MIRParser: Use dot instead of colon to mark subregisters

Change the syntax to use `%0.sub8` to denote a subregister.

This seems like a more natural fit to denote subregisters; I also plan
to introduce a new ":classname" syntax in upcoming patches to denote the
register class of a vreg.

Note that this commit disallows plain identifiers to start with a '.'
character.  This shouldn't affect anything as external names/IR
references are all prefixed with '$'/'%', plain identifiers are only
used for instruction names, register mask names and subreg indexes.

Differential Revision: https://reviews.llvm.org/D22390

llvm-svn: 276815

3 files changed, 13 insertions, 5 deletions

diff --git a/llvm/lib/CodeGen/MIRParser/MILexer.cpp b/llvm/lib/CodeGen/MIRParser/MILexer.cpp
index 6770df9ac18..de9b773b6b5 100644
--- a/llvm/lib/CodeGen/MIRParser/MILexer.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MILexer.cpp
@@ -237,7 +237,7 @@ static MIToken::TokenKind getIdentifierKind(StringRef Identifier) {
 }
 
 static Cursor maybeLexIdentifier(Cursor C, MIToken &Token) {
-  if (!isalpha(C.peek()) && C.peek() != '_' && C.peek() != '.')
+  if (!isalpha(C.peek()) && C.peek() != '_')
     return None;
   auto Range = C;
   while (isIdentifierChar(C.peek()))
@@ -372,6 +372,11 @@ static Cursor lexVirtualRegister(Cursor C, MIToken &Token) {
   return C;
 }
 
+/// Returns true for a character allowed in a register name.
+static bool isRegisterChar(char C) {
+  return isIdentifierChar(C) && C != '.';
+}
+
 static Cursor maybeLexRegister(Cursor C, MIToken &Token) {
   if (C.peek() != '%')
     return None;
@@ -379,7 +384,7 @@ static Cursor maybeLexRegister(Cursor C, MIToken &Token) {
     return lexVirtualRegister(C, Token);
   auto Range = C;
   C.advance(); // Skip '%'
-  while (isIdentifierChar(C.peek()))
+  while (isRegisterChar(C.peek()))
     C.advance();
   Token.reset(MIToken::NamedRegister, Range.upto(C))
       .setStringValue(Range.upto(C).drop_front(1)); // Drop the '%'
@@ -491,6 +496,8 @@ static MIToken::TokenKind symbolToken(char C) {
   switch (C) {
   case ',':
     return MIToken::comma;
+  case '.':
+    return MIToken::dot;
   case '=':
     return MIToken::equal;
   case ':':
diff --git a/llvm/lib/CodeGen/MIRParser/MILexer.h b/llvm/lib/CodeGen/MIRParser/MILexer.h
index ea155c3ae2f..6f90612a640 100644
--- a/llvm/lib/CodeGen/MIRParser/MILexer.h
+++ b/llvm/lib/CodeGen/MIRParser/MILexer.h
@@ -38,6 +38,7 @@ struct MIToken {
     underscore,
     colon,
     coloncolon,
+    dot,
     exclaim,
     lparen,
     rparen,
diff --git a/llvm/lib/CodeGen/MIRParser/MIParser.cpp b/llvm/lib/CodeGen/MIRParser/MIParser.cpp
index 170f9735d1f..1ec3680d9d2 100644
--- a/llvm/lib/CodeGen/MIRParser/MIParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIParser.cpp
@@ -882,10 +882,10 @@ bool MIParser::parseRegisterFlag(unsigned &Flags) {
 }
 
 bool MIParser::parseSubRegisterIndex(unsigned &SubReg) {
-  assert(Token.is(MIToken::colon));
+  assert(Token.is(MIToken::dot));
   lex();
   if (Token.isNot(MIToken::Identifier))
-    return error("expected a subregister index after ':'");
+    return error("expected a subregister index after '.'");
   auto Name = Token.stringValue();
   SubReg = getSubRegIndex(Name);
   if (!SubReg)
@@ -970,7 +970,7 @@ bool MIParser::parseRegisterOperand(MachineOperand &Dest,
     return true;
   lex();
   unsigned SubReg = 0;
-  if (Token.is(MIToken::colon)) {
+  if (Token.is(MIToken::dot)) {
     if (parseSubRegisterIndex(SubReg))
       return true;
     if (!TargetRegisterInfo::isVirtualRegister(Reg))