Encode duplication factor from loop vectorization and loop unrolling to discriminator.
Summary:
This patch starts the implementation as discuss in the following RFC: http://lists.llvm.org/pipermail/llvm-dev/2016-October/106532.html
When optimization duplicates code that will scale down the execution count of a basic block, we will record the duplication factor as part of discriminator so that the offline process tool can find the duplication factor and collect the accurate execution frequency of the corresponding source code. Two important optimization that fall into this category is loop vectorization and loop unroll. This patch records the duplication factor for these 2 optimizations.
The recording will be guarded by a flag encode-duplication-in-discriminators, which is off by default.
Reviewers: probinson, aprantl, davidxl, hfinkel, echristo
Reviewed By: hfinkel
Subscribers: mehdi_amini, anemet, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26420
llvm-svn: 294782
diff --git a/llvm/lib/IR/Metadata.cpp b/llvm/lib/IR/Metadata.cpp
index 1d19304..77787ed 100644
--- a/llvm/lib/IR/Metadata.cpp
+++ b/llvm/lib/IR/Metadata.cpp
@@ -1459,6 +1459,15 @@
return cast_or_null<DISubprogram>(getMetadata(LLVMContext::MD_dbg));
}
+bool Function::isDebugInfoForProfiling() const {
+ if (DISubprogram *SP = getSubprogram()) {
+ if (DICompileUnit *CU = SP->getUnit()) {
+ return CU->getDebugInfoForProfiling();
+ }
+ }
+ return false;
+}
+
void GlobalVariable::addDebugInfo(DIGlobalVariableExpression *GV) {
addMetadata(LLVMContext::MD_dbg, *GV);
}
diff --git a/llvm/lib/Transforms/Utils/AddDiscriminators.cpp b/llvm/lib/Transforms/Utils/AddDiscriminators.cpp
index 2e95926..0d8ee84 100644
--- a/llvm/lib/Transforms/Utils/AddDiscriminators.cpp
+++ b/llvm/lib/Transforms/Utils/AddDiscriminators.cpp
@@ -190,8 +190,8 @@
// discriminator is needed to distinguish both instructions.
// Only the lowest 7 bits are used to represent a discriminator to fit
// it in 1 byte ULEB128 representation.
- unsigned Discriminator = (R.second ? ++LDM[L] : LDM[L]) & 0x7f;
- I.setDebugLoc(DIL->cloneWithDiscriminator(Discriminator));
+ unsigned Discriminator = R.second ? ++LDM[L] : LDM[L];
+ I.setDebugLoc(DIL->setBaseDiscriminator(Discriminator));
DEBUG(dbgs() << DIL->getFilename() << ":" << DIL->getLine() << ":"
<< DIL->getColumn() << ":" << Discriminator << " " << I
<< "\n");
@@ -216,8 +216,8 @@
Location L =
std::make_pair(CurrentDIL->getFilename(), CurrentDIL->getLine());
if (!CallLocations.insert(L).second) {
- Current->setDebugLoc(
- CurrentDIL->cloneWithDiscriminator((++LDM[L]) & 0x7f));
+ unsigned Discriminator = ++LDM[L];
+ Current->setDebugLoc(CurrentDIL->setBaseDiscriminator(Discriminator));
Changed = true;
}
}
diff --git a/llvm/lib/Transforms/Utils/LoopUnroll.cpp b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
index 1a9274d..a675797 100644
--- a/llvm/lib/Transforms/Utils/LoopUnroll.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
@@ -27,6 +27,7 @@
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/DebugInfoMetadata.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
@@ -462,6 +463,12 @@
for (Loop *SubLoop : *L)
LoopsToSimplify.insert(SubLoop);
+ if (Header->getParent()->isDebugInfoForProfiling())
+ for (BasicBlock *BB : L->getBlocks())
+ for (Instruction &I : *BB)
+ if (const DILocation *DIL = I.getDebugLoc())
+ I.setDebugLoc(DIL->cloneWithDuplicationFactor(Count));
+
for (unsigned It = 1; It != Count; ++It) {
std::vector<BasicBlock*> NewBlocks;
SmallDenseMap<const Loop *, Loop *, 4> NewLoops;
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 59e7f38..401b942 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -616,6 +616,10 @@
/// vector of instructions.
void addMetadata(ArrayRef<Value *> To, Instruction *From);
+ /// \brief Set the debug location in the builder using the debug location in
+ /// the instruction.
+ void setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr);
+
/// This is a helper class for maintaining vectorization state. It's used for
/// mapping values from the original loop to their corresponding values in
/// the new loop. Two mappings are maintained: one for vectorized values and
@@ -865,12 +869,14 @@
return I;
}
-/// \brief Set the debug location in the builder using the debug location in the
-/// instruction.
-static void setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr) {
- if (const Instruction *Inst = dyn_cast_or_null<Instruction>(Ptr))
- B.SetCurrentDebugLocation(Inst->getDebugLoc());
- else
+void InnerLoopVectorizer::setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr) {
+ if (const Instruction *Inst = dyn_cast_or_null<Instruction>(Ptr)) {
+ const DILocation *DIL = Inst->getDebugLoc();
+ if (DIL && Inst->getFunction()->isDebugInfoForProfiling())
+ B.SetCurrentDebugLocation(DIL->cloneWithDuplicationFactor(UF * VF));
+ else
+ B.SetCurrentDebugLocation(DIL);
+ } else
B.SetCurrentDebugLocation(DebugLoc());
}