llvm.org GIT mirror llvm / release_38 lib / Target / AMDGPU / SIInsertWaits.cpp
release_38

Tree @release_38 (Download .tar.gz)

SIInsertWaits.cpp @release_38raw · 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
//===-- SILowerControlFlow.cpp - Use predicates for control flow ----------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \file
/// \brief Insert wait instructions for memory reads and writes.
///
/// Memory reads and writes are issued asynchronously, so we need to insert
/// S_WAITCNT instructions when we want to access any of their results or
/// overwrite any register that's used asynchronously.
//
//===----------------------------------------------------------------------===//

#include "AMDGPU.h"
#include "AMDGPUSubtarget.h"
#include "SIDefines.h"
#include "SIInstrInfo.h"
#include "SIMachineFunctionInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"

#define DEBUG_TYPE "si-insert-waits"

using namespace llvm;

namespace {

/// \brief One variable for each of the hardware counters
typedef union {
  struct {
    unsigned VM;
    unsigned EXP;
    unsigned LGKM;
  } Named;
  unsigned Array[3];

} Counters;

typedef enum {
  OTHER,
  SMEM,
  VMEM
} InstType;

typedef Counters RegCounters[512];
typedef std::pair<unsigned, unsigned> RegInterval;

class SIInsertWaits : public MachineFunctionPass {

private:
  const SIInstrInfo *TII;
  const SIRegisterInfo *TRI;
  const MachineRegisterInfo *MRI;

  /// \brief Constant hardware limits
  static const Counters WaitCounts;

  /// \brief Constant zero value
  static const Counters ZeroCounts;

  /// \brief Counter values we have already waited on.
  Counters WaitedOn;

  /// \brief Counter values for last instruction issued.
  Counters LastIssued;

  /// \brief Registers used by async instructions.
  RegCounters UsedRegs;

  /// \brief Registers defined by async instructions.
  RegCounters DefinedRegs;

  /// \brief Different export instruction types seen since last wait.
  unsigned ExpInstrTypesSeen;

  /// \brief Type of the last opcode.
  InstType LastOpcodeType;

  bool LastInstWritesM0;

  /// \brief Whether the machine function returns void
  bool ReturnsVoid;

  /// \brief Get increment/decrement amount for this instruction.
  Counters getHwCounts(MachineInstr &MI);

  /// \brief Is operand relevant for async execution?
  bool isOpRelevant(MachineOperand &Op);

  /// \brief Get register interval an operand affects.
  RegInterval getRegInterval(const TargetRegisterClass *RC,
                             const MachineOperand &Reg) const;

  /// \brief Handle instructions async components
  void pushInstruction(MachineBasicBlock &MBB,
                       MachineBasicBlock::iterator I);

  /// \brief Insert the actual wait instruction
  bool insertWait(MachineBasicBlock &MBB,
                  MachineBasicBlock::iterator I,
                  const Counters &Counts);

  /// \brief Do we need def2def checks?
  bool unorderedDefines(MachineInstr &MI);

  /// \brief Resolve all operand dependencies to counter requirements
  Counters handleOperands(MachineInstr &MI);

  /// \brief Insert S_NOP between an instruction writing M0 and S_SENDMSG.
  void handleSendMsg(MachineBasicBlock &MBB, MachineBasicBlock::iterator I);

public:
  static char ID;

  SIInsertWaits() :
    MachineFunctionPass(ID),
    TII(nullptr),
    TRI(nullptr),
    ExpInstrTypesSeen(0) { }

  bool runOnMachineFunction(MachineFunction &MF) override;

  const char *getPassName() const override {
    return "SI insert wait instructions";
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.setPreservesCFG();
    MachineFunctionPass::getAnalysisUsage(AU);
  }
};

} // End anonymous namespace

INITIALIZE_PASS_BEGIN(SIInsertWaits, DEBUG_TYPE,
                      "SI Insert Waits", false, false)
INITIALIZE_PASS_END(SIInsertWaits, DEBUG_TYPE,
                    "SI Insert Waits", false, false)

char SIInsertWaits::ID = 0;

char &llvm::SIInsertWaitsID = SIInsertWaits::ID;

FunctionPass *llvm::createSIInsertWaitsPass() {
  return new SIInsertWaits();
}

const Counters SIInsertWaits::WaitCounts = { { 15, 7, 15 } };
const Counters SIInsertWaits::ZeroCounts = { { 0, 0, 0 } };


Counters SIInsertWaits::getHwCounts(MachineInstr &MI) {
  uint64_t TSFlags = MI.getDesc().TSFlags;
  Counters Result = { { 0, 0, 0 } };

  Result.Named.VM = !!(TSFlags & SIInstrFlags::VM_CNT);

  // Only consider stores or EXP for EXP_CNT
  Result.Named.EXP = !!(TSFlags & SIInstrFlags::EXP_CNT &&
      (MI.getOpcode() == AMDGPU::EXP || MI.getDesc().mayStore()));

  // LGKM may uses larger values
  if (TSFlags & SIInstrFlags::LGKM_CNT) {

    if (TII->isSMRD(MI)) {

      if (MI.getNumOperands() != 0) {
        assert(MI.getOperand(0).isReg() &&
               "First LGKM operand must be a register!");

        // XXX - What if this is a write into a super register?
        const TargetRegisterClass *RC = TII->getOpRegClass(MI, 0);
        unsigned Size = RC->getSize();
        Result.Named.LGKM = Size > 4 ? 2 : 1;
      } else {
        // s_dcache_inv etc. do not have a a destination register. Assume we
        // want a wait on these.
        // XXX - What is the right value?
        Result.Named.LGKM = 1;
      }
    } else {
      // DS
      Result.Named.LGKM = 1;
    }

  } else {
    Result.Named.LGKM = 0;
  }

  return Result;
}

bool SIInsertWaits::isOpRelevant(MachineOperand &Op) {
  // Constants are always irrelevant
  if (!Op.isReg() || !TRI->isInAllocatableClass(Op.getReg()))
    return false;

  // Defines are always relevant
  if (Op.isDef())
    return true;

  // For exports all registers are relevant
  MachineInstr &MI = *Op.getParent();
  if (MI.getOpcode() == AMDGPU::EXP)
    return true;

  // For stores the stored value is also relevant
  if (!MI.getDesc().mayStore())
    return false;

  // Check if this operand is the value being stored.
  // Special case for DS instructions, since the address
  // operand comes before the value operand and it may have
  // multiple data operands.

  if (TII->isDS(MI)) {
    MachineOperand *Data = TII->getNamedOperand(MI, AMDGPU::OpName::data);
    if (Data && Op.isIdenticalTo(*Data))
      return true;

    MachineOperand *Data0 = TII->getNamedOperand(MI, AMDGPU::OpName::data0);
    if (Data0 && Op.isIdenticalTo(*Data0))
      return true;

    MachineOperand *Data1 = TII->getNamedOperand(MI, AMDGPU::OpName::data1);
    if (Data1 && Op.isIdenticalTo(*Data1))
      return true;

    return false;
  }

  // NOTE: This assumes that the value operand is before the
  // address operand, and that there is only one value operand.
  for (MachineInstr::mop_iterator I = MI.operands_begin(),
       E = MI.operands_end(); I != E; ++I) {

    if (I->isReg() && I->isUse())
      return Op.isIdenticalTo(*I);
  }

  return false;
}

RegInterval SIInsertWaits::getRegInterval(const TargetRegisterClass *RC,
                                          const MachineOperand &Reg) const {
  unsigned Size = RC->getSize();
  assert(Size >= 4);

  RegInterval Result;
  Result.first = TRI->getEncodingValue(Reg.getReg());
  Result.second = Result.first + Size / 4;

  return Result;
}

void SIInsertWaits::pushInstruction(MachineBasicBlock &MBB,
                                    MachineBasicBlock::iterator I) {

  // Get the hardware counter increments and sum them up
  Counters Increment = getHwCounts(*I);
  Counters Limit = ZeroCounts;
  unsigned Sum = 0;

  for (unsigned i = 0; i < 3; ++i) {
    LastIssued.Array[i] += Increment.Array[i];
    if (Increment.Array[i])
      Limit.Array[i] = LastIssued.Array[i];
    Sum += Increment.Array[i];
  }

  // If we don't increase anything then that's it
  if (Sum == 0) {
    LastOpcodeType = OTHER;
    return;
  }

  if (MBB.getParent()->getSubtarget<AMDGPUSubtarget>().getGeneration() >=
      AMDGPUSubtarget::VOLCANIC_ISLANDS) {
    // Any occurrence of consecutive VMEM or SMEM instructions forms a VMEM
    // or SMEM clause, respectively.
    //
    // The temporary workaround is to break the clauses with S_NOP.
    //
    // The proper solution would be to allocate registers such that all source
    // and destination registers don't overlap, e.g. this is illegal:
    //   r0 = load r2
    //   r2 = load r0
    if ((LastOpcodeType == SMEM && TII->isSMRD(*I)) ||
        (LastOpcodeType == VMEM && Increment.Named.VM)) {
      // Insert a NOP to break the clause.
      BuildMI(MBB, I, DebugLoc(), TII->get(AMDGPU::S_NOP))
          .addImm(0);
      LastInstWritesM0 = false;
    }

    if (TII->isSMRD(*I))
      LastOpcodeType = SMEM;
    else if (Increment.Named.VM)
      LastOpcodeType = VMEM;
  }

  // Remember which export instructions we have seen
  if (Increment.Named.EXP) {
    ExpInstrTypesSeen |= I->getOpcode() == AMDGPU::EXP ? 1 : 2;
  }

  for (unsigned i = 0, e = I->getNumOperands(); i != e; ++i) {
    MachineOperand &Op = I->getOperand(i);
    if (!isOpRelevant(Op))
      continue;

    const TargetRegisterClass *RC = TII->getOpRegClass(*I, i);
    RegInterval Interval = getRegInterval(RC, Op);
    for (unsigned j = Interval.first; j < Interval.second; ++j) {

      // Remember which registers we define
      if (Op.isDef())
        DefinedRegs[j] = Limit;

      // and which one we are using
      if (Op.isUse())
        UsedRegs[j] = Limit;
    }
  }
}

bool SIInsertWaits::insertWait(MachineBasicBlock &MBB,
                               MachineBasicBlock::iterator I,
                               const Counters &Required) {

  // End of program? No need to wait on anything
  // A function not returning void needs to wait, because other bytecode will
  // be appended after it and we don't know what it will be.
  if (I != MBB.end() && I->getOpcode() == AMDGPU::S_ENDPGM && ReturnsVoid)
    return false;

  // Figure out if the async instructions execute in order
  bool Ordered[3];

  // VM_CNT is always ordered
  Ordered[0] = true;

  // EXP_CNT is unordered if we have both EXP & VM-writes
  Ordered[1] = ExpInstrTypesSeen == 3;

  // LGKM_CNT is handled as always unordered. TODO: Handle LDS and GDS
  Ordered[2] = false;

  // The values we are going to put into the S_WAITCNT instruction
  Counters Counts = WaitCounts;

  // Do we really need to wait?
  bool NeedWait = false;

  for (unsigned i = 0; i < 3; ++i) {

    if (Required.Array[i] <= WaitedOn.Array[i])
      continue;

    NeedWait = true;

    if (Ordered[i]) {
      unsigned Value = LastIssued.Array[i] - Required.Array[i];

      // Adjust the value to the real hardware possibilities.
      Counts.Array[i] = std::min(Value, WaitCounts.Array[i]);

    } else
      Counts.Array[i] = 0;

    // Remember on what we have waited on.
    WaitedOn.Array[i] = LastIssued.Array[i] - Counts.Array[i];
  }

  if (!NeedWait)
    return false;

  // Reset EXP_CNT instruction types
  if (Counts.Named.EXP == 0)
    ExpInstrTypesSeen = 0;

  // Build the wait instruction
  BuildMI(MBB, I, DebugLoc(), TII->get(AMDGPU::S_WAITCNT))
          .addImm((Counts.Named.VM & 0xF) |
                  ((Counts.Named.EXP & 0x7) << 4) |
                  ((Counts.Named.LGKM & 0xF) << 8));

  LastOpcodeType = OTHER;
  LastInstWritesM0 = false;
  return true;
}

/// \brief helper function for handleOperands
static void increaseCounters(Counters &Dst, const Counters &Src) {

  for (unsigned i = 0; i < 3; ++i)
    Dst.Array[i] = std::max(Dst.Array[i], Src.Array[i]);
}

Counters SIInsertWaits::handleOperands(MachineInstr &MI) {

  Counters Result = ZeroCounts;

  // S_SENDMSG implicitly waits for all outstanding LGKM transfers to finish,
  // but we also want to wait for any other outstanding transfers before
  // signalling other hardware blocks
  if (MI.getOpcode() == AMDGPU::S_SENDMSG)
    return LastIssued;

  // For each register affected by this instruction increase the result
  // sequence.
  //
  // TODO: We could probably just look at explicit operands if we removed VCC /
  // EXEC from SMRD dest reg classes.
  for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) {
    MachineOperand &Op = MI.getOperand(i);
    if (!Op.isReg() || !TRI->isInAllocatableClass(Op.getReg()))
      continue;

    const TargetRegisterClass *RC = TII->getOpRegClass(MI, i);
    RegInterval Interval = getRegInterval(RC, Op);
    for (unsigned j = Interval.first; j < Interval.second; ++j) {

      if (Op.isDef()) {
        increaseCounters(Result, UsedRegs[j]);
        increaseCounters(Result, DefinedRegs[j]);
      }

      if (Op.isUse())
        increaseCounters(Result, DefinedRegs[j]);
    }
  }

  return Result;
}

void SIInsertWaits::handleSendMsg(MachineBasicBlock &MBB,
                                  MachineBasicBlock::iterator I) {
  if (MBB.getParent()->getSubtarget<AMDGPUSubtarget>().getGeneration() <
      AMDGPUSubtarget::VOLCANIC_ISLANDS)
    return;

  // There must be "S_NOP 0" between an instruction writing M0 and S_SENDMSG.
  if (LastInstWritesM0 && I->getOpcode() == AMDGPU::S_SENDMSG) {
    BuildMI(MBB, I, DebugLoc(), TII->get(AMDGPU::S_NOP)).addImm(0);
    LastInstWritesM0 = false;
    return;
  }

  // Set whether this instruction sets M0
  LastInstWritesM0 = false;

  unsigned NumOperands = I->getNumOperands();
  for (unsigned i = 0; i < NumOperands; i++) {
    const MachineOperand &Op = I->getOperand(i);

    if (Op.isReg() && Op.isDef() && Op.getReg() == AMDGPU::M0)
      LastInstWritesM0 = true;
  }
}

// FIXME: Insert waits listed in Table 4.2 "Required User-Inserted Wait States"
// around other non-memory instructions.
bool SIInsertWaits::runOnMachineFunction(MachineFunction &MF) {
  bool Changes = false;

  TII = static_cast<const SIInstrInfo *>(MF.getSubtarget().getInstrInfo());
  TRI =
      static_cast<const SIRegisterInfo *>(MF.getSubtarget().getRegisterInfo());
  const AMDGPUSubtarget &ST = MF.getSubtarget<AMDGPUSubtarget>();
  MRI = &MF.getRegInfo();

  WaitedOn = ZeroCounts;
  LastIssued = ZeroCounts;
  LastOpcodeType = OTHER;
  LastInstWritesM0 = false;
  ReturnsVoid = MF.getInfo<SIMachineFunctionInfo>()->returnsVoid();

  memset(&UsedRegs, 0, sizeof(UsedRegs));
  memset(&DefinedRegs, 0, sizeof(DefinedRegs));

  for (MachineFunction::iterator BI = MF.begin(), BE = MF.end();
       BI != BE; ++BI) {

    MachineBasicBlock &MBB = *BI;
    for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
         I != E; ++I) {

      // Insert required wait states for SMRD reading an SGPR written by a VALU
      // instruction.
      if (ST.getGeneration() <= AMDGPUSubtarget::SOUTHERN_ISLANDS &&
          I->getOpcode() == AMDGPU::V_READFIRSTLANE_B32)
        TII->insertWaitStates(std::next(I), 4);

      // Wait for everything before a barrier.
      if (I->getOpcode() == AMDGPU::S_BARRIER)
        Changes |= insertWait(MBB, I, LastIssued);
      else
        Changes |= insertWait(MBB, I, handleOperands(*I));

      pushInstruction(MBB, I);
      handleSendMsg(MBB, I);
    }

    // Wait for everything at the end of the MBB
    Changes |= insertWait(MBB, MBB.getFirstTerminator(), LastIssued);
  }

  return Changes;
}