| //===--- 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_ADDW : Op; |
| def OP_SUB : Op; |
| def OP_SUBL : Op; |
| def OP_SUBW : Op; |
| def OP_MUL : Op; |
| def OP_MLA : Op; |
| def OP_MLAL : Op; |
| def OP_MLS : Op; |
| def OP_MLSL : 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_MULL_LN : Op; |
| def OP_MLA_LN: Op; |
| def OP_MLS_LN: Op; |
| def OP_MLAL_LN : Op; |
| def OP_MLSL_LN : Op; |
| def OP_QDMULL_LN : Op; |
| def OP_QDMLAL_LN : Op; |
| def OP_QDMLSL_LN : Op; |
| def OP_QDMULH_LN : Op; |
| def OP_QRDMULH_LN : 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_ABDL : Op; |
| def OP_ABA : Op; |
| def OP_ABAL : Op; |
| def OP_DIV : 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 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. |
| // w: double width elements, same num elts |
| // n: double width elements, half num elts |
| // h: half width elements, double num elts |
| // e: half width elements, double num elts, unsigned |
| // i: constant int |
| // l: constant uint64 |
| // s: scalar of element type |
| // a: scalar of element type (splat to vector type) |
| // 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: |
| // U: unsigned |
| // Q: 128b |
| // 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", "csiUcUsUiPcQcQsQiQUcQUsQUiQPc">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // 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 { |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // 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", "fQfQd">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // 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", "csiUcUsUiPcQcQsQiQlQUcQUsQUiQUlQPc">; |
| 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">; |
| |
| //////////////////////////////////////////////////////////////////////////////// |
| // Scalar Arithmetic |
| |
| // Scalar Addition |
| |
| def SCALAR_ADD : Inst<"vaddd", "ddd", "lUl", OP_ADD>; |
| |
| // Scalar Subtraction |
| def SCALAR_SUB : Inst<"vsubd", "ddd", "lUl", OP_SUB>; |
| |
| } |