summaryrefslogtreecommitdiff
path: root/lib/Transforms/Scalar/SimplifyCFGPass.cpp
blob: a09e4853fb32da8a1c09db830d143ceafe0acd8a (plain)
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
//===- SimplifyCFGPass.cpp - CFG Simplification Pass ----------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements dead code elimination and basic block merging, along
// with a collection of other peephole control flow optimizations.  For example:
//
//   * Removes basic blocks with no predecessors.
//   * Merges a basic block into its predecessor if there is only one and the
//     predecessor only has one successor.
//   * Eliminates PHI nodes for basic blocks with a single predecessor.
//   * Eliminates a basic block that only contains an unconditional branch.
//   * Changes invoke instructions to nounwind functions to be calls.
//   * Change things like "if (x) if (y)" into "if (x&y)".
//   * etc..
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/Pass.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
using std::error_code;

#define DEBUG_TYPE "simplifycfg"

STATISTIC(NumSimpl, "Number of blocks simplified");

namespace {
struct CFGSimplifyPass : public FunctionPass {
  static char ID; // Pass identification, replacement for typeid
  CFGSimplifyPass() : FunctionPass(ID) {
    initializeCFGSimplifyPassPass(*PassRegistry::getPassRegistry());
  }
  bool runOnFunction(Function &F) override;

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

char CFGSimplifyPass::ID = 0;
INITIALIZE_PASS_BEGIN(CFGSimplifyPass, "simplifycfg", "Simplify the CFG", false,
                      false)
INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
INITIALIZE_PASS_END(CFGSimplifyPass, "simplifycfg", "Simplify the CFG", false,
                    false)

// Public interface to the CFGSimplification pass
FunctionPass *llvm::createCFGSimplificationPass() {
  return new CFGSimplifyPass();
}

/// mergeEmptyReturnBlocks - If we have more than one empty (other than phi
/// node) return blocks, merge them together to promote recursive block merging.
static bool mergeEmptyReturnBlocks(Function &F) {
  bool Changed = false;

  BasicBlock *RetBlock = nullptr;

  // Scan all the blocks in the function, looking for empty return blocks.
  for (Function::iterator BBI = F.begin(), E = F.end(); BBI != E; ) {
    BasicBlock &BB = *BBI++;

    // Only look at return blocks.
    ReturnInst *Ret = dyn_cast<ReturnInst>(BB.getTerminator());
    if (!Ret) continue;

    // Only look at the block if it is empty or the only other thing in it is a
    // single PHI node that is the operand to the return.
    if (Ret != &BB.front()) {
      // Check for something else in the block.
      BasicBlock::iterator I = Ret;
      --I;
      // Skip over debug info.
      while (isa<DbgInfoIntrinsic>(I) && I != BB.begin())
        --I;
      if (!isa<DbgInfoIntrinsic>(I) &&
          (!isa<PHINode>(I) || I != BB.begin() ||
           Ret->getNumOperands() == 0 ||
           Ret->getOperand(0) != I))
        continue;
    }

    // If this is the first returning block, remember it and keep going.
    if (!RetBlock) {
      RetBlock = &BB;
      continue;
    }

    // Otherwise, we found a duplicate return block.  Merge the two.
    Changed = true;

    // Case when there is no input to the return or when the returned values
    // agree is trivial.  Note that they can't agree if there are phis in the
    // blocks.
    if (Ret->getNumOperands() == 0 ||
        Ret->getOperand(0) ==
          cast<ReturnInst>(RetBlock->getTerminator())->getOperand(0)) {
      BB.replaceAllUsesWith(RetBlock);
      BB.eraseFromParent();
      continue;
    }

    // If the canonical return block has no PHI node, create one now.
    PHINode *RetBlockPHI = dyn_cast<PHINode>(RetBlock->begin());
    if (!RetBlockPHI) {
      Value *InVal = cast<ReturnInst>(RetBlock->getTerminator())->getOperand(0);
      pred_iterator PB = pred_begin(RetBlock), PE = pred_end(RetBlock);
      RetBlockPHI = PHINode::Create(Ret->getOperand(0)->getType(),
                                    std::distance(PB, PE), "merge",
                                    &RetBlock->front());

      for (pred_iterator PI = PB; PI != PE; ++PI)
        RetBlockPHI->addIncoming(InVal, *PI);
      RetBlock->getTerminator()->setOperand(0, RetBlockPHI);
    }

    // Turn BB into a block that just unconditionally branches to the return
    // block.  This handles the case when the two return blocks have a common
    // predecessor but that return different things.
    RetBlockPHI->addIncoming(Ret->getOperand(0), &BB);
    BB.getTerminator()->eraseFromParent();
    BranchInst::Create(RetBlock, &BB);
  }

  return Changed;
}

/// iterativelySimplifyCFG - Call SimplifyCFG on all the blocks in the function,
/// iterating until no more changes are made.
static bool iterativelySimplifyCFG(Function &F, const TargetTransformInfo &TTI,
                                   const DataLayout *DL) {
  bool Changed = false;
  bool LocalChange = true;
  while (LocalChange) {
    LocalChange = false;

    // Loop over all of the basic blocks and remove them if they are unneeded...
    //
    for (Function::iterator BBIt = F.begin(); BBIt != F.end(); ) {
      if (SimplifyCFG(BBIt++, TTI, DL)) {
        LocalChange = true;
        ++NumSimpl;
      }
    }
    Changed |= LocalChange;
  }
  return Changed;
}

// It is possible that we may require multiple passes over the code to fully
// simplify the CFG.
//
bool CFGSimplifyPass::runOnFunction(Function &F) {
  if (skipOptnoneFunction(F))
    return false;

  const TargetTransformInfo &TTI = getAnalysis<TargetTransformInfo>();
  DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
  const DataLayout *DL = DLP ? &DLP->getDataLayout() : nullptr;
  bool EverChanged = removeUnreachableBlocks(F);
  EverChanged |= mergeEmptyReturnBlocks(F);
  EverChanged |= iterativelySimplifyCFG(F, TTI, DL);

  // If neither pass changed anything, we're done.
  if (!EverChanged) return false;

  // iterativelySimplifyCFG can (rarely) make some loops dead.  If this happens,
  // removeUnreachableBlocks is needed to nuke them, which means we should
  // iterate between the two optimizations.  We structure the code like this to
  // avoid reruning iterativelySimplifyCFG if the second pass of
  // removeUnreachableBlocks doesn't do anything.
  if (!removeUnreachableBlocks(F))
    return true;

  do {
    EverChanged = iterativelySimplifyCFG(F, TTI, DL);
    EverChanged |= removeUnreachableBlocks(F);
  } while (EverChanged);

  return true;
}