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
|
//===- AggressiveInstCombine.cpp ------------------------------------------===//
//
// 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 aggressive expression pattern combiner classes.
// Currently, it handles expression patterns for:
// * Truncate instruction
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/AggressiveInstCombine/AggressiveInstCombine.h"
#include "AggressiveInstCombineInternal.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/Utils/Local.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/Pass.h"
using namespace llvm;
using namespace PatternMatch;
#define DEBUG_TYPE "aggressive-instcombine"
namespace {
/// Contains expression pattern combiner logic.
/// This class provides both the logic to combine expression patterns and
/// combine them. It differs from InstCombiner class in that each pattern
/// combiner runs only once as opposed to InstCombine's multi-iteration,
/// which allows pattern combiner to have higher complexity than the O(1)
/// required by the instruction combiner.
class AggressiveInstCombinerLegacyPass : public FunctionPass {
public:
static char ID; // Pass identification, replacement for typeid
AggressiveInstCombinerLegacyPass() : FunctionPass(ID) {
initializeAggressiveInstCombinerLegacyPassPass(
*PassRegistry::getPassRegistry());
}
void getAnalysisUsage(AnalysisUsage &AU) const override;
/// Run all expression pattern optimizations on the given /p F function.
///
/// \param F function to optimize.
/// \returns true if the IR is changed.
bool runOnFunction(Function &F) override;
};
} // namespace
/// This is a recursive helper for 'and X, 1' that walks through a chain of 'or'
/// instructions looking for shift ops of a common source value (first member of
/// the pair). The second member of the pair is a mask constant for all of the
/// bits that are being compared. So this:
/// or (or (or X, (X >> 3)), (X >> 5)), (X >> 8)
/// returns {X, 0x129} and those are the operands of an 'and' that is compared
/// to zero.
static bool matchMaskedCmpOp(Value *V, std::pair<Value *, APInt> &Result) {
// Recurse through a chain of 'or' operands.
Value *Op0, *Op1;
if (match(V, m_Or(m_Value(Op0), m_Value(Op1))))
return matchMaskedCmpOp(Op0, Result) && matchMaskedCmpOp(Op1, Result);
// We need a shift-right or a bare value representing a compare of bit 0 of
// the original source operand.
Value *Candidate;
uint64_t BitIndex = 0;
if (!match(V, m_LShr(m_Value(Candidate), m_ConstantInt(BitIndex))))
Candidate = V;
// Initialize result source operand.
if (!Result.first)
Result.first = Candidate;
// Fill in the mask bit derived from the shift constant.
Result.second.setBit(BitIndex);
return Result.first == Candidate;
}
/// Match an 'and' of a chain of or-shifted bits from a common source value into
/// a masked compare:
/// and (or (lshr X, C), ...), 1 --> (X & C') != 0
static bool foldToMaskedCmp(Instruction &I) {
// TODO: This is only looking for 'any-bits-set' and 'all-bits-clear'.
// We should also match 'all-bits-set' and 'any-bits-clear' by looking for a
// a chain of 'and'.
if (!match(&I, m_And(m_OneUse(m_Or(m_Value(), m_Value())), m_One())))
return false;
std::pair<Value *, APInt>
MaskOps(nullptr, APInt::getNullValue(I.getType()->getScalarSizeInBits()));
if (!matchMaskedCmpOp(cast<BinaryOperator>(&I)->getOperand(0), MaskOps))
return false;
IRBuilder<> Builder(&I);
Value *Mask = Builder.CreateAnd(MaskOps.first, MaskOps.second);
Value *CmpZero = Builder.CreateIsNotNull(Mask);
Value *Zext = Builder.CreateZExt(CmpZero, I.getType());
I.replaceAllUsesWith(Zext);
return true;
}
/// This is the entry point for folds that could be implemented in regular
/// InstCombine, but they are separated because they are not expected to
/// occur frequently and/or have more than a constant-length pattern match.
static bool foldUnusualPatterns(Function &F, DominatorTree &DT) {
bool MadeChange = false;
for (BasicBlock &BB : F) {
// Ignore unreachable basic blocks.
if (!DT.isReachableFromEntry(&BB))
continue;
// Do not delete instructions under here and invalidate the iterator.
for (Instruction &I : BB)
MadeChange |= foldToMaskedCmp(I);
}
// We're done with transforms, so remove dead instructions.
if (MadeChange)
for (BasicBlock &BB : F)
SimplifyInstructionsInBlock(&BB);
return MadeChange;
}
/// This is the entry point for all transforms. Pass manager differences are
/// handled in the callers of this function.
static bool runImpl(Function &F, TargetLibraryInfo &TLI, DominatorTree &DT) {
bool MadeChange = false;
const DataLayout &DL = F.getParent()->getDataLayout();
TruncInstCombine TIC(TLI, DL, DT);
MadeChange |= TIC.run(F);
MadeChange |= foldUnusualPatterns(F, DT);
return MadeChange;
}
void AggressiveInstCombinerLegacyPass::getAnalysisUsage(
AnalysisUsage &AU) const {
AU.setPreservesCFG();
AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
AU.addPreserved<AAResultsWrapperPass>();
AU.addPreserved<BasicAAWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
}
bool AggressiveInstCombinerLegacyPass::runOnFunction(Function &F) {
auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
return runImpl(F, TLI, DT);
}
PreservedAnalyses AggressiveInstCombinePass::run(Function &F,
FunctionAnalysisManager &AM) {
auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
if (!runImpl(F, TLI, DT)) {
// No changes, all analyses are preserved.
return PreservedAnalyses::all();
}
// Mark all the analyses that instcombine updates as preserved.
PreservedAnalyses PA;
PA.preserveSet<CFGAnalyses>();
PA.preserve<AAManager>();
PA.preserve<GlobalsAA>();
return PA;
}
char AggressiveInstCombinerLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(AggressiveInstCombinerLegacyPass,
"aggressive-instcombine",
"Combine pattern based expressions", false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(AggressiveInstCombinerLegacyPass, "aggressive-instcombine",
"Combine pattern based expressions", false, false)
// Initialization Routines
void llvm::initializeAggressiveInstCombine(PassRegistry &Registry) {
initializeAggressiveInstCombinerLegacyPassPass(Registry);
}
void LLVMInitializeAggressiveInstCombiner(LLVMPassRegistryRef R) {
initializeAggressiveInstCombinerLegacyPassPass(*unwrap(R));
}
FunctionPass *llvm::createAggressiveInstCombinerPass() {
return new AggressiveInstCombinerLegacyPass();
}
void LLVMAddAggressiveInstCombinerPass(LLVMPassManagerRef PM) {
unwrap(PM)->add(createAggressiveInstCombinerPass());
}
|
