llvm.org GIT mirror llvm / release_39 lib / Target / AMDGPU / SIRegisterInfo.td
release_39

Tree @release_39 (Download .tar.gz)

SIRegisterInfo.td @release_39raw · 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
//===-- SIRegisterInfo.td - SI Register defs ---------------*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
//  Declarations that describe the SI registers
//===----------------------------------------------------------------------===//
class SIReg <string n, bits<16> regIdx = 0> : Register<n>,
  DwarfRegNum<[!cast<int>(HWEncoding)]> {
  let Namespace = "AMDGPU";

  // This is the not yet the complete register encoding. An additional
  // bit is set for VGPRs.
  let HWEncoding = regIdx;
}

// Special Registers
def VCC_LO : SIReg<"vcc_lo", 106>;
def VCC_HI : SIReg<"vcc_hi", 107>;

// VCC for 64-bit instructions
def VCC : RegisterWithSubRegs<"vcc", [VCC_LO, VCC_HI]>,
          DwarfRegAlias<VCC_LO> {
  let Namespace = "AMDGPU";
  let SubRegIndices = [sub0, sub1];
  let HWEncoding = 106;
}

def EXEC_LO : SIReg<"exec_lo", 126>;
def EXEC_HI : SIReg<"exec_hi", 127>;

def EXEC : RegisterWithSubRegs<"EXEC", [EXEC_LO, EXEC_HI]>,
           DwarfRegAlias<EXEC_LO> {
  let Namespace = "AMDGPU";
  let SubRegIndices = [sub0, sub1];
  let HWEncoding = 126;
}

def SCC : SIReg<"scc", 253>;
def M0 : SIReg <"m0", 124>;

// Trap handler registers
def TBA_LO : SIReg<"tba_lo", 108>;
def TBA_HI : SIReg<"tba_hi", 109>;

def TBA : RegisterWithSubRegs<"tba", [TBA_LO, TBA_HI]>,
          DwarfRegAlias<TBA_LO> {
  let Namespace = "AMDGPU";
  let SubRegIndices = [sub0, sub1];
  let HWEncoding = 108;
}

def TMA_LO : SIReg<"tma_lo", 110>;
def TMA_HI : SIReg<"tma_hi", 111>;

def TMA : RegisterWithSubRegs<"tma", [TMA_LO, TMA_HI]>,
          DwarfRegAlias<TMA_LO> {
  let Namespace = "AMDGPU";
  let SubRegIndices = [sub0, sub1];
  let HWEncoding = 110;
}

def TTMP0 : SIReg <"ttmp0", 112>;
def TTMP1 : SIReg <"ttmp1", 113>;
def TTMP2 : SIReg <"ttmp2", 114>;
def TTMP3 : SIReg <"ttmp3", 115>;
def TTMP4 : SIReg <"ttmp4", 116>;
def TTMP5 : SIReg <"ttmp5", 117>;
def TTMP6 : SIReg <"ttmp6", 118>;
def TTMP7 : SIReg <"ttmp7", 119>;
def TTMP8 : SIReg <"ttmp8", 120>;
def TTMP9 : SIReg <"ttmp9", 121>;
def TTMP10 : SIReg <"ttmp10", 122>;
def TTMP11 : SIReg <"ttmp11", 123>;

multiclass FLAT_SCR_LOHI_m <string n, bits<16> ci_e, bits<16> vi_e> {
  def _ci : SIReg<n, ci_e>;
  def _vi : SIReg<n, vi_e>;
  def "" : SIReg<"", 0>;
}

class FlatReg <Register lo, Register hi, bits<16> encoding> :
    RegisterWithSubRegs<"flat_scratch", [lo, hi]>,
    DwarfRegAlias<lo> {
  let Namespace = "AMDGPU";
  let SubRegIndices = [sub0, sub1];
  let HWEncoding = encoding;
}

defm FLAT_SCR_LO : FLAT_SCR_LOHI_m<"flat_scratch_lo", 104, 102>; // Offset in units of 256-bytes.
defm FLAT_SCR_HI : FLAT_SCR_LOHI_m<"flat_scratch_hi", 105, 103>; // Size is the per-thread scratch size, in bytes.

def FLAT_SCR_ci : FlatReg<FLAT_SCR_LO_ci, FLAT_SCR_HI_ci, 104>;
def FLAT_SCR_vi : FlatReg<FLAT_SCR_LO_vi, FLAT_SCR_HI_vi, 102>;
def FLAT_SCR : FlatReg<FLAT_SCR_LO, FLAT_SCR_HI, 0>;

// SGPR registers
foreach Index = 0-103 in {
  def SGPR#Index : SIReg <"SGPR"#Index, Index>;
}

// VGPR registers
foreach Index = 0-255 in {
  def VGPR#Index : SIReg <"VGPR"#Index, Index> {
    let HWEncoding{8} = 1;
  }
}

//===----------------------------------------------------------------------===//
//  Groupings using register classes and tuples
//===----------------------------------------------------------------------===//

def SCC_CLASS : RegisterClass<"AMDGPU", [i1], 1, (add SCC)> {
  let CopyCost = -1;
  let isAllocatable = 0;
}

// TODO: Do we need to set DwarfRegAlias on register tuples?

// SGPR 32-bit registers
def SGPR_32 : RegisterClass<"AMDGPU", [i32, f32], 32,
                            (add (sequence "SGPR%u", 0, 103))> {
  let AllocationPriority = 1;
}

// SGPR 64-bit registers
def SGPR_64Regs : RegisterTuples<[sub0, sub1],
                             [(add (decimate SGPR_32, 2)),
                              (add (decimate (shl SGPR_32, 1), 2))]>;

// SGPR 128-bit registers
def SGPR_128Regs : RegisterTuples<[sub0, sub1, sub2, sub3],
                              [(add (decimate SGPR_32, 4)),
                               (add (decimate (shl SGPR_32, 1), 4)),
                               (add (decimate (shl SGPR_32, 2), 4)),
                               (add (decimate (shl SGPR_32, 3), 4))]>;

// SGPR 256-bit registers
def SGPR_256 : RegisterTuples<[sub0, sub1, sub2, sub3, sub4, sub5, sub6, sub7],
                              [(add (decimate SGPR_32, 4)),
                               (add (decimate (shl SGPR_32, 1), 4)),
                               (add (decimate (shl SGPR_32, 2), 4)),
                               (add (decimate (shl SGPR_32, 3), 4)),
                               (add (decimate (shl SGPR_32, 4), 4)),
                               (add (decimate (shl SGPR_32, 5), 4)),
                               (add (decimate (shl SGPR_32, 6), 4)),
                               (add (decimate (shl SGPR_32, 7), 4))]>;

// SGPR 512-bit registers
def SGPR_512 : RegisterTuples<[sub0, sub1, sub2, sub3, sub4, sub5, sub6, sub7,
                               sub8, sub9, sub10, sub11, sub12, sub13, sub14, sub15],
                              [(add (decimate SGPR_32, 4)),
                               (add (decimate (shl SGPR_32, 1), 4)),
                               (add (decimate (shl SGPR_32, 2), 4)),
                               (add (decimate (shl SGPR_32, 3), 4)),
                               (add (decimate (shl SGPR_32, 4), 4)),
                               (add (decimate (shl SGPR_32, 5), 4)),
                               (add (decimate (shl SGPR_32, 6), 4)),
                               (add (decimate (shl SGPR_32, 7), 4)),
                               (add (decimate (shl SGPR_32, 8), 4)),
                               (add (decimate (shl SGPR_32, 9), 4)),
                               (add (decimate (shl SGPR_32, 10), 4)),
                               (add (decimate (shl SGPR_32, 11), 4)),
                               (add (decimate (shl SGPR_32, 12), 4)),
                               (add (decimate (shl SGPR_32, 13), 4)),
                               (add (decimate (shl SGPR_32, 14), 4)),
                               (add (decimate (shl SGPR_32, 15), 4))]>;

// Trap handler TMP 32-bit registers
def TTMP_32 : RegisterClass<"AMDGPU", [i32, f32], 32,
                            (add (sequence "TTMP%u", 0, 11))> {
  let isAllocatable = 0;
}

// Trap handler TMP 64-bit registers
def TTMP_64Regs : RegisterTuples<[sub0, sub1],
                             [(add (decimate TTMP_32, 2)),
                              (add (decimate (shl TTMP_32, 1), 2))]>;

// Trap handler TMP 128-bit registers
def TTMP_128Regs : RegisterTuples<[sub0, sub1, sub2, sub3],
                              [(add (decimate TTMP_32, 4)),
                               (add (decimate (shl TTMP_32, 1), 4)),
                               (add (decimate (shl TTMP_32, 2), 4)),
                               (add (decimate (shl TTMP_32, 3), 4))]>;

// VGPR 32-bit registers
def VGPR_32 : RegisterClass<"AMDGPU", [i32, f32], 32,
                            (add (sequence "VGPR%u", 0, 255))> {
  let AllocationPriority = 1;
}

// VGPR 64-bit registers
def VGPR_64 : RegisterTuples<[sub0, sub1],
                             [(add (trunc VGPR_32, 255)),
                              (add (shl VGPR_32, 1))]>;

// VGPR 96-bit registers
def VGPR_96 : RegisterTuples<[sub0, sub1, sub2],
                             [(add (trunc VGPR_32, 254)),
                              (add (shl VGPR_32, 1)),
                              (add (shl VGPR_32, 2))]>;

// VGPR 128-bit registers
def VGPR_128 : RegisterTuples<[sub0, sub1, sub2, sub3],
                              [(add (trunc VGPR_32, 253)),
                               (add (shl VGPR_32, 1)),
                               (add (shl VGPR_32, 2)),
                               (add (shl VGPR_32, 3))]>;

// VGPR 256-bit registers
def VGPR_256 : RegisterTuples<[sub0, sub1, sub2, sub3, sub4, sub5, sub6, sub7],
                              [(add (trunc VGPR_32, 249)),
                               (add (shl VGPR_32, 1)),
                               (add (shl VGPR_32, 2)),
                               (add (shl VGPR_32, 3)),
                               (add (shl VGPR_32, 4)),
                               (add (shl VGPR_32, 5)),
                               (add (shl VGPR_32, 6)),
                               (add (shl VGPR_32, 7))]>;

// VGPR 512-bit registers
def VGPR_512 : RegisterTuples<[sub0, sub1, sub2, sub3, sub4, sub5, sub6, sub7,
                               sub8, sub9, sub10, sub11, sub12, sub13, sub14, sub15],
                              [(add (trunc VGPR_32, 241)),
                               (add (shl VGPR_32, 1)),
                               (add (shl VGPR_32, 2)),
                               (add (shl VGPR_32, 3)),
                               (add (shl VGPR_32, 4)),
                               (add (shl VGPR_32, 5)),
                               (add (shl VGPR_32, 6)),
                               (add (shl VGPR_32, 7)),
                               (add (shl VGPR_32, 8)),
                               (add (shl VGPR_32, 9)),
                               (add (shl VGPR_32, 10)),
                               (add (shl VGPR_32, 11)),
                               (add (shl VGPR_32, 12)),
                               (add (shl VGPR_32, 13)),
                               (add (shl VGPR_32, 14)),
                               (add (shl VGPR_32, 15))]>;

//===----------------------------------------------------------------------===//
//  Register classes used as source and destination
//===----------------------------------------------------------------------===//

class RegImmMatcher<string name> : AsmOperandClass {
  let Name = name;
  let RenderMethod = "addRegOrImmOperands";
}

// Subset of SReg_32 without M0 for SMRD instructions and alike.
// See comments in SIInstructions.td for more info.
def SReg_32_XM0 : RegisterClass<"AMDGPU", [i32, f32], 32,
  (add SGPR_32, VCC_LO, VCC_HI, EXEC_LO, EXEC_HI, FLAT_SCR_LO, FLAT_SCR_HI,
   TTMP_32, TMA_LO, TMA_HI, TBA_LO, TBA_HI)> {
  let AllocationPriority = 1;
}

// Register class for all scalar registers (SGPRs + Special Registers)
def SReg_32 : RegisterClass<"AMDGPU", [i32, f32], 32,
  (add SReg_32_XM0, M0)> {
  let AllocationPriority = 1;
}

def SGPR_64 : RegisterClass<"AMDGPU", [v2i32, i64, f64], 32, (add SGPR_64Regs)> {
  let AllocationPriority = 2;
}

def TTMP_64 : RegisterClass<"AMDGPU", [v2i32, i64, f64], 32, (add TTMP_64Regs)> {
  let isAllocatable = 0;
}

def SReg_64 : RegisterClass<"AMDGPU", [v2i32, i64, f64, i1], 32,
  (add SGPR_64, VCC, EXEC, FLAT_SCR, TTMP_64, TBA, TMA)> {
  let AllocationPriority = 2;
}

// Requires 2 s_mov_b64 to copy
let CopyCost = 2 in {

def SGPR_128 : RegisterClass<"AMDGPU", [v4i32, v16i8, v2i64], 32, (add SGPR_128Regs)> {
  let AllocationPriority = 4;
}

def TTMP_128 : RegisterClass<"AMDGPU", [v4i32, v16i8, v2i64], 32, (add TTMP_128Regs)> {
  let isAllocatable = 0;
}

def SReg_128 : RegisterClass<"AMDGPU", [v4i32, v16i8, v2i64], 32, (add SGPR_128, TTMP_128)> {
  let AllocationPriority = 4;
}

} // End CopyCost = 2

def SReg_256 : RegisterClass<"AMDGPU", [v8i32, v8f32], 32, (add SGPR_256)> {
  // Requires 4 s_mov_b64 to copy
  let CopyCost = 4;
  let AllocationPriority = 5;
}

def SReg_512 : RegisterClass<"AMDGPU", [v64i8, v16i32], 32, (add SGPR_512)> {
  // Requires 8 s_mov_b64 to copy
  let CopyCost = 8;
  let AllocationPriority = 6;
}

// Register class for all vector registers (VGPRs + Interploation Registers)
def VReg_64 : RegisterClass<"AMDGPU", [i64, f64, v2i32, v2f32], 32, (add VGPR_64)> {
  // Requires 2 v_mov_b32 to copy
  let CopyCost = 2;
  let AllocationPriority = 2;
}

def VReg_96 : RegisterClass<"AMDGPU", [untyped], 32, (add VGPR_96)> {
  let Size = 96;

  // Requires 3 v_mov_b32 to copy
  let CopyCost = 3;
  let AllocationPriority = 3;
}

def VReg_128 : RegisterClass<"AMDGPU", [v4i32, v4f32, v2i64, v2f64], 32, (add VGPR_128)> {
  // Requires 4 v_mov_b32 to copy
  let CopyCost = 4;
  let AllocationPriority = 4;
}

def VReg_256 : RegisterClass<"AMDGPU", [v8i32, v8f32], 32, (add VGPR_256)> {
  let CopyCost = 8;
  let AllocationPriority = 5;
}

def VReg_512 : RegisterClass<"AMDGPU", [v16i32, v16f32], 32, (add VGPR_512)> {
  let CopyCost = 16;
  let AllocationPriority = 6;
}

def VReg_1 : RegisterClass<"AMDGPU", [i1], 32, (add VGPR_32)> {
  let Size = 32;
}

class RegImmOperand <RegisterClass rc> : RegisterOperand<rc> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_IMM32";
}

class RegInlineOperand <RegisterClass rc> : RegisterOperand<rc> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_INLINE_C";
}

//===----------------------------------------------------------------------===//
//  SSrc_* Operands with an SGPR or a 32-bit immediate
//===----------------------------------------------------------------------===//

def SSrc_32 : RegImmOperand<SReg_32> {
  let ParserMatchClass = RegImmMatcher<"SSrc32">;
}

def SSrc_64 : RegImmOperand<SReg_64> {
  let ParserMatchClass = RegImmMatcher<"SSrc64">;
}

//===----------------------------------------------------------------------===//
//  SCSrc_* Operands with an SGPR or a inline constant
//===----------------------------------------------------------------------===//

def SCSrc_32 : RegInlineOperand<SReg_32> {
  let ParserMatchClass = RegImmMatcher<"SCSrc32">;
}

//===----------------------------------------------------------------------===//
//  VSrc_* Operands with an SGPR, VGPR or a 32-bit immediate
//===----------------------------------------------------------------------===//

def VS_32 : RegisterClass<"AMDGPU", [i32, f32], 32, (add VGPR_32, SReg_32)>;

def VS_64 : RegisterClass<"AMDGPU", [i64, f64], 32, (add VReg_64, SReg_64)> {
  let CopyCost = 2;
}

def VSrc_32 : RegisterOperand<VS_32> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_IMM32";
  let ParserMatchClass = RegImmMatcher<"VSrc32">;
}

def VSrc_64 : RegisterOperand<VS_64> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_IMM32";
  let ParserMatchClass = RegImmMatcher<"VSrc64">;
}

//===----------------------------------------------------------------------===//
//  VCSrc_* Operands with an SGPR, VGPR or an inline constant
//===----------------------------------------------------------------------===//

def VCSrc_32 : RegisterOperand<VS_32> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_INLINE_C";
  let ParserMatchClass = RegImmMatcher<"VCSrc32">;
}

def VCSrc_64 : RegisterOperand<VS_64> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_INLINE_C";
  let ParserMatchClass = RegImmMatcher<"VCSrc64">;
}

//===----------------------------------------------------------------------===//
//  SCSrc_* Operands with an SGPR or an inline constant
//===----------------------------------------------------------------------===//

def SCSrc_64 : RegisterOperand<SReg_64> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_INLINE_C";
  let ParserMatchClass = RegImmMatcher<"SCSrc64">;
}