Initial submission for the attribute group feature.

Attribute groups are of the form:

  #0 = attributes { noinline "no-sse" "cpu"="cortex-a8" alignstack=4 }

Target-dependent attributes are represented as strings. Attributes can have
optional values associated with them. E.g., the "cpu" attribute has the value
"cortex-a8".

Target-independent attributes are listed as enums inside the attribute classes.

Multiple attribute groups can be referenced by the same object. In that case,
the attributes are merged together.

llvm-svn: 174493

docs/LangRef.rst

@@ -737,6 +737,36 @@ The compiler declares the supported values of *name*. Specifying a
 collector which will cause the compiler to alter its output in order to
 support the named garbage collection algorithm.
 
+.. _attrgrp:
+
+Attribute Groups
+----------------
+
+Attribute groups are groups of attributes that are referenced by objects within
+the IR. They are important for keeping ``.ll`` files readable, because a lot of
+functions will use the same set of attributes. In the degenerative case of a
+``.ll`` file that corresponds to a single ``.c`` file, the single attribute
+group will capture the important command line flags used to build that file.
+
+An attribute group is a module-level object. To use an attribute group, an
+object references the attribute group's ID (e.g. ``#37``). An object may refer
+to more than one attribute group. In that situation, the attributes from the
+different groups are merged.
+
+Here is an example of attribute groups for a function that should always be
+inlined, has a stack alignment of 4, and which shouldn't use SSE instructions:
+
+.. code-block:: llvm
+
+   ; Target-independent attributes:
+   #0 = attributes { alwaysinline alignstack=4 }
+
+   ; Target-dependent attributes:
+   #1 = attributes { "no-sse" }
+
+   ; Function @f has attributes: alwaysinline, alignstack=4, and "no-sse".
+   define void @f() #0 #1 { ... }
+
 .. _fnattrs:
 
 Function Attributes

lib/AsmParser/LLLexer.cpp

@@ -226,6 +226,7 @@ lltok::Kind LLLexer::LexToken() {
     SkipLineComment();
     return LexToken();
   case '!': return LexExclaim();
+  case '#': return LexHash();
   case '0': case '1': case '2': case '3': case '4':
   case '5': case '6': case '7': case '8': case '9':
   case '-':
@@ -394,6 +395,24 @@ lltok::Kind LLLexer::LexExclaim() {
   return lltok::exclaim;
 }
 
+/// LexHash - Lex all tokens that start with a # character:
+///    AttrGrpID ::= #[0-9]+
+lltok::Kind LLLexer::LexHash() {
+  // Handle AttrGrpID: #[0-9]+
+  if (isdigit(CurPtr[0])) {
+    for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+      /*empty*/;
+
+    uint64_t Val = atoull(TokStart+1, CurPtr);
+    if ((unsigned)Val != Val)
+      Error("invalid value number (too large)!");
+    UIntVal = unsigned(Val);
+    return lltok::AttrGrpID;
+  }
+
+  return lltok::Error;
+}
+
 /// LexIdentifier: Handle several related productions:
 ///    Label           [-a-zA-Z$._0-9]+:
 ///    IntegerType     i[0-9]+
@@ -531,35 +550,36 @@ lltok::Kind LLLexer::LexIdentifier() {
   KEYWORD(cc);
   KEYWORD(c);
 
-  KEYWORD(signext);
+  KEYWORD(attributes);
-  KEYWORD(zeroext);
+
+  KEYWORD(address_safety);
+  KEYWORD(alwaysinline);
+  KEYWORD(byval);
+  KEYWORD(inlinehint);
   KEYWORD(inreg);
-  KEYWORD(sret);
+  KEYWORD(minsize);
-  KEYWORD(nounwind);
+  KEYWORD(naked);
-  KEYWORD(noreturn);
+  KEYWORD(nest);
   KEYWORD(noalias);
   KEYWORD(nocapture);
-  KEYWORD(byval);
+  KEYWORD(noduplicate);
-  KEYWORD(nest);
+  KEYWORD(noimplicitfloat);
+  KEYWORD(noinline);
+  KEYWORD(nonlazybind);
+  KEYWORD(noredzone);
+  KEYWORD(noreturn);
+  KEYWORD(nounwind);
+  KEYWORD(optsize);
   KEYWORD(readnone);
   KEYWORD(readonly);
-  KEYWORD(uwtable);
   KEYWORD(returns_twice);
-
+  KEYWORD(signext);
-  KEYWORD(inlinehint);
+  KEYWORD(sret);
-  KEYWORD(noinline);
-  KEYWORD(alwaysinline);
-  KEYWORD(optsize);
   KEYWORD(ssp);
   KEYWORD(sspreq);
   KEYWORD(sspstrong);
-  KEYWORD(noredzone);
+  KEYWORD(uwtable);
-  KEYWORD(noimplicitfloat);
+  KEYWORD(zeroext);
-  KEYWORD(naked);
-  KEYWORD(nonlazybind);
-  KEYWORD(address_safety);
-  KEYWORD(minsize);
-  KEYWORD(noduplicate);
 
   KEYWORD(type);
   KEYWORD(opaque);

lib/AsmParser/LLLexer.h

@@ -81,6 +81,7 @@ namespace llvm {
     lltok::Kind LexPercent();
     lltok::Kind LexQuote();
     lltok::Kind Lex0x();
+    lltok::Kind LexHash();
 
     uint64_t atoull(const char *Buffer, const char *End);
     uint64_t HexIntToVal(const char *Buffer, const char *End);

lib/AsmParser/LLParser.cpp

@@ -174,7 +174,8 @@ bool LLParser::ParseTopLevelEntities() {
     case lltok::GlobalID:   if (ParseUnnamedGlobal()) return true; break;
     case lltok::GlobalVar:  if (ParseNamedGlobal()) return true; break;
     case lltok::exclaim:    if (ParseStandaloneMetadata()) return true; break;
-    case lltok::MetadataVar: if (ParseNamedMetadata()) return true; break;
+    case lltok::MetadataVar:if (ParseNamedMetadata()) return true; break;
+    case lltok::AttrGrpID:  if (ParseUnnamedAttrGrp()) return true; break;
 
     // The Global variable production with no name can have many different
     // optional leading prefixes, the production is:
@@ -740,6 +741,102 @@ bool LLParser::ParseGlobal(const std::string &Name, LocTy NameLoc,
   return false;
 }
 
+/// ParseUnnamedAttrGrp
+///   ::= AttrGrpID '=' '{' AttrValPair+ '}'
+bool LLParser::ParseUnnamedAttrGrp() {
+  assert(Lex.getKind() == lltok::AttrGrpID);
+  LocTy AttrGrpLoc = Lex.getLoc();
+  unsigned VarID = Lex.getUIntVal();
+  Lex.Lex();
+
+  if (ParseToken(lltok::equal, "expected '=' here") ||
+      ParseToken(lltok::kw_attributes, "expected 'attributes' keyword here") ||
+      ParseToken(lltok::lbrace, "expected '{' here") ||
+      ParseAttributeValuePairs(ForwardRefAttrBuilder[VarID]) ||
+      ParseToken(lltok::rbrace, "expected end of attribute group"))
+    return true;
+
+  if (!ForwardRefAttrBuilder[VarID].hasAttributes())
+    return Error(AttrGrpLoc, "attribute group has no attributes");
+
+  return false;
+}
+
+/// ParseAttributeValuePairs
+///   ::= <attr> | <attr> '=' <value>
+bool LLParser::ParseAttributeValuePairs(AttrBuilder &B) {
+  while (true) {
+    lltok::Kind Token = Lex.getKind();
+    switch (Token) {
+    default:
+      return Error(Lex.getLoc(), "unterminated attribute group");
+    case lltok::rbrace:
+      // Finished.
+      return false;
+
+    // Target-dependent attributes:
+    case lltok::StringConstant: {
+      std::string Attr = Lex.getStrVal();
+      Lex.Lex();
+      std::string Val;
+      if (EatIfPresent(lltok::equal) &&
+          ParseStringConstant(Val))
+        return true;
+
+      B.addAttribute(Attr, Val);
+      break;
+    }
+
+    // Target-independent attributes:
+    case lltok::kw_align: {
+      unsigned Alignment;
+      if (ParseToken(lltok::equal, "expected '=' here") ||
+          ParseUInt32(Alignment))
+        return true;
+      B.addAlignmentAttr(Alignment);
+      break;
+    }
+    case lltok::kw_alignstack: {
+      unsigned Alignment;
+      if (ParseToken(lltok::equal, "expected '=' here") ||
+          ParseUInt32(Alignment))
+        return true;
+      B.addStackAlignmentAttr(Alignment);
+      break;
+    }
+    case lltok::kw_address_safety:  B.addAttribute(Attribute::AddressSafety); break;
+    case lltok::kw_alwaysinline:    B.addAttribute(Attribute::AlwaysInline); break;
+    case lltok::kw_byval:           B.addAttribute(Attribute::ByVal); break;
+    case lltok::kw_inlinehint:      B.addAttribute(Attribute::InlineHint); break;
+    case lltok::kw_inreg:           B.addAttribute(Attribute::InReg); break;
+    case lltok::kw_minsize:         B.addAttribute(Attribute::MinSize); break;
+    case lltok::kw_naked:           B.addAttribute(Attribute::Naked); break;
+    case lltok::kw_nest:            B.addAttribute(Attribute::Nest); break;
+    case lltok::kw_noalias:         B.addAttribute(Attribute::NoAlias); break;
+    case lltok::kw_nocapture:       B.addAttribute(Attribute::NoCapture); break;
+    case lltok::kw_noduplicate:     B.addAttribute(Attribute::NoDuplicate); break;
+    case lltok::kw_noimplicitfloat: B.addAttribute(Attribute::NoImplicitFloat); break;
+    case lltok::kw_noinline:        B.addAttribute(Attribute::NoInline); break;
+    case lltok::kw_nonlazybind:     B.addAttribute(Attribute::NonLazyBind); break;
+    case lltok::kw_noredzone:       B.addAttribute(Attribute::NoRedZone); break;
+    case lltok::kw_noreturn:        B.addAttribute(Attribute::NoReturn); break;
+    case lltok::kw_nounwind:        B.addAttribute(Attribute::NoUnwind); break;
+    case lltok::kw_optsize:         B.addAttribute(Attribute::OptimizeForSize); break;
+    case lltok::kw_readnone:        B.addAttribute(Attribute::ReadNone); break;
+    case lltok::kw_readonly:        B.addAttribute(Attribute::ReadOnly); break;
+    case lltok::kw_returns_twice:   B.addAttribute(Attribute::ReturnsTwice); break;
+    case lltok::kw_signext:         B.addAttribute(Attribute::SExt); break;
+    case lltok::kw_sret:            B.addAttribute(Attribute::StructRet); break;
+    case lltok::kw_ssp:             B.addAttribute(Attribute::StackProtect); break;
+    case lltok::kw_sspreq:          B.addAttribute(Attribute::StackProtectReq); break;
+    case lltok::kw_sspstrong:       B.addAttribute(Attribute::StackProtectStrong); break;
+    case lltok::kw_uwtable:         B.addAttribute(Attribute::UWTable); break;
+    case lltok::kw_zeroext:         B.addAttribute(Attribute::ZExt); break;
+    }
+
+    Lex.Lex();
+  }
+}
 
 //===----------------------------------------------------------------------===//
 // GlobalValue Reference/Resolution Routines.

lib/AsmParser/LLParser.h

@@ -125,6 +125,9 @@ namespace llvm {
     std::map<ValID, std::vector<std::pair<ValID, GlobalValue*> > >
       ForwardRefBlockAddresses;
 
+    // Attribute builder reference information.
+    std::map<unsigned, AttrBuilder> ForwardRefAttrBuilder;
+
   public:
     LLParser(MemoryBuffer *F, SourceMgr &SM, SMDiagnostic &Err, Module *m) :
       Context(m->getContext()), Lex(F, SM, Err, m->getContext()),
@@ -236,6 +239,8 @@ namespace llvm {
     bool ParseMDString(MDString *&Result);
     bool ParseMDNodeID(MDNode *&Result);
     bool ParseMDNodeID(MDNode *&Result, unsigned &SlotNo);
+    bool ParseUnnamedAttrGrp();
+    bool ParseAttributeValuePairs(AttrBuilder &B);
 
     // Type Parsing.
     bool ParseType(Type *&Result, bool AllowVoid = false);

lib/AsmParser/LLToken.h

@@ -30,6 +30,7 @@ namespace lltok {
     lparen, rparen,    // (  )
     backslash,         // \    (not /)
     exclaim,           // !
+    hash,              // #
 
     kw_x,
     kw_true,    kw_false,
@@ -90,35 +91,36 @@ namespace lltok {
     kw_ptx_kernel, kw_ptx_device,
     kw_spir_kernel, kw_spir_func,
 
-    kw_signext,
+    // Attributes:
-    kw_zeroext,
+    kw_attributes,
+    kw_alwaysinline,
+    kw_address_safety,
+    kw_byval,
+    kw_inlinehint,
     kw_inreg,
-    kw_sret,
+    kw_minsize,
-    kw_nounwind,
+    kw_naked,
-    kw_noreturn,
+    kw_nest,
     kw_noalias,
     kw_nocapture,
-    kw_byval,
+    kw_noduplicate,
-    kw_nest,
+    kw_noimplicitfloat,
+    kw_noinline,
+    kw_nonlazybind,
+    kw_noredzone,
+    kw_noreturn,
+    kw_nounwind,
+    kw_optsize,
     kw_readnone,
     kw_readonly,
-    kw_uwtable,
     kw_returns_twice,
-
+    kw_signext,
-    kw_inlinehint,
-    kw_noinline,
-    kw_alwaysinline,
-    kw_optsize,
     kw_ssp,
     kw_sspreq,
     kw_sspstrong,
-    kw_noredzone,
+    kw_sret,
-    kw_noimplicitfloat,
+    kw_uwtable,
-    kw_naked,
+    kw_zeroext,
-    kw_nonlazybind,
-    kw_address_safety,
-    kw_minsize,
-    kw_noduplicate,
 
     kw_type,
     kw_opaque,
@@ -155,6 +157,7 @@ namespace lltok {
     // Unsigned Valued tokens (UIntVal).
     GlobalID,          // @42
     LocalVarID,        // %42
+    AttrGrpID,         // #42
 
     // String valued tokens (StrVal).
     LabelStr,          // foo: