[SampleFDO] New hierarchical discriminator for Flow Sensitive SampleFDO

This patch implements first part of Flow Sensitive SampleFDO (FSAFDO).
It has the following changes:
(1) disable current discriminator encoding scheme,
(2) new hierarchical discriminator for FSAFDO.

For this patch, option "-enable-fs-discriminator=true" turns on the new
functionality. Option "-enable-fs-discriminator=false" (the default)
keeps the current SampleFDO behavior. When the fs-discriminator is
enabled, we insert a flag variable, namely, llvm_fs_discriminator, to
the object. This symbol will checked by create_llvm_prof tool, and used
to generate a profile with FS-AFDO discriminators enabled. If this
happens, for an extbinary format profile, create_llvm_prof tool
will add a flag to profile summary section.

Differential Revision: https://reviews.llvm.org/D102246

llvm/include/llvm/CodeGen/MIRFSDiscriminator.h

@@ -0,0 +1,74 @@
+//===----- MIRFSDiscriminator.h: MIR FS Discriminator Support --0-- c++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the supporting functions for adding Machine level IR
+// Flow Sensitive discriminators to the instruction debug information. With
+// this, a cloned machine instruction in a different MachineBasicBlock will
+// have its own discriminator value. This is done in a MIRAddFSDiscriminators
+// pass.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_MIRFSDISCRIMINATOR_H
+#define LLVM_CODEGEN_MIRFSDISCRIMINATOR_H
+
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
+#include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
+#include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h"
+#include "llvm/CodeGen/MachinePostDominators.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Module.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/ProfileData/InstrProf.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "llvm/ProfileData/SampleProfReader.h"
+
+#include <cassert>
+
+namespace llvm {
+
+class MIRAddFSDiscriminators : public MachineFunctionPass {
+  MachineFunction *MF;
+  unsigned LowBit;
+  unsigned HighBit;
+
+public:
+  static char ID;
+  /// FS bits that will be used in this pass (numbers are 0 based and
+  /// inclusive).
+  MIRAddFSDiscriminators(unsigned LowBit = 0, unsigned HighBit = 0)
+      : MachineFunctionPass(ID), LowBit(LowBit), HighBit(HighBit) {
+    assert(LowBit < HighBit && "HighBit needs to be greater than Lowbit");
+  }
+
+  /// getNumFSBBs() - Return the number of machine BBs that have FS samples.
+  unsigned getNumFSBBs();
+
+  /// getNumFSSamples() - Return the number of samples that have flow sensitive
+  /// values.
+  uint64_t getNumFSSamples();
+
+  /// getMachineFunction - Return the current machine function.
+  const MachineFunction *getMachineFunction() const { return MF; }
+
+private:
+  bool runOnMachineFunction(MachineFunction &) override;
+};
+
+} // namespace llvm
+
+#endif // LLVM_CODEGEN_MIRFSDISCRIMINATOR_H

llvm/include/llvm/CodeGen/Passes.h

@@ -165,6 +165,9 @@ namespace llvm {
   /// This pass perform post-ra machine sink for COPY instructions.
   extern char &PostRAMachineSinkingID;
 
+  /// This pass adds flow sensitive discriminators.
+  extern char &MIRAddFSDiscriminatorsID;
+
   /// FastRegisterAllocation Pass - This pass register allocates as fast as
   /// possible. It is best suited for debug code where live ranges are short.
   ///
@@ -487,6 +490,10 @@ namespace llvm {
   /// Create IR Type Promotion pass. \see TypePromotion.cpp
   FunctionPass *createTypePromotionPass();
 
+  /// Add Flow Sensitive Discriminators.
+  FunctionPass *createMIRAddFSDiscriminatorsPass(unsigned LowBit,
+                                                 unsigned HighBit);
+
   /// Creates MIR Debugify pass. \see MachineDebugify.cpp
   ModulePass *createDebugifyMachineModulePass();
 

llvm/include/llvm/IR/DebugInfoMetadata.h

@@ -26,6 +26,8 @@
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Metadata.h"
 #include "llvm/Support/Casting.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Discriminator.h"
 #include <cassert>
 #include <climits>
 #include <cstddef>
@@ -60,6 +62,8 @@
 
 namespace llvm {
 
+extern cl::opt<bool> EnableFSDiscriminator;
+
 class DITypeRefArray {
   const MDTuple *N = nullptr;
 
@@ -1576,31 +1580,6 @@ class DILocation : public MDNode {
                    ShouldCreate);
   }
 
-  /// With a given unsigned int \p U, use up to 13 bits to represent it.
-  /// old_bit 1~5  --> new_bit 1~5
-  /// old_bit 6~12 --> new_bit 7~13
-  /// new_bit_6 is 0 if higher bits (7~13) are all 0
-  static unsigned getPrefixEncodingFromUnsigned(unsigned U) {
-    U &= 0xfff;
-    return U > 0x1f ? (((U & 0xfe0) << 1) | (U & 0x1f) | 0x20) : U;
-  }
-
-  /// Reverse transformation as getPrefixEncodingFromUnsigned.
-  static unsigned getUnsignedFromPrefixEncoding(unsigned U) {
-    if (U & 1)
-      return 0;
-    U >>= 1;
-    return (U & 0x20) ? (((U >> 1) & 0xfe0) | (U & 0x1f)) : (U & 0x1f);
-  }
-
-  /// Returns the next component stored in discriminator.
-  static unsigned getNextComponentInDiscriminator(unsigned D) {
-    if ((D & 1) == 0)
-      return D >> ((D & 0x40) ? 14 : 7);
-    else
-      return D >> 1;
-  }
-
   TempDILocation cloneImpl() const {
     // Get the raw scope/inlinedAt since it is possible to invoke this on
     // a DILocation containing temporary metadata.
@@ -1608,14 +1587,6 @@ class DILocation : public MDNode {
                         getRawInlinedAt(), isImplicitCode());
   }
 
-  static unsigned encodeComponent(unsigned C) {
-    return (C == 0) ? 1U : (getPrefixEncodingFromUnsigned(C) << 1);
-  }
-
-  static unsigned encodingBits(unsigned C) {
-    return (C == 0) ? 1 : (C > 0x1f ? 14 : 7);
-  }
-
 public:
   // Disallow replacing operands.
   void replaceOperandWith(unsigned I, Metadata *New) = delete;
@@ -1762,8 +1733,20 @@ public:
   static
   const DILocation *getMergedLocations(ArrayRef<const DILocation *> Locs);
 
+  /// Return the masked discriminator value for an input discrimnator value D
+  /// (i.e. zero out the (B+1)-th and above bits for D (B is 0-base).
+  // Example: an input of (0x1FF, 7) returns 0xFF.
+  static unsigned getMaskedDiscriminator(unsigned D, unsigned B) {
+    return (D & getN1Bits(B));
+  }
+
+  /// Return the bits used for base discriminators.
+  static unsigned getBaseDiscriminatorBits() { return BASE_DIS_BIT_END; }
+
   /// Returns the base discriminator for a given encoded discriminator \p D.
   static unsigned getBaseDiscriminatorFromDiscriminator(unsigned D) {
+    if (EnableFSDiscriminator)
+      return getMaskedDiscriminator(D, getBaseDiscriminatorBits());
     return getUnsignedFromPrefixEncoding(D);
   }
 
@@ -1785,6 +1768,8 @@ public:
   /// Returns the duplication factor for a given encoded discriminator \p D, or
   /// 1 if no value or 0 is encoded.
   static unsigned getDuplicationFactorFromDiscriminator(unsigned D) {
+    if (EnableFSDiscriminator)
+      return 1;
     D = getNextComponentInDiscriminator(D);
     unsigned Ret = getUnsignedFromPrefixEncoding(D);
     if (Ret == 0)
@@ -2226,6 +2211,14 @@ unsigned DILocation::getCopyIdentifier() const {
 
 Optional<const DILocation *> DILocation::cloneWithBaseDiscriminator(unsigned D) const {
   unsigned BD, DF, CI;
+
+  if (EnableFSDiscriminator) {
+    BD = getBaseDiscriminator();
+    if (D == BD)
+      return this;
+    return cloneWithDiscriminator(D);
+  }
+
   decodeDiscriminator(getDiscriminator(), BD, DF, CI);
   if (D == BD)
     return this;
@@ -2235,6 +2228,8 @@ Optional<const DILocation *> DILocation::cloneWithBaseDiscriminator(unsigned D)
 }
 
 Optional<const DILocation *> DILocation::cloneByMultiplyingDuplicationFactor(unsigned DF) const {
+  assert(!EnableFSDiscriminator && "FSDiscriminator should not call this.");
+
   DF *= getDuplicationFactor();
   if (DF <= 1)
     return this;

llvm/include/llvm/InitializePasses.h

@@ -275,6 +275,7 @@ void initializeLowerSwitchLegacyPassPass(PassRegistry &);
 void initializeLowerTypeTestsPass(PassRegistry&);
 void initializeLowerMatrixIntrinsicsLegacyPassPass(PassRegistry &);
 void initializeLowerMatrixIntrinsicsMinimalLegacyPassPass(PassRegistry &);
+void initializeMIRAddFSDiscriminatorsPass(PassRegistry &);
 void initializeMIRCanonicalizerPass(PassRegistry &);
 void initializeMIRNamerPass(PassRegistry &);
 void initializeMIRPrintingPassPass(PassRegistry&);

llvm/include/llvm/LTO/Config.h

@@ -171,6 +171,9 @@ struct Config {
   bool ShouldDiscardValueNames = true;
   DiagnosticHandlerFunction DiagHandler;
 
+  /// Add FSAFDO discriminators.
+  bool AddFSDiscriminator = false;
+
   /// If this field is set, LTO will write input file paths and symbol
   /// resolutions here in llvm-lto2 command line flag format. This can be
   /// used for testing and for running the LTO pipeline outside of the linker

llvm/include/llvm/Support/Discriminator.h

@@ -0,0 +1,73 @@
+//===---- llvm/Support/Discriminator.h -- Discriminator Utils ---*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the constants and utility functions for discriminators.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_DISCRIMINATOR_H
+#define LLVM_SUPPORT_DISCRIMINATOR_H
+
+// Utility functions for encoding / decoding discriminators.
+/// With a given unsigned int \p U, use up to 13 bits to represent it.
+/// old_bit 1~5  --> new_bit 1~5
+/// old_bit 6~12 --> new_bit 7~13
+/// new_bit_6 is 0 if higher bits (7~13) are all 0
+static inline unsigned getPrefixEncodingFromUnsigned(unsigned U) {
+  U &= 0xfff;
+  return U > 0x1f ? (((U & 0xfe0) << 1) | (U & 0x1f) | 0x20) : U;
+}
+
+/// Reverse transformation as getPrefixEncodingFromUnsigned.
+static inline unsigned getUnsignedFromPrefixEncoding(unsigned U) {
+  if (U & 1)
+    return 0;
+  U >>= 1;
+  return (U & 0x20) ? (((U >> 1) & 0xfe0) | (U & 0x1f)) : (U & 0x1f);
+}
+
+/// Returns the next component stored in discriminator.
+static inline unsigned getNextComponentInDiscriminator(unsigned D) {
+  if ((D & 1) == 0)
+    return D >> ((D & 0x40) ? 14 : 7);
+  else
+    return D >> 1;
+}
+
+static inline unsigned encodeComponent(unsigned C) {
+  return (C == 0) ? 1U : (getPrefixEncodingFromUnsigned(C) << 1);
+}
+
+static inline unsigned encodingBits(unsigned C) {
+  return (C == 0) ? 1 : (C > 0x1f ? 14 : 7);
+}
+
+// Some constants used in FS Discriminators.
+#define BASE_DIS_BIT_BEG 0
+#define BASE_DIS_BIT_END 7
+
+#define PASS_1_DIS_BIT_BEG 8
+#define PASS_1_DIS_BIT_END 13
+
+#define PASS_2_DIS_BIT_BEG 14
+#define PASS_2_DIS_BIT_END 19
+
+#define PASS_3_DIS_BIT_BEG 20
+#define PASS_3_DIS_BIT_END 25
+
+#define PASS_LAST_DIS_BIT_BEG 26
+#define PASS_LAST_DIS_BIT_END 31
+
+// Set bits range [0 .. n] to 1. Used in FS Discriminators.
+static inline unsigned getN1Bits(int N) {
+  if (N >= 31)
+    return 0xFFFFFFFF;
+  return (1 << (N + 1)) - 1;
+}
+
+#endif /* LLVM_SUPPORT_DISCRIMINATOR_H */

llvm/lib/CodeGen/CMakeLists.txt

@@ -106,6 +106,7 @@ add_llvm_component_library(LLVMCodeGen
   MachineStripDebug.cpp
   MachineTraceMetrics.cpp
   MachineVerifier.cpp
+  MIRFSDiscriminator.cpp
   MIRYamlMapping.cpp
   ModuloSchedule.cpp
   MultiHazardRecognizer.cpp

llvm/lib/CodeGen/MIRFSDiscriminator.cpp

@@ -0,0 +1,139 @@
+//===-------- MIRFSDiscriminator.cpp: Flow Sensitive Discriminator --------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file provides the implementation of a machine pass that adds the flow
+// sensitive discriminator to the instruction debug information.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MIRFSDiscriminator.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/Analysis/BlockFrequencyInfoImpl.h"
+#include "llvm/IR/Function.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+#include <unordered_map>
+
+using namespace llvm;
+
+#define DEBUG_TYPE "mirfs-discriminators"
+
+char MIRAddFSDiscriminators::ID = 0;
+
+INITIALIZE_PASS(MIRAddFSDiscriminators, DEBUG_TYPE,
+                "Add MIR Flow Sensitive Discriminators",
+                /* cfg = */ false, /* is_analysis = */ false)
+
+char &llvm::MIRAddFSDiscriminatorsID = MIRAddFSDiscriminators::ID;
+
+FunctionPass *llvm::createMIRAddFSDiscriminatorsPass(unsigned LowBit,
+                                                     unsigned HighBit) {
+  return new MIRAddFSDiscriminators(LowBit, HighBit);
+}
+
+// Compute a hash value using debug line number, and the line numbers from the
+// inline stack.
+static uint64_t getCallStackHash(const MachineBasicBlock &BB,
+                                 const MachineInstr &MI,
+                                 const DILocation *DIL) {
+  uint64_t Ret = MD5Hash(std::to_string(DIL->getLine()));
+  Ret ^= MD5Hash(BB.getName());
+  Ret ^= MD5Hash(DIL->getScope()->getSubprogram()->getLinkageName());
+  for (DIL = DIL->getInlinedAt(); DIL; DIL = DIL->getInlinedAt()) {
+    Ret ^= MD5Hash(std::to_string(DIL->getLine()));
+    Ret ^= MD5Hash(DIL->getScope()->getSubprogram()->getLinkageName());
+  }
+  return Ret;
+}
+
+// Traverse the CFG and assign FD discriminators. If two instructions
+// have the same lineno and discriminator, but residing in different BBs,
+// the latter instruction will get a new discriminator value. The new
+// discriminator keeps the existing discriminator value but sets new bits
+// b/w LowBit and HighBit.
+bool MIRAddFSDiscriminators::runOnMachineFunction(MachineFunction &MF) {
+  if (!EnableFSDiscriminator)
+    return false;
+
+  bool Changed = false;
+  using LocationDiscriminator = std::tuple<StringRef, unsigned, unsigned>;
+  using BBSet = DenseSet<const MachineBasicBlock *>;
+  using LocationDiscriminatorBBMap = DenseMap<LocationDiscriminator, BBSet>;
+  using LocationDiscriminatorCurrPassMap =
+      DenseMap<LocationDiscriminator, unsigned>;
+
+  LocationDiscriminatorBBMap LDBM;
+  LocationDiscriminatorCurrPassMap LDCM;
+
+  // Mask of discriminators before this pass.
+  unsigned BitMaskBefore = getN1Bits(LowBit);
+  // Mask of discriminators including this pass.
+  unsigned BitMaskNow = getN1Bits(HighBit);
+  // Mask of discriminators for bits specific to this pass.
+  unsigned BitMaskThisPass = BitMaskNow ^ BitMaskBefore;
+  unsigned NumNewD = 0;
+
+  LLVM_DEBUG(dbgs() << "MIRAddFSDiscriminators working on Func: "
+                    << MF.getFunction().getName() << "\n");
+  for (MachineBasicBlock &BB : MF) {
+    for (MachineInstr &I : BB) {
+      const DILocation *DIL = I.getDebugLoc().get();
+      if (!DIL)
+        continue;
+      unsigned LineNo = DIL->getLine();
+      if (LineNo == 0)
+        continue;
+      unsigned Discriminator = DIL->getDiscriminator();
+      LocationDiscriminator LD = {DIL->getFilename(), LineNo, Discriminator};
+      auto &BBMap = LDBM[LD];
+      auto R = BBMap.insert(&BB);
+      if (BBMap.size() == 1)
+        continue;
+
+      unsigned DiscriminatorCurrPass;
+      DiscriminatorCurrPass = R.second ? ++LDCM[LD] : LDCM[LD];
+      DiscriminatorCurrPass = DiscriminatorCurrPass << LowBit;
+      DiscriminatorCurrPass += getCallStackHash(BB, I, DIL);
+      DiscriminatorCurrPass &= BitMaskThisPass;
+      unsigned NewD = Discriminator | DiscriminatorCurrPass;
+      const auto *const NewDIL = DIL->cloneWithDiscriminator(NewD);
+      if (!NewDIL) {
+        LLVM_DEBUG(dbgs() << "Could not encode discriminator: "
+                          << DIL->getFilename() << ":" << DIL->getLine() << ":"
+                          << DIL->getColumn() << ":" << Discriminator << " "
+                          << I << "\n");
+        continue;
+      }
+
+      I.setDebugLoc(NewDIL);
+      NumNewD++;
+      LLVM_DEBUG(dbgs() << DIL->getFilename() << ":" << DIL->getLine() << ":"
+                        << DIL->getColumn() << ": add FS discriminator, from "
+                        << Discriminator << " -> " << NewD << "\n");
+      Changed = true;
+    }
+  }
+
+  if (Changed) {
+    Module *M = MF.getFunction().getParent();
+    const char *FSDiscriminatorVar = "__llvm_fs_discriminator__";
+    if (!M->getGlobalVariable(FSDiscriminatorVar)) {
+      auto &Context = M->getContext();
+      // Create a global variable to flag that FSDiscriminators are used.
+      new GlobalVariable(*M, Type::getInt1Ty(Context), true,
+                         GlobalValue::WeakAnyLinkage,
+                         ConstantInt::getTrue(Context), FSDiscriminatorVar);
+    }
+
+    LLVM_DEBUG(dbgs() << "Num of FS Discriminators: " << NumNewD << "\n");
+  }
+
+  return Changed;
+}

llvm/lib/CodeGen/TargetPassConfig.cpp

@@ -39,6 +39,7 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/Discriminator.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/SaveAndRestore.h"
 #include "llvm/Support/Threading.h"
@@ -165,6 +166,13 @@ static cl::opt<GlobalISelAbortMode> EnableGlobalISelAbort(
         clEnumValN(GlobalISelAbortMode::DisableWithDiag, "2",
                    "Disable the abort but emit a diagnostic on failure")));
 
+// An option that disables inserting FS-AFDO discriminators before emit.
+// This is mainly for debugging and tuning purpose.
+static cl::opt<bool>
+    FSNoFinalDiscrim("fs-no-final-discrim", cl::init(false), cl::Hidden,
+                     cl::desc("Do not insert FS-AFDO discriminators before "
+                              "emit."));
+
 // Temporary option to allow experimenting with MachineScheduler as a post-RA
 // scheduler. Targets can "properly" enable this with
 // substitutePass(&PostRASchedulerID, &PostMachineSchedulerID).
@@ -334,6 +342,8 @@ struct InsertedPass {
 
 namespace llvm {
 
+extern cl::opt<bool> EnableFSDiscriminator;
+
 class PassConfigImpl {
 public:
   // List of passes explicitly substituted by this target. Normally this is
@@ -1167,6 +1177,10 @@ void TargetPassConfig::addMachinePasses() {
   addPass(&XRayInstrumentationID);
   addPass(&PatchableFunctionID);
 
+  if (EnableFSDiscriminator && !FSNoFinalDiscrim)
+    addPass(createMIRAddFSDiscriminatorsPass(PASS_LAST_DIS_BIT_BEG,
+                                             PASS_LAST_DIS_BIT_END));
+
   addPreEmitPass();
 
   if (TM->Options.EnableIPRA)

llvm/lib/IR/DebugInfoMetadata.cpp

@@ -23,6 +23,13 @@
 
 using namespace llvm;
 
+namespace llvm {
+// Use FS-AFDO discriminator.
+cl::opt<bool> EnableFSDiscriminator(
+    "enable-fs-discriminator", cl::Hidden, cl::init(false),
+    cl::desc("Enable adding flow sensitive discriminators"));
+} // namespace llvm
+
 const DIExpression::FragmentInfo DebugVariable::DefaultFragment = {
     std::numeric_limits<uint64_t>::max(), std::numeric_limits<uint64_t>::min()};
 

llvm/lib/LTO/LTOBackend.cpp

@@ -215,10 +215,15 @@ static void runNewPMPasses(const Config &Conf, Module &Mod, TargetMachine *TM,
                         PGOOptions::SampleUse, PGOOptions::NoCSAction, true);
   else if (Conf.RunCSIRInstr) {
     PGOOpt = PGOOptions("", Conf.CSIRProfile, Conf.ProfileRemapping,
-                        PGOOptions::IRUse, PGOOptions::CSIRInstr);
+                        PGOOptions::IRUse, PGOOptions::CSIRInstr,
+                        Conf.AddFSDiscriminator);
   } else if (!Conf.CSIRProfile.empty()) {
     PGOOpt = PGOOptions(Conf.CSIRProfile, "", Conf.ProfileRemapping,
-                        PGOOptions::IRUse, PGOOptions::CSIRUse);
+                        PGOOptions::IRUse, PGOOptions::CSIRUse,
+                        Conf.AddFSDiscriminator);
+  } else if (Conf.AddFSDiscriminator) {
+    PGOOpt = PGOOptions("", "", "", PGOOptions::NoAction,
+                        PGOOptions::NoCSAction, true);
   }
 
   LoopAnalysisManager LAM;

llvm/lib/Transforms/Utils/LoopUnroll.cpp

@@ -570,7 +570,9 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
   for (Loop *SubLoop : *L)
     LoopsToSimplify.insert(SubLoop);
 
-  if (Header->getParent()->isDebugInfoForProfiling())
+  // When a FSDiscriminator is enabled, we don't need to add the multiply
+  // factors to the discriminators.
+  if (Header->getParent()->isDebugInfoForProfiling() && !EnableFSDiscriminator)
     for (BasicBlock *BB : L->getBlocks())
       for (Instruction &I : *BB)
         if (!isa<DbgInfoIntrinsic>(&I))

llvm/lib/Transforms/Utils/LoopUnrollAndJam.cpp

@@ -349,7 +349,9 @@ llvm::UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
   LoopBlocksDFS::RPOIterator BlockBegin = DFS.beginRPO();
   LoopBlocksDFS::RPOIterator BlockEnd = DFS.endRPO();
 
-  if (Header->getParent()->isDebugInfoForProfiling())
+  // When a FSDiscriminator is enabled, we don't need to add the multiply
+  // factors to the discriminators.
+  if (Header->getParent()->isDebugInfoForProfiling() && !EnableFSDiscriminator)
     for (BasicBlock *BB : L->getBlocks())
       for (Instruction &I : *BB)
         if (!isa<DbgInfoIntrinsic>(&I))

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1047,8 +1047,11 @@ static Instruction *getDebugLocFromInstOrOperands(Instruction *I) {
 void InnerLoopVectorizer::setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr) {
   if (const Instruction *Inst = dyn_cast_or_null<Instruction>(Ptr)) {
     const DILocation *DIL = Inst->getDebugLoc();
+
+    // When a FSDiscriminator is enabled, we don't need to add the multiply
+    // factors to the discriminators.
     if (DIL && Inst->getFunction()->isDebugInfoForProfiling() &&
-        !isa<DbgInfoIntrinsic>(Inst)) {
+        !isa<DbgInfoIntrinsic>(Inst) && !EnableFSDiscriminator) {
       assert(!VF.isScalable() && "scalable vectors not yet supported.");
       auto NewDIL =
           DIL->cloneByMultiplyingDuplicationFactor(UF * VF.getKnownMinValue());
@@ -1058,8 +1061,7 @@ void InnerLoopVectorizer::setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr)
         LLVM_DEBUG(dbgs()
                    << "Failed to create new discriminator: "
                    << DIL->getFilename() << " Line: " << DIL->getLine());
-    }
+    } else
-    else
       B.SetCurrentDebugLocation(DIL);
   } else
     B.SetCurrentDebugLocation(DebugLoc());

llvm/test/CodeGen/X86/fsafdo_test1.ll

@@ -0,0 +1,60 @@
+; RUN: llc -enable-fs-discriminator < %s | FileCheck %s
+;
+; Check that fs-afdo discriminators are generated.
+; CHECK: .loc    1 7 3 is_stmt 0 discriminator 2 # foo.c:7:3
+; Check: .loc    1 9 5 is_stmt 1 discriminator 2 # foo.c:9:5
+; CHECK: .loc    1 9 5 is_stmt 0 discriminator 3623878658 # foo.c:9:5
+; CHECK: .loc    1 7 3 is_stmt 1 discriminator 805306370 # foo.c:7:3
+; Check that variable __llvm_fs_discriminator__ is generated.
+; CHECK: .type   __llvm_fs_discriminator__,@object # @__llvm_fs_discriminator__
+; CHECK: .section        .rodata,"a",@progbits
+; CHECK: .weak   __llvm_fs_discriminator__
+; CHECK: __llvm_fs_discriminator__:
+; CHECK: .byte   1
+; CHECK: .size   __llvm_fs_discriminator__, 1
+
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.Node = type { %struct.Node* }
+
+define i32 @foo(%struct.Node* readonly %node, %struct.Node* readnone %root) !dbg !6 {
+entry:
+  %cmp = icmp eq %struct.Node* %node, %root, !dbg !8
+  br i1 %cmp, label %while.end4, label %while.cond1.preheader.lr.ph, !dbg !10
+
+while.cond1.preheader.lr.ph:
+  %tobool = icmp eq %struct.Node* %node, null
+  br i1 %tobool, label %while.cond1.preheader.us.preheader, label %while.body2.preheader, !dbg !11
+
+while.body2.preheader:
+  br label %while.body2, !dbg !11
+
+while.cond1.preheader.us.preheader:
+  br label %while.cond1.preheader.us, !dbg !10
+
+while.cond1.preheader.us:
+  br label %while.cond1.preheader.us, !dbg !10
+
+while.body2:
+  br label %while.body2, !dbg !11
+
+while.end4:
+  ret i32 0, !dbg !12
+}
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, isOptimized: true, emissionKind: LineTablesOnly)
+!1 = !DIFile(filename: "foo.c", directory: "b/")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{}
+!6 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 5, type: !7, isLocal: false, isDefinition: true, scopeLine: 5, flags: DIFlagPrototyped, isOptimized: true, unit: !0, retainedNodes: !2)
+!7 = !DISubroutineType(types: !2)
+!8 = !DILocation(line: 7, column: 15, scope: !9)
+!9 = !DILexicalBlockFile(scope: !6, file: !1, discriminator: 2)
+!10 = !DILocation(line: 7, column: 3, scope: !9)
+!11 = !DILocation(line: 9, column: 5, scope: !9)
+!12 = !DILocation(line: 14, column: 3, scope: !6)

llvm/test/CodeGen/X86/fsafdo_test2.ll

@@ -0,0 +1,233 @@
+; RUN: llc -enable-fs-discriminator < %s | FileCheck %s
+;;
+;; C source code for the test (compiler at -O3):
+;; // A test case for loop unroll.
+;;
+;; __attribute__((noinline)) int bar(int i){
+;;   volatile int j;
+;;   j = i;
+;;   return j;
+;; }
+;;
+;; unsigned sum;
+;; __attribute__((noinline)) void work(int i){
+;;   if (sum % 7)
+;;     sum += i;
+;;   else
+;;     sum -= i;
+;; }
+;;
+;; __attribute__((noinline)) void foo(){
+;;   int i, j;
+;;   for (j = 0; j < 48; j++)
+;;     for (i = 0; i < 4; i++) {
+;;       int ii = bar(i+j*48);
+;;       if (ii % 2)
+;;         work(ii*2);
+;;       if (ii % 4)
+;;         work(ii*3);
+;;   }
+;; }
+;;
+;; int main() {
+;;   int i;
+;;   for (i = 0; i < 10000000; i++) {
+;;     foo();
+;;   }
+;; }
+;;
+;; Check that fs-afdo discriminators are generated.
+; CHECK: .loc    1 23 9 is_stmt 0 discriminator 1 # unroll.c:23:9
+; CHECK: .loc    1 23 9 is_stmt 0 discriminator 1073741825 # unroll.c:23:9
+; CHECK: .loc    1 23 9 is_stmt 0 discriminator 2147483649 # unroll.c:23:9
+; CHECK: .loc    1 23 9 is_stmt 0 discriminator 268435457 # unroll.c:23:9
+;;
+;; Check that variable __llvm_fs_discriminator__ is generated.
+; CHECK: .type   __llvm_fs_discriminator__,@object # @__llvm_fs_discriminator__
+; CHECK: .section        .rodata,"a",@progbits
+; CHECK: .weak   __llvm_fs_discriminator__
+; CHECK: __llvm_fs_discriminator__:
+; CHECK: .byte   1
+; CHECK: .size   __llvm_fs_discriminator__, 1
+
+target triple = "x86_64-unknown-linux-gnu"
+
+@sum = dso_local local_unnamed_addr global i32 0, align 4
+
+declare i32 @bar(i32 %i) #0
+declare void @work(i32 %i) #2
+
+define dso_local void @foo() #0 !dbg !29 {
+entry:
+  br label %for.cond1.preheader, !dbg !30
+
+for.cond1.preheader:
+  %j.012 = phi i32 [ 0, %entry ], [ %inc11, %if.end9.3 ]
+  %mul = mul nuw nsw i32 %j.012, 48
+  %call = tail call i32 @bar(i32 %mul), !dbg !32
+  %0 = and i32 %call, 1, !dbg !33
+  %tobool.not = icmp eq i32 %0, 0, !dbg !33
+  br i1 %tobool.not, label %if.end, label %if.then, !dbg !35
+
+if.then:
+  %mul4 = shl nsw i32 %call, 1, !dbg !36
+  tail call void @work(i32 %mul4), !dbg !37
+  br label %if.end, !dbg !38
+
+if.end:
+  %1 = and i32 %call, 3, !dbg !39
+  %tobool6.not = icmp eq i32 %1, 0, !dbg !39
+  br i1 %tobool6.not, label %if.end9, label %if.then7, !dbg !40
+
+if.then7:
+  %mul8 = mul nsw i32 %call, 3, !dbg !41
+  tail call void @work(i32 %mul8), !dbg !42
+  br label %if.end9, !dbg !43
+
+if.end9:
+  %add.1 = or i32 %mul, 1, !dbg !44
+  %call.1 = tail call i32 @bar(i32 %add.1), !dbg !32
+  %2 = and i32 %call.1, 1, !dbg !33
+  %tobool.not.1 = icmp eq i32 %2, 0, !dbg !33
+  br i1 %tobool.not.1, label %if.end.1, label %if.then.1, !dbg !35
+
+for.end12:
+  ret void, !dbg !45
+
+if.then.1:
+  %mul4.1 = shl nsw i32 %call.1, 1, !dbg !36
+  tail call void @work(i32 %mul4.1), !dbg !37
+  br label %if.end.1, !dbg !38
+
+if.end.1:
+  %3 = and i32 %call.1, 3, !dbg !39
+  %tobool6.not.1 = icmp eq i32 %3, 0, !dbg !39
+  br i1 %tobool6.not.1, label %if.end9.1, label %if.then7.1, !dbg !40
+
+if.then7.1:
+  %mul8.1 = mul nsw i32 %call.1, 3, !dbg !41
+  tail call void @work(i32 %mul8.1), !dbg !42
+  br label %if.end9.1, !dbg !43
+
+if.end9.1:
+  %add.2 = or i32 %mul, 2, !dbg !44
+  %call.2 = tail call i32 @bar(i32 %add.2), !dbg !32
+  %4 = and i32 %call.2, 1, !dbg !33
+  %tobool.not.2 = icmp eq i32 %4, 0, !dbg !33
+  br i1 %tobool.not.2, label %if.end.2, label %if.then.2, !dbg !35
+
+if.then.2:
+  %mul4.2 = shl nsw i32 %call.2, 1, !dbg !36
+  tail call void @work(i32 %mul4.2), !dbg !37
+  br label %if.end.2, !dbg !38
+
+if.end.2:
+  %5 = and i32 %call.2, 3, !dbg !39
+  %tobool6.not.2 = icmp eq i32 %5, 0, !dbg !39
+  br i1 %tobool6.not.2, label %if.end9.2, label %if.then7.2, !dbg !40
+
+if.then7.2:
+  %mul8.2 = mul nsw i32 %call.2, 3, !dbg !41
+  tail call void @work(i32 %mul8.2), !dbg !42
+  br label %if.end9.2, !dbg !43
+
+if.end9.2:
+  %add.3 = or i32 %mul, 3, !dbg !44
+  %call.3 = tail call i32 @bar(i32 %add.3), !dbg !32
+  %6 = and i32 %call.3, 1, !dbg !33
+  %tobool.not.3 = icmp eq i32 %6, 0, !dbg !33
+  br i1 %tobool.not.3, label %if.end.3, label %if.then.3, !dbg !35
+
+if.then.3:
+  %mul4.3 = shl nsw i32 %call.3, 1, !dbg !36
+  tail call void @work(i32 %mul4.3), !dbg !37
+  br label %if.end.3, !dbg !38
+
+if.end.3:
+  %7 = and i32 %call.3, 3, !dbg !39
+  %tobool6.not.3 = icmp eq i32 %7, 0, !dbg !39
+  br i1 %tobool6.not.3, label %if.end9.3, label %if.then7.3, !dbg !40
+
+if.then7.3:
+  %mul8.3 = mul nsw i32 %call.3, 3, !dbg !41
+  tail call void @work(i32 %mul8.3), !dbg !42
+  br label %if.end9.3, !dbg !43
+
+if.end9.3:
+  %inc11 = add nuw nsw i32 %j.012, 1, !dbg !46
+  %exitcond.not = icmp eq i32 %inc11, 48, !dbg !48
+  br i1 %exitcond.not, label %for.end12, label %for.cond1.preheader, !dbg !30, !llvm.loop !49
+}
+
+
+attributes #0 = { noinline nounwind uwtable "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { argmemonly nounwind willreturn }
+attributes #2 = { nofree noinline norecurse nounwind uwtable "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #3 = { nounwind uwtable "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, splitDebugInlining: false, debugInfoForProfiling: true, nameTableKind: None)
+!1 = !DIFile(filename: "unroll.c", directory: "a/")
+!2 = !{}
+!3 = !{i32 7, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!7 = distinct !DISubprogram(name: "bar", scope: !1, file: !1, line: 3, type: !8, scopeLine: 3, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 4, column: 3, scope: !7)
+!10 = !DILocation(line: 5, column: 5, scope: !7)
+!11 = !{!12, !12, i64 0}
+!12 = !{!"int", !13, i64 0}
+!13 = !{!"omnipotent char", !14, i64 0}
+!14 = !{!"Simple C/C++ TBAA"}
+!15 = !DILocation(line: 6, column: 10, scope: !7)
+!16 = !DILocation(line: 7, column: 1, scope: !7)
+!17 = !DILocation(line: 6, column: 3, scope: !18)
+!18 = !DILexicalBlockFile(scope: !7, file: !1, discriminator: 1)
+!19 = distinct !DISubprogram(name: "work", scope: !1, file: !1, line: 10, type: !8, scopeLine: 10, flags: DIFlagPrototyped | DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!20 = !DILocation(line: 11, column: 7, scope: !19)
+!21 = !DILocation(line: 11, column: 11, scope: !22)
+!22 = !DILexicalBlockFile(scope: !19, file: !1, discriminator: 1)
+!23 = !DILocation(line: 11, column: 11, scope: !24)
+!24 = !DILexicalBlockFile(scope: !19, file: !1, discriminator: 2)
+!25 = !DILocation(line: 11, column: 7, scope: !26)
+!26 = !DILexicalBlockFile(scope: !19, file: !1, discriminator: 3)
+!27 = !DILocation(line: 0, scope: !22)
+!28 = !DILocation(line: 15, column: 1, scope: !19)
+!29 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 17, type: !8, scopeLine: 17, flags: DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!30 = !DILocation(line: 19, column: 3, scope: !31)
+!31 = !DILexicalBlockFile(scope: !29, file: !1, discriminator: 2)
+!32 = !DILocation(line: 21, column: 16, scope: !31)
+!33 = !DILocation(line: 22, column: 14, scope: !34)
+!34 = !DILexicalBlockFile(scope: !29, file: !1, discriminator: 1)
+!35 = !DILocation(line: 22, column: 11, scope: !31)
+!36 = !DILocation(line: 23, column: 16, scope: !29)
+!37 = !DILocation(line: 23, column: 9, scope: !34)
+!38 = !DILocation(line: 23, column: 9, scope: !31)
+!39 = !DILocation(line: 24, column: 14, scope: !34)
+!40 = !DILocation(line: 24, column: 11, scope: !31)
+!41 = !DILocation(line: 25, column: 16, scope: !29)
+!42 = !DILocation(line: 25, column: 9, scope: !34)
+!43 = !DILocation(line: 25, column: 9, scope: !31)
+!44 = !DILocation(line: 21, column: 21, scope: !34)
+!45 = !DILocation(line: 27, column: 1, scope: !29)
+!46 = !DILocation(line: 19, column: 24, scope: !47)
+!47 = !DILexicalBlockFile(scope: !29, file: !1, discriminator: 3)
+!48 = !DILocation(line: 19, column: 17, scope: !34)
+!49 = distinct !{!49, !50, !51}
+!50 = !DILocation(line: 19, column: 3, scope: !29)
+!51 = !DILocation(line: 26, column: 3, scope: !29)
+!52 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 29, type: !8, scopeLine: 29, flags: DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !2)
+!53 = !DILocation(line: 31, column: 3, scope: !54)
+!54 = !DILexicalBlockFile(scope: !52, file: !1, discriminator: 2)
+!55 = !DILocation(line: 32, column: 5, scope: !52)
+!56 = !DILocation(line: 31, column: 30, scope: !57)
+!57 = !DILexicalBlockFile(scope: !52, file: !1, discriminator: 3)
+!58 = !DILocation(line: 31, column: 17, scope: !59)
+!59 = !DILexicalBlockFile(scope: !52, file: !1, discriminator: 1)
+!60 = distinct !{!60, !61, !62}
+!61 = !DILocation(line: 31, column: 3, scope: !52)
+!62 = !DILocation(line: 33, column: 3, scope: !52)
+!63 = !DILocation(line: 34, column: 1, scope: !52)