When tensor is resized, reference array to it's sizes may become invalid. Make a copy in advance.

<details>
<summary>ASAN report</summary>

```
=================================================================
==1115867==ERROR: AddressSanitizer: heap-use-after-free on address 0x61000013d790 at pc 0x03ff8e7da360 bp 0x03fff53c83a0 sp 0x03fff53c8390
READ of size 8 at 0x61000013d790 thread T0
    #0 0x3ff8e7da35f in c10::SymInt::is_heap_allocated() const /home/user/pytorch/c10/core/SymInt.h:154
    ROCm#1 0x3ff8e7da35f in c10::SymInt::maybe_as_int() const /home/user/pytorch/c10/core/SymInt.h:215
    ROCm#2 0x3ff8e7d0a6d in c10::SymInt::sym_eq(c10::SymInt const&) const /home/user/pytorch/c10/core/SymInt.cpp:69
    ROCm#3 0x3ff7a9ab0bd in c10::SymInt::operator==(c10::SymInt const&) const /home/user/pytorch/c10/core/SymInt.h:177
    ROCm#4 0x3ff7a9aaedd in bool std::__equal<false>::equal<c10::SymInt const*, c10::SymInt const*>(c10::SymInt const*, c10::SymInt const*, c10::SymInt const*) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-
v11/bits/stl_algobase.h:1162
    ROCm#5 0x3ff7a9aae4b in bool std::__equal_aux1<c10::SymInt const*, c10::SymInt const*>(c10::SymInt const*, c10::SymInt const*, c10::SymInt const*) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/
stl_algobase.h:1211
    ROCm#6 0x3ff7a9aae05 in bool std::__equal_aux<c10::SymInt const*, c10::SymInt const*>(c10::SymInt const*, c10::SymInt const*, c10::SymInt const*) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/s
tl_algobase.h:1219
    ROCm#7 0x3ff7a9aad97 in bool std::equal<c10::SymInt const*, c10::SymInt const*>(c10::SymInt const*, c10::SymInt const*, c10::SymInt const*) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_alg
obase.h:1556
    ROCm#8 0x3ff4b23c771 in c10::ArrayRef<c10::SymInt>::equals(c10::ArrayRef<c10::SymInt>) const /home/user/pytorch/c10/util/ArrayRef.h:188
    ROCm#9 0x3ff4cb91bc1 in bool c10::operator!=<c10::SymInt>(c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>) /home/user/pytorch/c10/util/ArrayRef.h:341
    ROCm#10 0x3ff6d1b57ff in torch::ADInplaceOrView::resize_(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pytorch/torch/csrc/autograd/Variab
leTypeManual.cpp:408
    ROCm#11 0x3ff6d1e59c7 in c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c1
0::MemoryFormat>), &torch::ADInplaceOrView::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>
> >::operator()(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFunctionIntoFunctor.h:13
    ROCm#12 0x3ff6d1e59c7 in c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10:
:ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>), &torch::ADInplaceOrView::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::Sy
mInt>, c10::optional<c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::call(c10::OperatorKernel*, c10::Disp
atchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h:480
    ROCm#13 0x3ff51ca5129 in at::Tensor const& c10::callUnboxedKernelFunction<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(void*, c10::OperatorKernel*,
c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>&&, c10::optional<c10::MemoryFormat>&&) /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:50
    ROCm#14 0x3ff51ca6e8f in at::Tensor const& c10::KernelFunction::call<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::OperatorHandle const&, c10::D
ispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:90
    ROCm#15 0x3ff51ca6e8f in at::Tensor const& c10::Dispatcher::redispatch<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::TypedOperatorHandle<at::Ten
sor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)> const&, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)
const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:656
    ROCm#16 0x3ff5182006b in c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::redispatch(c10::DispatchKeySet, at::Tensor const&, c
10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:492
    ROCm#17 0x3ff5182006b in at::_ops::resize_::redispatch(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) aten/src/ATen/Operators_4.cpp:2144
    ROCm#18 0x3ff6d1d5e07 in at::redispatch::resize__symint(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) aten/src/ATen/RedispatchFunctions.h:2847
    ROCm#19 0x3ff6d1bbb67 in torch::autograd::VariableType::(anonymous namespace)::resize_(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pyto
rch/torch/csrc/autograd/VariableTypeManual.cpp:243
    ROCm#20 0x3ff6d1bd197 in c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c1
0::MemoryFormat>), &torch::autograd::VariableType::(anonymous namespace)::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10
::optional<c10::MemoryFormat> > >::operator()(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFu
nctionIntoFunctor.h:13
    ROCm#21 0x3ff6d1bd197 in c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10:
:ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>), &torch::autograd::VariableType::(anonymous namespace)::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor
 const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::call(c
10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor
.h:480
    ROCm#22 0x3ff51ca5129 in at::Tensor const& c10::callUnboxedKernelFunction<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(void*, c10::OperatorKernel*,
c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>&&, c10::optional<c10::MemoryFormat>&&) /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:50
    ROCm#23 0x3ff5181ead1 in at::Tensor const& c10::KernelFunction::call<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::OperatorHandle const&, c10::D
ispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:90
    ROCm#24 0x3ff5181ead1 in at::Tensor const& c10::Dispatcher::call<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::TypedOperatorHandle<at::Tensor co
nst& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)> const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const /home/user/pytorch/at
en/src/ATen/core/dispatch/Dispatcher.h:639
    ROCm#25 0x3ff5181ead1 in c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>,
c10::optional<c10::MemoryFormat>) const /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:487
    ROCm#26 0x3ff5181ead1 in at::_ops::resize_::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) aten/src/ATen/Operators_4.cpp:2137
    ROCm#27 0x3ff79b44fcf in at::Tensor::resize__symint(c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const aten/src/ATen/core/TensorBody.h:2452
    ROCm#28 0x3ff79a802db in torch::autograd::THPVariable_resize_(_object*, _object*, _object*)::$_0::operator()(at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const /home/us
er/pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:13417
    ROCm#29 0x3ff7999f1eb in torch::autograd::THPVariable_resize_(_object*, _object*, _object*) /home/user/pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:13419
    ROCm#30 0x3ffa2c9b009 in method_vectorcall_VARARGS_KEYWORDS Objects/descrobject.c:344
    ROCm#31 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#32 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#33 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#34 0x3ffa2dff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#35 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#36 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#37 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#38 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#39 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#40 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#41 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#42 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#43 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#44 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#45 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#46 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#47 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#48 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#49 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#50 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#51 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#52 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#53 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#54 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#55 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#56 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#57 0x3ffa2dff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#58 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#59 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#60 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#61 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#62 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#63 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#64 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#65 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#66 0x3ffa2dff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#67 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#68 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#69 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#70 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#71 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#72 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#73 0x3ffa2dff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#74 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#75 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#76 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#77 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#78 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#79 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#80 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#81 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#82 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#83 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#84 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#85 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#86 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#87 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#88 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#89 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#90 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#91 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#92 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#93 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#94 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#95 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#96 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#97 0x3ffa2c8ab9b in PyVectorcall_Call Objects/call.c:267
    ROCm#98 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#99 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#100 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#101 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#102 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#103 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#104 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#105 0x3ffa2c8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#106 0x3ffa2c8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#107 0x3ffa2d3f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#108 0x3ffa2c8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#109 0x3ffa2df0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#110 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#111 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#112 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#113 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#114 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#115 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#116 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#117 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#118 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#119 0x3ffa2dff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#120 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#121 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#122 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#123 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#124 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#125 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#126 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#127 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#128 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#129 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#130 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#131 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#132 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#133 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#134 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#135 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#136 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#137 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#138 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#139 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#140 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#141 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#142 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#143 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#144 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#145 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#146 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#147 0x3ffa2c8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#148 0x3ffa2c8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#149 0x3ffa2d3f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#150 0x3ffa2c8ad17 in _PyObject_Call Objects/call.c:305
    ROCm#151 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#152 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#153 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#154 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#155 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#156 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#157 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#158 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#159 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#160 0x3ffa2dff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#161 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#162 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#163 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#164 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#165 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#166 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#167 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#168 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#169 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#170 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#171 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#172 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#173 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#174 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#175 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#176 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#177 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#178 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#179 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#180 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#181 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#182 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#183 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#184 0x3ffa2dff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#185 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#186 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#187 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#188 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#189 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#190 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#191 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#192 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#193 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#194 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#195 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#196 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#197 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#198 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#199 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#200 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#201 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#202 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#203 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#204 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#205 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#206 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#207 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#208 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#209 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#210 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#211 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#212 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#213 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#214 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#215 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#216 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#217 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#218 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#219 0x3ffa2c8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#220 0x3ffa2c8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#221 0x3ffa2d3f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#222 0x3ffa2c8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#223 0x3ffa2df0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#224 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#225 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#226 0x3ffa2dffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#227 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#228 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#229 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#230 0x3ffa2c8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#231 0x3ffa2c8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#232 0x3ffa2c8ada9 in PyObject_Call Objects/call.c:317
    ROCm#233 0x3ffa2e059c7 in do_call_core Python/ceval.c:5943
    ROCm#234 0x3ffa2dffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#235 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#236 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#237 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#238 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#239 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#240 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#241 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#242 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#243 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#244 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#245 0x3ffa2c8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#246 0x3ffa2c8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#247 0x3ffa2df00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#248 0x3ffa2df013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#249 0x3ffa2e05447 in call_function Python/ceval.c:5891
    ROCm#250 0x3ffa2dff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#251 0x3ffa2df052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#252 0x3ffa2e02b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#253 0x3ffa2c8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#254 0x3ffa2c8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#255 0x3ffa2c8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#256 0x3ffa2d3f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#257 0x3ffa2c8a933 in _PyObject_MakeTpCall Objects/call.c:215

0x61000013d790 is located 80 bytes inside of 192-byte region [0x61000013d740,0x61000013d800)
freed by thread T0 here:
    #0 0x3ffa3237de5 in operator delete(void*) /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:160
    ROCm#1 0x3ff8e7e3221 in c10::TensorImpl::~TensorImpl() /home/user/pytorch/c10/core/TensorImpl.cpp:75

previously allocated by thread T0 here:
    #0 0x3ffa323734f in operator new(unsigned long) /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:99
    ROCm#1 0x3ff4aeeb3d1 in c10::intrusive_ptr<c10::TensorImpl, c10::detail::intrusive_target_default_null_type<c10::TensorImpl> > c10::intrusive_ptr<c10::TensorImpl, c10::detail::intrusive_target_default_nul
l_type<c10::TensorImpl> >::make<c10::intrusive_ptr<c10::StorageImpl, c10::detail::intrusive_target_default_null_type<c10::StorageImpl> >, c10::DispatchKeySet&, caffe2::TypeMeta&>(c10::intrusive_ptr<c10::S
torageImpl, c10::detail::intrusive_target_default_null_type<c10::StorageImpl> >&&, c10::DispatchKeySet&, caffe2::TypeMeta&) /home/user/pytorch/c10/util/intrusive_ptr.h:498
    ROCm#2 0x3ff76f79e17  (/home/user/pytorch/build/lib.linux-s390x-cpython-310/torch/lib/libtorch_cpu.so+0x2fb79e17)

SUMMARY: AddressSanitizer: heap-use-after-free /home/user/pytorch/c10/core/SymInt.h:154 in c10::SymInt::is_heap_allocated() const
Shadow bytes around the buggy address:
  0x100c2000027aa0: fa fa fa fa fa fa fa fa fd fd fd fd fd fd fd fd
  0x100c2000027ab0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd
  0x100c2000027ac0: fa fa fa fa fa fa fa fa fd fd fd fd fd fd fd fd
  0x100c2000027ad0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd
  0x100c2000027ae0: fa fa fa fa fa fa fa fa fd fd fd fd fd fd fd fd
=>0x100c2000027af0: fd fd[fd]fd fd fd fd fd fd fd fd fd fd fd fd fd
  0x100c2000027b00: fa fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
  0x100c2000027b10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  0x100c2000027b20: fa fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
  0x100c2000027b30: 00 00 00 00 04 fa fa fa fa fa fa fa fa fa fa fa
  0x100c2000027b40: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
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
==1115867==ABORTING
```
</details>

<details>
<summary>Additional backtraces (not full)</summary>

Memory deallocation:
```
#0  operator delete (ptr=0x61000013d740) at /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:160
ROCm#1  0x000003ffa77e3222 in c10::TensorImpl::~TensorImpl (this=0x61000013d740) at /home/user/pytorch/c10/core/TensorImpl.cpp:75
ROCm#2  0x000003ff63e76e8c in c10::intrusive_ptr<c10::TensorImpl, c10::UndefinedTensorImpl>::reset_ (this=0x3ffd7ec8230) at /home/user/pytorch/c10/util/intrusive_ptr.h:291
ROCm#3  0x000003ff63e76910 in c10::intrusive_ptr<c10::TensorImpl, c10::UndefinedTensorImpl>::~intrusive_ptr (this=0x3ffd7ec8230) at /home/user/pytorch/c10/util/intrusive_ptr.h:370
ROCm#4  0x000003ff63e67240 in at::TensorBase::~TensorBase (this=0x3ffd7ec8230) at /home/user/pytorch/aten/src/ATen/core/TensorBase.h:80
ROCm#5  0x000003ff63e85ee0 in at::Tensor::~Tensor (this=0x3ffd7ec8230) at aten/src/ATen/core/TensorBody.h:90
ROCm#6  0x000003ff63f67304 in resize__functionalization (dispatchKeySet=..., self=..., size=..., memory_format=...) at /home/user/pytorch/aten/src/ATen/FunctionalizeFallbackKernel.cpp:173
ROCm#7  0x000003ff63f89258 in c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>), &(resize__functionalization(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>))>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat> > >::operator()(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>) (
    this=0x6030000390a0, args=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFunctionIntoFunctor.h:13
ROCm#8  c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>), &(resize__functionalization(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>))>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>) (functor=0x6030000390a0, dispatchKeySet=..., args=..., args=...,
    args=...) at /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h:480
ROCm#9  0x000003ff6aca560a in c10::callUnboxedKernelFunction<at::Tensor const&, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat> > (
    unboxed_kernel_func=0x3ff63f88a80 <c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tenso
r const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>), &(resize__functionalization(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>))>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<long>, c10::optional<c10::MemoryFormat>)>, functor=0x6030000390a0,
    dispatchKeySet=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:50
ROCm#10 0x000003ff6aca715c in c10::KernelFunction::call<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> > (this=0x6210005e1b28, opHandle=...,
    dispatchKeySet=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:96
ROCm#11 c10::Dispatcher::redispatch<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)> const&, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const (
    this=0x3ff919400e0 <c10::Dispatcher::realSingleton()::_singleton>, op=..., currentDispatchKeySet=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:656
ROCm#12 0x000003ff6a82006c in c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::redispatch(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const (
    this=0x3ff919a07e0 <at::_ops::resize_::redispatch(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)::op>, currentDispatchKeySet=..., args=...,
    args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:492
ROCm#13 at::_ops::resize_::redispatch (dispatchKeySet=..., self=..., size=..., memory_format=...) at /home/user/pytorch/build/aten/src/ATen/Operators_4.cpp:2144
ROCm#14 0x000003ff861d5e08 in at::redispatch::resize__symint (dispatchKeySet=..., self=..., size=..., memory_format=...) at aten/src/ATen/RedispatchFunctions.h:2847
ROCm#15 0x000003ff861b579e in torch::ADInplaceOrView::resize_ (ks=..., self=..., size=..., optional_memory_format=...) at /home/user/pytorch/torch/csrc/autograd/VariableTypeManual.cpp:401
```

Memory access:
```
#0  c10::SymInt::maybe_as_int (this=0x61000013d790) at /home/user/pytorch/c10/core/SymInt.h:215
ROCm#1  0x000003ff734d0a6e in c10::SymInt::sym_eq (this=0x61000013d790, sci=...) at /home/user/pytorch/c10/core/SymInt.cpp:69
ROCm#2  0x000003ff5f6ab0be in c10::SymInt::operator== (this=0x61000013d790, o=...) at /home/user/pytorch/c10/core/SymInt.h:177
ROCm#3  0x000003ff5f6aaede in std::__equal<false>::equal<c10::SymInt const*, c10::SymInt const*> (__first1=0x61000013d790, __last1=0x61000013d7a0, __first2=0x602000015c30)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_algobase.h:1162
ROCm#4  0x000003ff5f6aae4c in std::__equal_aux1<c10::SymInt const*, c10::SymInt const*> (__first1=0x61000013d790, __last1=0x61000013d7a0, __first2=0x602000015c30)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_algobase.h:1211
ROCm#5  0x000003ff5f6aae06 in std::__equal_aux<c10::SymInt const*, c10::SymInt const*> (__first1=0x61000013d790, __last1=0x61000013d7a0, __first2=0x602000015c30)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_algobase.h:1219
ROCm#6  0x000003ff5f6aad98 in std::equal<c10::SymInt const*, c10::SymInt const*> (__first1=0x61000013d790, __last1=0x61000013d7a0, __first2=0x602000015c30)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_algobase.h:1556
ROCm#7  0x000003ff2ff3c772 in c10::ArrayRef<c10::SymInt>::equals (this=0x3ffed7c9900, RHS=...) at /home/user/pytorch/c10/util/ArrayRef.h:188
ROCm#8  0x000003ff31891bc2 in c10::operator!=<c10::SymInt> (a1=..., a2=...) at /home/user/pytorch/c10/util/ArrayRef.h:341
ROCm#9  0x000003ff51eb5800 in torch::ADInplaceOrView::resize_ (ks=..., self=..., size=..., optional_memory_format=...) at /home/user/pytorch/torch/csrc/autograd/VariableTypeManual.cpp:408
ROCm#10 0x000003ff51ee59c8 in c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c
10::MemoryFormat>), &torch::ADInplaceOrView::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>
 > >::operator()(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) (this=0x6030007dca40, args=..., args=..., args=..., args=...)
    at /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFunctionIntoFunctor.h:13
ROCm#11 c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt
>, c10::optional<c10::MemoryFormat>), &torch::ADInplaceOrView::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<
c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tenso
r const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) (functor=0x6030007dca40, dispatchKeySet=..., args=..., args=..., args=...)
    at /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h:480
ROCm#12 0x000003ff369a512a in c10::callUnboxedKernelFunction<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> > (
    unboxed_kernel_func=0x3ff51ee51f0 <c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor const& (c10::DispatchKeySet, at::Tenso
r const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>), &torch::ADInplaceOrView::resize_>, at::Tensor const&, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::Ar
rayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> > >, at::Tensor const& (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::call(c10::OperatorKern
el*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>, functor=0x6030007dca40, dispatchKeySet=..., args=..., args=..., args=...)
    at /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:50
ROCm#13 0x000003ff369a6e90 in c10::KernelFunction::call<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> > (this=0x6210005e1bc8, opHandle=...,
    dispatchKeySet=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/boxing/KernelFunction_impl.h:90
ROCm#14 c10::Dispatcher::redispatch<at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat> >(c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::Arr
ayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)> const&, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const (
    this=0x3ff5d6400e0 <c10::Dispatcher::realSingleton()::_singleton>, op=..., currentDispatchKeySet=..., args=..., args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:656
ROCm#15 0x000003ff3652006c in c10::TypedOperatorHandle<at::Tensor const& (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)>::redispatch(c10::DispatchKeySet, at::Tensor const&,
c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>) const (
    this=0x3ff5d6a07e0 <at::_ops::resize_::redispatch(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::optional<c10::MemoryFormat>)::op>, currentDispatchKeySet=..., args=...,
    args=..., args=...) at /home/user/pytorch/aten/src/ATen/core/dispatch/Dispatcher.h:492
ROCm#16 at::_ops::resize_::redispatch (dispatchKeySet=..., self=..., size=..., memory_format=...) at /home/user/pytorch/build/aten/src/ATen/Operators_4.cpp:2144
ROCm#17 0x000003ff51ed5e08 in at::redispatch::resize__symint (dispatchKeySet=..., self=..., size=..., memory_format=...) at aten/src/ATen/RedispatchFunctions.h:2847
ROCm#18 0x000003ff51ebbb68 in torch::autograd::VariableType::(anonymous namespace)::resize_ (ks=..., self=..., size=..., optional_memory_format=...)
    at /home/user/pytorch/torch/csrc/autograd/VariableTypeManual.cpp:243
```
</details>
Pull Request resolved: pytorch#101064
Approved by: https://github.com/Skylion007, https://github.com/albanD

arguments() returns vector member of object returned by schema() call.
When object returned by schema() call is destroyed, the vector is deallocated as well,
it's lifetime isn't extended.

This issue detected while running `pytest -v test/mobile/test_lite_script_type.py -k test_nest_typing_namedtuple_custom_classtype` with ASAN.

<details>
<summary>ASAN output</summary>

```
==1134126==ERROR: AddressSanitizer: heap-use-after-free on address 0x60d0005a5790 at pc 0x03ff844488d8 bp 0x03fff584afe8 sp 0x03fff584afd8
READ of size 8 at 0x60d0005a5790 thread T0
    #0 0x3ff844488d7 in __gnu_cxx::__normal_iterator<c10::Argument const*, std::vector<c10::Argument, std::allocator<c10::Argument> > >::__normal_iterator(c10::Argument const* const&) /usr/lib/gcc/s390x-i
bm-linux-gnu/11/include/g++-v11/bits/stl_iterator.h:1028
    #1 0x3ff8444293f in std::vector<c10::Argument, std::allocator<c10::Argument> >::begin() const /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_vector.h:821
    #2 0x3ff84d807d1 in torch::jit::toPyObject(c10::IValue) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:617
    ROCm#3 0x3ff84d80305 in torch::jit::toPyObject(c10::IValue) /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:604
    ROCm#4 0x3ff84856871 in pybind11::detail::type_caster<c10::IValue, void>::cast(c10::IValue, pybind11::return_value_policy, pybind11::handle) /home/user/pytorch/torch/csrc/jit/python/pybind.h:138
    ROCm#5 0x3ff85318191 in pybind11::cpp_function::initialize<torch::jit::initJitScriptBindings(_object*)::$_45, c10::IValue, torch::jit::mobile::Module&, pybind11::tuple const&, pybind11::name, pybind11::is
_method, pybind11::sibling, pybind11::arg>(torch::jit::initJitScriptBindings(_object*)::$_45&&, c10::IValue (*)(torch::jit::mobile::Module&, pybind11::tuple const&), pybind11::name const&, pybind11::is_me
thod const&, pybind11::sibling const&, pybind11::arg const&)::{lambda(pybind11::detail::function_call&)#1}::operator()(pybind11::detail::function_call&) const /home/user/pytorch/cmake/../third_party/pybin
d11/include/pybind11/pybind11.h:249
    ROCm#6 0x3ff85317cfd in pybind11::cpp_function::initialize<torch::jit::initJitScriptBindings(_object*)::$_45, c10::IValue, torch::jit::mobile::Module&, pybind11::tuple const&, pybind11::name, pybind11::is
_method, pybind11::sibling, pybind11::arg>(torch::jit::initJitScriptBindings(_object*)::$_45&&, c10::IValue (*)(torch::jit::mobile::Module&, pybind11::tuple const&), pybind11::name const&, pybind11::is_me
thod const&, pybind11::sibling const&, pybind11::arg const&)::{lambda(pybind11::detail::function_call&)#1}::__invoke(pybind11::detail::function_call&) /home/user/pytorch/cmake/../third_party/pybind11/incl
ude/pybind11/pybind11.h:224
    ROCm#7 0x3ff82ee52e9 in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/cmake/../third_party/pybind11/include/pybind11/pybind11.h:929
    ROCm#8 0x3ffab002903 in cfunction_call Objects/methodobject.c:543
    ROCm#9 0x3ffaaf8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#10 0x3ffaaf8e919 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#11 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#12 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#13 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#14 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#15 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#16 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#17 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#18 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#19 0x3ffaaf8a615 in _PyObject_FastCallDictTstate Objects/call.c:142
    ROCm#20 0x3ffaaf8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#21 0x3ffab03f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#22 0x3ffaaf8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#23 0x3ffab0f0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#24 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#25 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#26 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#27 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#28 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#29 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#30 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#31 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#32 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#33 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#34 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#35 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#36 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#37 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#38 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#39 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#40 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#41 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#42 0x3ffab0ff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#43 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#44 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#45 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#46 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#47 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#48 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#49 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#50 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#51 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#52 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#53 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#54 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#55 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#56 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#57 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#58 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#59 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#60 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#61 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#62 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#63 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#64 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#65 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#66 0x3ffaaf8ab9b in PyVectorcall_Call Objects/call.c:267
    ROCm#67 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#68 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#69 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#70 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#71 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#72 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#73 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#74 0x3ffaaf8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#75 0x3ffaaf8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#76 0x3ffab03f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#77 0x3ffaaf8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#78 0x3ffab0f0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#79 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#80 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#81 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#82 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#83 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#84 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#85 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#86 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#87 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#88 0x3ffab0ff7d7 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#89 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#90 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#91 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#92 0x3ffaaf8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#93 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#94 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#95 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#96 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#97 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#98 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#99 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#100 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#101 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#102 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#103 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#104 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#105 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#106 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#107 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#108 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#109 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#110 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#111 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#112 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#113 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#114 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#115 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#116 0x3ffaaf8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#117 0x3ffaaf8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#118 0x3ffab03f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#119 0x3ffaaf8ad17 in _PyObject_Call Objects/call.c:305
    ROCm#120 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#121 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#122 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#123 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#124 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#125 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#126 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#127 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#128 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#129 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#130 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#131 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#132 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#133 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#134 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#135 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#136 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#137 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#138 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#139 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#140 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#141 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#142 0x3ffaaf8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#143 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#144 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#145 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#146 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#147 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#148 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#149 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#150 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#151 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#152 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#153 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#154 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#155 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#156 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#157 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#158 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#159 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#160 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#161 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#162 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#163 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#164 0x3ffaaf8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#165 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#166 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#167 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#168 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#169 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#170 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#171 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#172 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#173 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#174 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#175 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#176 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#177 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#178 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#179 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#180 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#181 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#182 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#183 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#184 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#185 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#186 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#187 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#188 0x3ffaaf8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#189 0x3ffaaf8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#190 0x3ffab03f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#191 0x3ffaaf8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#192 0x3ffab0f0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#193 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#194 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#195 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#196 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#197 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#198 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#199 0x3ffaaf8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#200 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290
    ROCm#201 0x3ffaaf8ada9 in PyObject_Call Objects/call.c:317
    ROCm#202 0x3ffab1059c7 in do_call_core Python/ceval.c:5943
    ROCm#203 0x3ffab0ffd39 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#204 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#205 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#206 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#207 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#208 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#209 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#210 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#211 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#212 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#213 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#214 0x3ffaaf8e941 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#215 0x3ffaaf8eddd in method_vectorcall Objects/classobject.c:53
    ROCm#216 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#216 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#217 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#218 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#219 0x3ffab0ff779 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#220 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#221 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#222 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#223 0x3ffaaf8a695 in _PyObject_FastCallDictTstate Objects/call.c:153
    ROCm#224 0x3ffaaf8b271 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#225 0x3ffab03f307 in slot_tp_call Objects/typeobject.c:7494
    ROCm#226 0x3ffaaf8a933 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#227 0x3ffab0f0081 in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#228 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#229 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#230 0x3ffab0ffa57 in _PyEval_EvalFrameDefault Python/ceval.c:4231
    ROCm#231 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#232 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#233 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#234 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#235 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#236 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#237 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#238 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#239 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#240 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#241 0x3ffab0f00a9 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#242 0x3ffab0f013d in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#243 0x3ffab105447 in call_function Python/ceval.c:5891
    ROCm#244 0x3ffab0ff905 in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#245 0x3ffab0f052b in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#246 0x3ffab102b67 in _PyEval_Vector Python/ceval.c:5065
    ROCm#247 0x3ffaaf8aec1 in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#248 0x3ffaaf8ab15 in PyVectorcall_Call Objects/call.c:255
    ROCm#249 0x3ffaaf8ac65 in _PyObject_Call Objects/call.c:290

0x60d0005a5790 is located 80 bytes inside of 136-byte region [0x60d0005a5740,0x60d0005a57c8)
freed by thread T0 here:
    #0 0x3ffab537de5 in operator delete(void*) /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:160
    #1 0x3ff55984fdb in __gnu_cxx::new_allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> >::deallocate(std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2>*, unsigned long) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/ext/new_allocator.h:145

previously allocated by thread T0 here:
    #0 0x3ffab53734f in operator new(unsigned long) /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:99
    #1 0x3ff5598443f in __gnu_cxx::new_allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> >::allocate(unsigned long, void const*) /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/ext/new_allocator.h:127
    #2 0x3fff5849ecf  ([stack]+0xb2ecf)

SUMMARY: AddressSanitizer: heap-use-after-free /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/stl_iterator.h:1028 in __gnu_cxx::__normal_iterator<c10::Argument const*, std::vector<c10::Argument, std::allocator<c10::Argument> > >::__normal_iterator(c10::Argument const* const&)
Shadow bytes around the buggy address:
  0x100c1a000b4aa0: fd fd fd fd fd fd fd fd fd fd fd fa fa fa fa fa
  0x100c1a000b4ab0: fa fa fa fa fd fd fd fd fd fd fd fd fd fd fd fd
  0x100c1a000b4ac0: fd fd fd fd fd fa fa fa fa fa fa fa fa fa fd fd
  0x100c1a000b4ad0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fa
  0x100c1a000b4ae0: fa fa fa fa fa fa fa fa fd fd fd fd fd fd fd fd
=>0x100c1a000b4af0: fd fd[fd]fd fd fd fd fd fd fa fa fa fa fa fa fa
  0x100c1a000b4b00: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x100c1a000b4b10: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x100c1a000b4b20: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x100c1a000b4b30: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
  0x100c1a000b4b40: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
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
==1134126==ABORTING
```

Additional backtraces (not full):
Allocation:
```
#0  __memset_z196 () at ../sysdeps/s390/memset-z900.S:144
#1  0x000003ff96f3072a in __asan::Allocator::Allocate (this=this@entry=0x3ff97041eb8 <__asan::instance>, size=size@entry=136, alignment=8, alignment@entry=0, stack=<optimized out>,
    stack@entry=0x3ffdbb45d78, alloc_type=<optimized out>, can_fill=true) at /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_allocator.cpp:599
#2  0x000003ff96f2c088 in __asan::asan_memalign (alignment=alignment@entry=0, size=size@entry=136, stack=stack@entry=0x3ffdbb45d78, alloc_type=alloc_type@entry=__asan::FROM_NEW)
    at /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_allocator.cpp:1039
ROCm#3  0x000003ff96fb73b0 in operator new (size=136) at /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:99
ROCm#4  0x000003ff41404440 in __gnu_cxx::new_allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> >::allocate (this=0x3ffdbb468c0,
    __n=1) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/ext/new_allocator.h:127
ROCm#5  0x000003ff414042a0 in std::allocator_traits<std::allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> > >::allocate (__a=...,
    __n=1) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/alloc_traits.h:464
ROCm#6  0x000003ff41403b66 in std::__allocate_guarded<std::allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> > > (__a=...)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/allocated_ptr.h:98
ROCm#7  0x000003ff4140372a in std::__shared_count<(__gnu_cxx::_Lock_policy)2>::__shared_count<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<c10::Argument, std::allocator<c10::Argument> >, std::vector<c10::Argument, std::allocator<c10::Argument> > > (this=0x3ffdbb47888, __p=@0x3ffdbb47880: 0x0, __a=..., __args=..., __args=..., __args=..., __args=...)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:648
ROCm#8  0x000003ff41403328 in std::__shared_ptr<c10::FunctionSchema, (__gnu_cxx::_Lock_policy)2>::__shared_ptr<std::allocator<c10::FunctionSchema>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<c10::Argument, std::allocator<c10::Argument> >, std::vector<c10::Argument, std::allocator<c10::Argument> > > (this=0x3ffdbb47880, __tag=..., __args=..., __args=..., __args=..., __args=...) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:1342
ROCm#9  0x000003ff41402f06 in std::shared_ptr<c10::FunctionSchema>::shared_ptr<std::allocator<c10::FunctionSchema>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<c10::Argument, std::allocator<c10::Argument> >, std::vector<c10::Argument, std::allocator<c10::Argument> > > (
    this=0x3ffdbb47880, __tag=..., __args=..., __args=..., __args=..., __args=...) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr.h:409
ROCm#10 0x000003ff41402b6e in std::allocate_shared<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<c10::Argument, std::allocator<c10::Argument> >, std::vector<c10::Argument, std::allocator<c10::Argument> > > (__a=...,
    __args=..., __args=..., __args=..., __args=...) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr.h:862
ROCm#11 0x000003ff4140215c in std::make_shared<c10::FunctionSchema, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::vector<c10::Argument, std::allocator<c10::Argument> >, std::vector<c10::Argument, std::allocator<c10::Argument> > > (__args=..., __args=..., __args=..., __args=...)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr.h:878
ROCm#12 0x000003ff413d180c in c10::TupleType::createWithSpec<c10::basic_string_view<char> > (qualName=..., field_names=std::vector of length 1, capacity 1 = {...},
    field_types=std::vector of length 1, capacity 1 = {...}, field_defaults=std::vector of length 0, capacity 0) at /home/user/pytorch/aten/src/ATen/core/type.cpp:769
ROCm#13 0x000003ff413b9ca6 in c10::TupleType::createNamed (qualName=..., field_names=std::vector of length 1, capacity 1 = {...}, field_types=std::vector of length 1, capacity 1 = {...})
    at /home/user/pytorch/aten/src/ATen/core/type.cpp:725
ROCm#14 0x000003ff4115fbac in c10::ivalue::TupleTypeFactory<c10::TupleType>::fallback (type=...) at /home/user/pytorch/aten/src/ATen/core/dynamic_type.cpp:383
ROCm#15 0x000003ff708217fe in c10::ivalue::Tuple::type<c10::TupleType> (this=0x6080004b8520) at /home/user/pytorch/aten/src/ATen/core/ivalue_inl.h:781
ROCm#16 0x000003ff70800740 in torch::jit::toPyObject (ivalue=...) at /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:613
ROCm#17 0x000003ff70800306 in torch::jit::toPyObject (ivalue=...) at /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:604
ROCm#18 0x000003ff702d6872 in pybind11::detail::type_caster<c10::IValue, void>::cast (src=...) at /home/user/pytorch/torch/csrc/jit/python/pybind.h:138
ROCm#19 0x000003ff70d98192 in pybind11::cpp_function::initialize<torch::jit::initJitScriptBindings(_object*)::$_45, c10::IValue, torch::jit::mobile::Module&, pybind11::tuple const&, pybind11::name, pybind11::is_method, pybind11::sibling, pybind11::arg>(torch::jit::initJitScriptBindings(_object*)::$_45&&, c10::IValue (*)(torch::jit::mobile::Module&, pybind11::tuple const&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&, pybind11::arg const&)::{lambda(pybind11::detail::function_call&)#1}::operator()(pybind11::detail::function_call&) const (this=0x3ffdbb4ca20, call=...)
    at /home/user/pytorch/cmake/../third_party/pybind11/include/pybind11/pybind11.h:249
ROCm#20 0x000003ff70d97cfe in pybind11::cpp_function::initialize<torch::jit::initJitScriptBindings(_object*)::$_45, c10::IValue, torch::jit::mobile::Module&, pybind11::tuple const&, pybind11::name, pybind11::is_method, pybind11::sibling, pybind11::arg>(torch::jit::initJitScriptBindings(_object*)::$_45&&, c10::IValue (*)(torch::jit::mobile::Module&, pybind11::tuple const&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&, pybind11::arg const&)::{lambda(pybind11::detail::function_call&)#1}::__invoke(pybind11::detail::function_call&) (call=...)
    at /home/user/pytorch/cmake/../third_party/pybind11/include/pybind11/pybind11.h:224
ROCm#21 0x000003ff6e9652ea in pybind11::cpp_function::dispatcher (self=<PyCapsule at remote 0x3ff83e27720>,
    args_in=(<torch._C.LiteScriptModule at remote 0x3ff811844b0>, (<Tensor at remote 0x3ff814efb00>,)), kwargs_in=0x0) at /home/user/pytorch/cmake/../third_party/pybind11/include/pybind11/pybind11.h:929
```

Deallocation:
```
#0  operator delete (ptr=0x60d0005a5740) at /var/tmp/portage/sys-devel/gcc-11.3.1_p20230303/work/gcc-11-20230303/libsanitizer/asan/asan_new_delete.cpp:160
#1  0x000003ff44904fdc in __gnu_cxx::new_allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> >::deallocate (this=0x3ffc5dc8020,
    __p=0x60d0005a5740, __t=1) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/ext/new_allocator.h:145
#2  0x000003ff44904fa8 in std::allocator_traits<std::allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> > >::deallocate (
    __a=..., __p=0x60d0005a5740, __n=1) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/alloc_traits.h:496
ROCm#3  0x000003ff449041f2 in std::__allocated_ptr<std::allocator<std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2> > >::~__allocated_ptr (
    this=0x3ffc5dc8030) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/allocated_ptr.h:74
ROCm#4  0x000003ff44904888 in std::_Sp_counted_ptr_inplace<c10::FunctionSchema, std::allocator<c10::FunctionSchema>, (__gnu_cxx::_Lock_policy)2>::_M_destroy (this=0x60d0005a5740)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:538
ROCm#5  0x000003ff43895a62 in std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release (this=0x60d0005a5740) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:184
ROCm#6  0x000003ff43895420 in std::__shared_count<(__gnu_cxx::_Lock_policy)2>::~__shared_count (this=0x611000c40648) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:705
ROCm#7  0x000003ff4466e7f4 in std::__shared_ptr<c10::FunctionSchema, (__gnu_cxx::_Lock_policy)2>::~__shared_ptr (this=0x611000c40640)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:1154
ROCm#8  0x000003ff4466d820 in std::shared_ptr<c10::FunctionSchema>::~shared_ptr (this=0x611000c40640) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr.h:122
ROCm#9  0x000003ff448d82f6 in c10::TupleType::~TupleType (this=0x611000c40580) at /home/user/pytorch/aten/src/ATen/core/jit_type.h:1142
ROCm#10 0x000003ff448d8346 in c10::TupleType::~TupleType (this=0x611000c40580) at /home/user/pytorch/aten/src/ATen/core/jit_type.h:1142
ROCm#11 0x000003ff731296a4 in std::_Sp_counted_ptr<c10::TupleType*, (__gnu_cxx::_Lock_policy)2>::_M_dispose (this=0x603000c43ae0)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:348
ROCm#12 0x000003ff71eaf666 in std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release (this=0x603000c43ae0) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:168
ROCm#13 0x000003ff71eaf330 in std::__shared_count<(__gnu_cxx::_Lock_policy)2>::~__shared_count (this=0x3ffc5dc9368) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:705
ROCm#14 0x000003ff73129ee4 in std::__shared_ptr<c10::TupleType, (__gnu_cxx::_Lock_policy)2>::~__shared_ptr (this=0x3ffc5dc9360)
    at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr_base.h:1154
ROCm#15 0x000003ff73122390 in std::shared_ptr<c10::TupleType>::~shared_ptr (this=0x3ffc5dc9360) at /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/shared_ptr.h:122
ROCm#16 0x000003ff73d00788 in torch::jit::toPyObject (ivalue=...) at /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:613
ROCm#17 0x000003ff73d00306 in torch::jit::toPyObject (ivalue=...) at /home/user/pytorch/torch/csrc/jit/python/pybind_utils.cpp:604
```
</details>
Pull Request resolved: pytorch#101400
Approved by: https://github.com/zou3519

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
    ROCm#1 0x3ff6704e95f in rempif /home/user/pytorch/third_party/sleef/src/libm/sleefsimdsp.c:550
    ROCm#2 0x3ff6704e95f in Sleef_cosf4_u10vxe2 /home/user/pytorch/third_party/sleef/src/libm/sleefsimdsp.c:1021
    ROCm#3 0x3ff67029cfb in Sleef_cosf4_u10 /home/user/pytorch/build/sleef/src/libm/disps390x_128.c:182
    ROCm#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
    ROCm#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
    ROCm#6 0x3ff5685df97 in at::vml::ZVECTOR::vcos<float>(float*, float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)ROCm#1}::operator()(at::vec::ZVECTOR::Vectorized<float, void>) const /home/
user/pytorch/aten/src/ATen/cpu/vml.h:71
    ROCm#7 0x3ff5689b691 in void at::vec::map<float, at::vml::ZVECTOR::vcos<float>(float*, float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)ROCm#1}, 0>(at::vml::ZVECTOR::vcos<float>(float*,
float const*, long)::{lambda(at::vec::ZVECTOR::Vectorized<float, void>)ROCm#1} const&, float*, float const*, long) /home/user/pytorch/aten/src/ATen/cpu/vec/functional_base.h:239
    ROCm#8 0x3ff5685e0df in void at::vml::ZVECTOR::vcos<float>(float*, float const*, long) /home/user/pytorch/aten/src/ATen/cpu/vml.h:71
    ROCm#9 0x3ff563fdde3 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770
    ROCm#10 0x3ff5648e4a3 in operator() /home/user/pytorch/aten/src/ATen/TensorIterator.h:406
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#17 0x3ff563fe5f9 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770
    ROCm#18 0x3ff56400915 in operator() /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770
    ROCm#19 0x3ff56400f1d in at::native::ZVECTOR::cos_kernel(at::TensorIteratorBase&) /home/user/pytorch/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp:770
    ROCm#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
    ROCm#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
    ROCm#22 0x3ff526ef739 in wrapper_CPU_cos /home/user/pytorch/build/aten/src/ATen/RegisterCPU.cpp:4307
    ROCm#23 0x3ff52c651d9 in operator() /home/user/pytorch/aten/src/ATen/core/boxing/impl/WrapFunctionIntoFunctor.h:13
    ROCm#24 0x3ff52c651d9 in call /home/user/pytorch/aten/src/ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h:463
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#29 0x3ff5009a93f in at::_ops::cos::call(at::Tensor const&) /home/user/pytorch/build/aten/src/ATen/Operators_0.cpp:2215
    ROCm#30 0x3ff7d813741 in at::Tensor::cos() const /home/user/pytorch/build/aten/src/ATen/core/TensorBody.h:2107
    ROCm#31 0x3ff7dc0f2b7 in operator() /home/user/pytorch/torch/csrc/autograd/generated/python_torch_functions_2.cpp:2953
    ROCm#32 0x3ff7dc0faf7 in THPVariable_cos /home/user/pytorch/torch/csrc/autograd/generated/python_torch_functions_2.cpp:2955
    ROCm#33 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543
    ROCm#34 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#35 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#36 0x3ffa5feb50d in do_call_core Python/ceval.c:5915
    ROCm#37 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#38 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#39 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#40 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#41 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#42 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#43 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#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
    ROCm#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> >*)ROCm#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
    ROCm#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> >*)ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#52 0x3ff65a05641 in operator() /home/user/pytorch/torch/csrc/jit/runtime/register_c10_ops.cpp:15
    ROCm#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
    ROCm#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
    ROCm#55 0x3ff65a084e1 in _M_invoke /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/std_function.h:290
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#60 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549
    ROCm#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
    ROCm#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
    ROCm#63 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249
    ROCm#64 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224
    ROCm#65 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929
    ROCm#66 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543
    ROCm#67 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#68 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#69 0x3ffa5feb50d in do_call_core Python/ceval.c:5915
    ROCm#70 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#71 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#72 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#73 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#74 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142
    ROCm#75 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#76 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494
    ROCm#77 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#78 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#79 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#80 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#81 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#82 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#83 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#84 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#85 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#86 0x3ffa5feb289 in call_function Python/ceval.c:5891
    ROCm#87 0x3ffa5fe5c3b in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#88 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#89 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#90 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#91 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#92 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#93 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#94 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#95 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#96 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#97 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#98 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#99 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#100 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#101 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#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
    ROCm#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> >*)ROCm#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
    ROCm#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> >*)ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#110 0x3ff65a05641 in operator() /home/user/pytorch/torch/csrc/jit/runtime/register_c10_ops.cpp:15
    ROCm#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
    ROCm#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
    ROCm#113 0x3ff65a084e1 in _M_invoke /usr/lib/gcc/s390x-ibm-linux-gnu/11/include/g++-v11/bits/std_function.h:290
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#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
    ROCm#118 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549
    ROCm#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
    ROCm#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
    ROCm#121 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249
    ROCm#122 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224
    ROCm#123 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929
    ROCm#124 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543
    ROCm#125 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#126 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#127 0x3ffa5feb50d in do_call_core Python/ceval.c:5915
    ROCm#128 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#129 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#130 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#131 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#132 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142
    ROCm#133 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#134 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494
    ROCm#135 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#136 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#137 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#138 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#139 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#140 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#141 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#142 0x3ffa5e87d2b in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#143 0x3ffa5e882dd in method_vectorcall Objects/classobject.c:83
    ROCm#144 0x3ffa5e836d3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#145 0x3ffa5e84b6f in _PyObject_CallFunctionVa Objects/call.c:485
    ROCm#146 0x3ffa5e84f2d in callmethod Objects/call.c:557
    ROCm#147 0x3ffa5e85039 in PyObject_CallMethod Objects/call.c:577
    ROCm#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
    ROCm#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
    ROCm#150 0x3ff7e573eb9 in operator() /home/user/pytorch/torch/csrc/jit/python/init.cpp:1549
    ROCm#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
    ROCm#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
    ROCm#153 0x3ff7e5da259 in operator() /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:249
    ROCm#154 0x3ff7e5da441 in _FUN /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:224
    ROCm#155 0x3ff7d317a1f in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) /home/user/pytorch/third_party/pybind11/include/pybind11/pybind11.h:929
    ROCm#156 0x3ffa5ef5ae1 in cfunction_call Objects/methodobject.c:543
    ROCm#157 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#158 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#159 0x3ffa5feb50d in do_call_core Python/ceval.c:5915
    ROCm#160 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#161 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#162 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#163 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#164 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142
    ROCm#165 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#166 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494
    ROCm#167 0x3ffa5e84027 in _PyObject_MakeTpCall Objects/call.c:215
    ROCm#168 0x3ffa5fd767b in _PyObject_VectorcallTstate Include/cpython/abstract.h:112
    ROCm#169 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#170 0x3ffa5feb289 in call_function Python/ceval.c:5891
    ROCm#171 0x3ffa5fe5ad1 in _PyEval_EvalFrameDefault Python/ceval.c:4181
    ROCm#172 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#173 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#174 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#175 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#176 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#177 0x3ffa5feb289 in call_function Python/ceval.c:5891
    ROCm#178 0x3ffa5fe5c3b in _PyEval_EvalFrameDefault Python/ceval.c:4213
    ROCm#179 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#180 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#181 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#182 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267
    ROCm#183 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#184 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#185 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#186 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#187 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#188 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#189 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#190 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#191 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#192 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#193 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#194 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#195 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#196 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#197 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#198 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#199 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#200 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#201 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#202 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#203 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#204 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#205 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#206 0x3ffa5e841fb in PyVectorcall_Call Objects/call.c:255
    ROCm#207 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#208 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#209 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#210 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#211 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#212 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#213 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#214 0x3ffa5e83d1f in _PyObject_FastCallDictTstate Objects/call.c:142
    ROCm#215 0x3ffa5e84937 in _PyObject_Call_Prepend Objects/call.c:431
    ROCm#216 0x3ffa5f2f577 in slot_tp_call Objects/typeobject.c:7494
    ROCm#217 0x3ffa5e843f3 in _PyObject_Call Objects/call.c:305
    ROCm#218 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#219 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#220 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#221 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#222 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#223 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#224 0x3ffa5fd76a3 in _PyObject_VectorcallTstate Include/cpython/abstract.h:114
    ROCm#225 0x3ffa5fd772f in PyObject_Vectorcall Include/cpython/abstract.h:123
    ROCm#226 0x3ffa5feb289 in call_function Python/ceval.c:5891
    ROCm#227 0x3ffa5fe5b21 in _PyEval_EvalFrameDefault Python/ceval.c:4198
    ROCm#228 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#229 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#230 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#231 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267
    ROCm#232 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#233 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#234 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#235 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#236 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#237 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#238 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#239 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267
    ROCm#240 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#241 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#242 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#243 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#244 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#245 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#246 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#247 0x3ffa5e8427f in PyVectorcall_Call Objects/call.c:267
    ROCm#248 0x3ffa5e84347 in _PyObject_Call Objects/call.c:290
    ROCm#249 0x3ffa5e84483 in PyObject_Call Objects/call.c:317
    ROCm#250 0x3ffa5feb7cf in do_call_core Python/ceval.c:5943
    ROCm#251 0x3ffa5fe6019 in _PyEval_EvalFrameDefault Python/ceval.c:4277
    ROCm#252 0x3ffa5fd7aed in _PyEval_EvalFrame Include/internal/pycore_ceval.h:46
    ROCm#253 0x3ffa5fe8ba9 in _PyEval_Vector Python/ceval.c:5065
    ROCm#254 0x3ffa5e8459b in _PyFunction_Vectorcall Objects/call.c:342
    ROCm#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

…rch#165479)

These happen when building with CMAKE_BUILD_TYPE=RelWithAssert

This should fix two types of failures that started with pytorch#163665

Disclaimer that I used a lot of AI since I don't how pybind works or what refcounts and pointers are, so idk if this is a good solution, or even a solution at all (fwiw the tests pass now)

The first one type is

Truncated:
```
    default_pg, _ = _new_process_group_helper(
  File "/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 2096, in _new_process_group_helper
    backend_class = creator_fn(dist_backend_opts, backend_options)
  File "/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/testing/_internal/distributed/fake_pg.py", line 25, in _create_fake_pg
    return FakeProcessGroup._create_internal(
RuntimeError: new_refcount != 1 INTERNAL ASSERT FAILED at "/var/lib/jenkins/workspace/c10/util/intrusive_ptr.h":319, please report a bug to PyTorch. intrusive_ptr: Cannot increase refcount after it reached zero.
Exception raised from retain_ at /var/lib/jenkins/workspace/c10/util/intrusive_ptr.h:319 (most recent call first):
C++ CapturedTraceback:
#4 std::_Function_handler<std::shared_ptr<c10::LazyValue<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > const> (), c10::SetStackTraceFetcher(std::function<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > ()>)::{lambda()#1}>::_M_invoke(std::_Any_data const&) from Logging.cpp:0
#5 c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) from ??:0
#6 c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) from ??:0
#7 c10::detail::torchInternalAssertFail(char const*, char const*, unsigned int, char const*, char const*) from ??:0
#8 void pybind11::class_<c10d::FakeProcessGroup, (anonymous namespace)::IntrusivePtrNoGilDestructor<c10d::FakeProcessGroup> >::init_instance<(anonymous namespace)::IntrusivePtrNoGilDestructor<c10d::FakeProcessGroup>, 0>(pybind11::detail::instance*, void const*) from init.cpp:0
#9 pybind11::detail::type_caster_generic::cast(void const*, pybind11::return_value_policy, pybind11::handle, pybind11::detail::type_info const*, void* (*)(void const*), void* (*)(void const*), void const*) from :0
#10 pybind11::cpp_function::initialize<torch::distributed::c10d::(anonymous namespace)::c10d_init(_object*, _object*)::{lambda(int, int, c10::intrusive_ptr<c10d::FakeProcessGroup::Options, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup::Options> >)#127}, c10::intrusive_ptr<c10d::FakeProcessGroup, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup> >, int, int, c10::intrusive_ptr<c10d::FakeProcessGroup::Options, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup::Options> >, pybind11::name, pybind11::scope, pybind11::sibling, pybind11::arg, pybind11::arg, pybind11::arg_v>(torch::distributed::c10d::(anonymous namespace)::c10d_init(_object*, _object*)::{lambda(int, int, c10::intrusive_ptr<c10d::FakeProcessGroup::Options, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup::Options> >)#127}&&, c10::intrusive_ptr<c10d::FakeProcessGroup, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup> > (*)(int, int, c10::intrusive_ptr<c10d::FakeProcessGroup::Options, c10::detail::intrusive_target_default_null_type<c10d::FakeProcessGroup::Options> >), pybind11::name const&, pybind11::scope const&, pybind11::sibling const&, pybind11::arg const&, pybind11::arg const&, pybind11::arg_v const&)::{lambda(pybind11::detail::function_call&)#3}::_FUN(pybind11::detail::function_call&) from init.cpp:0
```
and I fix it here by getting rid of `DontIncreaseRefcount` and using make_intrusive to do the ref count handling instead.  However, I also had to move the constructor to be public, which I think is not good, based on the reasoning of the original PR

The other one type is
```
Traceback (most recent call last):
  File "/var/lib/jenkins/workspace/test/test_testing.py", line 2415, in test_no_warning_on_import
    self.assertEqual(out, "")
  File "/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/testing/_internal/common_utils.py", line 4233, in assertEqual
    raise error_metas.pop()[0].to_error(  # type: ignore[index]
AssertionError: String comparison failed: "/opt/conda/envs/py_3.10/lib/python3.10/s[352 chars]):\n" != ''
- /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/distributed/__init__.py:29: FutureWarning: pybind11-bound class 'torch._C._distributed_c10d.FakeProcessGroup' is using an old-style placement-new '__init__' which has been deprecated. See the upgrade guide in pybind11's docs. This message is only visible when compiled in debug mode.
-   if is_available() and not torch._C._c10d_init():

To execute this test, run the following from the base repo dir:
    python test/test_testing.py TestImports.test_no_warning_on_import
```
which I fix by getting rid of the `__init__` which I think is ok since it'll just error if you try to make one?

Pull Request resolved: pytorch#165479
Approved by: https://github.com/ezyang