llvm.org GIT mirror llvm / 0392724 lib / Target / AMDGPU / SIDefines.h
0392724

Tree @0392724 (Download .tar.gz)

SIDefines.h @0392724raw · 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
//===-- SIDefines.h - SI Helper Macros ----------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
/// \file
//===----------------------------------------------------------------------===//

#include "llvm/MC/MCInstrDesc.h"

#ifndef LLVM_LIB_TARGET_AMDGPU_SIDEFINES_H
#define LLVM_LIB_TARGET_AMDGPU_SIDEFINES_H

namespace llvm {

namespace SIInstrFlags {
// This needs to be kept in sync with the field bits in InstSI.
enum : uint64_t {
  // Low bits - basic encoding information.
  SALU = 1 << 0,
  VALU = 1 << 1,

  // SALU instruction formats.
  SOP1 = 1 << 2,
  SOP2 = 1 << 3,
  SOPC = 1 << 4,
  SOPK = 1 << 5,
  SOPP = 1 << 6,

  // VALU instruction formats.
  VOP1 = 1 << 7,
  VOP2 = 1 << 8,
  VOPC = 1 << 9,

 // TODO: Should this be spilt into VOP3 a and b?
  VOP3 = 1 << 10,
  VOP3P = 1 << 12,

  VINTRP = 1 << 13,
  SDWA = 1 << 14,
  DPP = 1 << 15,

  // Memory instruction formats.
  MUBUF = 1 << 16,
  MTBUF = 1 << 17,
  SMRD = 1 << 18,
  MIMG = 1 << 19,
  EXP = 1 << 20,
  FLAT = 1 << 21,
  DS = 1 << 22,

  // Pseudo instruction formats.
  VGPRSpill = 1 << 23,
  SGPRSpill = 1 << 24,

  // High bits - other information.
  VM_CNT = UINT64_C(1) << 32,
  EXP_CNT = UINT64_C(1) << 33,
  LGKM_CNT = UINT64_C(1) << 34,

  WQM = UINT64_C(1) << 35,
  DisableWQM = UINT64_C(1) << 36,
  Gather4 = UINT64_C(1) << 37,
  SOPK_ZEXT = UINT64_C(1) << 38,
  SCALAR_STORE = UINT64_C(1) << 39,
  FIXED_SIZE = UINT64_C(1) << 40,
  VOPAsmPrefer32Bit = UINT64_C(1) << 41,
  VOP3_OPSEL = UINT64_C(1) << 42,
  maybeAtomic = UINT64_C(1) << 43,
  renamedInGFX9 = UINT64_C(1) << 44,

  // Is a clamp on FP type.
  FPClamp = UINT64_C(1) << 45,

  // Is an integer clamp
  IntClamp = UINT64_C(1) << 46,

  // Clamps lo component of register.
  ClampLo = UINT64_C(1) << 47,

  // Clamps hi component of register.
  // ClampLo and ClampHi set for packed clamp.
  ClampHi = UINT64_C(1) << 48,

  // Is a packed VOP3P instruction.
  IsPacked = UINT64_C(1) << 49,

  // Is a D16 buffer instruction.
  D16Buf = UINT64_C(1) << 50,

  // FLAT instruction accesses FLAT_GLBL or FLAT_SCRATCH segment.
  IsNonFlatSeg = UINT64_C(1) << 51,

  // Uses floating point double precision rounding mode
  FPDPRounding = UINT64_C(1) << 52,

  // Instruction is FP atomic.
  FPAtomic = UINT64_C(1) << 53
};

// v_cmp_class_* etc. use a 10-bit mask for what operation is checked.
// The result is true if any of these tests are true.
enum ClassFlags : unsigned {
  S_NAN = 1 << 0,        // Signaling NaN
  Q_NAN = 1 << 1,        // Quiet NaN
  N_INFINITY = 1 << 2,   // Negative infinity
  N_NORMAL = 1 << 3,     // Negative normal
  N_SUBNORMAL = 1 << 4,  // Negative subnormal
  N_ZERO = 1 << 5,       // Negative zero
  P_ZERO = 1 << 6,       // Positive zero
  P_SUBNORMAL = 1 << 7,  // Positive subnormal
  P_NORMAL = 1 << 8,     // Positive normal
  P_INFINITY = 1 << 9    // Positive infinity
};
}

namespace AMDGPU {
  enum OperandType : unsigned {
    /// Operands with register or 32-bit immediate
    OPERAND_REG_IMM_INT32 = MCOI::OPERAND_FIRST_TARGET,
    OPERAND_REG_IMM_INT64,
    OPERAND_REG_IMM_INT16,
    OPERAND_REG_IMM_FP32,
    OPERAND_REG_IMM_FP64,
    OPERAND_REG_IMM_FP16,
    OPERAND_REG_IMM_V2FP16,
    OPERAND_REG_IMM_V2INT16,

    /// Operands with register or inline constant
    OPERAND_REG_INLINE_C_INT16,
    OPERAND_REG_INLINE_C_INT32,
    OPERAND_REG_INLINE_C_INT64,
    OPERAND_REG_INLINE_C_FP16,
    OPERAND_REG_INLINE_C_FP32,
    OPERAND_REG_INLINE_C_FP64,
    OPERAND_REG_INLINE_C_V2FP16,
    OPERAND_REG_INLINE_C_V2INT16,

    OPERAND_REG_IMM_FIRST = OPERAND_REG_IMM_INT32,
    OPERAND_REG_IMM_LAST = OPERAND_REG_IMM_V2INT16,

    OPERAND_REG_INLINE_C_FIRST = OPERAND_REG_INLINE_C_INT16,
    OPERAND_REG_INLINE_C_LAST = OPERAND_REG_INLINE_C_V2INT16,

    OPERAND_SRC_FIRST = OPERAND_REG_IMM_INT32,
    OPERAND_SRC_LAST = OPERAND_REG_INLINE_C_LAST,

    // Operand for source modifiers for VOP instructions
    OPERAND_INPUT_MODS,

    // Operand for SDWA instructions
    OPERAND_SDWA_VOPC_DST,

    /// Operand with 32-bit immediate that uses the constant bus.
    OPERAND_KIMM32,
    OPERAND_KIMM16
  };
}

// Input operand modifiers bit-masks
// NEG and SEXT share same bit-mask because they can't be set simultaneously.
namespace SISrcMods {
  enum : unsigned {
   NEG = 1 << 0,   // Floating-point negate modifier
   ABS = 1 << 1,   // Floating-point absolute modifier
   SEXT = 1 << 0,  // Integer sign-extend modifier
   NEG_HI = ABS,   // Floating-point negate high packed component modifier.
   OP_SEL_0 = 1 << 2,
   OP_SEL_1 = 1 << 3,
   DST_OP_SEL = 1 << 3 // VOP3 dst op_sel (share mask with OP_SEL_1)
  };
}

namespace SIOutMods {
  enum : unsigned {
    NONE = 0,
    MUL2 = 1,
    MUL4 = 2,
    DIV2 = 3
  };
}

namespace AMDGPU {
namespace VGPRIndexMode {

enum Id : unsigned { // id of symbolic names
  ID_SRC0 = 0,
  ID_SRC1,
  ID_SRC2,
  ID_DST,

  ID_MIN = ID_SRC0,
  ID_MAX = ID_DST
};

enum EncBits : unsigned {
  OFF = 0,
  SRC0_ENABLE = 1 << ID_SRC0,
  SRC1_ENABLE = 1 << ID_SRC1,
  SRC2_ENABLE = 1 << ID_SRC2,
  DST_ENABLE = 1 << ID_DST,
  ENABLE_MASK = SRC0_ENABLE | SRC1_ENABLE | SRC2_ENABLE | DST_ENABLE
};

} // namespace VGPRIndexMode
} // namespace AMDGPU

namespace AMDGPUAsmVariants {
  enum : unsigned {
    DEFAULT = 0,
    VOP3 = 1,
    SDWA = 2,
    SDWA9 = 3,
    DPP = 4
  };
}

namespace AMDGPU {
namespace EncValues { // Encoding values of enum9/8/7 operands

enum : unsigned {
  SGPR_MIN = 0,
  SGPR_MAX_SI = 101,
  SGPR_MAX_GFX10 = 105,
  TTMP_VI_MIN = 112,
  TTMP_VI_MAX = 123,
  TTMP_GFX9_GFX10_MIN = 108,
  TTMP_GFX9_GFX10_MAX = 123,
  INLINE_INTEGER_C_MIN = 128,
  INLINE_INTEGER_C_POSITIVE_MAX = 192, // 64
  INLINE_INTEGER_C_MAX = 208,
  INLINE_FLOATING_C_MIN = 240,
  INLINE_FLOATING_C_MAX = 248,
  LITERAL_CONST = 255,
  VGPR_MIN = 256,
  VGPR_MAX = 511
};

} // namespace EncValues
} // namespace AMDGPU

namespace AMDGPU {
namespace SendMsg { // Encoding of SIMM16 used in s_sendmsg* insns.

enum Id { // Message ID, width(4) [3:0].
  ID_UNKNOWN_ = -1,
  ID_INTERRUPT = 1,
  ID_GS,
  ID_GS_DONE,
  ID_GS_ALLOC_REQ = 9,
  ID_SYSMSG = 15,
  ID_GAPS_LAST_, // Indicate that sequence has gaps.
  ID_GAPS_FIRST_ = ID_INTERRUPT,
  ID_SHIFT_ = 0,
  ID_WIDTH_ = 4,
  ID_MASK_ = (((1 << ID_WIDTH_) - 1) << ID_SHIFT_)
};

enum Op { // Both GS and SYS operation IDs.
  OP_UNKNOWN_ = -1,
  OP_SHIFT_ = 4,
  OP_NONE_ = 0,
  // Bits used for operation encoding
  OP_WIDTH_ = 3,
  OP_MASK_ = (((1 << OP_WIDTH_) - 1) << OP_SHIFT_),
  // GS operations are encoded in bits 5:4
  OP_GS_NOP = 0,
  OP_GS_CUT,
  OP_GS_EMIT,
  OP_GS_EMIT_CUT,
  OP_GS_LAST_,
  OP_GS_FIRST_ = OP_GS_NOP,
  // SYS operations are encoded in bits 6:4
  OP_SYS_ECC_ERR_INTERRUPT = 1,
  OP_SYS_REG_RD,
  OP_SYS_HOST_TRAP_ACK,
  OP_SYS_TTRACE_PC,
  OP_SYS_LAST_,
  OP_SYS_FIRST_ = OP_SYS_ECC_ERR_INTERRUPT,
};

enum StreamId : unsigned { // Stream ID, (2) [9:8].
  STREAM_ID_NONE_ = 0,
  STREAM_ID_DEFAULT_ = 0,
  STREAM_ID_LAST_ = 4,
  STREAM_ID_FIRST_ = STREAM_ID_DEFAULT_,
  STREAM_ID_SHIFT_ = 8,
  STREAM_ID_WIDTH_=  2,
  STREAM_ID_MASK_ = (((1 << STREAM_ID_WIDTH_) - 1) << STREAM_ID_SHIFT_)
};

} // namespace SendMsg

namespace Hwreg { // Encoding of SIMM16 used in s_setreg/getreg* insns.

enum Id { // HwRegCode, (6) [5:0]
  ID_UNKNOWN_ = -1,
  ID_SYMBOLIC_FIRST_ = 1, // There are corresponding symbolic names defined.
  ID_MODE = 1,
  ID_STATUS = 2,
  ID_TRAPSTS = 3,
  ID_HW_ID = 4,
  ID_GPR_ALLOC = 5,
  ID_LDS_ALLOC = 6,
  ID_IB_STS = 7,
  ID_MEM_BASES = 15,
  ID_SYMBOLIC_FIRST_GFX9_ = ID_MEM_BASES,
  ID_TBA_LO = 16,
  ID_SYMBOLIC_FIRST_GFX10_ = ID_TBA_LO,
  ID_TBA_HI = 17,
  ID_TMA_LO = 18,
  ID_TMA_HI = 19,
  ID_FLAT_SCR_LO = 20,
  ID_FLAT_SCR_HI = 21,
  ID_XNACK_MASK = 22,
  ID_POPS_PACKER = 25,
  ID_SYMBOLIC_LAST_ = 26,
  ID_SHIFT_ = 0,
  ID_WIDTH_ = 6,
  ID_MASK_ = (((1 << ID_WIDTH_) - 1) << ID_SHIFT_)
};

enum Offset : unsigned { // Offset, (5) [10:6]
  OFFSET_DEFAULT_ = 0,
  OFFSET_SHIFT_ = 6,
  OFFSET_WIDTH_ = 5,
  OFFSET_MASK_ = (((1 << OFFSET_WIDTH_) - 1) << OFFSET_SHIFT_),

  OFFSET_MEM_VIOL = 8,

  OFFSET_SRC_SHARED_BASE = 16,
  OFFSET_SRC_PRIVATE_BASE = 0
};

enum WidthMinusOne : unsigned { // WidthMinusOne, (5) [15:11]
  WIDTH_M1_DEFAULT_ = 31,
  WIDTH_M1_SHIFT_ = 11,
  WIDTH_M1_WIDTH_ = 5,
  WIDTH_M1_MASK_ = (((1 << WIDTH_M1_WIDTH_) - 1) << WIDTH_M1_SHIFT_),

  WIDTH_M1_SRC_SHARED_BASE = 15,
  WIDTH_M1_SRC_PRIVATE_BASE = 15
};

// Some values from WidthMinusOne mapped into Width domain.
enum Width : unsigned {
  WIDTH_DEFAULT_ = WIDTH_M1_DEFAULT_ + 1,
};

} // namespace Hwreg

namespace Swizzle { // Encoding of swizzle macro used in ds_swizzle_b32.

enum Id : unsigned { // id of symbolic names
  ID_QUAD_PERM = 0,
  ID_BITMASK_PERM,
  ID_SWAP,
  ID_REVERSE,
  ID_BROADCAST
};

enum EncBits : unsigned {

  // swizzle mode encodings

  QUAD_PERM_ENC         = 0x8000,
  QUAD_PERM_ENC_MASK    = 0xFF00,

  BITMASK_PERM_ENC      = 0x0000,
  BITMASK_PERM_ENC_MASK = 0x8000,

  // QUAD_PERM encodings

  LANE_MASK             = 0x3,
  LANE_MAX              = LANE_MASK,
  LANE_SHIFT            = 2,
  LANE_NUM              = 4,

  // BITMASK_PERM encodings

  BITMASK_MASK          = 0x1F,
  BITMASK_MAX           = BITMASK_MASK,
  BITMASK_WIDTH         = 5,

  BITMASK_AND_SHIFT     = 0,
  BITMASK_OR_SHIFT      = 5,
  BITMASK_XOR_SHIFT     = 10
};

} // namespace Swizzle

namespace SDWA {

enum SdwaSel : unsigned {
  BYTE_0 = 0,
  BYTE_1 = 1,
  BYTE_2 = 2,
  BYTE_3 = 3,
  WORD_0 = 4,
  WORD_1 = 5,
  DWORD = 6,
};

enum DstUnused : unsigned {
  UNUSED_PAD = 0,
  UNUSED_SEXT = 1,
  UNUSED_PRESERVE = 2,
};

enum SDWA9EncValues : unsigned {
  SRC_SGPR_MASK = 0x100,
  SRC_VGPR_MASK = 0xFF,
  VOPC_DST_VCC_MASK = 0x80,
  VOPC_DST_SGPR_MASK = 0x7F,

  SRC_VGPR_MIN = 0,
  SRC_VGPR_MAX = 255,
  SRC_SGPR_MIN = 256,
  SRC_SGPR_MAX_SI = 357,
  SRC_SGPR_MAX_GFX10 = 361,
  SRC_TTMP_MIN = 364,
  SRC_TTMP_MAX = 379,
};

} // namespace SDWA

namespace DPP {

enum DppCtrl : unsigned {
  QUAD_PERM_FIRST   = 0,
  QUAD_PERM_LAST    = 0xFF,
  DPP_UNUSED1       = 0x100,
  ROW_SHL0          = 0x100,
  ROW_SHL_FIRST     = 0x101,
  ROW_SHL_LAST      = 0x10F,
  DPP_UNUSED2       = 0x110,
  ROW_SHR0          = 0x110,
  ROW_SHR_FIRST     = 0x111,
  ROW_SHR_LAST      = 0x11F,
  DPP_UNUSED3       = 0x120,
  ROW_ROR0          = 0x120,
  ROW_ROR_FIRST     = 0x121,
  ROW_ROR_LAST      = 0x12F,
  WAVE_SHL1         = 0x130,
  DPP_UNUSED4_FIRST = 0x131,
  DPP_UNUSED4_LAST  = 0x133,
  WAVE_ROL1         = 0x134,
  DPP_UNUSED5_FIRST = 0x135,
  DPP_UNUSED5_LAST  = 0x137,
  WAVE_SHR1         = 0x138,
  DPP_UNUSED6_FIRST = 0x139,
  DPP_UNUSED6_LAST  = 0x13B,
  WAVE_ROR1         = 0x13C,
  DPP_UNUSED7_FIRST = 0x13D,
  DPP_UNUSED7_LAST  = 0x13F,
  ROW_MIRROR        = 0x140,
  ROW_HALF_MIRROR   = 0x141,
  BCAST15           = 0x142,
  BCAST31           = 0x143,
  DPP_UNUSED8_FIRST = 0x144,
  DPP_UNUSED8_LAST  = 0x14F,
  ROW_SHARE_FIRST   = 0x150,
  ROW_SHARE_LAST    = 0x15F,
  ROW_XMASK_FIRST   = 0x160,
  ROW_XMASK_LAST    = 0x16F,
  DPP_LAST          = ROW_XMASK_LAST
};

enum DppFiMode {
  DPP_FI_0  = 0,
  DPP_FI_1  = 1,
  DPP8_FI_0 = 0xE9,
  DPP8_FI_1 = 0xEA,
};

} // namespace DPP
} // namespace AMDGPU

#define R_00B028_SPI_SHADER_PGM_RSRC1_PS                                0x00B028
#define R_00B02C_SPI_SHADER_PGM_RSRC2_PS                                0x00B02C
#define   S_00B02C_EXTRA_LDS_SIZE(x)                                  (((x) & 0xFF) << 8)
#define R_00B128_SPI_SHADER_PGM_RSRC1_VS                                0x00B128
#define R_00B228_SPI_SHADER_PGM_RSRC1_GS                                0x00B228
#define R_00B328_SPI_SHADER_PGM_RSRC1_ES                                0x00B328
#define R_00B428_SPI_SHADER_PGM_RSRC1_HS                                0x00B428
#define R_00B528_SPI_SHADER_PGM_RSRC1_LS                                0x00B528
#define R_00B848_COMPUTE_PGM_RSRC1                                      0x00B848
#define   S_00B028_VGPRS(x)                                           (((x) & 0x3F) << 0)
#define   S_00B028_SGPRS(x)                                           (((x) & 0x0F) << 6)

#define R_00B84C_COMPUTE_PGM_RSRC2                                      0x00B84C
#define   S_00B84C_SCRATCH_EN(x)                                      (((x) & 0x1) << 0)
#define   G_00B84C_SCRATCH_EN(x)                                      (((x) >> 0) & 0x1)
#define   C_00B84C_SCRATCH_EN                                         0xFFFFFFFE
#define   S_00B84C_USER_SGPR(x)                                       (((x) & 0x1F) << 1)
#define   G_00B84C_USER_SGPR(x)                                       (((x) >> 1) & 0x1F)
#define   C_00B84C_USER_SGPR                                          0xFFFFFFC1
#define   S_00B84C_TRAP_HANDLER(x)                                    (((x) & 0x1) << 6)
#define   G_00B84C_TRAP_HANDLER(x)                                    (((x) >> 6) & 0x1)
#define   C_00B84C_TRAP_HANDLER                                       0xFFFFFFBF
#define   S_00B84C_TGID_X_EN(x)                                       (((x) & 0x1) << 7)
#define   G_00B84C_TGID_X_EN(x)                                       (((x) >> 7) & 0x1)
#define   C_00B84C_TGID_X_EN                                          0xFFFFFF7F
#define   S_00B84C_TGID_Y_EN(x)                                       (((x) & 0x1) << 8)
#define   G_00B84C_TGID_Y_EN(x)                                       (((x) >> 8) & 0x1)
#define   C_00B84C_TGID_Y_EN                                          0xFFFFFEFF
#define   S_00B84C_TGID_Z_EN(x)                                       (((x) & 0x1) << 9)
#define   G_00B84C_TGID_Z_EN(x)                                       (((x) >> 9) & 0x1)
#define   C_00B84C_TGID_Z_EN                                          0xFFFFFDFF
#define   S_00B84C_TG_SIZE_EN(x)                                      (((x) & 0x1) << 10)
#define   G_00B84C_TG_SIZE_EN(x)                                      (((x) >> 10) & 0x1)
#define   C_00B84C_TG_SIZE_EN                                         0xFFFFFBFF
#define   S_00B84C_TIDIG_COMP_CNT(x)                                  (((x) & 0x03) << 11)
#define   G_00B84C_TIDIG_COMP_CNT(x)                                  (((x) >> 11) & 0x03)
#define   C_00B84C_TIDIG_COMP_CNT                                     0xFFFFE7FF
/* CIK */
#define   S_00B84C_EXCP_EN_MSB(x)                                     (((x) & 0x03) << 13)
#define   G_00B84C_EXCP_EN_MSB(x)                                     (((x) >> 13) & 0x03)
#define   C_00B84C_EXCP_EN_MSB                                        0xFFFF9FFF
/*     */
#define   S_00B84C_LDS_SIZE(x)                                        (((x) & 0x1FF) << 15)
#define   G_00B84C_LDS_SIZE(x)                                        (((x) >> 15) & 0x1FF)
#define   C_00B84C_LDS_SIZE                                           0xFF007FFF
#define   S_00B84C_EXCP_EN(x)                                         (((x) & 0x7F) << 24)
#define   G_00B84C_EXCP_EN(x)                                         (((x) >> 24) & 0x7F)
#define   C_00B84C_EXCP_EN

#define R_0286CC_SPI_PS_INPUT_ENA                                       0x0286CC
#define R_0286D0_SPI_PS_INPUT_ADDR                                      0x0286D0

#define R_00B848_COMPUTE_PGM_RSRC1                                      0x00B848
#define   S_00B848_VGPRS(x)                                           (((x) & 0x3F) << 0)
#define   G_00B848_VGPRS(x)                                           (((x) >> 0) & 0x3F)
#define   C_00B848_VGPRS                                              0xFFFFFFC0
#define   S_00B848_SGPRS(x)                                           (((x) & 0x0F) << 6)
#define   G_00B848_SGPRS(x)                                           (((x) >> 6) & 0x0F)
#define   C_00B848_SGPRS                                              0xFFFFFC3F
#define   S_00B848_PRIORITY(x)                                        (((x) & 0x03) << 10)
#define   G_00B848_PRIORITY(x)                                        (((x) >> 10) & 0x03)
#define   C_00B848_PRIORITY                                           0xFFFFF3FF
#define   S_00B848_FLOAT_MODE(x)                                      (((x) & 0xFF) << 12)
#define   G_00B848_FLOAT_MODE(x)                                      (((x) >> 12) & 0xFF)
#define   C_00B848_FLOAT_MODE                                         0xFFF00FFF
#define   S_00B848_PRIV(x)                                            (((x) & 0x1) << 20)
#define   G_00B848_PRIV(x)                                            (((x) >> 20) & 0x1)
#define   C_00B848_PRIV                                               0xFFEFFFFF
#define   S_00B848_DX10_CLAMP(x)                                      (((x) & 0x1) << 21)
#define   G_00B848_DX10_CLAMP(x)                                      (((x) >> 21) & 0x1)
#define   C_00B848_DX10_CLAMP                                         0xFFDFFFFF
#define   S_00B848_DEBUG_MODE(x)                                      (((x) & 0x1) << 22)
#define   G_00B848_DEBUG_MODE(x)                                      (((x) >> 22) & 0x1)
#define   C_00B848_DEBUG_MODE                                         0xFFBFFFFF
#define   S_00B848_IEEE_MODE(x)                                       (((x) & 0x1) << 23)
#define   G_00B848_IEEE_MODE(x)                                       (((x) >> 23) & 0x1)
#define   C_00B848_IEEE_MODE                                          0xFF7FFFFF
#define   S_00B848_WGP_MODE(x)                                        (((x) & 0x1) << 29)
#define   G_00B848_WGP_MODE(x)                                        (((x) >> 29) & 0x1)
#define   C_00B848_WGP_MODE                                           0xDFFFFFFF
#define   S_00B848_MEM_ORDERED(x)                                     (((x) & 0x1) << 30)
#define   G_00B848_MEM_ORDERED(x)                                     (((x) >> 30) & 0x1)
#define   C_00B848_MEM_ORDERED                                        0xBFFFFFFF
#define   S_00B848_FWD_PROGRESS(x)                                    (((x) & 0x1) << 31)
#define   G_00B848_FWD_PROGRESS(x)                                    (((x) >> 31) & 0x1)
#define   C_00B848_FWD_PROGRESS                                       0x7FFFFFFF


// Helpers for setting FLOAT_MODE
#define FP_ROUND_ROUND_TO_NEAREST 0
#define FP_ROUND_ROUND_TO_INF 1
#define FP_ROUND_ROUND_TO_NEGINF 2
#define FP_ROUND_ROUND_TO_ZERO 3

// Bits 3:0 control rounding mode. 1:0 control single precision, 3:2 double
// precision.
#define FP_ROUND_MODE_SP(x) ((x) & 0x3)
#define FP_ROUND_MODE_DP(x) (((x) & 0x3) << 2)

#define FP_DENORM_FLUSH_IN_FLUSH_OUT 0
#define FP_DENORM_FLUSH_OUT 1
#define FP_DENORM_FLUSH_IN 2
#define FP_DENORM_FLUSH_NONE 3


// Bits 7:4 control denormal handling. 5:4 control single precision, 6:7 double
// precision.
#define FP_DENORM_MODE_SP(x) (((x) & 0x3) << 4)
#define FP_DENORM_MODE_DP(x) (((x) & 0x3) << 6)

#define R_00B860_COMPUTE_TMPRING_SIZE                                   0x00B860
#define   S_00B860_WAVESIZE(x)                                        (((x) & 0x1FFF) << 12)

#define R_0286E8_SPI_TMPRING_SIZE                                       0x0286E8
#define   S_0286E8_WAVESIZE(x)                                        (((x) & 0x1FFF) << 12)

#define R_028B54_VGT_SHADER_STAGES_EN                                 0x028B54
#define   S_028B54_HS_W32_EN(x)                                       (((x) & 0x1) << 21)
#define   S_028B54_GS_W32_EN(x)                                       (((x) & 0x1) << 22)
#define   S_028B54_VS_W32_EN(x)                                       (((x) & 0x1) << 23)
#define R_0286D8_SPI_PS_IN_CONTROL                                    0x0286D8
#define   S_0286D8_PS_W32_EN(x)                                       (((x) & 0x1) << 15)
#define R_00B800_COMPUTE_DISPATCH_INITIATOR                           0x00B800
#define   S_00B800_CS_W32_EN(x)                                       (((x) & 0x1) << 15)

#define R_SPILLED_SGPRS         0x4
#define R_SPILLED_VGPRS         0x8
} // End namespace llvm

#endif