search

NVIDIA / TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
https://developer.nvidia.com/tensorrt
Apache License 2.0
10.52k stars 2.1k forks source link

Cross compiling for Jetson Nano needs better support!!!! #1168

Open Alex-EEE opened 3 years ago

Alex-EEE commented 3 years ago

This is here for anyone else trying to cross compile for Jetson. If you want to use the cross compile docker image, this post has workarounds for step 3, "(Optional) JetPack SDK for Jetson builds" (which you have to do)

They say just install the SDK manager and copy the files over. Ha! Here's what you really need to do:

1). The SDK manager only runs on Linux 2). The Docker image for the SDK manager WILL NOT let you "just download files." If you don't flash the target from the SDK, then you won't be able to get the files 3). Even if you run Ubuntu, or run it in a VM, IT STILL WONT LET YOU DOWNLOAD the Jetpack files. You'll have to hack your OS according to these instructions: https://forums.developer.nvidia.com/t/sdkmanager-not-supported-on-linux/71742/8. Note, I used the trick related to the file "/usr/lib/os-release-bionic," not the other tricks

ttyio commented 3 years ago

Adding @rajeevsrao , thanks

rarazac commented 3 years ago

I Agree!

I am currently trying to cross-compile for jetson Jetpack 4.5.1. Release 7.1.

cmake .. -DTRT_LIB_DIR=$TRT_RELEASE/lib -DTRT_OUT_DIR=pwd/out -DBUILD_PLUGINS=OFF -DCMAKE_TOOLCHAIN_FILE=$TRT_SOURCE/cmake/toolchains/cmake_aarch64.toolchain -DCMAKE_CUDA_SEPARABLE_COMPILATION=OFF -DCUDA_VERSION=10.2 -DCUBLASLT_LIB="/usr/lib/aarch64-linux-gnu/libcublasLt.so" -DCUBLAS_LIB="/usr/lib/aarch64-linux-gnu/libcublas.so" -DCUDNN_LIB="/pdk_files/cudnn/lib/libcudnn.so.8"

Building for TensorRT version: 7.1.3, library version: 7
-- Targeting TRT Platform: aarch64
-- CUDA version set to 10.2
-- cuDNN version set to 8.0
-- Protobuf version set to 3.0.0
-- Setting up another Protobuf build for cross compilation targeting aarch64-Linux
-- Using libprotobuf /workspace/TensorRT/build/third_party.protobuf_aarch64/lib/libprotobuf.a
-- ========================= Importing and creating target nvinfer ==========================
-- Looking for library nvinfer
-- Library that was found /pdk_files/tensorrt/lib/libnvinfer.so
-- ==========================================================================================
-- ========================= Importing and creating target nvuffparser ==========================
-- Looking for library nvparsers
-- Library that was found /pdk_files/tensorrt/lib/libnvparsers.so
-- ==========================================================================================
-- found:/pdk_files/cudnn/lib/libcudnn.so.8
-- found:/usr/lib/aarch64-linux-gnu/libcublas.so
-- found:/usr/lib/aarch64-linux-gnu/libcublasLt.so
CMake Warning at CMakeLists.txt:175 (message):
  Detected CUDA version is < 11.0.  SM80 not supported.

-- GPU_ARCHS is not defined. Generating CUDA code for default SMs: 35;53;61;70;75;72
-- ========================= Importing and creating target nvinfer_plugin ==========================
-- Looking for library nvinfer_plugin
-- Library that was found /pdk_files/tensorrt/lib/libnvinfer_plugin.so
-- ==========================================================================================
-- Protobuf proto/trtcaffe.proto -> proto/trtcaffe.pb.cc proto/trtcaffe.pb.h
-- /workspace/TensorRT/build/parsers/caffe
Generated: /workspace/TensorRT/build/parsers/onnx/third_party/onnx/onnx/onnx_onnx2trt_onnx-ml.proto
Generated: /workspace/TensorRT/build/parsers/onnx/third_party/onnx/onnx/onnx-operators_onnx2trt_onnx-ml.proto
-- 
-- ******** Summary ********
--   CMake version         : 3.14.4
--   CMake command         : /usr/local/bin/cmake
--   System                : Linux
--   C++ compiler          : /usr/bin/aarch64-linux-gnu-g++
--   C++ compiler version  : 7.5.0
--   CXX flags             : -Wno-deprecated-declarations  -DBUILD_SYSTEM=cmake_oss -Wall -Wno-deprecated-declarations -Wno-unused-function -Wnon-virtual-dtor
--   Build type            : Release
--   Compile definitions   : _PROTOBUF_INSTALL_DIR=/workspace/TensorRT/build/third_party.protobuf;ONNX_NAMESPACE=onnx2trt_onnx
--   CMAKE_PREFIX_PATH     : 
--   CMAKE_INSTALL_PREFIX  : /pdk_files/tensorrt/lib/..
--   CMAKE_MODULE_PATH     : 
-- 
--   ONNX version          : 1.6.0
--   ONNX NAMESPACE        : onnx2trt_onnx
--   ONNX_BUILD_TESTS      : OFF
--   ONNX_BUILD_BENCHMARKS : OFF
--   ONNX_USE_LITE_PROTO   : OFF
--   ONNXIFI_DUMMY_BACKEND : OFF
--   ONNXIFI_ENABLE_EXT    : OFF
-- 
--   Protobuf compiler     : 
--   Protobuf includes     : 
--   Protobuf libraries    : 
--   BUILD_ONNX_PYTHON     : OFF
-- Found TensorRT headers at /workspace/TensorRT/include
-- Find TensorRT libs at /pdk_files/tensorrt/lib/libnvinfer.so;/pdk_files/tensorrt/lib/libnvinfer_plugin.so;/pdk_files/tensorrt/lib/libmyelin.so
-- Adding new sample: sample_algorithm_selector
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_char_rnn
--     - Parsers Used: uff;caffe;onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_dynamic_reshape
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_fasterRCNN
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_googlenet
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_int8
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_int8_api
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mlp
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mnist
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mnist_api
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_movielens
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_movielens_mps
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_nmt
--     - Parsers Used: none
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_onnx_mnist
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_plugin
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_reformat_free_io
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_ssd
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_fasterRCNN
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_maskRCNN
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_mnist
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_uff_plugin_v2_ext
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_uff_ssd
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_onnx_mnist_coord_conv_ac
--     - Parsers Used: onnx
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: trtexec
--     - Parsers Used: caffe;uff;onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Configuring done
-- Generating done
-- Build files have been written to: /workspace/TensorRT/build

However, building fails with:

[ 58%] Linking CXX executable onnx2trt
/usr/lib/gcc-cross/aarch64-linux-gnu/7/../../../../aarch64-linux-gnu/bin/ld: warning: libcudart.so.10.2, needed by /pdk_files/tensorrt/lib/libnvinfer.so, not found (try using -rpath or -rpath-link)
/usr/lib/gcc-cross/aarch64-linux-gnu/7/../../../../aarch64-linux-gnu/bin/ld: warning: libcudnn.so.8, needed by /pdk_files/tensorrt/lib/libnvinfer.so, not found (try using -rpath or -rpath-link)
/usr/lib/gcc-cross/aarch64-linux-gnu/7/../../../../aarch64-linux-gnu/bin/ld: warning: libnvrtc.so.10.2, needed by /pdk_files/tensorrt/lib/libnvinfer.so, not found (try using -rpath or -rpath-link)
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMemcpyAsync'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnSetTensor4dDescriptor'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnPoolingForward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnActivationForward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreate@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionBackwardFilterAlgorithmMaxCount@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnConvolutionBackwardData@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetProgramLogSize@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetPTXSize@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaStreamWaitEvent@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaStreamDestroy'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyActivationDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaStreamWaitEvent'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetRNNParamsSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateLRNDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetPooling2dDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnTransformTensor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMemsetAsync'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetBatchNormalizationForwardTrainingExWorkspaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaLaunchKernel'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaFree'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetDropoutDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetBatchNormalizationBackwardExWorkspaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMallocHost'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaGetDeviceProperties'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetLRNDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventSynchronize'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetFilter4dDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaPeekAtLastError'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaFuncSetAttribute'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnConvolutionForward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaEventDestroy@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetFilterNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetTensorNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMalloc@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetActivationDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaGetDevice@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionBackwardDataAlgorithmMaxCount@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaGetDevice'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMemset'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaRegisterFunction'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcDestroyProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetPTX@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemcpyToSymbol@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetTensor4dDescriptorEx@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaRuntimeGetVersion@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyOpTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcCreateProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetVersion@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaLaunchKernel@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnBatchNormalizationForwardTrainingEx@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaGetDeviceProperties@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaStreamAddCallback@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnCreateTensorDescriptor'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaFuncSetAttribute@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventRecord'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventCreate'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaDeviceGetAttribute'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemcpy@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaFuncGetAttributes'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyConvolutionDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcCompileProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaCreateChannelDesc@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetRNNMatrixMathType@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetTensorNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetProgramLog@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnDestroyTensorDescriptor'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnAddTensor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventElapsedTime'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetTensor4dDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaStreamCreate'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionMathType@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionBackwardDataAlgorithm_v7@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyRNNDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetConvolution2dDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnBatchNormalizationBackwardEx@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaGetLastError@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaCreateTextureObject@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaGetErrorString@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnRNNForwardInference@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnDeriveBNTensorDescriptor'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaGetDeviceCount@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnDeriveBNTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroy@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaRegisterFatBinary@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateActivationDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcVersion@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaEventElapsedTime@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaFreeHost'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetConvolutionForwardWorkspaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionForwardAlgorithm_v7@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaRegisterFatBinaryEnd'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetErrorString@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetTensor4dDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaFree@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateRNNDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyDropoutDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventDestroy'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaGetErrorName'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaEventCreateWithFlags@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetTensorNdDescriptorEx@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyPoolingDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnConvolutionBackwardFilter@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionForwardAlgorithmMaxCount@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreatePoolingDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnSetStream'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaRegisterFunction@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetProperty@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyFilterDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDropoutGetStatesSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetConvolutionMathType@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaEventCreateWithFlags'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaEventRecord@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaStreamCreate@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetErrorString@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudnnBatchNormalizationForwardTraining'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnLRNCrossChannelForward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetRNNLinLayerBiasParams@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaDeviceSynchronize'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetBatchNormalizationTrainingExReserveSpaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaUnregisterFatBinary'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetRNNDescriptor_v6@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaStreamSynchronize'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaDestroyTextureObject@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSoftmaxForward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaHostAlloc'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaStreamDestroy@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaDeviceSynchronize@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemcpyAsync@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetRNNLinLayerMatrixParams@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaDeviceGetAttribute@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnGetConvolutionBackwardFilterAlgorithm_v7@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaPushCallConfiguration@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaRegisterFatBinary'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetConvolutionNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaStreamCreateWithPriority'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnOpTensor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateConvolutionDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaRegisterFatBinaryEnd@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateFilterDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnDestroyLRNDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaPopCallConfiguration'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaUnregisterFatBinary@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaEventSynchronize@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetOpTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `nvrtcAddNameExpression@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaPeekAtLastError@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemsetAsync@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetRNNWorkspaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMalloc'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnPoolingBackward@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaMemcpy'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetStream@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaPopCallConfiguration@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemGetInfo@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `nvrtcGetLoweredName@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetFilterNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaStreamSynchronize@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `__cudaRegisterVar@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudaMemcpy2DAsync@libcudart.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `cudnnSetPoolingNdDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaRegisterVar'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `__cudaPushCallConfiguration'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateOpTensorDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaGetLastError'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaGetErrorString'
/pdk_files/tensorrt/lib/libnvinfer_plugin.so: undefined reference to `cudaDeviceReset'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnGetConvolutionBackwardDataWorkspaceSize@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnCreateDropoutDescriptor@libcudnn.so.8'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `cudnnSetConvolutionGroupCount@libcudnn.so.8'
collect2: error: ld returned 1 exit status
parsers/onnx/CMakeFiles/onnx2trt.dir/build.make:91: recipe for target 'parsers/onnx/onnx2trt' failed
make[2]: *** [parsers/onnx/onnx2trt] Error 1
CMakeFiles/Makefile2:536: recipe for target 'parsers/onnx/CMakeFiles/onnx2trt.dir/all' failed
make[1]: *** [parsers/onnx/CMakeFiles/onnx2trt.dir/all] Error 2
Makefile:151: recipe for target 'all' failed
make: *** [all] Error 2
root@0870bd092350:/workspace/TensorRT/build#
Alex-EEE commented 3 years ago

Agreed, I also can't cross compile "out of the box." Same error as rarazac. Two of the files missing above, I can find on the container, so I supplied the path in a brute force way via this edit to CMakeLists.txt:

set(CMAKE_CXX_FLAGS "-Wno-deprecated-declarations ${CMAKE_CXX_FLAGS} -DBUILD_SYSTEM=cmake_oss -Wl,-rpath-link=/usr/local/cuda-10.2/targets/aarch64-linux/lib:/pdk_files/cudnn/usr/lib/aarch64-linux-gnu")

(I added the folders containing libcudart.so.10.2, libcudnn.so.8 via -rpath-link. Would love if this repo would patch the file themselves so I can upgrade in the future!)

However, I CANNOT FIND libnvrtc.so.10.2 anywhere in my container (And I downloaded the Jetpack that should have that file)

As it stands, I'm going to search my Jetson when I get home for this file (I provisioned it with the SD Card image from nVidia, so hoping since I didn't use the SDK manager, it's on there.)

@rarazac if you can find that file, will you upload it here? (I'll do the same, but won't be back until tomorrow night US time)

rarazac commented 3 years ago

Hey Alex-EEE, thanks for you input. I found the lib at:

root@e681a89083fc:/workspace/TensorRT/build# ll /usr/local/cuda-10.2/lib64/libnvrtc.so.10.2
lrwxrwxrwx 1 root root 19 Nov 13  2019 /usr/local/cuda-10.2/lib64/libnvrtc.so.10.2 -> libnvrtc.so.10.2.89

However, editing your CMakeLists.txt command to:

set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -DBUILD_SYSTEM=cmake_oss -Wl,-rpath=/usr/local/cuda-10.2/lib64:/usr/local/cuda-10.2/targets/aarch64-linux/lib:/pdk_files/cudnn/usr/lib/aarch64-linux-gnu")

Does not seem to solve the compile issue, i think because this is not the correct one for cross compile:

[ 58%] Linking CXX executable onnx2trt
/usr/lib/gcc-cross/aarch64-linux-gnu/7/../../../../aarch64-linux-gnu/bin/ld: warning: libnvrtc.so.10.2, needed by /pdk_files/tensorrt/lib/libnvinfer.so, not found (try using -rpath or -rpath-link)
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetProgramLogSize@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetPTXSize@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcDestroyProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetPTX@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcCreateProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcCompileProgram@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetProgramLog@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcVersion@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libnvinfer.so: undefined reference to `nvrtcGetErrorString@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `nvrtcAddNameExpression@libnvrtc.so.10.2'
/pdk_files/tensorrt/lib/libmyelin.so: undefined reference to `nvrtcGetLoweredName@libnvrtc.so.10.2'
collect2: error: ld returned 1 exit status
parsers/onnx/CMakeFiles/onnx2trt.dir/build.make:91: recipe for target 'parsers/onnx/onnx2trt' failed
make[2]: *** [parsers/onnx/onnx2trt] Error 1
CMakeFiles/Makefile2:536: recipe for target 'parsers/onnx/CMakeFiles/onnx2trt.dir/all' failed
make[1]: *** [parsers/onnx/CMakeFiles/onnx2trt.dir/all] Error 2
Makefile:151: recipe for target 'all' failed
make: *** [all] Error 2
root@e681a89083fc:/workspace/TensorRT/build#

Solution I used the libnvrtc found on the nano

ines@nano:~$ ldconfig -p | grep libnvrtc
        libnvrtc.so.10.2 (libc6,AArch64) => /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc.so.10.2
        libnvrtc.so (libc6,AArch64) => /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc.so
        libnvrtc-builtins.so.10.2 (libc6,AArch64) => /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc-builtins.so.10.2
        libnvrtc-builtins.so (libc6,AArch64) => /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc-builtins.so
ines@nano:~$

Copied it into to the build container into following dir:

root@e681a89083fc:/workspace/TensorRT/build#  ll /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc.so.10.2 
-rw-r--r-- 1 root root 20432800 Apr  6 14:15 /usr/local/cuda-10.2/targets/aarch64-linux/lib/libnvrtc.so.10.2

And it seems to work, thanks to your brute force adaption of CMakeLists:

root@e681a89083fc:/workspace/TensorRT/build# make -j 8
[  3%] Built target third_party.protobuf
[  6%] Built target third_party.protobuf_aarch64
[  6%] Built target gen_onnx_proto
[  6%] Built target caffe_proto
[  9%] Built target onnx_proto
[ 13%] Built target nvonnxparser
[ 17%] Built target nvonnxparser_static
[ 28%] Built target nvcaffeparser
[ 40%] Built target nvcaffeparser_static
[ 42%] Built target getSupportedAPITest
[ 44%] Built target sample_dynamic_reshape
[ 44%] Built target sample_googlenet
[ 45%] Built target sample_fasterRCNN
[ 46%] Built target sample_algorithm_selector
[ 48%] Built target sample_char_rnn
[ 49%] Built target sample_int8
[ 50%] Built target sample_mnist
[ 51%] Built target sample_int8_api
[ 53%] Built target sample_mlp
[ 54%] Built target sample_movielens
[ 55%] Built target sample_movielens_mps
[ 56%] Built target sample_mnist_api
[ 74%] Built target onnx
[ 75%] Built target sample_plugin
[ 76%] Built target sample_ssd
[ 77%] Built target sample_onnx_mnist
[ 79%] Built target sample_uff_maskRCNN
[ 80%] Built target sample_reformat_free_io
[ 81%] Built target sample_uff_fasterRCNN
[ 82%] Built target sample_uff_mnist
[ 91%] Built target sample_nmt
[ 92%] Built target sample_uff_plugin_v2_ext
[ 93%] Built target sample_onnx_mnist_coord_conv_ac
[ 95%] Built target sample_uff_ssd
[ 96%] Built target onnx2trt
[100%] Built target trtexec

Here you can find all files which I had to change:

dongyi-kim commented 3 years ago

hi there :) I also tried too many brute-force tries to cross-compile trt into jetson tx2/xavier. but failed. and finally found your works here. thanks about it. i gonna contribute your works when I got new something useful. But when i tried your way with @rarazac 's given files and the cmake command, I still fail with below logs.

could you comment about it? I used your CMakeLists, Dockerfile, libnvrtc and cmake command above. Plz let me know when I lost something.

[ 56%] Linking CXX shared library pwd/out/libnvcaffeparser.so
/pdk_files/tensorrt/lib/libnvinfer.so: error adding symbols: File in wrong format
collect2: error: ld returned 1 exit status
parsers/caffe/CMakeFiles/nvcaffeparser.dir/build.make:484: recipe for target 'parsers/caffe/pwd/out/libnvcaffeparser.so.7.2.3' failed
make[2]: *** [parsers/caffe/pwd/out/libnvcaffeparser.so.7.2.3] Error 1
CMakeFiles/Makefile2:316: recipe for target 'parsers/caffe/CMakeFiles/nvcaffeparser.dir/all' failed
make[1]: *** [parsers/caffe/CMakeFiles/nvcaffeparser.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 56%] Linking CXX static library pwd/out/libnvcaffeparser_static.a
[ 57%] Built target nvcaffeparser_static
[ 58%] Linking CXX static library libonnx.a
[ 58%] Built target onnx
[ 58%] Linking CXX shared library pwd/out/libnvonnxparser.so
/pdk_files/tensorrt/lib/libnvinfer.so: error adding symbols: File in wrong format
collect2: error: ld returned 1 exit status
parsers/onnx/CMakeFiles/nvonnxparser.dir/build.make:209: recipe for target 'parsers/onnx/pwd/out/libnvonnxparser.so.7.1.3' failed
make[2]: *** [parsers/onnx/pwd/out/libnvonnxparser.so.7.1.3] Error 1
CMakeFiles/Makefile2:454: recipe for target 'parsers/onnx/CMakeFiles/nvonnxparser.dir/all' failed
make[1]: *** [parsers/onnx/CMakeFiles/nvonnxparser.dir/all] Error 2
[ 58%] Linking CXX static library libnvonnxparser_static.a
[ 58%] Built target nvonnxparser_static
Makefile:151: recipe for target 'all' failed
make: *** [all] Error 2
rarazac commented 3 years ago

Hi @dongyi-kim

I think the problem is this line: /pdk_files/tensorrt/lib/libnvinfer.so: error adding symbols: File in wrong format

Indicates that the libs there are not for your target. You have to download the libs with JetPack SDK. Here are the steps from the readme:

  1. (Optional) JetPack SDK for Jetson builds

    Using the JetPack SDK manager, download the host components. Steps:

    1. Download and launch the SDK manager. Login with your developer account.
    2. Select the platform and target OS (example: Jetson AGX Xavier, Linux Jetpack 4.4), and click Continue.
    3. Under Download & Install Options change the download folder and select Download now, Install later. Agree to the license terms and click Continue.
    4. Move the extracted files into the <TensorRT-OSS>/docker/jetpack_files folder.
dongyi-kim commented 3 years ago

thx your comment. I also look at that point, it's strange. I surely downloaded jetpack_files from sdk manager. (Jetpack 4.4.1). like below

trtuser@80d9ae2a9c6c:/pdk_files$ ls
NVIDIA_Nsight_Graphics_L4T_2020.1.20059.deb
NVIDIA_VisionWorks_References.zip
NsightSystems-linux-public-2020.4.2.18-f0b18f6.deb
OpenCV-4.1.1-2-gd5a58aa75-aarch64-dev.deb
OpenCV-4.1.1-2-gd5a58aa75-aarch64-libs.deb
OpenCV-4.1.1-2-gd5a58aa75-aarch64-licenses.deb
OpenCV-4.1.1-2-gd5a58aa75-aarch64-python.deb
OpenCV-4.1.1-2-gd5a58aa75-aarch64-samples.deb
cuda-repo-cross-aarch64-10-2-local-10.2.89_1.0-1_all.deb
cuda-repo-l4t-10-2-local-10.2.89_1.0-1_arm64.deb
cuda-repo-ubuntu1804-10-2-local-10.2.89-440.40_1.0-1_amd64.deb
cudnn
graphsurgeon-tf_7.1.3-1+cuda10.2_arm64.deb
libcudnn8-dev_8.0.0.180-1+cuda10.2_arm64.deb
libcudnn8-doc_8.0.0.180-1+cuda10.2_arm64.deb
libcudnn8_8.0.0.180-1+cuda10.2_arm64.deb
libnvidia-container-tools_0.9.0_beta.1_arm64.deb
libnvidia-container0_0.9.0_beta.1_arm64.deb
libnvinfer-bin_7.1.3-1+cuda10.2_arm64.deb
libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb
libnvinfer-doc_7.1.3-1+cuda10.2_all.deb
libnvinfer-plugin-dev_7.1.3-1+cuda10.2_arm64.deb
libnvinfer-plugin7_7.1.3-1+cuda10.2_arm64.deb
libnvinfer-samples_7.1.3-1+cuda10.2_all.deb
libnvinfer7_7.1.3-1+cuda10.2_arm64.deb
libnvonnxparsers-dev_7.1.3-1+cuda10.2_arm64.deb
libnvonnxparsers7_7.1.3-1+cuda10.2_arm64.deb
libnvparsers-dev_7.1.3-1+cuda10.2_arm64.deb
libnvparsers7_7.1.3-1+cuda10.2_arm64.deb
libvisionworks-repo_1.6.0.501_amd64.deb
libvisionworks-repo_1.6.0.501_arm64.deb
libvisionworks-sfm-repo_0.90.4.501_amd64.deb
libvisionworks-sfm-repo_0.90.4.501_arm64.deb
libvisionworks-tracking-repo_0.88.2.501_amd64.deb
libvisionworks-tracking-repo_0.88.2.501_arm64.deb
nvidia-container-csv-cuda_10.2.89-1_arm64.deb
nvidia-container-csv-cudnn_8.0.0.180-1+cuda10.2_arm64.deb
nvidia-container-csv-tensorrt_7.1.3.0-1+cuda10.2_arm64.deb
nvidia-container-csv-visionworks_1.6.0.501_arm64.deb
nvidia-container-runtime_3.1.0-1_arm64.deb
nvidia-container-toolkit_1.0.1-1_arm64.deb
nvidia-docker2_2.2.0-1_all.deb
nvidia-l4t-jetson-multimedia-api_32.4.4-20201016123640_arm64.deb
python-libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb
python-libnvinfer_7.1.3-1+cuda10.2_arm64.deb
python3-libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb
python3-libnvinfer_7.1.3-1+cuda10.2_arm64.deb
sdkml3_jetpack_l4t_441.json
stubify.sh
tensorrt
tensorrt_7.1.3.0-1+cuda10.2_arm64.deb
uff-converter-tf_7.1.3-1+cuda10.2_arm64.deb
vpi-cross-aarch64-l4t-0.4.4-cuda10-x86_64-linux.deb
vpi-dev-0.4.4-cuda10-aarch64-l4t.deb
vpi-dev-0.4.4-cuda10-x86_64-linux.deb
vpi-lib-0.4.4-cuda10-aarch64-l4t.deb
vpi-lib-0.4.4-cuda10-x86_64-linux.deb
vpi-samples-0.4.4-cuda10-aarch64-l4t.deb
vpi-samples-0.4.4-cuda10-x86_64-linux.deb

and envs also indicates that files TRT_LIBPATH=/pdk_files/tensorrt/lib But it failed with File in wrong format error. :( Haven't encountered this situation?

rarazac commented 3 years ago

When I had this problem it was due wrong arch of a lib. Maybe your build system does not use the correct toolchain? I used following cmake command and it worked inside my docker container:

root@0b53a8d58ed7:/workspace/TensorRT# mkdir build
root@0b53a8d58ed7:/workspace/TensorRT# cmake .. -DTRT_LIB_DIR=$TRT_RELEASE/lib -DTRT_OUT_DIR=`pwd`/out -DBUILD_PLUGINS=OFF -DCMAKE_TOOLCHAIN_FILE=$TRT_SOURCE/cmake/toolchains/cmake_aarch64.toolchain -DCMAKE_CUDA_SEPARABLE_COMPILATION=OFF -DCUDA_VERSION=10.2 -DCUBLASLT_LIB="/usr/lib/aarch64-linux-gnu/libcublasLt.so" -DCUBLAS_LIB="/usr/lib/aarch64-linux-gnu/libcublas.so" -DCUDNN_LIB="/pdk_files/cudnn/lib/libcudnn.so.8"
root@0b53a8d58ed7:/workspace/TensorRT# make -j 8

And it compiled....

Env vars are:

root@0b53a8d58ed7:/workspace/TensorRT/build# echo $TRT_SOURCE/                           
/workspace/TensorRT/
root@0b53a8d58ed7:/workspace/TensorRT/build# echo $TRT_RELEASE/
/pdk_files/tensorrt/
dongyi-kim commented 3 years ago

thx for your check. I used identically same commands you gave in previous works. But it failed. lol :(((((((((( Can i ask you one more? it would be so helpful if you share me your env result inside docker container. mine is like below.

trtuser@bdbaa0e55ba5:/workspace$ env
LS_COLORS=rs=0:di=01;34:ln=01;36:mh=00:pi=40;33:so=01;35:do=01;35:bd=40;33;01:cd=40;33;01:or=40;31;01:mi=00:su=37;41:sg=30;43:ca=30;41:tw=30;42:ow=34;42:st=37;44:ex=01;32:*.tar=01;31:*.tgz=01;31:*.arc=01;31:*.arj=01;31:*.taz=01;31:*.lha=01;31:*.lz4=01;31:*.lzh=01;31:*.lzma=01;31:*.tlz=01;31:*.txz=01;31:*.tzo=01;31:*.t7z=01;31:*.zip=01;31:*.z=01;31:*.Z=01;31:*.dz=01;31:*.gz=01;31:*.lrz=01;31:*.lz=01;31:*.lzo=01;31:*.xz=01;31:*.zst=01;31:*.tzst=01;31:*.bz2=01;31:*.bz=01;31:*.tbz=01;31:*.tbz2=01;31:*.tz=01;31:*.deb=01;31:*.rpm=01;31:*.jar=01;31:*.war=01;31:*.ear=01;31:*.sar=01;31:*.rar=01;31:*.alz=01;31:*.ace=01;31:*.zoo=01;31:*.cpio=01;31:*.7z=01;31:*.rz=01;31:*.cab=01;31:*.wim=01;31:*.swm=01;31:*.dwm=01;31:*.esd=01;31:*.jpg=01;35:*.jpeg=01;35:*.mjpg=01;35:*.mjpeg=01;35:*.gif=01;35:*.bmp=01;35:*.pbm=01;35:*.pgm=01;35:*.ppm=01;35:*.tga=01;35:*.xbm=01;35:*.xpm=01;35:*.tif=01;35:*.tiff=01;35:*.png=01;35:*.svg=01;35:*.svgz=01;35:*.mng=01;35:*.pcx=01;35:*.mov=01;35:*.mpg=01;35:*.mpeg=01;35:*.m2v=01;35:*.mkv=01;35:*.webm=01;35:*.ogm=01;35:*.mp4=01;35:*.m4v=01;35:*.mp4v=01;35:*.vob=01;35:*.qt=01;35:*.nuv=01;35:*.wmv=01;35:*.asf=01;35:*.rm=01;35:*.rmvb=01;35:*.flc=01;35:*.avi=01;35:*.fli=01;35:*.flv=01;35:*.gl=01;35:*.dl=01;35:*.xcf=01;35:*.xwd=01;35:*.yuv=01;35:*.cgm=01;35:*.emf=01;35:*.ogv=01;35:*.ogx=01;35:*.aac=00;36:*.au=00;36:*.flac=00;36:*.m4a=00;36:*.mid=00;36:*.midi=00;36:*.mka=00;36:*.mp3=00;36:*.mpc=00;36:*.ogg=00;36:*.ra=00;36:*.wav=00;36:*.oga=00;36:*.opus=00;36:*.spx=00;36:*.xspf=00;36:
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
HOSTNAME=bdbaa0e55ba5
NVIDIA_VISIBLE_DEVICES=all
NCCL_VERSION=2.8.4
PWD=/workspace
HOME=/home/trtuser
LIBRARY_PATH=/usr/local/cuda/lib64/stubs
TERM=xterm
CUDA_PKG_VERSION=10-2=10.2.89-1
CUDA_VERSION=10.2.89
TRT_OSSPATH=/workspace/TensorRT
TRT_LIBPATH=/pdk_files/tensorrt/lib
NVIDIA_DRIVER_CAPABILITIES=compute,utility
SHLVL=1
NVIDIA_REQUIRE_CUDA=cuda>=10.2 brand=tesla,driver>=396,driver<397 brand=tesla,driver>=410,driver<411 brand=tesla,driver>=418,driver<419 brand=tesla,driver>=440,driver<441
PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
_=/usr/bin/env
trtuser@bdbaa0e55ba5:/workspace$
rarazac commented 3 years ago

Hi

My env is:

root@e74199ba6658:/workspace/TensorRT/build# env
LS_COLORS=rs=0:di=01;34:ln=01;36:mh=00:pi=40;33:so=01;35:do=01;35:bd=40;33;01:cd=40;33;01:or=40;31;01:mi=00:su=37;41:sg=30;43:ca=30;41:tw=30;42:ow=34;42:st=37;44:ex=01;32:*.tar=01;31:*.tgz=01;31:*.arc=01;31:*.arj=01;31:*.taz=01;31:*.lha=01;31:*.lz4=01;31:*.lzh=01;31:*.lzma=01;31:*.tlz=01;31:*.txz=01;31:*.tzo=01;31:*.t7z=01;31:*.zip=01;31:*.z=01;31:*.Z=01;31:*.dz=01;31:*.gz=01;31:*.lrz=01;31:*.lz=01;31:*.lzo=01;31:*.xz=01;31:*.zst=01;31:*.tzst=01;31:*.bz2=01;31:*.bz=01;31:*.tbz=01;31:*.tbz2=01;31:*.tz=01;31:*.deb=01;31:*.rpm=01;31:*.jar=01;31:*.war=01;31:*.ear=01;31:*.sar=01;31:*.rar=01;31:*.alz=01;31:*.ace=01;31:*.zoo=01;31:*.cpio=01;31:*.7z=01;31:*.rz=01;31:*.cab=01;31:*.wim=01;31:*.swm=01;31:*.dwm=01;31:*.esd=01;31:*.jpg=01;35:*.jpeg=01;35:*.mjpg=01;35:*.mjpeg=01;35:*.gif=01;35:*.bmp=01;35:*.pbm=01;35:*.pgm=01;35:*.ppm=01;35:*.tga=01;35:*.xbm=01;35:*.xpm=01;35:*.tif=01;35:*.tiff=01;35:*.png=01;35:*.svg=01;35:*.svgz=01;35:*.mng=01;35:*.pcx=01;35:*.mov=01;35:*.mpg=01;35:*.mpeg=01;35:*.m2v=01;35:*.mkv=01;35:*.webm=01;35:*.ogm=01;35:*.mp4=01;35:*.m4v=01;35:*.mp4v=01;35:*.vob=01;35:*.qt=01;35:*.nuv=01;35:*.wmv=01;35:*.asf=01;35:*.rm=01;35:*.rmvb=01;35:*.flc=01;35:*.avi=01;35:*.fli=01;35:*.flv=01;35:*.gl=01;35:*.dl=01;35:*.xcf=01;35:*.xwd=01;35:*.yuv=01;35:*.cgm=01;35:*.emf=01;35:*.ogv=01;35:*.ogx=01;35:*.aac=00;36:*.au=00;36:*.flac=00;36:*.m4a=00;36:*.mid=00;36:*.midi=00;36:*.mka=00;36:*.mp3=00;36:*.mpc=00;36:*.ogg=00;36:*.ra=00;36:*.wav=00;36:*.oga=00;36:*.opus=00;36:*.spx=00;36:*.xspf=00;36:
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
HOSTNAME=e74199ba6658
NVIDIA_VISIBLE_DEVICES=all
NCCL_VERSION=2.8.4
PWD=/workspace/TensorRT/build
HOME=/root
LIBRARY_PATH=/usr/local/cuda/lib64/stubs
TRT_SOURCE=/workspace/TensorRT
TERM=xterm
TRT_RELEASE=/pdk_files/tensorrt
CUDA_PKG_VERSION=10-2=10.2.89-1
CUDA_VERSION=10.2.89
NVIDIA_DRIVER_CAPABILITIES=compute,utility
SHLVL=1
NVIDIA_REQUIRE_CUDA=cuda>=10.2 brand=tesla,driver>=396,driver<397 brand=tesla,driver>=410,driver<411 brand=tesla,driver>=418,driver<419 brand=tesla,driver>=440,driver<441
PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
_=/usr/bin/env
OLDPWD=/workspace/TensorRT

Hope it helps you... Do you still have the wrong format error?

I have here again my current dockerfile, maybe I have changed something...

dongyi-kim commented 3 years ago

thx for your help!

I fixed my problem. I cleaned up everything and started again from scratch, and followed up your works above and in my case, I also added below cmake option Alex used above.

set(CMAKE_CXX_FLAGS "-Wno-deprecated-declarations ${CMAKE_CXX_FLAGS} -DBUILD_SYSTEM=cmake_oss -Wl,-rpath-link=/usr/local/cuda-10.2/targets/aarch64-linux/lib:/pdk_files/cudnn/usr/lib/aarch64-linux-gnu")
WangFengtu1996 commented 3 years ago

Hi,all About the README.md, I have some questions.

(Optional) JetPack SDK for Jetson builds
Using the JetPack SDK manager, download the host components. Steps:

Download and launch the SDK manager. Login with your developer account.
Select the platform and target OS (example: Jetson AGX Xavier, Linux Jetpack 4.4), and click Continue.
Under Download & Install Options change the download folder and select Download now, Install later. Agree to the license terms and click Continue.
Move the extracted files into the <TensorRT-OSS>/docker/jetpack_files folder.

I got some .dev package by SDKManager software. 

cuda-repo-cross-aarch64-10-2-local-10.2.89_1.0-1_all.deb        libvisionworks-sfm-repo_0.90.4.501_arm64.deb                          sdkml3_jetpack_l4t_451_deepstream.json
cuda-repo-l4t-10-2-local-10.2.89_1.0-1_arm64.deb                libvisionworks-tracking-repo_0.88.2.501_amd64.deb                     sdkml3_jetpack_l4t_451.json
cuda-repo-ubuntu1804-10-2-local-10.2.89-440.40_1.0-1_amd64.deb  libvisionworks-tracking-repo_0.88.2.501_arm64.deb                     sdkml3_jetpack_l4t_45.json
deepstream-5.1_5.1.0-1_arm64.deb.mtd                            nsight-systems-cli-2020.5.3_2020.5.3.17-1_arm64.deb                   Tegra_Linux_Sample-Root-Filesystem_R32.5.0_aarch64.tbz2
graphsurgeon-tf_7.1.3-1+cuda10.2_arm64.deb                      NsightSystems-linux-public-2020.5.3.17-0256620.deb                    Tegra_Linux_Sample-Root-Filesystem_R32.5.1_aarch64.tbz2.mtd
Jetson_Linux_R32.5.0_aarch64.tbz2                               nvidia-container-csv-cuda_10.2.89-1_arm64.deb                         tensorrt_7.1.3.0-1+cuda10.2_arm64.deb
Jetson_Linux_R32.5.1_aarch64.tbz2.mtd                           nvidia-container-csv-cudnn_8.0.0.180-1+cuda10.2_arm64.deb             uff-converter-tf_7.1.3-1+cuda10.2_arm64.deb
libcudnn8_8.0.0.180-1+cuda10.2_arm64.deb                        nvidia-container-csv-tensorrt_7.1.3.0-1+cuda10.2_arm64.deb            vpi-cross-aarch64-l4t-1.0.12-cuda10-x86_64-linux.deb
libcudnn8-dev_8.0.0.180-1+cuda10.2_arm64.deb                    nvidia-container-csv-visionworks_1.6.0.501_arm64.deb                  vpi-cross-aarch64-l4t-1.0.15-x86_64-linux.deb.mtd
libcudnn8-doc_8.0.0.180-1+cuda10.2_arm64.deb                    nvidia-container-runtime_3.1.0-1_arm64.deb                            vpi-demos-1.0.12-cuda10-aarch64-l4t.deb
libnvidia-container0_0.9.0_beta.1_arm64.deb                     nvidia-container-toolkit_1.0.1-1_arm64.deb                            vpi-demos-1.0.12-cuda10-x86_64-linux-ubuntu1804.deb
libnvidia-container-tools_0.9.0_beta.1_arm64.deb                nvidia-docker2_2.2.0-1_all.deb                                        vpi-demos-1.0.15-aarch64-l4t.deb
libnvinfer7_7.1.3-1+cuda10.2_arm64.deb                          nvidia-l4t-jetson-multimedia-api_32.5.0-20210115151051_arm64.deb      vpi-demos-1.0.15-cuda10-x86_64-linux-ubuntu1804.deb.mtd
libnvinfer-bin_7.1.3-1+cuda10.2_arm64.deb                       nvidia-l4t-jetson-multimedia-api_32.5.1-20210219084708_arm64.deb.mtd  vpi-dev-1.0.12-cuda10-aarch64-l4t.deb
libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb                       NVIDIA_Nsight_Graphics_L4T_Public_2020.5.20329.deb                    vpi-dev-1.0.12-cuda10-x86_64-linux.deb
libnvinfer-doc_7.1.3-1+cuda10.2_all.deb                         NVIDIA_VisionWorks_References.zip                                     vpi-dev-1.0.15-aarch64-l4t.deb
libnvinfer-plugin7_7.1.3-1+cuda10.2_arm64.deb                   OpenCV-4.1.1-2-gd5a58aa75-aarch64-dev.deb                             vpi-dev-1.0.15-cuda10-x86_64-linux.deb
libnvinfer-plugin-dev_7.1.3-1+cuda10.2_arm64.deb                OpenCV-4.1.1-2-gd5a58aa75-aarch64-libs.deb                            vpi-lib-1.0.12-cuda10-aarch64-l4t.deb
libnvinfer-samples_7.1.3-1+cuda10.2_all.deb                     OpenCV-4.1.1-2-gd5a58aa75-aarch64-licenses.deb                        vpi-lib-1.0.12-cuda10-x86_64-linux.deb
libnvonnxparsers7_7.1.3-1+cuda10.2_arm64.deb                    OpenCV-4.1.1-2-gd5a58aa75-aarch64-python.deb                          vpi-lib-1.0.15-aarch64-l4t.deb.mtd
libnvonnxparsers-dev_7.1.3-1+cuda10.2_arm64.deb                 OpenCV-4.1.1-2-gd5a58aa75-aarch64-samples.deb                         vpi-lib-1.0.15-cuda10-x86_64-linux.deb
libnvparsers7_7.1.3-1+cuda10.2_arm64.deb                        python3-libnvinfer_7.1.3-1+cuda10.2_arm64.deb                         vpi-samples-1.0.12-cuda10-aarch64-l4t.deb
libnvparsers-dev_7.1.3-1+cuda10.2_arm64.deb                     python3-libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb                     vpi-samples-1.0.12-cuda10-x86_64-linux.deb
libvisionworks-repo_1.6.0.501_amd64.deb                         python-libnvinfer_7.1.3-1+cuda10.2_arm64.deb                          vpi-samples-1.0.15-aarch64-l4t.deb.mtd
libvisionworks-repo_1.6.0.501_arm64.deb                         python-libnvinfer-dev_7.1.3-1+cuda10.2_arm64.deb                      vpi-samples-1.0.15-cuda10-x86_64-linux.deb.mtd
libvisionworks-sfm-repo_0.90.4.501_amd64.deb                    sdkmanager_1.5.1-7814_amd64.deb

which files should be extracted and move to the docker/jepack_files folder? just the Jetson_Linux_R32.5.0_aarch64.tbz2 file ?

WangFengtu1996 commented 3 years ago

read related dockerfile then get related information.

WangFengtu1996 commented 3 years ago

when I execute the command cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=pwd/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64.toolchain -DCUDA_VERSION=10.2 , I got the linked error.

trtuser@ecb476f7ab25:/workspace/TensorRT/build$  cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64.toolchain -DCUDA_VERSION=10.2
Building for TensorRT version: 7.2.3, library version: 7
-- Targeting TRT Platform: aarch64
-- CUDA version set to 10.2
-- cuDNN version set to 8.0
-- Protobuf version set to 3.0.0
-- Setting up another Protobuf build for cross compilation targeting aarch64-Linux
-- Using libprotobuf /workspace/TensorRT/build/third_party.protobuf_aarch64/lib/libprotobuf.a
-- ========================= Importing and creating target nvinfer ==========================
-- Looking for library nvinfer
-- Library that was found /pdk_files/tensorrt/lib/libnvinfer.so
-- ==========================================================================================
-- ========================= Importing and creating target nvuffparser ==========================
-- Looking for library nvparsers
-- Library that was found /pdk_files/tensorrt/lib/libnvparsers.so
-- ==========================================================================================
CMake Warning at CMakeLists.txt:157 (message):
  Detected CUDA version is < 11.0.  SM80 not supported.

-- GPU_ARCHS is not defined. Generating CUDA code for default SMs: 35;53;61;70;75;72
-- Protobuf proto/trtcaffe.proto -> proto/trtcaffe.pb.cc proto/trtcaffe.pb.h
-- /workspace/TensorRT/build/parsers/caffe
CMake Error at parsers/CMakeLists.txt:34 (add_subdirectory):
  The source directory

    /workspace/TensorRT/parsers/onnx

  does not contain a CMakeLists.txt file.

-- Adding new sample: sample_algorithm_selector
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_char_rnn
--     - Parsers Used: uff;caffe;onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_dynamic_reshape
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_fasterRCNN
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_googlenet
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_int8
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_int8_api
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mlp
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mnist
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_mnist_api
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_movielens
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_movielens_mps
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_nmt
--     - Parsers Used: none
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_onnx_mnist
--     - Parsers Used: onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_plugin
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_reformat_free_io
--     - Parsers Used: caffe
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_ssd
--     - Parsers Used: caffe
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_fasterRCNN
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_maskRCNN
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_uff_mnist
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_uff_plugin_v2_ext
--     - Parsers Used: uff
--     - InferPlugin Used: OFF
--     - Licensing: opensource
-- Adding new sample: sample_uff_ssd
--     - Parsers Used: uff
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: sample_onnx_mnist_coord_conv_ac
--     - Parsers Used: onnx
--     - InferPlugin Used: ON
--     - Licensing: opensource
-- Adding new sample: trtexec
--     - Parsers Used: caffe;uff;onnx
--     - InferPlugin Used: OFF
--     - Licensing: opensource
CMake Error: The following variables are used in this project, but they are set to NOTFOUND.
Please set them or make sure they are set and tested correctly in the CMake files:
CUBLASLT_LIB
    linked by target "nvinfer_plugin" in directory /workspace/TensorRT/plugin
CUBLAS_LIB
    linked by target "nvinfer_plugin" in directory /workspace/TensorRT/plugin
    linked by target "sample_algorithm_selector" in directory /workspace/TensorRT/samples/opensource/sampleAlgorithmSelector
    linked by target "sample_char_rnn" in directory /workspace/TensorRT/samples/opensource/sampleCharRNN
    linked by target "sample_dynamic_reshape" in directory /workspace/TensorRT/samples/opensource/sampleDynamicReshape
    linked by target "sample_fasterRCNN" in directory /workspace/TensorRT/samples/opensource/sampleFasterRCNN
    linked by target "sample_googlenet" in directory /workspace/TensorRT/samples/opensource/sampleGoogleNet
    linked by target "sample_int8" in directory /workspace/TensorRT/samples/opensource/sampleINT8
    linked by target "sample_int8_api" in directory /workspace/TensorRT/samples/opensource/sampleINT8API
    linked by target "sample_mlp" in directory /workspace/TensorRT/samples/opensource/sampleMLP
    linked by target "sample_mnist" in directory /workspace/TensorRT/samples/opensource/sampleMNIST
    linked by target "sample_mnist_api" in directory /workspace/TensorRT/samples/opensource/sampleMNISTAPI
    linked by target "sample_movielens" in directory /workspace/TensorRT/samples/opensource/sampleMovieLens
    linked by target "sample_movielens_mps" in directory /workspace/TensorRT/samples/opensource/sampleMovieLensMPS
    linked by target "sample_nmt" in directory /workspace/TensorRT/samples/opensource/sampleNMT
    linked by target "sample_onnx_mnist" in directory /workspace/TensorRT/samples/opensource/sampleOnnxMNIST
    linked by target "sample_plugin" in directory /workspace/TensorRT/samples/opensource/samplePlugin
    linked by target "sample_reformat_free_io" in directory /workspace/TensorRT/samples/opensource/sampleReformatFreeIO
    linked by target "sample_ssd" in directory /workspace/TensorRT/samples/opensource/sampleSSD
    linked by target "sample_uff_fasterRCNN" in directory /workspace/TensorRT/samples/opensource/sampleUffFasterRCNN
    linked by target "sample_uff_maskRCNN" in directory /workspace/TensorRT/samples/opensource/sampleUffMaskRCNN
    linked by target "sample_uff_mnist" in directory /workspace/TensorRT/samples/opensource/sampleUffMNIST
    linked by target "sample_uff_plugin_v2_ext" in directory /workspace/TensorRT/samples/opensource/sampleUffPluginV2Ext
    linked by target "sample_uff_ssd" in directory /workspace/TensorRT/samples/opensource/sampleUffSSD
    linked by target "sample_onnx_mnist_coord_conv_ac" in directory /workspace/TensorRT/samples/opensource/sampleOnnxMnistCoordConvAC
    linked by target "trtexec" in directory /workspace/TensorRT/samples/opensource/trtexec
CUDNN_LIB
    linked by target "nvinfer_plugin" in directory /workspace/TensorRT/plugin
    linked by target "sample_algorithm_selector" in directory /workspace/TensorRT/samples/opensource/sampleAlgorithmSelector
    linked by target "sample_char_rnn" in directory /workspace/TensorRT/samples/opensource/sampleCharRNN
    linked by target "sample_dynamic_reshape" in directory /workspace/TensorRT/samples/opensource/sampleDynamicReshape
    linked by target "sample_fasterRCNN" in directory /workspace/TensorRT/samples/opensource/sampleFasterRCNN
    linked by target "sample_googlenet" in directory /workspace/TensorRT/samples/opensource/sampleGoogleNet
    linked by target "sample_int8" in directory /workspace/TensorRT/samples/opensource/sampleINT8
    linked by target "sample_int8_api" in directory /workspace/TensorRT/samples/opensource/sampleINT8API
    linked by target "sample_mlp" in directory /workspace/TensorRT/samples/opensource/sampleMLP
    linked by target "sample_mnist" in directory /workspace/TensorRT/samples/opensource/sampleMNIST
    linked by target "sample_mnist_api" in directory /workspace/TensorRT/samples/opensource/sampleMNISTAPI
    linked by target "sample_movielens" in directory /workspace/TensorRT/samples/opensource/sampleMovieLens
    linked by target "sample_movielens_mps" in directory /workspace/TensorRT/samples/opensource/sampleMovieLensMPS
    linked by target "sample_nmt" in directory /workspace/TensorRT/samples/opensource/sampleNMT
    linked by target "sample_onnx_mnist" in directory /workspace/TensorRT/samples/opensource/sampleOnnxMNIST
    linked by target "sample_plugin" in directory /workspace/TensorRT/samples/opensource/samplePlugin
    linked by target "sample_reformat_free_io" in directory /workspace/TensorRT/samples/opensource/sampleReformatFreeIO
    linked by target "sample_ssd" in directory /workspace/TensorRT/samples/opensource/sampleSSD
    linked by target "sample_uff_fasterRCNN" in directory /workspace/TensorRT/samples/opensource/sampleUffFasterRCNN
    linked by target "sample_uff_maskRCNN" in directory /workspace/TensorRT/samples/opensource/sampleUffMaskRCNN
    linked by target "sample_uff_mnist" in directory /workspace/TensorRT/samples/opensource/sampleUffMNIST
    linked by target "sample_uff_plugin_v2_ext" in directory /workspace/TensorRT/samples/opensource/sampleUffPluginV2Ext
    linked by target "sample_uff_ssd" in directory /workspace/TensorRT/samples/opensource/sampleUffSSD
    linked by target "sample_onnx_mnist_coord_conv_ac" in directory /workspace/TensorRT/samples/opensource/sampleOnnxMnistCoordConvAC
    linked by target "trtexec" in directory /workspace/TensorRT/samples/opensource/trtexec

-- Configuring incomplete, errors occurred!
See also "/workspace/TensorRT/build/CMakeFiles/CMakeOutput.log".
See also "/workspace/TensorRT/build/CMakeFiles/CMakeError.log".
WangFengtu1996 commented 3 years ago

I execute the command cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=pwd/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64.toolchain -DCUDA_VERSION=10.2 -DCUBLASLT_LIB=/usr/lib/aarch64-linux-gnu/libcublasLt.so -DCUBLAS_LIB=/usr/lib/aarch64-linux-gnu/libcublas.so -DCUDNN_LIB=/pdk_files/cudnn/usr/lib/aarch64-linux-gnu/libcudnn.so

twmht commented 1 year ago

any update on this? is there any official image to use cross compiler?

cxiang26 commented 1 year ago

is there any official image to use cross compiler?