdmulh_lane", "ddgi", "siQsQi", OP_QRDMULH_LN>; |
| def VMLA_N : IOpInst<"vmla_n", "ddda", "siUsUifQsQiQUsQUiQf", OP_MLA_N>; |
| def VMLAL_N : SOpInst<"vmlal_n", "wwda", "siUsUi", OP_MLAL_N>; |
| def VQDMLAL_N : SInst<"vqdmlal_n", "wwda", "si">; |
| def VMLS_N : IOpInst<"vmls_n", "ddds", "siUsUifQsQiQUsQUiQf", OP_MLS_N>; |
| def VMLSL_N : SOpInst<"vmlsl_n", "wwda", "siUsUi", OP_MLSL_N>; |
| def VQDMLSL_N : SInst<"vqdmlsl_n", "wwda", "si">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.26 Vector Extract |
| def VEXT : WInst<"vext", "dddi", |
| "cUcPcsUsPsiUilUlfQcQUcQPcQsQUsQPsQiQUiQlQUlQf">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.27 Reverse vector elements |
| def VREV64 : WOpInst<"vrev64", "dd", "csiUcUsUiPcPsfQcQsQiQUcQUsQUiQPcQPsQf", |
| OP_REV64>; |
| def VREV32 : WOpInst<"vrev32", "dd", "csUcUsPcPsQcQsQUcQUsQPcQPs", OP_REV32>; |
| def VREV16 : WOpInst<"vrev16", "dd", "cUcPcQcQUcQPc", OP_REV16>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.28 Other single operand arithmetic |
| def VABS : SInst<"vabs", "dd", "csifQcQsQiQf">; |
| def VQABS : SInst<"vqabs", "dd", "csiQcQsQi">; |
| def VNEG : SOpInst<"vneg", "dd", "csifQcQsQiQf", OP_NEG>; |
| def VQNEG : SInst<"vqneg", "dd", "csiQcQsQi">; |
| def VCLS : SInst<"vcls", "dd", "csiQcQsQi">; |
| def VCLZ : IInst<"vclz", "dd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VCNT : WInst<"vcnt", "dd", "UccPcQUcQcQPc">; |
| def VRECPE : SInst<"vrecpe", "dd", "fUiQfQUi">; |
| def VRSQRTE : SInst<"vrsqrte", "dd", "fUiQfQUi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.29 Logical operations |
| def VMVN : LOpInst<"vmvn", "dd", "csiUcUsUiPcQcQsQiQUcQUsQUiQPc", OP_NOT>; |
| def VAND : LOpInst<"vand", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_AND>; |
| def VORR : LOpInst<"vorr", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_OR>; |
| def VEOR : LOpInst<"veor", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_XOR>; |
| def VBIC : LOpInst<"vbic", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ANDN>; |
| def VORN : LOpInst<"vorn", "ddd", "csilUcUsUiUlQcQsQiQlQUcQUsQUiQUl", OP_ORN>; |
| let isHiddenLInst = 1 in |
| def VBSL : SInst<"vbsl", "dudd", |
| "csilUcUsUiUlfPcPsQcQsQiQlQUcQUsQUiQUlQfQPcQPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.30 Transposition operations |
| def VTRN : WInst<"vtrn", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">; |
| def VZIP : WInst<"vzip", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">; |
| def VUZP : WInst<"vuzp", "2dd", "csiUcUsUifPcPsQcQsQiQUcQUsQUiQfQPcQPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // E.3.31 Vector reinterpret cast operations |
| def VREINTERPRET |
| : NoTestOpInst<"vreinterpret", "dd", |
| "csilUcUsUiUlhfPcPsQcQsQiQlQUcQUsQUiQUlQhQfQPcQPs", OP_REINT>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Vector fused multiply-add operations |
| |
| def VFMA : SInst<"vfma", "dddd", "fQf">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // AArch64 Intrinsics |
| |
| let isA64 = 1 in { |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Load/Store |
| // With additional QUl, Ql, Qd type. |
| def LD1 : WInst<"vld1", "dc", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def LD2 : WInst<"vld2", "2c", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def LD3 : WInst<"vld3", "3c", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def LD4 : WInst<"vld4", "4c", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def ST1 : WInst<"vst1", "vpd", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def ST2 : WInst<"vst2", "vp2", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def ST3 : WInst<"vst3", "vp3", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| def ST4 : WInst<"vst4", "vp4", |
| "QUcQUsQUiQUlQcQsQiQlQhQfQdQPcQPsUcUsUiUlcsilhfdPcPs">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Addition |
| // With additional Qd type. |
| def ADD : IOpInst<"vadd", "ddd", "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUlQd", OP_ADD>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Subtraction |
| // With additional Qd type. |
| def SUB : IOpInst<"vsub", "ddd", "csilfUcUsUiUlQcQsQiQlQfQUcQUsQUiQUlQd", OP_SUB>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Multiplication |
| // With additional Qd type. |
| def MUL : IOpInst<"vmul", "ddd", "csifUcUsUiQcQsQiQfQUcQUsQUiQd", OP_MUL>; |
| def MLA : IOpInst<"vmla", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUiQd", OP_MLA>; |
| def MLS : IOpInst<"vmls", "dddd", "csifUcUsUiQcQsQiQfQUcQUsQUiQd", OP_MLS>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Multiplication Extended |
| def MULX : SInst<"vmulx", "ddd", "fdQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Division |
| def FDIV : IOpInst<"vdiv", "ddd", "fQfQd", OP_DIV>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Vector fused multiply-add operations |
| // With additional Qd type. |
| def FMLA : SInst<"vfma", "dddd", "fQfQd">; |
| def FMLS : SInst<"vfms", "dddd", "fQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Logical operations |
| // With additional Qd type. |
| def BSL : SInst<"vbsl", "dudd", "csilUcUsUiUlfPcPsQcQsQiQlQUcQUsQUiQUlQfQPcQPsQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Absolute Difference |
| // With additional Qd type. |
| def ABD : SInst<"vabd", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Reciprocal/Sqrt |
| // With additional Qd type. |
| def FRECPS : IInst<"vrecps", "ddd", "fQfQd">; |
| def FRSQRTS : IInst<"vrsqrts", "ddd", "fQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Comparison |
| // With additional Qd type. |
| def FCAGE : IInst<"vcage", "udd", "fQfQd">; |
| def FCAGT : IInst<"vcagt", "udd", "fQfQd">; |
| def FCALE : IInst<"vcale", "udd", "fQfQd">; |
| def FCALT : IInst<"vcalt", "udd", "fQfQd">; |
| // With additional Ql, QUl, Qd types. |
| def CMTST : WInst<"vtst", "udd", "csiUcUsUiPcPsQcQsQiQlQUcQUsQUiQUlQPcQPs">; |
| def CFMEQ : SOpInst<"vceq", "udd", |
| "csifUcUsUiPcQcQsQiQlQfQUcQUsQUiQUlQPcQd", OP_EQ>; |
| def CFMGE : SOpInst<"vcge", "udd", "csifUcUsUiQcQsQiQlQfQUcQUsQUiQUlQd", OP_GE>; |
| def CFMLE : SOpInst<"vcle", "udd", "csifUcUsUiQcQsQiQlQfQUcQUsQUiQUlQd", OP_LE>; |
| def CFMGT : SOpInst<"vcgt", "udd", "csifUcUsUiQcQsQiQlQfQUcQUsQUiQUlQd", OP_GT>; |
| def CFMLT : SOpInst<"vclt", "udd", "csifUcUsUiQcQsQiQlQfQUcQUsQUiQUlQd", OP_LT>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Max/Min Integer |
| // With additional Qd type. |
| def MAX : SInst<"vmax", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| def MIN : SInst<"vmin", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // MaxNum/MinNum Floating Point |
| def FMAXNM : SInst<"vmaxnm", "ddd", "fQfQd">; |
| def FMINNM : SInst<"vminnm", "ddd", "fQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Pairwise Max/Min |
| // With additional Qc Qs Qi QUc QUs QUi Qf Qd types. |
| def MAXP : SInst<"vpmax", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| def MINP : SInst<"vpmin", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Pairwise MaxNum/MinNum Floating Point |
| def FMAXNMP : SInst<"vpmaxnm", "ddd", "fQfQd">; |
| def FMINNMP : SInst<"vpminnm", "ddd", "fQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Pairwise Addition |
| // With additional Qc Qs Qi QUc QUs QUi Qf Qd types. |
| def ADDP : IInst<"vpadd", "ddd", "csiUcUsUifQcQsQiQUcQUsQUiQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Shifts by constant |
| let isShift = 1 in { |
| // Left shift long high |
| def SHLL_HIGH_N : SOpInst<"vshll_high_n", "ndi", "HcHsHiHUcHUsHUi", |
| OP_LONG_HI>; |
| |
| // Right shift narrow high |
| def SHRN_HIGH_N : IOpInst<"vshrn_high_n", "hmdi", |
| "HsHiHlHUsHUiHUl", OP_NARROW_HI>; |
| def QSHRUN_HIGH_N : SOpInst<"vqshrun_high_n", "hmdi", |
| "HsHiHl", OP_NARROW_HI>; |
| def RSHRN_HIGH_N : IOpInst<"vrshrn_high_n", "hmdi", |
| "HsHiHlHUsHUiHUl", OP_NARROW_HI>; |
| def QRSHRUN_HIGH_N : SOpInst<"vqrshrun_high_n", "hmdi", |
| "HsHiHl", OP_NARROW_HI>; |
| def QSHRN_HIGH_N : SOpInst<"vqshrn_high_n", "hmdi", |
| "HsHiHlHUsHUiHUl", OP_NARROW_HI>; |
| def QRSHRN_HIGH_N : SOpInst<"vqrshrn_high_n", "hmdi", |
| "HsHiHlHUsHUiHUl", OP_NARROW_HI>; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Converting vectors |
| def VMOVL_HIGH : SOpInst<"vmovl_high", "nd", "HcHsHiHUcHUsHUi", OP_MOVL_HI>; |
| |
| let isVCVT_N = 1 in { |
| def CVTF_N_F64 : SInst<"vcvt_n_f64", "fdi", "QlQUl">; |
| def FCVTZS_N_S64 : SInst<"vcvt_n_s64", "xdi", "Qd">; |
| def FCVTZS_N_U64 : SInst<"vcvt_n_u64", "udi", "Qd">; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // 3VDiff class using high 64-bit in operands |
| def VADDL_HIGH : SOpInst<"vaddl_high", "wkk", "csiUcUsUi", OP_ADDLHi>; |
| def VADDW_HIGH : SOpInst<"vaddw_high", "wwk", "csiUcUsUi", OP_ADDWHi>; |
| def VSUBL_HIGH : SOpInst<"vsubl_high", "wkk", "csiUcUsUi", OP_SUBLHi>; |
| def VSUBW_HIGH : SOpInst<"vsubw_high", "wwk", "csiUcUsUi", OP_SUBWHi>; |
| |
| def VABDL_HIGH : SOpInst<"vabdl_high", "wkk", "csiUcUsUi", OP_ABDLHi>; |
| def VABAL_HIGH : SOpInst<"vabal_high", "wwkk", "csiUcUsUi", OP_ABALHi>; |
| |
| def VMULL_HIGH : SOpInst<"vmull_high", "wkk", "csiUcUsUiPc", OP_MULLHi>; |
| def VMLAL_HIGH : SOpInst<"vmlal_high", "wwkk", "csiUcUsUi", OP_MLALHi>; |
| def VMLSL_HIGH : SOpInst<"vmlsl_high", "wwkk", "csiUcUsUi", OP_MLSLHi>; |
| |
| def VADDHN_HIGH : SOpInst<"vaddhn_high", "qhkk", "silUsUiUl", OP_ADDHNHi>; |
| def VRADDHN_HIGH : SOpInst<"vraddhn_high", "qhkk", "silUsUiUl", OP_RADDHNHi>; |
| def VSUBHN_HIGH : SOpInst<"vsubhn_high", "qhkk", "silUsUiUl", OP_SUBHNHi>; |
| def VRSUBHN_HIGH : SOpInst<"vrsubhn_high", "qhkk", "silUsUiUl", OP_RSUBHNHi>; |
| |
| def VQDMULL_HIGH : SOpInst<"vqdmull_high", "wkk", "si", OP_QDMULLHi>; |
| def VQDMLAL_HIGH : SOpInst<"vqdmlal_high", "wwkk", "si", OP_QDMLALHi>; |
| def VQDMLSL_HIGH : SOpInst<"vqdmlsl_high", "wwkk", "si", OP_QDMLSLHi>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Extract or insert element from vector |
| def GET_LANE : IInst<"vget_lane", "sdi", |
| "csilPcPsUcUsUiUlQcQsQiQlQUcQUsQUiQUlPcPsQPcQPsfdQfQd">; |
| def SET_LANE : IInst<"vset_lane", "dsdi", |
| "csilPcPsUcUsUiUlQcQsQiQlQUcQUsQUiQUlPcPsQPcQPsfdQfQd">; |
| def COPY_LANE : IOpInst<"vcopy_lane", "ddidi", |
| "csiPcPsUcUsUiPcPsf", OP_COPY_LN>; |
| def COPYQ_LANE : IOpInst<"vcopy_lane", "ddigi", |
| "QcQsQiQlQUcQUsQUiQUlQPcQPsQfQd", OP_COPYQ_LN>; |
| def COPY_LANEQ : IOpInst<"vcopy_laneq", "ddiki", |
| "csiPcPsUcUsUif", OP_COPY_LNQ>; |
| def COPYQ_LANEQ : IOpInst<"vcopy_laneq", "ddidi", |
| "QcQsQiQlQUcQUsQUiQUlQPcQPsQfd", OP_COPY_LN>; |
| |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Set all lanes to same value |
| def VDUP_LANE1: WOpInst<"vdup_lane", "dgi", |
| "csilPcPsUcUsUiUlhfdQcQsQiQlQPcQPsQUcQUsQUiQUlQhQfQd", |
| OP_DUP_LN>; |
| def VDUP_LANE2: WOpInst<"vdup_laneq", "dki", |
| "csilPcPsUcUsUiUlhfdQcQsQiQlQPcQPsQUcQUsQUiQUlQhQfQd", |
| OP_DUP_LN>; |
| def DUP_N : WOpInst<"vdup_n", "ds", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUldQd", |
| OP_DUP>; |
| def MOV_N : WOpInst<"vmov_n", "ds", |
| "UcUsUicsiPcPsfQUcQUsQUiQcQsQiQPcQPsQflUlQlQUldQd", |
| OP_DUP>; |
| //////////////////////////////////////////////////////////////////////////////// |
| //Initialize a vector from bit pattern |
| def CREATE : NoTestOpInst<"vcreate", "dl", "csihfdUcUsUiUlPcPsl", OP_CAST>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| |
| def VMLA_LANEQ : IOpInst<"vmla_laneq", "dddji", |
| "siUsUifQsQiQUsQUiQf", OP_MLA_LN>; |
| def VMLS_LANEQ : IOpInst<"vmls_laneq", "dddji", |
| "siUsUifQsQiQUsQUiQf", OP_MLS_LN>; |
| |
| def VFMA_LANE : IInst<"vfma_lane", "dddgi", "fdQfQd">; |
| def VFMA_LANEQ : IInst<"vfma_laneq", "dddji", "fdQfQd">; |
| def VFMS_LANE : IOpInst<"vfms_lane", "dddgi", "fdQfQd", OP_FMS_LN>; |
| def VFMS_LANEQ : IOpInst<"vfms_laneq", "dddji", "fdQfQd", OP_FMS_LNQ>; |
| |
| def VMLAL_LANEQ : SOpInst<"vmlal_laneq", "wwdki", "siUsUi", OP_MLAL_LN>; |
| def VMLAL_HIGH_LANE : SOpInst<"vmlal_high_lane", "wwkdi", "siUsUi", |
| OP_MLALHi_LN>; |
| def VMLAL_HIGH_LANEQ : SOpInst<"vmlal_high_laneq", "wwkki", "siUsUi", |
| OP_MLALHi_LN>; |
| def VMLSL_LANEQ : SOpInst<"vmlsl_laneq", "wwdki", "siUsUi", OP_MLSL_LN>; |
| def VMLSL_HIGH_LANE : SOpInst<"vmlsl_high_lane", "wwkdi", "siUsUi", |
| OP_MLSLHi_LN>; |
| def VMLSL_HIGH_LANEQ : SOpInst<"vmlsl_high_laneq", "wwkki", "siUsUi", |
| OP_MLSLHi_LN>; |
| |
| def VQDMLAL_LANEQ : SOpInst<"vqdmlal_laneq", "wwdki", "si", OP_QDMLAL_LN>; |
| def VQDMLAL_HIGH_LANE : SOpInst<"vqdmlal_high_lane", "wwkdi", "si", |
| OP_QDMLALHi_LN>; |
| def VQDMLAL_HIGH_LANEQ : SOpInst<"vqdmlal_high_laneq", "wwkki", "si", |
| OP_QDMLALHi_LN>; |
| def VQDMLSL_LANEQ : SOpInst<"vqdmlsl_laneq", "wwdki", "si", OP_QDMLSL_LN>; |
| def VQDMLSL_HIGH_LANE : SOpInst<"vqdmlsl_high_lane", "wwkdi", "si", |
| OP_QDMLSLHi_LN>; |
| def VQDMLSL_HIGH_LANEQ : SOpInst<"vqdmlsl_high_laneq", "wwkki", "si", |
| OP_QDMLSLHi_LN>; |
| |
| // Newly add double parameter for vmul_lane in aarch64 |
| def VMUL_LANE_A64 : IOpInst<"vmul_lane", "ddgi", "dQd", OP_MUL_LN>; |
| |
| def VMUL_LANEQ : IOpInst<"vmul_laneq", "ddji", |
| "sifdUsUiQsQiQfQUsQUiQfQd", OP_MUL_LN>; |
| def VMULL_LANEQ : SOpInst<"vmull_laneq", "wdki", "siUsUi", OP_MULL_LN>; |
| def VMULL_HIGH_LANE : SOpInst<"vmull_high_lane", "wkdi", "siUsUi", |
| OP_MULLHi_LN>; |
| def VMULL_HIGH_LANEQ : SOpInst<"vmull_high_laneq", "wkki", "siUsUi", |
| OP_MULLHi_LN>; |
| |
| def VQDMULL_LANEQ : SOpInst<"vqdmull_laneq", "wdki", "si", OP_QDMULL_LN>; |
| def VQDMULL_HIGH_LANE : SOpInst<"vqdmull_high_lane", "wkdi", "si", |
| OP_QDMULLHi_LN>; |
| def VQDMULL_HIGH_LANEQ : SOpInst<"vqdmull_high_laneq", "wkki", "si", |
| OP_QDMULLHi_LN>; |
| |
| def VQDMULH_LANEQ : SOpInst<"vqdmulh_laneq", "ddji", "siQsQi", OP_QDMULH_LN>; |
| def VQRDMULH_LANEQ : SOpInst<"vqrdmulh_laneq", "ddji", "siQsQi", OP_QRDMULH_LN>; |
| |
| def VMULX_LANE : IOpInst<"vmulx_lane", "ddgi", "fdQfQd", OP_MULX_LN>; |
| def VMULX_LANEQ : IOpInst<"vmulx_laneq", "ddji", "fdQfQd", OP_MULX_LN>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Across vectors class |
| def VADDLV : SInst<"vaddlv", "rd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def VMAXV : SInst<"vmaxv", "sd", "csiUcUsUiQcQsQiQUcQUsQUiQf">; |
| def VMINV : SInst<"vminv", "sd", "csiUcUsUiQcQsQiQUcQUsQUiQf">; |
| def VADDV : SInst<"vaddv", "sd", "csiUcUsUiQcQsQiQUcQUsQUi">; |
| def FMAXNMV : SInst<"vmaxnmv", "sd", "Qf">; |
| def FMINNMV : SInst<"vminnmv", "sd", "Qf">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Newly added Vector Extract for f64 |
| def VEXT_A64 : WInst<"vext", "dddi", |
| "cUcPcsUsPsiUilUlfdQcQUcQPcQsQUsQPsQiQUiQlQUlQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Crypto |
| def AESE : SInst<"vaese", "ddd", "QUc">; |
| def AESD : SInst<"vaesd", "ddd", "QUc">; |
| def AESMC : SInst<"vaesmc", "dd", "QUc">; |
| def AESIMC : SInst<"vaesimc", "dd", "QUc">; |
| |
| def SHA1H : SInst<"vsha1h", "ss", "Ui">; |
| def SHA1SU1 : SInst<"vsha1su1", "ddd", "QUi">; |
| def SHA256SU0 : SInst<"vsha256su0", "ddd", "QUi">; |
| |
| def SHA1C : SInst<"vsha1c", "ddsd", "QUi">; |
| def SHA1P : SInst<"vsha1p", "ddsd", "QUi">; |
| def SHA1M : SInst<"vsha1m", "ddsd", "QUi">; |
| def SHA1SU0 : SInst<"vsha1su0", "dddd", "QUi">; |
| def SHA256H : SInst<"vsha256h", "dddd", "QUi">; |
| def SHA256H2 : SInst<"vsha256h2", "dddd", "QUi">; |
| def SHA256SU1 : SInst<"vsha256su1", "dddd", "QUi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Permutation |
| def VTRN1 : SOpInst<"vtrn1", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_TRN1>; |
| def VZIP1 : SOpInst<"vzip1", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_ZIP1>; |
| def VUZP1 : SOpInst<"vuzp1", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_UZP1>; |
| def VTRN2 : SOpInst<"vtrn2", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_TRN2>; |
| def VZIP2 : SOpInst<"vzip2", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_ZIP2>; |
| def VUZP2 : SOpInst<"vuzp2", "ddd", |
| "csiUcUsUifPcPsQcQsQiQlQUcQUsQUiQUlQfQdQPcQPs", OP_UZP2>; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Arithmetic |
| |
| // Scalar Addition |
| def SCALAR_ADD : SInst<"vadd", "sss", "SlSUl">; |
| // Scalar Saturating Add |
| def SCALAR_QADD : SInst<"vqadd", "sss", "ScSsSiSlSUcSUsSUiSUl">; |
| |
| // Scalar Subtraction |
| def SCALAR_SUB : SInst<"vsub", "sss", "SlSUl">; |
| // Scalar Saturating Sub |
| def SCALAR_QSUB : SInst<"vqsub", "sss", "ScSsSiSlSUcSUsSUiSUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Shift |
| // Scalar Shift Left |
| def SCALAR_SHL: SInst<"vshl", "sss", "SlSUl">; |
| // Scalar Saturating Shift Left |
| def SCALAR_QSHL: SInst<"vqshl", "sss", "ScSsSiSlSUcSUsSUiSUl">; |
| // Scalar Saturating Rounding Shift Left |
| def SCALAR_QRSHL: SInst<"vqrshl", "sss", "ScSsSiSlSUcSUsSUiSUl">; |
| // Scalar Shift Rouding Left |
| def SCALAR_RSHL: SInst<"vrshl", "sss", "SlSUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Shift (Immediate) |
| let isScalarShift = 1 in { |
| // Signed/Unsigned Shift Right (Immediate) |
| def SCALAR_SSHR_N: SInst<"vshr_n", "ssi", "SlSUl">; |
| // Signed/Unsigned Rounding Shift Right (Immediate) |
| def SCALAR_SRSHR_N: SInst<"vrshr_n", "ssi", "SlSUl">; |
| |
| // Signed/Unsigned Shift Right and Accumulate (Immediate) |
| def SCALAR_SSRA_N: SInst<"vsra_n", "sssi", "SlSUl">; |
| // Signed/Unsigned Rounding Shift Right and Accumulate (Immediate) |
| def SCALAR_SRSRA_N: SInst<"vrsra_n", "sssi", "SlSUl">; |
| |
| // Shift Left (Immediate) |
| def SCALAR_SHL_N: SInst<"vshl_n", "ssi", "SlSUl">; |
| // Signed/Unsigned Saturating Shift Left (Immediate) |
| def SCALAR_SQSHL_N: SInst<"vqshl_n", "ssi", "ScSsSiSlSUcSUsSUiSUl">; |
| // Signed Saturating Shift Left Unsigned (Immediate) |
| def SCALAR_SQSHLU_N: SInst<"vqshlu_n", "ssi", "ScSsSiSl">; |
| |
| // Shift Right And Insert (Immediate) |
| def SCALAR_SRI_N: SInst<"vsri_n", "ssi", "SlSUl">; |
| // Shift Left And Insert (Immediate) |
| def SCALAR_SLI_N: SInst<"vsli_n", "ssi", "SlSUl">; |
| |
| // Signed/Unsigned Saturating Shift Right Narrow (Immediate) |
| def SCALAR_SQSHRN_N: SInst<"vqshrn_n", "zsi", "SsSiSlSUsSUiSUl">; |
| // Signed/Unsigned Saturating Rounded Shift Right Narrow (Immediate) |
| def SCALAR_SQRSHRN_N: SInst<"vqrshrn_n", "zsi", "SsSiSlSUsSUiSUl">; |
| // Signed Saturating Shift Right Unsigned Narrow (Immediate) |
| def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "zsi", "SsSiSl">; |
| // Signed Saturating Rounded Shift Right Unsigned Narrow (Immediate) |
| def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "zsi", "SsSiSl">; |
| } |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed/Unsigned Fixed-point Convert To Floating-Point (Immediate) |
| def SCALAR_SCVTF_N_F32: SInst<"vcvt_n_f32", "ysi", "SiSUi">; |
| def SCALAR_SCVTF_N_F64: SInst<"vcvt_n_f64", "osi", "SlSUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Convert To Signed/Unsigned Fixed-point (Immediate) |
| def SCALAR_FCVTZS_N_S32 : SInst<"vcvt_n_s32", "xsi", "Sf">; |
| def SCALAR_FCVTZU_N_U32 : SInst<"vcvt_n_u32", "usi", "Sf">; |
| def SCALAR_FCVTZS_N_S64 : SInst<"vcvt_n_s64", "xsi", "Sd">; |
| def SCALAR_FCVTZU_N_U64 : SInst<"vcvt_n_u64", "usi", "Sd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Reduce Pairwise Addition (Scalar and Floating Point) |
| def SCALAR_ADDP : SInst<"vpadd", "sd", "SfSHlSHd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Reduce Floating Point Pairwise Max/Min |
| def SCALAR_FMAXP : SInst<"vpmax", "sd", "SfSQd">; |
| |
| def SCALAR_FMINP : SInst<"vpmin", "sd", "SfSQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Reduce Floating Point Pairwise maxNum/minNum |
| def SCALAR_FMAXNMP : SInst<"vpmaxnm", "sd", "SfSQd">; |
| def SCALAR_FMINNMP : SInst<"vpminnm", "sd", "SfSQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Integer Saturating Doubling Multiply Half High |
| def SCALAR_SQDMULH : SInst<"vqdmulh", "sss", "SsSi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Integer Saturating Rounding Doubling Multiply Half High |
| def SCALAR_SQRDMULH : SInst<"vqrdmulh", "sss", "SsSi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Multiply Extended |
| def SCALAR_FMULX : IInst<"vmulx", "sss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Reciprocal Step |
| def SCALAR_FRECPS : IInst<"vrecps", "sss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Reciprocal Square Root Step |
| def SCALAR_FRSQRTS : IInst<"vrsqrts", "sss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Integer Convert To Floating-point |
| def SCALAR_SCVTFS : SInst<"vcvt_f32", "ys", "Si">; |
| def SCALAR_SCVTFD : SInst<"vcvt_f64", "os", "Sl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Unsigned Integer Convert To Floating-point |
| def SCALAR_UCVTFS : SInst<"vcvt_f32", "ys", "SUi">; |
| def SCALAR_UCVTFD : SInst<"vcvt_f64", "os", "SUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Reciprocal Estimate |
| def SCALAR_FRECPE : IInst<"vrecpe", "ss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Reciprocal Exponent |
| def SCALAR_FRECPX : IInst<"vrecpx", "ss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Reciprocal Square Root Estimate |
| def SCALAR_FRSQRTE : IInst<"vrsqrte", "ss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Integer Comparison |
| def SCALAR_CMEQ : SInst<"vceq", "sss", "SlSUl">; |
| def SCALAR_CMEQZ : SInst<"vceqz", "ss", "SlSUl">; |
| def SCALAR_CMGE : SInst<"vcge", "sss", "Sl">; |
| def SCALAR_CMGEZ : SInst<"vcgez", "ss", "Sl">; |
| def SCALAR_CMHS : SInst<"vcge", "sss", "SUl">; |
| def SCALAR_CMLE : SInst<"vcle", "sss", "SlSUl">; |
| def SCALAR_CMLEZ : SInst<"vclez", "ss", "Sl">; |
| def SCALAR_CMLT : SInst<"vclt", "sss", "SlSUl">; |
| def SCALAR_CMLTZ : SInst<"vcltz", "ss", "Sl">; |
| def SCALAR_CMGT : SInst<"vcgt", "sss", "Sl">; |
| def SCALAR_CMGTZ : SInst<"vcgtz", "ss", "Sl">; |
| def SCALAR_CMHI : SInst<"vcgt", "sss", "SUl">; |
| def SCALAR_CMTST : SInst<"vtst", "sss", "SlSUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Comparison |
| def SCALAR_FCMEQ : IInst<"vceq", "bss", "SfSd">; |
| def SCALAR_FCMEQZ : IInst<"vceqz", "bs", "SfSd">; |
| def SCALAR_FCMGE : IInst<"vcge", "bss", "SfSd">; |
| def SCALAR_FCMGEZ : IInst<"vcgez", "bs", "SfSd">; |
| def SCALAR_FCMGT : IInst<"vcgt", "bss", "SfSd">; |
| def SCALAR_FCMGTZ : IInst<"vcgtz", "bs", "SfSd">; |
| def SCALAR_FCMLE : IInst<"vcle", "bss", "SfSd">; |
| def SCALAR_FCMLEZ : IInst<"vclez", "bs", "SfSd">; |
| def SCALAR_FCMLT : IInst<"vclt", "bss", "SfSd">; |
| def SCALAR_FCMLTZ : IInst<"vcltz", "bs", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Absolute Compare Mask Greater Than Or Equal |
| def SCALAR_FACGE : IInst<"vcage", "bss", "SfSd">; |
| def SCALAR_FACLE : IInst<"vcale", "bss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Floating-point Absolute Compare Mask Greater Than |
| def SCALAR_FACGT : IInst<"vcagt", "bss", "SfSd">; |
| def SCALAR_FACLT : IInst<"vcalt", "bss", "SfSd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Absolute Value |
| def SCALAR_ABS : SInst<"vabs", "ss", "Sl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Saturating Absolute Value |
| def SCALAR_SQABS : SInst<"vqabs", "ss", "ScSsSiSl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Negate |
| def SCALAR_NEG : SInst<"vneg", "ss", "Sl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Saturating Negate |
| def SCALAR_SQNEG : SInst<"vqneg", "ss", "ScSsSiSl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Saturating Accumulated of Unsigned Value |
| def SCALAR_SUQADD : SInst<"vuqadd", "sss", "ScSsSiSl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Unsigned Saturating Accumulated of Signed Value |
| def SCALAR_USQADD : SInst<"vsqadd", "sss", "SUcSUsSUiSUl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Signed Saturating Doubling Multiply-Add Long |
| def SCALAR_SQDMLAL : SInst<"vqdmlal", "rrss", "SsSi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Signed Saturating Doubling Multiply-Subtract Long |
| def SCALAR_SQDMLSL : SInst<"vqdmlsl", "rrss", "SsSi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Signed Saturating Doubling Multiply Long |
| def SCALAR_SQDMULL : SInst<"vqdmull", "rss", "SsSi">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Saturating Extract Unsigned Narrow |
| def SCALAR_SQXTUN : SInst<"vqmovun", "zs", "SsSiSl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Signed Saturating Extract Narrow |
| def SCALAR_SQXTN : SInst<"vqmovn", "zs", "SsSiSl">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Unsigned Saturating Extract Narrow |
| def SCALAR_UQXTN : SInst<"vqmovn", "zs", "SUsSUiSUl">; |
| } |