Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[BUG][MetaSchedule] ResNet Integration Test Error on LLVM #437

Closed
zxybazh opened this issue Aug 12, 2021 · 1 comment
Closed

[BUG][MetaSchedule] ResNet Integration Test Error on LLVM #437

zxybazh opened this issue Aug 12, 2021 · 1 comment

Comments

@zxybazh
Copy link
Collaborator

zxybazh commented Aug 12, 2021 •
edited
Loading

When using the main branch code, I encountered the following error when running test_resnet_end_to_end.py.
To be specific, I was running rpc server on llvm target instead of the original raspberry-pi/4b-64 target.

conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
One or more operators have not been tuned. Please tune your model for better performance. Use DEBUG logging level to see more details.
Exception in thread Thread-1:
Traceback (most recent call last):
  File "/home/zxybazh/anaconda3/lib/python3.8/threading.py", line 932, in _bootstrap_inner
    self.run()
  File "/home/zxybazh/anaconda3/lib/python3.8/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/home/zxybazh/tvm-tensorir/python/tvm/meta_schedule/relay_integration.py", line 75, in call_all_topi_funcs
    from tvm.relay.backend import graph_runtime_codegen
ImportError: cannot import name 'graph_runtime_codegen' from 'tvm.relay.backend' (/home/zxybazh/tvm-tensorir/python/tvm/relay/backend/__init__.py)
[11:27:09] /home/zxybazh/tvm-tensorir/src/meta_schedule/database.cc:157: Loading tuning records from: resnet.json
[11:27:09] /home/zxybazh/tvm-tensorir/src/meta_schedule/database.cc:183: Nothing is loaded. File does not exist or cannot be opened
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
conv2d NHWC layout is not optimized for x86 with autotvm.
Traceback (most recent call last):
  File "test_resnet_end_to_end.py", line 238, in <module>
    test_end_to_end_resnet("resnet.json")
  File "test_resnet_end_to_end.py", line 184, in test_end_to_end_resnet
    lib = relay.build_module.build(mod, target, params=params)
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/build_module.py", line 363, in build
    executor_config, runtime_mod, params = bld_mod.build(
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/build_module.py", line 174, in build
    self._build(mod, target, target_host, executor, mod_name)
  File "/home/zxybazh/tvm-tensorir/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
    raise get_last_ffi_error()
TypeError: Traceback (most recent call last):
  30: TVMFuncCall
  29: _ZNSt17_Function_handlerIFvN
  28: tvm::relay::backend::RelayBuildModule::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#3}::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
  27: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, std::unordered_map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, tvm::runtime::NDArray, std::hash<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::equal_to<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, tvm::runtime::NDArray> > > const&, tvm::runtime::String)
  26: tvm::relay::backend::RelayBuildModule::Optimize(tvm::IRModule, tvm::runtime::Map<tvm::Integer, tvm::Target, void, void> const&, std::unordered_map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, tvm::runtime::NDArray, std::hash<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::equal_to<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, tvm::runtime::NDArray> > > const&)
  25: tvm::transform::Pass::operator()(tvm::IRModule) const
  24: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
  23: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
  22: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
  21: tvm::relay::transform::FunctionPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
  20: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), tvm::runtime::TypedPackedFunc<tvm::relay::Function (tvm::relay::Function, tvm::IRModule, tvm::transform::PassContext)>::AssignTypedLambda<tvm::relay::transform::AlterOpLayout()::{lambda(tvm::relay::Function, tvm::IRModule, tvm::transform::PassContext)#1}>(tvm::relay::transform::AlterOpLayout()::{lambda(tvm::relay::Function, tvm::IRModule, tvm::transform::PassContext)#1})::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  19: tvm::relay::alter_op_layout::AlterOpLayout(tvm::RelayExpr const&)
  18: tvm::relay::ForwardRewrite(tvm::RelayExpr const&, tvm::runtime::TypedPackedFunc<tvm::RelayExpr (tvm::relay::Call const&, tvm::runtime::Array<tvm::RelayExpr, void> const&, tvm::runtime::ObjectRef const&)> const&, std::function<tvm::runtime::ObjectRef (tvm::relay::Call const&)>, std::function<tvm::RelayExpr (tvm::RelayExpr const&)>)
  17: tvm::relay::MixedModeMutator::VisitExpr(tvm::RelayExpr const&)
  16: _ZN3tvm5relay16MixedModeMutator17DispatchVisitExprERKNS_9Re
  15: tvm::relay::ExprMutator::VisitExpr(tvm::RelayExpr const&)
  14: tvm::relay::ExprFunctor<tvm::RelayExpr (tvm::RelayExpr const&)>::VisitExpr(tvm::RelayExpr const&)
  13: _ZZN3tvm5relay11ExprFunctorIFNS_9RelayExprERKS2_EE10InitVTableEvENUlR
  12: tvm::relay::ExprMutator::VisitExpr_(tvm::relay::FunctionNode const*)
  11: tvm::relay::MixedModeMutator::VisitExpr(tvm::RelayExpr const&)
  10: _ZN3tvm5relay16MixedModeMutator17DispatchVisitExprERKNS_9Re
  9: tvm::relay::ExprMutator::VisitExpr(tvm::RelayExpr const&)
  8: tvm::relay::ExprFunctor<tvm::RelayExpr (tvm::RelayExpr const&)>::VisitExpr(tvm::RelayExpr const&)
  7: _ZZN3tvm5relay11ExprFunctorIFNS_9RelayExprERKS2_EE10InitVTableEvENUlR
  6: tvm::relay::MixedModeMutator::VisitExpr_(tvm::relay::CallNode const*)
  5: tvm::relay::ForwardRewriter::Rewrite_(tvm::relay::CallNode const*, tvm::RelayExpr const&)
  4: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), tvm::runtime::TypedPackedFunc<tvm::RelayExpr (tvm::relay::Call const&, tvm::runtime::Array<tvm::RelayExpr, void> const&, tvm::runtime::ObjectRef const&)>::AssignTypedLambda<tvm::RelayExpr (*)(tvm::relay::Call const&, tvm::runtime::Array<tvm::RelayExpr, void> const&, tvm::runtime::ObjectRef const&)>(tvm::RelayExpr (*)(tvm::relay::Call const&, tvm::runtime::Array<tvm::RelayExpr, void> const&, tvm::runtime::ObjectRef const&))::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  3: tvm::RelayExpr tvm::relay::LayoutRewriter<tvm::relay::alter_op_layout::AlterTransformMemorizer>(tvm::relay::Call const&, tvm::runtime::Array<tvm::RelayExpr, void> const&, tvm::runtime::ObjectRef const&)
  2: tvm::relay::TransformMemorizer::CallWithNewLayouts(tvm::relay::Call const&, std::vector<tvm::RelayExpr, std::allocator<tvm::RelayExpr> > const&)
  1: tvm::relay::alter_op_layout::AlterTransformMemorizer::CallWithNewLayouts(tvm::relay::Call const&, tvm::Attrs, std::vector<tvm::RelayExpr, std::allocator<tvm::RelayExpr> > const&)
  0: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), TVMFuncCreateFromCFunc::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#2}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  File "/home/zxybazh/tvm-tensorir/python/tvm/_ffi/_ctypes/packed_func.py", line 81, in cfun
    rv = local_pyfunc(*pyargs)
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/op/nn/_nn.py", line 110, in alter_op_layout_dense
    return topi.nn.dense_alter_layout(attrs, inputs, tinfos, out_type)
  File "<decorator-gen-71>", line 2, in dense_alter_layout
  File "/home/zxybazh/tvm-tensorir/python/tvm/target/generic_func.py", line 275, in dispatch_func
    return dispatch_dict[k](*args, **kwargs)
  File "/home/zxybazh/tvm-tensorir/python/tvm/topi/x86/dense_alter_op.py", line 38, in _alter_dense_layout
    impl, outs = relay.backend.compile_engine.select_implementation(
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/backend/compile_engine.py", line 216, in select_implementation
    outs = best_plevel_impl.compute(attrs, inputs, out_type)
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/op/op.py", line 126, in compute
    return _OpImplementationCompute(self, attrs, inputs, out_type)
  File "/home/zxybazh/tvm-tensorir/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
    raise get_last_ffi_error()
  3: TVMFuncCall
  2: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), tvm::relay::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#4}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  1: tvm::relay::OpImplementation::Compute(tvm::Attrs const&, tvm::runtime::Array<tvm::te::Tensor, void> const&, tvm::Type const&)
  0: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), TVMFuncCreateFromCFunc::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#2}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  File "/home/zxybazh/tvm-tensorir/python/tvm/_ffi/_ctypes/packed_func.py", line 81, in cfun
    rv = local_pyfunc(*pyargs)
  File "/home/zxybazh/tvm-tensorir/python/tvm/relay/op/strategy/generic.py", line 813, in _compute_dense
    return [topi_compute(*args)]
TypeError: dense() takes from 2 to 5 positional arguments but 6 were given
@zxybazh zxybazh changed the title [BUG][MetaSchedule] Resnet Integration Test Error [BUG][MetaSchedule] ResNet Integration Test Error Aug 12, 2021
@zxybazh zxybazh changed the title [BUG][MetaSchedule] ResNet Integration Test Error [BUG][MetaSchedule] ResNet Integration Test Error on LLVM Aug 12, 2021
@zxybazh zxybazh mentioned this issue Aug 12, 2021
Merged
@junrushao
Copy link
Member

Won't fix

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zxybazh @junrushao