Use uint64_t index types to avoid
```
 torch_np/numpy_tests/core/test_einsum.py::TestEinsum::test_einsum_broadcast /var/lib/jenkins/workspace/aten/src/ATen/native/cpu/BlasKernel.cpp:132:24: runtime error: signed integer overflow: 9223365439786057728 + 13194139533312 cannot be represented in type 'long'
    #0 0x7f30d26166ba in std::enable_if<std::is_same_v<long, long>, void>::type at::native::cpublas::(anonymous namespace)::gemm_notrans_<long, long, long>(long, long, long, long, long const*, long, long const*, long, long, long*, long) /var/lib/jenkins/workspace/aten/src/ATen/native/cpu/BlasKernel.cpp:132:24
    #1 0x7f30d26166ba in void at::native::cpublas::(anonymous namespace)::gemm_core_<long, long, long>(at::native::TransposeType, at::native::TransposeType, long, long, long, long, long const*, long, long const*, long, long, long*, long) /var/lib/jenkins/workspace/aten/src/ATen/native/cpu/BlasKernel.cpp:451:12
    #2 0x7f30d25fba1b in at::native::cpublas::(anonymous namespace)::cpublas_gemm_impl(c10::ScalarType, at::native::TransposeType, at::native::TransposeType, long, long, long, c10::Scalar const&, void const*, long, void const*, long, c10::Scalar const&, void*, long)::$_2::operator()() const::'lambda2'()::operator()() const /var/lib/jenkins/workspace/aten/src/ATen/native/cpu/BlasKernel.cpp:485:3
    #3 0x7f30d25fba1b in at::native::cpublas::(anonymous namespace)::cpublas_gemm_impl(c10::ScalarType, at::native::TransposeType, at::native::TransposeType, long, long, long, c10::Scalar const&, void const*, long, void const*, long, c10::Scalar const&, void*, long)::$_2::operator()() const /var/lib/jenkins/workspace/aten/src/ATen/native/cpu/BlasKernel.cpp:485:3
```

Pull Request resolved: pytorch#154809
Approved by: https://github.com/soulitzer

…5603)

Example new error message

```
torch.fx.experimental.symbolic_shapes.ConstraintViolationError: Constraints violated (L['x'].size()[0])! For more information, run with TORCH_LOGS="+dynamic".
  - You marked L['x'].size()[0] as dynamic but your code specialized it to be a constant (5). Either remove the mark_dynamic or use a less strict API such as maybe_mark_dynamic or Dim.AUTO.

Framework stack:
  File "??", line 0, in _start
  File "", line 0, in __libc_start_main_alias_2
  File "??", line 0, in __libc_start_call_main
  File "/usr/local/src/conda/python-3.10.16/Modules/main.c", line 1094, in Py_BytesMain
  File "/usr/local/src/conda/python-3.10.16/Modules/main.c", line 357, in pymain_run_file_obj
  File "/usr/local/src/conda/python-3.10.16/Python/pythonrun.c", line 90, in _PyRun_AnyFileObject
  File "/usr/local/src/conda/python-3.10.16/Python/pythonrun.c", line 456, in _PyRun_SimpleFileObject
  File "/usr/local/src/conda/python-3.10.16/Python/pythonrun.c", line 1208, in pyrun_file
  File "/usr/local/src/conda/python-3.10.16/Python/pythonrun.c", line 1312, in run_mod
  File "/usr/local/src/conda/python-3.10.16/Python/pythonrun.c", line 1291, in run_eval_code_obj
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 1134, in PyEval_EvalCode
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/scratch/repro.py", line 9, in <module>
    foo(x)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/eval_frame.py", line 699, in compile_wrapper
    return fn(*args, **kwargs)
  File "offloadstuff.c", line 0, in dynamo__custom_eval_frame
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 305, in _PyObject_Call
  File "/usr/local/src/conda/python-3.10.16/Objects/typeobject.c", line 7494, in slot_tp_call
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 431, in _PyObject_Call_Prepend
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 1469, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Objects/typeobject.c", line 7494, in slot_tp_call
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 431, in _PyObject_Call_Prepend
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 153, in _PyObject_FastCallDictTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 1248, in __call__
    result = self._inner_convert(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Objects/typeobject.c", line 7494, in slot_tp_call
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 431, in _PyObject_Call_Prepend
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 153, in _PyObject_FastCallDictTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 625, in __call__
    return _compile(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 1092, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_utils_internal.py", line 97, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 779, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 818, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/bytecode_transformation.py", line 1424, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 265, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/convert_frame.py", line 743, in transform
    tracer.run()
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/symbolic_convert.py", line 3531, in run
    super().run()
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/symbolic_convert.py", line 1359, in run
    while self.step():
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/symbolic_convert.py", line 1263, in step
    self.dispatch_table[inst.opcode](self, inst)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/symbolic_convert.py", line 422, in impl
    self.push(fn_var.call_function(self, self.popn(nargs), {}))
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builtin.py", line 1160, in call_function
    return handler(tx, args, kwargs)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builtin.py", line 792, in <lambda>
    return lambda tx, args, kwargs: obj.call_function(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builtin.py", line 1160, in call_function
    return handler(tx, args, kwargs)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builtin.py", line 1120, in _handle_insert_op_in_graph
    return wrap_fx_proxy(tx, proxy)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builder.py", line 2500, in wrap_fx_proxy
    return wrap_fx_proxy_cls(target_cls=TensorVariable, **kwargs)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 267, in PyVectorcall_Call
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builder.py", line 2566, in wrap_fx_proxy_cls
    return _wrap_fx_proxy(
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/variables/builder.py", line 2664, in _wrap_fx_proxy
    example_value = get_fake_value(proxy.node, tx, allow_non_graph_fake=True)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/utils.py", line 3205, in get_fake_value
    ret_val = wrap_fake_exception(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/utils.py", line 2705, in wrap_fake_exception
    return fn()
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/utils.py", line 3206, in <lambda>
    lambda: run_node(tx.output, node, args, kwargs, nnmodule)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_dynamo/utils.py", line 3373, in run_node
    return node.target(*args, **kwargs)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5917, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Objects/methodobject.c", line 430, in cfunction_vectorcall_FASTCALL
  File "/usr/local/src/conda/python-3.10.16/Objects/abstract.c", line 891, in binary_op1
  File "/usr/local/src/conda/python-3.10.16/Objects/typeobject.c", line 7284, in slot_nb_multiply
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/descrobject.c", line 344, in method_vectorcall_VARARGS_KEYWORDS
  File "python_variable_methods.cpp", line 0, in _object* torch::autograd::TypeError_to_NotImplemented_<&torch::autograd::THPVariable_mul>(_object*, _object*, _object*)
  File "python_variable_methods.cpp", line 0, in torch::autograd::THPVariable_mul(_object*, _object*, _object*)
  File "??", line 0, in at::_ops::mul_Tensor::call(at::Tensor const&, at::Tensor const&)
  File "offloadstuff.c", line 0, in c10::impl::BoxedKernelWrapper<at::Tensor (at::Tensor const&, at::Tensor const&), void>::call(c10::BoxedKernel const&, c10::OperatorHandle const&, c10::DispatchKeySet, at::Tensor const&, at::Tensor const&)
  File "PyInterpreter.cpp", line 0, in torch::detail::(anonymous namespace)::ConcretePyInterpreterVTable::python_dispatcher(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const
  File "offloadstuff.c", line 0, in c10::OperatorHandle::callBoxedForDispatchKey(c10::DispatchKey, std::vector<c10::IValue, std::allocator<c10::IValue> >&) const
  File "PythonFallbackKernel.cpp", line 0, in void c10::BoxedKernel::make_boxed_function<&(anonymous namespace)::pythonTLSSnapshotFallback>(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)
  File "PyInterpreter.cpp", line 0, in torch::detail::(anonymous namespace)::ConcretePyInterpreterVTable::python_dispatcher(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const
  File "offloadstuff.c", line 0, in c10::OperatorHandle::callBoxedForDispatchKey(c10::DispatchKey, std::vector<c10::IValue, std::allocator<c10::IValue> >&) const
  File "VariableType_0.cpp", line 0, in c10::impl::make_boxed_from_unboxed_functor<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor (c10::DispatchKeySet, at::Tensor const&, at::Tensor const&), &torch::autograd::VariableType::(anonymous namespace)::mul_Tensor>, at::Tensor, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, at::Tensor const&> >, false>::call(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)
  File "VariableType_0.cpp", line 0, in torch::autograd::VariableType::(anonymous namespace)::mul_Tensor(c10::DispatchKeySet, at::Tensor const&, at::Tensor const&)
  File "??", line 0, in at::_ops::mul_Tensor::redispatch(c10::DispatchKeySet, at::Tensor const&, at::Tensor const&)
  File "offloadstuff.c", line 0, in c10::impl::BoxedKernelWrapper<at::Tensor (at::Tensor const&, at::Tensor const&), void>::call(c10::BoxedKernel const&, c10::OperatorHandle const&, c10::DispatchKeySet, at::Tensor const&, at::Tensor const&)
  File "PyInterpreter.cpp", line 0, in torch::detail::(anonymous namespace)::ConcretePyInterpreterVTable::python_dispatcher(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const
  File "offloadstuff.c", line 0, in c10::OperatorHandle::callBoxedForDispatchKey(c10::DispatchKey, std::vector<c10::IValue, std::allocator<c10::IValue> >&) const
  File "PythonFallbackKernel.cpp", line 0, in (anonymous namespace)::pythonFallback(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*)
  File "PyInterpreter.cpp", line 0, in torch::detail::(anonymous namespace)::ConcretePyInterpreterVTable::dispatch(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*) const
  File "??", line 0, in torch::handle_torch_function_no_python_arg_parser(c10::ArrayRef<_object*>, _object*, _object*, char const*, _object*, char const*, torch::TorchFunctionName)
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 577, in PyObject_CallMethod
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/utils/_stats.py", line 27, in wrapper
    return fn(*args, **kwargs)
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_tensor.py", line 1346, in __torch_dispatch__
    return self.dispatch(func, types, args, kwargs)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_tensor.py", line 2029, in dispatch
    return self._cached_dispatch_impl(func, types, args, kwargs)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_tensor.py", line 1442, in _cached_dispatch_impl
    return self._dispatch_impl(func, types, args, kwargs)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_tensor.py", line 2552, in _dispatch_impl
    return maybe_propagate_real_tensors(fast_impl(self, *args, **kwargs))
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_impls.py", line 956, in fast_binary_impl
    final_shape = infer_size(final_shape, shape)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/_subclasses/fake_impls.py", line 916, in infer_size
    torch._check(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/__init__.py", line 1669, in _check
    _check_with(RuntimeError, cond, message)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/__init__.py", line 1632, in _check_with
    if expect_true(cond):
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 1686, in expect_true
    return a.node.expect_true(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/sym_node.py", line 552, in expect_true
    return self.guard_bool(file, line)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/sym_node.py", line 536, in guard_bool
    r = self.evaluate()
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/sym_node.py", line 510, in evaluate
    return self.shape_env.evaluate_sym_node(self, size_oblivious)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 7113, in evaluate_sym_node
    return self.evaluate_expr(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Modules/_functoolsmodule.c", line 1020, in bounded_lru_cache_wrapper
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 267, in PyVectorcall_Call
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/recording.py", line 272, in wrapper
    return retlog(fn(*args, **kwargs))
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 267, in PyVectorcall_Call
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 7215, in evaluate_expr
    return self._inner_evaluate_expr(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Modules/_functoolsmodule.c", line 1020, in bounded_lru_cache_wrapper
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/recording.py", line 272, in wrapper
    return retlog(fn(*args, **kwargs))
  File "/usr/local/src/conda/python-3.10.16/Python/ceval.c", line 5945, in do_call_core
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 7238, in _inner_evaluate_expr
    return self._evaluate_expr(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 7505, in _evaluate_expr
    self._maybe_guard_rel(g)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Modules/_functoolsmodule.c", line 1020, in bounded_lru_cache_wrapper
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 6758, in _maybe_guard_rel
    self._refine_ranges(expr)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 7709, in _refine_ranges
    self._set_replacement(
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/fx/experimental/symbolic_shapes.py", line 6667, in _set_replacement
    self.framework_specialization_stacks[source] = CapturedTraceback.extract(cpp=True)
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 114, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Include/internal/pycore_ceval.h", line 46, in _PyEval_EvalFrame
  File "/home/bobren/local/a/pytorch/torch/utils/_traceback.py", line 207, in extract
    torch._C._profiler.gather_traceback(python=True, script=script, cpp=cpp),
  File "/usr/local/src/conda/python-3.10.16/Include/cpython/abstract.h", line 112, in _PyObject_VectorcallTstate
  File "/usr/local/src/conda/python-3.10.16/Objects/call.c", line 215, in _PyObject_MakeTpCall
  File "/usr/local/src/conda/python-3.10.16/Objects/methodobject.c", line 543, in cfunction_call
  File "offloadstuff.c", line 0, in pybind11::cpp_function::dispatcher(_object*, _object*, _object*)
  File "offloadstuff.c", line 0, in pybind11::cpp_function::initialize<std::shared_ptr<torch::CapturedTraceback> (*&)(bool, bool, bool), std::shared_ptr<torch::CapturedTraceback>, bool, bool, bool, pybind11::name, pybind11::scope, pybind11::sibling, pybind11::arg_v, pybind11::arg_v, pybind11::arg_v>(std::shared_ptr<torch::CapturedTraceback> (*&)(bool, bool, bool), std::shared_ptr<torch::CapturedTraceback> (*)(bool, bool, bool), pybind11::name const&, pybind11::scope const&, pybind11::sibling const&, pybind11::arg_v const&, pybind11::arg_v const&, pybind11::arg_v const&)::{lambda(pybind11::detail::function_call&)#3}::_FUN(pybind11::detail::function_call&)
  File "??", line 0, in torch::CapturedTraceback::gather(bool, bool, bool)
  File "??", line 0, in torch::unwind::unwind()

User stack:
  File "/home/bobren/local/a/pytorch/scratch/repro.py", line 5, in foo
    return torch.randn(5) * x
```

Pull Request resolved: pytorch#155603
Approved by: https://github.com/zou3519, https://github.com/cyyever
ghstack dependencies: pytorch#155133

For tensor with non-zero offset, it must be multiplied by element size

Add regression test by creating Tensor in array of 6 elements with offset 3, which before the fix crashed with
```
C++ exception with description "setStorage: sizes [3, 3], strides [0, 1], storage offset 3, and itemsize 4 requiring a storage size of 24 are out of bounds for storage of size 15
Exception raised from checkInBoundsForStorage at /Users/nshulga/git/pytorch/pytorch/aten/src/ATen/native/Resize.h:123 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>) + 56 (0x104a9cd44 in libc10.dylib)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) + 120 (0x104a9a05c in libc10.dylib)
frame #2: void at::native::checkInBoundsForStorage<long long>(c10::ArrayRef<long long>, c10::ArrayRef<long long>, long long, caffe2::TypeMeta const&, c10::Storage const&) + 656 (0x111dbd314 in libtorch_cpu.dylib)
frame #3: void at::native::setStrided<long long>(at::Tensor const&, c10::ArrayRef<long long>, c10::ArrayRef<long long>, long long) + 152 (0x111dcd22c in libtorch_cpu.dylib)
frame #4: at::native::as_strided_tensorimpl(at::Tensor const&, c10::ArrayRef<long long>, c10::ArrayRef<long long>, std::__1::optional<long long>) + 312 (0x111dccf98 in libtorch_cpu.dylib)
frame pytorch#5: c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>), &at::(anonymous namespace)::(anonymous namespace)::wrapper_CPU__as_strided(at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>)>, at::Tensor, c10::guts::typelist::typelist<at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>>>, at::Tensor (at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>) + 104 (0x1129a1e94 in libtorch_cpu.dylib)
frame pytorch#6: at::_ops::as_strided::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, std::__1::optional<c10::SymInt>) + 476 (0x112200ad0 in libtorch_cpu.dylib)
frame pytorch#7: at::Tensor::as_strided(c10::ArrayRef<long long>, c10::ArrayRef<long long>, std::__1::optional<long long>) const + 236 (0x1115db098 in libtorch_cpu.dylib)
frame pytorch#8: at::native::expand(at::Tensor const&, c10::ArrayRef<long long>, bool) + 348 (0x111dcc0d4 in libtorch_cpu.dylib)
frame pytorch#9: c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool), &torch::ADInplaceOrView::(anonymous namespace)::expand(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool)>, at::Tensor, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool>>, at::Tensor (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool) + 116 (0x1157ac410 in libtorch_cpu.dylib)
frame pytorch#10: c10::impl::wrap_kernel_functor_unboxed_<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool), &torch::autograd::VariableType::(anonymous namespace)::expand(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool)>, at::Tensor, c10::guts::typelist::typelist<c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool>>, at::Tensor (c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool)>::call(c10::OperatorKernel*, c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool) + 992 (0x114e8b010 in libtorch_cpu.dylib)
frame pytorch#11: at::_ops::expand::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>, bool) + 316 (0x112743c90 in libtorch_cpu.dylib)
frame pytorch#12: at::expand_size(at::Tensor const&, c10::ArrayRef<long long>) + 164 (0x1047d82b4 in basic)
frame pytorch#13: BasicTest_TestForBlobResizeCPU_Test::TestBody() + 284 (0x1047d8048 in basic)
```
Pull Request resolved: pytorch#158690
Approved by: https://github.com/angelayi