X86InstrXOP.td 23.9 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
//===-- X86InstrXOP.td - XOP Instruction Set ---------------*- tablegen -*-===//
//
// 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 describes XOP (eXtended OPerations)
//
//===----------------------------------------------------------------------===//

multiclass xop2op<bits<8> opc, string OpcodeStr, Intrinsic Int> {
  def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[SchedWritePHAdd.XMM]>;
  def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins i128mem:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int (load addr:$src)))]>, XOP,
           Sched<[SchedWritePHAdd.XMM.Folded, SchedWritePHAdd.XMM.ReadAfterFold]>;
}

let ExeDomain = SSEPackedInt in {
  defm VPHSUBWD  : xop2op<0xE2, "vphsubwd", int_x86_xop_vphsubwd>;
  defm VPHSUBDQ  : xop2op<0xE3, "vphsubdq", int_x86_xop_vphsubdq>;
  defm VPHSUBBW  : xop2op<0xE1, "vphsubbw", int_x86_xop_vphsubbw>;
  defm VPHADDWQ  : xop2op<0xC7, "vphaddwq", int_x86_xop_vphaddwq>;
  defm VPHADDWD  : xop2op<0xC6, "vphaddwd", int_x86_xop_vphaddwd>;
  defm VPHADDUWQ : xop2op<0xD7, "vphadduwq", int_x86_xop_vphadduwq>;
  defm VPHADDUWD : xop2op<0xD6, "vphadduwd", int_x86_xop_vphadduwd>;
  defm VPHADDUDQ : xop2op<0xDB, "vphaddudq", int_x86_xop_vphaddudq>;
  defm VPHADDUBW : xop2op<0xD1, "vphaddubw", int_x86_xop_vphaddubw>;
  defm VPHADDUBQ : xop2op<0xD3, "vphaddubq", int_x86_xop_vphaddubq>;
  defm VPHADDUBD : xop2op<0xD2, "vphaddubd", int_x86_xop_vphaddubd>;
  defm VPHADDDQ  : xop2op<0xCB, "vphadddq", int_x86_xop_vphadddq>;
  defm VPHADDBW  : xop2op<0xC1, "vphaddbw", int_x86_xop_vphaddbw>;
  defm VPHADDBQ  : xop2op<0xC3, "vphaddbq", int_x86_xop_vphaddbq>;
  defm VPHADDBD  : xop2op<0xC2, "vphaddbd", int_x86_xop_vphaddbd>;
}

// Scalar load 2 addr operand instructions
multiclass xop2opsld<bits<8> opc, string OpcodeStr, Intrinsic Int,
                     Operand memop, ComplexPattern mem_cpat,
                     X86FoldableSchedWrite sched> {
  def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[sched]>;
  def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins memop:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int mem_cpat:$src))]>, XOP,
           Sched<[sched.Folded, sched.ReadAfterFold]>;
}

multiclass xop2op128<bits<8> opc, string OpcodeStr, Intrinsic Int,
                     X86FoldableSchedWrite sched> {
  def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[sched]>;
  def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR128:$dst, (Int (load addr:$src)))]>, XOP,
           Sched<[sched.Folded, sched.ReadAfterFold]>;
}

multiclass xop2op256<bits<8> opc, string OpcodeStr, Intrinsic Int,
                     X86FoldableSchedWrite sched> {
  def Yrr : IXOP<opc, MRMSrcReg, (outs VR256:$dst), (ins VR256:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR256:$dst, (Int VR256:$src))]>, XOP, VEX_L, Sched<[sched]>;
  def Yrm : IXOP<opc, MRMSrcMem, (outs VR256:$dst), (ins f256mem:$src),
           !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
           [(set VR256:$dst, (Int (load addr:$src)))]>, XOP, VEX_L,
           Sched<[sched.Folded, sched.ReadAfterFold]>;
}

let ExeDomain = SSEPackedSingle in {
  defm VFRCZSS : xop2opsld<0x82, "vfrczss", int_x86_xop_vfrcz_ss,
                           ssmem, sse_load_f32, SchedWriteFRnd.Scl>;
  defm VFRCZPS : xop2op128<0x80, "vfrczps", int_x86_xop_vfrcz_ps,
                           SchedWriteFRnd.XMM>;
  defm VFRCZPS : xop2op256<0x80, "vfrczps", int_x86_xop_vfrcz_ps_256,
                           SchedWriteFRnd.YMM>;
}

let ExeDomain = SSEPackedDouble in {
  defm VFRCZSD : xop2opsld<0x83, "vfrczsd", int_x86_xop_vfrcz_sd,
                           sdmem, sse_load_f64, SchedWriteFRnd.Scl>;
  defm VFRCZPD : xop2op128<0x81, "vfrczpd", int_x86_xop_vfrcz_pd,
                           SchedWriteFRnd.XMM>;
  defm VFRCZPD : xop2op256<0x81, "vfrczpd", int_x86_xop_vfrcz_pd_256,
                           SchedWriteFRnd.YMM>;
}

multiclass xop3op<bits<8> opc, string OpcodeStr, SDNode OpNode,
                  ValueType vt128, X86FoldableSchedWrite sched> {
  def rr : IXOP<opc, MRMSrcReg4VOp3, (outs VR128:$dst),
           (ins VR128:$src1, VR128:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           [(set VR128:$dst,
              (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2))))]>,
           XOP, Sched<[sched]>;
  def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst),
           (ins VR128:$src1, i128mem:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           [(set VR128:$dst,
              (vt128 (OpNode (vt128 VR128:$src1),
                             (vt128 (load addr:$src2)))))]>,
           XOP_4V, VEX_W, Sched<[sched.Folded, sched.ReadAfterFold]>;
  def mr : IXOP<opc, MRMSrcMem4VOp3, (outs VR128:$dst),
           (ins i128mem:$src1, VR128:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           [(set VR128:$dst,
              (vt128 (OpNode (vt128 (load addr:$src1)),
                             (vt128 VR128:$src2))))]>,
             XOP, Sched<[sched.Folded, sched.ReadAfterFold]>;
  // For disassembler
  let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
  def rr_REV : IXOP<opc, MRMSrcReg, (outs VR128:$dst),
               (ins VR128:$src1, VR128:$src2),
               !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
               []>,
               XOP_4V, VEX_W, Sched<[sched]>, FoldGenData<NAME#rr>;
}

let ExeDomain = SSEPackedInt in {
  defm VPROTB : xop3op<0x90, "vprotb", rotl, v16i8, SchedWriteVarVecShift.XMM>;
  defm VPROTD : xop3op<0x92, "vprotd", rotl, v4i32, SchedWriteVarVecShift.XMM>;
  defm VPROTQ : xop3op<0x93, "vprotq", rotl, v2i64, SchedWriteVarVecShift.XMM>;
  defm VPROTW : xop3op<0x91, "vprotw", rotl, v8i16, SchedWriteVarVecShift.XMM>;
  defm VPSHAB : xop3op<0x98, "vpshab", X86vpsha, v16i8, SchedWriteVarVecShift.XMM>;
  defm VPSHAD : xop3op<0x9A, "vpshad", X86vpsha, v4i32, SchedWriteVarVecShift.XMM>;
  defm VPSHAQ : xop3op<0x9B, "vpshaq", X86vpsha, v2i64, SchedWriteVarVecShift.XMM>;
  defm VPSHAW : xop3op<0x99, "vpshaw", X86vpsha, v8i16, SchedWriteVarVecShift.XMM>;
  defm VPSHLB : xop3op<0x94, "vpshlb", X86vpshl, v16i8, SchedWriteVarVecShift.XMM>;
  defm VPSHLD : xop3op<0x96, "vpshld", X86vpshl, v4i32, SchedWriteVarVecShift.XMM>;
  defm VPSHLQ : xop3op<0x97, "vpshlq", X86vpshl, v2i64, SchedWriteVarVecShift.XMM>;
  defm VPSHLW : xop3op<0x95, "vpshlw", X86vpshl, v8i16, SchedWriteVarVecShift.XMM>;
}

multiclass xop3opimm<bits<8> opc, string OpcodeStr, SDNode OpNode,
                     ValueType vt128, X86FoldableSchedWrite sched> {
  def ri : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
           (ins VR128:$src1, u8imm:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           [(set VR128:$dst,
              (vt128 (OpNode (vt128 VR128:$src1), timm:$src2)))]>,
           XOP, Sched<[sched]>;
  def mi : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
           (ins i128mem:$src1, u8imm:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           [(set VR128:$dst,
              (vt128 (OpNode (vt128 (load addr:$src1)), timm:$src2)))]>,
           XOP, Sched<[sched.Folded, sched.ReadAfterFold]>;
}

let ExeDomain = SSEPackedInt in {
  defm VPROTB : xop3opimm<0xC0, "vprotb", X86vrotli, v16i8,
                          SchedWriteVecShiftImm.XMM>;
  defm VPROTD : xop3opimm<0xC2, "vprotd", X86vrotli, v4i32,
                          SchedWriteVecShiftImm.XMM>;
  defm VPROTQ : xop3opimm<0xC3, "vprotq", X86vrotli, v2i64,
                          SchedWriteVecShiftImm.XMM>;
  defm VPROTW : xop3opimm<0xC1, "vprotw", X86vrotli, v8i16,
                          SchedWriteVecShiftImm.XMM>;
}

// Instruction where second source can be memory, but third must be register
multiclass xop4opm2<bits<8> opc, string OpcodeStr, Intrinsic Int,
                    X86FoldableSchedWrite sched> {
  let isCommutable = 1 in
  def rr : IXOPi8Reg<opc, MRMSrcReg, (outs VR128:$dst),
           (ins VR128:$src1, VR128:$src2, VR128:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR128:$dst,
              (Int VR128:$src1, VR128:$src2, VR128:$src3))]>, XOP_4V,
           Sched<[sched]>;
  def rm : IXOPi8Reg<opc, MRMSrcMem, (outs VR128:$dst),
           (ins VR128:$src1, i128mem:$src2, VR128:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR128:$dst,
              (Int VR128:$src1, (load addr:$src2),
              VR128:$src3))]>, XOP_4V, Sched<[sched.Folded, sched.ReadAfterFold]>;
}

let ExeDomain = SSEPackedInt in {
  defm VPMADCSWD  : xop4opm2<0xB6, "vpmadcswd",
                             int_x86_xop_vpmadcswd, SchedWriteVecIMul.XMM>;
  defm VPMADCSSWD : xop4opm2<0xA6, "vpmadcsswd",
                             int_x86_xop_vpmadcsswd, SchedWriteVecIMul.XMM>;
  defm VPMACSWW   : xop4opm2<0x95, "vpmacsww",
                             int_x86_xop_vpmacsww, SchedWriteVecIMul.XMM>;
  defm VPMACSWD   : xop4opm2<0x96, "vpmacswd",
                             int_x86_xop_vpmacswd, SchedWriteVecIMul.XMM>;
  defm VPMACSSWW  : xop4opm2<0x85, "vpmacssww",
                             int_x86_xop_vpmacssww, SchedWriteVecIMul.XMM>;
  defm VPMACSSWD  : xop4opm2<0x86, "vpmacsswd",
                             int_x86_xop_vpmacsswd, SchedWriteVecIMul.XMM>;
  defm VPMACSSDQL : xop4opm2<0x87, "vpmacssdql",
                             int_x86_xop_vpmacssdql, SchedWritePMULLD.XMM>;
  defm VPMACSSDQH : xop4opm2<0x8F, "vpmacssdqh",
                             int_x86_xop_vpmacssdqh, SchedWritePMULLD.XMM>;
  defm VPMACSSDD  : xop4opm2<0x8E, "vpmacssdd",
                             int_x86_xop_vpmacssdd, SchedWritePMULLD.XMM>;
  defm VPMACSDQL  : xop4opm2<0x97, "vpmacsdql",
                             int_x86_xop_vpmacsdql, SchedWritePMULLD.XMM>;
  defm VPMACSDQH  : xop4opm2<0x9F, "vpmacsdqh",
                             int_x86_xop_vpmacsdqh, SchedWritePMULLD.XMM>;
  defm VPMACSDD   : xop4opm2<0x9E, "vpmacsdd",
                             int_x86_xop_vpmacsdd, SchedWritePMULLD.XMM>;
}

// IFMA patterns - for cases where we can safely ignore the overflow bits from
// the multiply or easily match with existing intrinsics.
let Predicates = [HasXOP] in {
  def : Pat<(v8i16 (add (mul (v8i16 VR128:$src1), (v8i16 VR128:$src2)),
                        (v8i16 VR128:$src3))),
            (VPMACSWWrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v4i32 (add (mul (v4i32 VR128:$src1), (v4i32 VR128:$src2)),
                        (v4i32 VR128:$src3))),
            (VPMACSDDrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v2i64 (add (X86pmuldq (bc_v2i64 (X86PShufd (v4i32 VR128:$src1), (i8 -11))),
                                   (bc_v2i64 (X86PShufd (v4i32 VR128:$src2), (i8 -11)))),
                        (v2i64 VR128:$src3))),
            (VPMACSDQHrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v2i64 (add (X86pmuldq (v2i64 VR128:$src1), (v2i64 VR128:$src2)),
                        (v2i64 VR128:$src3))),
            (VPMACSDQLrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v4i32 (add (X86vpmaddwd (v8i16 VR128:$src1), (v8i16 VR128:$src2)),
                        (v4i32 VR128:$src3))),
            (VPMADCSWDrr VR128:$src1, VR128:$src2, VR128:$src3)>;
}

// Transforms to swizzle an immediate to help matching memory operand in first
// operand.
def CommuteVPCOMCC : SDNodeXForm<imm, [{
  uint8_t Imm = N->getZExtValue() & 0x7;
  Imm = X86::getSwappedVPCOMImm(Imm);
  return getI8Imm(Imm, SDLoc(N));
}]>;

// Instruction where second source can be memory, third must be imm8
multiclass xopvpcom<bits<8> opc, string Suffix, SDNode OpNode, ValueType vt128,
                    X86FoldableSchedWrite sched> {
  let ExeDomain = SSEPackedInt in { // SSE integer instructions
    let isCommutable = 1 in
    def ri : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
             (ins VR128:$src1, VR128:$src2, u8imm:$cc),
             !strconcat("vpcom", Suffix,
             "\t{$cc, $src2, $src1, $dst|$dst, $src1, $src2, $cc}"),
             [(set VR128:$dst,
                (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
                               timm:$cc)))]>,
             XOP_4V, Sched<[sched]>;
    def mi : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
             (ins VR128:$src1, i128mem:$src2, u8imm:$cc),
             !strconcat("vpcom", Suffix,
             "\t{$cc, $src2, $src1, $dst|$dst, $src1, $src2, $cc}"),
             [(set VR128:$dst,
                (vt128 (OpNode (vt128 VR128:$src1),
                               (vt128 (load addr:$src2)),
                                timm:$cc)))]>,
             XOP_4V, Sched<[sched.Folded, sched.ReadAfterFold]>;
  }

  def : Pat<(OpNode (load addr:$src2),
                    (vt128 VR128:$src1), timm:$cc),
            (!cast<Instruction>(NAME#"mi") VR128:$src1, addr:$src2,
                                           (CommuteVPCOMCC timm:$cc))>;
}

defm VPCOMB  : xopvpcom<0xCC, "b", X86vpcom, v16i8, SchedWriteVecALU.XMM>;
defm VPCOMW  : xopvpcom<0xCD, "w", X86vpcom, v8i16, SchedWriteVecALU.XMM>;
defm VPCOMD  : xopvpcom<0xCE, "d", X86vpcom, v4i32, SchedWriteVecALU.XMM>;
defm VPCOMQ  : xopvpcom<0xCF, "q", X86vpcom, v2i64, SchedWriteVecALU.XMM>;
defm VPCOMUB : xopvpcom<0xEC, "ub", X86vpcomu, v16i8, SchedWriteVecALU.XMM>;
defm VPCOMUW : xopvpcom<0xED, "uw", X86vpcomu, v8i16, SchedWriteVecALU.XMM>;
defm VPCOMUD : xopvpcom<0xEE, "ud", X86vpcomu, v4i32, SchedWriteVecALU.XMM>;
defm VPCOMUQ : xopvpcom<0xEF, "uq", X86vpcomu, v2i64, SchedWriteVecALU.XMM>;

multiclass xop4op<bits<8> opc, string OpcodeStr, SDNode OpNode,
                  ValueType vt128, X86FoldableSchedWrite sched> {
  def rrr : IXOPi8Reg<opc, MRMSrcReg, (outs VR128:$dst),
            (ins VR128:$src1, VR128:$src2, VR128:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set VR128:$dst,
              (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
                             (vt128 VR128:$src3))))]>,
            XOP_4V, Sched<[sched]>;
  def rrm : IXOPi8Reg<opc, MRMSrcMemOp4, (outs VR128:$dst),
            (ins VR128:$src1, VR128:$src2, i128mem:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set VR128:$dst,
              (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
                             (vt128 (load addr:$src3)))))]>,
            XOP_4V, VEX_W, Sched<[sched.Folded, sched.ReadAfterFold, sched.ReadAfterFold]>;
  def rmr : IXOPi8Reg<opc, MRMSrcMem, (outs VR128:$dst),
            (ins VR128:$src1, i128mem:$src2, VR128:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set VR128:$dst,
              (v16i8 (OpNode (vt128 VR128:$src1), (vt128 (load addr:$src2)),
                             (vt128 VR128:$src3))))]>,
            XOP_4V, Sched<[sched.Folded, sched.ReadAfterFold,
                           // 128mem:$src2
                           ReadDefault, ReadDefault, ReadDefault, ReadDefault,
                           ReadDefault,
                           // VR128:$src3
                           sched.ReadAfterFold]>;
  // For disassembler
  let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
  def rrr_REV : IXOPi8Reg<opc, MRMSrcRegOp4, (outs VR128:$dst),
                (ins VR128:$src1, VR128:$src2, VR128:$src3),
                !strconcat(OpcodeStr,
                "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
                []>, XOP_4V, VEX_W, Sched<[sched]>, FoldGenData<NAME#rrr>;
}

let ExeDomain = SSEPackedInt in {
  defm VPPERM : xop4op<0xA3, "vpperm", X86vpperm, v16i8,
                       SchedWriteVarShuffle.XMM>;
}

// Instruction where either second or third source can be memory
multiclass xop4op_int<bits<8> opc, string OpcodeStr, RegisterClass RC,
                      X86MemOperand x86memop, ValueType VT,
                      X86FoldableSchedWrite sched> {
  def rrr : IXOPi8Reg<opc, MRMSrcReg, (outs RC:$dst),
            (ins RC:$src1, RC:$src2, RC:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set RC:$dst, (VT (or (and RC:$src3, RC:$src1),
                                   (X86andnp RC:$src3, RC:$src2))))]>, XOP_4V,
            Sched<[sched]>;
  // FIXME: This pattern can't match.
  def rrm : IXOPi8Reg<opc, MRMSrcMemOp4, (outs RC:$dst),
            (ins RC:$src1, RC:$src2, x86memop:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set RC:$dst, (VT (or (and (load addr:$src3), RC:$src1),
                                   (X86andnp (load addr:$src3), RC:$src2))))]>,
            XOP_4V, VEX_W, Sched<[sched.Folded, sched.ReadAfterFold, sched.ReadAfterFold]>;
  def rmr : IXOPi8Reg<opc, MRMSrcMem, (outs RC:$dst),
            (ins RC:$src1, x86memop:$src2, RC:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            [(set RC:$dst, (VT (or (and RC:$src3, RC:$src1),
                                   (X86andnp RC:$src3, (load addr:$src2)))))]>,
            XOP_4V, Sched<[sched.Folded, sched.ReadAfterFold,
                           // x86memop:$src2
                           ReadDefault, ReadDefault, ReadDefault, ReadDefault,
                           ReadDefault,
                           // RC::$src3
                           sched.ReadAfterFold]>;
  // For disassembler
  let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
  def rrr_REV : IXOPi8Reg<opc, MRMSrcRegOp4, (outs RC:$dst),
            (ins RC:$src1, RC:$src2, RC:$src3),
            !strconcat(OpcodeStr,
            "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
            []>, XOP_4V, VEX_W, Sched<[sched]>, FoldGenData<NAME#rrr>;
}

let ExeDomain = SSEPackedInt in {
  defm VPCMOV : xop4op_int<0xA2, "vpcmov", VR128, i128mem, v2i64,
                           SchedWriteShuffle.XMM>;
  defm VPCMOVY : xop4op_int<0xA2, "vpcmov", VR256, i256mem, v4i64,
                            SchedWriteShuffle.YMM>, VEX_L;
}

let Predicates = [HasXOP] in {
  def : Pat<(v16i8 (or (and VR128:$src3, VR128:$src1),
                   (X86andnp VR128:$src3, VR128:$src2))),
            (VPCMOVrrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v8i16 (or (and VR128:$src3, VR128:$src1),
                   (X86andnp VR128:$src3, VR128:$src2))),
            (VPCMOVrrr VR128:$src1, VR128:$src2, VR128:$src3)>;
  def : Pat<(v4i32 (or (and VR128:$src3, VR128:$src1),
                   (X86andnp VR128:$src3, VR128:$src2))),
            (VPCMOVrrr VR128:$src1, VR128:$src2, VR128:$src3)>;

  def : Pat<(or (and VR128:$src3, VR128:$src1),
                (X86andnp VR128:$src3, (bc_v16i8 (loadv2i64 addr:$src2)))),
            (VPCMOVrmr VR128:$src1, addr:$src2, VR128:$src3)>;
  def : Pat<(or (and VR128:$src3, VR128:$src1),
                (X86andnp VR128:$src3, (bc_v8i16 (loadv2i64 addr:$src2)))),
            (VPCMOVrmr VR128:$src1, addr:$src2, VR128:$src3)>;
  def : Pat<(or (and VR128:$src3, VR128:$src1),
                (X86andnp VR128:$src3, (bc_v4i32 (loadv2i64 addr:$src2)))),
            (VPCMOVrmr VR128:$src1, addr:$src2, VR128:$src3)>;

  def : Pat<(v32i8 (or (and VR256:$src3, VR256:$src1),
                   (X86andnp VR256:$src3, VR256:$src2))),
            (VPCMOVYrrr VR256:$src1, VR256:$src2, VR256:$src3)>;
  def : Pat<(v16i16 (or (and VR256:$src3, VR256:$src1),
                    (X86andnp VR256:$src3, VR256:$src2))),
            (VPCMOVYrrr VR256:$src1, VR256:$src2, VR256:$src3)>;
  def : Pat<(v8i32 (or (and VR256:$src3, VR256:$src1),
                   (X86andnp VR256:$src3, VR256:$src2))),
            (VPCMOVYrrr VR256:$src1, VR256:$src2, VR256:$src3)>;

  def : Pat<(or (and VR256:$src3, VR256:$src1),
                (X86andnp VR256:$src3, (bc_v32i8 (loadv4i64 addr:$src2)))),
            (VPCMOVYrmr VR256:$src1, addr:$src2, VR256:$src3)>;
  def : Pat<(or (and VR256:$src3, VR256:$src1),
                (X86andnp VR256:$src3, (bc_v16i16 (loadv4i64 addr:$src2)))),
            (VPCMOVYrmr VR256:$src1, addr:$src2, VR256:$src3)>;
  def : Pat<(or (and VR256:$src3, VR256:$src1),
                (X86andnp VR256:$src3, (bc_v8i32 (loadv4i64 addr:$src2)))),
            (VPCMOVYrmr VR256:$src1, addr:$src2, VR256:$src3)>;
}

multiclass xop_vpermil2<bits<8> Opc, string OpcodeStr, RegisterClass RC,
                        X86MemOperand intmemop, X86MemOperand fpmemop,
                        ValueType VT, PatFrag FPLdFrag, PatFrag IntLdFrag,
                        X86FoldableSchedWrite sched> {
  def rr : IXOP5<Opc, MRMSrcReg, (outs RC:$dst),
        (ins RC:$src1, RC:$src2, RC:$src3, u4imm:$src4),
        !strconcat(OpcodeStr,
        "\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
        [(set RC:$dst,
           (VT (X86vpermil2 RC:$src1, RC:$src2, RC:$src3, (i8 timm:$src4))))]>,
        Sched<[sched]>;
  def rm : IXOP5<Opc, MRMSrcMemOp4, (outs RC:$dst),
        (ins RC:$src1, RC:$src2, intmemop:$src3, u4imm:$src4),
        !strconcat(OpcodeStr,
        "\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
        [(set RC:$dst,
          (VT (X86vpermil2 RC:$src1, RC:$src2, (IntLdFrag addr:$src3),
                           (i8 timm:$src4))))]>, VEX_W,
        Sched<[sched.Folded, sched.ReadAfterFold, sched.ReadAfterFold]>;
  def mr : IXOP5<Opc, MRMSrcMem, (outs RC:$dst),
        (ins RC:$src1, fpmemop:$src2, RC:$src3, u4imm:$src4),
        !strconcat(OpcodeStr,
        "\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
        [(set RC:$dst,
          (VT (X86vpermil2 RC:$src1, (FPLdFrag addr:$src2),
                           RC:$src3, (i8 timm:$src4))))]>,
        Sched<[sched.Folded, sched.ReadAfterFold,
               // fpmemop:$src2
               ReadDefault, ReadDefault, ReadDefault, ReadDefault, ReadDefault,
               // RC:$src3
               sched.ReadAfterFold]>;
  // For disassembler
  let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
  def rr_REV : IXOP5<Opc, MRMSrcRegOp4, (outs RC:$dst),
        (ins RC:$src1, RC:$src2, RC:$src3, u4imm:$src4),
        !strconcat(OpcodeStr,
        "\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
        []>, VEX_W, Sched<[sched]>, FoldGenData<NAME#rr>;
}

let ExeDomain = SSEPackedDouble in {
  defm VPERMIL2PD : xop_vpermil2<0x49, "vpermil2pd", VR128, i128mem, f128mem,
                                 v2f64, loadv2f64, loadv2i64,
                                 SchedWriteFVarShuffle.XMM>;
  defm VPERMIL2PDY : xop_vpermil2<0x49, "vpermil2pd", VR256, i256mem, f256mem,
                                  v4f64, loadv4f64, loadv4i64,
                                  SchedWriteFVarShuffle.YMM>, VEX_L;
}

let ExeDomain = SSEPackedSingle in {
  defm VPERMIL2PS : xop_vpermil2<0x48, "vpermil2ps", VR128, i128mem, f128mem,
                                 v4f32, loadv4f32, loadv4i32,
                                 SchedWriteFVarShuffle.XMM>;
  defm VPERMIL2PSY : xop_vpermil2<0x48, "vpermil2ps", VR256, i256mem, f256mem,
                                  v8f32, loadv8f32, loadv8i32,
                                  SchedWriteFVarShuffle.YMM>, VEX_L;
}