Update TensorRT to version 6.0.1.5 (#1966)

* remove onnx-tensorrt submodule

* add new onnx-tensorrt submodule (experiment) for trt6

* update engine build for trt6

* update compile and compute for tensorrt6.0

* Update tensorrt_execution_provider.cc

* Update tensorrt_execution_provider.cc

* Update tensorrt_execution_provider.cc

* Update tensorrt_execution_provider.cc

* switch to onnx-tensorrt master for TensorRT6'

* Update tensorrt_execution_provider.cc

* Handle dynamic batch size and add memcpy in TensorRT EP

* update test cases

* Update tensorrt_execution_provider.cc

* update onnx-tensorrt submodule

* Update Dockerfile.ubuntu_tensorrt

* Update Dockerfile.ubuntu_tensorrt

* Update run_dockerbuild.sh

* Update run_dockerbuild.sh

* Update install_ubuntu.sh

* Update concat_op_test.cc

* Update tensorrt_execution_provider.cc

* Upgrade TensorRT to version 6.0.1.5

* Update onnxruntime_providers.cmake

* Update CMakeLists.txt

* Update reduction_ops_test.cc

* Update install_ubuntu.sh

* Update Dockerfile.ubuntu_tensorrt

* Update Dockerfile.tensorrt

* Update BUILD.md

* Update run_dockerbuild.sh

* Update install_ubuntu.sh

* Update onnxruntime_providers.cmake

* Update install_ubuntu.sh

* Update install_ubuntu.sh

* Update gemm_test.cc

* Update gather_op_test.cc

* Update CMakeLists.txt

* Removed submodule

* update onnx-tensorrt submodule

* Add Ubuntu18.04 build option

* Add Ubuntu18.04 build option

* Add Ubuntu18.04 build option

* Add Ubuntu18.04 build option

* Remove redundency

* Fix issue that it does not add memcopy node correctly if some nodes fall back to CUDA EP.
e.g. after partition, there's TRT_Node -> Cuda_node (with CPU memory expected), we still need to add memcpy node between them.

* update for Trt Windows build

* Update onnxruntime_providers.cmake

* Disable opset11 tests on TensorRT

* Update pad_test.cc

* Update build.py

* update scripts for ubuntu18.04

* Disable warning for Windows build