[Clang] Add __builtin_reduce_or and __builtin_reduce_and

This patch implements two builtins specified in D111529.
The last __builtin_reduce_add will be seperated into another one.

Differential Revision: https://reviews.llvm.org/D116736

clang/include/clang/Basic/Builtins.def

@@ -656,6 +656,8 @@ BUILTIN(__builtin_elementwise_trunc, "v.", "nct")
 BUILTIN(__builtin_reduce_max, "v.", "nct")
 BUILTIN(__builtin_reduce_min, "v.", "nct")
 BUILTIN(__builtin_reduce_xor, "v.", "nct")
+BUILTIN(__builtin_reduce_or, "v.", "nct")
+BUILTIN(__builtin_reduce_and, "v.", "nct")
 
 BUILTIN(__builtin_matrix_transpose, "v.", "nFt")
 BUILTIN(__builtin_matrix_column_major_load, "v.", "nFt")

clang/lib/CodeGen/CGBuiltin.cpp

@@ -3221,6 +3221,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
   case Builtin::BI__builtin_reduce_xor:
     return RValue::get(emitUnaryBuiltin(
         *this, E, llvm::Intrinsic::vector_reduce_xor, "rdx.xor"));
+  case Builtin::BI__builtin_reduce_or:
+    return RValue::get(emitUnaryBuiltin(
+        *this, E, llvm::Intrinsic::vector_reduce_or, "rdx.or"));
+  case Builtin::BI__builtin_reduce_and:
+    return RValue::get(emitUnaryBuiltin(
+        *this, E, llvm::Intrinsic::vector_reduce_and, "rdx.and"));
 
   case Builtin::BI__builtin_matrix_transpose: {
     auto *MatrixTy = E->getArg(0)->getType()->castAs<ConstantMatrixType>();

clang/lib/Sema/SemaChecking.cpp

@@ -2237,8 +2237,10 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
     break;
   }
 
-  // __builtin_reduce_xor supports vector of integers only.
-  case Builtin::BI__builtin_reduce_xor: {
+  // These builtins support vectors of integers only.
+  case Builtin::BI__builtin_reduce_xor:
+  case Builtin::BI__builtin_reduce_or:
+  case Builtin::BI__builtin_reduce_and: {
     if (PrepareBuiltinReduceMathOneArgCall(TheCall))
       return ExprError();
 

clang/test/CodeGen/builtins-reduction-math.c

@@ -68,3 +68,25 @@ void test_builtin_reduce_xor(si8 vi1, u4 vu1) {
   // CHECK-NEXT: call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> [[VU1]])
   unsigned r3 = __builtin_reduce_xor(vu1);
 }
+
+void test_builtin_reduce_or(si8 vi1, u4 vu1) {
+
+  // CHECK:      [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
+  // CHECK-NEXT: call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> [[VI1]])
+  short r2 = __builtin_reduce_or(vi1);
+
+  // CHECK:      [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
+  // CHECK-NEXT: call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> [[VU1]])
+  unsigned r3 = __builtin_reduce_or(vu1);
+}
+
+void test_builtin_reduce_and(si8 vi1, u4 vu1) {
+
+  // CHECK:      [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
+  // CHECK-NEXT: call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> [[VI1]])
+  short r2 = __builtin_reduce_and(vi1);
+
+  // CHECK:      [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
+  // CHECK-NEXT: call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> [[VU1]])
+  unsigned r3 = __builtin_reduce_and(vu1);
+}

clang/test/Sema/builtins-reduction-math.c

@@ -52,3 +52,37 @@ void test_builtin_reduce_xor(int i, float4 v, int3 iv) {
   i = __builtin_reduce_xor(v);
   // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}}
 }
+
+void test_builtin_reduce_or(int i, float4 v, int3 iv) {
+  struct Foo s = __builtin_reduce_or(iv);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
+
+  i = __builtin_reduce_or();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_reduce_or(iv, iv);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  i = __builtin_reduce_or(i);
+  // expected-error@-1 {{1st argument must be a vector of integers (was 'int')}}
+
+  i = __builtin_reduce_or(v);
+  // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}}
+}
+
+void test_builtin_reduce_and(int i, float4 v, int3 iv) {
+  struct Foo s = __builtin_reduce_and(iv);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
+
+  i = __builtin_reduce_and();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_reduce_and(iv, iv);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  i = __builtin_reduce_and(i);
+  // expected-error@-1 {{1st argument must be a vector of integers (was 'int')}}
+
+  i = __builtin_reduce_and(v);
+  // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}}
+}