Revert "Revert r347596 "Support for inserting profile-directed cache prefetches""

Summary:
This reverts commit d8517b96dfbd42e6a8db33c50d1fa1e58e63fbb9.

Fix: correct  the use of DenseMap.

Reviewers: davidxl, hans, wmi

Reviewed By: wmi

Subscribers: mgorny, eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D55088

llvm-svn: 347938

lib/Target/X86/CMakeLists.txt

@@ -30,6 +30,7 @@ set(sources
   X86CmovConversion.cpp
   X86CondBrFolding.cpp
   X86DomainReassignment.cpp
+  X86DiscriminateMemOps.cpp
   X86ExpandPseudo.cpp
   X86FastISel.cpp
   X86FixupBWInsts.cpp
@@ -44,6 +45,7 @@ set(sources
   X86ISelLowering.cpp
   X86IndirectBranchTracking.cpp
   X86InterleavedAccess.cpp
+  X86InsertPrefetch.cpp
   X86InstrFMA3Info.cpp
   X86InstrFoldTables.cpp
   X86InstrInfo.cpp

lib/Target/X86/LLVMBuild.txt

@@ -31,5 +31,5 @@ has_jit = 1
 type = Library
 name = X86CodeGen
 parent = X86
-required_libraries = Analysis AsmPrinter CodeGen Core MC SelectionDAG Support Target X86AsmPrinter X86Desc X86Info X86Utils GlobalISel
+required_libraries = Analysis AsmPrinter CodeGen Core MC SelectionDAG Support Target X86AsmPrinter X86Desc X86Info X86Utils GlobalISel ProfileData
 add_to_library_groups = X86

lib/Target/X86/X86.h

@@ -122,6 +122,13 @@ FunctionPass *createX86EvexToVexInsts();
 /// This pass creates the thunks for the retpoline feature.
 FunctionPass *createX86RetpolineThunksPass();
 
+/// This pass ensures instructions featuring a memory operand
+/// have distinctive <LineNumber, Discriminator> (with respect to eachother)
+FunctionPass *createX86DiscriminateMemOpsPass();
+
+/// This pass applies profiling information to insert cache prefetches.
+FunctionPass *createX86InsertPrefetchPass();
+
 InstructionSelector *createX86InstructionSelector(const X86TargetMachine &TM,
                                                   X86Subtarget &,
                                                   X86RegisterBankInfo &);

lib/Target/X86/X86DiscriminateMemOps.cpp

@@ -0,0 +1,132 @@
+//===- X86DiscriminateMemOps.cpp - Unique IDs for Mem Ops -----------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// This pass aids profile-driven cache prefetch insertion by ensuring all
+/// instructions that have a memory operand are distinguishible from each other.
+///
+//===----------------------------------------------------------------------===//
+
+#include "X86.h"
+#include "X86InstrBuilder.h"
+#include "X86InstrInfo.h"
+#include "X86MachineFunctionInfo.h"
+#include "X86Subtarget.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "llvm/ProfileData/SampleProfReader.h"
+#include "llvm/Transforms/IPO/SampleProfile.h"
+using namespace llvm;
+
+namespace {
+
+using Location = std::pair<StringRef, unsigned>;
+
+Location diToLocation(const DILocation *Loc) {
+  return std::make_pair(Loc->getFilename(), Loc->getLine());
+}
+
+/// Ensure each instruction having a memory operand has a distinct <LineNumber,
+/// Discriminator> pair.
+void updateDebugInfo(MachineInstr *MI, const DILocation *Loc) {
+  DebugLoc DL(Loc);
+  MI->setDebugLoc(DL);
+}
+
+class X86DiscriminateMemOps : public MachineFunctionPass {
+  bool runOnMachineFunction(MachineFunction &MF) override;
+  StringRef getPassName() const override {
+    return "X86 Discriminate Memory Operands";
+  }
+
+public:
+  static char ID;
+
+  /// Default construct and initialize the pass.
+  X86DiscriminateMemOps();
+};
+
+} // end anonymous namespace
+
+//===----------------------------------------------------------------------===//
+//            Implementation
+//===----------------------------------------------------------------------===//
+
+char X86DiscriminateMemOps::ID = 0;
+
+/// Default construct and initialize the pass.
+X86DiscriminateMemOps::X86DiscriminateMemOps() : MachineFunctionPass(ID) {}
+
+bool X86DiscriminateMemOps::runOnMachineFunction(MachineFunction &MF) {
+  DISubprogram *FDI = MF.getFunction().getSubprogram();
+  if (!FDI || !FDI->getUnit()->getDebugInfoForProfiling())
+    return false;
+
+  // Have a default DILocation, if we find instructions with memops that don't
+  // have any debug info.
+  const DILocation *ReferenceDI =
+      DILocation::get(FDI->getContext(), FDI->getLine(), 0, FDI);
+
+  DenseMap<Location, unsigned> MemOpDiscriminators;
+  MemOpDiscriminators[diToLocation(ReferenceDI)] = 0;
+
+  // Figure out the largest discriminator issued for each Location. When we
+  // issue new discriminators, we can thus avoid issuing discriminators
+  // belonging to instructions that don't have memops. This isn't a requirement
+  // for the goals of this pass, however, it avoids unnecessary ambiguity.
+  for (auto &MBB : MF) {
+    for (auto &MI : MBB) {
+      const auto &DI = MI.getDebugLoc();
+      if (!DI)
+        continue;
+      Location Loc = diToLocation(DI);
+      MemOpDiscriminators[Loc] =
+          std::max(MemOpDiscriminators[Loc], DI->getBaseDiscriminator());
+    }
+  }
+
+  // Keep track of the discriminators seen at each Location. If an instruction's
+  // DebugInfo has a Location and discriminator we've already seen, replace its
+  // discriminator with a new one, to guarantee uniqueness.
+  DenseMap<Location, DenseSet<unsigned>> Seen;
+
+  bool Changed = false;
+  for (auto &MBB : MF) {
+    for (auto &MI : MBB) {
+      if (X86II::getMemoryOperandNo(MI.getDesc().TSFlags) < 0)
+        continue;
+      const DILocation *DI = MI.getDebugLoc();
+      if (!DI) {
+        DI = ReferenceDI;
+      }
+      DenseSet<unsigned> &Set = Seen[diToLocation(DI)];
+      const std::pair<DenseSet<unsigned>::iterator, bool> TryInsert =
+          Set.insert(DI->getBaseDiscriminator());
+      if (!TryInsert.second) {
+        DI = DI->setBaseDiscriminator(++MemOpDiscriminators[diToLocation(DI)]);
+        updateDebugInfo(&MI, DI);
+        Changed = true;
+        const std::pair<DenseSet<unsigned>::iterator, bool> MustInsert =
+            Set.insert(DI->getBaseDiscriminator());
+        assert(MustInsert.second);
+      }
+
+      // Bump the reference DI to avoid cramming discriminators on line 0.
+      // FIXME(mtrofin): pin ReferenceDI on blocks or first instruction with DI
+      // in a block. It's more consistent than just relying on the last memop
+      // instruction we happened to see.
+      ReferenceDI = DI;
+    }
+  }
+  return Changed;
+}
+
+FunctionPass *llvm::createX86DiscriminateMemOpsPass() {
+  return new X86DiscriminateMemOps();
+}

lib/Target/X86/X86InsertPrefetch.cpp

@@ -0,0 +1,253 @@
+//===------- X86InsertPrefetch.cpp - Insert cache prefetch hints ----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass applies cache prefetch instructions based on a profile. The pass
+// assumes DiscriminateMemOps ran immediately before, to ensure debug info
+// matches the one used at profile generation time. The profile is encoded in
+// afdo format (text or binary). It contains prefetch hints recommendations.
+// Each recommendation is made in terms of debug info locations, a type (i.e.
+// nta, t{0|1|2}) and a delta. The debug info identifies an instruction with a
+// memory operand (see X86DiscriminateMemOps). The prefetch will be made for
+// a location at that memory operand + the delta specified in the
+// recommendation.
+//
+//===----------------------------------------------------------------------===//
+
+#include "X86.h"
+#include "X86InstrBuilder.h"
+#include "X86InstrInfo.h"
+#include "X86MachineFunctionInfo.h"
+#include "X86Subtarget.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "llvm/ProfileData/SampleProfReader.h"
+#include "llvm/Transforms/IPO/SampleProfile.h"
+using namespace llvm;
+using namespace sampleprof;
+
+static cl::opt<std::string>
+    PrefetchHintsFile("prefetch-hints-file",
+                      cl::desc("Path to the prefetch hints profile."),
+                      cl::Hidden);
+namespace {
+
+class X86InsertPrefetch : public MachineFunctionPass {
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+  bool doInitialization(Module &) override;
+
+  bool runOnMachineFunction(MachineFunction &MF) override;
+  struct PrefetchInfo {
+    unsigned InstructionID;
+    int64_t Delta;
+  };
+  typedef SmallVectorImpl<PrefetchInfo> Prefetches;
+  bool findPrefetchInfo(const FunctionSamples *Samples, const MachineInstr &MI,
+                        Prefetches &prefetches) const;
+
+public:
+  static char ID;
+  X86InsertPrefetch(const std::string &PrefetchHintsFilename);
+  StringRef getPassName() const override {
+    return "X86 Insert Cache Prefetches";
+  }
+
+private:
+  std::string Filename;
+  std::unique_ptr<SampleProfileReader> Reader;
+};
+
+using PrefetchHints = SampleRecord::CallTargetMap;
+
+// Return any prefetching hints for the specified MachineInstruction. The hints
+// are returned as pairs (name, delta).
+ErrorOr<PrefetchHints> getPrefetchHints(const FunctionSamples *TopSamples,
+                                        const MachineInstr &MI) {
+  if (const auto &Loc = MI.getDebugLoc())
+    if (const auto *Samples = TopSamples->findFunctionSamples(Loc))
+      return Samples->findCallTargetMapAt(FunctionSamples::getOffset(Loc),
+                                          Loc->getBaseDiscriminator());
+  return std::error_code();
+}
+
+// The prefetch instruction can't take memory operands involving vector
+// registers.
+bool IsMemOpCompatibleWithPrefetch(const MachineInstr &MI, int Op) {
+  unsigned BaseReg = MI.getOperand(Op + X86::AddrBaseReg).getReg();
+  unsigned IndexReg = MI.getOperand(Op + X86::AddrIndexReg).getReg();
+  return (BaseReg == 0 ||
+          X86MCRegisterClasses[X86::GR64RegClassID].contains(BaseReg) ||
+          X86MCRegisterClasses[X86::GR32RegClassID].contains(BaseReg)) &&
+         (IndexReg == 0 ||
+          X86MCRegisterClasses[X86::GR64RegClassID].contains(IndexReg) ||
+          X86MCRegisterClasses[X86::GR32RegClassID].contains(IndexReg));
+}
+
+} // end anonymous namespace
+
+//===----------------------------------------------------------------------===//
+//            Implementation
+//===----------------------------------------------------------------------===//
+
+char X86InsertPrefetch::ID = 0;
+
+X86InsertPrefetch::X86InsertPrefetch(const std::string &PrefetchHintsFilename)
+    : MachineFunctionPass(ID), Filename(PrefetchHintsFilename) {}
+
+/// Return true if the provided MachineInstruction has cache prefetch hints. In
+/// that case, the prefetch hints are stored, in order, in the Prefetches
+/// vector.
+bool X86InsertPrefetch::findPrefetchInfo(const FunctionSamples *TopSamples,
+                                         const MachineInstr &MI,
+                                         Prefetches &Prefetches) const {
+  assert(Prefetches.empty() &&
+         "Expected caller passed empty PrefetchInfo vector.");
+  static const std::pair<const StringRef, unsigned> HintTypes[] = {
+      {"_nta_", X86::PREFETCHNTA},
+      {"_t0_", X86::PREFETCHT0},
+      {"_t1_", X86::PREFETCHT1},
+      {"_t2_", X86::PREFETCHT2},
+  };
+  static const char *SerializedPrefetchPrefix = "__prefetch";
+
+  const ErrorOr<PrefetchHints> T = getPrefetchHints(TopSamples, MI);
+  if (!T)
+    return false;
+  int16_t max_index = -1;
+  // Convert serialized prefetch hints into PrefetchInfo objects, and populate
+  // the Prefetches vector.
+  for (const auto &S_V : *T) {
+    StringRef Name = S_V.getKey();
+    if (Name.consume_front(SerializedPrefetchPrefix)) {
+      int64_t D = static_cast<int64_t>(S_V.second);
+      unsigned IID = 0;
+      for (const auto &HintType : HintTypes) {
+        if (Name.startswith(HintType.first)) {
+          Name = Name.drop_front(HintType.first.size());
+          IID = HintType.second;
+          break;
+        }
+      }
+      if (IID == 0)
+        return false;
+      uint8_t index = 0;
+      Name.consumeInteger(10, index);
+
+      if (index >= Prefetches.size())
+        Prefetches.resize(index + 1);
+      Prefetches[index] = {IID, D};
+      max_index = std::max(max_index, static_cast<int16_t>(index));
+    }
+  }
+  assert(max_index + 1 >= 0 &&
+         "Possible overflow: max_index + 1 should be positive.");
+  assert(static_cast<size_t>(max_index + 1) == Prefetches.size() &&
+         "The number of prefetch hints received should match the number of "
+         "PrefetchInfo objects returned");
+  return !Prefetches.empty();
+}
+
+bool X86InsertPrefetch::doInitialization(Module &M) {
+  if (Filename.empty())
+    return false;
+
+  LLVMContext &Ctx = M.getContext();
+  ErrorOr<std::unique_ptr<SampleProfileReader>> ReaderOrErr =
+      SampleProfileReader::create(Filename, Ctx);
+  if (std::error_code EC = ReaderOrErr.getError()) {
+    std::string Msg = "Could not open profile: " + EC.message();
+    Ctx.diagnose(DiagnosticInfoSampleProfile(Filename, Msg,
+                                             DiagnosticSeverity::DS_Warning));
+    return false;
+  }
+  Reader = std::move(ReaderOrErr.get());
+  Reader->read();
+  return true;
+}
+
+void X86InsertPrefetch::getAnalysisUsage(AnalysisUsage &AU) const {
+  AU.setPreservesAll();
+  AU.addRequired<MachineModuleInfo>();
+}
+
+bool X86InsertPrefetch::runOnMachineFunction(MachineFunction &MF) {
+  if (!Reader)
+    return false;
+  const FunctionSamples *Samples = Reader->getSamplesFor(MF.getFunction());
+  if (!Samples)
+    return false;
+
+  bool Changed = false;
+
+  const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
+  SmallVector<PrefetchInfo, 4> Prefetches;
+  for (auto &MBB : MF) {
+    for (auto MI = MBB.instr_begin(); MI != MBB.instr_end();) {
+      auto Current = MI;
+      ++MI;
+
+      int Offset = X86II::getMemoryOperandNo(Current->getDesc().TSFlags);
+      if (Offset < 0)
+        continue;
+      unsigned Bias = X86II::getOperandBias(Current->getDesc());
+      int MemOpOffset = Offset + Bias;
+      // FIXME(mtrofin): ORE message when the recommendation cannot be taken.
+      if (!IsMemOpCompatibleWithPrefetch(*Current, MemOpOffset))
+        continue;
+      Prefetches.clear();
+      if (!findPrefetchInfo(Samples, *Current, Prefetches))
+        continue;
+      assert(!Prefetches.empty() &&
+             "The Prefetches vector should contain at least a value if "
+             "findPrefetchInfo returned true.");
+      for (auto &PrefInfo : Prefetches) {
+        unsigned PFetchInstrID = PrefInfo.InstructionID;
+        int64_t Delta = PrefInfo.Delta;
+        const MCInstrDesc &Desc = TII->get(PFetchInstrID);
+        MachineInstr *PFetch =
+            MF.CreateMachineInstr(Desc, Current->getDebugLoc(), true);
+        MachineInstrBuilder MIB(MF, PFetch);
+
+        assert(X86::AddrBaseReg == 0 && X86::AddrScaleAmt == 1 &&
+               X86::AddrIndexReg == 2 && X86::AddrDisp == 3 &&
+               X86::AddrSegmentReg == 4 &&
+               "Unexpected change in X86 operand offset order.");
+
+        // This assumes X86::AddBaseReg = 0, {...}ScaleAmt = 1, etc.
+        // FIXME(mtrofin): consider adding a:
+        //     MachineInstrBuilder::set(unsigned offset, op).
+        MIB.addReg(Current->getOperand(MemOpOffset + X86::AddrBaseReg).getReg())
+            .addImm(
+                Current->getOperand(MemOpOffset + X86::AddrScaleAmt).getImm())
+            .addReg(
+                Current->getOperand(MemOpOffset + X86::AddrIndexReg).getReg())
+            .addImm(Current->getOperand(MemOpOffset + X86::AddrDisp).getImm() +
+                    Delta)
+            .addReg(Current->getOperand(MemOpOffset + X86::AddrSegmentReg)
+                        .getReg());
+
+        if (!Current->memoperands_empty()) {
+          MachineMemOperand *CurrentOp = *(Current->memoperands_begin());
+          MIB.addMemOperand(MF.getMachineMemOperand(
+              CurrentOp, CurrentOp->getOffset() + Delta, CurrentOp->getSize()));
+        }
+
+        // Insert before Current. This is because Current may clobber some of
+        // the registers used to describe the input memory operand.
+        MBB.insert(Current, PFetch);
+        Changed = true;
+      }
+    }
+  }
+  return Changed;
+}
+
+FunctionPass *llvm::createX86InsertPrefetchPass() {
+  return new X86InsertPrefetch(PrefetchHintsFile);
+}

lib/Target/X86/X86TargetMachine.cpp

@@ -497,6 +497,8 @@ void X86PassConfig::addPreEmitPass() {
     addPass(createX86FixupLEAs());
     addPass(createX86EvexToVexInsts());
   }
+  addPass(createX86DiscriminateMemOpsPass());
+  addPass(createX86InsertPrefetchPass());
 }
 
 void X86PassConfig::addPreEmitPass2() {

test/CodeGen/X86/O0-pipeline.ll

@@ -58,6 +58,8 @@
 ; CHECK-NEXT:       Shadow Call Stack
 ; CHECK-NEXT:       X86 Indirect Branch Tracking
 ; CHECK-NEXT:       X86 vzeroupper inserter
+; CHECK-NEXT:       X86 Discriminate Memory Operands
+; CHECK-NEXT:       X86 Insert Cache Prefetches
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis

test/CodeGen/X86/O3-pipeline.ll

@@ -159,6 +159,8 @@
 ; CHECK-NEXT:       X86 Atom pad short functions
 ; CHECK-NEXT:       X86 LEA Fixup
 ; CHECK-NEXT:       Compressing EVEX instrs to VEX encoding when possible
+; CHECK-NEXT:       X86 Discriminate Memory Operands
+; CHECK-NEXT:       X86 Insert Cache Prefetches
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis

test/CodeGen/X86/discriminate-mem-ops.ll

@@ -0,0 +1,55 @@
+; RUN: llc < %s | FileCheck %s
+;
+; original source, compiled with -O3 -gmlt -fdebug-info-for-profiling:
+; int sum(int* arr, int pos1, int pos2) {
+;   return arr[pos1] + arr[pos2];
+; }
+;
+; ModuleID = 'test.cc'
+source_filename = "test.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind readonly uwtable
+define i32 @sum(i32* %arr, i32 %pos1, i32 %pos2) !dbg !7 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !9
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !9
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !9, !tbaa !10
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !14
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !14
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !14, !tbaa !10
+  %add = add nsw i32 %1, %0, !dbg !15
+  ret i32 %add, !dbg !16
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 322155) (llvm/trunk 322159)"}
+!7 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 2, column: 10, scope: !7)
+!10 = !{!11, !11, i64 0}
+!11 = !{!"int", !12, i64 0}
+!12 = !{!"omnipotent char", !13, i64 0}
+!13 = !{!"Simple C++ TBAA"}
+!14 = !DILocation(line: 2, column: 22, scope: !7)
+!15 = !DILocation(line: 2, column: 20, scope: !7)
+!16 = !DILocation(line: 2, column: 3, scope: !7)
+
+;CHECK-LABEL: sum:
+;CHECK:       # %bb.0:
+;CHECK:       movl (%rdi,%rax,4), %eax
+;CHECK-NEXT:  .loc 1 2 20 discriminator 2  # test.cc:2:20
+;CHECK-NEXT:  addl (%rdi,%rcx,4), %eax
+;CHECK-NEXT:  .loc 1 2 3                   # test.cc:2:3

test/CodeGen/X86/insert-prefetch-inline.afdo

@@ -0,0 +1,4 @@
+caller:0:0
+ 2:sum:0
+  3: 0 __prefetch_nta_0:23456
+  3.1: 0 __prefetch_nta_0:8764 __prefetch_nta_1:64

test/CodeGen/X86/insert-prefetch-inline.ll

@@ -0,0 +1,76 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-inline.afdo | FileCheck %s
+;
+; Verify we can insert prefetch instructions in code belonging to inlined
+; functions.
+;
+; ModuleID = 'test.cc'
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind readonly uwtable
+define dso_local i32 @sum(i32* nocapture readonly %arr, i32 %pos1, i32 %pos2) local_unnamed_addr #0 !dbg !7 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !10
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !10
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !10, !tbaa !11
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !15
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !15
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !15, !tbaa !11
+  %add = add nsw i32 %1, %0, !dbg !16
+  ret i32 %add, !dbg !17
+}
+
+; "caller" inlines "sum". The associated .afdo file references instructions
+; in "caller" that came from "sum"'s inlining.
+;
+; Function Attrs: norecurse nounwind readonly uwtable
+define dso_local i32 @caller(i32* nocapture readonly %arr) local_unnamed_addr #0 !dbg !18 {
+entry:
+  %0 = load i32, i32* %arr, align 4, !dbg !19, !tbaa !11
+  %arrayidx2.i = getelementptr inbounds i32, i32* %arr, i64 2, !dbg !21
+  %1 = load i32, i32* %arrayidx2.i, align 4, !dbg !21, !tbaa !11
+  %add.i = add nsw i32 %1, %0, !dbg !22
+  ret i32 %add.i, !dbg !23
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 7.0.0 (trunk 324940) (llvm/trunk 324941)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 324940) (llvm/trunk 324941)"}
+!7 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !8, file: !8, line: 3, type: !9, isLocal: false, isDefinition: true, scopeLine: 3, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DIFile(filename: "./test.h", directory: "/tmp")
+!9 = !DISubroutineType(types: !2)
+!10 = !DILocation(line: 6, column: 10, scope: !7)
+!11 = !{!12, !12, i64 0}
+!12 = !{!"int", !13, i64 0}
+!13 = !{!"omnipotent char", !14, i64 0}
+!14 = !{!"Simple C++ TBAA"}
+!15 = !DILocation(line: 6, column: 22, scope: !7)
+!16 = !DILocation(line: 6, column: 20, scope: !7)
+!17 = !DILocation(line: 6, column: 3, scope: !7)
+!18 = distinct !DISubprogram(name: "caller", linkageName: "caller", scope: !1, file: !1, line: 4, type: !9, isLocal: false, isDefinition: true, scopeLine: 4, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!19 = !DILocation(line: 6, column: 10, scope: !7, inlinedAt: !20)
+!20 = distinct !DILocation(line: 6, column: 10, scope: !18)
+!21 = !DILocation(line: 6, column: 22, scope: !7, inlinedAt: !20)
+!22 = !DILocation(line: 6, column: 20, scope: !7, inlinedAt: !20)
+!23 = !DILocation(line: 6, column: 3, scope: !18)
+
+; CHECK-LABEL: caller:
+; CHECK-LABEL: # %bb.0:
+; CHECK-NEXT: .loc 1 6 22 prologue_end
+; CHECK-NEXT: prefetchnta 23464(%rdi)
+; CHECK-NEXT: movl 8(%rdi), %eax
+; CHECK-NEXT: .loc 1 6 20 is_stmt 0 discriminator 2
+; CHECK-NEXT: prefetchnta 8764(%rdi)
+; CHECK-NEXT: prefetchnta 64(%rdi)
+; CHECK-NEXT: addl (%rdi), %eax

test/CodeGen/X86/insert-prefetch-invalid-instr.afdo

@@ -0,0 +1,2 @@
+main:0:0
+ 6: 0 __prefetch_nta_0:42

test/CodeGen/X86/insert-prefetch-invalid-instr.ll

@@ -0,0 +1,46 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-invalid-instr.afdo | FileCheck %s
+; ModuleID = 'prefetch.cc'
+source_filename = "prefetch.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind uwtable
+define dso_local i32 @main() local_unnamed_addr #0 !dbg !7 {
+entry:
+  tail call void @llvm.prefetch(i8* inttoptr (i64 291 to i8*), i32 0, i32 0, i32 1), !dbg !9
+  tail call void @llvm.x86.avx512.gatherpf.dpd.512(i8 97, <8 x i32> undef, i8* null, i32 1, i32 2), !dbg !10
+  ret i32 291, !dbg !11
+}
+
+; Function Attrs: inaccessiblemem_or_argmemonly nounwind
+declare void @llvm.prefetch(i8* nocapture readonly, i32, i32, i32) #1
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.x86.avx512.gatherpf.dpd.512(i8, <8 x i32>, i8*, i32, i32) #2
+
+attributes #0 = {"target-cpu"="x86-64" "target-features"="+avx512pf,+sse4.2,+ssse3"}
+attributes #1 = { inaccessiblemem_or_argmemonly nounwind }
+attributes #2 = { argmemonly nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "prefetch.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 327078) (llvm/trunk 327086)"}
+!7 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 8, type: !8, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 12, column: 3, scope: !7)
+!10 = !DILocation(line: 14, column: 3, scope: !7)
+!11 = !DILocation(line: 15, column: 3, scope: !7)
+
+;CHECK-LABEL: main:
+;CHECK:       # %bb.0:
+;CHECK:       prefetchnta 291
+;CHECK-NOT:   prefetchnta 42(%rax,%ymm0)
+;CHECK:       vgatherpf1dpd (%rax,%ymm0) {%k1}

test/CodeGen/X86/insert-prefetch-other.afdo

@@ -0,0 +1,3 @@
+sum:0:0
+ 1: 0 __prefetch_t0_1:0 __prefetch_t2_0:42
+ 1.1: 0 __prefetch_t1_0:18446744073709551615

test/CodeGen/X86/insert-prefetch.afdo

@@ -0,0 +1,3 @@
+sum:0:0
+ 1: 0 __prefetch_nta_1:0 __prefetch_nta_0:42
+ 1.1: 0 __prefetch_nta_0:18446744073709551615

test/CodeGen/X86/insert-prefetch.ll

@@ -0,0 +1,101 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch.afdo | FileCheck %s
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-other.afdo | FileCheck %s -check-prefix=OTHERS
+;
+; original source, compiled with -O3 -gmlt -fdebug-info-for-profiling:
+; int sum(int* arr, int pos1, int pos2) {
+;   return arr[pos1] + arr[pos2];
+; }
+;
+; NOTE: debug line numbers were adjusted such that the function would start
+; at line 15 (an arbitrary number). The sample profile file format uses
+; offsets from the start of the symbol instead of file-relative line numbers.
+; The .afdo file reflects that - the instructions are offset '1'.
+;
+; ModuleID = 'test.cc'
+source_filename = "test.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @sum(i32* %arr, i32 %pos1, i32 %pos2) !dbg !35 !prof !37 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !38
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !38
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !38, !tbaa !39
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !43
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !43
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !43, !tbaa !39
+  %add = add nsw i32 %1, %0, !dbg !44
+  ret i32 %add, !dbg !45
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6}
+!llvm.ident = !{!33}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{i32 1, !"ProfileSummary", !7}
+!7 = !{!8, !9, !10, !11, !12, !13, !14, !15}
+!8 = !{!"ProfileFormat", !"SampleProfile"}
+!9 = !{!"TotalCount", i64 0}
+!10 = !{!"MaxCount", i64 0}
+!11 = !{!"MaxInternalCount", i64 0}
+!12 = !{!"MaxFunctionCount", i64 0}
+!13 = !{!"NumCounts", i64 2}
+!14 = !{!"NumFunctions", i64 1}
+!15 = !{!"DetailedSummary", !16}
+!16 = !{!17, !18, !19, !20, !21, !22, !22, !23, !23, !24, !25, !26, !27, !28, !29, !30, !31, !32}
+!17 = !{i32 10000, i64 0, i32 0}
+!18 = !{i32 100000, i64 0, i32 0}
+!19 = !{i32 200000, i64 0, i32 0}
+!20 = !{i32 300000, i64 0, i32 0}
+!21 = !{i32 400000, i64 0, i32 0}
+!22 = !{i32 500000, i64 0, i32 0}
+!23 = !{i32 600000, i64 0, i32 0}
+!24 = !{i32 700000, i64 0, i32 0}
+!25 = !{i32 800000, i64 0, i32 0}
+!26 = !{i32 900000, i64 0, i32 0}
+!27 = !{i32 950000, i64 0, i32 0}
+!28 = !{i32 990000, i64 0, i32 0}
+!29 = !{i32 999000, i64 0, i32 0}
+!30 = !{i32 999900, i64 0, i32 0}
+!31 = !{i32 999990, i64 0, i32 0}
+!32 = !{i32 999999, i64 0, i32 0}
+!33 = !{!"clang version 7.0.0 (trunk 322593) (llvm/trunk 322526)"}
+!35 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !1, file: !1, line: 15, type: !36, isLocal: false, isDefinition: true, scopeLine: 15, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!36 = !DISubroutineType(types: !2)
+!37 = !{!"function_entry_count", i64 -1}
+!38 = !DILocation(line: 16, column: 10, scope: !35)
+!39 = !{!40, !40, i64 0}
+!40 = !{!"int", !41, i64 0}
+!41 = !{!"omnipotent char", !42, i64 0}
+!42 = !{!"Simple C++ TBAA"}
+!43 = !DILocation(line: 16, column: 22, scope: !35)
+!44 = !DILocation(line: 16, column: 20, scope: !35)
+!45 = !DILocation(line: 16, column: 3, scope: !35)
+
+;CHECK-LABEL: sum:
+;CHECK:       # %bb.0:
+;CHECK:       prefetchnta 42(%rdi,%rax,4)
+;CHECK-NEXT:  prefetchnta (%rdi,%rax,4)
+;CHECK-NEXT:  movl (%rdi,%rax,4), %eax
+;CHECK-NEXT:  .loc 1 16 20 discriminator 2  # test.cc:16:20
+;CHECK-NEXT:  prefetchnta -1(%rdi,%rcx,4)
+;CHECK-NEXT:  addl (%rdi,%rcx,4), %eax
+;CHECK-NEXT:  .loc 1 16 3                   # test.cc:16:3
+
+;OTHERS-LABEL: sum:
+;OTHERS:       # %bb.0:
+;OTHERS:       prefetcht2 42(%rdi,%rax,4)
+;OTHERS-NEXT:  prefetcht0 (%rdi,%rax,4)
+;OTHERS-NEXT:  movl (%rdi,%rax,4), %eax
+;OTHERS-NEXT:  .loc 1 16 20 discriminator 2  # test.cc:16:20
+;OTHERS-NEXT:  prefetcht1 -1(%rdi,%rcx,4)
+;OTHERS-NEXT:  addl (%rdi,%rcx,4), %eax
+;OTHERS-NEXT:  .loc 1 16 3                   # test.cc:16:3