llvm.org GIT mirror llvm / testing lib / Target / X86 / X86.td
testing

Tree @testing (Download .tar.gz)

X86.td @testingraw · 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
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
//===-- X86.td - Target definition file for the Intel X86 --*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This is a target description file for the Intel i386 architecture, referred
// to here as the "X86" architecture.
//
//===----------------------------------------------------------------------===//

// Get the target-independent interfaces which we are implementing...
//
include "llvm/Target/Target.td"

//===----------------------------------------------------------------------===//
// X86 Subtarget state
//

def Mode64Bit : SubtargetFeature<"64bit-mode", "In64BitMode", "true",
                                  "64-bit mode (x86_64)">;
def Mode32Bit : SubtargetFeature<"32bit-mode", "In32BitMode", "true",
                                  "32-bit mode (80386)">;
def Mode16Bit : SubtargetFeature<"16bit-mode", "In16BitMode", "true",
                                  "16-bit mode (i8086)">;

//===----------------------------------------------------------------------===//
// X86 Subtarget features
//===----------------------------------------------------------------------===//

def FeatureX87     : SubtargetFeature<"x87","HasX87", "true",
                                      "Enable X87 float instructions">;

def FeatureCMOV    : SubtargetFeature<"cmov","HasCMov", "true",
                                      "Enable conditional move instructions">;

def FeaturePOPCNT   : SubtargetFeature<"popcnt", "HasPOPCNT", "true",
                                       "Support POPCNT instruction">;

def FeatureFXSR    : SubtargetFeature<"fxsr", "HasFXSR", "true",
                                      "Support fxsave/fxrestore instructions">;

def FeatureXSAVE   : SubtargetFeature<"xsave", "HasXSAVE", "true",
                                       "Support xsave instructions">;

def FeatureXSAVEOPT: SubtargetFeature<"xsaveopt", "HasXSAVEOPT", "true",
                                       "Support xsaveopt instructions">;

def FeatureXSAVEC  : SubtargetFeature<"xsavec", "HasXSAVEC", "true",
                                       "Support xsavec instructions">;

def FeatureXSAVES  : SubtargetFeature<"xsaves", "HasXSAVES", "true",
                                       "Support xsaves instructions">;

def FeatureSSE1    : SubtargetFeature<"sse", "X86SSELevel", "SSE1",
                                      "Enable SSE instructions",
                                      // SSE codegen depends on cmovs, and all
                                      // SSE1+ processors support them.
                                      [FeatureCMOV]>;
def FeatureSSE2    : SubtargetFeature<"sse2", "X86SSELevel", "SSE2",
                                      "Enable SSE2 instructions",
                                      [FeatureSSE1]>;
def FeatureSSE3    : SubtargetFeature<"sse3", "X86SSELevel", "SSE3",
                                      "Enable SSE3 instructions",
                                      [FeatureSSE2]>;
def FeatureSSSE3   : SubtargetFeature<"ssse3", "X86SSELevel", "SSSE3",
                                      "Enable SSSE3 instructions",
                                      [FeatureSSE3]>;
def FeatureSSE41   : SubtargetFeature<"sse4.1", "X86SSELevel", "SSE41",
                                      "Enable SSE 4.1 instructions",
                                      [FeatureSSSE3]>;
def FeatureSSE42   : SubtargetFeature<"sse4.2", "X86SSELevel", "SSE42",
                                      "Enable SSE 4.2 instructions",
                                      [FeatureSSE41]>;
// The MMX subtarget feature is separate from the rest of the SSE features
// because it's important (for odd compatibility reasons) to be able to
// turn it off explicitly while allowing SSE+ to be on.
def FeatureMMX     : SubtargetFeature<"mmx","X863DNowLevel", "MMX",
                                      "Enable MMX instructions">;
def Feature3DNow   : SubtargetFeature<"3dnow", "X863DNowLevel", "ThreeDNow",
                                      "Enable 3DNow! instructions",
                                      [FeatureMMX]>;
def Feature3DNowA  : SubtargetFeature<"3dnowa", "X863DNowLevel", "ThreeDNowA",
                                      "Enable 3DNow! Athlon instructions",
                                      [Feature3DNow]>;
// All x86-64 hardware has SSE2, but we don't mark SSE2 as an implied
// feature, because SSE2 can be disabled (e.g. for compiling OS kernels)
// without disabling 64-bit mode.
def Feature64Bit   : SubtargetFeature<"64bit", "HasX86_64", "true",
                                      "Support 64-bit instructions",
                                      [FeatureCMOV]>;
def FeatureCMPXCHG16B : SubtargetFeature<"cx16", "HasCmpxchg16b", "true",
                                      "64-bit with cmpxchg16b",
                                      [Feature64Bit]>;
def FeatureSlowSHLD : SubtargetFeature<"slow-shld", "IsSHLDSlow", "true",
                                       "SHLD instruction is slow">;
def FeatureSlowPMULLD : SubtargetFeature<"slow-pmulld", "IsPMULLDSlow", "true",
                                        "PMULLD instruction is slow">;
// FIXME: This should not apply to CPUs that do not have SSE.
def FeatureSlowUAMem16 : SubtargetFeature<"slow-unaligned-mem-16",
                                "IsUAMem16Slow", "true",
                                "Slow unaligned 16-byte memory access">;
def FeatureSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32",
                                "IsUAMem32Slow", "true",
                                "Slow unaligned 32-byte memory access">;
def FeatureSSE4A   : SubtargetFeature<"sse4a", "HasSSE4A", "true",
                                      "Support SSE 4a instructions",
                                      [FeatureSSE3]>;

def FeatureAVX     : SubtargetFeature<"avx", "X86SSELevel", "AVX",
                                      "Enable AVX instructions",
                                      [FeatureSSE42]>;
def FeatureAVX2    : SubtargetFeature<"avx2", "X86SSELevel", "AVX2",
                                      "Enable AVX2 instructions",
                                      [FeatureAVX]>;
def FeatureFMA     : SubtargetFeature<"fma", "HasFMA", "true",
                                      "Enable three-operand fused multiple-add",
                                      [FeatureAVX]>;
def FeatureF16C    : SubtargetFeature<"f16c", "HasF16C", "true",
                       "Support 16-bit floating point conversion instructions",
                       [FeatureAVX]>;
def FeatureAVX512   : SubtargetFeature<"avx512f", "X86SSELevel", "AVX512F",
                                      "Enable AVX-512 instructions",
                                      [FeatureAVX2, FeatureFMA, FeatureF16C]>;
def FeatureERI      : SubtargetFeature<"avx512er", "HasERI", "true",
                      "Enable AVX-512 Exponential and Reciprocal Instructions",
                                      [FeatureAVX512]>;
def FeatureCDI      : SubtargetFeature<"avx512cd", "HasCDI", "true",
                      "Enable AVX-512 Conflict Detection Instructions",
                                      [FeatureAVX512]>;
def FeatureVPOPCNTDQ : SubtargetFeature<"avx512vpopcntdq", "HasVPOPCNTDQ",
                       "true", "Enable AVX-512 Population Count Instructions",
                                      [FeatureAVX512]>;
def FeaturePFI      : SubtargetFeature<"avx512pf", "HasPFI", "true",
                      "Enable AVX-512 PreFetch Instructions",
                                      [FeatureAVX512]>;
def FeaturePREFETCHWT1  : SubtargetFeature<"prefetchwt1", "HasPFPREFETCHWT1",
                                   "true",
                                   "Prefetch with Intent to Write and T1 Hint">;
def FeatureDQI     : SubtargetFeature<"avx512dq", "HasDQI", "true",
                      "Enable AVX-512 Doubleword and Quadword Instructions",
                                      [FeatureAVX512]>;
def FeatureBWI     : SubtargetFeature<"avx512bw", "HasBWI", "true",
                      "Enable AVX-512 Byte and Word Instructions",
                                      [FeatureAVX512]>;
def FeatureVLX     : SubtargetFeature<"avx512vl", "HasVLX", "true",
                      "Enable AVX-512 Vector Length eXtensions",
                                      [FeatureAVX512]>;
def FeatureVBMI     : SubtargetFeature<"avx512vbmi", "HasVBMI", "true",
                      "Enable AVX-512 Vector Byte Manipulation Instructions",
                                      [FeatureBWI]>;
def FeatureIFMA     : SubtargetFeature<"avx512ifma", "HasIFMA", "true",
                      "Enable AVX-512 Integer Fused Multiple-Add",
                                      [FeatureAVX512]>;
def FeaturePKU   : SubtargetFeature<"pku", "HasPKU", "true",
                      "Enable protection keys">;
def FeaturePCLMUL  : SubtargetFeature<"pclmul", "HasPCLMUL", "true",
                         "Enable packed carry-less multiplication instructions",
                               [FeatureSSE2]>;
def FeatureFMA4    : SubtargetFeature<"fma4", "HasFMA4", "true",
                                      "Enable four-operand fused multiple-add",
                                      [FeatureAVX, FeatureSSE4A]>;
def FeatureXOP     : SubtargetFeature<"xop", "HasXOP", "true",
                                      "Enable XOP instructions",
                                      [FeatureFMA4]>;
def FeatureSSEUnalignedMem : SubtargetFeature<"sse-unaligned-mem",
                                          "HasSSEUnalignedMem", "true",
                      "Allow unaligned memory operands with SSE instructions">;
def FeatureAES     : SubtargetFeature<"aes", "HasAES", "true",
                                      "Enable AES instructions",
                                      [FeatureSSE2]>;
def FeatureTBM     : SubtargetFeature<"tbm", "HasTBM", "true",
                                      "Enable TBM instructions">;
def FeatureLWP     : SubtargetFeature<"lwp", "HasLWP", "true",
                                      "Enable LWP instructions">;
def FeatureMOVBE   : SubtargetFeature<"movbe", "HasMOVBE", "true",
                                      "Support MOVBE instruction">;
def FeatureRDRAND  : SubtargetFeature<"rdrnd", "HasRDRAND", "true",
                                      "Support RDRAND instruction">;
def FeatureFSGSBase : SubtargetFeature<"fsgsbase", "HasFSGSBase", "true",
                                       "Support FS/GS Base instructions">;
def FeatureLZCNT   : SubtargetFeature<"lzcnt", "HasLZCNT", "true",
                                      "Support LZCNT instruction">;
def FeatureBMI     : SubtargetFeature<"bmi", "HasBMI", "true",
                                      "Support BMI instructions">;
def FeatureBMI2    : SubtargetFeature<"bmi2", "HasBMI2", "true",
                                      "Support BMI2 instructions">;
def FeatureRTM     : SubtargetFeature<"rtm", "HasRTM", "true",
                                      "Support RTM instructions">;
def FeatureADX     : SubtargetFeature<"adx", "HasADX", "true",
                                      "Support ADX instructions">;
def FeatureSHA     : SubtargetFeature<"sha", "HasSHA", "true",
                                      "Enable SHA instructions",
                                      [FeatureSSE2]>;
def FeaturePRFCHW  : SubtargetFeature<"prfchw", "HasPRFCHW", "true",
                                      "Support PRFCHW instructions">;
def FeatureRDSEED  : SubtargetFeature<"rdseed", "HasRDSEED", "true",
                                      "Support RDSEED instruction">;
def FeatureLAHFSAHF : SubtargetFeature<"sahf", "HasLAHFSAHF", "true",
                                       "Support LAHF and SAHF instructions">;
def FeatureMWAITX  : SubtargetFeature<"mwaitx", "HasMWAITX", "true",
                                      "Enable MONITORX/MWAITX timer functionality">;
def FeatureCLZERO  : SubtargetFeature<"clzero", "HasCLZERO", "true",
                                      "Enable Cache Line Zero">;
def FeatureMPX     : SubtargetFeature<"mpx", "HasMPX", "true",
                                      "Support MPX instructions">;
def FeatureLEAForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true",
                                     "Use LEA for adjusting the stack pointer">;
def FeatureSlowDivide32 : SubtargetFeature<"idivl-to-divb",
                                     "HasSlowDivide32", "true",
                                     "Use 8-bit divide for positive values less than 256">;
def FeatureSlowDivide64 : SubtargetFeature<"idivq-to-divl",
                                     "HasSlowDivide64", "true",
                                     "Use 32-bit divide for positive values less than 2^32">;
def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions",
                                     "PadShortFunctions", "true",
                                     "Pad short functions">;
def FeatureSGX     : SubtargetFeature<"sgx", "HasSGX", "true",
                                      "Enable Software Guard Extensions">;
def FeatureCLFLUSHOPT : SubtargetFeature<"clflushopt", "HasCLFLUSHOPT", "true",
                                      "Flush A Cache Line Optimized">;
def FeatureCLWB    : SubtargetFeature<"clwb", "HasCLWB", "true",
                                      "Cache Line Write Back">;
// On some processors, instructions that implicitly take two memory operands are
// slow. In practice, this means that CALL, PUSH, and POP with memory operands
// should be avoided in favor of a MOV + register CALL/PUSH/POP.
def FeatureSlowTwoMemOps : SubtargetFeature<"slow-two-mem-ops",
                                     "SlowTwoMemOps", "true",
                                     "Two memory operand instructions are slow">;
def FeatureLEAUsesAG : SubtargetFeature<"lea-uses-ag", "LEAUsesAG", "true",
                                   "LEA instruction needs inputs at AG stage">;
def FeatureSlowLEA : SubtargetFeature<"slow-lea", "SlowLEA", "true",
                                   "LEA instruction with certain arguments is slow">;
def FeatureSlow3OpsLEA : SubtargetFeature<"slow-3ops-lea", "Slow3OpsLEA", "true",
                                   "LEA instruction with 3 ops or certain registers is slow">;
def FeatureSlowIncDec : SubtargetFeature<"slow-incdec", "SlowIncDec", "true",
                                   "INC and DEC instructions are slower than ADD and SUB">;
def FeatureSoftFloat
    : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
                       "Use software floating point features.">;
// On some X86 processors, there is no performance hazard to writing only the
// lower parts of a YMM or ZMM register without clearing the upper part.
def FeatureFastPartialYMMorZMMWrite
    : SubtargetFeature<"fast-partial-ymm-or-zmm-write",
                       "HasFastPartialYMMorZMMWrite",
                       "true", "Partial writes to YMM/ZMM registers are fast">;
// FeatureFastScalarFSQRT should be enabled if scalar FSQRT has shorter latency
// than the corresponding NR code. FeatureFastVectorFSQRT should be enabled if
// vector FSQRT has higher throughput than the corresponding NR code.
// The idea is that throughput bound code is likely to be vectorized, so for
// vectorized code we should care about the throughput of SQRT operations.
// But if the code is scalar that probably means that the code has some kind of
// dependency and we should care more about reducing the latency.
def FeatureFastScalarFSQRT
    : SubtargetFeature<"fast-scalar-fsqrt", "HasFastScalarFSQRT",
                       "true", "Scalar SQRT is fast (disable Newton-Raphson)">;
def FeatureFastVectorFSQRT
    : SubtargetFeature<"fast-vector-fsqrt", "HasFastVectorFSQRT",
                       "true", "Vector SQRT is fast (disable Newton-Raphson)">;
// If lzcnt has equivalent latency/throughput to most simple integer ops, it can
// be used to replace test/set sequences.
def FeatureFastLZCNT
    : SubtargetFeature<
          "fast-lzcnt", "HasFastLZCNT", "true",
          "LZCNT instructions are as fast as most simple integer ops">;


// Sandy Bridge and newer processors can use SHLD with the same source on both
// inputs to implement rotate to avoid the partial flag update of the normal
// rotate instructions.
def FeatureFastSHLDRotate
    : SubtargetFeature<
          "fast-shld-rotate", "HasFastSHLDRotate", "true",
          "SHLD can be used as a faster rotate">;

// Ivy Bridge and newer processors have enhanced REP MOVSB and STOSB (aka
// "string operations"). See "REP String Enhancement" in the Intel Software
// Development Manual. This feature essentially means that REP MOVSB will copy
// using the largest available size instead of copying bytes one by one, making
// it at least as fast as REPMOVS{W,D,Q}.
def FeatureERMSB
    : SubtargetFeature<
          "ermsb", "HasERMSB", "true",
          "REP MOVS/STOS are fast">;

// Sandy Bridge and newer processors have many instructions that can be
// fused with conditional branches and pass through the CPU as a single
// operation.
def FeatureMacroFusion
    : SubtargetFeature<"macrofusion", "HasMacroFusion", "true",
                 "Various instructions can be fused with conditional branches">;

//===----------------------------------------------------------------------===//
// X86 processors supported.
//===----------------------------------------------------------------------===//

include "X86Schedule.td"

def ProcIntelAtom : SubtargetFeature<"atom", "X86ProcFamily", "IntelAtom",
                    "Intel Atom processors">;
def ProcIntelSLM  : SubtargetFeature<"slm", "X86ProcFamily", "IntelSLM",
                    "Intel Silvermont processors">;
def ProcIntelGLM  : SubtargetFeature<"glm", "X86ProcFamily", "IntelGLM",
                    "Intel Goldmont processors">;
def ProcIntelHSW  : SubtargetFeature<"haswell", "X86ProcFamily",
                    "IntelHaswell", "Intel Haswell processors">;
def ProcIntelBDW  : SubtargetFeature<"broadwell", "X86ProcFamily",
                    "IntelBroadwell", "Intel Broadwell processors">;
def ProcIntelSKL  : SubtargetFeature<"skylake", "X86ProcFamily",
                    "IntelSkylake", "Intel Skylake processors">;
def ProcIntelKNL  : SubtargetFeature<"knl", "X86ProcFamily",
                    "IntelKNL", "Intel Knights Landing processors">;
def ProcIntelSKX  : SubtargetFeature<"skx", "X86ProcFamily",
                    "IntelSKX", "Intel Skylake Server processors">;
def ProcIntelCNL  : SubtargetFeature<"cannonlake", "X86ProcFamily",
                    "IntelCannonlake", "Intel Cannonlake processors">;

class Proc<string Name, list<SubtargetFeature> Features>
 : ProcessorModel<Name, GenericModel, Features>;

def : Proc<"generic",         [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i386",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i486",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i586",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"pentium",         [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"pentium-mmx",     [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;

foreach P = ["i686", "pentiumpro"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureCMOV]>;
}

def : Proc<"pentium2",        [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                               FeatureCMOV, FeatureFXSR]>;

foreach P = ["pentium3", "pentium3m"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE1,
                 FeatureFXSR]>;
}

// Enable the PostRAScheduler for SSE2 and SSE3 class cpus.
// The intent is to enable it for pentium4 which is the current default
// processor in a vanilla 32-bit clang compilation when no specific
// architecture is specified.  This generally gives a nice performance
// increase on silvermont, with largely neutral behavior on other
// contemporary large core processors.
// pentium-m, pentium4m, prescott and nocona are included as a preventative
// measure to avoid performance surprises, in case clang's default cpu
// changes slightly.

def : ProcessorModel<"pentium-m", GenericPostRAModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                      FeatureSSE2, FeatureFXSR]>;

foreach P = ["pentium4", "pentium4m"] in {
  def : ProcessorModel<P, GenericPostRAModel,
                       [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                        FeatureSSE2, FeatureFXSR]>;
}

// Intel Quark.
def : Proc<"lakemont",        []>;

// Intel Core Duo.
def : ProcessorModel<"yonah", SandyBridgeModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE3,
                      FeatureFXSR]>;

// NetBurst.
def : ProcessorModel<"prescott", GenericPostRAModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE3,
                      FeatureFXSR]>;
def : ProcessorModel<"nocona", GenericPostRAModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSE3,
  FeatureFXSR,
  FeatureCMPXCHG16B
]>;

// Intel Core 2 Solo/Duo.
def : ProcessorModel<"core2", SandyBridgeModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSSE3,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : ProcessorModel<"penryn", SandyBridgeModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSE41,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;

// Atom CPUs.
class BonnellProc<string Name> : ProcessorModel<Name, AtomModel, [
  ProcIntelAtom,
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSSE3,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeatureLEAForSP,
  FeatureSlowDivide32,
  FeatureSlowDivide64,
  FeatureSlowTwoMemOps,
  FeatureLEAUsesAG,
  FeaturePadShortFunctions,
  FeatureLAHFSAHF
]>;
def : BonnellProc<"bonnell">;
def : BonnellProc<"atom">; // Pin the generic name to the baseline.

class SilvermontProc<string Name> : ProcessorModel<Name, SLMModel, [
  ProcIntelSLM,
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeaturePOPCNT,
  FeaturePCLMUL,
  FeatureAES,
  FeatureSlowDivide64,
  FeatureSlowTwoMemOps,
  FeaturePRFCHW,
  FeatureSlowLEA,
  FeatureSlowIncDec,
  FeatureSlowPMULLD,
  FeatureLAHFSAHF
]>;
def : SilvermontProc<"silvermont">;
def : SilvermontProc<"slm">; // Legacy alias.

class GoldmontProc<string Name> : ProcessorModel<Name, SLMModel, [
  ProcIntelGLM,
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeaturePOPCNT,
  FeaturePCLMUL,
  FeatureAES,
  FeaturePRFCHW,
  FeatureSlowTwoMemOps,
  FeatureSlowLEA,
  FeatureSlowIncDec,
  FeatureLAHFSAHF,
  FeatureMPX,
  FeatureSHA,
  FeatureRDRAND,
  FeatureRDSEED,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureXSAVEC,
  FeatureXSAVES,
  FeatureCLFLUSHOPT,
  FeatureFSGSBase
]>;
def : GoldmontProc<"goldmont">;

// "Arrandale" along with corei3 and corei5
class NehalemProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : NehalemProc<"nehalem">;
def : NehalemProc<"corei7">;

// Westmere is a similar machine to nehalem with some additional features.
// Westmere is the corei3/i5/i7 path from nehalem to sandybridge
class WestmereProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureAES,
  FeaturePCLMUL,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : WestmereProc<"westmere">;

class ProcessorFeatures<list<SubtargetFeature> Inherited,
                        list<SubtargetFeature> NewFeatures> {
  list<SubtargetFeature> Value = !listconcat(Inherited, NewFeatures);
}

class ProcModel<string Name, SchedMachineModel Model,
                list<SubtargetFeature> ProcFeatures,
                list<SubtargetFeature> OtherFeatures> :
  ProcessorModel<Name, Model, !listconcat(ProcFeatures, OtherFeatures)>;

// SSE is not listed here since llvm treats AVX as a reimplementation of SSE,
// rather than a superset.
def SNBFeatures : ProcessorFeatures<[], [
  FeatureX87,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureAES,
  FeatureSlowDivide64,
  FeaturePCLMUL,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureLAHFSAHF,
  FeatureSlow3OpsLEA,
  FeatureFastScalarFSQRT,
  FeatureFastSHLDRotate,
  FeatureSlowIncDec,
  FeatureMacroFusion
]>;

class SandyBridgeProc<string Name> : ProcModel<Name, SandyBridgeModel,
                                               SNBFeatures.Value, [
  FeatureSlowUAMem32
]>;
def : SandyBridgeProc<"sandybridge">;
def : SandyBridgeProc<"corei7-avx">; // Legacy alias.

def IVBFeatures : ProcessorFeatures<SNBFeatures.Value, [
  FeatureRDRAND,
  FeatureF16C,
  FeatureFSGSBase
]>;

class IvyBridgeProc<string Name> : ProcModel<Name, SandyBridgeModel,
                                             IVBFeatures.Value, [
  FeatureSlowUAMem32
]>;
def : IvyBridgeProc<"ivybridge">;
def : IvyBridgeProc<"core-avx-i">; // Legacy alias.

def HSWFeatures : ProcessorFeatures<IVBFeatures.Value, [
  FeatureAVX2,
  FeatureBMI,
  FeatureBMI2,
  FeatureERMSB,
  FeatureFMA,
  FeatureLZCNT,
  FeatureMOVBE
]>;

class HaswellProc<string Name> : ProcModel<Name, HaswellModel,
                                           HSWFeatures.Value, [
  ProcIntelHSW
]>;
def : HaswellProc<"haswell">;
def : HaswellProc<"core-avx2">; // Legacy alias.

def BDWFeatures : ProcessorFeatures<HSWFeatures.Value, [
  FeatureADX,
  FeatureRDSEED
]>;
class BroadwellProc<string Name> : ProcModel<Name, BroadwellModel,
                                             BDWFeatures.Value, [
  ProcIntelBDW
]>;
def : BroadwellProc<"broadwell">;

def SKLFeatures : ProcessorFeatures<BDWFeatures.Value, [
  FeatureMPX,
  FeatureRTM,
  FeatureXSAVEC,
  FeatureXSAVES,
  FeatureSGX,
  FeatureCLFLUSHOPT,
  FeatureFastVectorFSQRT
]>;

class SkylakeClientProc<string Name> : ProcModel<Name, SkylakeClientModel,
                                                 SKLFeatures.Value, [
  ProcIntelSKL
]>;
def : SkylakeClientProc<"skylake">;

def KNLFeatures : ProcessorFeatures<IVBFeatures.Value, [
  FeatureAVX512,
  FeatureERI,
  FeatureCDI,
  FeaturePFI,
  FeaturePREFETCHWT1,
  FeatureADX,
  FeatureRDSEED,
  FeatureMOVBE,
  FeatureLZCNT,
  FeatureBMI,
  FeatureBMI2,
  FeatureFMA
]>;

// FIXME: define KNL model
class KnightsLandingProc<string Name> : ProcModel<Name, HaswellModel,
                                                  KNLFeatures.Value, [
  ProcIntelKNL,
  FeatureSlowTwoMemOps,
  FeatureFastPartialYMMorZMMWrite
]>;
def : KnightsLandingProc<"knl">;

class KnightsMillProc<string Name> : ProcModel<Name, HaswellModel,
                                               KNLFeatures.Value, [
  ProcIntelKNL,
  FeatureSlowTwoMemOps,
  FeatureFastPartialYMMorZMMWrite,
  FeatureVPOPCNTDQ
]>;
def : KnightsMillProc<"knm">; // TODO Add AVX5124FMAPS/AVX5124VNNIW features

def SKXFeatures : ProcessorFeatures<SKLFeatures.Value, [
  FeatureAVX512,
  FeatureCDI,
  FeatureDQI,
  FeatureBWI,
  FeatureVLX,
  FeaturePKU,
  FeatureCLWB
]>;

class SkylakeServerProc<string Name> : ProcModel<Name, SkylakeServerModel,
                                                 SKXFeatures.Value, [
  ProcIntelSKX
]>;
def : SkylakeServerProc<"skylake-avx512">;
def : SkylakeServerProc<"skx">; // Legacy alias.

def CNLFeatures : ProcessorFeatures<SKXFeatures.Value, [
  FeatureVBMI,
  FeatureIFMA,
  FeatureSHA
]>;

class CannonlakeProc<string Name> : ProcModel<Name, HaswellModel,
                                              CNLFeatures.Value, [
  ProcIntelCNL
]>;
def : CannonlakeProc<"cannonlake">;

// AMD CPUs.

def : Proc<"k6",              [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;
def : Proc<"k6-2",            [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"k6-3",            [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;

foreach P = ["athlon", "athlon-tbird"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, Feature3DNowA, FeatureSlowSHLD]>;
}

foreach P = ["athlon-4", "athlon-xp", "athlon-mp"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE1,
                 Feature3DNowA, FeatureFXSR, FeatureSlowSHLD]>;
}

foreach P = ["k8", "opteron", "athlon64", "athlon-fx"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
                 FeatureFXSR, Feature64Bit, FeatureSlowSHLD]>;
}

foreach P = ["k8-sse3", "opteron-sse3", "athlon64-sse3"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE3, Feature3DNowA,
                 FeatureFXSR, FeatureCMPXCHG16B, FeatureSlowSHLD]>;
}

foreach P = ["amdfam10", "barcelona"] in {
  def : Proc<P, [FeatureX87, FeatureSSE4A, Feature3DNowA, FeatureFXSR,
                 FeatureCMPXCHG16B, FeatureLZCNT, FeaturePOPCNT,
                 FeatureSlowSHLD, FeatureLAHFSAHF]>;
}

// Bobcat
def : Proc<"btver1", [
  FeatureX87,
  FeatureMMX,
  FeatureSSSE3,
  FeatureSSE4A,
  FeatureFXSR,
  FeatureCMPXCHG16B,
  FeaturePRFCHW,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureSlowSHLD,
  FeatureLAHFSAHF
]>;

// Jaguar
def : ProcessorModel<"btver2", BtVer2Model, [
  FeatureX87,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureSSE4A,
  FeatureCMPXCHG16B,
  FeaturePRFCHW,
  FeatureAES,
  FeaturePCLMUL,
  FeatureBMI,
  FeatureF16C,
  FeatureMOVBE,
  FeatureLZCNT,
  FeatureFastLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureFastPartialYMMorZMMWrite
]>;

// Bulldozer
def : Proc<"bdver1", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureSSE4A,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureLWP,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
// Piledriver
def : Proc<"bdver2", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureSSE4A,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;

// Steamroller
def : Proc<"bdver3", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureSSE4A,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureFSGSBase,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;

// Excavator
def : Proc<"bdver4", [
  FeatureX87,
  FeatureMMX,
  FeatureAVX2,
  FeatureFXSR,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureBMI2,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureFSGSBase,
  FeatureLAHFSAHF,
  FeatureMWAITX,
  FeatureMacroFusion
]>;

// Znver1
def: ProcessorModel<"znver1", Znver1Model, [
  FeatureADX,
  FeatureAES,
  FeatureAVX2,
  FeatureBMI,
  FeatureBMI2,
  FeatureCLFLUSHOPT,
  FeatureCLZERO,
  FeatureCMPXCHG16B,
  FeatureF16C,
  FeatureFMA,
  FeatureFSGSBase,
  FeatureFXSR,
  FeatureFastLZCNT,
  FeatureLAHFSAHF,
  FeatureLZCNT,
  FeatureMacroFusion,
  FeatureMMX,
  FeatureMOVBE,
  FeatureMWAITX,
  FeaturePCLMUL,
  FeaturePOPCNT,
  FeaturePRFCHW,
  FeatureRDRAND,
  FeatureRDSEED,
  FeatureSHA,
  FeatureSSE4A,
  FeatureSlowSHLD,
  FeatureX87,
  FeatureXSAVE,
  FeatureXSAVEC,
  FeatureXSAVEOPT,
  FeatureXSAVES]>;

def : Proc<"geode",           [FeatureX87, FeatureSlowUAMem16, Feature3DNowA]>;

def : Proc<"winchip-c6",      [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;
def : Proc<"winchip2",        [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"c3",              [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"c3-2",            [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                               FeatureSSE1, FeatureFXSR]>;

// We also provide a generic 64-bit specific x86 processor model which tries to
// be good for modern chips without enabling instruction set encodings past the
// basic SSE2 and 64-bit ones. It disables slow things from any mainstream and
// modern 64-bit x86 chip, and enables features that are generally beneficial.
//
// We currently use the Sandy Bridge model as the default scheduling model as
// we use it across Nehalem, Westmere, Sandy Bridge, and Ivy Bridge which
// covers a huge swath of x86 processors. If there are specific scheduling
// knobs which need to be tuned differently for AMD chips, we might consider
// forming a common base for them.
def : ProcessorModel<"x86-64", SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE2,
  FeatureFXSR,
  Feature64Bit,
  FeatureSlow3OpsLEA,
  FeatureSlowIncDec,
  FeatureMacroFusion
]>;

//===----------------------------------------------------------------------===//
// Register File Description
//===----------------------------------------------------------------------===//

include "X86RegisterInfo.td"
include "X86RegisterBanks.td"

//===----------------------------------------------------------------------===//
// Instruction Descriptions
//===----------------------------------------------------------------------===//

include "X86InstrInfo.td"

def X86InstrInfo : InstrInfo;

//===----------------------------------------------------------------------===//
// Calling Conventions
//===----------------------------------------------------------------------===//

include "X86CallingConv.td"


//===----------------------------------------------------------------------===//
// Assembly Parser
//===----------------------------------------------------------------------===//

def ATTAsmParserVariant : AsmParserVariant {
  int Variant = 0;

  // Variant name.
  string Name = "att";

  // Discard comments in assembly strings.
  string CommentDelimiter = "#";

  // Recognize hard coded registers.
  string RegisterPrefix = "%";
}

def IntelAsmParserVariant : AsmParserVariant {
  int Variant = 1;

  // Variant name.
  string Name = "intel";

  // Discard comments in assembly strings.
  string CommentDelimiter = ";";

  // Recognize hard coded registers.
  string RegisterPrefix = "";
}

//===----------------------------------------------------------------------===//
// Assembly Printers
//===----------------------------------------------------------------------===//

// The X86 target supports two different syntaxes for emitting machine code.
// This is controlled by the -x86-asm-syntax={att|intel}
def ATTAsmWriter : AsmWriter {
  string AsmWriterClassName  = "ATTInstPrinter";
  int Variant = 0;
}
def IntelAsmWriter : AsmWriter {
  string AsmWriterClassName  = "IntelInstPrinter";
  int Variant = 1;
}

def X86 : Target {
  // Information about the instructions...
  let InstructionSet = X86InstrInfo;
  let AssemblyParserVariants = [ATTAsmParserVariant, IntelAsmParserVariant];
  let AssemblyWriters = [ATTAsmWriter, IntelAsmWriter];
}