[AsmParser] Backends can parameterize ASM tokenization.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@252439 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Target/Target.td b/include/llvm/Target/Target.td
index 01c6e343208736b643f458e133a0d8493746d87b..859e21b1957160deeda477979e403f5a10e191d4 100644 (file)
--- a/include/llvm/Target/Target.td
+++ b/include/llvm/Target/Target.td
@@ -965,6 +965,15 @@ class AsmParserVariant {
   // register tokens as constrained registers, instead of tokens, for the
   // purposes of matching.
   string RegisterPrefix = "";
   // register tokens as constrained registers, instead of tokens, for the
   // purposes of matching.
   string RegisterPrefix = "";

+
+  // TokenizingCharacters - Characters that are standalone tokens
+  string TokenizingCharacters = "[]*!";
+
+  // SeparatorCharacters - Characters that are not tokens
+  string SeparatorCharacters = " \t,";
+
+  // BreakCharacters - Characters that start new identifiers
+  string BreakCharacters = "";

 }
 def DefaultAsmParserVariant : AsmParserVariant;
 
 }
 def DefaultAsmParserVariant : AsmParserVariant;
 

diff --git a/lib/MC/MCParser/AsmParser.cpp b/lib/MC/MCParser/AsmParser.cpp
index aa3489a0573f3abac22625584df0817b60490c0f..245ba44a2498e2738dd6e501c162cb1433227306 100644 (file)
--- a/lib/MC/MCParser/AsmParser.cpp
+++ b/lib/MC/MCParser/AsmParser.cpp
@@ -1334,6 +1334,15 @@ bool AsmParser::parseStatement(ParseStatementInfo &Info,
     // Treat '.' as a valid identifier in this context.
     Lex();
     IDVal = ".";
     // Treat '.' as a valid identifier in this context.
     Lex();
     IDVal = ".";

+  } else if (Lexer.is(AsmToken::LCurly)) {
+    // Treat '{' as a valid identifier in this context.
+    Lex();
+    IDVal = "{";
+
+  } else if (Lexer.is(AsmToken::RCurly)) {
+    // Treat '}' as a valid identifier in this context.
+    Lex();
+    IDVal = "}";

   } else if (parseIdentifier(IDVal)) {
     if (!TheCondState.Ignore)
       return TokError("unexpected token at start of statement");
   } else if (parseIdentifier(IDVal)) {
     if (!TheCondState.Ignore)
       return TokError("unexpected token at start of statement");

diff --git a/lib/Target/AArch64/AArch64.td b/lib/Target/AArch64/AArch64.td
index ad6a79ed718eee750c3e0af677b10c7ce645c757..af30ff96f18f7d40b64a8d0f48e08ff8ef20b988 100644 (file)
--- a/lib/Target/AArch64/AArch64.td
+++ b/lib/Target/AArch64/AArch64.td
@@ -125,11 +125,13 @@ def : ProcessorModel<"cyclone", CycloneModel, [ProcCyclone]>;
 def GenericAsmParserVariant : AsmParserVariant {
   int Variant = 0;
   string Name = "generic";
 def GenericAsmParserVariant : AsmParserVariant {
   int Variant = 0;
   string Name = "generic";

+  string BreakCharacters = ".";

 }
 
 def AppleAsmParserVariant : AsmParserVariant {
   int Variant = 1;
   string Name = "apple-neon";
 }
 
 def AppleAsmParserVariant : AsmParserVariant {
   int Variant = 1;
   string Name = "apple-neon";

+  string BreakCharacters = ".";

 }
 
 //===----------------------------------------------------------------------===//
 }
 
 //===----------------------------------------------------------------------===//

diff --git a/lib/Target/ARM/ARM.td b/lib/Target/ARM/ARM.td
index e7423c3dcf8bb82b521afe468e9f4023221da634..855b41c03c95c6bdd68f755b8d4b1602f68d9f62 100644 (file)
--- a/lib/Target/ARM/ARM.td
+++ b/lib/Target/ARM/ARM.td
@@ -511,8 +511,15 @@ def ARMAsmWriter : AsmWriter {
   bit isMCAsmWriter = 1;
 }
 
   bit isMCAsmWriter = 1;
 }
 

+def ARMAsmParserVariant : AsmParserVariant {
+  int Variant = 0;
+  string Name = "ARM";
+  string BreakCharacters = ".";
+}
+

 def ARM : Target {
   // Pull in Instruction Info:
   let InstructionSet = ARMInstrInfo;
   let AssemblyWriters = [ARMAsmWriter];
 def ARM : Target {
   // Pull in Instruction Info:
   let InstructionSet = ARMInstrInfo;
   let AssemblyWriters = [ARMAsmWriter];

+  let AssemblyParserVariants = [ARMAsmParserVariant];

 }
 }

diff --git a/lib/Target/BPF/BPF.td b/lib/Target/BPF/BPF.td
index a4ce90af0439d9f47dfc6835bc7154a36a7fc650..8493b0fd1e4a08ae7de258c852d898feb9f96892 100644 (file)
--- a/lib/Target/BPF/BPF.td
+++ b/lib/Target/BPF/BPF.td
@@ -25,7 +25,14 @@ def BPFInstPrinter : AsmWriter {
   bit isMCAsmWriter = 1;
 }
 
   bit isMCAsmWriter = 1;
 }
 

+def BPFAsmParserVariant : AsmParserVariant {
+  int Variant = 0;
+  string Name = "BPF";
+  string BreakCharacters = ".";
+}
+

 def BPF : Target {
   let InstructionSet = BPFInstrInfo;
   let AssemblyWriters = [BPFInstPrinter];
 def BPF : Target {
   let InstructionSet = BPFInstrInfo;
   let AssemblyWriters = [BPFInstPrinter];

+  let AssemblyParserVariants = [BPFAsmParserVariant];

 }
 }

diff --git a/lib/Target/PowerPC/PPC.td b/lib/Target/PowerPC/PPC.td
index 641b2377de40de4dbe7d1e9fad41e8b61eda4c89..f50100e7a8ad8e8d5e4e4da01f2ecb9feedc6aab 100644 (file)
--- a/lib/Target/PowerPC/PPC.td
+++ b/lib/Target/PowerPC/PPC.td
@@ -403,6 +403,7 @@ def PPCAsmParserVariant : AsmParserVariant {
   // InstAlias definitions use immediate literals.  Set RegisterPrefix
   // so that those are not misinterpreted as registers.
   string RegisterPrefix = "%";
   // InstAlias definitions use immediate literals.  Set RegisterPrefix
   // so that those are not misinterpreted as registers.
   string RegisterPrefix = "%";

+  string BreakCharacters = ".";

 }
 
 def PPC : Target {
 }
 
 def PPC : Target {

diff --git a/utils/TableGen/AsmMatcherEmitter.cpp b/utils/TableGen/AsmMatcherEmitter.cpp
index 3964330a4a84ab793007a8759cf54dd054e0d202..2d6b399d60f53f6f046c2565465664d98ac509a1 100644 (file)
--- a/utils/TableGen/AsmMatcherEmitter.cpp
+++ b/utils/TableGen/AsmMatcherEmitter.cpp
@@ -294,6 +294,13 @@ public:
   }
 };
 
   }
 };
 

+class AsmVariantInfo {
+public:
+  std::string TokenizingCharacters;
+  std::string SeparatorCharacters;
+  std::string BreakCharacters;
+};
+

 /// MatchableInfo - Helper class for storing the necessary information for an
 /// instruction or alias which is capable of being matched.
 struct MatchableInfo {
 /// MatchableInfo - Helper class for storing the necessary information for an
 /// instruction or alias which is capable of being matched.
 struct MatchableInfo {


@@ -484,7 +491,8 @@ struct MatchableInfo {
 
   void initialize(const AsmMatcherInfo &Info,
                   SmallPtrSetImpl<Record*> &SingletonRegisters,
 
   void initialize(const AsmMatcherInfo &Info,
                   SmallPtrSetImpl<Record*> &SingletonRegisters,

-                  int AsmVariantNo, StringRef RegisterPrefix);
+                  int AsmVariantNo, StringRef RegisterPrefix,
+                  AsmVariantInfo const &Variant);

 
   /// validate - Return true if this matchable is a valid thing to match against
   /// and perform a bunch of validity checking.
 
   /// validate - Return true if this matchable is a valid thing to match against
   /// and perform a bunch of validity checking.


@@ -584,8 +592,10 @@ struct MatchableInfo {
   void dump() const;
 
 private:
   void dump() const;
 
 private:

-  void tokenizeAsmString(const AsmMatcherInfo &Info);
-  void addAsmOperand(size_t Start, size_t End);
+  void tokenizeAsmString(AsmMatcherInfo const &Info,
+                         AsmVariantInfo const &Variant);
+  void addAsmOperand(size_t Start, size_t End,
+                     std::string const &SeparatorCharacters);

 };
 
 /// SubtargetFeatureInfo - Helper class for storing information on a subtarget
 };
 
 /// SubtargetFeatureInfo - Helper class for storing information on a subtarget


@@ -828,12 +838,13 @@ extractSingletonRegisterForAsmOperand(MatchableInfo::AsmOperand &Op,
 
 void MatchableInfo::initialize(const AsmMatcherInfo &Info,
                                SmallPtrSetImpl<Record*> &SingletonRegisters,
 
 void MatchableInfo::initialize(const AsmMatcherInfo &Info,
                                SmallPtrSetImpl<Record*> &SingletonRegisters,

-                               int AsmVariantNo, StringRef RegisterPrefix) {
+                               int AsmVariantNo, StringRef RegisterPrefix,
+                               AsmVariantInfo const &Variant) {

   AsmVariantID = AsmVariantNo;
   AsmString =
     CodeGenInstruction::FlattenAsmStringVariants(AsmString, AsmVariantNo);
 
   AsmVariantID = AsmVariantNo;
   AsmString =
     CodeGenInstruction::FlattenAsmStringVariants(AsmString, AsmVariantNo);
 

-  tokenizeAsmString(Info);
+  tokenizeAsmString(Info, Variant);

 
   // Compute the require features.
   for (Record *Predicate : TheDef->getValueAsListOfDefs("Predicates"))
 
   // Compute the require features.
   for (Record *Predicate : TheDef->getValueAsListOfDefs("Predicates"))


@@ -857,9 +868,9 @@ void MatchableInfo::initialize(const AsmMatcherInfo &Info,
 }
 
 /// Append an AsmOperand for the given substring of AsmString.
 }
 
 /// Append an AsmOperand for the given substring of AsmString.

-void MatchableInfo::addAsmOperand(size_t Start, size_t End) {
+void MatchableInfo::addAsmOperand(size_t Start, size_t End,
+                                  std::string const &Separators) {

   StringRef String = AsmString;
   StringRef String = AsmString;

-  StringRef Separators = "[]*! \t,";

   // Look for separators before and after to figure out is this token is
   // isolated.  Accept '$$' as that's how we escape '$'.
   bool IsIsolatedToken =
   // Look for separators before and after to figure out is this token is
   // isolated.  Accept '$$' as that's how we escape '$'.
   bool IsIsolatedToken =


@@ -870,42 +881,54 @@ void MatchableInfo::addAsmOperand(size_t Start, size_t End) {
 }
 
 /// tokenizeAsmString - Tokenize a simplified assembly string.
 }
 
 /// tokenizeAsmString - Tokenize a simplified assembly string.

-void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
+void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info,
+                                      AsmVariantInfo const &Variant) {

   StringRef String = AsmString;
   StringRef String = AsmString;

-  size_t Prev = 0;
-  bool InTok = true;
-  for (size_t i = 0, e = String.size(); i != e; ++i) {
-    switch (String[i]) {
-    case '[':
-    case ']':
-    case '*':
-    case '!':
-    case ' ':
-    case '\t':
-    case ',':
-      if (InTok) {
-        addAsmOperand(Prev, i);
+  unsigned Prev = 0;
+  bool InTok = false;
+  std::string Separators = Variant.TokenizingCharacters +
+                           Variant.SeparatorCharacters;
+  for (unsigned i = 0, e = String.size(); i != e; ++i) {
+    if(Variant.BreakCharacters.find(String[i]) != std::string::npos) {
+      if(InTok) {
+        addAsmOperand(Prev, i, Separators);
+        Prev = i;
+      }
+      InTok = true;
+      continue;
+    }
+    if(Variant.TokenizingCharacters.find(String[i]) != std::string::npos) {
+      if(InTok) {
+        addAsmOperand(Prev, i, Separators);

         InTok = false;
       }
         InTok = false;
       }

-      if (!isspace(String[i]) && String[i] != ',')
-        addAsmOperand(i, i + 1);
+      addAsmOperand(i, i + 1, Separators);

       Prev = i + 1;
       Prev = i + 1;

-      break;
-
+      continue;
+    }
+    if(Variant.SeparatorCharacters.find(String[i]) != std::string::npos) {
+      if(InTok) {
+        addAsmOperand(Prev, i, Separators);
+        InTok = false;
+      }
+      Prev = i + 1;
+      continue;
+    }
+    switch (String[i]) {

     case '\\':
       if (InTok) {
     case '\\':
       if (InTok) {

-        addAsmOperand(Prev, i);
+        addAsmOperand(Prev, i, Separators);

         InTok = false;
       }
       ++i;
       assert(i != String.size() && "Invalid quoted character");
         InTok = false;
       }
       ++i;
       assert(i != String.size() && "Invalid quoted character");

-      addAsmOperand(i, i + 1);
+      addAsmOperand(i, i + 1, Separators);

       Prev = i + 1;
       break;
 
     case '$': {
       Prev = i + 1;
       break;
 
     case '$': {

-      if (InTok) {
-        addAsmOperand(Prev, i);
+      if (InTok && Prev != i) {
+        addAsmOperand(Prev, i, Separators);

         InTok = false;
       }
 
         InTok = false;
       }
 


@@ -915,31 +938,20 @@ void MatchableInfo::tokenizeAsmString(const AsmMatcherInfo &Info) {
         break;
       }
 
         break;
       }
 

-      // If this is "${" find the next "}" and make an identifier like "${xxx}"
-      size_t EndPos = String.find('}', i);
-      assert(EndPos != StringRef::npos &&
-             "Missing brace in operand reference!");
-      addAsmOperand(i, EndPos+1);
+      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();
+      addAsmOperand(i, EndPos+1, Separators);

       Prev = EndPos + 1;
       i = EndPos;
       break;
     }
       Prev = EndPos + 1;
       i = EndPos;
       break;
     }

-
-    case '.':
-      if (!Info.AsmParser->getValueAsBit("MnemonicContainsDot")) {
-        if (InTok)
-          addAsmOperand(Prev, i);
-        Prev = i;
-      }
-      InTok = true;
-      break;
-

     default:
       InTok = true;
     }
   }
   if (InTok && Prev != String.size())
     default:
       InTok = true;
     }
   }
   if (InTok && Prev != String.size())

-    addAsmOperand(Prev, StringRef::npos);
+    addAsmOperand(Prev, StringRef::npos, Separators);

 
   // The first token of the instruction is the mnemonic, which must be a
   // simple string, not a $foo variable or a singleton register.
 
   // The first token of the instruction is the mnemonic, which must be a
   // simple string, not a $foo variable or a singleton register.


@@ -1373,6 +1385,13 @@ void AsmMatcherInfo::buildInfo() {
     std::string CommentDelimiter =
       AsmVariant->getValueAsString("CommentDelimiter");
     std::string RegisterPrefix = AsmVariant->getValueAsString("RegisterPrefix");
     std::string CommentDelimiter =
       AsmVariant->getValueAsString("CommentDelimiter");
     std::string RegisterPrefix = AsmVariant->getValueAsString("RegisterPrefix");

+    AsmVariantInfo Variant;
+    Variant.TokenizingCharacters =
+        AsmVariant->getValueAsString("TokenizingCharacters");
+    Variant.SeparatorCharacters =
+        AsmVariant->getValueAsString("SeparatorCharacters");
+    Variant.BreakCharacters =
+        AsmVariant->getValueAsString("BreakCharacters");

     int AsmVariantNo = AsmVariant->getValueAsInt("Variant");
 
     for (const CodeGenInstruction *CGI : Target.instructions()) {
     int AsmVariantNo = AsmVariant->getValueAsInt("Variant");
 
     for (const CodeGenInstruction *CGI : Target.instructions()) {


@@ -1388,7 +1407,8 @@ void AsmMatcherInfo::buildInfo() {
 
       auto II = llvm::make_unique<MatchableInfo>(*CGI);
 
 
       auto II = llvm::make_unique<MatchableInfo>(*CGI);
 

-      II->initialize(*this, SingletonRegisters, AsmVariantNo, RegisterPrefix);
+      II->initialize(*this, SingletonRegisters, AsmVariantNo, RegisterPrefix,
+                     Variant);

 
       // Ignore instructions which shouldn't be matched and diagnose invalid
       // instruction definitions with an error.
 
       // Ignore instructions which shouldn't be matched and diagnose invalid
       // instruction definitions with an error.


@@ -1415,7 +1435,8 @@ void AsmMatcherInfo::buildInfo() {
 
       auto II = llvm::make_unique<MatchableInfo>(std::move(Alias));
 
 
       auto II = llvm::make_unique<MatchableInfo>(std::move(Alias));
 

-      II->initialize(*this, SingletonRegisters, AsmVariantNo, RegisterPrefix);
+      II->initialize(*this, SingletonRegisters, AsmVariantNo, RegisterPrefix,
+                     Variant);

 
       // Validate the alias definitions.
       II->validate(CommentDelimiter, false);
 
       // Validate the alias definitions.
       II->validate(CommentDelimiter, false);