constexpr reduce_add

Author: c8ef

clang/docs/ReleaseNotes.rst

@@ -353,6 +353,8 @@ Non-comprehensive list of changes in this release
   The flexible array member (FAM) can now be accessed immediately without causing
   issues with the sanitizer because the counter is automatically set.
 
+- ``__builtin_reduce_add`` function can now be used in constant expressions.
+
 New Compiler Flags
 ------------------
 

clang/include/clang/Basic/Builtins.td

@@ -1504,7 +1504,7 @@ def ReduceAnd : Builtin {
 
 def ReduceAdd : Builtin {
   let Spellings = ["__builtin_reduce_add"];
-  let Attributes = [NoThrow, Const, CustomTypeChecking];
+  let Attributes = [NoThrow, Const, CustomTypeChecking, Constexpr];
   let Prototype = "void(...)";
 }
 

clang/lib/AST/ExprConstant.cpp

@@ -13528,6 +13528,20 @@ bool IntExprEvaluator::VisitBuiltinCallExpr(const CallExpr *E,
     return Success(DidOverflow, E);
   }
 
+  case Builtin::BI__builtin_reduce_add: {
+    APValue Source;
+    if (!EvaluateAsRValue(Info, E->getArg(0), Source))
+      return false;
+
+    auto SourceLen = Source.getVectorLength();
+    APSInt Reduced = Source.getVectorElt(0).getInt();
+    for (unsigned EltNum = 1; EltNum < SourceLen; ++EltNum) {
+      Reduced += Source.getVectorElt(EltNum).getInt();
+    }
+
+    return Success(Reduced, E);
+  }
+
   case clang::X86::BI__builtin_ia32_addcarryx_u32:
   case clang::X86::BI__builtin_ia32_addcarryx_u64:
   case clang::X86::BI__builtin_ia32_subborrow_u32:

clang/test/Sema/constant_builtins_vector.cpp

@@ -723,3 +723,9 @@ not within the bounds of the input vectors; index of -1 found at position 0 is n
 permitted in a constexpr context}}
         vector4charConst1,
         vector4charConst2, -1, -1, -1, -1);
+
+static_assert(__builtin_reduce_add((vector4char){}) == 0);
+static_assert(__builtin_reduce_add((vector4char){1, 2, 3, 4}) == 10);
+static_assert(__builtin_reduce_add((vector4short){10, 20, 30, 40}) == 100);
+static_assert(__builtin_reduce_add((vector4int){100, 200, 300, 400}) == 1000);
+static_assert(__builtin_reduce_add((vector4long){1000, 2000, 3000, 4000}) == 10000);