llvm.org GIT mirror llvm / 508e0c4 lib / Target / X86 / X86InstrFragmentsSIMD.td
508e0c4

Tree @508e0c4 (Download .tar.gz)

X86InstrFragmentsSIMD.td @508e0c4raw · history · blame

  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
//===-- X86InstrFragmentsSIMD.td - x86 SIMD ISA ------------*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file provides pattern fragments useful for SIMD instructions.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// MMX Pattern Fragments
//===----------------------------------------------------------------------===//

def load_mmx : PatFrag<(ops node:$ptr), (x86mmx (load node:$ptr))>;
def bc_mmx  : PatFrag<(ops node:$in), (x86mmx  (bitconvert node:$in))>;

//===----------------------------------------------------------------------===//
// SSE specific DAG Nodes.
//===----------------------------------------------------------------------===//

def SDTX86FPShiftOp : SDTypeProfile<1, 2, [ SDTCisSameAs<0, 1>,
                                            SDTCisFP<0>, SDTCisInt<2> ]>;
def SDTX86VFCMP : SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<1, 2>,
                                       SDTCisFP<1>, SDTCisVT<3, i8>,
                                       SDTCisVec<1>]>;

def X86umin    : SDNode<"X86ISD::UMIN",      SDTIntBinOp>;
def X86umax    : SDNode<"X86ISD::UMAX",      SDTIntBinOp>;
def X86smin    : SDNode<"X86ISD::SMIN",      SDTIntBinOp>;
def X86smax    : SDNode<"X86ISD::SMAX",      SDTIntBinOp>;

def X86fmin    : SDNode<"X86ISD::FMIN",      SDTFPBinOp>;
def X86fmax    : SDNode<"X86ISD::FMAX",      SDTFPBinOp>;

// Commutative and Associative FMIN and FMAX.
def X86fminc    : SDNode<"X86ISD::FMINC", SDTFPBinOp,
    [SDNPCommutative, SDNPAssociative]>;
def X86fmaxc    : SDNode<"X86ISD::FMAXC", SDTFPBinOp,
    [SDNPCommutative, SDNPAssociative]>;

def X86fand    : SDNode<"X86ISD::FAND",      SDTFPBinOp,
                        [SDNPCommutative, SDNPAssociative]>;
def X86for     : SDNode<"X86ISD::FOR",       SDTFPBinOp,
                        [SDNPCommutative, SDNPAssociative]>;
def X86fxor    : SDNode<"X86ISD::FXOR",      SDTFPBinOp,
                        [SDNPCommutative, SDNPAssociative]>;
def X86fandn   : SDNode<"X86ISD::FANDN",     SDTFPBinOp,
                        [SDNPCommutative, SDNPAssociative]>;
def X86frsqrt  : SDNode<"X86ISD::FRSQRT",    SDTFPUnaryOp>;
def X86frcp    : SDNode<"X86ISD::FRCP",      SDTFPUnaryOp>;
def X86fsrl    : SDNode<"X86ISD::FSRL",      SDTX86FPShiftOp>;
def X86fgetsign: SDNode<"X86ISD::FGETSIGNx86",SDTFPToIntOp>;
def X86fhadd   : SDNode<"X86ISD::FHADD",     SDTFPBinOp>;
def X86fhsub   : SDNode<"X86ISD::FHSUB",     SDTFPBinOp>;
def X86hadd    : SDNode<"X86ISD::HADD",      SDTIntBinOp>;
def X86hsub    : SDNode<"X86ISD::HSUB",      SDTIntBinOp>;
def X86comi    : SDNode<"X86ISD::COMI",      SDTX86CmpTest>;
def X86ucomi   : SDNode<"X86ISD::UCOMI",     SDTX86CmpTest>;
def X86cmps    : SDNode<"X86ISD::FSETCC",     SDTX86Cmps>;
//def X86cmpsd   : SDNode<"X86ISD::FSETCCsd",    SDTX86Cmpsd>;
def X86pshufb  : SDNode<"X86ISD::PSHUFB",
                 SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisSameAs<0,2>]>>;
def X86andnp   : SDNode<"X86ISD::ANDNP",
                 SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisSameAs<0,2>]>>;
def X86psign   : SDNode<"X86ISD::PSIGN",
                 SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisSameAs<0,2>]>>;
def X86pextrb  : SDNode<"X86ISD::PEXTRB",
                 SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<2>]>>;
def X86pextrw  : SDNode<"X86ISD::PEXTRW",
                 SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<2>]>>;
def X86pinsrb  : SDNode<"X86ISD::PINSRB",
                 SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
                                      SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
def X86pinsrw  : SDNode<"X86ISD::PINSRW",
                 SDTypeProfile<1, 3, [SDTCisVT<0, v8i16>, SDTCisSameAs<0,1>,
                                      SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
def X86insrtps : SDNode<"X86ISD::INSERTPS",
                 SDTypeProfile<1, 3, [SDTCisVT<0, v4f32>, SDTCisSameAs<0,1>,
                                      SDTCisVT<2, v4f32>, SDTCisPtrTy<3>]>>;
def X86vzmovl  : SDNode<"X86ISD::VZEXT_MOVL",
                 SDTypeProfile<1, 1, [SDTCisSameAs<0,1>]>>;

def X86vzload  : SDNode<"X86ISD::VZEXT_LOAD", SDTLoad,
                        [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;

def X86vzext   : SDNode<"X86ISD::VZEXT",
                         SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
                                              SDTCisInt<0>, SDTCisInt<1>,
                                              SDTCisOpSmallerThanOp<1, 0>]>>;

def X86vsext   : SDNode<"X86ISD::VSEXT",
                         SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
                                              SDTCisInt<0>, SDTCisInt<1>,
                                              SDTCisOpSmallerThanOp<1, 0>]>>;

def X86vtrunc   : SDNode<"X86ISD::VTRUNC",
                         SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
                                              SDTCisInt<0>, SDTCisInt<1>,
                                              SDTCisOpSmallerThanOp<0, 1>]>>;
def X86trunc    : SDNode<"X86ISD::TRUNC",
                         SDTypeProfile<1, 1, [SDTCisInt<0>, SDTCisInt<1>,
                                              SDTCisOpSmallerThanOp<0, 1>]>>;

def X86vtruncm   : SDNode<"X86ISD::VTRUNCM",
                         SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
                                              SDTCisInt<0>, SDTCisInt<1>,
                                              SDTCisVec<2>, SDTCisInt<2>,
                                              SDTCisOpSmallerThanOp<0, 2>]>>;
def X86vfpext  : SDNode<"X86ISD::VFPEXT",
                        SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
                                             SDTCisFP<0>, SDTCisFP<1>,
                                             SDTCisOpSmallerThanOp<1, 0>]>>;
def X86vfpround: SDNode<"X86ISD::VFPROUND",
                        SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
                                             SDTCisFP<0>, SDTCisFP<1>,
                                             SDTCisOpSmallerThanOp<0, 1>]>>;

def X86vshldq  : SDNode<"X86ISD::VSHLDQ",    SDTIntShiftOp>;
def X86vshrdq  : SDNode<"X86ISD::VSRLDQ",    SDTIntShiftOp>;
def X86cmpp    : SDNode<"X86ISD::CMPP",      SDTX86VFCMP>;
def X86pcmpeq  : SDNode<"X86ISD::PCMPEQ", SDTIntBinOp, [SDNPCommutative]>;
def X86pcmpgt  : SDNode<"X86ISD::PCMPGT", SDTIntBinOp>;

def X86IntCmpMask : SDTypeProfile<1, 2,
    [SDTCisVec<0>, SDTCisSameAs<1, 2>, SDTCisInt<1>]>;
def X86pcmpeqm  : SDNode<"X86ISD::PCMPEQM", X86IntCmpMask, [SDNPCommutative]>;
def X86pcmpgtm  : SDNode<"X86ISD::PCMPGTM", X86IntCmpMask>;

def X86CmpMaskCC :
      SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisInt<0>, SDTCisVec<1>,
                           SDTCisSameAs<1, 2>, SDTCisVT<3, i8>]>;
def X86CmpMaskCCScalar :
      SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<1, 2>, SDTCisVT<3, i8>]>;

def X86cmpm   : SDNode<"X86ISD::CMPM",    X86CmpMaskCC>;
def X86cmpmu  : SDNode<"X86ISD::CMPMU",   X86CmpMaskCC>;
def X86cmpms  : SDNode<"X86ISD::FSETCC",  X86CmpMaskCCScalar>;

def X86vshl    : SDNode<"X86ISD::VSHL",
                        SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisVec<2>]>>;
def X86vsrl    : SDNode<"X86ISD::VSRL",
                        SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisVec<2>]>>;
def X86vsra    : SDNode<"X86ISD::VSRA",
                        SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                      SDTCisVec<2>]>>;

def X86vshli   : SDNode<"X86ISD::VSHLI", SDTIntShiftOp>;
def X86vsrli   : SDNode<"X86ISD::VSRLI", SDTIntShiftOp>;
def X86vsrai   : SDNode<"X86ISD::VSRAI", SDTIntShiftOp>;

def SDTX86CmpPTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
                                          SDTCisVec<1>,
                                          SDTCisSameAs<2, 1>]>;
def X86subus   : SDNode<"X86ISD::SUBUS", SDTIntBinOp>;
def X86ptest   : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
def X86testp   : SDNode<"X86ISD::TESTP", SDTX86CmpPTest>;
def X86kortest : SDNode<"X86ISD::KORTEST", SDTX86CmpPTest>;
def X86testm   : SDNode<"X86ISD::TESTM", SDTypeProfile<1, 2, [SDTCisVec<0>,
                                          SDTCisVec<1>,
                                          SDTCisSameAs<2, 1>]>>;
def X86testnm  : SDNode<"X86ISD::TESTNM", SDTypeProfile<1, 2, [SDTCisVec<0>,
                                          SDTCisVec<1>,
                                          SDTCisSameAs<2, 1>]>>;
def X86select  : SDNode<"X86ISD::SELECT"     , SDTSelect>;

def X86pmuludq : SDNode<"X86ISD::PMULUDQ",
                        SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
                                      SDTCisSameAs<1,2>]>>;

// Specific shuffle nodes - At some point ISD::VECTOR_SHUFFLE will always get
// translated into one of the target nodes below during lowering.
// Note: this is a work in progress...
def SDTShuff1Op : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDTShuff2Op : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                SDTCisSameAs<0,2>]>;
def SDTShuff3Op : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                SDTCisSameAs<0,2>, SDTCisSameAs<0,3>]>;

def SDTShuff2OpI : SDTypeProfile<1, 2, [SDTCisVec<0>,
                                 SDTCisSameAs<0,1>, SDTCisInt<2>]>;
def SDTShuff3OpI : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                 SDTCisSameAs<0,2>, SDTCisInt<3>]>;

def SDTVBroadcast  : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
def SDTVBroadcastm : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>]>;

def SDTBlend : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                             SDTCisSameAs<1,2>, SDTCisVT<3, i32>]>;

def SDTFma : SDTypeProfile<1, 3, [SDTCisSameAs<0,1>,
                           SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;

def X86PAlignr : SDNode<"X86ISD::PALIGNR", SDTShuff3OpI>;

def X86PShufd  : SDNode<"X86ISD::PSHUFD", SDTShuff2OpI>;
def X86PShufhw : SDNode<"X86ISD::PSHUFHW", SDTShuff2OpI>;
def X86PShuflw : SDNode<"X86ISD::PSHUFLW", SDTShuff2OpI>;

def X86Shufp : SDNode<"X86ISD::SHUFP", SDTShuff3OpI>;

def X86Movddup  : SDNode<"X86ISD::MOVDDUP", SDTShuff1Op>;
def X86Movshdup : SDNode<"X86ISD::MOVSHDUP", SDTShuff1Op>;
def X86Movsldup : SDNode<"X86ISD::MOVSLDUP", SDTShuff1Op>;

def X86Movsd : SDNode<"X86ISD::MOVSD", SDTShuff2Op>;
def X86Movss : SDNode<"X86ISD::MOVSS", SDTShuff2Op>;

def X86Movlhps : SDNode<"X86ISD::MOVLHPS", SDTShuff2Op>;
def X86Movlhpd : SDNode<"X86ISD::MOVLHPD", SDTShuff2Op>;
def X86Movhlps : SDNode<"X86ISD::MOVHLPS", SDTShuff2Op>;

def X86Movlps : SDNode<"X86ISD::MOVLPS", SDTShuff2Op>;
def X86Movlpd : SDNode<"X86ISD::MOVLPD", SDTShuff2Op>;

def X86Unpckl : SDNode<"X86ISD::UNPCKL", SDTShuff2Op>;
def X86Unpckh : SDNode<"X86ISD::UNPCKH", SDTShuff2Op>;

def X86VPermilp  : SDNode<"X86ISD::VPERMILP", SDTShuff2OpI>;
def X86VPermv    : SDNode<"X86ISD::VPERMV",   SDTShuff2Op>;
def X86VPermi    : SDNode<"X86ISD::VPERMI",   SDTShuff2OpI>;
def X86VPermv3   : SDNode<"X86ISD::VPERMV3",  SDTShuff3Op>;
def X86VPermiv3   : SDNode<"X86ISD::VPERMIV3",  SDTShuff3Op>;

def X86VPerm2x128 : SDNode<"X86ISD::VPERM2X128", SDTShuff3OpI>;

def X86VBroadcast : SDNode<"X86ISD::VBROADCAST", SDTVBroadcast>;
def X86VBroadcastm : SDNode<"X86ISD::VBROADCASTM", SDTVBroadcastm>;
def X86Vinsert   : SDNode<"X86ISD::VINSERT",  SDTypeProfile<1, 3,
                              [SDTCisSameAs<0, 1>, SDTCisPtrTy<3>]>, []>;
def X86Vextract   : SDNode<"X86ISD::VEXTRACT",  SDTypeProfile<1, 2,
                              [SDTCisVec<1>, SDTCisPtrTy<2>]>, []>;

def X86Blendi    : SDNode<"X86ISD::BLENDI",   SDTBlend>;
def X86Fmadd     : SDNode<"X86ISD::FMADD",     SDTFma>;
def X86Fnmadd    : SDNode<"X86ISD::FNMADD",    SDTFma>;
def X86Fmsub     : SDNode<"X86ISD::FMSUB",     SDTFma>;
def X86Fnmsub    : SDNode<"X86ISD::FNMSUB",    SDTFma>;
def X86Fmaddsub  : SDNode<"X86ISD::FMADDSUB",  SDTFma>;
def X86Fmsubadd  : SDNode<"X86ISD::FMSUBADD",  SDTFma>;

def SDT_PCMPISTRI : SDTypeProfile<2, 3, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
                                         SDTCisVT<2, v16i8>, SDTCisVT<3, v16i8>,
                                         SDTCisVT<4, i8>]>;
def SDT_PCMPESTRI : SDTypeProfile<2, 5, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
                                         SDTCisVT<2, v16i8>, SDTCisVT<3, i32>,
                                         SDTCisVT<4, v16i8>, SDTCisVT<5, i32>,
                                         SDTCisVT<6, i8>]>;

def X86pcmpistri : SDNode<"X86ISD::PCMPISTRI", SDT_PCMPISTRI>;
def X86pcmpestri : SDNode<"X86ISD::PCMPESTRI", SDT_PCMPESTRI>;

//===----------------------------------------------------------------------===//
// SSE Complex Patterns
//===----------------------------------------------------------------------===//

// These are 'extloads' from a scalar to the low element of a vector, zeroing
// the top elements.  These are used for the SSE 'ss' and 'sd' instruction
// forms.
def sse_load_f32 : ComplexPattern<v4f32, 5, "SelectScalarSSELoad", [],
                                  [SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
                                   SDNPWantRoot]>;
def sse_load_f64 : ComplexPattern<v2f64, 5, "SelectScalarSSELoad", [],
                                  [SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
                                   SDNPWantRoot]>;

def ssmem : Operand<v4f32> {
  let PrintMethod = "printf32mem";
  let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
  let ParserMatchClass = X86Mem32AsmOperand;
  let OperandType = "OPERAND_MEMORY";
}
def sdmem : Operand<v2f64> {
  let PrintMethod = "printf64mem";
  let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
  let ParserMatchClass = X86Mem64AsmOperand;
  let OperandType = "OPERAND_MEMORY";
}

//===----------------------------------------------------------------------===//
// SSE pattern fragments
//===----------------------------------------------------------------------===//

// 128-bit load pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def loadv4f32    : PatFrag<(ops node:$ptr), (v4f32 (load node:$ptr))>;
def loadv2f64    : PatFrag<(ops node:$ptr), (v2f64 (load node:$ptr))>;
def loadv2i64    : PatFrag<(ops node:$ptr), (v2i64 (load node:$ptr))>;

// 256-bit load pattern fragments
// NOTE: all 256-bit integer vector loads are promoted to v4i64
def loadv8f32    : PatFrag<(ops node:$ptr), (v8f32 (load node:$ptr))>;
def loadv4f64    : PatFrag<(ops node:$ptr), (v4f64 (load node:$ptr))>;
def loadv4i64    : PatFrag<(ops node:$ptr), (v4i64 (load node:$ptr))>;

// 512-bit load pattern fragments
def loadv16f32   : PatFrag<(ops node:$ptr), (v16f32 (load node:$ptr))>;
def loadv8f64    : PatFrag<(ops node:$ptr), (v8f64 (load node:$ptr))>;
def loadv16i32   : PatFrag<(ops node:$ptr), (v16i32 (load node:$ptr))>;
def loadv8i64    : PatFrag<(ops node:$ptr), (v8i64 (load node:$ptr))>;

// 128-/256-/512-bit extload pattern fragments
def extloadv2f32 : PatFrag<(ops node:$ptr), (v2f64 (extloadvf32 node:$ptr))>;
def extloadv4f32 : PatFrag<(ops node:$ptr), (v4f64 (extloadvf32 node:$ptr))>;
def extloadv8f32 : PatFrag<(ops node:$ptr), (v8f64 (extloadvf32 node:$ptr))>;

// Like 'store', but always requires 128-bit vector alignment.
def alignedstore : PatFrag<(ops node:$val, node:$ptr),
                           (store node:$val, node:$ptr), [{
  return cast<StoreSDNode>(N)->getAlignment() >= 16;
}]>;

// Like 'store', but always requires 256-bit vector alignment.
def alignedstore256 : PatFrag<(ops node:$val, node:$ptr),
                              (store node:$val, node:$ptr), [{
  return cast<StoreSDNode>(N)->getAlignment() >= 32;
}]>;

// Like 'store', but always requires 512-bit vector alignment.
def alignedstore512 : PatFrag<(ops node:$val, node:$ptr),
                              (store node:$val, node:$ptr), [{
  return cast<StoreSDNode>(N)->getAlignment() >= 64;
}]>;

// Like 'load', but always requires 128-bit vector alignment.
def alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return cast<LoadSDNode>(N)->getAlignment() >= 16;
}]>;

// Like 'X86vzload', but always requires 128-bit vector alignment.
def alignedX86vzload : PatFrag<(ops node:$ptr), (X86vzload node:$ptr), [{
  return cast<MemSDNode>(N)->getAlignment() >= 16;
}]>;

// Like 'load', but always requires 256-bit vector alignment.
def alignedload256 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return cast<LoadSDNode>(N)->getAlignment() >= 32;
}]>;

// Like 'load', but always requires 512-bit vector alignment.
def alignedload512 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return cast<LoadSDNode>(N)->getAlignment() >= 64;
}]>;

def alignedloadfsf32 : PatFrag<(ops node:$ptr),
                               (f32 (alignedload node:$ptr))>;
def alignedloadfsf64 : PatFrag<(ops node:$ptr),
                               (f64 (alignedload node:$ptr))>;

// 128-bit aligned load pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def alignedloadv4f32 : PatFrag<(ops node:$ptr),
                               (v4f32 (alignedload node:$ptr))>;
def alignedloadv2f64 : PatFrag<(ops node:$ptr),
                               (v2f64 (alignedload node:$ptr))>;
def alignedloadv2i64 : PatFrag<(ops node:$ptr),
                               (v2i64 (alignedload node:$ptr))>;

// 256-bit aligned load pattern fragments
// NOTE: all 256-bit integer vector loads are promoted to v4i64
def alignedloadv8f32 : PatFrag<(ops node:$ptr),
                               (v8f32 (alignedload256 node:$ptr))>;
def alignedloadv4f64 : PatFrag<(ops node:$ptr),
                               (v4f64 (alignedload256 node:$ptr))>;
def alignedloadv4i64 : PatFrag<(ops node:$ptr),
                               (v4i64 (alignedload256 node:$ptr))>;

// 512-bit aligned load pattern fragments
def alignedloadv16f32 : PatFrag<(ops node:$ptr),
                                (v16f32 (alignedload512 node:$ptr))>;
def alignedloadv16i32 : PatFrag<(ops node:$ptr),
                                (v16i32 (alignedload512 node:$ptr))>;
def alignedloadv8f64  : PatFrag<(ops node:$ptr),
                                (v8f64  (alignedload512 node:$ptr))>;
def alignedloadv8i64  : PatFrag<(ops node:$ptr),
                                (v8i64  (alignedload512 node:$ptr))>;

// Like 'load', but uses special alignment checks suitable for use in
// memory operands in most SSE instructions, which are required to
// be naturally aligned on some targets but not on others.  If the subtarget
// allows unaligned accesses, match any load, though this may require
// setting a feature bit in the processor (on startup, for example).
// Opteron 10h and later implement such a feature.
def memop : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return    Subtarget->hasVectorUAMem()
         || cast<LoadSDNode>(N)->getAlignment() >= 16;
}]>;

def memop4 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return    Subtarget->hasVectorUAMem()
         || cast<LoadSDNode>(N)->getAlignment() >= 4;
}]>;

def memop8 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return    Subtarget->hasVectorUAMem()
         || cast<LoadSDNode>(N)->getAlignment() >= 8;
}]>;

def memopfsf32 : PatFrag<(ops node:$ptr), (f32   (memop node:$ptr))>;
def memopfsf64 : PatFrag<(ops node:$ptr), (f64   (memop node:$ptr))>;

// 128-bit memop pattern fragments
// NOTE: all 128-bit integer vector loads are promoted to v2i64
def memopv4f32 : PatFrag<(ops node:$ptr), (v4f32 (memop node:$ptr))>;
def memopv2f64 : PatFrag<(ops node:$ptr), (v2f64 (memop node:$ptr))>;
def memopv2i64 : PatFrag<(ops node:$ptr), (v2i64 (memop node:$ptr))>;

// 256-bit memop pattern fragments
// NOTE: all 256-bit integer vector loads are promoted to v4i64
def memopv8f32 : PatFrag<(ops node:$ptr), (v8f32 (memop node:$ptr))>;
def memopv4f64 : PatFrag<(ops node:$ptr), (v4f64 (memop node:$ptr))>;
def memopv4i64 : PatFrag<(ops node:$ptr), (v4i64 (memop node:$ptr))>;

// 512-bit memop pattern fragments
def memopv16f32 : PatFrag<(ops node:$ptr), (v16f32 (memop4 node:$ptr))>;
def memopv8f64  : PatFrag<(ops node:$ptr), (v8f64  (memop8 node:$ptr))>;
def memopv16i32 : PatFrag<(ops node:$ptr), (v16i32 (memop4 node:$ptr))>;
def memopv8i64  : PatFrag<(ops node:$ptr), (v8i64  (memop8 node:$ptr))>;

// SSSE3 uses MMX registers for some instructions. They aren't aligned on a
// 16-byte boundary.
// FIXME: 8 byte alignment for mmx reads is not required
def memop64 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return cast<LoadSDNode>(N)->getAlignment() >= 8;
}]>;

def memopmmx  : PatFrag<(ops node:$ptr), (x86mmx  (memop64 node:$ptr))>;

// MOVNT Support
// Like 'store', but requires the non-temporal bit to be set
def nontemporalstore : PatFrag<(ops node:$val, node:$ptr),
                           (st node:$val, node:$ptr), [{
  if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
    return ST->isNonTemporal();
  return false;
}]>;

def alignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
                                    (st node:$val, node:$ptr), [{
  if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
    return ST->isNonTemporal() && !ST->isTruncatingStore() &&
           ST->getAddressingMode() == ISD::UNINDEXED &&
           ST->getAlignment() >= 16;
  return false;
}]>;

def unalignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
                                      (st node:$val, node:$ptr), [{
  if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
    return ST->isNonTemporal() &&
           ST->getAlignment() < 16;
  return false;
}]>;

// 128-bit bitconvert pattern fragments
def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>;
def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>;
def bc_v16i8 : PatFrag<(ops node:$in), (v16i8 (bitconvert node:$in))>;
def bc_v8i16 : PatFrag<(ops node:$in), (v8i16 (bitconvert node:$in))>;
def bc_v4i32 : PatFrag<(ops node:$in), (v4i32 (bitconvert node:$in))>;
def bc_v2i64 : PatFrag<(ops node:$in), (v2i64 (bitconvert node:$in))>;

// 256-bit bitconvert pattern fragments
def bc_v32i8 : PatFrag<(ops node:$in), (v32i8 (bitconvert node:$in))>;
def bc_v16i16 : PatFrag<(ops node:$in), (v16i16 (bitconvert node:$in))>;
def bc_v8i32 : PatFrag<(ops node:$in), (v8i32 (bitconvert node:$in))>;
def bc_v4i64 : PatFrag<(ops node:$in), (v4i64 (bitconvert node:$in))>;
def bc_v8f32 : PatFrag<(ops node:$in), (v8f32 (bitconvert node:$in))>;

// 512-bit bitconvert pattern fragments
def bc_v16i32 : PatFrag<(ops node:$in), (v16i32 (bitconvert node:$in))>;
def bc_v8i64 : PatFrag<(ops node:$in), (v8i64 (bitconvert node:$in))>;
def bc_v8f64 : PatFrag<(ops node:$in), (v8f64 (bitconvert node:$in))>;
def bc_v16f32 : PatFrag<(ops node:$in), (v16f32 (bitconvert node:$in))>;

def vzmovl_v2i64 : PatFrag<(ops node:$src),
                           (bitconvert (v2i64 (X86vzmovl
                             (v2i64 (scalar_to_vector (loadi64 node:$src))))))>;
def vzmovl_v4i32 : PatFrag<(ops node:$src),
                           (bitconvert (v4i32 (X86vzmovl
                             (v4i32 (scalar_to_vector (loadi32 node:$src))))))>;

def vzload_v2i64 : PatFrag<(ops node:$src),
                           (bitconvert (v2i64 (X86vzload node:$src)))>;


def fp32imm0 : PatLeaf<(f32 fpimm), [{
  return N->isExactlyValue(+0.0);
}]>;

def I8Imm : SDNodeXForm<imm, [{
  // Transformation function: get the low 8 bits.
  return getI8Imm((uint8_t)N->getZExtValue());
}]>;

def FROUND_NO_EXC : ImmLeaf<i32, [{ return Imm == 8; }]>;
def FROUND_CURRENT : ImmLeaf<i32, [{ return Imm == 4; }]>;

// BYTE_imm - Transform bit immediates into byte immediates.
def BYTE_imm  : SDNodeXForm<imm, [{
  // Transformation function: imm >> 3
  return getI32Imm(N->getZExtValue() >> 3);
}]>;

// EXTRACT_get_vextract128_imm xform function: convert extract_subvector index
// to VEXTRACTF128/VEXTRACTI128 imm.
def EXTRACT_get_vextract128_imm : SDNodeXForm<extract_subvector, [{
  return getI8Imm(X86::getExtractVEXTRACT128Immediate(N));
}]>;

// INSERT_get_vinsert128_imm xform function: convert insert_subvector index to
// VINSERTF128/VINSERTI128 imm.
def INSERT_get_vinsert128_imm : SDNodeXForm<insert_subvector, [{
  return getI8Imm(X86::getInsertVINSERT128Immediate(N));
}]>;

// EXTRACT_get_vextract256_imm xform function: convert extract_subvector index
// to VEXTRACTF64x4 imm.
def EXTRACT_get_vextract256_imm : SDNodeXForm<extract_subvector, [{
  return getI8Imm(X86::getExtractVEXTRACT256Immediate(N));
}]>;

// INSERT_get_vinsert256_imm xform function: convert insert_subvector index to
// VINSERTF64x4 imm.
def INSERT_get_vinsert256_imm : SDNodeXForm<insert_subvector, [{
  return getI8Imm(X86::getInsertVINSERT256Immediate(N));
}]>;

def vextract128_extract : PatFrag<(ops node:$bigvec, node:$index),
                                   (extract_subvector node:$bigvec,
                                                      node:$index), [{
  return X86::isVEXTRACT128Index(N);
}], EXTRACT_get_vextract128_imm>;

def vinsert128_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
                                      node:$index),
                                 (insert_subvector node:$bigvec, node:$smallvec,
                                                   node:$index), [{
  return X86::isVINSERT128Index(N);
}], INSERT_get_vinsert128_imm>;


def vextract256_extract : PatFrag<(ops node:$bigvec, node:$index),
                                   (extract_subvector node:$bigvec,
                                                      node:$index), [{
  return X86::isVEXTRACT256Index(N);
}], EXTRACT_get_vextract256_imm>;

def vinsert256_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
                                      node:$index),
                                 (insert_subvector node:$bigvec, node:$smallvec,
                                                   node:$index), [{
  return X86::isVINSERT256Index(N);
}], INSERT_get_vinsert256_imm>;