AsmPrinter: Store abbreviation data directly in DIE and DIEValue

Stop storing a `DIEAbbrev` in `DIE`, since the data fits neatly inside
the `DIEValue` list.  Besides being a cleaner data structure (avoiding
the parallel arrays), this gives us more freedom to rearrange the
`DIEValue` list.

This fixes the temporary memory regression from 845 MB up to 879 MB, and
drops it further to 829 MB for a net memory decrease of around 1.9%
(incremental decrease around 5.7%).

(I'm looking at `llc` memory usage on `verify-uselistorder.lto.opt.bc`;
see r236629 for details.)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@238364 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/AsmPrinter/AsmPrinterDwarf.cpp

@@ -254,24 +254,20 @@ void AsmPrinter::emitCFIInstruction(const MCCFIInstruction &Inst) const {
 }
 
 void AsmPrinter::emitDwarfDIE(const DIE &Die) const {
-  // Get the abbreviation for this DIE.
-  const DIEAbbrev &Abbrev = Die.getAbbrev();
-
   // Emit the code (index) for the abbreviation.
   if (isVerbose())
-    OutStreamer->AddComment("Abbrev [" + Twine(Abbrev.getNumber()) +
-                            "] 0x" + Twine::utohexstr(Die.getOffset()) +
-                            ":0x" + Twine::utohexstr(Die.getSize()) + " " +
-                            dwarf::TagString(Abbrev.getTag()));
-  EmitULEB128(Abbrev.getNumber());
+    OutStreamer->AddComment("Abbrev [" + Twine(Die.getAbbrevNumber()) + "] 0x" +
+                            Twine::utohexstr(Die.getOffset()) + ":0x" +
+                            Twine::utohexstr(Die.getSize()) + " " +
+                            dwarf::TagString(Die.getTag()));
+  EmitULEB128(Die.getAbbrevNumber());
 
   const SmallVectorImpl<DIEValue> &Values = Die.getValues();
-  const SmallVectorImpl<DIEAbbrevData> &AbbrevData = Abbrev.getData();
 
   // Emit the DIE attribute values.
   for (unsigned i = 0, N = Values.size(); i < N; ++i) {
-    dwarf::Attribute Attr = AbbrevData[i].getAttribute();
-    dwarf::Form Form = AbbrevData[i].getForm();
+    dwarf::Attribute Attr = Values[i].getAttribute();
+    dwarf::Form Form = Values[i].getForm();
     assert(Form && "Too many attributes for DIE (check abbreviation)");
 
     if (isVerbose()) {
@@ -286,7 +282,7 @@ void AsmPrinter::emitDwarfDIE(const DIE &Die) const {
   }
 
   // Emit the DIE children if any.
-  if (Abbrev.hasChildren()) {
+  if (Die.hasChildren()) {
     for (auto &Child : Die.getChildren())
       emitDwarfDIE(*Child);
 

lib/CodeGen/AsmPrinter/DIE.cpp

@@ -107,6 +107,13 @@ void DIEAbbrev::print(raw_ostream &O) {
 void DIEAbbrev::dump() { print(dbgs()); }
 #endif
 
+DIEAbbrev DIE::generateAbbrev() const {
+  DIEAbbrev Abbrev(Tag, hasChildren());
+  for (const DIEValue &V : Values)
+    Abbrev.AddAttribute(V.getAttribute(), V.getForm());
+  return Abbrev;
+}
+
 /// Climb up the parent chain to get the unit DIE to which this DIE
 /// belongs.
 const DIE *DIE::getUnit() const {
@@ -130,12 +137,11 @@ const DIE *DIE::getUnitOrNull() const {
 
 DIEValue DIE::findAttribute(dwarf::Attribute Attribute) const {
   const SmallVectorImpl<DIEValue> &Values = getValues();
-  const DIEAbbrev &Abbrevs = getAbbrev();
 
   // Iterate through all the attributes until we find the one we're
   // looking for, if we can't find it return NULL.
   for (size_t i = 0; i < Values.size(); ++i)
-    if (Abbrevs.getData()[i].getAttribute() == Attribute)
+    if (Values[i].getAttribute() == Attribute)
       return Values[i];
   return DIEValue();
 }
@@ -143,7 +149,7 @@ DIEValue DIE::findAttribute(dwarf::Attribute Attribute) const {
 #ifndef NDEBUG
 void DIE::print(raw_ostream &O, unsigned IndentCount) const {
   const std::string Indent(IndentCount, ' ');
-  bool isBlock = Abbrev.getTag() == 0;
+  bool isBlock = getTag() == 0;
 
   if (!isBlock) {
     O << Indent
@@ -153,26 +159,24 @@ void DIE::print(raw_ostream &O, unsigned IndentCount) const {
       << ", Size: " << Size << "\n";
 
     O << Indent
-      << dwarf::TagString(Abbrev.getTag())
+      << dwarf::TagString(getTag())
       << " "
-      << dwarf::ChildrenString(Abbrev.hasChildren()) << "\n";
+      << dwarf::ChildrenString(hasChildren()) << "\n";
   } else {
     O << "Size: " << Size << "\n";
   }
 
-  const SmallVectorImpl<DIEAbbrevData> &Data = Abbrev.getData();
-
   IndentCount += 2;
-  for (unsigned i = 0, N = Data.size(); i < N; ++i) {
+  for (unsigned i = 0, N = Values.size(); i < N; ++i) {
     O << Indent;
 
     if (!isBlock)
-      O << dwarf::AttributeString(Data[i].getAttribute());
+      O << dwarf::AttributeString(Values[i].getAttribute());
     else
       O << "Blk[" << i << "]";
 
     O <<  "  "
-      << dwarf::FormEncodingString(Data[i].getForm())
+      << dwarf::FormEncodingString(Values[i].getForm())
       << " ";
     Values[i].print(O);
     O << "\n";
@@ -505,9 +509,8 @@ void DIETypeSignature::print(raw_ostream &O) const {
 ///
 unsigned DIELoc::ComputeSize(const AsmPrinter *AP) const {
   if (!Size) {
-    const SmallVectorImpl<DIEAbbrevData> &AbbrevData = Abbrev.getData();
     for (unsigned i = 0, N = Values.size(); i < N; ++i)
-      Size += Values[i].SizeOf(AP, AbbrevData[i].getForm());
+      Size += Values[i].SizeOf(AP, Values[i].getForm());
   }
 
   return Size;
@@ -526,9 +529,8 @@ void DIELoc::EmitValue(const AsmPrinter *Asm, dwarf::Form Form) const {
     Asm->EmitULEB128(Size); break;
   }
 
-  const SmallVectorImpl<DIEAbbrevData> &AbbrevData = Abbrev.getData();
   for (unsigned i = 0, N = Values.size(); i < N; ++i)
-    Values[i].EmitValue(Asm, AbbrevData[i].getForm());
+    Values[i].EmitValue(Asm, Values[i].getForm());
 }
 
 /// SizeOf - Determine size of location data in bytes.
@@ -560,9 +562,8 @@ void DIELoc::print(raw_ostream &O) const {
 ///
 unsigned DIEBlock::ComputeSize(const AsmPrinter *AP) const {
   if (!Size) {
-    const SmallVectorImpl<DIEAbbrevData> &AbbrevData = Abbrev.getData();
     for (unsigned i = 0, N = Values.size(); i < N; ++i)
-      Size += Values[i].SizeOf(AP, AbbrevData[i].getForm());
+      Size += Values[i].SizeOf(AP, Values[i].getForm());
   }
 
   return Size;
@@ -579,9 +580,8 @@ void DIEBlock::EmitValue(const AsmPrinter *Asm, dwarf::Form Form) const {
   case dwarf::DW_FORM_block:  Asm->EmitULEB128(Size); break;
   }
 
-  const SmallVectorImpl<DIEAbbrevData> &AbbrevData = Abbrev.getData();
   for (unsigned i = 0, N = Values.size(); i < N; ++i)
-    Values[i].EmitValue(Asm, AbbrevData[i].getForm());
+    Values[i].EmitValue(Asm, Values[i].getForm());
 }
 
 /// SizeOf - Determine size of block data in bytes.

lib/CodeGen/AsmPrinter/DIEHash.cpp

@@ -32,12 +32,11 @@ using namespace llvm;
 /// a reference to it.
 static StringRef getDIEStringAttr(const DIE &Die, uint16_t Attr) {
   const auto &Values = Die.getValues();
-  const DIEAbbrev &Abbrevs = Die.getAbbrev();
 
   // Iterate through all the attributes until we find the one we're
   // looking for, if we can't find it return an empty string.
   for (size_t i = 0; i < Values.size(); ++i) {
-    if (Abbrevs.getData()[i].getAttribute() == Attr)
+    if (Values[i].getAttribute() == Attr)
       return Values[i].getDIEString().getString();
   }
   return StringRef("");
@@ -120,19 +119,17 @@ void DIEHash::addParentContext(const DIE &Parent) {
 // Collect all of the attributes for a particular DIE in single structure.
 void DIEHash::collectAttributes(const DIE &Die, DIEAttrs &Attrs) {
   const SmallVectorImpl<DIEValue> &Values = Die.getValues();
-  const DIEAbbrev &Abbrevs = Die.getAbbrev();
 
 #define COLLECT_ATTR(NAME)                                                     \
   case dwarf::NAME:                                                            \
     Attrs.NAME.Val = Values[i];                                                \
-    Attrs.NAME.Desc = &Abbrevs.getData()[i];                                   \
     break
 
   for (size_t i = 0, e = Values.size(); i != e; ++i) {
     DEBUG(dbgs() << "Attribute: "
-                 << dwarf::AttributeString(Abbrevs.getData()[i].getAttribute())
+                 << dwarf::AttributeString(Values[i].getAttribute())
                  << " added.\n");
-    switch (Abbrevs.getData()[i].getAttribute()) {
+    switch (Values[i].getAttribute()) {
       COLLECT_ATTR(DW_AT_name);
       COLLECT_ATTR(DW_AT_accessibility);
       COLLECT_ATTR(DW_AT_address_class);
@@ -288,8 +285,7 @@ void DIEHash::hashLocList(const DIELocList &LocList) {
 // the form.
 void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
   const DIEValue &Value = Attr.Val;
-  const DIEAbbrevData *Desc = Attr.Desc;
-  dwarf::Attribute Attribute = Desc->getAttribute();
+  dwarf::Attribute Attribute = Value.getAttribute();
 
   // Other attribute values use the letter 'A' as the marker, and the value
   // consists of the form code (encoded as an unsigned LEB128 value) followed by
@@ -311,7 +307,7 @@ void DIEHash::hashAttribute(AttrEntry Attr, dwarf::Tag Tag) {
   case DIEValue::isInteger: {
     addULEB128('A');
     addULEB128(Attribute);
-    switch (Desc->getForm()) {
+    switch (Value.getForm()) {
     case dwarf::DW_FORM_data1:
     case dwarf::DW_FORM_data2:
     case dwarf::DW_FORM_data4:

lib/CodeGen/AsmPrinter/DIEHash.h

@@ -28,9 +28,10 @@ class CompileUnit;
 class DIEHash {
 
   // The entry for a particular attribute.
+  //
+  // FIXME: Remove this struct, it's pretty boring now.
   struct AttrEntry {
     DIEValue Val;
-    const DIEAbbrevData *Desc;
   };
 
   // Collection of all attributes used in hashing a particular DIE.

lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp

@@ -51,8 +51,10 @@ void DwarfCompileUnit::addLocalLabelAddress(DIE &Die,
   if (Label)
     DD->addArangeLabel(SymbolCU(this, Label));
 
-  Die.addValue(Attribute, dwarf::DW_FORM_addr,
-               Label ? DIEValue(DIELabel(Label)) : DIEValue(DIEInteger(0)));
+  if (Label)
+    Die.addValue(Attribute, dwarf::DW_FORM_addr, DIELabel(Label));
+  else
+    Die.addValue(Attribute, dwarf::DW_FORM_addr, DIEInteger(0));
 }
 
 unsigned DwarfCompileUnit::getOrCreateSourceID(StringRef FileName,
@@ -253,9 +255,7 @@ void DwarfCompileUnit::initStmtList() {
 }
 
 void DwarfCompileUnit::applyStmtList(DIE &D) {
-  D.addValue(dwarf::DW_AT_stmt_list,
-             UnitDie.getAbbrev().getData()[stmtListIndex].getForm(),
-             UnitDie.getValues()[stmtListIndex]);
+  D.addValue(UnitDie.getValues()[stmtListIndex]);
 }
 
 void DwarfCompileUnit::attachLowHighPC(DIE &D, const MCSymbol *Begin,

lib/CodeGen/AsmPrinter/DwarfFile.cpp

@@ -24,21 +24,27 @@ DwarfFile::~DwarfFile() {}
 
 // Define a unique number for the abbreviation.
 //
-void DwarfFile::assignAbbrevNumber(DIEAbbrev &Abbrev) {
-  // Check the set for priors.
-  DIEAbbrev *InSet = AbbreviationsSet.GetOrInsertNode(&Abbrev);
+DIEAbbrev &DwarfFile::assignAbbrevNumber(DIE &Die) {
+  FoldingSetNodeID ID;
+  DIEAbbrev Abbrev = Die.generateAbbrev();
+  Abbrev.Profile(ID);
 
-  // If it's newly added.
-  if (InSet == &Abbrev) {
-    // Add to abbreviation list.
-    Abbreviations.push_back(&Abbrev);
-
-    // Assign the vector position + 1 as its number.
-    Abbrev.setNumber(Abbreviations.size());
-  } else {
-    // Assign existing abbreviation number.
-    Abbrev.setNumber(InSet->getNumber());
+  void *InsertPos;
+  if (DIEAbbrev *Existing =
+          AbbreviationsSet.FindNodeOrInsertPos(ID, InsertPos)) {
+    Die.setAbbrevNumber(Existing->getNumber());
+    return *Existing;
   }
+
+  // Move the abbreviation to the heap and assign a number.
+  DIEAbbrev *New = new (AbbrevAllocator) DIEAbbrev(std::move(Abbrev));
+  Abbreviations.push_back(New);
+  New->setNumber(Abbreviations.size());
+  Die.setAbbrevNumber(Abbreviations.size());
+
+  // Store it for lookup.
+  AbbreviationsSet.InsertNode(New, InsertPos);
+  return *New;
 }
 
 void DwarfFile::addUnit(std::unique_ptr<DwarfUnit> U) {
@@ -83,10 +89,7 @@ void DwarfFile::computeSizeAndOffsets() {
 // CU. It returns the offset after laying out the DIE.
 unsigned DwarfFile::computeSizeAndOffset(DIE &Die, unsigned Offset) {
   // Record the abbreviation.
-  assignAbbrevNumber(Die.getAbbrev());
-
-  // Get the abbreviation for this DIE.
-  const DIEAbbrev &Abbrev = Die.getAbbrev();
+  const DIEAbbrev &Abbrev = assignAbbrevNumber(Die);
 
   // Set DIE offset
   Die.setOffset(Offset);

lib/CodeGen/AsmPrinter/DwarfFile.h

@@ -37,6 +37,8 @@ class DwarfFile {
   // Target of Dwarf emission, used for sizing of abbreviations.
   AsmPrinter *Asm;
 
+  BumpPtrAllocator AbbrevAllocator;
+
   // Used to uniquely define abbreviations.
   FoldingSet<DIEAbbrev> AbbreviationsSet;
 
@@ -72,8 +74,11 @@ public:
   /// \brief Compute the size and offset of all the DIEs.
   void computeSizeAndOffsets();
 
-  /// \brief Define a unique number for the abbreviation.
-  void assignAbbrevNumber(DIEAbbrev &Abbrev);
+  /// Define a unique number for the abbreviation.
+  ///
+  /// Compute the abbreviation for \c Die, look up its unique number, and
+  /// return a reference to it in the uniquing table.
+  DIEAbbrev &assignAbbrevNumber(DIE &Die);
 
   /// \brief Add a unit to the list of CUs.
   void addUnit(std::unique_ptr<DwarfUnit> U);