[ThinLTO] Compute the basic block count across modules.

[hjyamauchi]

Summary

Count the per-module number of basic blocks when the module summary is computed
and sum them up during Thin LTO indexing.

This is used to estimate the working set size under the partial sample PGO.

This is split off of D79831.

[hjyamauchi]

Address comment (from D79831).

[tejohnson]

llvm/include/llvm/IR/ModuleSummaryIndex.h

1010

Also specify that this would be the total number of bbs in the LTO unit in the combined index (it is the total in the module in the per-module summary).

1034

I'm not convinced a version bump is required. Isn't the lack of a block count record handled naturally ( i.e. the count stays at 0 in the index)?

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

6244

Remove commented out line. Presumably this uses addBlockCount instead of setBlockCount so that it gets merged properly when building the combined index?

[hjyamauchi]

Address comments.

llvm/include/llvm/IR/ModuleSummaryIndex.h

1010

Done.

1034

Yes, apparently bumping wasn't necessary. Done.

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

6244

Yes. Done.

[tejohnson]

LGTM

lld/test/COFF/thinlto-index-only.ll

 ; BACKEND2-NEXT: <ENTRY {{.*}} record string = '{{.*}}thinlto-index-only.ll.tmp2.obj'
 ; BACKEND2-NOT: <ENTRY
 ; BACKEND2: </MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; BACKEND2-NEXT: <VERSION
 ; BACKEND2-NEXT: <FLAGS
 ; BACKEND2-NEXT: <VALUE_GUID op0=1 op1=-5300342847281564238
 ; BACKEND2-NEXT: <COMBINED
+; BACKEND2-NEXT: <BLOCK_COUNT op0=2/>
 ; BACKEND2-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 ; Thin archive tests. Check that the module paths point to the original files.
 ; RUN: rm -rf %t
 ; RUN: mkdir %t
 ; RUN: opt -thinlto-bc -o %t/foo.obj < %s
 ; RUN: opt -thinlto-bc -o %t/bar.obj < %p/Inputs/thinlto.ll
 ; RUN: llvm-ar rcsT %t5.lib %t/bar.obj %t3.obj

lld/test/ELF/lto/thinlto-index-only.ll

 ; BACKEND2: <MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <ENTRY {{.*}} record string = '{{.*}}thinlto-index-only.ll.tmp2.o'
 ; BACKEND2-NEXT: </MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; BACKEND2-NEXT: <VERSION
 ; BACKEND2-NEXT: <FLAGS
 ; BACKEND2-NEXT: <VALUE_GUID op0=1 op1=-5300342847281564238
 ; BACKEND2-NEXT: <COMBINED
+; BACKEND2-NEXT: <BLOCK_COUNT op0=2/>
 ; BACKEND2-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 declare void @g(...)
 
 define void @f() {
 entry:
   call void (...) @g()
   ret void
 }

llvm/include/llvm/Bitcode/LLVMBitCodes.h

enum GlobalValueSummarySymtabCodes {
   // TYPE_ID_METADATA: [typeid, n x (valueid, offset)]
   FS_TYPE_ID_METADATA = 22,
   // Summarizes vtable definition for use in index-based whole program
   // devirtualization during the thin link.
   // PERMODULE_VTABLE_GLOBALVAR_INIT_REFS: [valueid, flags, varflags,
   //                                        numrefs, numrefs x valueid,
   //                                        n x (valueid, offset)]
   FS_PERMODULE_VTABLE_GLOBALVAR_INIT_REFS = 23,
+  // The total number of basic blocks in the module.
+  FS_BLOCK_COUNT = 24,
 };
 
 enum MetadataCodes {
   METADATA_STRING_OLD = 1,     // MDSTRING:      [values]
   METADATA_VALUE = 2,          // VALUE:         [type num, value num]
   METADATA_NODE = 3,           // NODE:          [n x md num]
   METADATA_NAME = 4,           // STRING:        [values]
   METADATA_DISTINCT_NODE = 5,  // DISTINCT_NODE: [n x md num]

llvm/include/llvm/IR/ModuleSummaryIndex.h

private:
   std::set<std::string> CfiFunctionDefs;
   std::set<std::string> CfiFunctionDecls;
 
   // Used in cases where we want to record the name of a global, but
   // don't have the string owned elsewhere (e.g. the Strtab on a module).
   StringSaver Saver;
   BumpPtrAllocator Alloc;
 
+  // The total number of basic blocks in the module in the per-module summary or
+  // the total number of basic blocks in the LTO unit in the combined index.
+  uint64_t BlockCount;
+
   // YAML I/O support.
   friend yaml::MappingTraits<ModuleSummaryIndex>;
 
   GlobalValueSummaryMapTy::value_type *
   getOrInsertValuePtr(GlobalValue::GUID GUID) {
     return &*GlobalValueMap.emplace(GUID, GlobalValueSummaryInfo(HaveGVs))
                  .first;
   }
 
 public:
   // See HaveGVs variable comment.
   ModuleSummaryIndex(bool HaveGVs, bool EnableSplitLTOUnit = false)
-      : HaveGVs(HaveGVs), EnableSplitLTOUnit(EnableSplitLTOUnit), Saver(Alloc) {
-  }
+      : HaveGVs(HaveGVs), EnableSplitLTOUnit(EnableSplitLTOUnit), Saver(Alloc),
+        BlockCount(0) {}
 
   // Current version for the module summary in bitcode files.
   // The BitcodeSummaryVersion should be bumped whenever we introduce changes
   // in the way some record are interpreted, like flags for instance.
   // Note that incrementing this may require changes in both BitcodeReader.cpp
   // and BitcodeWriter.cpp.
   static constexpr uint64_t BitcodeSummaryVersion = 8;
 
   // Regular LTO module name for ASM writer
   static constexpr const char *getRegularLTOModuleName() {
     return "[Regular LTO]";
   }
 
   bool haveGVs() const { return HaveGVs; }
 
   uint64_t getFlags() const;
   void setFlags(uint64_t Flags);
 
+  uint64_t getBlockCount() const { return BlockCount; }
+  void addBlockCount(uint64_t C) { BlockCount += C; }
+  void setBlockCount(uint64_t C) { BlockCount = C; }
+
   gvsummary_iterator begin() { return GlobalValueMap.begin(); }
   const_gvsummary_iterator begin() const { return GlobalValueMap.begin(); }
   gvsummary_iterator end() { return GlobalValueMap.end(); }
   const_gvsummary_iterator end() const { return GlobalValueMap.end(); }
   size_t size() const { return GlobalValueMap.size(); }
 
   /// Convenience function for doing a DFS on a ValueInfo. Marks the function in
   /// the FunctionHasParent map.

llvm/lib/Analysis/ModuleSummaryAnalysis.cpp

for (const Instruction &I : BB) {
         auto CandidateProfileData =
             ICallAnalysis.getPromotionCandidatesForInstruction(
                 &I, NumVals, TotalCount, NumCandidates);
         for (auto &Candidate : CandidateProfileData)
           CallGraphEdges[Index.getOrInsertValueInfo(Candidate.Value)]
               .updateHotness(getHotness(Candidate.Count, PSI));
       }
     }
+  Index.addBlockCount(F.size());
 
   std::vector<ValueInfo> Refs;
   if (IsThinLTO) {
     auto AddRefEdges = [&](const std::vector<const Instruction *> &Instrs,
                            SetVector<ValueInfo> &Edges,
                            SmallPtrSet<const User *, 8> &Cache) {
       for (const auto *I : Instrs) {
         Cache.erase(I);

llvm/lib/AsmParser/LLLexer.cpp

#define KEYWORD(STR)                                                           \
   // Summary index keywords.
   KEYWORD(path);
   KEYWORD(hash);
   KEYWORD(gv);
   KEYWORD(guid);
   KEYWORD(name);
   KEYWORD(summaries);
   KEYWORD(flags);
+  KEYWORD(blockcount);
   KEYWORD(linkage);
   KEYWORD(notEligibleToImport);
   KEYWORD(live);
   KEYWORD(dsoLocal);
   KEYWORD(canAutoHide);
   KEYWORD(function);
   KEYWORD(insts);
   KEYWORD(funcFlags);

llvm/lib/AsmParser/LLParser.h

private:
 
     // Module Summary Index Parsing.
     bool SkipModuleSummaryEntry();
     bool ParseSummaryEntry();
     bool ParseModuleEntry(unsigned ID);
     bool ParseModuleReference(StringRef &ModulePath);
     bool ParseGVReference(ValueInfo &VI, unsigned &GVId);
     bool ParseSummaryIndexFlags();
+    bool ParseBlockCount();
     bool ParseGVEntry(unsigned ID);
     bool ParseFunctionSummary(std::string Name, GlobalValue::GUID, unsigned ID);
     bool ParseVariableSummary(std::string Name, GlobalValue::GUID, unsigned ID);
     bool ParseAliasSummary(std::string Name, GlobalValue::GUID, unsigned ID);
     bool ParseGVFlags(GlobalValueSummary::GVFlags &GVFlags);
     bool ParseGVarFlags(GlobalVarSummary::GVarFlags &GVarFlags);
     bool ParseOptionalFFlags(FunctionSummary::FFlags &FFlags);
     bool ParseOptionalCalls(std::vector<FunctionSummary::EdgeTy> &Calls);

llvm/lib/AsmParser/LLParser.cpp

case lltok::kw_typeid:
     result = ParseTypeIdEntry(SummaryID);
     break;
   case lltok::kw_typeidCompatibleVTable:
     result = ParseTypeIdCompatibleVtableEntry(SummaryID);
     break;
   case lltok::kw_flags:
     result = ParseSummaryIndexFlags();
     break;
+  case lltok::kw_blockcount:
+    result = ParseBlockCount();
+    break;
   default:
     result = Error(Lex.getLoc(), "unexpected summary kind");
     break;
   }
   Lex.setIgnoreColonInIdentifiers(false);
   return result;
 }
 
if (ParseToken(lltok::colon, "expected ':' here"))
     return true;
   uint64_t Flags;
   if (ParseUInt64(Flags))
     return true;
   Index->setFlags(Flags);
   return false;
 }
 
+/// ParseBlockCount
+///   ::= 'blockcount' ':' UInt64
+bool LLParser::ParseBlockCount() {
+  assert(Lex.getKind() == lltok::kw_blockcount);
+  Lex.Lex();
+
+  if (ParseToken(lltok::colon, "expected ':' here"))
+    return true;
+  uint64_t BlockCount;
+  if (ParseUInt64(BlockCount))
+    return true;
+  Index->setBlockCount(BlockCount);
+  return false;
+}
+
 /// ParseGVEntry
 ///   ::= 'gv' ':' '(' ('name' ':' STRINGCONSTANT | 'guid' ':' UInt64)
 ///         [',' 'summaries' ':' Summary[',' Summary]* ]? ')'
 /// Summary ::= '(' (FunctionSummary | VariableSummary | AliasSummary) ')'
 bool LLParser::ParseGVEntry(unsigned ID) {
   assert(Lex.getKind() == lltok::kw_gv);
   Lex.Lex();
 

llvm/lib/AsmParser/LLToken.h

enum Kind {
   // Summary index keywords
   kw_path,
   kw_hash,
   kw_gv,
   kw_guid,
   kw_name,
   kw_summaries,
   kw_flags,
+  kw_blockcount,
   kw_linkage,
   kw_notEligibleToImport,
   kw_live,
   kw_dsoLocal,
   kw_canAutoHide,
   kw_function,
   kw_insts,
   kw_funcFlags,

llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp

default:
       STRINGIFY_CODE(FS, TYPE_CHECKED_LOAD_VCALLS)
       STRINGIFY_CODE(FS, TYPE_TEST_ASSUME_CONST_VCALL)
       STRINGIFY_CODE(FS, TYPE_CHECKED_LOAD_CONST_VCALL)
       STRINGIFY_CODE(FS, VALUE_GUID)
       STRINGIFY_CODE(FS, CFI_FUNCTION_DEFS)
       STRINGIFY_CODE(FS, CFI_FUNCTION_DECLS)
       STRINGIFY_CODE(FS, TYPE_ID)
       STRINGIFY_CODE(FS, TYPE_ID_METADATA)
+      STRINGIFY_CODE(FS, BLOCK_COUNT)
     }
   case bitc::METADATA_ATTACHMENT_ID:
     switch (CodeID) {
     default:
       return None;
       STRINGIFY_CODE(METADATA, ATTACHMENT)
     }
   case bitc::METADATA_BLOCK_ID:

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

while (true) {
 
     case bitc::FS_TYPE_ID:
       parseTypeIdSummaryRecord(Record, Strtab, TheIndex);
       break;
 
     case bitc::FS_TYPE_ID_METADATA:
       parseTypeIdCompatibleVtableSummaryRecord(Record);
       break;
+
+    case bitc::FS_BLOCK_COUNT:
+      TheIndex.addBlockCount(Record[0]);
     }
   }
   llvm_unreachable("Exit infinite loop");
 }
 
 // Parse the  module string table block into the Index.
 // This populates the ModulePathStringTable map in the index.
 Error ModuleSummaryIndexBitcodeReader::parseModuleStringTable() {

llvm/lib/Bitcode/Writer/BitcodeWriter.cpp

void ModuleBitcodeWriterBase::writePerModuleGlobalValueSummary() {
   for (auto &S : Index->typeIdCompatibleVtableMap()) {
     writeTypeIdCompatibleVtableSummaryRecord(NameVals, StrtabBuilder, S.first,
                                              S.second, VE);
     Stream.EmitRecord(bitc::FS_TYPE_ID_METADATA, NameVals,
                       TypeIdCompatibleVtableAbbrev);
     NameVals.clear();
   }
 
+  Stream.EmitRecord(bitc::FS_BLOCK_COUNT,
+                    ArrayRef<uint64_t>{Index->getBlockCount()});
+
   Stream.ExitBlock();
 }
 
 /// Emit the combined summary section into the combined index file.
 void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
   Stream.EnterSubblock(bitc::GLOBALVAL_SUMMARY_BLOCK_ID, 3);
   Stream.EmitRecord(
       bitc::FS_VERSION,
for (auto &T : ReferencedTypeIds) {
     for (auto It = TidIter.first; It != TidIter.second; ++It) {
       writeTypeIdSummaryRecord(NameVals, StrtabBuilder, It->second.first,
                                It->second.second);
       Stream.EmitRecord(bitc::FS_TYPE_ID, NameVals);
       NameVals.clear();
     }
   }
 
+  Stream.EmitRecord(bitc::FS_BLOCK_COUNT,
+                    ArrayRef<uint64_t>{Index.getBlockCount()});
+
   Stream.ExitBlock();
 }
 
 /// Create the "IDENTIFICATION_BLOCK_ID" containing a single string with the
 /// current llvm version, and a record for the epoch number.
 static void writeIdentificationBlock(BitstreamWriter &Stream) {
   Stream.EnterSubblock(bitc::IDENTIFICATION_BLOCK_ID, 5);
 

llvm/lib/IR/AsmWriter.cpp

for (auto &TId : TheIndex->typeIdCompatibleVtableMap()) {
     auto GUID = GlobalValue::getGUID(TId.first);
     Out << "^" << Machine.getGUIDSlot(GUID)
         << " = typeidCompatibleVTable: (name: \"" << TId.first << "\"";
     printTypeIdCompatibleVtableSummary(TId.second);
     Out << ") ; guid = " << GUID << "\n";
   }
 
   // Don't emit flags when it's not really needed (value is zero by default).
-  if (TheIndex->getFlags())
+  if (TheIndex->getFlags()) {
     Out << "^" << NumSlots << " = flags: " << TheIndex->getFlags() << "\n";
+    ++NumSlots;
+  }
+
+  Out << "^" << NumSlots << " = blockcount: " << TheIndex->getBlockCount()
+      << "\n";
 }
 
 static const char *
 getWholeProgDevirtResKindName(WholeProgramDevirtResolution::Kind K) {
   switch (K) {
   case WholeProgramDevirtResolution::Indir:
     return "indir";
   case WholeProgramDevirtResolution::SingleImpl:

llvm/test/Assembler/thinlto-vtable-summary.ll

 ^1 = gv: (name: "_ZN1A1nEi") ; guid = 1621563287929432257
 ^2 = gv: (name: "_ZTV1B", summaries: (variable: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), varFlags: (readonly: 0, writeonly: 0, constant: 0, vcall_visibility: 0), vTableFuncs: ((virtFunc: ^3, offset: 16), (virtFunc: ^1, offset: 24)), refs: (^3, ^1)))) ; guid = 5283576821522790367
 ^3 = gv: (name: "_ZN1B1fEi") ; guid = 7162046368816414394
 ^4 = gv: (name: "_ZTV1C", summaries: (variable: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), varFlags: (readonly: 0, writeonly: 0, constant: 0, vcall_visibility: 0), vTableFuncs: ((virtFunc: ^5, offset: 16), (virtFunc: ^1, offset: 24)), refs: (^1, ^5)))) ; guid = 13624023785555846296
 ^5 = gv: (name: "_ZN1C1fEi") ; guid = 14876272565662207556
 ^6 = typeidCompatibleVTable: (name: "_ZTS1A", summary: ((offset: 16, ^2), (offset: 16, ^4))) ; guid = 7004155349499253778
 ^7 = typeidCompatibleVTable: (name: "_ZTS1B", summary: ((offset: 16, ^2))) ; guid = 6203814149063363976
 ^8 = typeidCompatibleVTable: (name: "_ZTS1C", summary: ((offset: 16, ^4))) ; guid = 1884921850105019584
+^9 = blockcount: 0

llvm/test/Bitcode/thinlto-alias.ll

 ; "analias"
 ; CHECK-NEXT: <FUNCTION op0=4 op1=7
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; See if the call to func is registered.
 ; The value id 1 matches the second FUNCTION record above.
 ; CHECK-NEXT:    <PERMODULE {{.*}} op7=1/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=1/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'mainanalias{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <FLAGS
 ; See if the call to analias is registered, using the expected value id.
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[ALIASID:[0-9]+]] op1=-5751648690987223394/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[ALIASEEID:[0-9]+]] op1=-1039159065113703048/>
 ; COMBINED-NEXT:    <COMBINED {{.*}} op9=[[ALIASID]]/>
 ; COMBINED-NEXT:    <COMBINED {{.*}}
 ; COMBINED-NEXT:    <COMBINED_ALIAS  {{.*}} op3=[[ALIASEEID]]
+; COMBINED-NEXT:    <BLOCK_COUNT op0=2/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; Function Attrs: nounwind uwtable
 define i32 @main() {
 entry:
     call void (...) @analias()
     ret i32 0
 }
 
 declare void @analias(...)
 
 ; DIS: ^0 = module: (path: "{{.*}}", hash: (0, 0, 0, 0, 0))
 ; DIS: ^1 = gv: (name: "analias", summaries: (alias: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), aliasee: ^2))) ; guid = 12695095382722328222
 ; DIS: ^2 = gv: (name: "aliasee", summaries: (function: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1))) ; guid = 17407585008595848568
+; DIS: ^3 = blockcount: 1
 
 ; COMBINED-DIS: ^0 = module: (path: "{{.*}}thinlto-alias.ll.tmp.o", hash: (0, 0, 0, 0, 0))
 ; COMBINED-DIS: ^1 = module: (path: "{{.*}}thinlto-alias.ll.tmp2.o", hash: (0, 0, 0, 0, 0))
 ; COMBINED-DIS: ^2 = gv: (guid: 12695095382722328222, summaries: (alias: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), aliasee: ^4)))
 ; COMBINED-DIS: ^3 = gv: (guid: 15822663052811949562, summaries: (function: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 2, calls: ((callee: ^2)))))
 ; COMBINED-DIS: ^4 = gv: (guid: 17407585008595848568, summaries: (function: (module: ^1, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0, canAutoHide: 0), insts: 1)))
+; COMBINED-DIS: ^5 = blockcount: 2

llvm/test/Bitcode/thinlto-alias2.ll

 ; Test to check the callgraph for call to alias in module.
 ; RUN: opt -module-summary %s -o %t.o
 ; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
 
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; CHECK-NEXT:    <PERMODULE {{.*}} op4=0 op5=0 op6=0 op7=[[ALIASID:[0-9]+]]/>
 ; CHECK-NEXT:    <PERMODULE {{.*}} op0=[[ALIASEEID:[0-9]+]]
 ; CHECK-NEXT:    <ALIAS {{.*}} op0=[[ALIASID]] {{.*}} op2=[[ALIASEEID]]/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=2/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; ModuleID = 'thinlto-alias2.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 define i32 @main() {
 entry:

llvm/test/Bitcode/thinlto-function-summary-callgraph-cast.ll

 ; Test to check the callgraph for calls to casts.
 ; RUN: opt -module-summary %s -o %t.o
 ; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
 ; PR34966
 
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; "op7" is a call to "callee" function.
 ; CHECK-NEXT:    <PERMODULE {{.*}} op9=3 op10=[[ALIASID:[0-9]+]]/>
 ; "another_caller" has only references but no calls.
 ; CHECK-NEXT:    <PERMODULE {{.*}} op4=3 {{.*}} op9={{[0-9]+}}/>
 ; CHECK-NEXT:    <PERMODULE {{.*}} op0=[[ALIASEEID:[0-9]+]]
 ; CHECK-NEXT:    <ALIAS {{.*}} op0=[[ALIASID]] {{.*}} op2=[[ALIASEEID]]/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=3/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; ModuleID = 'thinlto-function-summary-callgraph-cast.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 define void @caller() {
     call void bitcast (void (...)* @callee to void ()*)()

llvm/test/Bitcode/thinlto-function-summary-callgraph-pgo.ll

 ; CHECK-NEXT: <FUNCTION
 ; "func"
 ; CHECK-NEXT: <FUNCTION op0=4 op1=4
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; See if the call to func is registered, using the expected hotness type.
 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op7=1 op8=2/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=1/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'mainfunc{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[FUNCID:[0-9]+]] op1=7289175272376759421/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <COMBINED
 ; See if the call to func is registered, using the expected hotness type.
 ; op6=2 which is hotnessType::None.
 ; COMBINED-NEXT:    <COMBINED_PROFILE {{.*}} op9=[[FUNCID]] op10=2/>
+; COMBINED-NEXT:    <BLOCK_COUNT op0=2/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; Function Attrs: nounwind uwtable
 define i32 @main() #0 !prof !2 {

llvm/test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll

 ; "none3"
 ; CHECK-NEXT: <FUNCTION op0=42 op1=5
 ; CHECK-LABEL:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; CHECK-NEXT:    <VALUE_GUID op0=25 op1=123/>
 ; op4=hot1 op6=cold op8=hot2 op10=hot4 op12=none1 op14=hot3 op16=none2 op18=none3 op20=123
 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op7=1 op8=3 op9=5 op10=1 op11=2 op12=3 op13=4 op14=1 op15=6 op16=2 op17=3 op18=3 op19=7 op20=2 op21=8 op22=2 op23=25 op24=4/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=6/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3hot4coldnone1none2none3{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <FLAGS
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED_PROFILE {{.*}} op9=[[HOT1:.*]] op10=3 op11=[[COLD:.*]] op12=1 op13=[[HOT2:.*]] op14=3 op15=[[NONE1:.*]] op16=2 op17=[[HOT3:.*]] op18=3 op19=[[NONE2:.*]] op20=2 op21=[[NONE3:.*]] op22=2/>
-; COMBINED_NEXT:    <COMBINED abbrevid=
-; COMBINED_NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
+; COMBINED-NEXT:    <COMBINED abbrevid=
+; COMBINED-NEXT:    <BLOCK_COUNT op0=13/>
+; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; This function have high profile count, so entry block is hot.
 define void @hot_function(i1 %a, i1 %a2) !prof !20 {

llvm/test/Bitcode/thinlto-function-summary-callgraph-relbf.ll

 ; CHECK-NEXT: <FUNCTION
 ; "func"
 ; CHECK-NEXT: <FUNCTION op0=17 op1=4
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; See if the call to func is registered.
 ; CHECK-NEXT:    <PERMODULE_RELBF {{.*}} op4=1 {{.*}} op9=256
+; CHECK-NEXT:    <BLOCK_COUNT op0=1/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'undefinedglobmainfunc{{.*}}'
 
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"

llvm/test/Bitcode/thinlto-function-summary-callgraph-sample-profile-summary.ll

 ; CHECK-NEXT: <FUNCTION op0=49 op1=5
 
 ; CHECK-LABEL:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; CHECK-NEXT:    <VALUE_GUID op0=26 op1=123/>
 ; op4=none1 op6=hot1 op8=cold1 op10=none2 op12=hot2 op14=cold2 op16=none3 op18=hot3 op20=cold3 op22=123
 ; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op7=7 op8=0 op9=1 op10=3 op11=4 op12=1 op13=8 op14=0 op15=2 op16=3 op17=5 op18=1 op19=9 op20=0 op21=3 op22=3 op23=6 op24=1 op25=26 op26=4/>
+; CHECK-NEXT:    <BLOCK_COUNT op0=4/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'hot_functionhot1hot2hot3cold1cold2cold3none1none2none3{{.*}}'
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <FLAGS

 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED_PROFILE {{.*}} op9=[[NONE1:.*]] op10=0 op11=[[HOT1:.*]] op12=3 op13=[[COLD1:.*]] op14=1 op15=[[NONE2:.*]] op16=0 op17=[[HOT2:.*]] op18=3 op19=[[COLD2:.*]] op20=1 op21=[[NONE3:.*]] op22=0 op23=[[HOT3:.*]] op24=3 op25=[[COLD3:.*]] op26=1/>
-; COMBINED_NEXT:    <COMBINED abbrevid=
-; COMBINED_NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
+; COMBINED-NEXT:    <COMBINED abbrevid=
+; COMBINED-NEXT:    <BLOCK_COUNT op0=13/>
+; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; This function have high profile count, so entry block is hot.
 define void @hot_function(i1 %a, i1 %a2) !prof !20 {

llvm/test/Bitcode/thinlto-function-summary-callgraph.ll

 ; CHECK-NEXT: <FUNCTION
 ; "func"
 ; CHECK-NEXT: <FUNCTION op0=17 op1=4
 ; CHECK:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; CHECK-NEXT:    <FLAGS
 ; See if the call to func is registered
 ; CHECK-NEXT:    <PERMODULE {{.*}} op4=1
+; CHECK-NEXT:    <BLOCK_COUNT op0=1/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK: <STRTAB_BLOCK
 ; CHECK-NEXT: blob data = 'undefinedglobmainfunc{{.*}}'
 
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <FLAGS
 ; Only 2 VALUE_GUID since reference to undefinedglob should not be included in
 ; combined index.
 ; COMBINED-NEXT:    <VALUE_GUID op0=[[FUNCID:[0-9]+]] op1=7289175272376759421/>
 ; COMBINED-NEXT:    <VALUE_GUID
 ; COMBINED-NEXT:    <COMBINED
 ; See if the call to func is registered.
 ; COMBINED-NEXT:    <COMBINED {{.*}} op9=[[FUNCID]]/>
+; COMBINED-NEXT:    <BLOCK_COUNT op0=2/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; Function Attrs: nounwind uwtable
 define i32 @main() #0 {

llvm/test/Bitcode/thinlto-function-summary-originalnames.ll

 ; COMBINED-NEXT:    <VALUE_GUID {{.*}} op1=-6591587165810580810/>
 ; COMBINED-NEXT:    <VALUE_GUID {{.*}} op1=-4377693495213223786/>
 ; COMBINED-DAG:    <COMBINED{{ }}
 ; COMBINED-DAG:    <COMBINED_ORIGINAL_NAME op0=6699318081062747564/>
 ; COMBINED-DAG:    <COMBINED_GLOBALVAR_INIT_REFS
 ; COMBINED-DAG:    <COMBINED_ORIGINAL_NAME op0=-2012135647395072713/>
 ; COMBINED-DAG:    <COMBINED_ALIAS
 ; COMBINED-DAG:    <COMBINED_ORIGINAL_NAME op0=-4170563161550796836/>
+; COMBINED-NEXT:   <BLOCK_COUNT op0=1/>
 ; COMBINED-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 
 source_filename = "/path/to/source.c"
 
 ; ModuleID = 'thinlto-function-summary-callgraph.ll'
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @bar = internal global i32 0
 @fooalias = internal alias void (...), bitcast (void ()* @foo to void (...)*)
 
 define internal void @foo() {
     ret void
 }

llvm/test/Bitcode/thinlto-function-summary.ll

 ; BC: <GLOBALVAL_SUMMARY_BLOCK
 ; BC-NEXT: <VERSION
 ; BC-NEXT: <FLAGS
 ; BC-NEXT: <PERMODULE {{.*}} op0=1 op1=0
 ; BC-NEXT: <PERMODULE {{.*}} op0=2 op1=0
 ; BC-NEXT: <PERMODULE {{.*}} op0=3 op1=7
 ; BC-NEXT: <PERMODULE {{.*}} op0=4 op1=0 op2=4 op3=0
 ; BC-NEXT: <ALIAS {{.*}} op0=6 op1=0 op2=3
+; BC-NEXT: <BLOCK_COUNT op0=5/>
 ; BC-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 ; BC: <STRTAB_BLOCK
 ; BC-NEXT: blob data = 'hfoobaranon.{{................................}}.0variadicllvm.va_startf{{.*}}'
 
 
 ; RUN: opt -name-anon-globals -module-summary < %s | llvm-dis | FileCheck %s
 ; Check that this round-trips correctly.
 

llvm/test/ThinLTO/X86/distributed_indexes.ll

 ; BACKEND1-NEXT: <VERSION
 ; BACKEND1-DAG: <VALUE_GUID op0={{.*}} op1=-5751648690987223394
 ; BACKEND1-DAG: <VALUE_GUID op0={{.*}} op1=-5300342847281564238
 ; BACKEND1-DAG: <VALUE_GUID op0={{.*}} op1=-3706093650706652785
 ; BACKEND1-DAG: <VALUE_GUID op0={{.*}} op1=-1039159065113703048
 ; BACKEND1-DAG: <COMBINED {{.*}} op1=0
 ; BACKEND1-DAG: <COMBINED {{.*}} op1=1
 ; BACKEND1-DAG: <COMBINED_ALIAS {{.*}} op1=1
+; BACKEND1-NEXT: <BLOCK_COUNT op0=3/>
 ; BACKEND1-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 ; The backend index for Input/distributed_indexes.ll contains summaries from
 ; itself only, as it does not import anything.
 ; BACKEND2: <MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <ENTRY {{.*}} record string = '{{.*}}distributed_indexes.ll.tmp2.bc'
 ; BACKEND2-NEXT: </MODULE_STRTAB_BLOCK
 ; BACKEND2-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; BACKEND2-NEXT: <VERSION
 ; BACKEND2-DAG: <VALUE_GUID op0={{.*}} op1=-5751648690987223394/>
 ; BACKEND2-DAG: <VALUE_GUID op0={{.*}} op1=-5300342847281564238/>
 ; BACKEND2-DAG: <VALUE_GUID op0={{.*}} op1=-1039159065113703048/>
 ; BACKEND2-NEXT: <COMBINED
 ; BACKEND2-NEXT: <COMBINED
 ; BACKEND2-NEXT: <COMBINED_ALIAS
+; BACKEND2-NEXT: <BLOCK_COUNT op0=3/>
 ; BACKEND2-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 ; Make sure that when the alias is imported as a copy of the aliasee, but the
 ; aliasee is not being imported by itself, that we can still print the summary.
 ; The aliasee should be "null".
 ; RUN: llvm-dis %t1.bc.thinlto.bc -o - | FileCheck %s --check-prefix=DIS
 ; DIS: aliasee: null
 

llvm/test/tools/llvm-lto/thinlto.ll

 ; COMBINED-NEXT: </MODULE_STRTAB_BLOCK
 ; COMBINED-NEXT: <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT: <VERSION
 ; COMBINED-NEXT: <FLAGS
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <VALUE_GUID op0={{1|2}} op1={{-3706093650706652785|-5300342847281564238}}
 ; COMBINED-NEXT: <COMBINED
 ; COMBINED-NEXT: <COMBINED
+; COMBINED-NEXT: <BLOCK_COUNT op0=2/>
 ; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 define void @f() {
 entry:
   ret void
 }