diff --git a/clang/include/clang/Basic/Builtins.def b/clang/include/clang/Basic/Builtins.def --- a/clang/include/clang/Basic/Builtins.def +++ b/clang/include/clang/Basic/Builtins.def @@ -649,6 +649,7 @@ BUILTIN(__builtin_elementwise_ceil, "v.", "nct") BUILTIN(__builtin_reduce_max, "v.", "nct") BUILTIN(__builtin_reduce_min, "v.", "nct") +BUILTIN(__builtin_reduce_xor, "v.", "nct") BUILTIN(__builtin_matrix_transpose, "v.", "nFt") BUILTIN(__builtin_matrix_column_major_load, "v.", "nFt") diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td --- a/clang/include/clang/Basic/DiagnosticSemaKinds.td +++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td @@ -11378,7 +11378,8 @@ "%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}1 (was %2)">; + "floating point type|" + "vector of integers}1 (was %2)">; def err_builtin_matrix_disabled: Error< "matrix types extension is disabled. Pass -fenable-matrix to enable it">; diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h --- a/clang/include/clang/Sema/Sema.h +++ b/clang/include/clang/Sema/Sema.h @@ -12784,7 +12784,7 @@ bool SemaBuiltinElementwiseMath(CallExpr *TheCall); bool PrepareBuiltinElementwiseMathOneArgCall(CallExpr *TheCall); - bool SemaBuiltinReduceMath(CallExpr *TheCall); + bool PrepareBuiltinReduceMathOneArgCall(CallExpr *TheCall); // Matrix builtin handling. ExprResult SemaBuiltinMatrixTranspose(CallExpr *TheCall, diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -3211,6 +3211,13 @@ return RValue::get(Result); } + case Builtin::BI__builtin_reduce_xor: { + Value *Op0 = EmitScalarExpr(E->getArg(0)); + Value *Result = Builder.CreateUnaryIntrinsic( + llvm::Intrinsic::vector_reduce_xor, Op0, nullptr, "rdx.xor"); + return RValue::get(Result); + } + case Builtin::BI__builtin_matrix_transpose: { const auto *MatrixTy = E->getArg(0)->getType()->getAs(); Value *MatValue = EmitScalarExpr(E->getArg(0)); diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp --- a/clang/lib/Sema/SemaChecking.cpp +++ b/clang/lib/Sema/SemaChecking.cpp @@ -2216,10 +2216,38 @@ return ExprError(); break; case Builtin::BI__builtin_reduce_max: - case Builtin::BI__builtin_reduce_min: - if (SemaBuiltinReduceMath(TheCall)) + case Builtin::BI__builtin_reduce_min: { + if (PrepareBuiltinReduceMathOneArgCall(TheCall)) return ExprError(); + + const Expr *Arg = TheCall->getArg(0); + const auto *TyA = Arg->getType()->getAs(); + if (!TyA) { + Diag(Arg->getBeginLoc(), diag::err_builtin_invalid_arg_type) + << 1 << /* vector ty*/ 4 << Arg->getType(); + return ExprError(); + } + + TheCall->setType(TyA->getElementType()); break; + } + + // __builtin_reduce_xor supports vector of integers only. + case Builtin::BI__builtin_reduce_xor: { + if (PrepareBuiltinReduceMathOneArgCall(TheCall)) + return ExprError(); + + const Expr *Arg = TheCall->getArg(0); + const auto *TyA = Arg->getType()->getAs(); + if (!TyA || !TyA->getElementType()->isIntegerType()) { + Diag(Arg->getBeginLoc(), diag::err_builtin_invalid_arg_type) + << 1 << /* vector of integers */ 6 << Arg->getType(); + return ExprError(); + } + TheCall->setType(TyA->getElementType()); + break; + } + case Builtin::BI__builtin_matrix_transpose: return SemaBuiltinMatrixTranspose(TheCall, TheCallResult); @@ -16882,7 +16910,7 @@ return false; } -bool Sema::SemaBuiltinReduceMath(CallExpr *TheCall) { +bool Sema::PrepareBuiltinReduceMathOneArgCall(CallExpr *TheCall) { if (checkArgCount(*this, TheCall, 1)) return true; @@ -16891,14 +16919,6 @@ return true; TheCall->setArg(0, A.get()); - const VectorType *TyA = A.get()->getType()->getAs(); - if (!TyA) { - SourceLocation ArgLoc = TheCall->getArg(0)->getBeginLoc(); - return Diag(ArgLoc, diag::err_builtin_invalid_arg_type) - << 1 << /* vector ty*/ 4 << A.get()->getType(); - } - - TheCall->setType(TyA->getElementType()); return false; } diff --git a/clang/test/CodeGen/builtins-reduction-math.c b/clang/test/CodeGen/builtins-reduction-math.c --- a/clang/test/CodeGen/builtins-reduction-math.c +++ b/clang/test/CodeGen/builtins-reduction-math.c @@ -57,3 +57,14 @@ const si8 cvi1 = vi1; unsigned long long r5 = __builtin_reduce_min(cvi1); } + +void test_builtin_reduce_xor(si8 vi1, u4 vu1) { + + // CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16 + // CHECK-NEXT: call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> [[VI1]]) + short r2 = __builtin_reduce_xor(vi1); + + // CHECK: [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16 + // CHECK-NEXT: call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> [[VU1]]) + unsigned r3 = __builtin_reduce_xor(vu1); +} diff --git a/clang/test/Sema/builtins-reduction-math.c b/clang/test/Sema/builtins-reduction-math.c --- a/clang/test/Sema/builtins-reduction-math.c +++ b/clang/test/Sema/builtins-reduction-math.c @@ -35,3 +35,20 @@ i = __builtin_reduce_min(i); // expected-error@-1 {{1st argument must be a vector type (was 'int')}} } + +void test_builtin_reduce_xor(int i, float4 v, int3 iv) { + struct Foo s = __builtin_reduce_xor(iv); + // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}} + + i = __builtin_reduce_xor(); + // expected-error@-1 {{too few arguments to function call, expected 1, have 0}} + + i = __builtin_reduce_xor(iv, iv); + // expected-error@-1 {{too many arguments to function call, expected 1, have 2}} + + i = __builtin_reduce_xor(i); + // expected-error@-1 {{1st argument must be a vector of integers (was 'int')}} + + i = __builtin_reduce_xor(v); + // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}} +}