aboutsummaryrefslogtreecommitdiff
path: root/contrib/llvm/lib/Transforms/Scalar/CorrelatedValuePropagation.cpp
blob: 686bd40711049cbc7ee9fe9ed4fc9f2845ad09f1 (plain) (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
//===- CorrelatedValuePropagation.cpp - Propagate CFG-derived info --------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the Correlated Value Propagation pass.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LazyValueInfo.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Module.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;

#define DEBUG_TYPE "correlated-value-propagation"

STATISTIC(NumPhis,      "Number of phis propagated");
STATISTIC(NumSelects,   "Number of selects propagated");
STATISTIC(NumMemAccess, "Number of memory access targets propagated");
STATISTIC(NumCmps,      "Number of comparisons propagated");
STATISTIC(NumReturns,   "Number of return values propagated");
STATISTIC(NumDeadCases, "Number of switch cases removed");

namespace {
  class CorrelatedValuePropagation : public FunctionPass {
    LazyValueInfo *LVI;

    bool processSelect(SelectInst *SI);
    bool processPHI(PHINode *P);
    bool processMemAccess(Instruction *I);
    bool processCmp(CmpInst *C);
    bool processSwitch(SwitchInst *SI);
    bool processCallSite(CallSite CS);

    /// Return a constant value for V usable at At and everything it
    /// dominates.  If no such Constant can be found, return nullptr.
    Constant *getConstantAt(Value *V, Instruction *At);

  public:
    static char ID;
    CorrelatedValuePropagation(): FunctionPass(ID) {
     initializeCorrelatedValuePropagationPass(*PassRegistry::getPassRegistry());
    }

    bool runOnFunction(Function &F) override;

    void getAnalysisUsage(AnalysisUsage &AU) const override {
      AU.addRequired<LazyValueInfo>();
      AU.addPreserved<GlobalsAAWrapperPass>();
    }
  };
}

char CorrelatedValuePropagation::ID = 0;
INITIALIZE_PASS_BEGIN(CorrelatedValuePropagation, "correlated-propagation",
                "Value Propagation", false, false)
INITIALIZE_PASS_DEPENDENCY(LazyValueInfo)
INITIALIZE_PASS_END(CorrelatedValuePropagation, "correlated-propagation",
                "Value Propagation", false, false)

// Public interface to the Value Propagation pass
Pass *llvm::createCorrelatedValuePropagationPass() {
  return new CorrelatedValuePropagation();
}

bool CorrelatedValuePropagation::processSelect(SelectInst *S) {
  if (S->getType()->isVectorTy()) return false;
  if (isa<Constant>(S->getOperand(0))) return false;

  Constant *C = LVI->getConstant(S->getOperand(0), S->getParent(), S);
  if (!C) return false;

  ConstantInt *CI = dyn_cast<ConstantInt>(C);
  if (!CI) return false;

  Value *ReplaceWith = S->getOperand(1);
  Value *Other = S->getOperand(2);
  if (!CI->isOne()) std::swap(ReplaceWith, Other);
  if (ReplaceWith == S) ReplaceWith = UndefValue::get(S->getType());

  S->replaceAllUsesWith(ReplaceWith);
  S->eraseFromParent();

  ++NumSelects;

  return true;
}

bool CorrelatedValuePropagation::processPHI(PHINode *P) {
  bool Changed = false;

  BasicBlock *BB = P->getParent();
  for (unsigned i = 0, e = P->getNumIncomingValues(); i < e; ++i) {
    Value *Incoming = P->getIncomingValue(i);
    if (isa<Constant>(Incoming)) continue;

    Value *V = LVI->getConstantOnEdge(Incoming, P->getIncomingBlock(i), BB, P);

    // Look if the incoming value is a select with a scalar condition for which
    // LVI can tells us the value. In that case replace the incoming value with
    // the appropriate value of the select. This often allows us to remove the
    // select later.
    if (!V) {
      SelectInst *SI = dyn_cast<SelectInst>(Incoming);
      if (!SI) continue;

      Value *Condition = SI->getCondition();
      if (!Condition->getType()->isVectorTy()) {
        if (Constant *C = LVI->getConstantOnEdge(
                Condition, P->getIncomingBlock(i), BB, P)) {
          if (C->isOneValue()) {
            V = SI->getTrueValue();
          } else if (C->isZeroValue()) {
            V = SI->getFalseValue();
          }
          // Once LVI learns to handle vector types, we could also add support
          // for vector type constants that are not all zeroes or all ones.
        }
      }

      // Look if the select has a constant but LVI tells us that the incoming
      // value can never be that constant. In that case replace the incoming
      // value with the other value of the select. This often allows us to
      // remove the select later.
      if (!V) {
        Constant *C = dyn_cast<Constant>(SI->getFalseValue());
        if (!C) continue;

        if (LVI->getPredicateOnEdge(ICmpInst::ICMP_EQ, SI, C,
              P->getIncomingBlock(i), BB, P) !=
            LazyValueInfo::False)
          continue;
        V = SI->getTrueValue();
      }

      DEBUG(dbgs() << "CVP: Threading PHI over " << *SI << '\n');
    }

    P->setIncomingValue(i, V);
    Changed = true;
  }

  // FIXME: Provide TLI, DT, AT to SimplifyInstruction.
  const DataLayout &DL = BB->getModule()->getDataLayout();
  if (Value *V = SimplifyInstruction(P, DL)) {
    P->replaceAllUsesWith(V);
    P->eraseFromParent();
    Changed = true;
  }

  if (Changed)
    ++NumPhis;

  return Changed;
}

bool CorrelatedValuePropagation::processMemAccess(Instruction *I) {
  Value *Pointer = nullptr;
  if (LoadInst *L = dyn_cast<LoadInst>(I))
    Pointer = L->getPointerOperand();
  else
    Pointer = cast<StoreInst>(I)->getPointerOperand();

  if (isa<Constant>(Pointer)) return false;

  Constant *C = LVI->getConstant(Pointer, I->getParent(), I);
  if (!C) return false;

  ++NumMemAccess;
  I->replaceUsesOfWith(Pointer, C);
  return true;
}

/// processCmp - See if LazyValueInfo's ability to exploit edge conditions,
/// or range information is sufficient to prove this comparison.  Even for
/// local conditions, this can sometimes prove conditions instcombine can't by
/// exploiting range information.
bool CorrelatedValuePropagation::processCmp(CmpInst *C) {
  Value *Op0 = C->getOperand(0);
  Constant *Op1 = dyn_cast<Constant>(C->getOperand(1));
  if (!Op1) return false;

  // As a policy choice, we choose not to waste compile time on anything where
  // the comparison is testing local values.  While LVI can sometimes reason
  // about such cases, it's not its primary purpose.  We do make sure to do
  // the block local query for uses from terminator instructions, but that's
  // handled in the code for each terminator.
  auto *I = dyn_cast<Instruction>(Op0);
  if (I && I->getParent() == C->getParent())
    return false;

  LazyValueInfo::Tristate Result =
    LVI->getPredicateAt(C->getPredicate(), Op0, Op1, C);
  if (Result == LazyValueInfo::Unknown) return false;

  ++NumCmps;
  if (Result == LazyValueInfo::True)
    C->replaceAllUsesWith(ConstantInt::getTrue(C->getContext()));
  else
    C->replaceAllUsesWith(ConstantInt::getFalse(C->getContext()));
  C->eraseFromParent();

  return true;
}

/// processSwitch - Simplify a switch instruction by removing cases which can
/// never fire.  If the uselessness of a case could be determined locally then
/// constant propagation would already have figured it out.  Instead, walk the
/// predecessors and statically evaluate cases based on information available
/// on that edge.  Cases that cannot fire no matter what the incoming edge can
/// safely be removed.  If a case fires on every incoming edge then the entire
/// switch can be removed and replaced with a branch to the case destination.
bool CorrelatedValuePropagation::processSwitch(SwitchInst *SI) {
  Value *Cond = SI->getCondition();
  BasicBlock *BB = SI->getParent();

  // If the condition was defined in same block as the switch then LazyValueInfo
  // currently won't say anything useful about it, though in theory it could.
  if (isa<Instruction>(Cond) && cast<Instruction>(Cond)->getParent() == BB)
    return false;

  // If the switch is unreachable then trying to improve it is a waste of time.
  pred_iterator PB = pred_begin(BB), PE = pred_end(BB);
  if (PB == PE) return false;

  // Analyse each switch case in turn.  This is done in reverse order so that
  // removing a case doesn't cause trouble for the iteration.
  bool Changed = false;
  for (SwitchInst::CaseIt CI = SI->case_end(), CE = SI->case_begin(); CI-- != CE;
       ) {
    ConstantInt *Case = CI.getCaseValue();

    // Check to see if the switch condition is equal to/not equal to the case
    // value on every incoming edge, equal/not equal being the same each time.
    LazyValueInfo::Tristate State = LazyValueInfo::Unknown;
    for (pred_iterator PI = PB; PI != PE; ++PI) {
      // Is the switch condition equal to the case value?
      LazyValueInfo::Tristate Value = LVI->getPredicateOnEdge(CmpInst::ICMP_EQ,
                                                              Cond, Case, *PI,
                                                              BB, SI);
      // Give up on this case if nothing is known.
      if (Value == LazyValueInfo::Unknown) {
        State = LazyValueInfo::Unknown;
        break;
      }

      // If this was the first edge to be visited, record that all other edges
      // need to give the same result.
      if (PI == PB) {
        State = Value;
        continue;
      }

      // If this case is known to fire for some edges and known not to fire for
      // others then there is nothing we can do - give up.
      if (Value != State) {
        State = LazyValueInfo::Unknown;
        break;
      }
    }

    if (State == LazyValueInfo::False) {
      // This case never fires - remove it.
      CI.getCaseSuccessor()->removePredecessor(BB);
      SI->removeCase(CI); // Does not invalidate the iterator.

      // The condition can be modified by removePredecessor's PHI simplification
      // logic.
      Cond = SI->getCondition();

      ++NumDeadCases;
      Changed = true;
    } else if (State == LazyValueInfo::True) {
      // This case always fires.  Arrange for the switch to be turned into an
      // unconditional branch by replacing the switch condition with the case
      // value.
      SI->setCondition(Case);
      NumDeadCases += SI->getNumCases();
      Changed = true;
      break;
    }
  }

  if (Changed)
    // If the switch has been simplified to the point where it can be replaced
    // by a branch then do so now.
    ConstantFoldTerminator(BB);

  return Changed;
}

/// processCallSite - Infer nonnull attributes for the arguments at the
/// specified callsite.
bool CorrelatedValuePropagation::processCallSite(CallSite CS) {
  SmallVector<unsigned, 4> Indices;
  unsigned ArgNo = 0;

  for (Value *V : CS.args()) {
    PointerType *Type = dyn_cast<PointerType>(V->getType());

    if (Type && !CS.paramHasAttr(ArgNo + 1, Attribute::NonNull) &&
        LVI->getPredicateAt(ICmpInst::ICMP_EQ, V,
                            ConstantPointerNull::get(Type),
                            CS.getInstruction()) == LazyValueInfo::False)
      Indices.push_back(ArgNo + 1);
    ArgNo++;
  }

  assert(ArgNo == CS.arg_size() && "sanity check");

  if (Indices.empty())
    return false;

  AttributeSet AS = CS.getAttributes();
  LLVMContext &Ctx = CS.getInstruction()->getContext();
  AS = AS.addAttribute(Ctx, Indices, Attribute::get(Ctx, Attribute::NonNull));
  CS.setAttributes(AS);

  return true;
}

Constant *CorrelatedValuePropagation::getConstantAt(Value *V, Instruction *At) {
  if (Constant *C = LVI->getConstant(V, At->getParent(), At))
    return C;

  // TODO: The following really should be sunk inside LVI's core algorithm, or
  // at least the outer shims around such.
  auto *C = dyn_cast<CmpInst>(V);
  if (!C) return nullptr;

  Value *Op0 = C->getOperand(0);
  Constant *Op1 = dyn_cast<Constant>(C->getOperand(1));
  if (!Op1) return nullptr;
  
  LazyValueInfo::Tristate Result =
    LVI->getPredicateAt(C->getPredicate(), Op0, Op1, At);
  if (Result == LazyValueInfo::Unknown)
    return nullptr;
  
  return (Result == LazyValueInfo::True) ?
    ConstantInt::getTrue(C->getContext()) :
    ConstantInt::getFalse(C->getContext());
}

bool CorrelatedValuePropagation::runOnFunction(Function &F) {
  if (skipOptnoneFunction(F))
    return false;

  LVI = &getAnalysis<LazyValueInfo>();

  bool FnChanged = false;

  for (Function::iterator FI = F.begin(), FE = F.end(); FI != FE; ++FI) {
    bool BBChanged = false;
    for (BasicBlock::iterator BI = FI->begin(), BE = FI->end(); BI != BE; ) {
      Instruction *II = &*BI++;
      switch (II->getOpcode()) {
      case Instruction::Select:
        BBChanged |= processSelect(cast<SelectInst>(II));
        break;
      case Instruction::PHI:
        BBChanged |= processPHI(cast<PHINode>(II));
        break;
      case Instruction::ICmp:
      case Instruction::FCmp:
        BBChanged |= processCmp(cast<CmpInst>(II));
        break;
      case Instruction::Load:
      case Instruction::Store:
        BBChanged |= processMemAccess(II);
        break;
      case Instruction::Call:
      case Instruction::Invoke:
        BBChanged |= processCallSite(CallSite(II));
        break;
      }
    }

    Instruction *Term = FI->getTerminator();
    switch (Term->getOpcode()) {
    case Instruction::Switch:
      BBChanged |= processSwitch(cast<SwitchInst>(Term));
      break;
    case Instruction::Ret: {
      auto *RI = cast<ReturnInst>(Term);
      // Try to determine the return value if we can.  This is mainly here to
      // simplify the writing of unit tests, but also helps to enable IPO by
      // constant folding the return values of callees.
      auto *RetVal = RI->getReturnValue();
      if (!RetVal) break; // handle "ret void"
      if (isa<Constant>(RetVal)) break; // nothing to do
      if (auto *C = getConstantAt(RetVal, RI)) {
        ++NumReturns;
        RI->replaceUsesOfWith(RetVal, C);
        BBChanged = true;        
      }
    }
    };

    FnChanged |= BBChanged;
  }

  return FnChanged;
}