PPCISelLowering.h 57.4 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
//===-- PPCISelLowering.h - PPC32 DAG Lowering Interface --------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that PPC uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_POWERPC_PPCISELLOWERING_H
#define LLVM_LIB_TARGET_POWERPC_PPCISELLOWERING_H

#include "PPCInstrInfo.h"
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/SelectionDAGNodes.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Type.h"
#include "llvm/Support/MachineValueType.h"
#include <utility>

namespace llvm {

  namespace PPCISD {

    // When adding a NEW PPCISD node please add it to the correct position in
    // the enum. The order of elements in this enum matters!
    // Values that are added after this entry:
    //     STBRX = ISD::FIRST_TARGET_MEMORY_OPCODE
    // are considered memory opcodes and are treated differently than entries
    // that come before it. For example, ADD or MUL should be placed before
    // the ISD::FIRST_TARGET_MEMORY_OPCODE while a LOAD or STORE should come
    // after it.
  enum NodeType : unsigned {
    // Start the numbering where the builtin ops and target ops leave off.
    FIRST_NUMBER = ISD::BUILTIN_OP_END,

    /// FSEL - Traditional three-operand fsel node.
    ///
    FSEL,

    /// XSMAXCDP, XSMINCDP - C-type min/max instructions.
    XSMAXCDP,
    XSMINCDP,

    /// FCFID - The FCFID instruction, taking an f64 operand and producing
    /// and f64 value containing the FP representation of the integer that
    /// was temporarily in the f64 operand.
    FCFID,

    /// Newer FCFID[US] integer-to-floating-point conversion instructions for
    /// unsigned integers and single-precision outputs.
    FCFIDU,
    FCFIDS,
    FCFIDUS,

    /// FCTI[D,W]Z - The FCTIDZ and FCTIWZ instructions, taking an f32 or f64
    /// operand, producing an f64 value containing the integer representation
    /// of that FP value.
    FCTIDZ,
    FCTIWZ,

    /// Newer FCTI[D,W]UZ floating-point-to-integer conversion instructions for
    /// unsigned integers with round toward zero.
    FCTIDUZ,
    FCTIWUZ,

    /// Floating-point-to-interger conversion instructions
    FP_TO_UINT_IN_VSR,
    FP_TO_SINT_IN_VSR,

    /// VEXTS, ByteWidth - takes an input in VSFRC and produces an output in
    /// VSFRC that is sign-extended from ByteWidth to a 64-byte integer.
    VEXTS,

    /// Reciprocal estimate instructions (unary FP ops).
    FRE,
    FRSQRTE,

    /// VPERM - The PPC VPERM Instruction.
    ///
    VPERM,

    /// XXSPLT - The PPC VSX splat instructions
    ///
    XXSPLT,

    /// XXSPLTI_SP_TO_DP - The PPC VSX splat instructions for immediates for
    /// converting immediate single precision numbers to double precision
    /// vector or scalar.
    XXSPLTI_SP_TO_DP,

    /// XXSPLTI32DX - The PPC XXSPLTI32DX instruction.
    ///
    XXSPLTI32DX,

    /// VECINSERT - The PPC vector insert instruction
    ///
    VECINSERT,

    /// VECSHL - The PPC vector shift left instruction
    ///
    VECSHL,

    /// XXPERMDI - The PPC XXPERMDI instruction
    ///
    XXPERMDI,

    /// The CMPB instruction (takes two operands of i32 or i64).
    CMPB,

    /// Hi/Lo - These represent the high and low 16-bit parts of a global
    /// address respectively.  These nodes have two operands, the first of
    /// which must be a TargetGlobalAddress, and the second of which must be a
    /// Constant.  Selected naively, these turn into 'lis G+C' and 'li G+C',
    /// though these are usually folded into other nodes.
    Hi,
    Lo,

    /// The following two target-specific nodes are used for calls through
    /// function pointers in the 64-bit SVR4 ABI.

    /// OPRC, CHAIN = DYNALLOC(CHAIN, NEGSIZE, FRAME_INDEX)
    /// This instruction is lowered in PPCRegisterInfo::eliminateFrameIndex to
    /// compute an allocation on the stack.
    DYNALLOC,

    /// This instruction is lowered in PPCRegisterInfo::eliminateFrameIndex to
    /// compute an offset from native SP to the address  of the most recent
    /// dynamic alloca.
    DYNAREAOFFSET,

    /// To avoid stack clash, allocation is performed by block and each block is
    /// probed.
    PROBED_ALLOCA,

    /// GlobalBaseReg - On Darwin, this node represents the result of the mflr
    /// at function entry, used for PIC code.
    GlobalBaseReg,

    /// These nodes represent PPC shifts.
    ///
    /// For scalar types, only the last `n + 1` bits of the shift amounts
    /// are used, where n is log2(sizeof(element) * 8). See sld/slw, etc.
    /// for exact behaviors.
    ///
    /// For vector types, only the last n bits are used. See vsld.
    SRL,
    SRA,
    SHL,

    /// FNMSUB - Negated multiply-subtract instruction.
    FNMSUB,

    /// EXTSWSLI = The PPC extswsli instruction, which does an extend-sign
    /// word and shift left immediate.
    EXTSWSLI,

    /// The combination of sra[wd]i and addze used to implemented signed
    /// integer division by a power of 2. The first operand is the dividend,
    /// and the second is the constant shift amount (representing the
    /// divisor).
    SRA_ADDZE,

    /// CALL - A direct function call.
    /// CALL_NOP is a call with the special NOP which follows 64-bit
    /// CALL_NOTOC the caller does not use the TOC.
    /// SVR4 calls and 32-bit/64-bit AIX calls.
    CALL,
    CALL_NOP,
    CALL_NOTOC,

    /// CHAIN,FLAG = MTCTR(VAL, CHAIN[, INFLAG]) - Directly corresponds to a
    /// MTCTR instruction.
    MTCTR,

    /// CHAIN,FLAG = BCTRL(CHAIN, INFLAG) - Directly corresponds to a
    /// BCTRL instruction.
    BCTRL,

    /// CHAIN,FLAG = BCTRL(CHAIN, ADDR, INFLAG) - The combination of a bctrl
    /// instruction and the TOC reload required on 64-bit ELF, 32-bit AIX
    /// and 64-bit AIX.
    BCTRL_LOAD_TOC,

    /// Return with a flag operand, matched by 'blr'
    RET_FLAG,

    /// R32 = MFOCRF(CRREG, INFLAG) - Represents the MFOCRF instruction.
    /// This copies the bits corresponding to the specified CRREG into the
    /// resultant GPR.  Bits corresponding to other CR regs are undefined.
    MFOCRF,

    /// Direct move from a VSX register to a GPR
    MFVSR,

    /// Direct move from a GPR to a VSX register (algebraic)
    MTVSRA,

    /// Direct move from a GPR to a VSX register (zero)
    MTVSRZ,

    /// Direct move of 2 consecutive GPR to a VSX register.
    BUILD_FP128,

    /// BUILD_SPE64 and EXTRACT_SPE are analogous to BUILD_PAIR and
    /// EXTRACT_ELEMENT but take f64 arguments instead of i64, as i64 is
    /// unsupported for this target.
    /// Merge 2 GPRs to a single SPE register.
    BUILD_SPE64,

    /// Extract SPE register component, second argument is high or low.
    EXTRACT_SPE,

    /// Extract a subvector from signed integer vector and convert to FP.
    /// It is primarily used to convert a (widened) illegal integer vector
    /// type to a legal floating point vector type.
    /// For example v2i32 -> widened to v4i32 -> v2f64
    SINT_VEC_TO_FP,

    /// Extract a subvector from unsigned integer vector and convert to FP.
    /// As with SINT_VEC_TO_FP, used for converting illegal types.
    UINT_VEC_TO_FP,

    /// PowerPC instructions that have SCALAR_TO_VECTOR semantics tend to
    /// place the value into the least significant element of the most
    /// significant doubleword in the vector. This is not element zero for
    /// anything smaller than a doubleword on either endianness. This node has
    /// the same semantics as SCALAR_TO_VECTOR except that the value remains in
    /// the aforementioned location in the vector register.
    SCALAR_TO_VECTOR_PERMUTED,

    // FIXME: Remove these once the ANDI glue bug is fixed:
    /// i1 = ANDI_rec_1_[EQ|GT]_BIT(i32 or i64 x) - Represents the result of the
    /// eq or gt bit of CR0 after executing andi. x, 1. This is used to
    /// implement truncation of i32 or i64 to i1.
    ANDI_rec_1_EQ_BIT,
    ANDI_rec_1_GT_BIT,

    // READ_TIME_BASE - A read of the 64-bit time-base register on a 32-bit
    // target (returns (Lo, Hi)). It takes a chain operand.
    READ_TIME_BASE,

    // EH_SJLJ_SETJMP - SjLj exception handling setjmp.
    EH_SJLJ_SETJMP,

    // EH_SJLJ_LONGJMP - SjLj exception handling longjmp.
    EH_SJLJ_LONGJMP,

    /// RESVEC = VCMP(LHS, RHS, OPC) - Represents one of the altivec VCMP*
    /// instructions.  For lack of better number, we use the opcode number
    /// encoding for the OPC field to identify the compare.  For example, 838
    /// is VCMPGTSH.
    VCMP,

    /// RESVEC, OUTFLAG = VCMPo(LHS, RHS, OPC) - Represents one of the
    /// altivec VCMP*o instructions.  For lack of better number, we use the
    /// opcode number encoding for the OPC field to identify the compare.  For
    /// example, 838 is VCMPGTSH.
    VCMPo,

    /// CHAIN = COND_BRANCH CHAIN, CRRC, OPC, DESTBB [, INFLAG] - This
    /// corresponds to the COND_BRANCH pseudo instruction.  CRRC is the
    /// condition register to branch on, OPC is the branch opcode to use (e.g.
    /// PPC::BLE), DESTBB is the destination block to branch to, and INFLAG is
    /// an optional input flag argument.
    COND_BRANCH,

    /// CHAIN = BDNZ CHAIN, DESTBB - These are used to create counter-based
    /// loops.
    BDNZ,
    BDZ,

    /// F8RC = FADDRTZ F8RC, F8RC - This is an FADD done with rounding
    /// towards zero.  Used only as part of the long double-to-int
    /// conversion sequence.
    FADDRTZ,

    /// F8RC = MFFS - This moves the FPSCR (not modeled) into the register.
    MFFS,

    /// TC_RETURN - A tail call return.
    ///   operand #0 chain
    ///   operand #1 callee (register or absolute)
    ///   operand #2 stack adjustment
    ///   operand #3 optional in flag
    TC_RETURN,

    /// ch, gl = CR6[UN]SET ch, inglue - Toggle CR bit 6 for SVR4 vararg calls
    CR6SET,
    CR6UNSET,

    /// GPRC = address of _GLOBAL_OFFSET_TABLE_. Used by initial-exec TLS
    /// for non-position independent code on PPC32.
    PPC32_GOT,

    /// GPRC = address of _GLOBAL_OFFSET_TABLE_. Used by general dynamic and
    /// local dynamic TLS and position indendepent code on PPC32.
    PPC32_PICGOT,

    /// G8RC = ADDIS_GOT_TPREL_HA %x2, Symbol - Used by the initial-exec
    /// TLS model, produces an ADDIS8 instruction that adds the GOT
    /// base to sym\@got\@tprel\@ha.
    ADDIS_GOT_TPREL_HA,

    /// G8RC = LD_GOT_TPREL_L Symbol, G8RReg - Used by the initial-exec
    /// TLS model, produces a LD instruction with base register G8RReg
    /// and offset sym\@got\@tprel\@l.  This completes the addition that
    /// finds the offset of "sym" relative to the thread pointer.
    LD_GOT_TPREL_L,

    /// G8RC = ADD_TLS G8RReg, Symbol - Used by the initial-exec TLS
    /// model, produces an ADD instruction that adds the contents of
    /// G8RReg to the thread pointer.  Symbol contains a relocation
    /// sym\@tls which is to be replaced by the thread pointer and
    /// identifies to the linker that the instruction is part of a
    /// TLS sequence.
    ADD_TLS,

    /// G8RC = ADDIS_TLSGD_HA %x2, Symbol - For the general-dynamic TLS
    /// model, produces an ADDIS8 instruction that adds the GOT base
    /// register to sym\@got\@tlsgd\@ha.
    ADDIS_TLSGD_HA,

    /// %x3 = ADDI_TLSGD_L G8RReg, Symbol - For the general-dynamic TLS
    /// model, produces an ADDI8 instruction that adds G8RReg to
    /// sym\@got\@tlsgd\@l and stores the result in X3.  Hidden by
    /// ADDIS_TLSGD_L_ADDR until after register assignment.
    ADDI_TLSGD_L,

    /// %x3 = GET_TLS_ADDR %x3, Symbol - For the general-dynamic TLS
    /// model, produces a call to __tls_get_addr(sym\@tlsgd).  Hidden by
    /// ADDIS_TLSGD_L_ADDR until after register assignment.
    GET_TLS_ADDR,

    /// G8RC = ADDI_TLSGD_L_ADDR G8RReg, Symbol, Symbol - Op that
    /// combines ADDI_TLSGD_L and GET_TLS_ADDR until expansion following
    /// register assignment.
    ADDI_TLSGD_L_ADDR,

    /// G8RC = ADDIS_TLSLD_HA %x2, Symbol - For the local-dynamic TLS
    /// model, produces an ADDIS8 instruction that adds the GOT base
    /// register to sym\@got\@tlsld\@ha.
    ADDIS_TLSLD_HA,

    /// %x3 = ADDI_TLSLD_L G8RReg, Symbol - For the local-dynamic TLS
    /// model, produces an ADDI8 instruction that adds G8RReg to
    /// sym\@got\@tlsld\@l and stores the result in X3.  Hidden by
    /// ADDIS_TLSLD_L_ADDR until after register assignment.
    ADDI_TLSLD_L,

    /// %x3 = GET_TLSLD_ADDR %x3, Symbol - For the local-dynamic TLS
    /// model, produces a call to __tls_get_addr(sym\@tlsld).  Hidden by
    /// ADDIS_TLSLD_L_ADDR until after register assignment.
    GET_TLSLD_ADDR,

    /// G8RC = ADDI_TLSLD_L_ADDR G8RReg, Symbol, Symbol - Op that
    /// combines ADDI_TLSLD_L and GET_TLSLD_ADDR until expansion
    /// following register assignment.
    ADDI_TLSLD_L_ADDR,

    /// G8RC = ADDIS_DTPREL_HA %x3, Symbol - For the local-dynamic TLS
    /// model, produces an ADDIS8 instruction that adds X3 to
    /// sym\@dtprel\@ha.
    ADDIS_DTPREL_HA,

    /// G8RC = ADDI_DTPREL_L G8RReg, Symbol - For the local-dynamic TLS
    /// model, produces an ADDI8 instruction that adds G8RReg to
    /// sym\@got\@dtprel\@l.
    ADDI_DTPREL_L,

    /// G8RC = PADDI_DTPREL %x3, Symbol - For the pc-rel based local-dynamic TLS
    /// model, produces a PADDI8 instruction that adds X3 to sym\@dtprel.
    PADDI_DTPREL,

    /// VRRC = VADD_SPLAT Elt, EltSize - Temporary node to be expanded
    /// during instruction selection to optimize a BUILD_VECTOR into
    /// operations on splats.  This is necessary to avoid losing these
    /// optimizations due to constant folding.
    VADD_SPLAT,

    /// CHAIN = SC CHAIN, Imm128 - System call.  The 7-bit unsigned
    /// operand identifies the operating system entry point.
    SC,

    /// CHAIN = CLRBHRB CHAIN - Clear branch history rolling buffer.
    CLRBHRB,

    /// GPRC, CHAIN = MFBHRBE CHAIN, Entry, Dummy - Move from branch
    /// history rolling buffer entry.
    MFBHRBE,

    /// CHAIN = RFEBB CHAIN, State - Return from event-based branch.
    RFEBB,

    /// VSRC, CHAIN = XXSWAPD CHAIN, VSRC - Occurs only for little
    /// endian.  Maps to an xxswapd instruction that corrects an lxvd2x
    /// or stxvd2x instruction.  The chain is necessary because the
    /// sequence replaces a load and needs to provide the same number
    /// of outputs.
    XXSWAPD,

    /// An SDNode for swaps that are not associated with any loads/stores
    /// and thereby have no chain.
    SWAP_NO_CHAIN,

    /// An SDNode for Power9 vector absolute value difference.
    /// operand #0 vector
    /// operand #1 vector
    /// operand #2 constant i32 0 or 1, to indicate whether needs to patch
    /// the most significant bit for signed i32
    ///
    /// Power9 VABSD* instructions are designed to support unsigned integer
    /// vectors (byte/halfword/word), if we want to make use of them for signed
    /// integer vectors, we have to flip their sign bits first. To flip sign bit
    /// for byte/halfword integer vector would become inefficient, but for word
    /// integer vector, we can leverage XVNEGSP to make it efficiently. eg:
    /// abs(sub(a,b)) => VABSDUW(a+0x80000000, b+0x80000000)
    ///               => VABSDUW((XVNEGSP a), (XVNEGSP b))
    VABSD,

    /// FP_EXTEND_HALF(VECTOR, IDX) - Custom extend upper (IDX=0) half or
    /// lower (IDX=1) half of v4f32 to v2f64.
    FP_EXTEND_HALF,

    /// MAT_PCREL_ADDR = Materialize a PC Relative address. This can be done
    /// either through an add like PADDI or through a PC Relative load like
    /// PLD.
    MAT_PCREL_ADDR,

    /// TLS_DYNAMIC_MAT_PCREL_ADDR = Materialize a PC Relative address for
    /// TLS global address when using dynamic access models. This can be done
    /// through an add like PADDI.
    TLS_DYNAMIC_MAT_PCREL_ADDR,

    /// TLS_LOCAL_EXEC_MAT_ADDR = Materialize an address for TLS global address
    /// when using local exec access models, and when prefixed instructions are
    /// available. This is used with ADD_TLS to produce an add like PADDI.
    TLS_LOCAL_EXEC_MAT_ADDR,

    /// ACC_BUILD = Build an accumulator register from 4 VSX registers.
    ACC_BUILD,

    /// PAIR_BUILD = Build a vector pair register from 2 VSX registers.
    PAIR_BUILD,

    /// EXTRACT_VSX_REG = Extract one of the underlying vsx registers of
    /// an accumulator or pair register. This node is needed because
    /// EXTRACT_SUBVECTOR expects the input and output vectors to have the same
    /// element type.
    EXTRACT_VSX_REG,

    /// XXMFACC = This corresponds to the xxmfacc instruction.
    XXMFACC,

    // Constrained conversion from floating point to int
    STRICT_FCTIDZ = ISD::FIRST_TARGET_STRICTFP_OPCODE,
    STRICT_FCTIWZ,
    STRICT_FCTIDUZ,
    STRICT_FCTIWUZ,

    /// Constrained integer-to-floating-point conversion instructions.
    STRICT_FCFID,
    STRICT_FCFIDU,
    STRICT_FCFIDS,
    STRICT_FCFIDUS,

    /// Constrained floating point add in round-to-zero mode.
    STRICT_FADDRTZ,

    /// CHAIN = STBRX CHAIN, GPRC, Ptr, Type - This is a
    /// byte-swapping store instruction.  It byte-swaps the low "Type" bits of
    /// the GPRC input, then stores it through Ptr.  Type can be either i16 or
    /// i32.
    STBRX = ISD::FIRST_TARGET_MEMORY_OPCODE,

    /// GPRC, CHAIN = LBRX CHAIN, Ptr, Type - This is a
    /// byte-swapping load instruction.  It loads "Type" bits, byte swaps it,
    /// then puts it in the bottom bits of the GPRC.  TYPE can be either i16
    /// or i32.
    LBRX,

    /// STFIWX - The STFIWX instruction.  The first operand is an input token
    /// chain, then an f64 value to store, then an address to store it to.
    STFIWX,

    /// GPRC, CHAIN = LFIWAX CHAIN, Ptr - This is a floating-point
    /// load which sign-extends from a 32-bit integer value into the
    /// destination 64-bit register.
    LFIWAX,

    /// GPRC, CHAIN = LFIWZX CHAIN, Ptr - This is a floating-point
    /// load which zero-extends from a 32-bit integer value into the
    /// destination 64-bit register.
    LFIWZX,

    /// GPRC, CHAIN = LXSIZX, CHAIN, Ptr, ByteWidth - This is a load of an
    /// integer smaller than 64 bits into a VSR. The integer is zero-extended.
    /// This can be used for converting loaded integers to floating point.
    LXSIZX,

    /// STXSIX - The STXSI[bh]X instruction. The first operand is an input
    /// chain, then an f64 value to store, then an address to store it to,
    /// followed by a byte-width for the store.
    STXSIX,

    /// VSRC, CHAIN = LXVD2X_LE CHAIN, Ptr - Occurs only for little endian.
    /// Maps directly to an lxvd2x instruction that will be followed by
    /// an xxswapd.
    LXVD2X,

    /// LXVRZX - Load VSX Vector Rightmost and Zero Extend
    /// This node represents v1i128 BUILD_VECTOR of a zero extending load
    /// instruction from <byte, halfword, word, or doubleword> to i128.
    /// Allows utilization of the Load VSX Vector Rightmost Instructions.
    LXVRZX,

    /// VSRC, CHAIN = LOAD_VEC_BE CHAIN, Ptr - Occurs only for little endian.
    /// Maps directly to one of lxvd2x/lxvw4x/lxvh8x/lxvb16x depending on
    /// the vector type to load vector in big-endian element order.
    LOAD_VEC_BE,

    /// VSRC, CHAIN = LD_VSX_LH CHAIN, Ptr - This is a floating-point load of a
    /// v2f32 value into the lower half of a VSR register.
    LD_VSX_LH,

    /// VSRC, CHAIN = LD_SPLAT, CHAIN, Ptr - a splatting load memory
    /// instructions such as LXVDSX, LXVWSX.
    LD_SPLAT,

    /// CHAIN = STXVD2X CHAIN, VSRC, Ptr - Occurs only for little endian.
    /// Maps directly to an stxvd2x instruction that will be preceded by
    /// an xxswapd.
    STXVD2X,

    /// CHAIN = STORE_VEC_BE CHAIN, VSRC, Ptr - Occurs only for little endian.
    /// Maps directly to one of stxvd2x/stxvw4x/stxvh8x/stxvb16x depending on
    /// the vector type to store vector in big-endian element order.
    STORE_VEC_BE,

    /// Store scalar integers from VSR.
    ST_VSR_SCAL_INT,

    /// ATOMIC_CMP_SWAP - the exact same as the target-independent nodes
    /// except they ensure that the compare input is zero-extended for
    /// sub-word versions because the atomic loads zero-extend.
    ATOMIC_CMP_SWAP_8,
    ATOMIC_CMP_SWAP_16,

    /// GPRC = TOC_ENTRY GA, TOC
    /// Loads the entry for GA from the TOC, where the TOC base is given by
    /// the last operand.
    TOC_ENTRY
  };

  } // end namespace PPCISD

  /// Define some predicates that are used for node matching.
  namespace PPC {

    /// isVPKUHUMShuffleMask - Return true if this is the shuffle mask for a
    /// VPKUHUM instruction.
    bool isVPKUHUMShuffleMask(ShuffleVectorSDNode *N, unsigned ShuffleKind,
                              SelectionDAG &DAG);

    /// isVPKUWUMShuffleMask - Return true if this is the shuffle mask for a
    /// VPKUWUM instruction.
    bool isVPKUWUMShuffleMask(ShuffleVectorSDNode *N, unsigned ShuffleKind,
                              SelectionDAG &DAG);

    /// isVPKUDUMShuffleMask - Return true if this is the shuffle mask for a
    /// VPKUDUM instruction.
    bool isVPKUDUMShuffleMask(ShuffleVectorSDNode *N, unsigned ShuffleKind,
                              SelectionDAG &DAG);

    /// isVMRGLShuffleMask - Return true if this is a shuffle mask suitable for
    /// a VRGL* instruction with the specified unit size (1,2 or 4 bytes).
    bool isVMRGLShuffleMask(ShuffleVectorSDNode *N, unsigned UnitSize,
                            unsigned ShuffleKind, SelectionDAG &DAG);

    /// isVMRGHShuffleMask - Return true if this is a shuffle mask suitable for
    /// a VRGH* instruction with the specified unit size (1,2 or 4 bytes).
    bool isVMRGHShuffleMask(ShuffleVectorSDNode *N, unsigned UnitSize,
                            unsigned ShuffleKind, SelectionDAG &DAG);

    /// isVMRGEOShuffleMask - Return true if this is a shuffle mask suitable for
    /// a VMRGEW or VMRGOW instruction
    bool isVMRGEOShuffleMask(ShuffleVectorSDNode *N, bool CheckEven,
                             unsigned ShuffleKind, SelectionDAG &DAG);
    /// isXXSLDWIShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXSLDWI instruction.
    bool isXXSLDWIShuffleMask(ShuffleVectorSDNode *N, unsigned &ShiftElts,
                              bool &Swap, bool IsLE);

    /// isXXBRHShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXBRH instruction.
    bool isXXBRHShuffleMask(ShuffleVectorSDNode *N);

    /// isXXBRWShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXBRW instruction.
    bool isXXBRWShuffleMask(ShuffleVectorSDNode *N);

    /// isXXBRDShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXBRD instruction.
    bool isXXBRDShuffleMask(ShuffleVectorSDNode *N);

    /// isXXBRQShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXBRQ instruction.
    bool isXXBRQShuffleMask(ShuffleVectorSDNode *N);

    /// isXXPERMDIShuffleMask - Return true if this is a shuffle mask suitable
    /// for a XXPERMDI instruction.
    bool isXXPERMDIShuffleMask(ShuffleVectorSDNode *N, unsigned &ShiftElts,
                              bool &Swap, bool IsLE);

    /// isVSLDOIShuffleMask - If this is a vsldoi shuffle mask, return the
    /// shift amount, otherwise return -1.
    int isVSLDOIShuffleMask(SDNode *N, unsigned ShuffleKind,
                            SelectionDAG &DAG);

    /// isSplatShuffleMask - Return true if the specified VECTOR_SHUFFLE operand
    /// specifies a splat of a single element that is suitable for input to
    /// VSPLTB/VSPLTH/VSPLTW.
    bool isSplatShuffleMask(ShuffleVectorSDNode *N, unsigned EltSize);

    /// isXXINSERTWMask - Return true if this VECTOR_SHUFFLE can be handled by
    /// the XXINSERTW instruction introduced in ISA 3.0. This is essentially any
    /// shuffle of v4f32/v4i32 vectors that just inserts one element from one
    /// vector into the other. This function will also set a couple of
    /// output parameters for how much the source vector needs to be shifted and
    /// what byte number needs to be specified for the instruction to put the
    /// element in the desired location of the target vector.
    bool isXXINSERTWMask(ShuffleVectorSDNode *N, unsigned &ShiftElts,
                         unsigned &InsertAtByte, bool &Swap, bool IsLE);

    /// getSplatIdxForPPCMnemonics - Return the splat index as a value that is
    /// appropriate for PPC mnemonics (which have a big endian bias - namely
    /// elements are counted from the left of the vector register).
    unsigned getSplatIdxForPPCMnemonics(SDNode *N, unsigned EltSize,
                                        SelectionDAG &DAG);

    /// get_VSPLTI_elt - If this is a build_vector of constants which can be
    /// formed by using a vspltis[bhw] instruction of the specified element
    /// size, return the constant being splatted.  The ByteSize field indicates
    /// the number of bytes of each element [124] -> [bhw].
    SDValue get_VSPLTI_elt(SDNode *N, unsigned ByteSize, SelectionDAG &DAG);

    /// If this is a qvaligni shuffle mask, return the shift
    /// amount, otherwise return -1.
    int isQVALIGNIShuffleMask(SDNode *N);

  } // end namespace PPC

  class PPCTargetLowering : public TargetLowering {
    const PPCSubtarget &Subtarget;

  public:
    explicit PPCTargetLowering(const PPCTargetMachine &TM,
                               const PPCSubtarget &STI);

    /// getTargetNodeName() - This method returns the name of a target specific
    /// DAG node.
    const char *getTargetNodeName(unsigned Opcode) const override;

    bool isSelectSupported(SelectSupportKind Kind) const override {
      // PowerPC does not support scalar condition selects on vectors.
      return (Kind != SelectSupportKind::ScalarCondVectorVal);
    }

    /// getPreferredVectorAction - The code we generate when vector types are
    /// legalized by promoting the integer element type is often much worse
    /// than code we generate if we widen the type for applicable vector types.
    /// The issue with promoting is that the vector is scalaraized, individual
    /// elements promoted and then the vector is rebuilt. So say we load a pair
    /// of v4i8's and shuffle them. This will turn into a mess of 8 extending
    /// loads, moves back into VSR's (or memory ops if we don't have moves) and
    /// then the VPERM for the shuffle. All in all a very slow sequence.
    TargetLoweringBase::LegalizeTypeAction getPreferredVectorAction(MVT VT)
      const override {
      if (VT.getVectorNumElements() != 1 && VT.getScalarSizeInBits() % 8 == 0)
        return TypeWidenVector;
      return TargetLoweringBase::getPreferredVectorAction(VT);
    }

    bool useSoftFloat() const override;

    bool hasSPE() const;

    MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override {
      return MVT::i32;
    }

    bool isCheapToSpeculateCttz() const override {
      return true;
    }

    bool isCheapToSpeculateCtlz() const override {
      return true;
    }

    bool isCtlzFast() const override {
      return true;
    }

    bool isEqualityCmpFoldedWithSignedCmp() const override {
      return false;
    }

    bool hasAndNotCompare(SDValue) const override {
      return true;
    }

    bool preferIncOfAddToSubOfNot(EVT VT) const override;

    bool convertSetCCLogicToBitwiseLogic(EVT VT) const override {
      return VT.isScalarInteger();
    }

    SDValue getNegatedExpression(SDValue Op, SelectionDAG &DAG, bool LegalOps,
                                 bool OptForSize, NegatibleCost &Cost,
                                 unsigned Depth = 0) const override;

    /// getSetCCResultType - Return the ISD::SETCC ValueType
    EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
                           EVT VT) const override;

    /// Return true if target always beneficiates from combining into FMA for a
    /// given value type. This must typically return false on targets where FMA
    /// takes more cycles to execute than FADD.
    bool enableAggressiveFMAFusion(EVT VT) const override;

    /// getPreIndexedAddressParts - returns true by value, base pointer and
    /// offset pointer and addressing mode by reference if the node's address
    /// can be legally represented as pre-indexed load / store address.
    bool getPreIndexedAddressParts(SDNode *N, SDValue &Base,
                                   SDValue &Offset,
                                   ISD::MemIndexedMode &AM,
                                   SelectionDAG &DAG) const override;

    /// SelectAddressEVXRegReg - Given the specified addressed, check to see if
    /// it can be more efficiently represented as [r+imm].
    bool SelectAddressEVXRegReg(SDValue N, SDValue &Base, SDValue &Index,
                                SelectionDAG &DAG) const;

    /// SelectAddressRegReg - Given the specified addressed, check to see if it
    /// can be more efficiently represented as [r+imm]. If \p EncodingAlignment
    /// is non-zero, only accept displacement which is not suitable for [r+imm].
    /// Returns false if it can be represented by [r+imm], which are preferred.
    bool SelectAddressRegReg(SDValue N, SDValue &Base, SDValue &Index,
                             SelectionDAG &DAG,
                             MaybeAlign EncodingAlignment = None) const;

    /// SelectAddressRegImm - Returns true if the address N can be represented
    /// by a base register plus a signed 16-bit displacement [r+imm], and if it
    /// is not better represented as reg+reg. If \p EncodingAlignment is
    /// non-zero, only accept displacements suitable for instruction encoding
    /// requirement, i.e. multiples of 4 for DS form.
    bool SelectAddressRegImm(SDValue N, SDValue &Disp, SDValue &Base,
                             SelectionDAG &DAG,
                             MaybeAlign EncodingAlignment) const;

    /// SelectAddressRegRegOnly - Given the specified addressed, force it to be
    /// represented as an indexed [r+r] operation.
    bool SelectAddressRegRegOnly(SDValue N, SDValue &Base, SDValue &Index,
                                 SelectionDAG &DAG) const;

    /// SelectAddressPCRel - Represent the specified address as pc relative to
    /// be represented as [pc+imm]
    bool SelectAddressPCRel(SDValue N, SDValue &Base) const;

    Sched::Preference getSchedulingPreference(SDNode *N) const override;

    /// LowerOperation - Provide custom lowering hooks for some operations.
    ///
    SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;

    /// LowerOperationWrapper - Place custom new result values for node in
    /// Results.
    void LowerOperationWrapper(SDNode *N,
                               SmallVectorImpl<SDValue> &Results,
                               SelectionDAG &DAG) const override;

    /// ReplaceNodeResults - Replace the results of node with an illegal result
    /// type with new values built out of custom code.
    ///
    void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue>&Results,
                            SelectionDAG &DAG) const override;

    SDValue expandVSXLoadForLE(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue expandVSXStoreForLE(SDNode *N, DAGCombinerInfo &DCI) const;

    SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;

    SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
                          SmallVectorImpl<SDNode *> &Created) const override;

    Register getRegisterByName(const char* RegName, LLT VT,
                               const MachineFunction &MF) const override;

    void computeKnownBitsForTargetNode(const SDValue Op,
                                       KnownBits &Known,
                                       const APInt &DemandedElts,
                                       const SelectionDAG &DAG,
                                       unsigned Depth = 0) const override;

    Align getPrefLoopAlignment(MachineLoop *ML) const override;

    bool shouldInsertFencesForAtomic(const Instruction *I) const override {
      return true;
    }

    Instruction *emitLeadingFence(IRBuilder<> &Builder, Instruction *Inst,
                                  AtomicOrdering Ord) const override;
    Instruction *emitTrailingFence(IRBuilder<> &Builder, Instruction *Inst,
                                   AtomicOrdering Ord) const override;

    MachineBasicBlock *
    EmitInstrWithCustomInserter(MachineInstr &MI,
                                MachineBasicBlock *MBB) const override;
    MachineBasicBlock *EmitAtomicBinary(MachineInstr &MI,
                                        MachineBasicBlock *MBB,
                                        unsigned AtomicSize,
                                        unsigned BinOpcode,
                                        unsigned CmpOpcode = 0,
                                        unsigned CmpPred = 0) const;
    MachineBasicBlock *EmitPartwordAtomicBinary(MachineInstr &MI,
                                                MachineBasicBlock *MBB,
                                                bool is8bit,
                                                unsigned Opcode,
                                                unsigned CmpOpcode = 0,
                                                unsigned CmpPred = 0) const;

    MachineBasicBlock *emitEHSjLjSetJmp(MachineInstr &MI,
                                        MachineBasicBlock *MBB) const;

    MachineBasicBlock *emitEHSjLjLongJmp(MachineInstr &MI,
                                         MachineBasicBlock *MBB) const;

    MachineBasicBlock *emitProbedAlloca(MachineInstr &MI,
                                        MachineBasicBlock *MBB) const;

    bool hasInlineStackProbe(MachineFunction &MF) const override;

    unsigned getStackProbeSize(MachineFunction &MF) const;

    ConstraintType getConstraintType(StringRef Constraint) const override;

    /// Examine constraint string and operand type and determine a weight value.
    /// The operand object must already have been set up with the operand type.
    ConstraintWeight getSingleConstraintMatchWeight(
      AsmOperandInfo &info, const char *constraint) const override;

    std::pair<unsigned, const TargetRegisterClass *>
    getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
                                 StringRef Constraint, MVT VT) const override;

    /// getByValTypeAlignment - Return the desired alignment for ByVal aggregate
    /// function arguments in the caller parameter area.  This is the actual
    /// alignment, not its logarithm.
    unsigned getByValTypeAlignment(Type *Ty,
                                   const DataLayout &DL) const override;

    /// LowerAsmOperandForConstraint - Lower the specified operand into the Ops
    /// vector.  If it is invalid, don't add anything to Ops.
    void LowerAsmOperandForConstraint(SDValue Op,
                                      std::string &Constraint,
                                      std::vector<SDValue> &Ops,
                                      SelectionDAG &DAG) const override;

    unsigned
    getInlineAsmMemConstraint(StringRef ConstraintCode) const override {
      if (ConstraintCode == "es")
        return InlineAsm::Constraint_es;
      else if (ConstraintCode == "o")
        return InlineAsm::Constraint_o;
      else if (ConstraintCode == "Q")
        return InlineAsm::Constraint_Q;
      else if (ConstraintCode == "Z")
        return InlineAsm::Constraint_Z;
      else if (ConstraintCode == "Zy")
        return InlineAsm::Constraint_Zy;
      return TargetLowering::getInlineAsmMemConstraint(ConstraintCode);
    }

    /// isLegalAddressingMode - Return true if the addressing mode represented
    /// by AM is legal for this target, for a load/store of the specified type.
    bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM,
                               Type *Ty, unsigned AS,
                               Instruction *I = nullptr) const override;

    /// isLegalICmpImmediate - Return true if the specified immediate is legal
    /// icmp immediate, that is the target has icmp instructions which can
    /// compare a register against the immediate without having to materialize
    /// the immediate into a register.
    bool isLegalICmpImmediate(int64_t Imm) const override;

    /// isLegalAddImmediate - Return true if the specified immediate is legal
    /// add immediate, that is the target has add instructions which can
    /// add a register and the immediate without having to materialize
    /// the immediate into a register.
    bool isLegalAddImmediate(int64_t Imm) const override;

    /// isTruncateFree - Return true if it's free to truncate a value of
    /// type Ty1 to type Ty2. e.g. On PPC it's free to truncate a i64 value in
    /// register X1 to i32 by referencing its sub-register R1.
    bool isTruncateFree(Type *Ty1, Type *Ty2) const override;
    bool isTruncateFree(EVT VT1, EVT VT2) const override;

    bool isZExtFree(SDValue Val, EVT VT2) const override;

    bool isFPExtFree(EVT DestVT, EVT SrcVT) const override;

    /// Returns true if it is beneficial to convert a load of a constant
    /// to just the constant itself.
    bool shouldConvertConstantLoadToIntImm(const APInt &Imm,
                                           Type *Ty) const override;

    bool convertSelectOfConstantsToMath(EVT VT) const override {
      return true;
    }

    bool isDesirableToTransformToIntegerOp(unsigned Opc,
                                           EVT VT) const override {
      // Only handle float load/store pair because float(fpr) load/store
      // instruction has more cycles than integer(gpr) load/store in PPC.
      if (Opc != ISD::LOAD && Opc != ISD::STORE)
        return false;
      if (VT != MVT::f32 && VT != MVT::f64)
        return false;

      return true;
    }

    // Returns true if the address of the global is stored in TOC entry.
    bool isAccessedAsGotIndirect(SDValue N) const;

    bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const override;

    bool getTgtMemIntrinsic(IntrinsicInfo &Info,
                            const CallInst &I,
                            MachineFunction &MF,
                            unsigned Intrinsic) const override;

    /// It returns EVT::Other if the type should be determined using generic
    /// target-independent logic.
    EVT getOptimalMemOpType(const MemOp &Op,
                            const AttributeList &FuncAttributes) const override;

    /// Is unaligned memory access allowed for the given type, and is it fast
    /// relative to software emulation.
    bool allowsMisalignedMemoryAccesses(
        EVT VT, unsigned AddrSpace, unsigned Align = 1,
        MachineMemOperand::Flags Flags = MachineMemOperand::MONone,
        bool *Fast = nullptr) const override;

    /// isFMAFasterThanFMulAndFAdd - Return true if an FMA operation is faster
    /// than a pair of fmul and fadd instructions. fmuladd intrinsics will be
    /// expanded to FMAs when this method returns true, otherwise fmuladd is
    /// expanded to fmul + fadd.
    bool isFMAFasterThanFMulAndFAdd(const MachineFunction &MF,
                                    EVT VT) const override;

    bool isFMAFasterThanFMulAndFAdd(const Function &F, Type *Ty) const override;

    /// isProfitableToHoist - Check if it is profitable to hoist instruction
    /// \p I to its dominator block.
    /// For example, it is not profitable if \p I and it's only user can form a
    /// FMA instruction, because Powerpc prefers FMADD.
    bool isProfitableToHoist(Instruction *I) const override;

    const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const override;

    // Should we expand the build vector with shuffles?
    bool
    shouldExpandBuildVectorWithShuffles(EVT VT,
                                        unsigned DefinedValues) const override;

    /// createFastISel - This method returns a target-specific FastISel object,
    /// or null if the target does not support "fast" instruction selection.
    FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,
                             const TargetLibraryInfo *LibInfo) const override;

    /// Returns true if an argument of type Ty needs to be passed in a
    /// contiguous block of registers in calling convention CallConv.
    bool functionArgumentNeedsConsecutiveRegisters(
      Type *Ty, CallingConv::ID CallConv, bool isVarArg) const override {
      // We support any array type as "consecutive" block in the parameter
      // save area.  The element type defines the alignment requirement and
      // whether the argument should go in GPRs, FPRs, or VRs if available.
      //
      // Note that clang uses this capability both to implement the ELFv2
      // homogeneous float/vector aggregate ABI, and to avoid having to use
      // "byval" when passing aggregates that might fully fit in registers.
      return Ty->isArrayTy();
    }

    /// If a physical register, this returns the register that receives the
    /// exception address on entry to an EH pad.
    Register
    getExceptionPointerRegister(const Constant *PersonalityFn) const override;

    /// If a physical register, this returns the register that receives the
    /// exception typeid on entry to a landing pad.
    Register
    getExceptionSelectorRegister(const Constant *PersonalityFn) const override;

    /// isMulhCheaperThanMulShift - Return true if a mulh[s|u] node for a
    /// specific type is cheaper than a multiply followed by a shift.
    /// This is true for words and doublewords on 64-bit PowerPC.
    bool isMulhCheaperThanMulShift(EVT Type) const override;

    /// Override to support customized stack guard loading.
    bool useLoadStackGuardNode() const override;
    void insertSSPDeclarations(Module &M) const override;

    bool isFPImmLegal(const APFloat &Imm, EVT VT,
                      bool ForCodeSize) const override;

    unsigned getJumpTableEncoding() const override;
    bool isJumpTableRelative() const override;
    SDValue getPICJumpTableRelocBase(SDValue Table,
                                     SelectionDAG &DAG) const override;
    const MCExpr *getPICJumpTableRelocBaseExpr(const MachineFunction *MF,
                                               unsigned JTI,
                                               MCContext &Ctx) const override;

    /// Structure that collects some common arguments that get passed around
    /// between the functions for call lowering.
    struct CallFlags {
      const CallingConv::ID CallConv;
      const bool IsTailCall : 1;
      const bool IsVarArg : 1;
      const bool IsPatchPoint : 1;
      const bool IsIndirect : 1;
      const bool HasNest : 1;
      const bool NoMerge : 1;

      CallFlags(CallingConv::ID CC, bool IsTailCall, bool IsVarArg,
                bool IsPatchPoint, bool IsIndirect, bool HasNest, bool NoMerge)
          : CallConv(CC), IsTailCall(IsTailCall), IsVarArg(IsVarArg),
            IsPatchPoint(IsPatchPoint), IsIndirect(IsIndirect),
            HasNest(HasNest), NoMerge(NoMerge) {}
    };

  private:
    struct ReuseLoadInfo {
      SDValue Ptr;
      SDValue Chain;
      SDValue ResChain;
      MachinePointerInfo MPI;
      bool IsDereferenceable = false;
      bool IsInvariant = false;
      Align Alignment;
      AAMDNodes AAInfo;
      const MDNode *Ranges = nullptr;

      ReuseLoadInfo() = default;

      MachineMemOperand::Flags MMOFlags() const {
        MachineMemOperand::Flags F = MachineMemOperand::MONone;
        if (IsDereferenceable)
          F |= MachineMemOperand::MODereferenceable;
        if (IsInvariant)
          F |= MachineMemOperand::MOInvariant;
        return F;
      }
    };

    bool canReuseLoadAddress(SDValue Op, EVT MemVT, ReuseLoadInfo &RLI,
                             SelectionDAG &DAG,
                             ISD::LoadExtType ET = ISD::NON_EXTLOAD) const;
    void spliceIntoChain(SDValue ResChain, SDValue NewResChain,
                         SelectionDAG &DAG) const;

    void LowerFP_TO_INTForReuse(SDValue Op, ReuseLoadInfo &RLI,
                                SelectionDAG &DAG, const SDLoc &dl) const;
    SDValue LowerFP_TO_INTDirectMove(SDValue Op, SelectionDAG &DAG,
                                     const SDLoc &dl) const;

    bool directMoveIsProfitable(const SDValue &Op) const;
    SDValue LowerINT_TO_FPDirectMove(SDValue Op, SelectionDAG &DAG,
                                     const SDLoc &dl) const;

    SDValue LowerINT_TO_FPVector(SDValue Op, SelectionDAG &DAG,
                                 const SDLoc &dl) const;

    SDValue LowerTRUNCATEVector(SDValue Op, SelectionDAG &DAG) const;

    SDValue getFramePointerFrameIndex(SelectionDAG & DAG) const;
    SDValue getReturnAddrFrameIndex(SelectionDAG & DAG) const;

    bool
    IsEligibleForTailCallOptimization(SDValue Callee,
                                      CallingConv::ID CalleeCC,
                                      bool isVarArg,
                                      const SmallVectorImpl<ISD::InputArg> &Ins,
                                      SelectionDAG& DAG) const;

    bool IsEligibleForTailCallOptimization_64SVR4(
        SDValue Callee, CallingConv::ID CalleeCC, const CallBase *CB,
        bool isVarArg, const SmallVectorImpl<ISD::OutputArg> &Outs,
        const SmallVectorImpl<ISD::InputArg> &Ins, SelectionDAG &DAG) const;

    SDValue EmitTailCallLoadFPAndRetAddr(SelectionDAG &DAG, int SPDiff,
                                         SDValue Chain, SDValue &LROpOut,
                                         SDValue &FPOpOut,
                                         const SDLoc &dl) const;

    SDValue getTOCEntry(SelectionDAG &DAG, const SDLoc &dl, SDValue GA) const;

    SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerVASTART(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerVAARG(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerVACOPY(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSTACKRESTORE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerGET_DYNAMIC_AREA_OFFSET(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerEH_DWARF_CFA(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG,
                           const SDLoc &dl) const;
    SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSHL_PARTS(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSRL_PARTS(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSRA_PARTS(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerFunnelShift(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerINSERT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerINTRINSIC_VOID(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerBSWAP(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSCALAR_TO_VECTOR(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerMUL(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerABS(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerROTL(SDValue Op, SelectionDAG &DAG) const;

    SDValue LowerVectorLoad(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerVectorStore(SDValue Op, SelectionDAG &DAG) const;

    SDValue LowerCallResult(SDValue Chain, SDValue InFlag,
                            CallingConv::ID CallConv, bool isVarArg,
                            const SmallVectorImpl<ISD::InputArg> &Ins,
                            const SDLoc &dl, SelectionDAG &DAG,
                            SmallVectorImpl<SDValue> &InVals) const;

    SDValue FinishCall(CallFlags CFlags, const SDLoc &dl, SelectionDAG &DAG,
                       SmallVector<std::pair<unsigned, SDValue>, 8> &RegsToPass,
                       SDValue InFlag, SDValue Chain, SDValue CallSeqStart,
                       SDValue &Callee, int SPDiff, unsigned NumBytes,
                       const SmallVectorImpl<ISD::InputArg> &Ins,
                       SmallVectorImpl<SDValue> &InVals,
                       const CallBase *CB) const;

    SDValue
    LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
                         const SmallVectorImpl<ISD::InputArg> &Ins,
                         const SDLoc &dl, SelectionDAG &DAG,
                         SmallVectorImpl<SDValue> &InVals) const override;

    SDValue LowerCall(TargetLowering::CallLoweringInfo &CLI,
                      SmallVectorImpl<SDValue> &InVals) const override;

    bool CanLowerReturn(CallingConv::ID CallConv, MachineFunction &MF,
                        bool isVarArg,
                        const SmallVectorImpl<ISD::OutputArg> &Outs,
                        LLVMContext &Context) const override;

    SDValue LowerReturn(SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
                        const SmallVectorImpl<ISD::OutputArg> &Outs,
                        const SmallVectorImpl<SDValue> &OutVals,
                        const SDLoc &dl, SelectionDAG &DAG) const override;

    SDValue extendArgForPPC64(ISD::ArgFlagsTy Flags, EVT ObjectVT,
                              SelectionDAG &DAG, SDValue ArgVal,
                              const SDLoc &dl) const;

    SDValue LowerFormalArguments_AIX(
        SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
        const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
        SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const;
    SDValue LowerFormalArguments_Darwin(
        SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
        const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
        SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const;
    SDValue LowerFormalArguments_64SVR4(
        SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
        const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
        SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const;
    SDValue LowerFormalArguments_32SVR4(
        SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
        const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
        SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const;

    SDValue createMemcpyOutsideCallSeq(SDValue Arg, SDValue PtrOff,
                                       SDValue CallSeqStart,
                                       ISD::ArgFlagsTy Flags, SelectionDAG &DAG,
                                       const SDLoc &dl) const;

    SDValue LowerCall_Darwin(SDValue Chain, SDValue Callee, CallFlags CFlags,
                             const SmallVectorImpl<ISD::OutputArg> &Outs,
                             const SmallVectorImpl<SDValue> &OutVals,
                             const SmallVectorImpl<ISD::InputArg> &Ins,
                             const SDLoc &dl, SelectionDAG &DAG,
                             SmallVectorImpl<SDValue> &InVals,
                             const CallBase *CB) const;
    SDValue LowerCall_64SVR4(SDValue Chain, SDValue Callee, CallFlags CFlags,
                             const SmallVectorImpl<ISD::OutputArg> &Outs,
                             const SmallVectorImpl<SDValue> &OutVals,
                             const SmallVectorImpl<ISD::InputArg> &Ins,
                             const SDLoc &dl, SelectionDAG &DAG,
                             SmallVectorImpl<SDValue> &InVals,
                             const CallBase *CB) const;
    SDValue LowerCall_32SVR4(SDValue Chain, SDValue Callee, CallFlags CFlags,
                             const SmallVectorImpl<ISD::OutputArg> &Outs,
                             const SmallVectorImpl<SDValue> &OutVals,
                             const SmallVectorImpl<ISD::InputArg> &Ins,
                             const SDLoc &dl, SelectionDAG &DAG,
                             SmallVectorImpl<SDValue> &InVals,
                             const CallBase *CB) const;
    SDValue LowerCall_AIX(SDValue Chain, SDValue Callee, CallFlags CFlags,
                          const SmallVectorImpl<ISD::OutputArg> &Outs,
                          const SmallVectorImpl<SDValue> &OutVals,
                          const SmallVectorImpl<ISD::InputArg> &Ins,
                          const SDLoc &dl, SelectionDAG &DAG,
                          SmallVectorImpl<SDValue> &InVals,
                          const CallBase *CB) const;

    SDValue lowerEH_SJLJ_SETJMP(SDValue Op, SelectionDAG &DAG) const;
    SDValue lowerEH_SJLJ_LONGJMP(SDValue Op, SelectionDAG &DAG) const;
    SDValue LowerBITCAST(SDValue Op, SelectionDAG &DAG) const;

    SDValue DAGCombineExtBoolTrunc(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue DAGCombineBuildVector(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue DAGCombineTruncBoolExt(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineStoreFPToInt(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineFPToIntToFP(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineSHL(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineSRA(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineSRL(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineMUL(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineADD(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineFMALike(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineTRUNCATE(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineSetCC(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineABS(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineVSelect(SDNode *N, DAGCombinerInfo &DCI) const;
    SDValue combineVectorShuffle(ShuffleVectorSDNode *SVN,
                                 SelectionDAG &DAG) const;
    SDValue combineVReverseMemOP(ShuffleVectorSDNode *SVN, LSBaseSDNode *LSBase,
                                 DAGCombinerInfo &DCI) const;

    /// ConvertSETCCToSubtract - looks at SETCC that compares ints. It replaces
    /// SETCC with integer subtraction when (1) there is a legal way of doing it
    /// (2) keeping the result of comparison in GPR has performance benefit.
    SDValue ConvertSETCCToSubtract(SDNode *N, DAGCombinerInfo &DCI) const;

    SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled,
                            int &RefinementSteps, bool &UseOneConstNR,
                            bool Reciprocal) const override;
    SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled,
                             int &RefinementSteps) const override;
    unsigned combineRepeatedFPDivisors() const override;

    SDValue
    combineElementTruncationToVectorTruncation(SDNode *N,
                                               DAGCombinerInfo &DCI) const;

    /// lowerToVINSERTH - Return the SDValue if this VECTOR_SHUFFLE can be
    /// handled by the VINSERTH instruction introduced in ISA 3.0. This is
    /// essentially any shuffle of v8i16 vectors that just inserts one element
    /// from one vector into the other.
    SDValue lowerToVINSERTH(ShuffleVectorSDNode *N, SelectionDAG &DAG) const;

    /// lowerToVINSERTB - Return the SDValue if this VECTOR_SHUFFLE can be
    /// handled by the VINSERTB instruction introduced in ISA 3.0. This is
    /// essentially v16i8 vector version of VINSERTH.
    SDValue lowerToVINSERTB(ShuffleVectorSDNode *N, SelectionDAG &DAG) const;

    /// lowerToXXSPLTI32DX - Return the SDValue if this VECTOR_SHUFFLE can be
    /// handled by the XXSPLTI32DX instruction introduced in ISA 3.1.
    SDValue lowerToXXSPLTI32DX(ShuffleVectorSDNode *N, SelectionDAG &DAG) const;

    // Return whether the call instruction can potentially be optimized to a
    // tail call. This will cause the optimizers to attempt to move, or
    // duplicate return instructions to help enable tail call optimizations.
    bool mayBeEmittedAsTailCall(const CallInst *CI) const override;
    bool hasBitPreservingFPLogic(EVT VT) const override;
    bool isMaskAndCmp0FoldingBeneficial(const Instruction &AndI) const override;
  }; // end class PPCTargetLowering

  namespace PPC {

    FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,
                             const TargetLibraryInfo *LibInfo);

  } // end namespace PPC

  bool isIntS16Immediate(SDNode *N, int16_t &Imm);
  bool isIntS16Immediate(SDValue Op, int16_t &Imm);

  bool convertToNonDenormSingle(APInt &ArgAPInt);
  bool convertToNonDenormSingle(APFloat &ArgAPFloat);

} // end namespace llvm

#endif // LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H