[clang] Implement __builtin_{clzg,ctzg} (llvm#83431)

Fixes llvm#83075, fixes llvm#83076.

Author: overmighty

clang/docs/LanguageExtensions.rst

@@ -3553,6 +3553,47 @@ argument can be of any unsigned integer type.
 ``__builtin_popcount{,l,ll}`` builtins, with support for other integer types,
 such as ``unsigned __int128`` and C23 ``unsigned _BitInt(N)``.
 
+``__builtin_clzg`` and ``__builtin_ctzg``
+-----------------------------------------
+
+``__builtin_clzg`` (respectively ``__builtin_ctzg``) returns the number of
+leading (respectively trailing) 0 bits in the first argument. The first argument
+can be of any unsigned integer type.
+
+If the first argument is 0 and an optional second argument of ``int`` type is
+provided, then the second argument is returned. If the first argument is 0, but
+only one argument is provided, then the behavior is undefined.
+
+**Syntax**:
+
+.. code-block:: c++
+
+  int __builtin_clzg(type x[, int fallback])
+  int __builtin_ctzg(type x[, int fallback])
+
+**Examples**:
+
+.. code-block:: c++
+
+  unsigned int x = 1;
+  int x_lz = __builtin_clzg(x);
+  int x_tz = __builtin_ctzg(x);
+
+  unsigned long y = 2;
+  int y_lz = __builtin_clzg(y);
+  int y_tz = __builtin_ctzg(y);
+
+  unsigned _BitInt(128) z = 4;
+  int z_lz = __builtin_clzg(z);
+  int z_tz = __builtin_ctzg(z);
+
+**Description**:
+
+``__builtin_clzg`` (respectively ``__builtin_ctzg``) is meant to be a
+type-generic alternative to the ``__builtin_clz{,l,ll}`` (respectively
+``__builtin_ctz{,l,ll}``) builtins, with support for other integer types, such
+as ``unsigned __int128`` and C23 ``unsigned _BitInt(N)``.
+
 Multiprecision Arithmetic Builtins
 ----------------------------------
 

clang/include/clang/Basic/Builtins.td

@@ -676,15 +676,23 @@ def Clz : Builtin, BitShort_Int_Long_LongLongTemplate {
   let Prototype = "int(unsigned T)";
 }
 
-// FIXME: Add int clzimax(uintmax_t)
+def Clzg : Builtin {
+  let Spellings = ["__builtin_clzg"];
+  let Attributes = [NoThrow, Const, CustomTypeChecking];
+  let Prototype = "int(...)";
+}
 
 def Ctz : Builtin, BitShort_Int_Long_LongLongTemplate {
   let Spellings = ["__builtin_ctz"];
   let Attributes = [NoThrow, Const, Constexpr];
   let Prototype = "int(unsigned T)";
 }
 
-// FIXME: Add int ctzimax(uintmax_t)
+def Ctzg : Builtin {
+  let Spellings = ["__builtin_ctzg"];
+  let Attributes = [NoThrow, Const, CustomTypeChecking];
+  let Prototype = "int(...)";
+}
 
 def FFS : Builtin, BitInt_Long_LongLongTemplate {
   let Spellings = ["__builtin_ffs"];

clang/include/clang/Basic/DiagnosticSemaKinds.td

@@ -12020,13 +12020,14 @@ def err_builtin_launder_invalid_arg : Error<
   "'__builtin_launder' is not allowed">;
 
 def err_builtin_invalid_arg_type: Error <
-  "%ordinal0 argument must be a "
-  "%select{vector, integer or floating point type|matrix|"
-  "pointer to a valid matrix element type|"
-  "signed integer or floating point type|vector type|"
-  "floating point type|"
-  "vector of integers|"
-  "type of unsigned integer}1 (was %2)">;
+  "%ordinal0 argument must be "
+  "%select{a vector, integer or floating point type|a matrix|"
+  "a pointer to a valid matrix element type|"
+  "a signed integer or floating point type|a vector type|"
+  "a floating point type|"
+  "a vector of integers|"
+  "an unsigned integer|"
+  "an 'int'}1 (was %2)">;
 
 def err_builtin_matrix_disabled: Error<
   "matrix types extension is disabled. Pass -fenable-matrix to enable it">;

clang/lib/CodeGen/CGBuiltin.cpp

@@ -3128,36 +3128,66 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
   case Builtin::BI__builtin_ctzs:
   case Builtin::BI__builtin_ctz:
   case Builtin::BI__builtin_ctzl:
-  case Builtin::BI__builtin_ctzll: {
-    Value *ArgValue = EmitCheckedArgForBuiltin(E->getArg(0), BCK_CTZPassedZero);
+  case Builtin::BI__builtin_ctzll:
+  case Builtin::BI__builtin_ctzg: {
+    bool HasFallback = BuiltinIDIfNoAsmLabel == Builtin::BI__builtin_ctzg &&
+                       E->getNumArgs() > 1;
+
+    Value *ArgValue =
+        HasFallback ? EmitScalarExpr(E->getArg(0))
+                    : EmitCheckedArgForBuiltin(E->getArg(0), BCK_CTZPassedZero);
 
     llvm::Type *ArgType = ArgValue->getType();
     Function *F = CGM.getIntrinsic(Intrinsic::cttz, ArgType);
 
     llvm::Type *ResultType = ConvertType(E->getType());
-    Value *ZeroUndef = Builder.getInt1(getTarget().isCLZForZeroUndef());
+    Value *ZeroUndef =
+        Builder.getInt1(HasFallback || getTarget().isCLZForZeroUndef());
     Value *Result = Builder.CreateCall(F, {ArgValue, ZeroUndef});
     if (Result->getType() != ResultType)
       Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                      "cast");
-    return RValue::get(Result);
+    if (!HasFallback)
+      return RValue::get(Result);
+
+    Value *Zero = Constant::getNullValue(ArgType);
+    Value *IsZero = Builder.CreateICmpEQ(ArgValue, Zero, "iszero");
+    Value *FallbackValue = EmitScalarExpr(E->getArg(1));
+    Value *ResultOrFallback =
+        Builder.CreateSelect(IsZero, FallbackValue, Result, "ctzg");
+    return RValue::get(ResultOrFallback);
   }
   case Builtin::BI__builtin_clzs:
   case Builtin::BI__builtin_clz:
   case Builtin::BI__builtin_clzl:
-  case Builtin::BI__builtin_clzll: {
-    Value *ArgValue = EmitCheckedArgForBuiltin(E->getArg(0), BCK_CLZPassedZero);
+  case Builtin::BI__builtin_clzll:
+  case Builtin::BI__builtin_clzg: {
+    bool HasFallback = BuiltinIDIfNoAsmLabel == Builtin::BI__builtin_clzg &&
+                       E->getNumArgs() > 1;
+
+    Value *ArgValue =
+        HasFallback ? EmitScalarExpr(E->getArg(0))
+                    : EmitCheckedArgForBuiltin(E->getArg(0), BCK_CLZPassedZero);
 
     llvm::Type *ArgType = ArgValue->getType();
     Function *F = CGM.getIntrinsic(Intrinsic::ctlz, ArgType);
 
     llvm::Type *ResultType = ConvertType(E->getType());
-    Value *ZeroUndef = Builder.getInt1(getTarget().isCLZForZeroUndef());
+    Value *ZeroUndef =
+        Builder.getInt1(HasFallback || getTarget().isCLZForZeroUndef());
     Value *Result = Builder.CreateCall(F, {ArgValue, ZeroUndef});
     if (Result->getType() != ResultType)
       Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
                                      "cast");
-    return RValue::get(Result);
+    if (!HasFallback)
+      return RValue::get(Result);
+
+    Value *Zero = Constant::getNullValue(ArgType);
+    Value *IsZero = Builder.CreateICmpEQ(ArgValue, Zero, "iszero");
+    Value *FallbackValue = EmitScalarExpr(E->getArg(1));
+    Value *ResultOrFallback =
+        Builder.CreateSelect(IsZero, FallbackValue, Result, "clzg");
+    return RValue::get(ResultOrFallback);
   }
   case Builtin::BI__builtin_ffs:
   case Builtin::BI__builtin_ffsl:

clang/lib/Sema/SemaChecking.cpp

@@ -2399,6 +2399,48 @@ static bool SemaBuiltinPopcountg(Sema &S, CallExpr *TheCall) {
   return false;
 }
 
+/// Checks that __builtin_{clzg,ctzg} was called with a first argument, which is
+/// an unsigned integer, and an optional second argument, which is promoted to
+/// an 'int'.
+static bool SemaBuiltinCountZeroBitsGeneric(Sema &S, CallExpr *TheCall) {
+  if (checkArgCountRange(S, TheCall, 1, 2))
+    return true;
+
+  ExprResult Arg0Res = S.DefaultLvalueConversion(TheCall->getArg(0));
+  if (Arg0Res.isInvalid())
+    return true;
+
+  Expr *Arg0 = Arg0Res.get();
+  TheCall->setArg(0, Arg0);
+
+  QualType Arg0Ty = Arg0->getType();
+
+  if (!Arg0Ty->isUnsignedIntegerType()) {
+    S.Diag(Arg0->getBeginLoc(), diag::err_builtin_invalid_arg_type)
+        << 1 << /*unsigned integer ty*/ 7 << Arg0Ty;
+    return true;
+  }
+
+  if (TheCall->getNumArgs() > 1) {
+    ExprResult Arg1Res = S.UsualUnaryConversions(TheCall->getArg(1));
+    if (Arg1Res.isInvalid())
+      return true;
+
+    Expr *Arg1 = Arg1Res.get();
+    TheCall->setArg(1, Arg1);
+
+    QualType Arg1Ty = Arg1->getType();
+
+    if (!Arg1Ty->isSpecificBuiltinType(BuiltinType::Int)) {
+      S.Diag(Arg1->getBeginLoc(), diag::err_builtin_invalid_arg_type)
+          << 2 << /*'int' ty*/ 8 << Arg1Ty;
+      return true;
+    }
+  }
+
+  return false;
+}
+
 ExprResult
 Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
                                CallExpr *TheCall) {
@@ -3187,6 +3229,11 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
     if (SemaBuiltinPopcountg(*this, TheCall))
       return ExprError();
     break;
+  case Builtin::BI__builtin_clzg:
+  case Builtin::BI__builtin_ctzg:
+    if (SemaBuiltinCountZeroBitsGeneric(*this, TheCall))
+      return ExprError();
+    break;
   }
 
   if (getLangOpts().HLSL && CheckHLSLBuiltinFunctionCall(BuiltinID, TheCall))