[Apache TVM Discuss] [Questions] Load_module error for Android RPC on Snapdragon 865

[YK via Apache TVM Discuss <no...@discuss.tvm.ai>]

Hi,

I met an error on 'remote.load_module( )' function.
I am trying to run a model using Snapdragon's GPU, so I set the target like this,

> target = tvm.target.Target("opencl -device=mali", host="llvm -mtriple=arm64-linux-android")

After build the model,

> with tvm.transform.PassContext(opt_level=3):  
  lib = relay.build_module.build(mod, target=target, params=params)  



Then, set the device, upload and load the module
```
ctx = remote.device(str(target), 0)  
remote.upload(lib_fname)  
rlib = remote.load_module("net.so")

The error occured at the point like this,
>Traceback (most recent call last):
  File "trial4_android_opencl.py", line 254, in <module>
    rlib = remote.load_module("net.so")
  File "/workspace/python/tvm/rpc/client.py", line 161, in load_module
    return _ffi_api.LoadRemoteModule(self._sess, path)
  File "/workspace/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
    raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
  5: TVMFuncCall
  4: std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), void tvm::runtime::TypedPackedFunc<tvm::runtime::Module (tvm::runtime::Module, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)>::AssignTypedLambda<tvm::runtime::{lambda(tvm::runtime::Module, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)#5}>(tvm::runtime::{lambda(tvm::runtime::Module, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)#5}, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)
  3: _ZNSt17_Function_handlerIFvN3tvm7runtime7TVMArgsEPNS1_1
  2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
  1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
  0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
  File "/workspace/src/runtime/rpc/rpc_endpoint.cc", line 797
TVMError:
An internal invariant was violated during the execution of TVM.
Please read TVM's error reporting guidelines.
More details can be found here: https://discuss.tvm.ai/t/error-reporting/7793.
---------------------------------------------------------------
  Check failed: (code == RPCCode::kReturn) is false: code=1
```

What is the problem on this error?





---
[Visit Topic](https://discuss.tvm.apache.org/t/load-module-error-for-android-rpc-on-snapdragon-865/9813/1) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/25234d6b63b0b8e2c6f7ca144efc05798d5679b747de050b6e8230da67ef7571).