[PGO] Value profile for size of memory intrinsic calls

This patch adds the value profile support to profile the size parameter of
memory intrinsic calls: memcpy, memcmp, and memmov.

Differential Revision: http://reviews.llvm.org/D28965


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297897 91177308-0d34-0410-b5e6-96231b3b80d8

docs/CommandGuide/llvm-profdata.rst

@@ -196,6 +196,10 @@ OPTIONS
 
  Specify that the input profile is a sample-based profile.
 
+.. option:: -memop-sizes
+
+ Show the profiled sizes of the memory intrinsic calls for shown functions.
+
 EXIT STATUS
 -----------
 

include/llvm/ProfileData/InstrProf.h

@@ -94,6 +94,11 @@ inline StringRef getInstrProfValueProfFuncName() {
   return INSTR_PROF_VALUE_PROF_FUNC_STR;
 }
 
+/// Return the name profile runtime entry point to do value range profiling.
+inline StringRef getInstrProfValueRangeProfFuncName() {
+  return INSTR_PROF_VALUE_RANGE_PROF_FUNC_STR;
+}
+
 /// Return the name of the section containing function coverage mapping
 /// data.
 inline StringRef getInstrProfCoverageSectionName(bool AddSegment) {
@@ -689,12 +694,15 @@ struct InstrProfRecord {
 
 private:
   std::vector<InstrProfValueSiteRecord> IndirectCallSites;
+  std::vector<InstrProfValueSiteRecord> MemOPSizes;
   const std::vector<InstrProfValueSiteRecord> &
 
   getValueSitesForKind(uint32_t ValueKind) const {
     switch (ValueKind) {
     case IPVK_IndirectCallTarget:
       return IndirectCallSites;
+    case IPVK_MemOPSize:
+      return MemOPSizes;
     default:
       llvm_unreachable("Unknown value kind!");
     }

include/llvm/ProfileData/InstrProfData.inc

@@ -153,7 +153,17 @@ INSTR_PROF_RAW_HEADER(uint64_t, ValueKindLast, IPVK_Last)
 VALUE_PROF_FUNC_PARAM(uint64_t, TargetValue, Type::getInt64Ty(Ctx)) \
                       INSTR_PROF_COMMA
 VALUE_PROF_FUNC_PARAM(void *, Data, Type::getInt8PtrTy(Ctx)) INSTR_PROF_COMMA
+#ifndef VALUE_RANGE_PROF
 VALUE_PROF_FUNC_PARAM(uint32_t, CounterIndex, Type::getInt32Ty(Ctx))
+#else /* VALUE_RANGE_PROF */
+VALUE_PROF_FUNC_PARAM(uint32_t, CounterIndex, Type::getInt32Ty(Ctx)) \
+                      INSTR_PROF_COMMA
+VALUE_PROF_FUNC_PARAM(uint64_t, PreciseRangeStart, Type::getInt64Ty(Ctx)) \
+                      INSTR_PROF_COMMA
+VALUE_PROF_FUNC_PARAM(uint64_t, PreciseRangeLast, Type::getInt64Ty(Ctx)) \
+                      INSTR_PROF_COMMA
+VALUE_PROF_FUNC_PARAM(uint64_t, LargeValue, Type::getInt64Ty(Ctx))
+#endif /*VALUE_RANGE_PROF */
 #undef VALUE_PROF_FUNC_PARAM
 #undef INSTR_PROF_COMMA
 /* VALUE_PROF_FUNC_PARAM end */
@@ -174,13 +184,15 @@ VALUE_PROF_FUNC_PARAM(uint32_t, CounterIndex, Type::getInt32Ty(Ctx))
  * name hash and the function address.
  */
 VALUE_PROF_KIND(IPVK_IndirectCallTarget, 0)
+/* For memory intrinsic functions size profiling. */
+VALUE_PROF_KIND(IPVK_MemOPSize, 1)
 /* These two kinds must be the last to be
  * declared. This is to make sure the string
  * array created with the template can be
  * indexed with the kind value.
  */
 VALUE_PROF_KIND(IPVK_First, IPVK_IndirectCallTarget)
-VALUE_PROF_KIND(IPVK_Last, IPVK_IndirectCallTarget)
+VALUE_PROF_KIND(IPVK_Last, IPVK_MemOPSize)
 
 #undef VALUE_PROF_KIND
 /* VALUE_PROF_KIND end */
@@ -649,6 +661,9 @@ serializeValueProfDataFrom(ValueProfRecordClosure *Closure,
 #define INSTR_PROF_VALUE_PROF_FUNC __llvm_profile_instrument_target
 #define INSTR_PROF_VALUE_PROF_FUNC_STR \
         INSTR_PROF_QUOTE(INSTR_PROF_VALUE_PROF_FUNC)
+#define INSTR_PROF_VALUE_RANGE_PROF_FUNC __llvm_profile_instrument_range
+#define INSTR_PROF_VALUE_RANGE_PROF_FUNC_STR \
+        INSTR_PROF_QUOTE(INSTR_PROF_VALUE_RANGE_PROF_FUNC)
 
 /* InstrProfile per-function control data alignment.  */
 #define INSTR_PROF_DATA_ALIGNMENT 8

include/llvm/Transforms/InstrProfiling.h

@@ -59,6 +59,14 @@ class InstrProfiling : public PassInfoMixin<InstrProfiling> {
   GlobalVariable *NamesVar;
   size_t NamesSize;
 
+  // The start value of precise value profile range for memory intrinsic sizes.
+  const int64_t DefaultMemOPSizeRangeStart = 0;
+  int64_t MemOPSizeRangeStart;
+  // The end value of precise value profile range for memory intrinsic sizes.
+  const int64_t DefaultMemOPSizeRangeLast = 8;
+  int64_t MemOPSizeRangeLast;
+  int64_t MemOPSizeLargeVal;
+
   bool isMachO() const;
 
   /// Get the section name for the counter variables.
@@ -109,6 +117,9 @@ class InstrProfiling : public PassInfoMixin<InstrProfiling> {
   /// Create a static initializer for our data, on platforms that need it,
   /// and for any profile output file that was specified.
   void emitInitialization();
+
+  /// Helper funtion that parsing the MemOPSize value profile options
+  void getMemOPSizeOptions();
 };
 
 } // end namespace llvm

lib/Transforms/Instrumentation/InstrProfiling.cpp

@@ -77,6 +77,17 @@ cl::opt<double> NumCountersPerValueSite(
     // is usually smaller than 2.
     cl::init(1.0));
 
+cl::opt<std::string> MemOPSizeRange(
+    "memop-size-range",
+    cl::desc("Set the range of size in memory intrinsic calls to be profiled "
+             "precisely, in a format of <start_val>:<end_val>"),
+    cl::init(""));
+cl::opt<unsigned> MemOPSizeLarge(
+    "memop-size-large",
+    cl::desc("Set large value thresthold in memory intrinsic size profiling. "
+             "Value of 0 disables the large value profiling."),
+    cl::init(8192));
+
 class InstrProfilingLegacyPass : public ModulePass {
   InstrProfiling InstrProf;
 
@@ -165,6 +176,7 @@ bool InstrProfiling::run(Module &M, const TargetLibraryInfo &TLI) {
   NamesSize = 0;
   ProfileDataMap.clear();
   UsedVars.clear();
+  getMemOPSizeOptions();
 
   // We did not know how many value sites there would be inside
   // the instrumented function. This is counting the number of instrumented
@@ -217,17 +229,34 @@ bool InstrProfiling::run(Module &M, const TargetLibraryInfo &TLI) {
 }
 
 static Constant *getOrInsertValueProfilingCall(Module &M,
-                                               const TargetLibraryInfo &TLI) {
+                                               const TargetLibraryInfo &TLI,
+                                               bool IsRange = false) {
   LLVMContext &Ctx = M.getContext();
   auto *ReturnTy = Type::getVoidTy(M.getContext());
-  Type *ParamTypes[] = {
+
+  Constant *Res;
+  if (!IsRange) {
+    Type *ParamTypes[] = {
 #define VALUE_PROF_FUNC_PARAM(ParamType, ParamName, ParamLLVMType) ParamLLVMType
 #include "llvm/ProfileData/InstrProfData.inc"
-  };
-  auto *ValueProfilingCallTy =
-      FunctionType::get(ReturnTy, makeArrayRef(ParamTypes), false);
-  Constant *Res = M.getOrInsertFunction(getInstrProfValueProfFuncName(),
-                                        ValueProfilingCallTy);
+    };
+    auto *ValueProfilingCallTy =
+        FunctionType::get(ReturnTy, makeArrayRef(ParamTypes), false);
+    Res = M.getOrInsertFunction(getInstrProfValueProfFuncName(),
+                                ValueProfilingCallTy);
+  } else {
+    Type *RangeParamTypes[] = {
+#define VALUE_RANGE_PROF 1
+#define VALUE_PROF_FUNC_PARAM(ParamType, ParamName, ParamLLVMType) ParamLLVMType
+#include "llvm/ProfileData/InstrProfData.inc"
+#undef VALUE_RANGE_PROF
+    };
+    auto *ValueRangeProfilingCallTy =
+        FunctionType::get(ReturnTy, makeArrayRef(RangeParamTypes), false);
+    Res = M.getOrInsertFunction(getInstrProfValueRangeProfFuncName(),
+                                ValueRangeProfilingCallTy);
+  }
+
   if (Function *FunRes = dyn_cast<Function>(Res)) {
     if (auto AK = TLI.getExtAttrForI32Param(false))
       FunRes->addAttribute(3, AK);
@@ -261,11 +290,24 @@ void InstrProfiling::lowerValueProfileInst(InstrProfValueProfileInst *Ind) {
     Index += It->second.NumValueSites[Kind];
 
   IRBuilder<> Builder(Ind);
-  Value *Args[3] = {Ind->getTargetValue(),
-                    Builder.CreateBitCast(DataVar, Builder.getInt8PtrTy()),
-                    Builder.getInt32(Index)};
-  CallInst *Call = Builder.CreateCall(getOrInsertValueProfilingCall(*M, *TLI),
-                                      Args);
+  bool IsRange = (Ind->getValueKind()->getZExtValue() ==
+                  llvm::InstrProfValueKind::IPVK_MemOPSize);
+  CallInst *Call = nullptr;
+  if (!IsRange) {
+    Value *Args[3] = {Ind->getTargetValue(),
+                      Builder.CreateBitCast(DataVar, Builder.getInt8PtrTy()),
+                      Builder.getInt32(Index)};
+    Call = Builder.CreateCall(getOrInsertValueProfilingCall(*M, *TLI), Args);
+  } else {
+    Value *Args[6] = {Ind->getTargetValue(),
+                      Builder.CreateBitCast(DataVar, Builder.getInt8PtrTy()),
+                      Builder.getInt32(Index),
+                      Builder.getInt64(MemOPSizeRangeStart),
+                      Builder.getInt64(MemOPSizeRangeLast),
+                      Builder.getInt64(MemOPSizeLargeVal)};
+    Call =
+        Builder.CreateCall(getOrInsertValueProfilingCall(*M, *TLI, true), Args);
+  }
   if (auto AK = TLI->getExtAttrForI32Param(false))
     Call->addAttribute(3, AK);
   Ind->replaceAllUsesWith(Call);
@@ -658,3 +700,24 @@ void InstrProfiling::emitInitialization() {
 
   appendToGlobalCtors(*M, F, 0);
 }
+
+void InstrProfiling::getMemOPSizeOptions() {
+  // Parse the value profile options.
+  MemOPSizeRangeStart = DefaultMemOPSizeRangeStart;
+  MemOPSizeRangeLast = DefaultMemOPSizeRangeLast;
+  if (!MemOPSizeRange.empty()) {
+    auto Pos = MemOPSizeRange.find(":");
+    if (Pos != std::string::npos) {
+      if (Pos > 0)
+        MemOPSizeRangeStart = std::stoi(MemOPSizeRange.substr(0, Pos));
+      if (Pos < MemOPSizeRange.size() - 1)
+        MemOPSizeRangeLast = std::stoi(MemOPSizeRange.substr(Pos + 1));
+    } else
+      MemOPSizeRangeLast = std::stoi(MemOPSizeRange);
+  }
+  assert(MemOPSizeRangeLast >= MemOPSizeRangeStart);
+
+  MemOPSizeLargeVal = MemOPSizeLarge;
+  if (MemOPSizeLargeVal == 0)
+    MemOPSizeLargeVal = INT64_MIN;
+}

lib/Transforms/Instrumentation/PGOInstrumentation.cpp

@@ -91,6 +91,7 @@ using namespace llvm;
 
 STATISTIC(NumOfPGOInstrument, "Number of edges instrumented.");
 STATISTIC(NumOfPGOSelectInsts, "Number of select instruction instrumented.");
+STATISTIC(NumOfPGOMemIntrinsics, "Number of mem intrinsics instrumented.");
 STATISTIC(NumOfPGOEdge, "Number of edges.");
 STATISTIC(NumOfPGOBB, "Number of basic-blocks.");
 STATISTIC(NumOfPGOSplit, "Number of critical edge splits.");
@@ -168,6 +169,10 @@ static cl::opt<bool>
                               "display to only one function, use "
                               "filtering option -view-bfi-func-name."));
 
+// Command line option to enable/disable memop intrinsic calls..
+static cl::opt<bool> PGOInstrMemOP("pgo-instr-memop", cl::init(true),
+                                   cl::Hidden);
+
 // Command line option to turn on CFG dot dump after profile annotation.
 // Defined in Analysis/BlockFrequencyInfo.cpp:  -pgo-view-counts
 extern cl::opt<bool> PGOViewCounts;
@@ -235,6 +240,40 @@ struct SelectInstVisitor : public InstVisitor<SelectInstVisitor> {
   unsigned getNumOfSelectInsts() const { return NSIs; }
 };
 
+/// Instruction Visitor class to visit memory intrinsic calls.
+struct MemIntrinsicVisitor : public InstVisitor<MemIntrinsicVisitor> {
+  Function &F;
+  unsigned NMemIs = 0;          // Number of memIntrinsics instrumented.
+  VisitMode Mode = VM_counting; // Visiting mode.
+  unsigned CurCtrId = 0;        // Current counter index.
+  unsigned TotalNumCtrs = 0;    // Total number of counters
+  GlobalVariable *FuncNameVar = nullptr;
+  uint64_t FuncHash = 0;
+  PGOUseFunc *UseFunc = nullptr;
+
+  MemIntrinsicVisitor(Function &Func) : F(Func) {}
+
+  void countMemIntrinsics(Function &Func) {
+    NMemIs = 0;
+    Mode = VM_counting;
+    visit(Func);
+  }
+  void instrumentMemIntrinsics(Function &Func, unsigned TotalNC,
+                               GlobalVariable *FNV, uint64_t FHash) {
+    Mode = VM_instrument;
+    TotalNumCtrs = TotalNC;
+    FuncHash = FHash;
+    FuncNameVar = FNV;
+    visit(Func);
+  }
+
+  // Visit the IR stream and annotate all mem intrinsic call instructions.
+  void instrumentOneMemIntrinsic(MemIntrinsic &MI);
+  // Visit \p MI instruction and perform tasks according to visit mode.
+  void visitMemIntrinsic(MemIntrinsic &SI);
+  unsigned getNumOfMemIntrinsics() const { return NMemIs; }
+};
+
 class PGOInstrumentationGenLegacyPass : public ModulePass {
 public:
   static char ID;
@@ -354,6 +393,7 @@ template <class Edge, class BBInfo> class FuncPGOInstrumentation {
 public:
   std::vector<std::vector<Instruction *>> ValueSites;
   SelectInstVisitor SIVisitor;
+  MemIntrinsicVisitor MIVisitor;
   std::string FuncName;
   GlobalVariable *FuncNameVar;
   // CFG hash value for this function.
@@ -384,11 +424,13 @@ template <class Edge, class BBInfo> class FuncPGOInstrumentation {
       bool CreateGlobalVar = false, BranchProbabilityInfo *BPI = nullptr,
       BlockFrequencyInfo *BFI = nullptr)
       : F(Func), ComdatMembers(ComdatMembers), ValueSites(IPVK_Last + 1),
-        SIVisitor(Func), FunctionHash(0), MST(F, BPI, BFI) {
+        SIVisitor(Func), MIVisitor(Func), FunctionHash(0), MST(F, BPI, BFI) {
 
     // This should be done before CFG hash computation.
     SIVisitor.countSelects(Func);
+    MIVisitor.countMemIntrinsics(Func);
     NumOfPGOSelectInsts += SIVisitor.getNumOfSelectInsts();
+    NumOfPGOMemIntrinsics += MIVisitor.getNumOfMemIntrinsics();
     ValueSites[IPVK_IndirectCallTarget] = findIndirectCallSites(Func);
 
     FuncName = getPGOFuncName(F);
@@ -605,6 +647,10 @@ static void instrumentOneFunc(
          Builder.getInt32(NumIndirectCallSites++)});
   }
   NumOfPGOICall += NumIndirectCallSites;
+
+  // Now instrument memop intrinsic calls.
+  FuncInfo.MIVisitor.instrumentMemIntrinsics(
+      F, NumCounters, FuncInfo.FuncNameVar, FuncInfo.FunctionHash);
 }
 
 // This class represents a CFG edge in profile use compilation.
@@ -1076,6 +1122,42 @@ void SelectInstVisitor::visitSelectInst(SelectInst &SI) {
   llvm_unreachable("Unknown visiting mode");
 }
 
+void MemIntrinsicVisitor::instrumentOneMemIntrinsic(MemIntrinsic &MI) {
+  Module *M = F.getParent();
+  IRBuilder<> Builder(&MI);
+  Type *Int64Ty = Builder.getInt64Ty();
+  Type *I8PtrTy = Builder.getInt8PtrTy();
+  Value *Length = MI.getLength();
+  assert(!dyn_cast<ConstantInt>(Length));
+  Builder.CreateCall(
+      Intrinsic::getDeclaration(M, Intrinsic::instrprof_value_profile),
+      {llvm::ConstantExpr::getBitCast(FuncNameVar, I8PtrTy),
+       Builder.getInt64(FuncHash), Builder.CreatePtrToInt(Length, Int64Ty),
+       Builder.getInt32(IPVK_MemOPSize), Builder.getInt32(CurCtrId)});
+  ++CurCtrId;
+}
+
+void MemIntrinsicVisitor::visitMemIntrinsic(MemIntrinsic &MI) {
+  if (!PGOInstrMemOP)
+    return;
+  Value *Length = MI.getLength();
+  // Not instrument constant length calls.
+  if (dyn_cast<ConstantInt>(Length))
+    return;
+
+  NMemIs++;
+  switch (Mode) {
+  case VM_counting:
+    return;
+  case VM_instrument:
+    instrumentOneMemIntrinsic(MI);
+    return;
+  case VM_annotate:
+    break;
+  }
+  llvm_unreachable("Unknown visiting mode");
+}
+
 // Traverse all valuesites and annotate the instructions for all value kind.
 void PGOUseFunc::annotateValueSites() {
   if (DisableValueProfiling)

test/Instrumentation/InstrProfiling/PR23499.ll

@@ -15,13 +15,13 @@ $_Z3barIvEvv = comdat any
 
 ; CHECK-NOT: __profn__Z3barIvEvv
 ; CHECK: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}__llvm_prf_cnts", comdat($__profv__Z3barIvEvv), align 8
-; CHECK: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [1 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [1 x i16] zeroinitializer }, section "{{.*}}__llvm_prf_data{{.*}}", comdat($__profv__Z3barIvEvv), align 8
+; CHECK: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [2 x i16] zeroinitializer }, section "{{.*}}__llvm_prf_data{{.*}}", comdat($__profv__Z3barIvEvv), align 8
 ; CHECK: @__llvm_prf_nm = private constant [{{.*}} x i8] c"{{.*}}", section "{{.*}}__llvm_prf_names"
 
 
 ; COFF-NOT: __profn__Z3barIvEvv
 ; COFF: @__profc__Z3barIvEvv = linkonce_odr hidden global [1 x i64] zeroinitializer, section "{{.*}}__llvm_prf_cnts", comdat, align 8
-; COFF: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [1 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [1 x i16] zeroinitializer }, section "{{.*}}__llvm_prf_data{{.*}}", comdat($__profc__Z3barIvEvv), align 8
+; COFF: @__profd__Z3barIvEvv = linkonce_odr hidden global { i64, i64, i64*, i8*, i8*, i32, [2 x i16] } { i64 4947693190065689389, i64 0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__Z3barIvEvv, i32 0, i32 0), i8*{{.*}}, i8* null, i32 1, [2 x i16] zeroinitializer }, section "{{.*}}__llvm_prf_data{{.*}}", comdat($__profc__Z3barIvEvv), align 8
 
 
 declare void @llvm.instrprof.increment(i8*, i64, i32, i32) #1

test/Instrumentation/InstrProfiling/icall.ll

@@ -37,9 +37,9 @@ attributes #0 = { nounwind }
 ; DYN-NOT: @__profvp_foo
 ; DYN-NOT: @__llvm_prf_vnodes
 
-; STATIC: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [1 x i16] }* @__profd_foo to i8*), i32 0)
-; STATIC-EXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [1 x i16] }* @__profd_foo to i8*), i32 zeroext 0)
-; STATIC-SEXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [1 x i16] }* @__profd_foo to i8*), i32 signext 0)
+; STATIC: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0)
+; STATIC-EXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 zeroext 0)
+; STATIC-SEXT: call void @__llvm_profile_instrument_target(i64 %3, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 signext 0)
 
 ; STATIC: declare void @__llvm_profile_instrument_target(i64, i8*, i32)
 ; STATIC-EXT: declare void @__llvm_profile_instrument_target(i64, i8*, i32 zeroext)