Comments (9)
lazycal
commented on September 24, 2024
1
Did you try removing the cache file and rerun to regenerate the topset? Something like rm /root/.cache/nnsmith/ -r.
from nnsmith.
ganler
commented on September 24, 2024
1
Hi @CelestineSmith , I did not reproduce your error in nnsmith-0.0.1; nonetheless, would you like to kindly try:
# install latest nnsmith w/ better debugging info
pip install "git+https://github.com/ise-uiuc/nnsmith@main#egg=nnsmith[torch,onnx]" --upgrade
# if you did not have tvm installed, also do: pip install apache-tvm --pre
# try to generate one onnx model for testing tvm
yes | nnsmith.model_gen model.type=onnx backend.type=tvm debug.viz=true mgen.max_nodes=100 hydra.verbose=dtestYou can omit all intermediate errors and see if it eventually successfully returns like:
If not, could you kindly paste the outputs here and let me know your TVM version? Thanks!
from nnsmith.
ganler
commented on September 24, 2024
BTW, using 100 nodes is actually not recommended for the purpose of fuzzing (oftentimes bugs can manifest themselves within 3~5 ops), for being likely to get you more duplicated reports where each of the model is too large to reduce manually. I do have a reducer to run DD automatically but it will take some time to bring it here as it depends on many other experimental features.
from nnsmith.
CelestineSmith
commented on September 24, 2024
@lazycal Thank you for your reply. I've removed the cache file by rm /root/.cache/nnsmith/ -r. But when I try again nnsmith.fuzz fuzz.time=86400s model.type=onnx backend.type=tvm fuzz.root=fuzz_report_1 debug.viz=true mgen.max_nodes=100. It turned out to be the log I met before:
INFO dtest - Inferring topset from scratch and cache it to /root/.cache/nnsmith/ONNXModel_tvm_llvm -keys=cpu .yaml.
INFO dtest - [1 / 76] ===> Trying <class 'nnsmith.abstract.op.ReLU'>
WARNING dtest - =====> [Failure] at core.ReLU((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.ReLU((float64,)) => (float64,)
INFO dtest - [2 / 76] ===> Trying <class 'nnsmith.abstract.op.GELU'>
WARNING dtest - =====> [Failure] at core.GELU((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.GELU((float64,)) => (float64,)
INFO dtest - [3 / 76] ===> Trying <class 'nnsmith.abstract.op.LeakyReLU'>
WARNING dtest - =====> [Failure] at core.LeakyReLU((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.LeakyReLU((float64,)) => (float64,)
INFO dtest - [4 / 76] ===> Trying <class 'nnsmith.abstract.op.PReLU'>
WARNING dtest - =====> [Failure] at core.PReLU((float32,)) => (float32,)
INFO dtest - [5 / 76] ===> Trying <class 'nnsmith.abstract.op.Sigmoid'>
WARNING dtest - =====> [Failure] at core.Sigmoid((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Sigmoid((float64,)) => (float64,)
INFO dtest - [6 / 76] ===> Trying <class 'nnsmith.abstract.op.Sin'>
WARNING dtest - =====> [Failure] at core.Sin((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Sin((float64,)) => (float64,)
INFO dtest - [7 / 76] ===> Trying <class 'nnsmith.abstract.op.Cos'>
WARNING dtest - =====> [Failure] at core.Cos((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Cos((float64,)) => (float64,)
INFO dtest - [8 / 76] ===> Trying <class 'nnsmith.abstract.op.Asin'>
WARNING dtest - =====> [Failure] at core.Asin((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Asin((float64,)) => (float64,)
INFO dtest - [9 / 76] ===> Trying <class 'nnsmith.abstract.op.Acos'>
WARNING dtest - =====> [Failure] at core.Acos((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Acos((float64,)) => (float64,)
INFO dtest - [10 / 76] ===> Trying <class 'nnsmith.abstract.op.Tan'>
WARNING dtest - =====> [Failure] at core.Tan((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Tan((float64,)) => (float64,)
INFO dtest - [11 / 76] ===> Trying <class 'nnsmith.abstract.op.Atan'>
WARNING dtest - =====> [Failure] at core.Atan((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Atan((float64,)) => (float64,)
INFO dtest - [12 / 76] ===> Trying <class 'nnsmith.abstract.op.Abs'>
WARNING dtest - =====> [Failure] at core.Abs((float32,)) => (float32,)
WARNING dtest - =====> [Failure] at core.Abs((float64,)) => (float64,)
WARNING dtest - =====> [Failure] at core.Abs((int32,)) => (int32,)
WARNING dtest - =====> [Failure] at core.Abs((int64,)) => (int64,)
INFO dtest - [13 / 76] ===> Trying <class 'nnsmith.abstract.op.Where'>
WARNING dtest - =====> [Failure] at core.Where((bool, float32, float32)) => (float32,)
WARNING dtest - =====> [Failure] at core.Where((bool, float64, float64)) => (float64,)
WARNING dtest - =====> [Failure] at core.Where((bool, int32, int32)) => (int32,)
WARNING dtest - =====> [Failure] at core.Where((bool, int64, int64)) => (int64,)
INFO dtest - [14 / 76] ===> Trying <class 'nnsmith.abstract.op.Add'>
WARNING dtest - =====> [Failure] at core.Add((float32, float32)) => (float32,)
WARNING dtest - =====> [Failure] at core.Add((float64, float64)) => (float64,)
WARNING dtest - =====> [Failure] at core.Add((int32, int32)) => (int32,)
WARNING dtest - =====> [Failure] at core.Add((int64, int64)) => (int64,)
INFO dtest - [15 / 76] ===> Trying <class 'nnsmith.abstract.op.Sub'>
WARNING dtest - =====> [Failure] at core.Sub((float32, float32)) => (float32,)
WARNING dtest - =====> [Failure] at core.Sub((float64, float64)) => (float64,)
WARNING dtest - =====> [Failure] at core.Sub((int32, int32)) => (int32,)
WARNING dtest - =====> [Failure] at core.Sub((int64, int64)) => (int64,)This is part of the information, could you tell me what should I do? Thank you very much.
from nnsmith.
CelestineSmith
commented on September 24, 2024
@ganler Thank you for your reply. When I try to excute yes | nnsmith.model_gen model.type=onnx backend.type=tvm debug.viz=true mgen.max_nodes=100 hydra.verbose=dtest. The result be like:
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
INFO dtest - [58 / 76] ===> Trying <class 'nnsmith.abstract.op.ReduceMin'>
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((float16,)) => (float16,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((float32,)) => (float32,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((float64,)) => (float64,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((int8,)) => (int8,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((int16,)) => (int16,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 69, in make_backend
onnx_model = model.native_model
File "/usr/local/lib/python3.8/site-packages/nnsmith/materialize/onnx/__init__.py", line 258, in native_model
self.onnx_model = self.get_onnx_from_torch()
File "/usr/local/lib/python3.8/site-packages/nnsmith/materialize/onnx/__init__.py", line 271, in get_onnx_from_torch
onnx.checker.check_model(onnx_model, full_check=True)
File "/usr/local/lib/python3.8/site-packages/onnx/checker.py", line 119, in check_model
C.check_model(protobuf_string, full_check)
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] (op_type:ReduceMin, node name: /ReduceMin): data typestr: T, has unsupported type: tensor(int16)
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((int32,)) => (int32,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((int64,)) => (int64,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (bf != nullptr) is false: target.build.llvm is not enabled
WARNING dtest - =====> [Failure] at core.ReduceMin(dim=0)((uint8,)) => (uint8,)
DEBUG dtest - Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 70, in checked_compile
return self.checked_make_backend(testcase.model)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 66, in checked_make_backend
return self.make_backend(model)
File "/usr/local/lib/python3.8/site-packages/multipledispatch/dispatcher.py", line 435, in __call__
return func(self.obj, *args, **kwargs)
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 77, in make_backend
executor = relay.build_module.create_executor(
File "/data/tvm/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/data/tvm/python/tvm/relay/build_module.py", line 519, in _make_executor
mod = build(self.mod, target=self.target)
File "/data/tvm/python/tvm/relay/build_module.py", line 364, in build
graph_json, runtime_mod, params = bld_mod.build(
File "/data/tvm/python/tvm/relay/build_module.py", line 161, in build
self._build(
File "/data/tvm/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):
7: TVMFuncCall
at /data/tvm/src/runtime/c_runtime_api.cc:477
6: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at /data/tvm/include/tvm/runtime/packed_func.h:1217
5: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<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}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
at /data/tvm/include/tvm/runtime/packed_func.h:1213
4: 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
at /data/tvm/src/relay/backend/build_module.cc:185
3: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
at /data/tvm/src/relay/backend/build_module.cc:306
2: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
at /data/tvm/src/relay/backend/build_module.cc:458
1: tvm::TIRToRuntime(tvm::runtime::Map<tvm::Target, tvm::IRModule, void, void> const&, tvm::Target const&)
at /data/tvm/src/driver/driver_api.cc:493
0: tvm::codegen::Build(tvm::IRModule, tvm::Target)
at /data/tvm/src/target/codegen.cc:58
File "/data/tvm/src/target/codegen.cc", line 58
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.htmlAnd my tvm version is tvm 1.0.0 (2020-07-19), which is install from https://github.com/dmlc/tvm.
When I removed the tvm 1.0.0 and install tvm by pip install apache-tvm --pre, and when excute ```yes | nnsmith.model_gen model.type=onnx backend.type=tvm debug.viz=true mgen.max_nodes=100 hydra.verbose=dtest
```console
Error executing job with overrides: ['model.type=onnx', 'backend.type=tvm', 'debug.viz=true', 'mgen.max_nodes=100']
Traceback (most recent call last):
File "/usr/local/lib/python3.8/site-packages/nnsmith/cli/model_gen.py", line 34, in main
factory = BackendFactory.init(
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/factory.py", line 328, in init
from nnsmith.backends.tvm import TVMFactory
File "/usr/local/lib/python3.8/site-packages/nnsmith/backends/tvm.py", line 3, in <module>
import tvm
File "/data/tvm/python/tvm/__init__.py", line 33, in <module>
from .runtime.object import Object
File "/data/tvm/python/tvm/runtime/__init__.py", line 23, in <module>
from .script_printer import Scriptable
File "/data/tvm/python/tvm/runtime/script_printer.py", line 28, in <module>
class PrinterConfig(Object):
File "/data/tvm/python/tvm/_ffi/registry.py", line 69, in register
check_call(_LIB.TVMObjectTypeKey2Index(c_str(object_name), ctypes.byref(tidx)))
File "/data/tvm/python/tvm/_ffi/base.py", line 348, in check_call
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
255: 0xffffffffffffffff
254: _start
253: __libc_start_main
252: Py_BytesMain
at Modules/main.c:743
251: pymain_main
at Modules/main.c:719
250: Py_RunMain
at Modules/main.c:689
249: pymain_run_python
at Modules/main.c:610
248: pymain_run_file
at Modules/main.c:385
247: PyRun_SimpleFileExFlags
at Python/pythonrun.c:472
246: pyrun_simple_file
at Python/pythonrun.c:439
245: pyrun_file
at Python/pythonrun.c:1085
244: run_mod
at Python/pythonrun.c:1188
243: run_eval_code_obj
at Python/pythonrun.c:1166
242: PyEval_EvalCode
at Python/ceval.c:718
241: PyEval_EvalCodeEx
at Python/ceval.c:4327
240: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
239: PyEval_EvalFrameEx
at Python/ceval.c:741
238: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
237: call_function
at Python/ceval.c:4963
236: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
235: _PyFunction_Vectorcall
at Objects/call.c:436
234: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
233: PyEval_EvalFrameEx
at Python/ceval.c:741
232: _PyEval_EvalFrameDefault
at Python/ceval.c:3515
231: call_function
at Python/ceval.c:4963
230: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
229: _PyFunction_Vectorcall
at Objects/call.c:436
228: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
227: PyEval_EvalFrameEx
at Python/ceval.c:741
226: _PyEval_EvalFrameDefault
at Python/ceval.c:3515
225: call_function
at Python/ceval.c:4963
224: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
223: _PyFunction_Vectorcall
at Objects/call.c:436
222: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
221: PyEval_EvalFrameEx
at Python/ceval.c:741
220: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
219: call_function
at Python/ceval.c:4963
218: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
217: function_code_fastcall
at Objects/call.c:284
216: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
215: call_function
at Python/ceval.c:4963
214: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
213: _PyFunction_Vectorcall
at Objects/call.c:436
212: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
211: PyEval_EvalFrameEx
at Python/ceval.c:741
210: _PyEval_EvalFrameDefault
at Python/ceval.c:3515
209: call_function
at Python/ceval.c:4963
208: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
207: method_vectorcall
at Objects/classobject.c:60
206: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
205: _PyFunction_Vectorcall
at Objects/call.c:436
204: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
203: PyEval_EvalFrameEx
at Python/ceval.c:741
202: _PyEval_EvalFrameDefault
at Python/ceval.c:3515
201: call_function
at Python/ceval.c:4963
200: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
199: _PyFunction_Vectorcall
at Objects/call.c:436
198: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
197: PyEval_EvalFrameEx
at Python/ceval.c:741
196: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
195: call_function
at Python/ceval.c:4963
194: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
193: function_code_fastcall
at Objects/call.c:284
192: _PyEval_EvalFrameDefault
at Python/ceval.c:3515
191: call_function
at Python/ceval.c:4963
190: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
189: _PyFunction_Vectorcall
at Objects/call.c:436
188: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
187: PyEval_EvalFrameEx
at Python/ceval.c:741
186: _PyEval_EvalFrameDefault
at Python/ceval.c:2993
185: import_name
at Python/ceval.c:5139
184: PyImport_ImportModuleLevelObject
at Python/import.c:1798
183: import_find_and_load
at Python/import.c:1698
182: _PyObject_CallMethodIdObjArgs
at Objects/call.c:1245
181: object_vacall
at Objects/call.c:1187
180: _PyObject_FastCall
at ./Include/cpython/abstract.h:147
179: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
178: function_code_fastcall
at Objects/call.c:284
177: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
176: call_function
at Python/ceval.c:4963
175: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
174: function_code_fastcall
at Objects/call.c:284
173: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
172: call_function
at Python/ceval.c:4963
171: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
170: function_code_fastcall
at Objects/call.c:284
169: _PyEval_EvalFrameDefault
at Python/ceval.c:3486
168: call_function
at Python/ceval.c:4963
167: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
166: function_code_fastcall
at Objects/call.c:284
165: _PyEval_EvalFrameDefault
at Python/ceval.c:3469
164: call_function
at Python/ceval.c:4963
163: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
162: _PyFunction_Vectorcall
at Objects/call.c:436
161: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
160: PyEval_EvalFrameEx
at Python/ceval.c:741
159: _PyEval_EvalFrameDefault
at Python/ceval.c:3559
158: do_call_core
at Python/ceval.c:4983
157: PyVectorcall_Call
at Objects/call.c:200
156: cfunction_vectorcall_FASTCALL
at Objects/methodobject.c:426
155: builtin_exec
at Python/clinic/bltinmodule.c.h:396
154: builtin_exec_impl
at Python/bltinmodule.c:1025
153: PyEval_EvalCode
at Python/ceval.c:718
152: PyEval_EvalCodeEx
at Python/ceval.c:4327
151: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
150: PyEval_EvalFrameEx
at Python/ceval.c:741
149: _PyEval_EvalFrameDefault
at Python/ceval.c:2993
148: import_name
at Python/ceval.c:5139
147: PyImport_ImportModuleLevelObject
at Python/import.c:1798
146: import_find_and_load
at Python/import.c:1698
145: _PyObject_CallMethodIdObjArgs
at Objects/call.c:1245
144: object_vacall
at Objects/call.c:1187
143: _PyObject_FastCall
at ./Include/cpython/abstract.h:147
142: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
141: function_code_fastcall
at Objects/call.c:284
140: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
139: call_function
at Python/ceval.c:4963
138: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
137: function_code_fastcall
at Objects/call.c:284
136: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
135: call_function
at Python/ceval.c:4963
134: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
133: function_code_fastcall
at Objects/call.c:284
132: _PyEval_EvalFrameDefault
at Python/ceval.c:3486
131: call_function
at Python/ceval.c:4963
130: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
129: function_code_fastcall
at Objects/call.c:284
128: _PyEval_EvalFrameDefault
at Python/ceval.c:3469
127: call_function
at Python/ceval.c:4963
126: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
125: _PyFunction_Vectorcall
at Objects/call.c:436
124: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
123: PyEval_EvalFrameEx
at Python/ceval.c:741
122: _PyEval_EvalFrameDefault
at Python/ceval.c:3559
121: do_call_core
at Python/ceval.c:4983
120: PyVectorcall_Call
at Objects/call.c:200
119: cfunction_vectorcall_FASTCALL
at Objects/methodobject.c:426
118: builtin_exec
at Python/clinic/bltinmodule.c.h:396
117: builtin_exec_impl
at Python/bltinmodule.c:1025
116: PyEval_EvalCode
at Python/ceval.c:718
115: PyEval_EvalCodeEx
at Python/ceval.c:4327
114: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
113: PyEval_EvalFrameEx
at Python/ceval.c:741
112: _PyEval_EvalFrameDefault
at Python/ceval.c:2993
111: import_name
at Python/ceval.c:5139
110: PyImport_ImportModuleLevelObject
at Python/import.c:1798
109: import_find_and_load
at Python/import.c:1698
108: _PyObject_CallMethodIdObjArgs
at Objects/call.c:1245
107: object_vacall
at Objects/call.c:1187
106: _PyObject_FastCall
at ./Include/cpython/abstract.h:147
105: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
104: function_code_fastcall
at Objects/call.c:284
103: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
102: call_function
at Python/ceval.c:4963
101: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
100: function_code_fastcall
at Objects/call.c:284
99: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
98: call_function
at Python/ceval.c:4963
97: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
96: _PyFunction_Vectorcall
at Objects/call.c:436
95: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
94: PyEval_EvalFrameEx
at Python/ceval.c:741
93: _PyEval_EvalFrameDefault
at Python/ceval.c:3559
92: do_call_core
at Python/ceval.c:4983
91: PyCFunction_Call
at Objects/call.c:773
90: cfunction_call_varargs
at Objects/call.c:743
89: builtin___import__
at Python/bltinmodule.c:271
88: PyImport_ImportModuleLevelObject
at Python/import.c:1798
87: import_find_and_load
at Python/import.c:1698
86: _PyObject_CallMethodIdObjArgs
at Objects/call.c:1245
85: object_vacall
at Objects/call.c:1187
84: _PyObject_FastCall
at ./Include/cpython/abstract.h:147
83: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
82: function_code_fastcall
at Objects/call.c:284
81: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
80: call_function
at Python/ceval.c:4963
79: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
78: function_code_fastcall
at Objects/call.c:284
77: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
76: call_function
at Python/ceval.c:4963
75: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
74: function_code_fastcall
at Objects/call.c:284
73: _PyEval_EvalFrameDefault
at Python/ceval.c:3486
72: call_function
at Python/ceval.c:4963
71: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
70: function_code_fastcall
at Objects/call.c:284
69: _PyEval_EvalFrameDefault
at Python/ceval.c:3469
68: call_function
at Python/ceval.c:4963
67: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
66: _PyFunction_Vectorcall
at Objects/call.c:436
65: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
64: PyEval_EvalFrameEx
at Python/ceval.c:741
63: _PyEval_EvalFrameDefault
at Python/ceval.c:3559
62: do_call_core
at Python/ceval.c:4983
61: PyVectorcall_Call
at Objects/call.c:200
60: cfunction_vectorcall_FASTCALL
at Objects/methodobject.c:426
59: builtin_exec
at Python/clinic/bltinmodule.c.h:396
58: builtin_exec_impl
at Python/bltinmodule.c:1025
57: PyEval_EvalCode
at Python/ceval.c:718
56: PyEval_EvalCodeEx
at Python/ceval.c:4327
55: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
54: PyEval_EvalFrameEx
at Python/ceval.c:741
53: _PyEval_EvalFrameDefault
at Python/ceval.c:2993
52: import_name
at Python/ceval.c:5139
51: PyImport_ImportModuleLevelObject
at Python/import.c:1798
50: import_find_and_load
at Python/import.c:1698
49: _PyObject_CallMethodIdObjArgs
at Objects/call.c:1245
48: object_vacall
at Objects/call.c:1187
47: _PyObject_FastCall
at ./Include/cpython/abstract.h:147
46: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
45: function_code_fastcall
at Objects/call.c:284
44: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
43: call_function
at Python/ceval.c:4963
42: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
41: function_code_fastcall
at Objects/call.c:284
40: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
39: call_function
at Python/ceval.c:4963
38: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
37: function_code_fastcall
at Objects/call.c:284
36: _PyEval_EvalFrameDefault
at Python/ceval.c:3486
35: call_function
at Python/ceval.c:4963
34: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
33: function_code_fastcall
at Objects/call.c:284
32: _PyEval_EvalFrameDefault
at Python/ceval.c:3469
31: call_function
at Python/ceval.c:4963
30: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
29: _PyFunction_Vectorcall
at Objects/call.c:436
28: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
27: PyEval_EvalFrameEx
at Python/ceval.c:741
26: _PyEval_EvalFrameDefault
at Python/ceval.c:3559
25: do_call_core
at Python/ceval.c:4983
24: PyVectorcall_Call
at Objects/call.c:200
23: cfunction_vectorcall_FASTCALL
at Objects/methodobject.c:426
22: builtin_exec
at Python/clinic/bltinmodule.c.h:396
21: builtin_exec_impl
at Python/bltinmodule.c:1025
20: PyEval_EvalCode
at Python/ceval.c:718
19: PyEval_EvalCodeEx
at Python/ceval.c:4327
18: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
17: PyEval_EvalFrameEx
at Python/ceval.c:741
16: _PyEval_EvalFrameDefault
at Python/ceval.c:3500
15: call_function
at Python/ceval.c:4963
14: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:127
13: _PyFunction_Vectorcall
at Objects/call.c:436
12: _PyEval_EvalCodeWithName
at Python/ceval.c:4298
11: PyEval_EvalFrameEx
at Python/ceval.c:741
10: _PyEval_EvalFrameDefault
at Python/ceval.c:3469
9: call_function
at Python/ceval.c:4963
8: _PyObject_Vectorcall
at ./Include/cpython/abstract.h:125
7: _PyObject_MakeTpCall
at Objects/call.c:159
6: PyCFuncPtr_call
at /data/Python-3.8.16/Modules/_ctypes/_ctypes.c:4201
5: _ctypes_callproc
at /data/Python-3.8.16/Modules/_ctypes/callproc.c:1264
4: _call_function_pointer
at /data/Python-3.8.16/Modules/_ctypes/callproc.c:921
3: ffi_call
2: ffi_call_unix64
1: TVMObjectTypeKey2Index
0: tvm::runtime::Object::TypeKey2Index(std::string const&)
File "/workspace/tvm/src/runtime/object.cc", line 165
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (it != type_key2index_.end()) is false: Cannot find type node.PrinterConfig. Did you forget to register the node by TVM_REGISTER_NODE_TYPE ?
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
Could you tell me what should I do? Thank you very much.
from nnsmith.
ganler
commented on September 24, 2024
@CelestineSmith Hi, as you can see from the text, "Check failed: (bf != nullptr) is false: target.build.llvm is not enabled". This is because you did not build tvm with LLVM (which is required for doing CPU codegen).
One simple way is to just use TVM's pre-build packages: https://pypi.org/project/apache-tvm/
pip install apache-tvmOr if you still want to build TVM from scratch, you should build TVM with CMAKE flag -DUSE_LLVM=ON. More details can be found https://tvm.apache.org/docs/install/from_source.html#developers-get-source-from-github
from nnsmith.
ganler
commented on September 24, 2024
From your second log, you can see your TVM path is /data/tvm/python/tvm/... which is not under a typical Python site package location -- it means you are still using the tvm that is compiled from scratch (there could be some potential conflicts with your newly installed version). As a result, you want to use the pre-built apache-tvm package: (i) with export PYTHONPATH=""; and (ii) run the code out of the tree/path of tvm's folder.
from nnsmith.
CelestineSmith
commented on September 24, 2024
@ganler Thank you for your reply. I delete all the documents in /data/tvm and can use nnsmith.fuzz successfully. Thank you very much.
from nnsmith.
ganler
commented on September 24, 2024
My pleasure!
from nnsmith.
Related Issues (20)
- [Tracking] Make Python >= 3.8 mandatory
- 💡 [Dynamic Graph] - Does nnsmith support dynamic graphs? HOT 3
- 💡 [REQUEST] TF Coverage Tutorial and Script
- TF Coverage Scripts and Tutorial HOT 1
- [Dev] `hydra` -> `click`
- [Question] Customize the number of input/output variables in generated graphs HOT 9
- 💡 [REQUEST] - Tutorial of adding a new operator for GIR HOT 4
- 🐛 [BUG] - <`ONNXModelCPU_tvm_0.9.0_cpu.yaml` file was empty, can't get opset properly properly> HOT 11
- Render seems to not work HOT 6
- 🐛 [BUG] - There is a problem with relative import in `fuzz.py` HOT 2
- Some questions about the replication of the experiment HOT 6
- Problems encountered while compiling the onnx model HOT 4
- [Help wanted] How to get the shape of the output tensor of a operator HOT 5
- [Help wanted] How to get the result of executing model_exec.py? HOT 7
- [User Question] integer type annotation in TVM HOT 2
- 🐛 [BUG] - <An error occurred when loading the onnx model generated by nnsmith using tvm.delay.> HOT 1
- [Help Wanted] Problems encountered when converting the onnx model to tvm.relay HOT 3
- [Help Wanted] How to only generate sequential models HOT 2
- Help Wanted - How does one generate minimum code examples from NNSmith bug reports HOT 3
- Instruction of TVM COV HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nnsmith.