s390x simd: disable functions with out-of-bounds reads (pytorch#102266)

AlekseiNikiforovIBM · pytorchmergebot · commit bcaa93e80c03 · 2023-05-26T20:59:42.000Z
3 disabled functions are attempting out of bounds reads. Disable them until sleef library is fixed. <details> <summary>ASAN report</summary> ``` ================================================================= ==2030580==ERROR: AddressSanitizer: global-buffer-overflow on address 0x03ff70f54570 at pc 0x03ff6704e960 bp 0x03ffce128940 sp 0x03ffce128930 READ of size 4 at 0x03ff70f54570 thread T0 #0 0x3ff6704e95f in vgather_vf_p_vi2 /home/user/pytorch/third_party/sleef/src/arch/helpers390x_128.h:129 #1 0x3ff6704e95f in rempif /home/user/pytorch/third_party/sleef/src/libm/sleefsimdsp.c:550 #2 0x3ff6704e95f in Sleef_cosf4_u10vxe2 /home/user/pytorch/third_party/sleef/src/libm/sleefsimdsp.c:1021 #3 0x3ff67029cfb in Sleef_cosf4_u10 /home/user/pytorch/build/sleef/src/libm/disps390x_128.c:182 #4 0x3ff55d21941 in at::vec::ZVECTOR::Vectorized<float, void> at::vec::ZVECTOR::Vectorized<float, void>::mapSleef<float __vector(4) const (*)(float __vector(4)), double __vector(2) const (*)(double __ vector(2)), float, 0>(float __vector(4) const (*)(float __vector(4)), double __vector(2) const (*)(double __vector(2))) const /home/user/pytorch/aten/src/ATen/cpu/vec/vec256/zarch/vec256_zarch.h:991 #5 0x3ff5689ad01 in at::vec::ZVECTOR::Vectorized<float, void>::cos() const /home/user/pytorch/aten/src/ATen/cpu/vec/vec256/zarch/vec256_zarch.h:1074 pytorch#6 0x3ff5685df97 in at::vml::ZVECTOR::vcos<float>(float*, float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)#1}::operator()(at::vec::ZVECTOR::Vectorized<float, void>) const /home/ user/pytorch/aten/src/ATen/cpu/vml.h:71 pytorch#7 0x3ff5689b691 in void at::vec::map<float, at::vml::ZVECTOR::vcos<float>(float*, float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)#1}, 0>(at::vml::ZVECTOR::vcos<float>(float*, float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)#1} const&, float*, float const*, long) /home/user/pytorch/aten/src/ATen/cpu/vec/functional_base.h:239 pytorch#8 0x3ff5685e0df in void at::vml::ZVECTOR::vcos<float>(float*, float const*, long) /home/user/pytorch/aten/src/ATen/cpu/vml.h:71 pytorch#9 0x3ff563fdde3 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770 pytorch#10 0x3ff5648e4a3 in operator() /home/user/pytorch/aten/src/ATen/TensorIterator.h:406 pytorch#11 0x3ff5663cae1 in callback_fn<at::TensorIteratorBase::loop_2d_from_1d<at::native::ZVECTOR::cos_kernel(at::TensorIteratorBase&)::<lambda()>::<lambda()>::<lambda(char**, const int64_t*, int64_t)> >(c onst at::native::ZVECTOR::cos_kernel(at::TensorIteratorBase&)::<lambda()>::<lambda()>::<lambda(char**, const int64_t*, int64_t)>&)::<lambda(char**, const int64_t*, int64_t, int64_t)> > /home/user/pytorch/ c10/util/FunctionRef.h:43 pytorch#12 0x3ff4d45a933 in c10::function_ref<void (char**, long const*, long, long)>::operator()(char**, long const*, long, long) const /home/user/pytorch/c10/util/FunctionRef.h:64 pytorch#13 0x3ff4d455133 in at::internal::serial_for_each(c10::ArrayRef<long>, c10::ArrayRef<long>, char**, unsigned long, c10::function_ref<void (char**, long const*, long, long)>, at::Range) /home/user/pyt orch/aten/src/ATen/TensorIteratorInternal.h:52 pytorch#14 0x3ff4d43b703 in at::TensorIteratorBase::serial_for_each(c10::function_ref<void (char**, long const*, long, long)>, at::Range) const /home/user/pytorch/aten/src/ATen/TensorIterator.cpp:777 pytorch#15 0x3ff4d43ab59 in at::TensorIteratorBase::for_each(c10::function_ref<void (char**, long const*, long, long)>, long) /home/user/pytorch/aten/src/ATen/TensorIterator.cpp:749 pytorch#16 0x3ff5648e851 in for_each<at::native::ZVECTOR::cos_kernel(at::TensorIteratorBase&)::<lambda()>::<lambda()>::<lambda(char**, const int64_t*, int64_t)> > /home/user/pytorch/aten/src/ATen/TensorItera tor.h:421 pytorch#17 0x3ff563fe5f9 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770 pytorch#18 0x3ff56400915 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770 pytorch#19 0x3ff56400f1d in at::native::ZVECTOR::cos_kernel(at::TensorIteratorBase&) /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770 pytorch#20 0x3ff4f303007 in void at::native::DispatchStub<void (*)(at::TensorIteratorBase&), at::native::cos_stub>::operator()<at::native::structured_cos_out&>(c10::DeviceType, at::native::structured_cos_out &) /home/user/pytorch/aten/src/ATen/native/DispatchStub.h:158 pytorch#21 0x3ff4f2edb3f in at::native::structured_cos_out::impl(at::Tensor const&, at::Tensor const&) /home/user/pytorch/aten/src/ATen/native/UnaryOps.cpp:330 pytorch#22 0x3ff526ef739 in wrapper_CPU_cos /home/user/pytorch/build/aten/src/ATen/RegisterCPU.cpp:4307 pytorch#23 0x3ff52c651d9 in operator() /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFunctionIntoFunctor.h:13 pytorch#24 0x3ff52c651d9 in call /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h:463 pytorch#25 0x3ff5076df2f in at::Tensor c10::callUnboxedKernelFunction<at::Tensor, at::Tensor const&>(void*, c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&) /home/user/pytorch/aten/src/ATen/core /boxing/KernelFunction_impl.h:50 pytorch#26 0x3ff5009a93f in at::Tensor c10::KernelFunction::call<at::Tensor, at::Tensor const&>(c10::OperatorHandle const&, c10::DispatchKeySet, at::Tensor const&) const /home/user/pytorch/aten/src/ATen/core /boxing/KernelFunction_impl.h:103 pytorch#27 0x3ff5009a93f in at::Tensor c10::Dispatcher::call<at::Tensor, at::Tensor const&>(c10::TypedOperatorHandle<at::Tensor (at::Tensor const&)> const&, at::Tensor const&) const /home/user/pytorch/aten/s rc/ATen/core/dispatch/Dispatcher.h:639 pytorch#28 0x3ff5009a93f in c10::TypedOperatorHandle<at::Tensor (at::Tensor const&)>::call(at::Tensor const&) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:487 pytorch#29 0x3ff5009a93f in at::_ops::cos::call(at::Tensor const&) /home/user/pytorch/build/aten/src/ATen/Operators_0.cpp:2215 pytorch#30 0x3ff7d813741 in at::Tensor::cos() const /home/user/pytorch/build/aten/src/ATen/core/TensorBody.h:2107 pytorch#31 0x3ff7dc0f2b7 in operator() /home/user/pytorch/torch/csrc/autograd/generated/python_torch_functions_2.cpp:2953 pytorch#32 0x3ff7dc0faf7 in THPVariable_cos /home/user/pytorch/torch/csrc/autograd/generated/python_torch_functions_2.cpp:2955 pytorch#33 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543 pytorch#34 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#35 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#36 0x3ffa5feb50d in do_call_core Python/ceval.c:5915 pytorch#37 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#38 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#39 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#40 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#41 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#42 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#43 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#44 0x3ff7f87a393 in torch::impl::dispatch::PythonKernelHolder::operator()(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) /home/user/pytorch/ torch/csrc/utils/python_dispatch.cpp:175 pytorch#45 0x3ff7f8871a7 in c10::BoxedKernel::makeFromFunctor<torch::impl::dispatch::PythonKernelHolder>(std::unique_ptr<torch::impl::dispatch::PythonKernelHolder, std::default_delete<torch::impl::dispatch:: PythonKernelHolder> >)::{lambda(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)#1}::operator()(c10::OperatorKernel*, c10::Op eratorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/boxing/BoxedKernel_impl.h:87 pytorch#46 0x3ff7f887261 in c10::BoxedKernel::makeFromFunctor<torch::impl::dispatch::PythonKernelHolder>(std::unique_ptr<torch::impl::dispatch::PythonKernelHolder, std::default_delete<torch::impl::dispatch:: PythonKernelHolder> >)::{lambda(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)#1}::_FUN(c10::OperatorKernel*, c10::Operator Handle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) /home/user/pytorch/aten/src/ATen/core/boxing/BoxedKernel_impl.h:86 pytorch#47 0x3ff7e0d10ab in c10::BoxedKernel::callBoxed(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/b oxing/BoxedKernel_impl.h:41 pytorch#48 0x3ff7e0d1459 in c10::KernelFunction::callBoxed(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/cor e/boxing/KernelFunction_impl.h:43 pytorch#49 0x3ff7f876421 in c10::Dispatcher::callBoxed(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:6 91 pytorch#50 0x3ff4d22bcdd in c10::OperatorHandle::callBoxed(std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:417 pytorch#51 0x3ff65a092d5 in c10::OperatorHandle::callBoxed(std::vector<c10::IValue, std::allocator<c10::IValue> >&) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:421 pytorch#52 0x3ff65a05641 in operator() /home/user/pytorch/torch/csrc/jit/runtime/register_c10_ops.cpp:15 pytorch#53 0x3ff65a08cb5 in __invoke_impl<void, torch::jit::(anonymous namespace)::createOperatorFromC10(const c10::OperatorHandle&)::<lambda(torch::jit::Stack&)>&, std::vector<c10::IValue, std::allocator<c1 0::IValue> >&> /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/invoke.h:61 pytorch#54 0x3ff65a0897b in __invoke_r<void, torch::jit::(anonymous namespace)::createOperatorFromC10(const c10::OperatorHandle&)::<lambda(torch::jit::Stack&)>&, std::vector<c10::IValue, std::allocator<c10:: IValue> >&> /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/invoke.h:111 pytorch#55 0x3ff65a084e1 in _M_invoke /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/std_function.h:290 pytorch#56 0x3ff7eb2cb21 in std::function<void (std::vector<c10::IValue, std::allocator<c10::IValue> >&)>::operator()(std::vector<c10::IValue, std::allocator<c10::IValue> >&) const /usr/lib/gcc/s390x-ibm-lin ux-gnu/11/include/g++-v11/bits/std_function.h:590 pytorch#57 0x3ff7eb1b659 in torch::jit::Operation::operator()(std::vector<c10::IValue, std::allocator<c10::IValue> >&) /home/user/pytorch/aten/src/ATen/core/stack.h:41 pytorch#58 0x3ff7eb08449 in torch::jit::invokeOperatorFromPython(std::vector<std::shared_ptr<torch::jit::Operator>, std::allocator<std::shared_ptr<torch::jit::Operator> > > const&, pybind11::args, pybind11:: kwargs const&, c10::optional<c10::DispatchKey>) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:764 pytorch#59 0x3ff7eb09d85 in torch::jit::_get_operation_for_overload_or_packet(std::vector<std::shared_ptr<torch::jit::Operator>, std::allocator<std::shared_ptr<torch::jit::Operator> > > const&, c10::Symbol, pybind11::args, pybind11::kwargs const&, bool, c10::optional<c10::DispatchKey>) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:829 pytorch#60 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549 pytorch#61 0x3ff7e6728dd in call_impl<pybind11::object, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&, 0, 1, pybind11::detail::vo id_type> /home/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1439 pytorch#62 0x3ff7e64312f in call<pybind11::object, pybind11::detail::void_type, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&> /h ome/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1408 pytorch#63 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249 pytorch#64 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224 pytorch#65 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929 pytorch#66 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543 pytorch#67 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#68 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#69 0x3ffa5feb50d in do_call_core Python/ceval.c:5915 pytorch#70 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#71 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#72 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#73 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#74 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142 pytorch#75 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431 pytorch#76 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494 pytorch#77 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#78 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#79 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#80 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#81 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#82 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#83 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#84 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114 pytorch#85 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123 pytorch#86 0x3ffa5feb289 in call_function Python/ceval.c:5891 pytorch#87 0x3ffa5fe5c3b in _PyEval_EvalFrameDefault Python/ceval.c:4213 pytorch#88 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#89 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#90 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#91 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#92 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#93 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#94 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#95 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#96 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#97 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#98 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#99 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#100 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#101 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#102 0x3ff7f87a393 in torch::impl::dispatch::PythonKernelHolder::operator()(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) /home/user/pytorch /torch/csrc/utils/python_dispatch.cpp:175 pytorch#103 0x3ff7f8871a7 in c10::BoxedKernel::makeFromFunctor<torch::impl::dispatch::PythonKernelHolder>(std::unique_ptr<torch::impl::dispatch::PythonKernelHolder, std::default_delete<torch::impl::dispatch: :PythonKernelHolder> >)::{lambda(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)#1}::operator()(c10::OperatorKernel*, c10::O peratorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/boxing/BoxedKernel_impl.h:87 pytorch#104 0x3ff7f887261 in c10::BoxedKernel::makeFromFunctor<torch::impl::dispatch::PythonKernelHolder>(std::unique_ptr<torch::impl::dispatch::PythonKernelHolder, std::default_delete<torch::impl::dispatch: :PythonKernelHolder> >)::{lambda(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)#1}::_FUN(c10::OperatorKernel*, c10::Operato rHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) /home/user/pytorch/aten/src/ATen/core/boxing/BoxedKernel_impl.h:86 pytorch#105 0x3ff7e0d10ab in c10::BoxedKernel::callBoxed(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/ boxing/BoxedKernel_impl.h:41 pytorch#106 0x3ff7e0d1459 in c10::KernelFunction::callBoxed(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/co re/boxing/KernelFunction_impl.h:43 pytorch#107 0x3ff7f876421 in c10::Dispatcher::callBoxed(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h: 691 pytorch#108 0x3ff4d22bcdd in c10::OperatorHandle::callBoxed(std::vector<c10::IValue, std::allocator<c10::IValue> >*) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:417 pytorch#109 0x3ff65a092d5 in c10::OperatorHandle::callBoxed(std::vector<c10::IValue, std::allocator<c10::IValue> >&) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:421 pytorch#110 0x3ff65a05641 in operator() /home/user/pytorch/torch/csrc/jit/runtime/register_c10_ops.cpp:15 pytorch#111 0x3ff65a08cb5 in __invoke_impl<void, torch::jit::(anonymous namespace)::createOperatorFromC10(const c10::OperatorHandle&)::<lambda(torch::jit::Stack&)>&, std::vector<c10::IValue, std::allocator<c 10::IValue> >&> /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/invoke.h:61 pytorch#112 0x3ff65a0897b in __invoke_r<void, torch::jit::(anonymous namespace)::createOperatorFromC10(const c10::OperatorHandle&)::<lambda(torch::jit::Stack&)>&, std::vector<c10::IValue, std::allocator<c10: :IValue> >&> /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/invoke.h:111 pytorch#113 0x3ff65a084e1 in _M_invoke /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/std_function.h:290 pytorch#114 0x3ff7eb2cb21 in std::function<void (std::vector<c10::IValue, std::allocator<c10::IValue> >&)>::operator()(std::vector<c10::IValue, std::allocator<c10::IValue> >&) const /usr/lib/gcc/s390x-ibm-li nux-gnu/11/include/g++-v11/bits/std_function.h:590 pytorch#115 0x3ff7eb1b659 in torch::jit::Operation::operator()(std::vector<c10::IValue, std::allocator<c10::IValue> >&) /home/user/pytorch/aten/src/ATen/core/stack.h:41 pytorch#116 0x3ff7eb08449 in torch::jit::invokeOperatorFromPython(std::vector<std::shared_ptr<torch::jit::Operator>, std::allocator<std::shared_ptr<torch::jit::Operator> > > const&, pybind11::args, pybind11: :kwargs const&, c10::optional<c10::DispatchKey>) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:764 pytorch#117 0x3ff7eb09d85 in torch::jit::_get_operation_for_overload_or_packet(std::vector<std::shared_ptr<torch::jit::Operator>, std::allocator<std::shared_ptr<torch::jit::Operator> > > const&, c10::Symbol, pybind11::args, pybind11::kwargs const&, bool, c10::optional<c10::DispatchKey>) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:829 pytorch#118 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549 pytorch#119 0x3ff7e6728dd in call_impl<pybind11::object, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&, 0, 1, pybind11::detail::v oid_type> /home/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1439 pytorch#120 0x3ff7e64312f in call<pybind11::object, pybind11::detail::void_type, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&> / home/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1408 pytorch#121 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249 pytorch#122 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224 pytorch#123 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929 pytorch#124 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543 pytorch#125 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#126 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#127 0x3ffa5feb50d in do_call_core Python/ceval.c:5915 pytorch#128 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#129 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#130 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#131 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#132 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142 pytorch#133 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431 pytorch#134 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494 pytorch#135 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#136 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#137 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#138 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#139 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#140 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#141 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#142 0x3ffa5e87d2b in _PyObject_VectorcallTstate Include/cpython/abstract.h:114 pytorch#143 0x3ffa5e882dd in method_vectorcall Objects/classobject.c:83 pytorch#144 0x3ffa5e836d3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114 pytorch#145 0x3ffa5e84b6f in _PyObject_CallFunctionVa Objects/call.c:485 pytorch#146 0x3ffa5e84f2d in callmethod Objects/call.c:557 pytorch#147 0x3ffa5e85039 in PyObject_CallMethod Objects/call.c:577 pytorch#148 0x3ff7f7efa05 in torch::handle_torch_function_no_python_arg_parser(c10::ArrayRef<pybind11::handle>, _object*, _object*, char const*, _object*, char const*, torch::TorchFunctionName) /home/user/py torch/torch/csrc/utils/python_arg_parser.cpp:338 pytorch#149 0x3ff7eb09b67 in torch::jit::_get_operation_for_overload_or_packet(std::vector<std::shared_ptr<torch::jit::Operator>, std::allocator<std::shared_ptr<torch::jit::Operator> > > const&, c10::Symbol, pybind11::args, pybind11::kwargs const&, bool, c10::optional<c10::DispatchKey>) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:827 pytorch#150 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549 pytorch#151 0x3ff7e6728dd in call_impl<pybind11::object, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&, 0, 1, pybind11::detail::v oid_type> /home/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1439 pytorch#152 0x3ff7e64312f in call<pybind11::object, pybind11::detail::void_type, torch::jit::initJITBindings(PyObject*)::<lambda(const string&, const string&)>::<lambda(pybind11::args, pybind11::kwargs)>&> / home/user/pytorch/third_party/pybind11/include/pybind11/cast.h:1408 pytorch#153 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249 pytorch#154 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224 pytorch#155 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929 pytorch#156 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543 pytorch#157 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#158 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#159 0x3ffa5feb50d in do_call_core Python/ceval.c:5915 pytorch#160 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#161 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#162 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#163 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#164 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142 pytorch#165 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431 pytorch#166 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494 pytorch#167 0x3ffa5e84027 in _PyObject_MakeTpCall Objects/call.c:215 pytorch#168 0x3ffa5fd767b in _PyObject_VectorcallTstate Include/cpython/abstract.h:112 pytorch#169 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123 pytorch#170 0x3ffa5feb289 in call_function Python/ceval.c:5891 pytorch#171 0x3ffa5fe5ad1 in _PyEval_EvalFrameDefault Python/ceval.c:4181 pytorch#172 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#173 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#174 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#175 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114 pytorch#176 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123 pytorch#177 0x3ffa5feb289 in call_function Python/ceval.c:5891 pytorch#178 0x3ffa5fe5c3b in _PyEval_EvalFrameDefault Python/ceval.c:4213 pytorch#179 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#180 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#181 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#182 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267 pytorch#183 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#184 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#185 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#186 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#187 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#188 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#189 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#190 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#191 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#192 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#193 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#194 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#195 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#196 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#197 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#198 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#199 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#200 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#201 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#202 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#203 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#204 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#205 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#206 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255 pytorch#207 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#208 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#209 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#210 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#211 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#212 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#213 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#214 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142 pytorch#215 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431 pytorch#216 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494 pytorch#217 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305 pytorch#218 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#219 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#220 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#221 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#222 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#223 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#224 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114 pytorch#225 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123 pytorch#226 0x3ffa5feb289 in call_function Python/ceval.c:5891 pytorch#227 0x3ffa5fe5b21 in _PyEval_EvalFrameDefault Python/ceval.c:4198 pytorch#228 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#229 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#230 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#231 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267 pytorch#232 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#233 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#234 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#235 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#236 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#237 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#238 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#239 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267 pytorch#240 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#241 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#242 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#243 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#244 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#245 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#246 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#247 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267 pytorch#248 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290 pytorch#249 0x3ffa5e84483 in PyObject_Call Objects/call.c:317 pytorch#250 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943 pytorch#251 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277 pytorch#252 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46 pytorch#253 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065 pytorch#254 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342 pytorch#255 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267 0x03ff70f54570 is located 0 bytes to the right of global variable 'Sleef_rempitabsp' defined in '/home/user/pytorch/third_party/sleef/src/libm/rempitab.c:986:34' (0x3ff70f53f00) of size 1648 SUMMARY: AddressSanitizer: global-buffer-overflow /home/user/pytorch/third_party/sleef/src/arch/helpers390x_128.h:129 in vgather_vf_p_vi2 Shadow bytes around the buggy address: 0x10007fee1ea850: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea860: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea870: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea890: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 =>0x10007fee1ea8a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00[f9]f9 0x10007fee1ea8b0: f9 f9 f9 f9 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea8c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea8d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea8e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x10007fee1ea8f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb Shadow gap: cc ==2030580==ABORTING ``` </details> It reproduces when running `pytest -v test/test_ops.py -k test_python_ref__refs_cos_cpu_bfloat16` under address sanitizer on s390x. See also: shibatch/sleef#464 Pull Request resolved: pytorch#102266 Approved by: https://github.com/malfet
diff --git a/aten/src/ATen/cpu/vec/vec256/zarch/vec256_zarch.h b/aten/src/ATen/cpu/vec/vec256/zarch/vec256_zarch.h
@@ -13,6 +13,8 @@
 #include <ATen/cpu/vec/vec_base.h>
 #include <c10/util/complex.h>
 
+#define SLEEF_MEMORY_WORKAROUND
+
 namespace at {
 namespace vec {
 
@@ -1039,20 +1041,32 @@ struct Vectorized<T, std::enable_if_t<is_zarch_implemented<T>()>> {
   }
 
   Vectorized<T> sin() const {
+#ifndef SLEEF_MEMORY_WORKAROUND
     return mapSleef(Sleef_sinf4_u10, Sleef_sind2_u10);
+#else
+    return mapOrdinary(std::sin);
+#endif
   }
   Vectorized<T> sinh() const {
     return mapSleef(Sleef_sinhf4_u10, Sleef_sinhd2_u10);
   }
   Vectorized<T> cos() const {
+#ifndef SLEEF_MEMORY_WORKAROUND
     return mapSleef(Sleef_cosf4_u10, Sleef_cosd2_u10);
+#else
+    return mapOrdinary(std::cos);
+#endif
   }
   Vectorized<T> cosh() const {
     return mapSleef(Sleef_coshf4_u10, Sleef_coshd2_u10);
   }
 
   Vectorized<T> tan() const {
+#ifndef SLEEF_MEMORY_WORKAROUND
     return mapSleef(Sleef_tanf4_u10, Sleef_tand2_u10);
+#else
+    return mapOrdinary(std::tan);
+#endif
   }
   Vectorized<T> tanh() const {
     return mapSleef(Sleef_tanhf4_u10, Sleef_tanhd2_u10);
