llvm.org GIT mirror llvm / release_50 include / llvm / IR / IntrinsicsAMDGPU.td
release_50

Tree @release_50 (Download .tar.gz)

IntrinsicsAMDGPU.td @release_50raw · 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
//===- IntrinsicsAMDGPU.td - Defines AMDGPU intrinsics -----*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines all of the R600-specific intrinsics.
//
//===----------------------------------------------------------------------===//

class AMDGPUReadPreloadRegisterIntrinsic
  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem, IntrSpeculatable]>;

class AMDGPUReadPreloadRegisterIntrinsicNamed<string name>
  : Intrinsic<[llvm_i32_ty], [], [IntrNoMem, IntrSpeculatable]>, GCCBuiltin<name>;

let TargetPrefix = "r600" in {

multiclass AMDGPUReadPreloadRegisterIntrinsic_xyz {
  def _x : AMDGPUReadPreloadRegisterIntrinsic;
  def _y : AMDGPUReadPreloadRegisterIntrinsic;
  def _z : AMDGPUReadPreloadRegisterIntrinsic;
}

multiclass AMDGPUReadPreloadRegisterIntrinsic_xyz_named<string prefix> {
  def _x : AMDGPUReadPreloadRegisterIntrinsicNamed<!strconcat(prefix, "_x")>;
  def _y : AMDGPUReadPreloadRegisterIntrinsicNamed<!strconcat(prefix, "_y")>;
  def _z : AMDGPUReadPreloadRegisterIntrinsicNamed<!strconcat(prefix, "_z")>;
}

defm int_r600_read_global_size : AMDGPUReadPreloadRegisterIntrinsic_xyz_named
                                 <"__builtin_r600_read_global_size">;
defm int_r600_read_ngroups : AMDGPUReadPreloadRegisterIntrinsic_xyz_named
                             <"__builtin_r600_read_ngroups">;
defm int_r600_read_tgid : AMDGPUReadPreloadRegisterIntrinsic_xyz_named
                          <"__builtin_r600_read_tgid">;

defm int_r600_read_local_size : AMDGPUReadPreloadRegisterIntrinsic_xyz;
defm int_r600_read_tidig : AMDGPUReadPreloadRegisterIntrinsic_xyz;

def int_r600_group_barrier : GCCBuiltin<"__builtin_r600_group_barrier">,
  Intrinsic<[], [], [IntrConvergent]>;

// AS 7 is PARAM_I_ADDRESS, used for kernel arguments
def int_r600_implicitarg_ptr :
  GCCBuiltin<"__builtin_r600_implicitarg_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 7>], [],
  [IntrNoMem, IntrSpeculatable]>;

def int_r600_rat_store_typed :
  // 1st parameter: Data
  // 2nd parameter: Index
  // 3rd parameter: Constant RAT ID
  Intrinsic<[], [llvm_v4i32_ty, llvm_v4i32_ty, llvm_i32_ty], []>,
  GCCBuiltin<"__builtin_r600_rat_store_typed">;

def int_r600_recipsqrt_ieee :  Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_r600_recipsqrt_clamped : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_r600_cube : Intrinsic<
  [llvm_v4f32_ty], [llvm_v4f32_ty], [IntrNoMem, IntrSpeculatable]
>;

} // End TargetPrefix = "r600"

let TargetPrefix = "amdgcn" in {

//===----------------------------------------------------------------------===//
// ABI Special Intrinsics
//===----------------------------------------------------------------------===//

defm int_amdgcn_workitem_id : AMDGPUReadPreloadRegisterIntrinsic_xyz;
defm int_amdgcn_workgroup_id : AMDGPUReadPreloadRegisterIntrinsic_xyz_named
                               <"__builtin_amdgcn_workgroup_id">;

def int_amdgcn_dispatch_ptr :
  GCCBuiltin<"__builtin_amdgcn_dispatch_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [],
  [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_queue_ptr :
  GCCBuiltin<"__builtin_amdgcn_queue_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [],
  [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_kernarg_segment_ptr :
  GCCBuiltin<"__builtin_amdgcn_kernarg_segment_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [],
  [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_implicitarg_ptr :
  GCCBuiltin<"__builtin_amdgcn_implicitarg_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [],
  [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_groupstaticsize :
  GCCBuiltin<"__builtin_amdgcn_groupstaticsize">,
  Intrinsic<[llvm_i32_ty], [], [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_dispatch_id :
  GCCBuiltin<"__builtin_amdgcn_dispatch_id">,
  Intrinsic<[llvm_i64_ty], [], [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_implicit_buffer_ptr :
  GCCBuiltin<"__builtin_amdgcn_implicit_buffer_ptr">,
  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [],
  [IntrNoMem, IntrSpeculatable]>;

// Set EXEC to the 64-bit value given.
// This is always moved to the beginning of the basic block.
def int_amdgcn_init_exec : Intrinsic<[],
  [llvm_i64_ty],      // 64-bit literal constant
  [IntrConvergent]>;

// Set EXEC according to a thread count packed in an SGPR input:
//    thread_count = (input >> bitoffset) & 0x7f;
// This is always moved to the beginning of the basic block.
def int_amdgcn_init_exec_from_input : Intrinsic<[],
  [llvm_i32_ty,       // 32-bit SGPR input
   llvm_i32_ty],      // bit offset of the thread count
  [IntrConvergent]>;


//===----------------------------------------------------------------------===//
// Instruction Intrinsics
//===----------------------------------------------------------------------===//

// The first parameter is s_sendmsg immediate (i16),
// the second one is copied to m0
def int_amdgcn_s_sendmsg : GCCBuiltin<"__builtin_amdgcn_s_sendmsg">,
  Intrinsic <[], [llvm_i32_ty, llvm_i32_ty], []>;
def int_amdgcn_s_sendmsghalt : GCCBuiltin<"__builtin_amdgcn_s_sendmsghalt">,
  Intrinsic <[], [llvm_i32_ty, llvm_i32_ty], []>;

def int_amdgcn_s_barrier : GCCBuiltin<"__builtin_amdgcn_s_barrier">,
  Intrinsic<[], [], [IntrConvergent]>;

def int_amdgcn_wave_barrier : GCCBuiltin<"__builtin_amdgcn_wave_barrier">,
  Intrinsic<[], [], [IntrConvergent]>;

def int_amdgcn_s_waitcnt : GCCBuiltin<"__builtin_amdgcn_s_waitcnt">,
  Intrinsic<[], [llvm_i32_ty], []>;

def int_amdgcn_div_scale : Intrinsic<
  // 1st parameter: Numerator
  // 2nd parameter: Denominator
  // 3rd parameter: Constant to select select between first and
  //                second. (0 = first, 1 = second).
  [llvm_anyfloat_ty, llvm_i1_ty],
  [LLVMMatchType<0>, LLVMMatchType<0>, llvm_i1_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_div_fmas : Intrinsic<[llvm_anyfloat_ty],
  [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>, llvm_i1_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_div_fixup : Intrinsic<[llvm_anyfloat_ty],
  [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_trig_preop : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_sin : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cos : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_log_clamp : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_fmul_legacy : GCCBuiltin<"__builtin_amdgcn_fmul_legacy">,
  Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_rcp : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_rcp_legacy : GCCBuiltin<"__builtin_amdgcn_rcp_legacy">,
  Intrinsic<[llvm_float_ty], [llvm_float_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_rsq :  Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_rsq_legacy :  GCCBuiltin<"__builtin_amdgcn_rsq_legacy">,
  Intrinsic<
  [llvm_float_ty], [llvm_float_ty], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_rsq_clamp : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]>;

def int_amdgcn_ldexp : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_frexp_mant : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_frexp_exp : Intrinsic<
  [llvm_anyint_ty], [llvm_anyfloat_ty], [IntrNoMem, IntrSpeculatable]
>;

// v_fract is buggy on SI/CI. It mishandles infinities, may return 1.0
// and always uses rtz, so is not suitable for implementing the OpenCL
// fract function. It should be ok on VI.
def int_amdgcn_fract : Intrinsic<
  [llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cvt_pkrtz : Intrinsic<
  [llvm_v2f16_ty], [llvm_float_ty, llvm_float_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_class : Intrinsic<
  [llvm_i1_ty], [llvm_anyfloat_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_fmed3 : GCCBuiltin<"__builtin_amdgcn_fmed3">,
  Intrinsic<[llvm_anyfloat_ty],
    [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>],
    [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cubeid : GCCBuiltin<"__builtin_amdgcn_cubeid">,
  Intrinsic<[llvm_float_ty],
    [llvm_float_ty, llvm_float_ty, llvm_float_ty],
    [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cubema : GCCBuiltin<"__builtin_amdgcn_cubema">,
  Intrinsic<[llvm_float_ty],
  [llvm_float_ty, llvm_float_ty, llvm_float_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cubesc : GCCBuiltin<"__builtin_amdgcn_cubesc">,
  Intrinsic<[llvm_float_ty],
    [llvm_float_ty, llvm_float_ty, llvm_float_ty],
    [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cubetc : GCCBuiltin<"__builtin_amdgcn_cubetc">,
  Intrinsic<[llvm_float_ty],
    [llvm_float_ty, llvm_float_ty, llvm_float_ty],
    [IntrNoMem, IntrSpeculatable]
>;

// v_ffbh_i32, as opposed to v_ffbh_u32. For v_ffbh_u32, llvm.ctlz
// should be used.
def int_amdgcn_sffbh :
  Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>],
  [IntrNoMem, IntrSpeculatable]
>;


// Fields should mirror atomicrmw
class AMDGPUAtomicIncIntrin : Intrinsic<[llvm_anyint_ty],
  [llvm_anyptr_ty,
  LLVMMatchType<0>,
  llvm_i32_ty, // ordering
  llvm_i32_ty, // scope
  llvm_i1_ty], // isVolatile
  [IntrArgMemOnly, NoCapture<0>]
>;

def int_amdgcn_atomic_inc : AMDGPUAtomicIncIntrin;
def int_amdgcn_atomic_dec : AMDGPUAtomicIncIntrin;

class AMDGPUImageLoad : Intrinsic <
  [llvm_anyfloat_ty], // vdata(VGPR)
  [llvm_anyint_ty,    // vaddr(VGPR)
   llvm_anyint_ty,    // rsrc(SGPR)
   llvm_i32_ty,       // dmask(imm)
   llvm_i1_ty,        // glc(imm)
   llvm_i1_ty,        // slc(imm)
   llvm_i1_ty,        // lwe(imm)
   llvm_i1_ty],       // da(imm)
  [IntrReadMem]>;

def int_amdgcn_image_load : AMDGPUImageLoad;
def int_amdgcn_image_load_mip : AMDGPUImageLoad;
def int_amdgcn_image_getresinfo : AMDGPUImageLoad;

class AMDGPUImageStore : Intrinsic <
  [],
  [llvm_anyfloat_ty,  // vdata(VGPR)
   llvm_anyint_ty,    // vaddr(VGPR)
   llvm_anyint_ty,    // rsrc(SGPR)
   llvm_i32_ty,       // dmask(imm)
   llvm_i1_ty,        // glc(imm)
   llvm_i1_ty,        // slc(imm)
   llvm_i1_ty,        // lwe(imm)
   llvm_i1_ty],       // da(imm)
  []>;

def int_amdgcn_image_store : AMDGPUImageStore;
def int_amdgcn_image_store_mip : AMDGPUImageStore;

class AMDGPUImageSample : Intrinsic <
    [llvm_anyfloat_ty], // vdata(VGPR)
    [llvm_anyfloat_ty,  // vaddr(VGPR)
     llvm_anyint_ty,    // rsrc(SGPR)
     llvm_v4i32_ty,     // sampler(SGPR)
     llvm_i32_ty,       // dmask(imm)
     llvm_i1_ty,        // unorm(imm)
     llvm_i1_ty,        // glc(imm)
     llvm_i1_ty,        // slc(imm)
     llvm_i1_ty,        // lwe(imm)
     llvm_i1_ty],       // da(imm)
     [IntrReadMem]>;

// Basic sample
def int_amdgcn_image_sample : AMDGPUImageSample;
def int_amdgcn_image_sample_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_d : AMDGPUImageSample;
def int_amdgcn_image_sample_d_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_l : AMDGPUImageSample;
def int_amdgcn_image_sample_b : AMDGPUImageSample;
def int_amdgcn_image_sample_b_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_lz : AMDGPUImageSample;
def int_amdgcn_image_sample_cd : AMDGPUImageSample;
def int_amdgcn_image_sample_cd_cl : AMDGPUImageSample;

// Sample with comparison
def int_amdgcn_image_sample_c : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_c_d : AMDGPUImageSample;
def int_amdgcn_image_sample_c_d_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_c_l : AMDGPUImageSample;
def int_amdgcn_image_sample_c_b : AMDGPUImageSample;
def int_amdgcn_image_sample_c_b_cl : AMDGPUImageSample;
def int_amdgcn_image_sample_c_lz : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cd : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cd_cl : AMDGPUImageSample;

// Sample with offsets
def int_amdgcn_image_sample_o : AMDGPUImageSample;
def int_amdgcn_image_sample_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_d_o : AMDGPUImageSample;
def int_amdgcn_image_sample_d_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_l_o : AMDGPUImageSample;
def int_amdgcn_image_sample_b_o : AMDGPUImageSample;
def int_amdgcn_image_sample_b_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_lz_o : AMDGPUImageSample;
def int_amdgcn_image_sample_cd_o : AMDGPUImageSample;
def int_amdgcn_image_sample_cd_cl_o : AMDGPUImageSample;

// Sample with comparison and offsets
def int_amdgcn_image_sample_c_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_d_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_d_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_l_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_b_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_b_cl_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_lz_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cd_o : AMDGPUImageSample;
def int_amdgcn_image_sample_c_cd_cl_o : AMDGPUImageSample;

// Basic gather4
def int_amdgcn_image_gather4 : AMDGPUImageSample;
def int_amdgcn_image_gather4_cl : AMDGPUImageSample;
def int_amdgcn_image_gather4_l : AMDGPUImageSample;
def int_amdgcn_image_gather4_b : AMDGPUImageSample;
def int_amdgcn_image_gather4_b_cl : AMDGPUImageSample;
def int_amdgcn_image_gather4_lz : AMDGPUImageSample;

// Gather4 with comparison
def int_amdgcn_image_gather4_c : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_cl : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_l : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_b : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_b_cl : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_lz : AMDGPUImageSample;

// Gather4 with offsets
def int_amdgcn_image_gather4_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_cl_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_l_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_b_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_b_cl_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_lz_o : AMDGPUImageSample;

// Gather4 with comparison and offsets
def int_amdgcn_image_gather4_c_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_cl_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_l_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_b_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_b_cl_o : AMDGPUImageSample;
def int_amdgcn_image_gather4_c_lz_o : AMDGPUImageSample;

def int_amdgcn_image_getlod : AMDGPUImageSample;

class AMDGPUImageAtomic : Intrinsic <
  [llvm_i32_ty],
  [llvm_i32_ty,       // vdata(VGPR)
   llvm_anyint_ty,    // vaddr(VGPR)
   llvm_v8i32_ty,     // rsrc(SGPR)
   llvm_i1_ty,        // r128(imm)
   llvm_i1_ty,        // da(imm)
   llvm_i1_ty],       // slc(imm)
  []>;

def int_amdgcn_image_atomic_swap : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_add : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_sub : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_smin : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_umin : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_smax : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_umax : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_and : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_or : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_xor : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_inc : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_dec : AMDGPUImageAtomic;
def int_amdgcn_image_atomic_cmpswap : Intrinsic <
  [llvm_i32_ty],
  [llvm_i32_ty,       // src(VGPR)
   llvm_i32_ty,       // cmp(VGPR)
   llvm_anyint_ty,    // vaddr(VGPR)
   llvm_v8i32_ty,     // rsrc(SGPR)
   llvm_i1_ty,        // r128(imm)
   llvm_i1_ty,        // da(imm)
   llvm_i1_ty],       // slc(imm)
  []>;

class AMDGPUBufferLoad : Intrinsic <
  [llvm_anyfloat_ty],
  [llvm_v4i32_ty,     // rsrc(SGPR)
   llvm_i32_ty,       // vindex(VGPR)
   llvm_i32_ty,       // offset(SGPR/VGPR/imm)
   llvm_i1_ty,        // glc(imm)
   llvm_i1_ty],       // slc(imm)
  [IntrReadMem]>;
def int_amdgcn_buffer_load_format : AMDGPUBufferLoad;
def int_amdgcn_buffer_load : AMDGPUBufferLoad;

class AMDGPUBufferStore : Intrinsic <
  [],
  [llvm_anyfloat_ty,  // vdata(VGPR) -- can currently only select f32, v2f32, v4f32
   llvm_v4i32_ty,     // rsrc(SGPR)
   llvm_i32_ty,       // vindex(VGPR)
   llvm_i32_ty,       // offset(SGPR/VGPR/imm)
   llvm_i1_ty,        // glc(imm)
   llvm_i1_ty],       // slc(imm)
  [IntrWriteMem]>;
def int_amdgcn_buffer_store_format : AMDGPUBufferStore;
def int_amdgcn_buffer_store : AMDGPUBufferStore;

def int_amdgcn_tbuffer_load : Intrinsic <
    [llvm_any_ty],    // overloaded for types f32/i32, v2f32/v2i32, v4f32/v4i32
    [llvm_v4i32_ty,   // rsrc(SGPR)
     llvm_i32_ty,     // vindex(VGPR)
     llvm_i32_ty,     // voffset(VGPR)
     llvm_i32_ty,     // soffset(SGPR)
     llvm_i32_ty,     // offset(imm)
     llvm_i32_ty,     // dfmt(imm)
     llvm_i32_ty,     // nfmt(imm)
     llvm_i1_ty,     // glc(imm)
     llvm_i1_ty],    // slc(imm)
    []>;

def int_amdgcn_tbuffer_store : Intrinsic <
    [],
    [llvm_any_ty,    // vdata(VGPR), overloaded for types f32/i32, v2f32/v2i32, v4f32/v4i32
     llvm_v4i32_ty,  // rsrc(SGPR)
     llvm_i32_ty,    // vindex(VGPR)
     llvm_i32_ty,    // voffset(VGPR)
     llvm_i32_ty,    // soffset(SGPR)
     llvm_i32_ty,    // offset(imm)
     llvm_i32_ty,    // dfmt(imm)
     llvm_i32_ty,    // nfmt(imm)
     llvm_i1_ty,     // glc(imm)
     llvm_i1_ty],    // slc(imm)
    []>;

class AMDGPUBufferAtomic : Intrinsic <
  [llvm_i32_ty],
  [llvm_i32_ty,       // vdata(VGPR)
   llvm_v4i32_ty,     // rsrc(SGPR)
   llvm_i32_ty,       // vindex(VGPR)
   llvm_i32_ty,       // offset(SGPR/VGPR/imm)
   llvm_i1_ty],       // slc(imm)
  []>;
def int_amdgcn_buffer_atomic_swap : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_add : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_sub : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_smin : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_umin : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_smax : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_umax : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_and : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_or : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_xor : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_cmpswap : Intrinsic<
  [llvm_i32_ty],
  [llvm_i32_ty,       // src(VGPR)
   llvm_i32_ty,       // cmp(VGPR)
   llvm_v4i32_ty,     // rsrc(SGPR)
   llvm_i32_ty,       // vindex(VGPR)
   llvm_i32_ty,       // offset(SGPR/VGPR/imm)
   llvm_i1_ty],       // slc(imm)
  []>;

// Uses that do not set the done bit should set IntrWriteMem on the
// call site.
def int_amdgcn_exp : Intrinsic <[], [
  llvm_i32_ty,       // tgt,
  llvm_i32_ty,       // en
  llvm_any_ty,       // src0 (f32 or i32)
  LLVMMatchType<0>,  // src1
  LLVMMatchType<0>,  // src2
  LLVMMatchType<0>,  // src3
  llvm_i1_ty,        // done
  llvm_i1_ty         // vm
  ],
  []
>;

// exp with compr bit set.
def int_amdgcn_exp_compr : Intrinsic <[], [
  llvm_i32_ty,       // tgt,
  llvm_i32_ty,       // en
  llvm_anyvector_ty, // src0 (v2f16 or v2i16)
  LLVMMatchType<0>,  // src1
  llvm_i1_ty,        // done
  llvm_i1_ty],       // vm
  []
>;

def int_amdgcn_buffer_wbinvl1_sc :
  GCCBuiltin<"__builtin_amdgcn_buffer_wbinvl1_sc">,
  Intrinsic<[], [], []>;

def int_amdgcn_buffer_wbinvl1 :
  GCCBuiltin<"__builtin_amdgcn_buffer_wbinvl1">,
  Intrinsic<[], [], []>;

def int_amdgcn_s_dcache_inv :
  GCCBuiltin<"__builtin_amdgcn_s_dcache_inv">,
  Intrinsic<[], [], []>;

def int_amdgcn_s_memtime :
  GCCBuiltin<"__builtin_amdgcn_s_memtime">,
  Intrinsic<[llvm_i64_ty], [], []>;

def int_amdgcn_s_sleep :
  GCCBuiltin<"__builtin_amdgcn_s_sleep">,
  Intrinsic<[], [llvm_i32_ty], []> {
}

def int_amdgcn_s_incperflevel :
  GCCBuiltin<"__builtin_amdgcn_s_incperflevel">,
  Intrinsic<[], [llvm_i32_ty], []> {
}

def int_amdgcn_s_decperflevel :
  GCCBuiltin<"__builtin_amdgcn_s_decperflevel">,
  Intrinsic<[], [llvm_i32_ty], []> {
}

def int_amdgcn_s_getreg :
  GCCBuiltin<"__builtin_amdgcn_s_getreg">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty],
  [IntrReadMem, IntrSpeculatable]
>;

// int_amdgcn_s_getpc is provided to allow a specific style of position
// independent code to determine the high part of its address when it is
// known (through convention) that the code and any data of interest does
// not cross a 4Gb address boundary. Use for any other purpose may not
// produce the desired results as optimizations may cause code movement,
// especially as we explicitly use IntrNoMem to allow optimizations.
def int_amdgcn_s_getpc :
  GCCBuiltin<"__builtin_amdgcn_s_getpc">,
  Intrinsic<[llvm_i64_ty], [], [IntrNoMem, IntrSpeculatable]>;

// __builtin_amdgcn_interp_mov <param>, <attr_chan>, <attr>, <m0>
// param values: 0 = P10, 1 = P20, 2 = P0
def int_amdgcn_interp_mov :
  GCCBuiltin<"__builtin_amdgcn_interp_mov">,
  Intrinsic<[llvm_float_ty],
            [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
            [IntrNoMem, IntrSpeculatable]>;

// __builtin_amdgcn_interp_p1 <i>, <attr_chan>, <attr>, <m0>
// This intrinsic reads from lds, but the memory values are constant,
// so it behaves like IntrNoMem.
def int_amdgcn_interp_p1 :
  GCCBuiltin<"__builtin_amdgcn_interp_p1">,
  Intrinsic<[llvm_float_ty],
            [llvm_float_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
            [IntrNoMem, IntrSpeculatable]>;

// __builtin_amdgcn_interp_p2 <p1>, <j>, <attr_chan>, <attr>, <m0>
def int_amdgcn_interp_p2 :
  GCCBuiltin<"__builtin_amdgcn_interp_p2">,
  Intrinsic<[llvm_float_ty],
            [llvm_float_ty, llvm_float_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
            [IntrNoMem, IntrSpeculatable]>;
          // See int_amdgcn_v_interp_p1 for why this is IntrNoMem.

// Pixel shaders only: whether the current pixel is live (i.e. not a helper
// invocation for derivative computation).
def int_amdgcn_ps_live : Intrinsic <
  [llvm_i1_ty],
  [],
  [IntrNoMem]>;

def int_amdgcn_mbcnt_lo :
  GCCBuiltin<"__builtin_amdgcn_mbcnt_lo">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;

def int_amdgcn_mbcnt_hi :
  GCCBuiltin<"__builtin_amdgcn_mbcnt_hi">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;

// llvm.amdgcn.ds.swizzle src offset
def int_amdgcn_ds_swizzle :
  GCCBuiltin<"__builtin_amdgcn_ds_swizzle">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;

def int_amdgcn_ubfe : Intrinsic<[llvm_anyint_ty],
  [LLVMMatchType<0>, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_sbfe : Intrinsic<[llvm_anyint_ty],
  [LLVMMatchType<0>, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_lerp :
  GCCBuiltin<"__builtin_amdgcn_lerp">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_sad_u8 :
  GCCBuiltin<"__builtin_amdgcn_sad_u8">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_msad_u8 :
  GCCBuiltin<"__builtin_amdgcn_msad_u8">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_sad_hi_u8 :
  GCCBuiltin<"__builtin_amdgcn_sad_hi_u8">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_sad_u16 :
  GCCBuiltin<"__builtin_amdgcn_sad_u16">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_qsad_pk_u16_u8 :
  GCCBuiltin<"__builtin_amdgcn_qsad_pk_u16_u8">,
  Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_mqsad_pk_u16_u8 :
  GCCBuiltin<"__builtin_amdgcn_mqsad_pk_u16_u8">,
  Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i32_ty, llvm_i64_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_mqsad_u32_u8 :
  GCCBuiltin<"__builtin_amdgcn_mqsad_u32_u8">,
  Intrinsic<[llvm_v4i32_ty], [llvm_i64_ty, llvm_i32_ty, llvm_v4i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_cvt_pk_u8_f32 :
  GCCBuiltin<"__builtin_amdgcn_cvt_pk_u8_f32">,
  Intrinsic<[llvm_i32_ty], [llvm_float_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_icmp :
  Intrinsic<[llvm_i64_ty], [llvm_anyint_ty, LLVMMatchType<0>, llvm_i32_ty],
            [IntrNoMem, IntrConvergent]>;

def int_amdgcn_fcmp :
  Intrinsic<[llvm_i64_ty], [llvm_anyfloat_ty, LLVMMatchType<0>, llvm_i32_ty],
            [IntrNoMem, IntrConvergent]>;

def int_amdgcn_readfirstlane :
  GCCBuiltin<"__builtin_amdgcn_readfirstlane">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrConvergent]>;

// The lane argument must be uniform across the currently active threads of the
// current wave. Otherwise, the result is undefined.
def int_amdgcn_readlane :
  GCCBuiltin<"__builtin_amdgcn_readlane">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;

def int_amdgcn_alignbit : Intrinsic<[llvm_i32_ty],
  [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

def int_amdgcn_alignbyte : Intrinsic<[llvm_i32_ty],
  [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
  [IntrNoMem, IntrSpeculatable]
>;

//===----------------------------------------------------------------------===//
// CI+ Intrinsics
//===----------------------------------------------------------------------===//

def int_amdgcn_s_dcache_inv_vol :
  GCCBuiltin<"__builtin_amdgcn_s_dcache_inv_vol">,
  Intrinsic<[], [], []>;

def int_amdgcn_buffer_wbinvl1_vol :
  GCCBuiltin<"__builtin_amdgcn_buffer_wbinvl1_vol">,
  Intrinsic<[], [], []>;

//===----------------------------------------------------------------------===//
// VI Intrinsics
//===----------------------------------------------------------------------===//

// llvm.amdgcn.mov.dpp.i32 <src> <dpp_ctrl> <row_mask> <bank_mask> <bound_ctrl>
def int_amdgcn_mov_dpp :
  Intrinsic<[llvm_anyint_ty],
            [LLVMMatchType<0>, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
             llvm_i1_ty], [IntrNoMem, IntrConvergent]>;

def int_amdgcn_s_dcache_wb :
  GCCBuiltin<"__builtin_amdgcn_s_dcache_wb">,
  Intrinsic<[], [], []>;

def int_amdgcn_s_dcache_wb_vol :
  GCCBuiltin<"__builtin_amdgcn_s_dcache_wb_vol">,
  Intrinsic<[], [], []>;

def int_amdgcn_s_memrealtime :
  GCCBuiltin<"__builtin_amdgcn_s_memrealtime">,
  Intrinsic<[llvm_i64_ty], [], []>;

// llvm.amdgcn.ds.permute <index> <src>
def int_amdgcn_ds_permute :
  GCCBuiltin<"__builtin_amdgcn_ds_permute">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;

// llvm.amdgcn.ds.bpermute <index> <src>
def int_amdgcn_ds_bpermute :
  GCCBuiltin<"__builtin_amdgcn_ds_bpermute">,
  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;


//===----------------------------------------------------------------------===//
// Special Intrinsics for backend internal use only. No frontend
// should emit calls to these.
// ===----------------------------------------------------------------------===//
def int_amdgcn_if : Intrinsic<[llvm_i1_ty, llvm_i64_ty],
  [llvm_i1_ty], [IntrConvergent]
>;

def int_amdgcn_else : Intrinsic<[llvm_i1_ty, llvm_i64_ty],
  [llvm_i64_ty], [IntrConvergent]
>;

def int_amdgcn_break : Intrinsic<[llvm_i64_ty],
  [llvm_i64_ty], [IntrNoMem, IntrConvergent]
>;

def int_amdgcn_if_break : Intrinsic<[llvm_i64_ty],
  [llvm_i1_ty, llvm_i64_ty], [IntrNoMem, IntrConvergent]
>;

def int_amdgcn_else_break : Intrinsic<[llvm_i64_ty],
  [llvm_i64_ty, llvm_i64_ty], [IntrNoMem, IntrConvergent]
>;

def int_amdgcn_loop : Intrinsic<[llvm_i1_ty],
  [llvm_i64_ty], [IntrConvergent]
>;

def int_amdgcn_end_cf : Intrinsic<[], [llvm_i64_ty], [IntrConvergent]>;

// Represent unreachable in a divergent region.
def int_amdgcn_unreachable : Intrinsic<[], [], [IntrConvergent]>;

// Emit 2.5 ulp, no denormal division. Should only be inserted by
// pass based on !fpmath metadata.
def int_amdgcn_fdiv_fast : Intrinsic<
  [llvm_float_ty], [llvm_float_ty, llvm_float_ty],
  [IntrNoMem, IntrSpeculatable]
>;
}