make error

[tencent]

make error

[yuanzexi]

Could you specify the Environment you used? Better following the Issue-get-started hints. Thanks.

Describe the bug
A clear and concise description of what the bug is.

Environment

TensorRT Version:
NVIDIA GPU:
NVIDIA Driver Version:
CUDA Version:
CUDNN Version:
Operating System:
Python Version (if applicable):
Tensorflow Version (if applicable):
PyTorch Version (if applicable):

Relevant Files

To Reproduce
Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

[CB-Jack-S]

OK, Let's see..
I am using Jetson AGX Xavier with Jetpack 4.4.1, operating system is "Ubuntu 18.04.5 LTS"
So the cuda version=10.2, cudnn version=8.0, TensorRT version=7.1.3, python version=3.6.9 and pytorch version=1.7.0
First I cd to the root file of forward
I changed the CMakelist.txt like :

...

Enable TensorRT

option(ENABLE_TENSORRT "Enable TensorRT" ON)

Enable Torch

option(ENABLE_TORCH "Enable Torch" ON)

Enable TensorFlow

option(ENABLE_TENSORFLOW "Enable TensorFlow" OFF)

Enable Keras

option(ENABLE_KERAS "Enable Keras" OFF)

Enable profiling

option(ENABLE_PROFILING "Enable profiling" ON)

Enable logging

option(ENABLE_LOGGING "Enable logging" ON)

Enable dynamic batch size

option(ENABLE_DYNAMIC_BATCH "Enable dynamic batch size" OFF)

Build Python Lib

option(BUILD_PYTHON_LIB "Build Python Lib" ON)

Enable Inference Tests (need OpenCV)

option(ENABLE_INFER_TESTS "Enable Inference Tests" OFF)

Enable RNN models forward

option(ENABLE_RNN "Enable RNN models forward" ON)

Enable unit tests

option(ENABLE_UNIT_TESTS "Enable unit tests" ON)
...

python

set(PYTHON_EXECUTABLE /usr/bin/python3.6)
...

Then I followed the orders:
'mkdir build' and 'cd build'
'cmake .. -DTensorRT_ROOT=/usr/src/tensorrt' and it shows'Generating done'

So I run 'make' and dangdang! error happens:

agx@agx-desktop:~/SCW/Forward-master/build$ make
Consolidate compiler generated dependencies of target simple-utils
[ 4%] Built target simple-utils
[ 5%] Building NVCC (Device) object source/trt_engine/CMakeFiles/trt_engine.dir/trt_network_crt/plugins/emb_layer_norm_plugin/trt_engine_generated_emb_layer_norm_kernel.cu.o
In file included from /home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/block_discontinuity.cuh:37:0,
from /home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/block_histogram_sort.cuh:37,
from /home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/block_histogram.cuh:36,
from /home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/cub.cuh:38,
from /home/agx/SCW/Forward-master/source/trt_engine/trt_network_crt/plugins/common/bert_plugin_util.h:33,
from /home/agx/SCW/Forward-master/source/trt_engine/trt_network_crt/plugins/emb_layer_norm_plugin/emb_layer_norm_kernel.cu:36:
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:238:61: warning: missing terminating " character
asprmt"bfi.b32 %0, %1, %2, %3;" : "=r"(ret) : ar"(x), "r"(x), b, in) - 1;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:282:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:284:2: error: #endif without #if
#endif
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:294:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:296:2: error: #endif without #if
#endif
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:306:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:308:2: error: #endif without #if
#endif}
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:319:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:321:46: warning: missing terminating " character
3;" : "word(ret) : word("(x), "rc_bit-of("(x), flags() + z;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:322:2: error: #endif without #if
#endif
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:334:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:336:46: warning: missing terminating " character
3;" : "word(ret) : word("(x), "rc_bit-of("(x), flags() + z;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:337:2: error: #endif without #if
#endif
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:349:2: error: #else without #if
#else
^~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:351:44: warning: missing terminating " character
3;" : "word(ret) : word("(x), "rc_lane("(x), flags() + z;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:352:2: error: #endif without #if
#endif
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:371:61: warning: missing terminating " character
asfma.rz.ffi.b32 %0, %1, %2, %3;" f"(d(ret)f: ar"(xf, "r"(xf, cr) - 1;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:375:2: error: #endif without #if
#endif // DOXYGEN_SHOULD_SKIP_THIS
^~~~~
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:383:20: warning: missing terminating " character
vo orileasexit;")>())
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:395:20: warning: missing terminating " character
vo orileasllup;")>()x;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:406:18: warning: missing terminating " character
tef adIdx"urn x;
^
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:475:1: error: unterminated comment
/**
^
In file included from /home/agx/SCW/Forward-master/source/trt_engine/trt_network_crt/plugins/common/bert_plugin_util.h:33:0,
from /home/agx/SCW/Forward-master/source/trt_engine/trt_network_crt/plugins/emb_layer_norm_plugin/emb_layer_norm_kernel.cu:36:
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/cub.cuh:54:10: fatal error: device/device_run_length_encode.cuh: No such file or directory
#include "device/device_run_length_encode.cuh"
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
CMake Error at trt_engine_generated_emb_layer_norm_kernel.cu.o.cmake:220 (message):
Error generating
/home/agx/SCW/Forward-master/build/source/trt_engine/CMakeFiles/trt_engine.dir/trt_network_crt/plugins/emb_layer_norm_plugin/./trt_engine_generated_emb_layer_norm_kernel.cu.o

source/trt_engine/CMakeFiles/trt_engine.dir/build.make:1591: recipe for target 'source/trt_engine/CMakeFiles/trt_engine.dir/trt_network_crt/plugins/emb_layer_norm_plugin/trt_engine_generated_emb_layer_norm_kernel.cu.o' failed
make[2]: *** [source/trt_engine/CMakeFiles/trt_engine.dir/trt_network_crt/plugins/emb_layer_norm_plugin/trt_engine_generated_emb_layer_norm_kernel.cu.o] Error 1
CMakeFiles/Makefile2:556: recipe for target 'source/trt_engine/CMakeFiles/trt_engine.dir/all' failed
make[1]: *** [source/trt_engine/CMakeFiles/trt_engine.dir/all] Error 2
Makefile:90: recipe for target 'all' failed
make: *** [all] Error 2

Appreciate it for listening！

[yuanzexi]

The Environment is almost the same as the passed Travis CI (https://travis-ci.com/github/Tencent/Forward) 'CUDA 10.2', so your environment has no problem and it should work. Here the error happens on the third-party 'cub-1.8.0', so maybe we need to check the files you download.

There is a character missing problem in your error message
/home/agx/SCW/Forward-master/source/third_party/cub-1.8.0/cub/block/specializations/../../block/../util_ptx.cuh:238:61: warning: missing terminating " character asprmt"bfi.b32 %0, %1, %2, %3;" : "=r"(ret) : ar"(x), "r"(x), b, in) - 1;
. However, you can see that
the statement in the line 238 of cub-1.8.0/cub/util_ptx.cuh is asm ("prmt.b32 %0, %1, %2, %3;" : "=r"(ret) : "r"(a), "r"(b), "r"(index));, so there must be some bad things happened, lead to missing terminating " character.

From my point of view, there are several possible reasons:

1. The code files you downloaded are damaged in the transmission.
2. The encoding of code files are not UTF-8 in your platform such that the files are analyzed in a wrong way.
3. The code files were changed because of some reasons.
4. The NVCC in your platform cannot decode asm codes well.

I suggest that you can download a new copy of source code and try again.

[CB-Jack-S]

Thanks a lot! That's the problem!
I'm using Xfpt to transfer those files and they are damaged in the transmission as you said!
But I came into a new 'make' error:

[ 4%] Built target simple-utils
[ 87%] Built target trt_engine
[ 97%] Built target fwd_torch
[ 98%] Building CXX object source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o
:0:0: warning: "_GLIBCXX_USE_CXX11_ABI" redefined
:0:0: note: this is the location of the previous definition
In file included from /home/agx/SCW/Forward-master/source/py_fwd/py_forward.cpp:32:0:
/home/agx/SCW/Forward-master/source/py_fwd/py_forward_torch.h:32:10: fatal error: torch/csrc/jit/pybind_utils.h: No such file or directory
#include <torch/csrc/jit/pybind_utils.h>
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
source/py_fwd/CMakeFiles/forward.dir/build.make:75: recipe for target 'source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o' failed
make[2]: *** [source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o] Error 1
CMakeFiles/Makefile2:573: recipe for target 'source/py_fwd/CMakeFiles/forward.dir/all' failed
make[1]: *** [source/py_fwd/CMakeFiles/forward.dir/all] Error 2
Makefile:90: recipe for target 'all' failed
make: *** [all] Error 2

I'm not so good at c++, so I don't know if I missed any essential library files like this 'pybind_utils.h' head file. But I do installed pybind11. Maybe you can give me some advice on this issue too. Thank you so much!

[yuanzexi]

Sorry, here has a missing code that I didn't submit. I submit a new commit (9b2139e) to fix this problem which is introduced by NEW_TORCH_API. You can view the commit to change your code and make again.

[CB-Jack-S]

Yes, I find that file in torch/csrc/jit/python/pybind_utils.h
Sorry to ask, but another error happens:

‘’‘[ 97%] Built target fwd_torch
[ 98%] Building CXX object source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o
:0:0: warning: "_GLIBCXX_USE_CXX11_ABI" redefined
:0:0: note: this is the location of the previous definition
In file included from /home/agx/SCW/Forward-master/source/py_fwd/py_forward.cpp:32:0:
/home/agx/SCW/Forward-master/source/py_fwd/py_forward_torch.h: In member function ‘bool pybind11::detail::type_casterc10::IValue::load(pybind11::handle, bool)’:
/home/agx/SCW/Forward-master/source/py_fwd/py_forward_torch.h:62:39: error: no matching function for call to ‘toIValue(pybind11::handle&)’
value = torch::jit::toIValue(src);
^
In file included from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/ir/named_value.h:5:0,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/ir/ir.h:5,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/api/function_impl.h:4,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/api/method.h:5,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/api/object.h:5,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/frontend/tracer.h:9,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/autograd/generated/variable_factories.h:12,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:7,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/agx/.local/lib/python3.6/site-packages/torch/include/torch/extension.h:4,
from /home/agx/SCW/Forward-master/source/py_fwd/py_forward_torch.h:32,
from /home/agx/SCW/Forward-master/source/py_fwd/py_forward.cpp:32:
/home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/ir/constants.h:48:33: note: candidate: c10::optionalc10::IValue torch::jit::toIValue(const torch::jit::Value*)
TORCH_API c10::optional toIValue(const Value* v);
^~~~~~~~
/home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/ir/constants.h:48:33: note: no known conversion for argument 1 from ‘pybind11::handle’ to ‘const torch::jit::Value*’
In file included from /home/agx/SCW/Forward-master/source/py_fwd/py_forward_torch.h:34:0,
from /home/agx/SCW/Forward-master/source/py_fwd/py_forward.cpp:32:
/home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/python/pybind_utils.h:509:15: note: candidate: c10::IValue torch::jit::toIValue(pybind11::handle, const TypePtr&, c10::optional)
inline IValue toIValue(
^~~~~~~~
/home/agx/.local/lib/python3.6/site-packages/torch/include/torch/csrc/jit/python/pybind_utils.h:509:15: note: candidate expects 3 arguments, 1 provided
source/py_fwd/CMakeFiles/forward.dir/build.make:75: recipe for target 'source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o' failed
make[2]: *** [source/py_fwd/CMakeFiles/forward.dir/py_forward.cpp.o] Error 1
CMakeFiles/Makefile2:573: recipe for target 'source/py_fwd/CMakeFiles/forward.dir/all' failed
make[1]: *** [source/py_fwd/CMakeFiles/forward.dir/all] Error 2
Makefile:90: recipe for target 'all' failed
make: *** [all] Error
’‘’

-_-//

[yuanzexi]

Sorry, a compile problem exists here because of torch 1.7.0. I submit a commit(640a788) to fix this problem. In this travis CI (https://travis-ci.com/github/Tencent/Forward/builds/221009275), the compilation of CUDA 10.2 + TRT 7.2 + Torch 1.7.0 has passed.