Infrastructure for PGO enhancements in inliner
This patch provides the following infrastructure for PGO enhancements in inliner:
Enable the use of block level profile information in inliner
Incremental update of block frequency information during inlining
Update the function entry counts of callees when they get inlined into callers.
Differential Revision: http://reviews.llvm.org/D16381
llvm-svn: 262636
diff --git a/llvm/lib/Transforms/Utils/CloneFunction.cpp b/llvm/lib/Transforms/Utils/CloneFunction.cpp
index 05b0a17..ac0867a 100644
--- a/llvm/lib/Transforms/Utils/CloneFunction.cpp
+++ b/llvm/lib/Transforms/Utils/CloneFunction.cpp
@@ -277,9 +277,10 @@
/// The specified block is found to be reachable, clone it and
/// anything that it can reach.
- void CloneBlock(const BasicBlock *BB,
+ void CloneBlock(const BasicBlock *BB,
BasicBlock::const_iterator StartingInst,
- std::vector<const BasicBlock*> &ToClone);
+ std::vector<const BasicBlock *> &ToClone,
+ BlockCloningFunctor Ftor = nullptr);
};
}
@@ -287,7 +288,8 @@
/// anything that it can reach.
void PruningFunctionCloner::CloneBlock(const BasicBlock *BB,
BasicBlock::const_iterator StartingInst,
- std::vector<const BasicBlock*> &ToClone){
+ std::vector<const BasicBlock *> &ToClone,
+ BlockCloningFunctor Ftor) {
WeakVH &BBEntry = VMap[BB];
// Have we already cloned this block?
@@ -424,18 +426,19 @@
CodeInfo->ContainsDynamicAllocas |= hasStaticAllocas &&
BB != &BB->getParent()->front();
}
+ // Call Ftor to tell BB has been cloned to NewBB
+ if (Ftor)
+ Ftor(BB, NewBB);
}
/// This works like CloneAndPruneFunctionInto, except that it does not clone the
/// entire function. Instead it starts at an instruction provided by the caller
/// and copies (and prunes) only the code reachable from that instruction.
-void llvm::CloneAndPruneIntoFromInst(Function *NewFunc, const Function *OldFunc,
- const Instruction *StartingInst,
- ValueToValueMapTy &VMap,
- bool ModuleLevelChanges,
- SmallVectorImpl<ReturnInst *> &Returns,
- const char *NameSuffix,
- ClonedCodeInfo *CodeInfo) {
+void llvm::CloneAndPruneIntoFromInst(
+ Function *NewFunc, const Function *OldFunc, const Instruction *StartingInst,
+ ValueToValueMapTy &VMap, bool ModuleLevelChanges,
+ SmallVectorImpl<ReturnInst *> &Returns, const char *NameSuffix,
+ ClonedCodeInfo *CodeInfo, BlockCloningFunctor Ftor) {
assert(NameSuffix && "NameSuffix cannot be null!");
ValueMapTypeRemapper *TypeMapper = nullptr;
@@ -461,11 +464,11 @@
// Clone the entry block, and anything recursively reachable from it.
std::vector<const BasicBlock*> CloneWorklist;
- PFC.CloneBlock(StartingBB, StartingInst->getIterator(), CloneWorklist);
+ PFC.CloneBlock(StartingBB, StartingInst->getIterator(), CloneWorklist, Ftor);
while (!CloneWorklist.empty()) {
const BasicBlock *BB = CloneWorklist.back();
CloneWorklist.pop_back();
- PFC.CloneBlock(BB, BB->begin(), CloneWorklist);
+ PFC.CloneBlock(BB, BB->begin(), CloneWorklist, Ftor);
}
// Loop over all of the basic blocks in the old function. If the block was
@@ -667,15 +670,14 @@
/// constant arguments cause a significant amount of code in the callee to be
/// dead. Since this doesn't produce an exact copy of the input, it can't be
/// used for things like CloneFunction or CloneModule.
-void llvm::CloneAndPruneFunctionInto(Function *NewFunc, const Function *OldFunc,
- ValueToValueMapTy &VMap,
- bool ModuleLevelChanges,
- SmallVectorImpl<ReturnInst*> &Returns,
- const char *NameSuffix,
- ClonedCodeInfo *CodeInfo,
- Instruction *TheCall) {
+void llvm::CloneAndPruneFunctionInto(
+ Function *NewFunc, const Function *OldFunc, ValueToValueMapTy &VMap,
+ bool ModuleLevelChanges, SmallVectorImpl<ReturnInst *> &Returns,
+ const char *NameSuffix, ClonedCodeInfo *CodeInfo, Instruction *TheCall,
+ BlockCloningFunctor Ftor) {
CloneAndPruneIntoFromInst(NewFunc, OldFunc, &OldFunc->front().front(), VMap,
- ModuleLevelChanges, Returns, NameSuffix, CodeInfo);
+ ModuleLevelChanges, Returns, NameSuffix, CodeInfo,
+ Ftor);
}
/// \brief Remaps instructions in \p Blocks using the mapping in \p VMap.