[TableGen] Introduce a `defvar` statement.

Summary:
This allows you to define a global or local variable to an arbitrary
value, and refer to it in subsequent definitions.

The main use I anticipate for this is if you have to compute some
difficult function of the parameters of a multiclass, and then use it
many times. For example:

  multiclass Foo<int i, string s> {
    defvar op = !cast<BaseClass>("whatnot_" # s # "_" # i);
    def myRecord {
      dag a = (op this, (op that, the other), (op x, y, z));
      int b = op.subfield;
    }
    def myOtherRecord<"template params including", op>;
  }

There are a couple of ways to do this already, but they're not really
satisfactory. You can replace `defvar x = y` with a loop over a
singleton list, `foreach x = [y] in { ... }` - but that's unintuitive
to someone who hasn't seen that workaround idiom before, and requires
an extra pair of braces that you often didn't really want. Or you can
define a nested pair of multiclasses, with the inner one taking `x` as
a template parameter, and the outer one instantiating it just once
with the desired value of `x` computed from its other parameters - but
that makes it awkward to sequentially compute each value based on the
previous ones. I think `defvar` makes things considerably easier.

You can also use `defvar` at the top level, where it inserts globals
into the same map used by `defset`. That allows you to define global
constants without having to make a dummy record for them to live in:

  defvar MAX_BUFSIZE = 512;

  // previously:
  // def Dummy { int MAX_BUFSIZE = 512; }
  // and then refer to Dummy.MAX_BUFSIZE everywhere

Reviewers: nhaehnle, hfinkel

Reviewed By: hfinkel

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71407

4 files changed, 135 insertions, 5 deletions

diff --git a/llvm/lib/TableGen/TGLexer.cpp b/llvm/lib/TableGen/TGLexer.cpp
index d22c96e8129..c160704b6e7 100644
--- a/llvm/lib/TableGen/TGLexer.cpp
+++ b/llvm/lib/TableGen/TGLexer.cpp
@@ -350,6 +350,7 @@ tgtok::TokKind TGLexer::LexIdentifier() {
     .Case("field", tgtok::Field)
     .Case("let", tgtok::Let)
     .Case("in", tgtok::In)
+    .Case("defvar", tgtok::Defvar)
     .Default(tgtok::Id);
 
   if (Kind == tgtok::Id)
diff --git a/llvm/lib/TableGen/TGLexer.h b/llvm/lib/TableGen/TGLexer.h
index b5cf4bd7374..04c72900b0b 100644
--- a/llvm/lib/TableGen/TGLexer.h
+++ b/llvm/lib/TableGen/TGLexer.h
@@ -46,7 +46,7 @@ namespace tgtok {
 
     // Keywords.
     Bit, Bits, Class, Code, Dag, Def, Foreach, Defm, Field, In, Int, Let, List,
-    MultiClass, String, Defset,
+    MultiClass, String, Defset, Defvar,
 
     // !keywords.
     XConcat, XADD, XMUL, XAND, XOR, XSRA, XSRL, XSHL, XListConcat, XListSplat,
diff --git a/llvm/lib/TableGen/TGParser.cpp b/llvm/lib/TableGen/TGParser.cpp
index 71786328c46..34d993c518a 100644
--- a/llvm/lib/TableGen/TGParser.cpp
+++ b/llvm/lib/TableGen/TGParser.cpp
@@ -482,7 +482,7 @@ bool TGParser::addDefOne(std::unique_ptr<Record> Rec) {
 static bool isObjectStart(tgtok::TokKind K) {
   return K == tgtok::Class || K == tgtok::Def || K == tgtok::Defm ||
          K == tgtok::Let || K == tgtok::MultiClass || K == tgtok::Foreach ||
-         K == tgtok::Defset;
+         K == tgtok::Defset || K == tgtok::Defvar;
 }
 
 /// ParseObjectName - If a valid object name is specified, return it. If no
@@ -869,6 +869,10 @@ Init *TGParser::ParseIDValue(Record *CurRec, StringInit *Name, SMLoc NameLoc,
     }
   }
 
+  if (CurLocalScope)
+    if (Init *I = CurLocalScope->getVar(Name->getValue()))
+      return I;
+
   // If this is in a foreach loop, make sure it's not a loop iterator
   for (const auto &L : Loops) {
     VarInit *IterVar = dyn_cast<VarInit>(L->IterVar);
@@ -2595,7 +2599,11 @@ bool TGParser::ParseTemplateArgList(Record *CurRec) {
 ///
 ///   BodyItem ::= Declaration ';'
 ///   BodyItem ::= LET ID OptionalBitList '=' Value ';'
+///   BodyItem ::= Defvar
 bool TGParser::ParseBodyItem(Record *CurRec) {
+  if (Lex.getCode() == tgtok::Defvar)
+    return ParseDefvar();
+
   if (Lex.getCode() != tgtok::Let) {
     if (!ParseDeclaration(CurRec, false))
       return true;
@@ -2658,10 +2666,15 @@ bool TGParser::ParseBody(Record *CurRec) {
   // Eat the '{'.
   Lex.Lex();
 
+  // An object body introduces a new scope for local variables.
+  TGLocalVarScope *BodyScope = PushLocalScope();
+
   while (Lex.getCode() != tgtok::r_brace)
     if (ParseBodyItem(CurRec))
       return true;
 
+  PopLocalScope(BodyScope);
+
   // Eat the '}'.
   Lex.Lex();
   return false;
@@ -2800,6 +2813,45 @@ bool TGParser::ParseDefset() {
   return false;
 }
 
+/// ParseDefvar - Parse a defvar statement.
+///
+///   Defvar ::= DEFVAR Id '=' Value ';'
+///
+bool TGParser::ParseDefvar() {
+  assert(Lex.getCode() == tgtok::Defvar);
+  Lex.Lex(); // Eat the 'defvar' token
+
+  if (Lex.getCode() != tgtok::Id)
+    return TokError("expected identifier");
+  StringInit *DeclName = StringInit::get(Lex.getCurStrVal());
+  if (CurLocalScope) {
+    if (CurLocalScope->varAlreadyDefined(DeclName->getValue()))
+      return TokError("local variable of this name already exists");
+  } else {
+    if (Records.getGlobal(DeclName->getValue()))
+      return TokError("def or global variable of this name already exists");
+  }
+
+  if (Lex.Lex() != tgtok::equal) // Eat the identifier
+    return TokError("expected '='");
+  Lex.Lex(); // Eat the '='
+
+  Init *Value = ParseValue(nullptr);
+  if (!Value)
+    return true;
+
+  if (Lex.getCode() != tgtok::semi)
+    return TokError("expected ';'");
+  Lex.Lex(); // Eat the ';'
+
+  if (CurLocalScope)
+    CurLocalScope->addVar(DeclName->getValue(), Value);
+  else
+    Records.addExtraGlobal(DeclName->getValue(), Value);
+
+  return false;
+}
+
 /// ParseForeach - Parse a for statement.  Return the record corresponding
 /// to it.  This returns true on error.
 ///
@@ -2825,6 +2877,9 @@ bool TGParser::ParseForeach(MultiClass *CurMultiClass) {
   // Create a loop object and remember it.
   Loops.push_back(std::make_unique<ForeachLoop>(Loc, IterName, ListValue));
 
+  // A foreach loop introduces a new scope for local variables.
+  TGLocalVarScope *ForeachScope = PushLocalScope();
+
   if (Lex.getCode() != tgtok::l_brace) {
     // FOREACH Declaration IN Object
     if (ParseObject(CurMultiClass))
@@ -2845,6 +2900,8 @@ bool TGParser::ParseForeach(MultiClass *CurMultiClass) {
     Lex.Lex();  // Eat the }
   }
 
+  PopLocalScope(ForeachScope);
+
   // Resolve the loop or store it for later resolution.
   std::unique_ptr<ForeachLoop> Loop = std::move(Loops.back());
   Loops.pop_back();
@@ -2957,6 +3014,8 @@ bool TGParser::ParseTopLevelLet(MultiClass *CurMultiClass) {
     return TokError("expected 'in' at end of top-level 'let'");
   Lex.Lex();
 
+  TGLocalVarScope *LetScope = PushLocalScope();
+
   // If this is a scalar let, just handle it now
   if (Lex.getCode() != tgtok::l_brace) {
     // LET LetList IN Object
@@ -2978,6 +3037,8 @@ bool TGParser::ParseTopLevelLet(MultiClass *CurMultiClass) {
     Lex.Lex();
   }
 
+  PopLocalScope(LetScope);
+
   // Outside this let scope, this let block is not active.
   LetStack.pop_back();
   return false;
@@ -3051,14 +3112,18 @@ bool TGParser::ParseMultiClass() {
     if (Lex.Lex() == tgtok::r_brace)  // eat the '{'.
       return TokError("multiclass must contain at least one def");
 
+    // A multiclass body introduces a new scope for local variables.
+    TGLocalVarScope *MulticlassScope = PushLocalScope();
+
     while (Lex.getCode() != tgtok::r_brace) {
       switch (Lex.getCode()) {
       default:
-        return TokError("expected 'let', 'def', 'defm' or 'foreach' in "
-                        "multiclass body");
+        return TokError("expected 'let', 'def', 'defm', 'defvar' or 'foreach' "
+                        "in multiclass body");
       case tgtok::Let:
       case tgtok::Def:
       case tgtok::Defm:
+      case tgtok::Defvar:
       case tgtok::Foreach:
         if (ParseObject(CurMultiClass))
           return true;
@@ -3066,6 +3131,8 @@ bool TGParser::ParseMultiClass() {
       }
     }
     Lex.Lex();  // eat the '}'.
+
+    PopLocalScope(MulticlassScope);
   }
 
   CurMultiClass = nullptr;
@@ -3207,6 +3274,8 @@ bool TGParser::ParseDefm(MultiClass *CurMultiClass) {
 ///   Object ::= DefMInst
 ///   Object ::= LETCommand '{' ObjectList '}'
 ///   Object ::= LETCommand Object
+///   Object ::= Defset
+///   Object ::= Defvar
 bool TGParser::ParseObject(MultiClass *MC) {
   switch (Lex.getCode()) {
   default:
@@ -3220,6 +3289,8 @@ bool TGParser::ParseObject(MultiClass *MC) {
     if (MC)
       return TokError("defset is not allowed inside multiclass");
     return ParseDefset();
+  case tgtok::Defvar:
+    return ParseDefvar();
   case tgtok::Class:
     if (MC)
       return TokError("class is not allowed inside multiclass");
diff --git a/llvm/lib/TableGen/TGParser.h b/llvm/lib/TableGen/TGParser.h
index cbe0b545d0f..edcac1e8fa7 100644
--- a/llvm/lib/TableGen/TGParser.h
+++ b/llvm/lib/TableGen/TGParser.h
@@ -74,6 +74,46 @@ namespace llvm {
     SmallVector<Init *, 16> Elements;
   };
 
+class TGLocalVarScope {
+  // A scope to hold local variable definitions from defvar.
+  std::map<std::string, Init *, std::less<>> vars;
+  std::unique_ptr<TGLocalVarScope> parent;
+
+public:
+  TGLocalVarScope() = default;
+  TGLocalVarScope(std::unique_ptr<TGLocalVarScope> parent)
+      : parent(std::move(parent)) {}
+
+  std::unique_ptr<TGLocalVarScope> extractParent() {
+    // This is expected to be called just before we are destructed, so
+    // it doesn't much matter what state we leave 'parent' in.
+    return std::move(parent);
+  }
+
+  Init *getVar(StringRef Name) const {
+    auto It = vars.find(Name);
+    if (It != vars.end())
+      return It->second;
+    if (parent)
+      return parent->getVar(Name);
+    return nullptr;
+  }
+
+  bool varAlreadyDefined(StringRef Name) const {
+    // When we check whether a variable is already defined, for the purpose of
+    // reporting an error on redefinition, we don't look up to the parent
+    // scope, because it's all right to shadow an outer definition with an
+    // inner one.
+    return vars.find(Name) != vars.end();
+  }
+
+  void addVar(StringRef Name, Init *I) {
+    bool Ins = vars.insert(std::make_pair(Name, I)).second;
+    (void)Ins;
+    assert(Ins && "Local variable already exists");
+  }
+};
+
 struct MultiClass {
   Record Rec;  // Placeholder for template args and Name.
   std::vector<RecordsEntry> Entries;
@@ -99,6 +139,10 @@ class TGParser {
   /// current value.
   MultiClass *CurMultiClass;
 
+  /// CurLocalScope - Innermost of the current nested scopes for 'defvar' local
+  /// variables.
+  std::unique_ptr<TGLocalVarScope> CurLocalScope;
+
   // Record tracker
   RecordKeeper &Records;
 
@@ -133,7 +177,20 @@ public:
     return Lex.getDependencies();
   }
 
-private:  // Semantic analysis methods.
+  TGLocalVarScope *PushLocalScope() {
+    CurLocalScope = std::make_unique<TGLocalVarScope>(std::move(CurLocalScope));
+    // Returns a pointer to the new scope, so that the caller can pass it back
+    // to PopLocalScope which will check by assertion that the pushes and pops
+    // match up properly.
+    return CurLocalScope.get();
+  }
+  void PopLocalScope(TGLocalVarScope *ExpectedStackTop) {
+    assert(ExpectedStackTop == CurLocalScope.get() &&
+           "Mismatched pushes and pops of local variable scopes");
+    CurLocalScope = CurLocalScope->extractParent();
+  }
+
+private: // Semantic analysis methods.
   bool AddValue(Record *TheRec, SMLoc Loc, const RecordVal &RV);
   bool SetValue(Record *TheRec, SMLoc Loc, Init *ValName,
                 ArrayRef<unsigned> BitList, Init *V,
@@ -161,6 +218,7 @@ private:  // Parser methods.
   bool ParseDefm(MultiClass *CurMultiClass);
   bool ParseDef(MultiClass *CurMultiClass);
   bool ParseDefset();
+  bool ParseDefvar();
   bool ParseForeach(MultiClass *CurMultiClass);
   bool ParseTopLevelLet(MultiClass *CurMultiClass);
   void ParseLetList(SmallVectorImpl<LetRecord> &Result);