unittests/test_adaptive_avg_pool2d_backward.py failed if diopiAdaptiveAvgPool2dBackward() not implement in GPU.

[Aaron20000101]

::diopiLayerNormBackward is not yet implemented, native_layer_norm_backward will be fallback to cpu
::diopiLayerNormBackward is not yet implemented, native_layer_norm_backward.out will be fallback to cpu
::diopiAdaptiveAvgPool2d is not yet implemented, adaptive_avg_pool2d.out will be fallback to cpu
::diopiAdaptiveAvgPool2d is not yet implemented, _adaptive_avg_pool2d will be fallback to cpu
::diopiAdaptiveAvgPool2dBackward is not yet implemented, _adaptive_avg_pool2d_backward will be fallback to cpu
::diopiAvgPool2d is not yet implemented, avg_pool2d.out will be fallback to cpu
....
::diopiAmpForeachNonFiniteCheckAndUnscaleInp is not yet implemented, _amp_foreach_non_finite_check_and_unscale_ will be fallback to cpu
::diopiAmpUpdateScaleInp is not yet implemented, _amp_update_scale_ will be fallback to cpu
::diopiConvTranspose2d is not yet implemented, conv_transpose2d.input will be fallback to cpu
test_adaptiveAvgPool2d_backward_1 (test_adaptive_avg_pool2d_backward.TestAdaptiveAvgPool2dBackward) ... fallback to cpu, name=aten::_adaptive_avg_pool2d
ok
test_adaptiveAvgPool2d_backward_2 (test_adaptive_avg_pool2d_backward.TestAdaptiveAvgPool2dBackward) ... ok
test_adaptiveAvgPool2d_backward_fp16 (test_adaptive_avg_pool2d_backward.TestAdaptiveAvgPool2dBackward) ... ERROR

======================================================================
ERROR: test_adaptiveAvgPool2d_backward_fp16 (test_adaptive_avg_pool2d_backward.TestAdaptiveAvgPool2dBackward)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/jenkins/host/github/deeplink.framework/dipu/tests/python/unittests/test_adaptive_avg_pool2d_backward.py", line 52, in test_adaptiveAvgPool2d_backward_fp16
    dipu_output = self._dipu_op_exec(dipu_input, output_size)
  File "/home/jenkins/host/github/deeplink.framework/dipu/tests/python/unittests/test_adaptive_avg_pool2d_backward.py", line 23, in _dipu_op_exec
    output = m(input_x)
  File "/home/jenkins/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/jenkins/.local/lib/python3.8/site-packages/torch/nn/modules/pooling.py", line 1196, in forward
    return F.adaptive_avg_pool2d(input, self.output_size)
  File "/home/jenkins/.local/lib/python3.8/site-packages/torch/nn/functional.py", line 1214, in adaptive_avg_pool2d
    return torch._C._nn.adaptive_avg_pool2d(input, _output_size)
RuntimeError: "adaptive_avg_pool2d" not implemented for 'Half'
Exception raised from operator() at /pytorch/aten/src/ATen/native/cpu/AdaptiveAvgPoolKernel.cpp:370 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x57 (0x7fe0406ced77 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::string const&) + 0x64 (0x7fe040698abb in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libc10.so)
frame #2: <unknown function> + 0x5e83aa9 (0x7fe0465a3aa9 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #3: <unknown function> + 0x1c03f2e (0x7fe042323f2e in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #4: at::native::adaptive_avg_pool2d_cpu(at::Tensor const&, c10::ArrayRef<long>) + 0x121 (0x7fe042324d31 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #5: <unknown function> + 0x2b380e0 (0x7fe0432580e0 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #6: <unknown function> + 0x2c9694d (0x7fe0433b694d in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #7: at::native::cpu_fallback(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*) + 0x338 (0x7fe0423be858 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #8: at::dipu_fallback(c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) + 0x512 (0x7fe01358d76e in /home/jenkins/host/github/deeplink.framework/dipu/torch_dipu/libtorch_dipu.so)
frame #9: void c10::BoxedKernel::make_boxed_function<&at::dipu_fallback>(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) + 0x3c (0x7fe0135b6228 in /home/jenkins/host/github/deeplink.framework/dipu/torch_dipu/libtorch_dipu.so)
frame #10: <unknown function> + 0x259409a (0x7fe042cb409a in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #11: at::_ops::_adaptive_avg_pool2d::redispatch(c10::DispatchKeySet, at::Tensor const&, c10::ArrayRef<c10::SymInt>) + 0x16b (0x7fe043163e3b in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #12: <unknown function> + 0x42e8901 (0x7fe044a08901 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #13: <unknown function> + 0x42e8e56 (0x7fe044a08e56 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #14: at::_ops::_adaptive_avg_pool2d::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>) + 0x172 (0x7fe04318d722 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #15: at::native::adaptive_avg_pool2d_symint(at::Tensor const&, c10::ArrayRef<c10::SymInt>) + 0x89 (0x7fe0423210e9 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #16: <unknown function> + 0x2e93d23 (0x7fe0435b3d23 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #17: at::_ops::adaptive_avg_pool2d::call(at::Tensor const&, c10::ArrayRef<c10::SymInt>) + 0x172 (0x7fe043090ce2 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_cpu.so)
frame #18: <unknown function> + 0x63b601 (0x7fe059982601 in /home/jenkins/.local/lib/python3.8/site-packages/torch/lib/libtorch_python.so)
<omitting python frames>
frame #25: python() [0x50b32c]
frame #30: python() [0x59cb2e]
frame #36: python() [0x50b3a0]
frame #41: python() [0x50b3a0]
frame #45: python() [0x50b32c]
frame #50: python() [0x59cb2e]
frame #55: python() [0x50b32c]
frame #60: python() [0x59cb2e]