1 files changed, 42 insertions, 19 deletions

diff --git a/utils/TableGen/AsmMatcherEmitter.cpp b/utils/TableGen/AsmMatcherEmitter.cpp
index d8f2619..0d7c5ff 100644
--- a/utils/TableGen/AsmMatcherEmitter.cpp
+++ b/utils/TableGen/AsmMatcherEmitter.cpp
@@ -310,11 +310,16 @@ struct MatchableInfo {
     /// The suboperand index within SrcOpName, or -1 for the entire operand.
     int SubOpIdx;
 
+    /// Whether the token is "isolated", i.e., it is preceded and followed
+    /// by separators.
+    bool IsIsolatedToken;
+
     /// Register record if this token is singleton register.
     Record *SingletonReg;
 
-    explicit AsmOperand(StringRef T) : Token(T), Class(nullptr), SubOpIdx(-1),
-                                       SingletonReg(nullptr) {}
+    explicit AsmOperand(bool IsIsolatedToken, StringRef T)
+        : Token(T), Class(nullptr), SubOpIdx(-1),
+          IsIsolatedToken(IsIsolatedToken), SingletonReg(nullptr) {}
   };
 
   /// ResOperand - This represents a single operand in the result instruction
@@ -572,6 +577,7 @@ struct MatchableInfo {
 
 private:
   void tokenizeAsmString(const AsmMatcherInfo &Info);
+  void addAsmOperand(size_t Start, size_t End);
 };
 
 /// SubtargetFeatureInfo - Helper class for storing information on a subtarget
@@ -811,6 +817,19 @@ void MatchableInfo::initialize(const AsmMatcherInfo &Info,
       DepMask ? !DepMask->getValue()->getAsUnquotedString().empty() : false;
 }
 
+/// Append an AsmOperand for the given substring of AsmString.
+void MatchableInfo::addAsmOperand(size_t Start, size_t End) {
+  StringRef String = AsmString;
+  StringRef Separators = "[]*! \t,";
+  // Look for separators before and after to figure out is this token is
+  // isolated.  Accept '$$' as that's how we escape '$'.
+  bool IsIsolatedToken =
+      (!Start || Separators.find(String[Start - 1]) != StringRef::npos ||
+       String.substr(Start - 1, 2) == "$$") &&
+      (End >= String.size() || Separators.find(String[End]) != StringRef::npos);
+  AsmOperands.push_back(AsmOperand(IsIsolatedToken, String.slice(Start, End)));
+}
+
 /// tokenizeAsmString - Tokenize a simplified assembly string.
 void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
   StringRef String = AsmString;
@@ -826,28 +845,28 @@ void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
     case '\t':
     case ',':
       if (InTok) {
-        AsmOperands.push_back(AsmOperand(String.slice(Prev, i)));
+        addAsmOperand(Prev, i);
         InTok = false;
       }
       if (!isspace(String[i]) && String[i] != ',')
-        AsmOperands.push_back(AsmOperand(String.substr(i, 1)));
+        addAsmOperand(i, i + 1);
       Prev = i + 1;
       break;
 
     case '\\':
       if (InTok) {
-        AsmOperands.push_back(AsmOperand(String.slice(Prev, i)));
+        addAsmOperand(Prev, i);
         InTok = false;
       }
       ++i;
       assert(i != String.size() && "Invalid quoted character");
-      AsmOperands.push_back(AsmOperand(String.substr(i, 1)));
+      addAsmOperand(i, i + 1);
       Prev = i + 1;
       break;
 
     case '$': {
       if (InTok) {
-        AsmOperands.push_back(AsmOperand(String.slice(Prev, i)));
+        addAsmOperand(Prev, i);
         InTok = false;
       }
 
@@ -860,7 +879,7 @@ void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
       StringRef::iterator End = std::find(String.begin() + i, String.end(),'}');
       assert(End != String.end() && "Missing brace in operand reference!");
       size_t EndPos = End - String.begin();
-      AsmOperands.push_back(AsmOperand(String.slice(i, EndPos+1)));
+      addAsmOperand(i, EndPos+1);
       Prev = EndPos + 1;
       i = EndPos;
       break;
@@ -869,7 +888,7 @@ void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
     case '.':
       if (!Info.AsmParser->getValueAsBit("MnemonicContainsDot")) {
         if (InTok)
-          AsmOperands.push_back(AsmOperand(String.slice(Prev, i)));
+          addAsmOperand(Prev, i);
         Prev = i;
       }
       InTok = true;
@@ -880,7 +899,7 @@ void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
     }
   }
   if (InTok && Prev != String.size())
-    AsmOperands.push_back(AsmOperand(String.substr(Prev)));
+    addAsmOperand(Prev, StringRef::npos);
 
   // The first token of the instruction is the mnemonic, which must be a
   // simple string, not a $foo variable or a singleton register.
@@ -962,6 +981,12 @@ extractSingletonRegisterForAsmOperand(unsigned OperandNo,
                                       const AsmMatcherInfo &Info,
                                       std::string &RegisterPrefix) {
   StringRef Tok = AsmOperands[OperandNo].Token;
+
+  // If this token is not an isolated token, i.e., it isn't separated from
+  // other tokens (e.g. with whitespace), don't interpret it as a register name.
+  if (!AsmOperands[OperandNo].IsIsolatedToken)
+    return;
+
   if (RegisterPrefix.empty()) {
     std::string LoweredTok = Tok.lower();
     if (const CodeGenRegister *Reg = Info.Target.getRegisterByName(LoweredTok))
@@ -1224,8 +1249,8 @@ void AsmMatcherInfo::buildOperandClasses() {
     CI->Kind = ClassInfo::UserClass0 + Index;
 
     ListInit *Supers = Rec->getValueAsListInit("SuperClasses");
-    for (unsigned i = 0, e = Supers->getSize(); i != e; ++i) {
-      DefInit *DI = dyn_cast<DefInit>(Supers->getElement(i));
+    for (Init *I : Supers->getValues()) {
+      DefInit *DI = dyn_cast<DefInit>(I);
       if (!DI) {
         PrintError(Rec->getLoc(), "Invalid super class reference!");
         continue;
@@ -1510,7 +1535,7 @@ buildInstructionOperandReference(MatchableInfo *II,
       // Insert remaining suboperands after AsmOpIdx in II->AsmOperands.
       StringRef Token = Op->Token; // save this in case Op gets moved
       for (unsigned SI = 1, SE = Operands[Idx].MINumOperands; SI != SE; ++SI) {
-        MatchableInfo::AsmOperand NewAsmOp(Token);
+        MatchableInfo::AsmOperand NewAsmOp(/*IsIsolatedToken=*/true, Token);
         NewAsmOp.SubOpIdx = SI;
         II->AsmOperands.insert(II->AsmOperands.begin()+AsmOpIdx+SI, NewAsmOp);
       }
@@ -1772,7 +1797,7 @@ static void emitConvertFuncs(CodeGenTarget &Target, StringRef ClassName,
                                     getEnumNameForToken(AsmMatchConverter));
 
       // Add the converter row for this instruction.
-      ConversionTable.push_back(std::vector<uint8_t>());
+      ConversionTable.emplace_back();
       ConversionTable.back().push_back(KindID);
       ConversionTable.back().push_back(CVT_Done);
 
@@ -2136,8 +2161,7 @@ static void emitMatchTokenString(CodeGenTarget &Target,
   std::vector<StringMatcher::StringPair> Matches;
   for (const auto &CI : Infos) {
     if (CI.Kind == ClassInfo::Token)
-      Matches.push_back(
-          StringMatcher::StringPair(CI.ValueName, "return " + CI.Name + ";"));
+      Matches.emplace_back(CI.ValueName, "return " + CI.Name + ";");
   }
 
   OS << "static MatchClassKind matchTokenString(StringRef Name) {\n";
@@ -2159,9 +2183,8 @@ static void emitMatchRegisterName(CodeGenTarget &Target, Record *AsmParser,
     if (Reg.TheDef->getValueAsString("AsmName").empty())
       continue;
 
-    Matches.push_back(
-        StringMatcher::StringPair(Reg.TheDef->getValueAsString("AsmName"),
-                                  "return " + utostr(Reg.EnumValue) + ";"));
+    Matches.emplace_back(Reg.TheDef->getValueAsString("AsmName"),
+                         "return " + utostr(Reg.EnumValue) + ";");
   }
 
   OS << "static unsigned MatchRegisterName(StringRef Name) {\n";