[NFC] Rename `FixedLenDecoderEmitter` as `DecoderEmitter`

[0x59616e]

Summary

Since now we are able to handle both fixed length & variable
length instructions.

[0x59616e]

Rename the class name.

[RKSimon]

No objections from me @myhsu ? Just a few minors to address.

There's some clang formatting that needs to be done since you've changed the length :-) of the class name

llvm/utils/TableGen/DecoderEmitter.cpp

2692–2698

clang format

llvm/utils/TableGen/DisassemblerEmitter.cpp

98–102

clang format

129

Raise a bug to track this?

142–145

clang format

149–151

clang format

[0x59616e]

Thanks !

I've noticed the clang-format problem. The weird thing is, It happened after I rename this file, before I change anything in it. That makes me confusing. It should have not happened because I only change the file name.

So I want to take some time looking into it.

llvm/utils/TableGen/DisassemblerEmitter.cpp

129

I change this TODO just for reflecting the status of this decoder emitter to avoid confusing someone.

Resolving this means we need to deploy our varlen encoding infra onto webassembly backend. I don't know whether this is a good idea since this is a non-trivial work I guess.

[0x59616e]

I know what is going on.

clang-format only modifies the diff part. Since now I rename the file,

the whole file will be checked and modified by clang-format.

[craig.topper]

llvm/utils/TableGen/DecoderEmitter.cpp

481

Please don't reformat lines that aren't affected by your change. Use clang-format-diff.py

[myhsu]

LGTM, please resolve the formatting issues though

llvm/utils/TableGen/DisassemblerEmitter.cpp

129

I prefer creating a bug for this (and ping the wasm backend maintainer) but leave the comment unchanged

[0x59616e]

address format issue

[0x59616e]

Revert the TODO suggested my myhsu

[0x59616e]

continue addressing formating issues

llvm/utils/TableGen/CMakeLists.txt

add_tablegen(llvm-tblgen LLVM
   CodeGenRegisters.cpp
   CodeGenSchedule.cpp
   CodeGenTarget.cpp
   DAGISelEmitter.cpp
   DAGISelMatcherEmitter.cpp
   DAGISelMatcherGen.cpp
   DAGISelMatcherOpt.cpp
   DAGISelMatcher.cpp
+  DecoderEmitter.cpp
   DFAEmitter.cpp
   DFAPacketizerEmitter.cpp
   DirectiveEmitter.cpp
   DisassemblerEmitter.cpp
   ExegesisEmitter.cpp
   FastISelEmitter.cpp
-  FixedLenDecoderEmitter.cpp
   GICombinerEmitter.cpp
   GlobalISelEmitter.cpp
   InfoByHwMode.cpp
   InstrInfoEmitter.cpp
   InstrDocsEmitter.cpp
   IntrinsicEmitter.cpp
   OptEmitter.cpp
   OptParserEmitter.cpp

llvm/utils/TableGen/DecoderEmitter.cpp

-//===------------ FixedLenDecoderEmitter.cpp - Decoder Generator ----------===//
+//===---------------- DecoderEmitter.cpp - Decoder Generator --------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // It contains the tablegen backend that emits the decoder functions for
-// targets with fixed length instruction set.
+// targets with fixed/variable length instruction set.
 //
 //===----------------------------------------------------------------------===//
 
 #include "CodeGenInstruction.h"
 #include "CodeGenTarget.h"
 #include "InfoByHwMode.h"
 #include "VarLenCodeEmitterGen.h"
 #include "llvm/ADT/APInt.h"

 STATISTIC(NumEncodingsLackingDisasm, "Number of encodings without disassembler info");
 STATISTIC(NumInstructions, "Number of instructions considered");
 STATISTIC(NumEncodingsSupported, "Number of encodings supported");
 STATISTIC(NumEncodingsOmitted, "Number of encodings omitted");
 
 struct EncodingField {
   unsigned Base, Width, Offset;
   EncodingField(unsigned B, unsigned W, unsigned O)
-    : Base(B), Width(W), Offset(O) { }
+      : Base(B), Width(W), Offset(O) {}
 };
 
 struct OperandInfo {
   std::vector<EncodingField> Fields;
   std::string Decoder;
   bool HasCompleteDecoder;
   uint64_t InitValue;
 
   OperandInfo(std::string D, bool HCD)
       : Decoder(std::move(D)), HasCompleteDecoder(HCD), InitValue(0) {}
 
   void addField(unsigned Base, unsigned Width, unsigned Offset) {
     Fields.push_back(EncodingField(Base, Width, Offset));
   }
 
   unsigned numFields() const { return Fields.size(); }
 
   typedef std::vector<EncodingField>::const_iterator const_iterator;
 
   const_iterator begin() const { return Fields.begin(); }
-  const_iterator end() const   { return Fields.end();   }
+  const_iterator end() const { return Fields.end(); }
 };
 
 typedef std::vector<uint8_t> DecoderTable;
 typedef uint32_t DecoderFixup;
 typedef std::vector<DecoderFixup> FixupList;
 typedef std::vector<FixupList> FixupScopeList;
 typedef SmallSetVector<CachedHashString, 16> PredicateSet;
 typedef SmallSetVector<CachedHashString, 16> DecoderSet;

 
 raw_ostream &operator<<(raw_ostream &OS, const EncodingAndInst &Value) {
   if (Value.EncodingDef != Value.Inst->TheDef)
     OS << Value.EncodingDef->getName() << ":";
   OS << Value.Inst->TheDef->getName();
   return OS;
 }
 
-class FixedLenDecoderEmitter {
+class DecoderEmitter {
   RecordKeeper &RK;
   std::vector<EncodingAndInst> NumberedEncodings;
 
 public:
   // Defaults preserved here for documentation, even though they aren't
   // strictly necessary given the way that this is currently being called.
-  FixedLenDecoderEmitter(RecordKeeper &R, std::string PredicateNamespace,
-                         std::string GPrefix = "if (",
-                         std::string GPostfix = " == MCDisassembler::Fail)",
-                         std::string ROK = "MCDisassembler::Success",
-                         std::string RFail = "MCDisassembler::Fail",
-                         std::string L = "")
+  DecoderEmitter(RecordKeeper &R, std::string PredicateNamespace,
+                 std::string RFail = "MCDisassembler::Fail", std::string L = "")
       : RK(R), Target(R), PredicateNamespace(std::move(PredicateNamespace)),
         GuardPrefix(std::move(GPrefix)), GuardPostfix(std::move(GPostfix)),
         ReturnOK(std::move(ROK)), ReturnFail(std::move(RFail)),
         Locals(std::move(L)) {}
 
   // Emit the decoder state machine table.
   void emitTable(formatted_raw_ostream &o, DecoderTable &Table,
                  unsigned Indentation, unsigned BitWidth,
                  StringRef Namespace) const;
   void emitInstrLenTable(formatted_raw_ostream &OS,
                          std::vector<unsigned> &InstrLen) const;
   void emitPredicateFunction(formatted_raw_ostream &OS,
                              PredicateSet &Predicates,
                              unsigned Indentation) const;
-  void emitDecoderFunction(formatted_raw_ostream &OS,
-                           DecoderSet &Decoders,
+  void emitDecoderFunction(formatted_raw_ostream &OS, DecoderSet &Decoders,
                            unsigned Indentation) const;
 
   // run - Output the code emitter
   void run(raw_ostream &o);
 
 private:
   CodeGenTarget Target;
 
typedef enum {
   BIT_UNSET,     // '?'
   BIT_UNFILTERED // unfiltered
 } bit_value_t;
 
 static bool ValueSet(bit_value_t V) {
   return (V == BIT_TRUE || V == BIT_FALSE);
 }
 
-static bool ValueNotSet(bit_value_t V) {
-  return (V == BIT_UNSET);
-}
+static bool ValueNotSet(bit_value_t V) { return (V == BIT_UNSET); }
 
 static int Value(bit_value_t V) {
   return ValueNotSet(V) ? -1 : (V == BIT_FALSE ? 0 : 1);
 }
 
 static bit_value_t bitFromBits(const BitsInit &bits, unsigned index) {
   if (BitInit *bit = dyn_cast<BitInit>(bits.getBit(index)))
     return bit->getValue() ? BIT_TRUE : BIT_FALSE;

 ///
 /// The encoding info in the .td files does not specify this meta information,
 /// which could have been used by the decoder to resolve the conflict.  The
 /// decoder could try to decode the even/odd register numbering and assign to
 /// VST4q8a or VST4q8b, but for the time being, the decoder chooses the "a"
 /// version and return the Opcode since the two have the same Asm format string.
 class Filter {
 protected:
-  const FilterChooser *Owner;// points to the FilterChooser who owns this filter
+  const FilterChooser
+      *Owner;        // points to the FilterChooser who owns this filter
   unsigned StartBit; // the starting bit position
-  unsigned NumBits; // number of bits to filter
-  bool Mixed; // a mixed region contains both set and unset bits
+  unsigned NumBits;  // number of bits to filter
+  bool Mixed;        // a mixed region contains both set and unset bits
 
   // Map of well-known segment value to the set of uid's with that value.
-  std::map<uint64_t, std::vector<EncodingIDAndOpcode>>
-      FilteredInstructions;
+  std::map<uint64_t, std::vector<EncodingIDAndOpcode>> FilteredInstructions;
 
   // Set of uid's with non-constant segment values.
   std::vector<EncodingIDAndOpcode> VariableInstructions;
 
   // Map of well-known segment value to its delegate.
   std::map<uint64_t, std::unique_ptr<const FilterChooser>> FilterChooserMap;
 
   // Number of instructions which fall under FilteredInstructions category.
protected:
 
   // Index of the best filter from Filters.
   int BestIndex;
 
   // Width of instructions
   unsigned BitWidth;
 
   // Parent emitter
-  const FixedLenDecoderEmitter *Emitter;
+  const DecoderEmitter *Emitter;
 
 public:
   FilterChooser(ArrayRef<EncodingAndInst> Insts,
                 const std::vector<EncodingIDAndOpcode> &IDs,
                 const std::map<unsigned, std::vector<OperandInfo>> &Ops,
-                unsigned BW, const FixedLenDecoderEmitter *E)
+                unsigned BW, const DecoderEmitter *E)
       : AllInstructions(Insts), Opcodes(IDs), Operands(Ops),
         FilterBitValues(BW, BIT_UNFILTERED), Parent(nullptr), BestIndex(-1),
         BitWidth(BW), Emitter(E) {
     doFilter();
   }
 
   FilterChooser(ArrayRef<EncodingAndInst> Insts,
                 const std::vector<EncodingIDAndOpcode> &IDs,
protected:
   // Returns false if there exists any uninitialized bit value in the range.
   // Returns true, otherwise.
   bool fieldFromInsn(uint64_t &Field, insn_t &Insn, unsigned StartBit,
                      unsigned NumBits) const;
 
   /// dumpFilterArray - dumpFilterArray prints out debugging info for the given
   /// filter array as a series of chars.
   void dumpFilterArray(raw_ostream &o,
                        const std::vector<bit_value_t> & filter) const;
 
   /// dumpStack - dumpStack traverses the filter chooser chain and calls
   /// dumpFilterArray on each filter chooser up to the top level one.
   void dumpStack(raw_ostream &o, const char *prefix) const;
 
   Filter &bestFilter() {
     assert(BestIndex != -1 && "BestIndex not set");
     return Filters[BestIndex];
protected:
 
   // Emits code to check the Predicates member of an instruction are true.
   // Returns true if predicate matches were emitted, false otherwise.
   bool emitPredicateMatch(raw_ostream &o, unsigned &Indentation,
                           unsigned Opc) const;
 
   bool doesOpcodeNeedPredicate(unsigned Opc) const;
   unsigned getPredicateIndex(DecoderTableInfo &TableInfo, StringRef P) const;
-  void emitPredicateTableEntry(DecoderTableInfo &TableInfo,
-                               unsigned Opc) const;
+  void emitPredicateTableEntry(DecoderTableInfo &TableInfo, unsigned Opc) const;
 
-  void emitSoftFailTableEntry(DecoderTableInfo &TableInfo,
-                              unsigned Opc) const;
+  void emitSoftFailTableEntry(DecoderTableInfo &TableInfo, unsigned Opc) const;
 
   // Emits table entries to decode the singleton.
   void emitSingletonTableEntry(DecoderTableInfo &TableInfo,
                                EncodingIDAndOpcode Opc) const;
 
   // Emits code to decode the singleton, and then to decode the rest.
   void emitSingletonTableEntry(DecoderTableInfo &TableInfo,
                                const Filter &Best) const;

 
 ///////////////////////////
 //                       //
 // Filter Implementation //
 //                       //
 ///////////////////////////
 
 Filter::Filter(Filter &&f)
     : Owner(f.Owner), StartBit(f.StartBit), NumBits(f.NumBits), Mixed(f.Mixed),
       FilteredInstructions(std::move(f.FilteredInstructions)),
       VariableInstructions(std::move(f.VariableInstructions)),
-    FilterChooserMap(std::move(f.FilterChooserMap)), NumFiltered(f.NumFiltered),
-    LastOpcFiltered(f.LastOpcFiltered) {
-}
+      FilterChooserMap(std::move(f.FilterChooserMap)),
+      NumFiltered(f.NumFiltered), LastOpcFiltered(f.LastOpcFiltered) {}
 
 Filter::Filter(FilterChooser &owner, unsigned startBit, unsigned numBits,
                bool mixed)
     : Owner(&owner), StartBit(startBit), NumBits(numBits), Mixed(mixed) {
   assert(StartBit + NumBits - 1 < Owner->BitWidth);
 
   NumFiltered = 0;
   LastOpcFiltered = {0, 0};
 
   for (unsigned i = 0, e = Owner->Opcodes.size(); i != e; ++i) {
     insn_t Insn;
 
if (ok) {
       ++NumFiltered;
     } else {
       // Some of the encoding bit(s) are unspecified.  This contributes to
       // one additional member of "Variable" instructions.
       VariableInstructions.push_back(Owner->Opcodes[i]);
     }
   }
 
-  assert((FilteredInstructions.size() + VariableInstructions.size() > 0)
-         && "Filter returns no instruction categories");
+  assert((FilteredInstructions.size() + VariableInstructions.size() > 0) &&
+         "Filter returns no instruction categories");
 }
 
 // Divides the decoding task into sub tasks and delegates them to the
 // inferior FilterChooser's.
 //
 // A special case arises when there's only one entry in the filtered
 // instructions.  In order to unambiguously decode the singleton, we need to
 // match the remaining undecoded encoding bits against the singleton.
 void Filter::recurse() {
   // Starts by inheriting our parent filter chooser's filter bit values.
   std::vector<bit_value_t> BitValueArray(Owner->FilterBitValues);
 
   if (!VariableInstructions.empty()) {
     // Conservatively marks each segment position as BIT_UNSET.
     for (unsigned bitIndex = 0; bitIndex < NumBits; ++bitIndex)
       BitValueArray[StartBit + bitIndex] = BIT_UNSET;
 
     // Delegates to an inferior filter chooser for further processing on this
     // group of instructions whose segment values are variable.
-    FilterChooserMap.insert(std::make_pair(NO_FIXED_SEGMENTS_SENTINEL,
+    FilterChooserMap.insert(std::make_pair(
+        NO_FIXED_SEGMENTS_SENTINEL,
         std::make_unique<FilterChooser>(Owner->AllInstructions,
-            VariableInstructions, Owner->Operands, BitValueArray, *Owner)));
+                                        VariableInstructions, Owner->Operands,
+                                        BitValueArray, *Owner)));
   }
 
   // No need to recurse for a singleton filtered instruction.
   // See also Filter::emit*().
   if (getNumFiltered() == 1) {
     assert(FilterChooserMap.size() == 1);
     return;
   }
 
   // Otherwise, create sub choosers.
   for (const auto &Inst : FilteredInstructions) {
 
     // Marks all the segment positions with either BIT_TRUE or BIT_FALSE.
     for (unsigned bitIndex = 0; bitIndex < NumBits; ++bitIndex) {
       if (Inst.first & (1ULL << bitIndex))
         BitValueArray[StartBit + bitIndex] = BIT_TRUE;
       else
         BitValueArray[StartBit + bitIndex] = BIT_FALSE;
     }
 
     // Delegates to an inferior filter chooser for further processing on this
     // category of instructions.
     FilterChooserMap.insert(std::make_pair(
         Inst.first, std::make_unique<FilterChooser>(
-                                Owner->AllInstructions, Inst.second,
-                                Owner->Operands, BitValueArray, *Owner)));
+                        Owner->AllInstructions, Inst.second, Owner->Operands,
+                        BitValueArray, *Owner)));
   }
 }
 
 static void resolveTableFixups(DecoderTable &Table, const FixupList &Fixups,
                                uint32_t DestIdx) {
   // Any NumToSkip fixups in the current scope can resolve to the
   // current location.
-  for (FixupList::const_reverse_iterator I = Fixups.rbegin(),
-                                         E = Fixups.rend();
+  for (FixupList::const_reverse_iterator I = Fixups.rbegin(), E = Fixups.rend();
        I != E; ++I) {
     // Calculate the distance from the byte following the fixup entry byte
     // to the destination. The Target is calculated from after the 16-bit
     // NumToSkip entry itself, so subtract two  from the displacement here
     // to account for that.
     uint32_t FixupIdx = *I;
     uint32_t Delta = DestIdx - FixupIdx - 3;
     // Our NumToSkip entries are 24-bits. Make sure our table isn't too
if (Filter.first == NO_FIXED_SEGMENTS_SENTINEL) {
 
       // Each scope should always have at least one filter value to check
       // for.
       assert(PrevFilter != 0 && "empty filter set!");
       FixupList &CurScope = TableInfo.FixupStack.back();
       // Resolve any NumToSkip fixups in the current scope.
       resolveTableFixups(Table, CurScope, Table.size());
       CurScope.clear();
-      PrevFilter = 0;  // Don't re-process the filter's fallthrough.
+      PrevFilter = 0; // Don't re-process the filter's fallthrough.
     } else {
       Table.push_back(MCD::OPC_FilterValue);
       // Encode and emit the value to filter against.
       uint8_t Buffer[16];
       unsigned Len = encodeULEB128(Filter.first, Buffer);
       Table.insert(Table.end(), Buffer, Buffer + Len);
       // Reserve space for the NumToSkip entry. We'll backpatch the value
       // later.
for (auto &Filter : FilterChooserMap) {
     // encoding bits do not match exactly.
     Filter.second->emitTableEntries(TableInfo);
 
     // Now that we've emitted the body of the handler, update the NumToSkip
     // of the filter itself to be able to skip forward when false. Subtract
     // two as to account for the width of the NumToSkip field itself.
     if (PrevFilter) {
       uint32_t NumToSkip = Table.size() - PrevFilter - 3;
-      assert(NumToSkip < (1u << 24) && "disassembler decoding table too large!");
+      assert(NumToSkip < (1u << 24) &&
+             "disassembler decoding table too large!");
       Table[PrevFilter] = (uint8_t)NumToSkip;
       Table[PrevFilter + 1] = (uint8_t)(NumToSkip >> 8);
       Table[PrevFilter + 2] = (uint8_t)(NumToSkip >> 16);
     }
   }
 
   // Any remaining unresolved fixups bubble up to the parent fixup scope.
   assert(TableInfo.FixupStack.size() > 1 && "fixup stack underflow!");

 
 //////////////////////////////////
 //                              //
 // Filterchooser Implementation //
 //                              //
 //////////////////////////////////
 
 // Emit the decoder state machine table.
-void FixedLenDecoderEmitter::emitTable(formatted_raw_ostream &OS,
-                                       DecoderTable &Table,
-                                       unsigned Indentation,
-                                       unsigned BitWidth,
-                                       StringRef Namespace) const {
+void DecoderEmitter::emitTable(formatted_raw_ostream &OS, DecoderTable &Table,
+                               unsigned Indentation, unsigned BitWidth,
   OS.indent(Indentation) << "static const uint8_t DecoderTable" << Namespace
                          << BitWidth << "[] = {\n";
 
   Indentation += 2;
 
   // FIXME: We may be able to use the NumToSkip values to recover
   // appropriate indentation levels.
   DecoderTable::const_iterator I = Table.begin();
   DecoderTable::const_iterator E = Table.end();
   while (I != E) {
-    assert (I < E && "incomplete decode table entry!");
+    assert(I < E && "incomplete decode table entry!");
 
     uint64_t Pos = I - Table.begin();
     OS << "/* " << Pos << " */";
     OS.PadToColumn(12);
 
     switch (*I) {
     default:
       PrintFatalError("invalid decode table opcode");
     case MCD::OPC_ExtractField: {
       ++I;
       unsigned Start = *I++;
       unsigned Len = *I++;
-      OS.indent(Indentation) << "MCD::OPC_ExtractField, " << Start << ", "
-        << Len << ",  // Inst{";
+      OS.indent(Indentation)
+          << "MCD::OPC_ExtractField, " << Start << ", " << Len << ",  // Inst{";
       if (Len > 1)
         OS << (Start + Len - 1) << "-";
       OS << Start << "} ...\n";
       break;
     }
     case MCD::OPC_FilterValue: {
       ++I;
       OS.indent(Indentation) << "MCD::OPC_FilterValue, ";
case MCD::OPC_FilterValue: {
       NumToSkip |= Byte << 16;
       OS << "// Skip to: " << ((I - Table.begin()) + NumToSkip) << "\n";
       break;
     }
     case MCD::OPC_CheckField: {
       ++I;
       unsigned Start = *I++;
       unsigned Len = *I++;
-      OS.indent(Indentation) << "MCD::OPC_CheckField, " << Start << ", "
-        << Len << ", ";// << Val << ", " << NumToSkip << ",\n";
+      OS.indent(Indentation) << "MCD::OPC_CheckField, " << Start << ", " << Len
+                             << ", "; // << Val << ", " << NumToSkip << ",\n";
       // ULEB128 encoded field value.
       for (; *I >= 128; ++I)
         OS << (unsigned)*I << ", ";
       OS << (unsigned)*I++ << ", ";
       // 24-bit numtoskip value.
       uint8_t Byte = *I++;
       uint32_t NumToSkip = Byte;
       OS << (unsigned)Byte << ", ";
while (I != E) {
     }
     case MCD::OPC_Decode:
     case MCD::OPC_TryDecode: {
       bool IsTry = *I == MCD::OPC_TryDecode;
       ++I;
       // Extract the ULEB128 encoded Opcode to a buffer.
       uint8_t Buffer[16], *p = Buffer;
       while ((*p++ = *I++) >= 128)
-        assert((p - Buffer) <= (ptrdiff_t)sizeof(Buffer)
-               && "ULEB128 value too large!");
+        assert((p - Buffer) <= (ptrdiff_t)sizeof(Buffer) &&
+               "ULEB128 value too large!");
       // Decode the Opcode value.
       unsigned Opc = decodeULEB128(Buffer);
-      OS.indent(Indentation) << "MCD::OPC_" << (IsTry ? "Try" : "")
-        << "Decode, ";
+      OS.indent(Indentation)
+          << "MCD::OPC_" << (IsTry ? "Try" : "") << "Decode, ";
       for (p = Buffer; *p >= 128; ++p)
         OS << (unsigned)*p << ", ";
       OS << (unsigned)*p << ", ";
 
       // Decoder index.
       for (; *I >= 128; ++I)
         OS << (unsigned)*I << ", ";
       OS << (unsigned)*I++ << ", ";
void DecoderEmitter::emitTable(formatted_raw_ostream &OS, DecoderTable &Table,
   }
   OS.indent(Indentation) << "0\n";
 
   Indentation -= 2;
 
   OS.indent(Indentation) << "};\n\n";
 }
 
-void FixedLenDecoderEmitter::emitInstrLenTable(
-    formatted_raw_ostream &OS, std::vector<unsigned> &InstrLen) const {
+void DecoderEmitter::emitInstrLenTable(formatted_raw_ostream &OS,
+                                       std::vector<unsigned> &InstrLen) const {
   OS << "static const uint8_t InstrLenTable[] = {\n";
   for (unsigned &Len : InstrLen) {
     OS << Len << ",\n";
   }
   OS << "};\n\n";
 }
 
-void FixedLenDecoderEmitter::
-emitPredicateFunction(formatted_raw_ostream &OS, PredicateSet &Predicates,
+void DecoderEmitter::emitPredicateFunction(formatted_raw_ostream &OS,
+                                           PredicateSet &Predicates,
                                            unsigned Indentation) const {
   // The predicate function is just a big switch statement based on the
   // input predicate index.
   OS.indent(Indentation) << "static bool checkDecoderPredicate(unsigned Idx, "
                          << "const FeatureBitset &Bits) {\n";
   Indentation += 2;
   if (!Predicates.empty()) {
     OS.indent(Indentation) << "switch (Idx) {\n";
-    OS.indent(Indentation) << "default: llvm_unreachable(\"Invalid index!\");\n";
+    OS.indent(Indentation)
+        << "default: llvm_unreachable(\"Invalid index!\");\n";
     unsigned Index = 0;
     for (const auto &Predicate : Predicates) {
       OS.indent(Indentation) << "case " << Index++ << ":\n";
-      OS.indent(Indentation+2) << "return (" << Predicate << ");\n";
+      OS.indent(Indentation + 2) << "return (" << Predicate << ");\n";
     }
     OS.indent(Indentation) << "}\n";
   } else {
     // No case statement to emit
     OS.indent(Indentation) << "llvm_unreachable(\"Invalid index!\");\n";
   }
   Indentation -= 2;
   OS.indent(Indentation) << "}\n\n";
 }
 
-void FixedLenDecoderEmitter::
-emitDecoderFunction(formatted_raw_ostream &OS, DecoderSet &Decoders,
+void DecoderEmitter::emitDecoderFunction(formatted_raw_ostream &OS,
+                                         DecoderSet &Decoders,
                                          unsigned Indentation) const {
   // The decoder function is just a big switch statement based on the
   // input decoder index.
   OS.indent(Indentation) << "template <typename InsnType>\n";
   OS.indent(Indentation) << "static DecodeStatus decodeToMCInst(DecodeStatus S,"
                          << " unsigned Idx, InsnType insn, MCInst &MI,\n";
   OS.indent(Indentation)
       << "                                   uint64_t "
       << "Address, const MCDisassembler *Decoder, bool &DecodeComplete) {\n";
   Indentation += 2;
   OS.indent(Indentation) << "DecodeComplete = true;\n";
   // TODO: When InsnType is large, using uint64_t limits all fields to 64 bits
   // It would be better for emitBinaryParser to use a 64-bit tmp whenever
   // possible but fall back to an InsnType-sized tmp for truly large fields.
   OS.indent(Indentation) << "using TmpType = "
                             "std::conditional_t<std::is_integral<InsnType>::"
                             "value, InsnType, uint64_t>;\n";
   OS.indent(Indentation) << "TmpType tmp;\n";
   OS.indent(Indentation) << "switch (Idx) {\n";
   OS.indent(Indentation) << "default: llvm_unreachable(\"Invalid index!\");\n";
   unsigned Index = 0;
   for (const auto &Decoder : Decoders) {
     OS.indent(Indentation) << "case " << Index++ << ":\n";
     OS << Decoder;
-    OS.indent(Indentation+2) << "return S;\n";
+    OS.indent(Indentation + 2) << "return S;\n";
   }
   OS.indent(Indentation) << "}\n";
   Indentation -= 2;
   OS.indent(Indentation) << "}\n\n";
 }
 
 // Populates the field of the insn given the start position and the number of
 // consecutive bits to scan for.
if (Insn[StartBit + i] == BIT_TRUE)
       Field = Field | (1ULL << i);
   }
 
   return true;
 }
 
 /// dumpFilterArray - dumpFilterArray prints out debugging info for the given
 /// filter array as a series of chars.
-void FilterChooser::dumpFilterArray(raw_ostream &o,
-                                 const std::vector<bit_value_t> &filter) const {
+void FilterChooser::dumpFilterArray(
+    raw_ostream &o, const std::vector<bit_value_t> &filter) const {
   for (unsigned bitIndex = BitWidth; bitIndex > 0; bitIndex--) {
     switch (filter[bitIndex - 1]) {
     case BIT_UNFILTERED:
       o << ".";
       break;
     case BIT_UNSET:
       o << "_";
       break;
unsigned FilterChooser::getIslands(std::vector<unsigned> &StartBits,
   // 1: Water (the bit value does not affect decoding)
   // 2: Island (well-known bit value needed for decoding)
   int State = 0;
 
   for (unsigned i = 0; i < BitWidth; ++i) {
     int64_t Val = Value(Insn[i]);
     bool Filtered = PositionFiltered(i);
     switch (State) {
-    default: llvm_unreachable("Unreachable code!");
+    default:
+      llvm_unreachable("Unreachable code!");
     case 0:
     case 1:
       if (Filtered || Val == -1)
         State = 1; // Still in Water
       else {
         State = 2; // Into the Island
         BitNo = 0;
         StartBits.push_back(i);
for (const EncodingField &EF : OpInfo) {
     else if (EF.Offset != 0)
       o << " << " << EF.Offset;
     o << ";\n";
   }
 
   if (Decoder != "") {
     OpHasCompleteDecoder = OpInfo.HasCompleteDecoder;
     o.indent(Indentation) << Emitter->GuardPrefix << Decoder
                           << "(MI, tmp, Address, Decoder)"
-      << Emitter->GuardPostfix
-      << " { " << (OpHasCompleteDecoder ? "" : "DecodeComplete = false; ")
+                          << Emitter->GuardPostfix << " { "
+                          << (OpHasCompleteDecoder ? ""
+                                                   : "DecodeComplete = false; ")
                           << "return MCDisassembler::Fail; }\n";
   } else {
     OpHasCompleteDecoder = true;
     o.indent(Indentation) << "MI.addOperand(MCOperand::createImm(tmp));\n";
   }
 }
 
 void FilterChooser::emitDecoder(raw_ostream &OS, unsigned Indentation,
                                 unsigned Opc, bool &HasCompleteDecoder) const {
   HasCompleteDecoder = true;
 
   for (const auto &Op : Operands.find(Opc)->second) {
     // If a custom instruction decoder was specified, use that.
     if (Op.numFields() == 0 && !Op.Decoder.empty()) {
       HasCompleteDecoder = Op.HasCompleteDecoder;
-      OS.indent(Indentation) << Emitter->GuardPrefix << Op.Decoder
-        << "(MI, insn, Address, Decoder)"
-        << Emitter->GuardPostfix
-        << " { " << (HasCompleteDecoder ? "" : "DecodeComplete = false; ")
+      OS.indent(Indentation)
+          << Emitter->GuardPrefix << Op.Decoder
+          << "(MI, insn, Address, Decoder)" << Emitter->GuardPostfix << " { "
+          << (HasCompleteDecoder ? "" : "DecodeComplete = false; ")
           << "return MCDisassembler::Fail; }\n";
       break;
     }
 
     bool OpHasCompleteDecoder;
     emitBinaryParser(OS, Indentation, Op, OpHasCompleteDecoder);
     if (!OpHasCompleteDecoder)
       HasCompleteDecoder = false;
   }
 }
 
-unsigned FilterChooser::getDecoderIndex(DecoderSet &Decoders,
-                                        unsigned Opc,
+unsigned FilterChooser::getDecoderIndex(DecoderSet &Decoders, unsigned Opc,
                                         bool &HasCompleteDecoder) const {
   // Build up the predicate string.
   SmallString<256> Decoder;
   // FIXME: emitDecoder() function can take a buffer directly rather than
   // a stream.
   raw_svector_ostream S(Decoder);
   unsigned I = 4;
   emitDecoder(S, I, Opc, HasCompleteDecoder);
void FilterChooser::emitPredicateTableEntry(DecoderTableInfo &TableInfo,
   TableInfo.Table.push_back(0);
 }
 
 void FilterChooser::emitSoftFailTableEntry(DecoderTableInfo &TableInfo,
                                            unsigned Opc) const {
   const RecordVal *RV = AllInstructions[Opc].EncodingDef->getValue("SoftFail");
   BitsInit *SFBits = RV ? dyn_cast<BitsInit>(RV->getValue()) : nullptr;
 
-  if (!SFBits) return;
+  if (!SFBits)
+    return;
   BitsInit *InstBits =
       AllInstructions[Opc].EncodingDef->getValueAsBitsInit("Inst");
 
   APInt PositiveMask(BitWidth, 0ULL);
   APInt NegativeMask(BitWidth, 0ULL);
   for (unsigned i = 0; i < BitWidth; ++i) {
     bit_value_t B = bitFromBits(*SFBits, i);
     bit_value_t IB = bitFromBits(*InstBits, i);
 
-    if (B != BIT_TRUE) continue;
+    if (B != BIT_TRUE)
+      continue;
 
     switch (IB) {
     case BIT_FALSE:
       // The bit is meant to be false, so emit a check to see if it is true.
       PositiveMask.setBit(i);
       break;
     case BIT_TRUE:
       // The bit is meant to be true, so emit a check to see if it is false.
void FilterChooser::emitSingletonTableEntry(DecoderTableInfo &TableInfo,
 
   unsigned Size = StartBits.size();
 
   // Emit the predicate table entry if one is needed.
   emitPredicateTableEntry(TableInfo, Opc.EncodingID);
 
   // Check any additional encoding fields needed.
   for (unsigned I = Size; I != 0; --I) {
-    unsigned NumBits = EndBits[I-1] - StartBits[I-1] + 1;
+    unsigned NumBits = EndBits[I - 1] - StartBits[I - 1] + 1;
     TableInfo.Table.push_back(MCD::OPC_CheckField);
-    TableInfo.Table.push_back(StartBits[I-1]);
+    TableInfo.Table.push_back(StartBits[I - 1]);
     TableInfo.Table.push_back(NumBits);
     uint8_t Buffer[16], *p;
-    encodeULEB128(FieldVals[I-1], Buffer);
-    for (p = Buffer; *p >= 128 ; ++p)
+    encodeULEB128(FieldVals[I - 1], Buffer);
+    for (p = Buffer; *p >= 128; ++p)
       TableInfo.Table.push_back(*p);
     TableInfo.Table.push_back(*p);
     // Push location for NumToSkip backpatching.
     TableInfo.FixupStack.back().push_back(TableInfo.Table.size());
     // The fixup is always 24-bits, so go ahead and allocate the space
     // in the table so all our relative position calculations work OK even
     // before we fully resolve the real value here.
     TableInfo.Table.push_back(0);
void FilterChooser::emitSingletonTableEntry(DecoderTableInfo &TableInfo,
   // whether the instruction decoder is complete or not. If it is complete
   // then it handles all possible values of remaining variable/unfiltered bits
   // and for any value can determine if the bitpattern is a valid instruction
   // or not. This means OPC_Decode will be the final step in the decoding
   // process. If it is not complete, then the Fail return code from the
   // decoder method indicates that additional processing should be done to see
   // if there is any other instruction that also matches the bitpattern and
   // can decode it.
-  TableInfo.Table.push_back(HasCompleteDecoder ? MCD::OPC_Decode :
-      MCD::OPC_TryDecode);
+  TableInfo.Table.push_back(HasCompleteDecoder ? MCD::OPC_Decode
+                                               : MCD::OPC_TryDecode);
   NumEncodingsSupported++;
   uint8_t Buffer[16], *p;
   encodeULEB128(Opc.Opcode, Buffer);
-  for (p = Buffer; *p >= 128 ; ++p)
+  for (p = Buffer; *p >= 128; ++p)
     TableInfo.Table.push_back(*p);
   TableInfo.Table.push_back(*p);
 
   SmallString<16> Bytes;
   raw_svector_ostream S(Bytes);
   encodeULEB128(DIdx, S);
 
   // Decoder index
for (auto Opcode : Opcodes) {
     errs() << '\n';
   }
 }
 
 static std::string findOperandDecoderMethod(Record *Record) {
   std::string Decoder;
 
   RecordVal *DecoderString = Record->getValue("DecoderMethod");
-  StringInit *String = DecoderString ?
-    dyn_cast<StringInit>(DecoderString->getValue()) : nullptr;
+  StringInit *String =
+      DecoderString ? dyn_cast<StringInit>(DecoderString->getValue()) : nullptr;
   if (String) {
     Decoder = std::string(String->getValue());
     if (!Decoder.empty())
       return Decoder;
   }
 
   if (Record->isSubClassOf("RegisterOperand"))
     Record = Record->getValueAsDef("RegClass");
 
   if (Record->isSubClassOf("RegisterClass")) {
     Decoder = "Decode" + Record->getName().str() + "RegisterClass";
   } else if (Record->isSubClassOf("PointerLikeRegClass")) {
     Decoder = "DecodePointerLikeRegClass" +
               utostr(Record->getValueAsInt("RegClassKind"));
   }
 
   return Decoder;
 }
 
 OperandInfo getOpInfo(Record *TypeRecord) {
   std::string Decoder = findOperandDecoderMethod(TypeRecord);
 
if (Bits.allInComplete())
     return 0;
 
   std::vector<OperandInfo> InsnOperands;
 
   // If the instruction has specified a custom decoding hook, use that instead
   // of trying to auto-generate the decoder.
   StringRef InstDecoder = EncodingDef.getValueAsString("DecoderMethod");
   if (InstDecoder != "") {
-    bool HasCompleteInstDecoder = EncodingDef.getValueAsBit("hasCompleteDecoder");
+    bool HasCompleteInstDecoder =
+        EncodingDef.getValueAsBit("hasCompleteDecoder");
     InsnOperands.push_back(
         OperandInfo(std::string(InstDecoder), HasCompleteInstDecoder));
     Operands[Opc] = InsnOperands;
     return Bits.getNumBits();
   }
 
   // Generate a description of the operand of the instruction that we know
   // how to decode automatically.
   // FIXME: We'll need to have a way to manually override this as needed.
 
   // Gather the outputs/inputs of the instruction, so we can find their
   // positions in the encoding.  This assumes for now that they appear in the
   // MCInst in the order that they're listed.
-  std::vector<std::pair<Init*, StringRef>> InOutOperands;
-  DagInit *Out  = Def.getValueAsDag("OutOperandList");
-  DagInit *In  = Def.getValueAsDag("InOperandList");
+  std::vector<std::pair<Init *, StringRef>> InOutOperands;
+  DagInit *Out = Def.getValueAsDag("OutOperandList");
+  DagInit *In = Def.getValueAsDag("InOperandList");
   for (unsigned i = 0; i < Out->getNumArgs(); ++i)
     InOutOperands.push_back(
         std::make_pair(Out->getArg(i), Out->getArgNameStr(i)));
   for (unsigned i = 0; i < In->getNumArgs(); ++i)
     InOutOperands.push_back(
         std::make_pair(In->getArg(i), In->getArgNameStr(i)));
 
   // Search for tied operands, so that we can correctly instantiate
   // operands that are not explicitly represented in the encoding.
   std::map<std::string, std::string> TiedNames;
   for (unsigned i = 0; i < CGI.Operands.size(); ++i) {
     int tiedTo = CGI.Operands[i].getTiedRegister();
     if (tiedTo != -1) {
       std::pair<unsigned, unsigned> SO =
           CGI.Operands.getSubOperandNumber(tiedTo);
       TiedNames[std::string(InOutOperands[i].second)] =
           std::string(InOutOperands[SO.first].second);
       TiedNames[std::string(InOutOperands[SO.first].second)] =
           std::string(InOutOperands[i].second);
     }
   }
 
   if (IsVarLenInst) {
OS << "      S = decodeToMCInst(S, DecodeIdx, insn, MI, Address, DisAsm, "
      << "    }\n"
      << "  }\n"
      << "  llvm_unreachable(\"bogosity detected in disassembler state "
         "machine!\");\n"
      << "}\n\n";
 }
 
 // Emits disassembler code for instruction decoding.
-void FixedLenDecoderEmitter::run(raw_ostream &o) {
+void DecoderEmitter::run(raw_ostream &o) {
   formatted_raw_ostream OS(o);
   OS << "#include \"llvm/MC/MCInst.h\"\n";
   OS << "#include \"llvm/MC/MCSubtargetInfo.h\"\n";
   OS << "#include \"llvm/MC/SubtargetFeature.h\"\n";
   OS << "#include \"llvm/Support/DataTypes.h\"\n";
   OS << "#include \"llvm/Support/Debug.h\"\n";
   OS << "#include \"llvm/Support/LEB128.h\"\n";
   OS << "#include \"llvm/Support/raw_ostream.h\"\n";
if (const RecordVal *RV =
       }
     }
     // This instruction is encoded the same on all HwModes. Emit it for all
     // HwModes.
     for (StringRef HwModeName : HwModeNames)
       NumberedEncodings.emplace_back(NumberedInstruction->TheDef,
                                      NumberedInstruction, HwModeName);
   }
-  for (const auto &NumberedAlias : RK.getAllDerivedDefinitions("AdditionalEncoding"))
+  for (const auto &NumberedAlias :
+       RK.getAllDerivedDefinitions("AdditionalEncoding"))
     NumberedEncodings.emplace_back(
         NumberedAlias,
         &Target.getInstruction(NumberedAlias->getValueAsDef("AliasOf")));
 
   std::map<std::pair<std::string, unsigned>, std::vector<EncodingIDAndOpcode>>
       OpcMap;
   std::map<unsigned, std::vector<OperandInfo>> Operands;
   std::vector<unsigned> InstrLen;
for (unsigned i = 0; i < NumberedEncodings.size(); ++i) {
     } else {
       NumEncodingsOmitted++;
     }
   }
 
   DecoderTableInfo TableInfo;
   for (const auto &Opc : OpcMap) {
     // Emit the decoder for this namespace+width combination.
-    ArrayRef<EncodingAndInst> NumberedEncodingsRef(
-        NumberedEncodings.data(), NumberedEncodings.size());
+    ArrayRef<EncodingAndInst> NumberedEncodingsRef(NumberedEncodings.data(),
+                                                   NumberedEncodings.size());
     FilterChooser FC(NumberedEncodingsRef, Opc.second, Operands,
                      IsVarLenInst ? MaxInstLen : 8 * Opc.first.second, this);
 
     // The decode table is cleared for each top level decoder function. The
     // predicates and decoders themselves, however, are shared across all
     // decoders to give more opportunities for uniqueing.
     TableInfo.Table.clear();
     TableInfo.FixupStack.clear();
void DecoderEmitter::run(raw_ostream &o) {
   // Emit the main entry point for the decoder, decodeInstruction().
   emitDecodeInstruction(OS, IsVarLenInst);
 
   OS << "\n} // end namespace llvm\n";
 }
 
 namespace llvm {
 
-void EmitFixedLenDecoder(RecordKeeper &RK, raw_ostream &OS,
-                         const std::string &PredicateNamespace,
-                         const std::string &GPrefix,
-                         const std::string &GPostfix, const std::string &ROK,
-                         const std::string &RFail, const std::string &L) {
-  FixedLenDecoderEmitter(RK, PredicateNamespace, GPrefix, GPostfix,
-                         ROK, RFail, L).run(OS);
+void EmitDecoder(RecordKeeper &RK, raw_ostream &OS,
+                 const std::string &GPrefix, const std::string &GPostfix,
+                 const std::string &ROK, const std::string &RFail,
+                 const std::string &L) {
+  DecoderEmitter(RK, PredicateNamespace, GPrefix, GPostfix, ROK, RFail, L)
+      .run(OS);
 }
 
 } // end namespace llvm

llvm/utils/TableGen/DisassemblerEmitter.cpp

 /// X86RecognizableInstr.h contains the interface for a single instruction,
 ///   which knows how to translate itself from a CodeGenInstruction and provide
 ///   the information necessary for integration into the tables.
 /// X86RecognizableInstr.cpp contains the implementation for a single
 ///   instruction.
 
 namespace llvm {
 
-extern void EmitFixedLenDecoder(RecordKeeper &RK, raw_ostream &OS,
-                                const std::string &PredicateNamespace,
-                                const std::string &GPrefix,
-                                const std::string &GPostfix,
-                                const std::string &ROK,
-                                const std::string &RFail, const std::string &L);
+extern void EmitDecoder(RecordKeeper &RK, raw_ostream &OS,
+                        const std::string &GPrefix, const std::string &GPostfix,
+                        const std::string &ROK, const std::string &RFail,
+                        const std::string &L);
 
 void EmitDisassembler(RecordKeeper &Records, raw_ostream &OS) {
   CodeGenTarget Target(Records);
   emitSourceFileHeader(" * " + Target.getName().str() + " Disassembler", OS);
 
   // X86 uses a custom disassembler.
   if (Target.getName() == "X86") {
     DisassemblerTables Tables;
 
     ArrayRef<const CodeGenInstruction*> numberedInstructions =
       Target.getInstructionsByEnumValue();
 
     for (unsigned i = 0, e = numberedInstructions.size(); i != e; ++i)
       RecognizableInstr::processInstr(Tables, *numberedInstructions[i], i);
 
     if (Tables.hasConflicts()) {
       PrintError(Target.getTargetRecord()->getLoc(), "Primary decode conflict");
       return;
     }
 
     Tables.emit(OS);
     return;
   }
 
-  // WebAssembly has variable length opcodes, so can't use EmitFixedLenDecoder
-  // below (which depends on a Size table-gen Record), and also uses a custom
-  // disassembler.
+  // TODO: Since now the original decoder emitter is able to emit decoder for
+  //       variable length opcode, we might have to migrate webassembly to use
+  //       that.
   if (Target.getName() == "WebAssembly") {
     emitWebAssemblyDisassemblerTables(OS, Target.getInstructionsByEnumValue());
     return;
   }
 
   // ARM and Thumb have a CHECK() macro to deal with DecodeStatuses.
   if (Target.getName() == "ARM" || Target.getName() == "Thumb" ||
       Target.getName() == "AArch64" || Target.getName() == "ARM64") {
     std::string PredicateNamespace = std::string(Target.getName());
     if (PredicateNamespace == "Thumb")
       PredicateNamespace = "ARM";
 
-    EmitFixedLenDecoder(Records, OS, PredicateNamespace,
-                        "if (!Check(S, ", "))",
-                        "S", "MCDisassembler::Fail",
-                        "  MCDisassembler::DecodeStatus S = "
-                          "MCDisassembler::Success;\n(void)S;");
+    EmitDecoder(Records, OS, PredicateNamespace, "if (!Check(S, ", "))", "S",
+                "MCDisassembler::Fail",
     return;
   }
 
-  EmitFixedLenDecoder(Records, OS, std::string(Target.getName()), "if (",
-                      " == MCDisassembler::Fail)", "MCDisassembler::Success",
-                      "MCDisassembler::Fail", "");
+  EmitDecoder(Records, OS, std::string(Target.getName()), "if (",
 }
 
 } // end namespace llvm

llvm/utils/gn/secondary/llvm/utils/TableGen/BUILD.gn

sources = [
     "CodeGenSchedule.cpp",
     "CodeGenTarget.cpp",
     "CompressInstEmitter.cpp",
     "DAGISelEmitter.cpp",
     "DAGISelMatcher.cpp",
     "DAGISelMatcherEmitter.cpp",
     "DAGISelMatcherGen.cpp",
     "DAGISelMatcherOpt.cpp",
+    "DecoderEmitter.cpp",
     "DFAEmitter.cpp",
     "DFAPacketizerEmitter.cpp",
     "DirectiveEmitter.cpp",
     "DisassemblerEmitter.cpp",
     "ExegesisEmitter.cpp",
     "FastISelEmitter.cpp",
-    "FixedLenDecoderEmitter.cpp",
     "GICombinerEmitter.cpp",
     "GlobalISelEmitter.cpp",
     "InfoByHwMode.cpp",
     "InstrDocsEmitter.cpp",
     "InstrInfoEmitter.cpp",
     "IntrinsicEmitter.cpp",
     "OptEmitter.cpp",
     "OptParserEmitter.cpp",