engineer1109 opened a new issue, #13075:
URL: https://github.com/apache/tvm/issues/13075

   ### Actual behavior
   
   ```
   Build the libraries..
   python3 prepare_test_libs.py
   /usr/local/lib/python3.8/dist-packages/tvm/target/target.py:799: 
UserWarning: tvm.target.create() is being deprecated. Please use 
tvm.target.Target() instead
     warnings.warn("tvm.target.create() is being deprecated. Please use 
tvm.target.Target() instead")
   g++ -c -std=c++17 -O2 -fPIC -I/home/wjl/gitlab_xdx/tvm/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dmlc-core/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o 
lib/libtvm_runtime_pack.o  tvm_runtime_pack.cc
   g++ -std=c++17 -O2 -fPIC -I/home/wjl/gitlab_xdx/tvm/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dmlc-core/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o lib/cpp_deploy_pack  
cpp_deploy.cc lib/test_addone_sys.o lib/libtvm_runtime_pack.o 
-L/home/wjl/gitlab_xdx/tvm/build -ldl -pthread
   g++ -std=c++17 -O2 -fPIC -I/home/wjl/gitlab_xdx/tvm/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dmlc-core/include 
-I/home/wjl/gitlab_xdx/tvm/3rdparty/dlpack/include 
-DDMLC_USE_LOGGING_LIBRARY=\<tvm/runtime/logging.h\> -o lib/cpp_deploy_normal  
cpp_deploy.cc lib/test_addone_sys.o -ltvm_runtime 
-L/home/wjl/gitlab_xdx/tvm/build -ldl -pthread
   Run the example
   Run the deployment with all in one packed library...
   [11:32:28] cpp_deploy.cc:77: Verify dynamic loading from test_addone_dll.so
   [11:32:28] cpp_deploy.cc:69: Finish verification...
   [11:32:28] cpp_deploy.cc:81: Verify load function from system lib
   terminate called after throwing an instance of 'tvm::runtime::InternalError'
     what():  [11:32:28] cpp_deploy.cc:34: 
   ---------------------------------------------------------------
   An error occurred during the execution of TVM.
   For more information, please see: https://tvm.apache.org/docs/errors.html
   ---------------------------------------------------------------
     Check failed: (f != nullptr) is false: 
   Stack trace:
     [bt] (0) lib/cpp_deploy_pack(+0x1bd5c) [0x55bdf3b99d5c]
     [bt] (1) lib/cpp_deploy_pack(+0x6f19) [0x55bdf3b84f19]
     [bt] (2) lib/cpp_deploy_pack(+0x130a4) [0x55bdf3b910a4]
     [bt] (3) lib/cpp_deploy_pack(+0x139a9) [0x55bdf3b919a9]
     [bt] (4) lib/cpp_deploy_pack(+0xe45d) [0x55bdf3b8c45d]
     [bt] (5) /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3) 
[0x7f74a909d083]
     [bt] (6) lib/cpp_deploy_pack(+0x1298e) [0x55bdf3b9098e]
   
   
   Aborted (core dumped)
   Run the cpp deployment with all in normal library...
   [11:32:29] cpp_deploy.cc:77: Verify dynamic loading from test_addone_dll.so
   [11:32:29] cpp_deploy.cc:69: Finish verification...
   [11:32:29] cpp_deploy.cc:81: Verify load function from system lib
   terminate called after throwing an instance of 'tvm::runtime::InternalError'
     what():  [11:32:29] cpp_deploy.cc:34: 
   ---------------------------------------------------------------
   An error occurred during the execution of TVM.
   For more information, please see: https://tvm.apache.org/docs/errors.html
   ---------------------------------------------------------------
     Check failed: (f != nullptr) is false: 
   Stack trace:
     0: Verify(tvm::runtime::Module, std::__cxx11::basic_string<char, 
std::char_traits<char>, std::allocator<char> >)
     1: DeploySingleOp()
     2: main
     3: __libc_start_main
           at ../csu/libc-start.c:308
     4: _start
     5: 0xffffffffffffffff
   
   
   Aborted (core dumped)
   Run the python deployment with all in normal library...
   Verify dynamic loading from test_addone_dll.so
   Finish verification...
   
   ```
   
   ### Environment
   
   Ubuntu 20.04 GCC 9.4.0
   
   ### Steps to reproduce
   
   ```
   cd tvm/apps/howto_deploy
   sh run_example.sh
   ```
   
   
   Verify Function is all failed.
   Function is nullptr when loading so
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to