briansp2020 · October 24, 2018 13:25
diff --git a/ROCmSoftwarePlatform\PyTorch build output Python3 b/ROCmSoftwarePlatform\PyTorch build output Python3
 Building wheel torch-1.0.0a0+664d8cd
 running install
 setup.py::run()
 running build_deps
 + SYNC_COMMAND=cp
 ++ command -v rsync
 + '[' -x '' ']'
 + CMAKE_COMMAND=cmake
 ++ command -v cmake3
 + [[ -x '' ]]
 + USE_CUDA=0
 + USE_ROCM=0
 + USE_NNPACK=0
 + USE_MKLDNN=0
 + USE_GLOO_IBVERBS=0
 + CAFFE2_STATIC_LINK_CUDA=0
 + RERUN_CMAKE=1
 + [[ 4 -gt 0 ]]
 + case "$1" in
 + USE_ROCM=1
 + shift
 + [[ 3 -gt 0 ]]
 + case "$1" in
 + USE_NNPACK=1
 + shift
 + [[ 2 -gt 0 ]]
 + case "$1" in
 + break
 + CMAKE_INSTALL='make install'
 + BUILD_SHARED_LIBS=ON
 + USER_CFLAGS=
 + USER_LDFLAGS=
 + [[ -n '' ]]
 + [[ -n '' ]]
 + [[ -n '' ]]
 ++ uname
 + '[' Linux == Darwin ']'
 +++ dirname ../tools/build_pytorch_libs.sh
 ++ cd ../tools/..
 +++ pwd
 ++ printf '%q\n' /root/pytorch
 + BASE_DIR=/root/pytorch
 + TORCH_LIB_DIR=/root/pytorch/torch/lib
 + INSTALL_DIR=/root/pytorch/torch/lib/tmp_install
 + THIRD_PARTY_DIR=/root/pytorch/third_party
 + C_FLAGS=' -I"/root/pytorch/torch/lib/tmp_install/include"   -I"/root/pytorch/torch/lib/tmp_install/include/TH" -I"/root/pytorch/torch/lib/tmp_install/include/THC"   -I"/root/pytorch/torch/lib/tmp_install/include/THS" -I"/root/pytorch/torch/lib/tmp_install/include/THCS"   -I"/root/pytorch/torch/lib/tmp_install/include/THNN" -I"/root/pytorch/torch/lib/tmp_install/include/THCUNN"'
 + C_FLAGS=' -I"/root/pytorch/torch/lib/tmp_install/include"   -I"/root/pytorch/torch/lib/tmp_install/include/TH" -I"/root/pytorch/torch/lib/tmp_install/include/THC"   -I"/root/pytorch/torch/lib/tmp_install/include/THS" -I"/root/pytorch/torch/lib/tmp_install/include/THCS"   -I"/root/pytorch/torch/lib/tmp_install/include/THNN" -I"/root/pytorch/torch/lib/tmp_install/include/THCUNN" -DOMPI_SKIP_MPICXX=1'
 + LDFLAGS='-L"/root/pytorch/torch/lib/tmp_install/lib" '
 + LD_POSTFIX=.so
 ++ uname
 + [[ Linux == \D\a\r\w\i\n ]]
 + [[ 1 -eq 1 ]]
 + LDFLAGS='-L"/root/pytorch/torch/lib/tmp_install/lib"  -Wl,-rpath,\\\$ORIGIN'
 + CPP_FLAGS=' -std=c++11 '
 + THD_FLAGS=
 + NCCL_ROOT_DIR=/root/pytorch/torch/lib/tmp_install
 + [[ 0 -eq 1 ]]
 + [[ 0 -eq 1 ]]
 + CWRAP_FILES='/root/pytorch/torch/lib/ATen/Declarations.cwrap;/root/pytorch/torch/lib/THNN/generic/THNN.h;/root/pytorch/torch/lib/THCUNN/generic/THCUNN.h;/root/pytorch/torch/lib/ATen/nn.yaml'
 + CUDA_NVCC_FLAGS=' -I"/root/pytorch/torch/lib/tmp_install/include"   -I"/root/pytorch/torch/lib/tmp_install/include/TH" -I"/root/pytorch/torch/lib/tmp_install/include/THC"   -I"/root/pytorch/torch/lib/tmp_install/include/THS" -I"/root/pytorch/torch/lib/tmp_install/include/THCS"   -I"/root/pytorch/torch/lib/tmp_install/include/THNN" -I"/root/pytorch/torch/lib/tmp_install/include/THCUNN" -DOMPI_SKIP_MPICXX=1'
 + [[ -z '' ]]
 + CUDA_DEVICE_DEBUG=0
 + '[' -z 16 ']'
 + BUILD_TYPE=Release
 + [[ -n '' ]]
 + [[ -n '' ]]
 + echo 'Building in Release mode'
 Building in Release mode
 + mkdir -p /root/pytorch/torch/lib/tmp_install
 + for arg in '"$@"'
 + [[ caffe2 == \n\c\c\l ]]
 + [[ caffe2 == \c\a\f\f\e\2 ]]
 + build_caffe2
 + [[ -z '' ]]
 + EXTRA_CAFFE2_CMAKE_FLAGS=()
 + [[ -n '' ]]
 + [[ -n /usr/lib/python3/dist-packages ]]
 + EXTRA_CAFFE2_CMAKE_FLAGS+=("-DCMAKE_PREFIX_PATH=$CMAKE_PREFIX_PATH")
 + [[ 1 -eq 1 ]]
 + cmake /root/pytorch -DPYTHON_EXECUTABLE=/usr/bin/python -DPYTHON_LIBRARY=/usr/lib/libpython3.6m.so.1.0 -DPYTHON_INCLUDE_DIR=/usr/include/python3.6m -DBUILDING_WITH_TORCH_LIBS=ON -DTORCH_BUILD_VERSION=1.0.0a0+664d8cd -DCMAKE_BUILD_TYPE=Release -DBUILD_TORCH=ON -DBUILD_PYTHON=ON -DBUILD_SHARED_LIBS=ON -DBUILD_BINARY=OFF -DBUILD_TEST=ON -DINSTALL_TEST=ON -DBUILD_CAFFE2_OPS=ON -DONNX_NAMESPACE=onnx_torch -DUSE_CUDA=0 -DUSE_NUMPY= -DCAFFE2_STATIC_LINK_CUDA=0 -DUSE_ROCM=1 -DUSE_NNPACK=1 -DUSE_LEVELDB=OFF -DUSE_LMDB=OFF -DUSE_OPENCV=OFF -DUSE_FFMPEG=OFF -DUSE_GLOG=OFF -DUSE_GFLAGS=OFF -DUSE_SYSTEM_EIGEN_INSTALL=OFF -DCUDNN_INCLUDE_DIR= -DCUDNN_LIB_DIR= -DCUDNN_LIBRARY= -DUSE_MKLDNN=0 -DMKLDNN_INCLUDE_DIR= -DMKLDNN_LIB_DIR= -DMKLDNN_LIBRARY= -DCMAKE_INSTALL_PREFIX=/root/pytorch/torch/lib/tmp_install -DCMAKE_C_FLAGS= -DCMAKE_CXX_FLAGS= '-DCMAKE_EXE_LINKER_FLAGS=-L"/root/pytorch/torch/lib/tmp_install/lib"  -Wl,-rpath,\\\$ORIGIN ' '-DCMAKE_SHARED_LINKER_FLAGS=-L"/root/pytorch/torch/lib/tmp_install/lib"  -Wl,-rpath,\\\$ORIGIN ' -DCMAKE_PREFIX_PATH=/usr/lib/python3/dist-packages
 -- The CXX compiler identification is Clang 7.0.0
 -- The C compiler identification is Clang 7.0.0
 -- Check for working CXX compiler: /usr/bin/c++
 -- Check for working CXX compiler: /usr/bin/c++ -- works
 -- Detecting CXX compiler ABI info
 -- Detecting CXX compiler ABI info - done
 -- Detecting CXX compile features
 -- Detecting CXX compile features - done
 -- Check for working C compiler: /usr/bin/cc
 -- Check for working C compiler: /usr/bin/cc -- works
 -- Detecting C compiler ABI info
 -- Detecting C compiler ABI info - done
 -- Detecting C compile features
 -- Detecting C compile features - done
 -- Not forcing any particular BLAS to be found
 -- Performing Test CAFFE2_EXCEPTION_PTR_SUPPORTED
 -- Performing Test CAFFE2_EXCEPTION_PTR_SUPPORTED - Success
 -- std::exception_ptr is supported.
 -- Performing Test CAFFE2_IS_NUMA_AVAILABLE
 -- Performing Test CAFFE2_IS_NUMA_AVAILABLE - Success
 -- NUMA is available
 -- Performing Test CAFFE2_NEED_TO_TURN_OFF_DEPRECATION_WARNING
 -- Performing Test CAFFE2_NEED_TO_TURN_OFF_DEPRECATION_WARNING - Failed
 -- Turning off deprecation warning due to glog.
 -- Performing Test CAFFE2_COMPILER_SUPPORTS_AVX2_EXTENSIONS
 -- Performing Test CAFFE2_COMPILER_SUPPORTS_AVX2_EXTENSIONS - Success
 -- Current compiler supports avx2 extension. Will build perfkernels.
 -- Performing Test COMPILER_SUPPORTS_HIDDEN_VISIBILITY
 -- Performing Test COMPILER_SUPPORTS_HIDDEN_VISIBILITY - Success
 -- Performing Test COMPILER_SUPPORTS_HIDDEN_INLINE_VISIBILITY
 -- Performing Test COMPILER_SUPPORTS_HIDDEN_INLINE_VISIBILITY - Success
 -- Performing Test COMPILER_SUPPORTS_RDYNAMIC
 -- Performing Test COMPILER_SUPPORTS_RDYNAMIC - Success
 -- Building using own protobuf under third_party per request.
 -- Use custom protobuf build.
 -- Looking for pthread.h
 -- Looking for pthread.h - found
 -- Looking for pthread_create
 -- Looking for pthread_create - not found
 -- Looking for pthread_create in pthreads
 -- Looking for pthread_create in pthreads - not found
 -- Looking for pthread_create in pthread
 -- Looking for pthread_create in pthread - found
 -- Found Threads: TRUE  
 -- Caffe2 protobuf include directory: $<BUILD_INTERFACE:/root/pytorch/third_party/protobuf/src>$<INSTALL_INTERFACE:include>
 -- The BLAS backend of choice:MKL
 -- Looking for sys/types.h
 -- Looking for sys/types.h - found
 -- Looking for stdint.h
 -- Looking for stdint.h - found
 -- Looking for stddef.h
 -- Looking for stddef.h - found
 -- Check size of void*
 -- Check size of void* - done
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl - guide - pthread - m]
 --   Library mkl: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl - guide - pthread - m]
 --   Library mkl: not found
 CMake Warning at cmake/Dependencies.cmake:76 (message):
  MKL could not be found.  Defaulting to Eigen
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 -- Brace yourself, we are building NNPACK
 -- The ASM compiler identification is Clang
 -- Found assembler: /usr/bin/cc
 -- Found PythonInterp: /usr/bin/python (found version "3.6.7") 
 -- Check if compiler accepts -pthread
 -- Check if compiler accepts -pthread - yes
 -- Failed to find LLVM FileCheck
 -- Found Git: /usr/bin/git (found version "2.7.4") 
 -- git Version: v1.4.0-505be96a
 -- Version: 1.4.0
 -- Performing Test HAVE_CXX_FLAG_STD_CXX11
 -- Performing Test HAVE_CXX_FLAG_STD_CXX11 - Success
 -- Performing Test HAVE_CXX_FLAG_WALL
 -- Performing Test HAVE_CXX_FLAG_WALL - Success
 -- Performing Test HAVE_CXX_FLAG_WEXTRA
 -- Performing Test HAVE_CXX_FLAG_WEXTRA - Success
 -- Performing Test HAVE_CXX_FLAG_WSHADOW
 -- Performing Test HAVE_CXX_FLAG_WSHADOW - Success
 -- Performing Test HAVE_CXX_FLAG_WERROR
 -- Performing Test HAVE_CXX_FLAG_WERROR - Success
 -- Performing Test HAVE_CXX_FLAG_PEDANTIC
 -- Performing Test HAVE_CXX_FLAG_PEDANTIC - Success
 -- Performing Test HAVE_CXX_FLAG_PEDANTIC_ERRORS
 -- Performing Test HAVE_CXX_FLAG_PEDANTIC_ERRORS - Success
 -- Performing Test HAVE_CXX_FLAG_WSHORTEN_64_TO_32
 -- Performing Test HAVE_CXX_FLAG_WSHORTEN_64_TO_32 - Success
 -- Performing Test HAVE_CXX_FLAG_WFLOAT_EQUAL
 -- Performing Test HAVE_CXX_FLAG_WFLOAT_EQUAL - Success
 -- Performing Test HAVE_CXX_FLAG_FSTRICT_ALIASING
 -- Performing Test HAVE_CXX_FLAG_FSTRICT_ALIASING - Success
 -- Performing Test HAVE_CXX_FLAG_WNO_DEPRECATED_DECLARATIONS
 -- Performing Test HAVE_CXX_FLAG_WNO_DEPRECATED_DECLARATIONS - Success
 -- Performing Test HAVE_CXX_FLAG_WSTRICT_ALIASING
 -- Performing Test HAVE_CXX_FLAG_WSTRICT_ALIASING - Success
 -- Performing Test HAVE_CXX_FLAG_WD654
 -- Performing Test HAVE_CXX_FLAG_WD654 - Failed
 -- Performing Test HAVE_CXX_FLAG_WTHREAD_SAFETY
 -- Performing Test HAVE_CXX_FLAG_WTHREAD_SAFETY - Success
 -- Performing Test HAVE_THREAD_SAFETY_ATTRIBUTES
 -- Performing Test HAVE_THREAD_SAFETY_ATTRIBUTES
 -- Performing Test HAVE_THREAD_SAFETY_ATTRIBUTES -- failed to compile
 -- Performing Test HAVE_CXX_FLAG_COVERAGE
 -- Performing Test HAVE_CXX_FLAG_COVERAGE - Success
 -- Performing Test HAVE_STD_REGEX
 -- Performing Test HAVE_STD_REGEX
 -- Performing Test HAVE_STD_REGEX -- success
 -- Performing Test HAVE_GNU_POSIX_REGEX
 -- Performing Test HAVE_GNU_POSIX_REGEX
 -- Performing Test HAVE_GNU_POSIX_REGEX -- failed to compile
 -- Performing Test HAVE_POSIX_REGEX
 -- Performing Test HAVE_POSIX_REGEX
 -- Performing Test HAVE_POSIX_REGEX -- success
 -- Performing Test HAVE_STEADY_CLOCK
 -- Performing Test HAVE_STEADY_CLOCK
 -- Performing Test HAVE_STEADY_CLOCK -- success
 -- Found Numa: /usr/include  
 -- Found Numa  (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libnuma.so)
 -- Using third party subdirectory Eigen.
 Python 3.6.7
 -- Found PythonInterp: /usr/bin/python (found suitable version "3.6.7", minimum required is "2.7") 
 -- Found PythonLibs: /usr/lib/libpython3.6m.so.1.0 (found suitable version "3.6.7", minimum required is "2.7") 
 -- Found NumPy: /usr/local/lib/python3.6/dist-packages/numpy/core/include (found version "1.15.3") 
 -- NumPy ver. 1.15.3 found (include: /usr/local/lib/python3.6/dist-packages/numpy/core/include)
 CMake Warning at cmake/Dependencies.cmake:418 (find_package):
  Could not find a package configuration file provided by "pybind11" with any
  of the following names:

    pybind11Config.cmake
    pybind11-config.cmake

  Add the installation prefix of "pybind11" to CMAKE_PREFIX_PATH or set
  "pybind11_DIR" to a directory containing one of the above files.  If
  "pybind11" provides a separate development package or SDK, be sure it has
  been installed.
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 -- Could NOT find pybind11 (missing:  pybind11_INCLUDE_DIR) 
 -- Using third_party/pybind11.
 -- Could NOT find MPI_C (missing:  MPI_C_LIBRARIES MPI_C_INCLUDE_PATH) 
 -- Could NOT find MPI_CXX (missing:  MPI_CXX_LIBRARIES MPI_CXX_INCLUDE_PATH) 
 CMake Warning at cmake/Dependencies.cmake:460 (message):
  Not compiling with MPI.  Suppress this warning with -DUSE_MPI=OFF
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 -- Found HIP: /opt/rocm (found suitable version "1.5.18382", minimum required is "1.0") 
 HIP VERSION: 1.5.18382

 ***** Library versions from dpkg *****

 rocm-dev VERSION: 1.9.247
 rocm-device-libs VERSION: 0.0.1
 hsakmt-roct VERSION: 1.0.9-8-g238782c
 hsakmt-roct-dev VERSION: 1.0.9-8-g238782c
 hsa-ext-rocr-dev VERSION: 1.1.9-10-g7336a0d
 hsa-rocr-dev VERSION: 1.1.9-10-g7336a0d
 hcc VERSION: 1.2.18383
 hip_base VERSION: 1.5.18382
 hip_hcc VERSION: 1.5.18382

 ***** Library versions from cmake find_package *****

 rocrand VERSION: 1.8.1
 hiprand VERSION: 1.8.1
 rocblas VERSION: 0.14.3.0
 miopen VERSION: 1.5.0-e1f0433
 miopengemm VERSION: 1.1.5-9547fb9
 rocfft VERSION: 0.8.6.0
 rocsparse VERSION: 0.1.3.1
 INFOCompiling with HIP for AMD.
 -- ROCM TRUE:
 -- CMAKE_CXX_COMPILER: /usr/bin/c++
 CMake Warning at cmake/Dependencies.cmake:613 (message):
  Not using CUDA, so disabling NCCL.  Suppress this warning with
  -DUSE_NCCL=OFF.
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 CMake Warning at cmake/Dependencies.cmake:691 (message):
  mobile opengl is only used in android or ios builds.
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 CMake Warning at cmake/Dependencies.cmake:767 (message):
  Metal is only used in ios builds.
 Call Stack (most recent call first):
  CMakeLists.txt:201 (include)


 -- 
 -- ******** Summary ********
 --   CMake version         : 3.5.1
 --   CMake command         : /usr/bin/cmake
 --   System                : Linux
 --   C++ compiler          : /usr/bin/c++
 --   C++ compiler version  : 7.0.0
 --   CXX flags             :  -Wno-deprecated -fvisibility-inlines-hidden
 --   Build type            : Release
 --   Compile definitions   : NDEBUG
 --   CMAKE_PREFIX_PATH     : /usr/lib/python3/dist-packages
 --   CMAKE_INSTALL_PREFIX  : /root/pytorch/torch/lib/tmp_install
 --   CMAKE_MODULE_PATH     : /opt/rocm/hip/cmake;/root/pytorch/cmake/Modules
 -- 
 --   ONNX version          : 1.3.0
 --   ONNX NAMESPACE        : onnx_torch
 --   ONNX_BUILD_TESTS      : OFF
 --   ONNX_BUILD_BENCHMARKS : OFF
 --   ONNX_USE_LITE_PROTO   : OFF
 --   ONNXIFI_DUMMY_BACKEND : OFF
 -- 
 --   Protobuf compiler     : 
 --   Protobuf includes     : 
 --   Protobuf libraries    : 
 --   BUILD_ONNX_PYTHON     : OFF
 -- Performing Test SUPPORT_GLIBCXX_USE_C99
 -- Performing Test SUPPORT_GLIBCXX_USE_C99 - Success
 -- Could not find CUDA with FP16 support, compiling without torch.CudaHalfTensor
 -- Removing -DNDEBUG from compile flags
 -- Try OpenMP C flag = [-fopenmp=libomp]
 -- Performing Test OpenMP_FLAG_DETECTED
 -- Performing Test OpenMP_FLAG_DETECTED - Success
 -- Try OpenMP CXX flag = [-fopenmp=libomp]
 -- Performing Test OpenMP_FLAG_DETECTED
 -- Performing Test OpenMP_FLAG_DETECTED - Success
 -- Found OpenMP: -fopenmp=libomp  
 -- Compiling with OpenMP support
 -- MAGMA not found. Compiling without MAGMA support
 -- Could not find hardware support for NEON on this machine.
 -- No OMAP3 processor on this machine.
 -- No OMAP4 processor on this machine.
 -- Performing Test COMPILER_WORKS
 -- Performing Test COMPILER_WORKS - Success
 -- Looking for cpuid.h
 -- Looking for cpuid.h - found
 -- Performing Test HAVE_GCC_GET_CPUID
 -- Performing Test HAVE_GCC_GET_CPUID - Success
 -- Performing Test NO_GCC_EBX_FPIC_BUG
 -- Performing Test NO_GCC_EBX_FPIC_BUG - Success
 -- Performing Test C_HAS_AVX_1
 -- Performing Test C_HAS_AVX_1 - Failed
 -- Performing Test C_HAS_AVX_2
 -- Performing Test C_HAS_AVX_2 - Success
 -- Performing Test C_HAS_AVX2_1
 -- Performing Test C_HAS_AVX2_1 - Failed
 -- Performing Test C_HAS_AVX2_2
 -- Performing Test C_HAS_AVX2_2 - Success
 -- Performing Test CXX_HAS_AVX_1
 -- Performing Test CXX_HAS_AVX_1 - Failed
 -- Performing Test CXX_HAS_AVX_2
 -- Performing Test CXX_HAS_AVX_2 - Success
 -- Performing Test CXX_HAS_AVX2_1
 -- Performing Test CXX_HAS_AVX2_1 - Failed
 -- Performing Test CXX_HAS_AVX2_2
 -- Performing Test CXX_HAS_AVX2_2 - Success
 -- AVX compiler support found
 -- AVX2 compiler support found
 -- Performing Test HAS_C11_ATOMICS
 -- Performing Test HAS_C11_ATOMICS - Failed
 -- Performing Test HAS_MSC_ATOMICS
 -- Performing Test HAS_MSC_ATOMICS - Failed
 -- Performing Test HAS_GCC_ATOMICS
 -- Performing Test HAS_GCC_ATOMICS - Success
 -- Atomics: using GCC intrinsics
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_sequential - mkl_core - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - iomp5 - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - guide - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl_intel_lp64 - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel_lp64: not found
 -- Checking for [mkl_intel - mkl_intel_thread - mkl_core - pthread - m - dl]
 --   Library mkl_intel: not found
 -- Checking for [mkl - guide - pthread - m]
 --   Library mkl: not found
 -- MKL library not found
 -- Checking for [Accelerate]
 --   Library Accelerate: BLAS_Accelerate_LIBRARY-NOTFOUND
 -- Checking for [vecLib]
 --   Library vecLib: BLAS_vecLib_LIBRARY-NOTFOUND
 -- Checking for [openblas]
 --   Library openblas: /usr/lib/libopenblas.so
 -- Looking for sgemm_
 -- Looking for sgemm_ - found
 -- Performing Test BLAS_F2C_DOUBLE_WORKS
 -- Performing Test BLAS_F2C_DOUBLE_WORKS - Failed
 -- Performing Test BLAS_F2C_FLOAT_WORKS
 -- Performing Test BLAS_F2C_FLOAT_WORKS - Success
 -- Performing Test BLAS_USE_CBLAS_DOT
 -- Performing Test BLAS_USE_CBLAS_DOT - Success
 -- Found a library with BLAS API (open).
 -- Looking for cheev_
 -- Looking for cheev_ - found
 -- Found a library with LAPACK API. (open)
 disabling CUDA because NOT USE_CUDA is set
 -- CuDNN not found. Compiling without CuDNN support
 -- Could NOT find MKLDNN (missing:  MKLDNN_INCLUDE_DIR MKLDNN_LIBRARY) 
 -- MKLDNN not found. Compiling without MKLDNN support
 -- Looking for clock_gettime in rt
 -- Looking for clock_gettime in rt - found
 -- Looking for mmap
 -- Looking for mmap - found
 -- Looking for shm_open
 -- Looking for shm_open - found
 -- Looking for shm_unlink
 -- Looking for shm_unlink - found
 -- Looking for malloc_usable_size
 -- Looking for malloc_usable_size - found
 -- Performing Test C_HAS_THREAD
 -- Performing Test C_HAS_THREAD - Success
 -- Using python found in /usr/bin/python
 HIP VERSION: 1.5.18382

 ***** Library versions from dpkg *****

 rocm-dev VERSION: 1.9.247
 rocm-device-libs VERSION: 0.0.1
 hsakmt-roct VERSION: 1.0.9-8-g238782c
 hsakmt-roct-dev VERSION: 1.0.9-8-g238782c
 hsa-ext-rocr-dev VERSION: 1.1.9-10-g7336a0d
 hsa-rocr-dev VERSION: 1.1.9-10-g7336a0d
 hcc VERSION: 1.2.18383
 hip_base VERSION: 1.5.18382
 hip_hcc VERSION: 1.5.18382

 ***** Library versions from cmake find_package *****

 rocrand VERSION: 1.8.1
 hiprand VERSION: 1.8.1
 rocblas VERSION: 0.14.3.0
 miopen VERSION: 1.5.0-e1f0433
 miopengemm VERSION: 1.1.5-9547fb9
 rocfft VERSION: 0.8.6.0
 rocsparse VERSION: 0.1.3.1
 ROCm is enabled.
 -- Check size of long double
 -- Check size of long double - done
 -- Performing Test COMPILER_SUPPORTS_LONG_DOUBLE
 -- Performing Test COMPILER_SUPPORTS_LONG_DOUBLE - Success
 -- Performing Test COMPILER_SUPPORTS_FLOAT128
 -- Performing Test COMPILER_SUPPORTS_FLOAT128 - Success
 -- Performing Test COMPILER_SUPPORTS_SSE2
 -- Performing Test COMPILER_SUPPORTS_SSE2 - Success
 -- Performing Test COMPILER_SUPPORTS_SSE4
 -- Performing Test COMPILER_SUPPORTS_SSE4 - Success
 -- Performing Test COMPILER_SUPPORTS_AVX
 -- Performing Test COMPILER_SUPPORTS_AVX - Success
 -- Performing Test COMPILER_SUPPORTS_FMA4
 -- Performing Test COMPILER_SUPPORTS_FMA4 - Success
 -- Performing Test COMPILER_SUPPORTS_AVX2
 -- Performing Test COMPILER_SUPPORTS_AVX2 - Success
 -- Performing Test COMPILER_SUPPORTS_SVE
 -- Performing Test COMPILER_SUPPORTS_SVE - Failed
 -- Performing Test COMPILER_SUPPORTS_AVX512F
 -- Performing Test COMPILER_SUPPORTS_AVX512F - Success
 -- Performing Test COMPILER_SUPPORTS_OPENMP
 -- Performing Test COMPILER_SUPPORTS_OPENMP - Success
 -- Performing Test COMPILER_SUPPORTS_WEAK_ALIASES
 -- Performing Test COMPILER_SUPPORTS_WEAK_ALIASES - Success
 -- Performing Test COMPILER_SUPPORTS_BUILTIN_MATH
 -- Performing Test COMPILER_SUPPORTS_BUILTIN_MATH - Failed
 -- Configuring build for SLEEF-v3.2
   Target system: Linux-4.15.0-38-generic
   Target processor: x86_64
   Host system: Linux-4.15.0-38-generic
   Host processor: x86_64
   Detected C compiler: Clang @ /usr/bin/cc
 -- Using option `-Wall -Wno-unused -Wno-attributes -Wno-unused-result -ffp-contract=off -fno-math-errno -fno-trapping-math` to compile libsleef
 -- Building shared libs : OFF
 -- MPFR : LIB_MPFR-NOTFOUND
 -- GMP : LIBGMP-NOTFOUND
 -- RUNNING_ON_TRAVIS : 0
 -- COMPILER_SUPPORTS_OPENMP : 1
 -- Using python found in /usr/bin/python
 -- NCCL operators skipped due to no CUDA support
 -- Excluding ideep operators as we are not using ideep
 -- Excluding image processing operators due to no opencv
 -- Excluding video processing operators due to no opencv
 -- MPI operators skipped due to no MPI support
 -- Include Observer library
 -- Using lib/python3/dist-packages as python relative installation path
 -- Automatically generating missing __init__.py files.
 CMake Warning at CMakeLists.txt:389 (message):
  Generated cmake files are only fully tested if one builds with system glog,
  gflags, and protobuf.  Other settings may generate files that are not well
  tested.


 -- 
 -- ******** Summary ********
 -- General:
 --   CMake version         : 3.5.1
 --   CMake command         : /usr/bin/cmake
 --   System                : Linux
 --   C++ compiler          : /usr/bin/c++
 --   C++ compiler version  : 7.0.0
 --   BLAS                  : MKL
 --   CXX flags             : --std=c++11  -Wno-deprecated -fvisibility-inlines-hidden -fopenmp=libomp -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -Wno-invalid-partial-specialization -Wno-typedef-redefinition -Wno-unknown-warning-option -Wno-unused-private-field -Wno-inconsistent-missing-override -Wno-aligned-allocation-unavailable -Wno-c++14-extensions -Wno-constexpr-not-const -Wno-missing-braces -Qunused-arguments -Wno-unused-but-set-variable -Wno-maybe-uninitialized
 --   Build type            : Release
 --   Compile definitions   : NDEBUG;ONNX_NAMESPACE=onnx_torch;USE_GCC_ATOMICS=1;HAVE_MMAP=1;_FILE_OFFSET_BITS=64;HAVE_SHM_OPEN=1;HAVE_SHM_UNLINK=1;HAVE_MALLOC_USABLE_SIZE=1
 --   CMAKE_PREFIX_PATH     : /usr/lib/python3/dist-packages
 --   CMAKE_INSTALL_PREFIX  : /root/pytorch/torch/lib/tmp_install
 -- 
 --   TORCH_VERSION         : 1.0.0
 --   CAFFE2_VERSION        : 1.0.0
 --   BUILD_ATEN_MOBILE     : OFF
 --   BUILD_ATEN_ONLY       : OFF
 --   BUILD_BINARY          : OFF
 --   BUILD_CUSTOM_PROTOBUF : ON
 --     Link local protobuf : ON
 --   BUILD_DOCS            : OFF
 --   BUILD_PYTHON          : ON
 --     Python version      : 3.6.7
 --     Python executable   : /usr/bin/python
 --     Pythonlibs version  : 3.6.7
 --     Python library      : /usr/lib/libpython3.6m.so.1.0
 --     Python includes     : /usr/include/python3.6m
 --     Python site-packages: lib/python3/dist-packages
 --   BUILD_CAFFE2_OPS      : ON
 --   BUILD_SHARED_LIBS     : ON
 --   BUILD_TEST            : ON
 --   USE_ASAN              : OFF
 --   USE_CUDA              : 0
 --   USE_ROCM              : ON
 --   USE_EIGEN_FOR_BLAS    : ON
 --   USE_FFMPEG            : OFF
 --   USE_GFLAGS            : OFF
 --   USE_GLOG              : OFF
 --   USE_LEVELDB           : OFF
 --   USE_LITE_PROTO        : OFF
 --   USE_LMDB              : OFF
 --   USE_METAL             : OFF
 --   USE_MKL               : 
 --   USE_MOBILE_OPENGL     : OFF
 --   USE_NCCL              : OFF
 --   USE_NNPACK            : 1
 --   USE_NUMPY             : ON
 --   USE_OBSERVERS         : ON
 --   USE_OPENCL            : OFF
 --   USE_OPENCV            : OFF
 --   USE_OPENMP            : OFF
 --   USE_PROF              : OFF
 --   USE_REDIS             : OFF
 --   USE_ROCKSDB           : OFF
 --   USE_ZMQ               : OFF
 --   USE_DISTRIBUTED       : ON
 --     USE_MPI             : OFF
 --     USE_GLOO            : ON
 --     USE_GLOO_IBVERBS    : OFF
 --   Public Dependencies  : Threads::Threads
 --   Private Dependencies : nnpack;cpuinfo;/usr/lib/x86_64-linux-gnu/libnuma.so;fp16;gloo;aten_op_header_gen;onnxifi_loader;rt;dl
 -- Configuring done
 -- Generating done
 CMake Warning:
  Manually-specified variables were not used by the project:

    CUDNN_INCLUDE_DIR
    CUDNN_LIBRARY
    CUDNN_LIB_DIR


 -- Build files have been written to: /root/pytorch/build
 + '[' -f /root/pytorch/torch/lib/tmp_install/lib/libnccl.so ']'
 + make install -j16
 Scanning dependencies of target onnxifi_dummy
 Scanning dependencies of target python_copy_files
 Scanning dependencies of target js_embed
 Scanning dependencies of target clog
 Scanning dependencies of target common
 Scanning dependencies of target pthreadpool
 Scanning dependencies of target mkrename
 Scanning dependencies of target onnxifi_loader
 Scanning dependencies of target mkdisp
 Scanning dependencies of target ATEN_CPU_FILES_GEN_TARGET
 [  0%] Building C object third_party/onnx/CMakeFiles/onnxifi_dummy.dir/onnx/onnxifi_dummy.c.o
 [  0%] Building C object confu-deps/cpuinfo/deps/clog/CMakeFiles/clog.dir/src/clog.c.o
 Scanning dependencies of target gtest
 [  0%] Building C object sleef/src/common/CMakeFiles/common.dir/common.c.o
 [  0%] Building C object sleef/src/libm/CMakeFiles/mkrename.dir/mkrename.c.o
 [  0%] Building C object sleef/src/libm/CMakeFiles/mkdisp.dir/mkdisp.c.o
 [  0%] Building CXX object third_party/protobuf/cmake/CMakeFiles/js_embed.dir/__/src/google/protobuf/compiler/js/embed.cc.o
 [  0%] Building C object third_party/onnx/CMakeFiles/onnxifi_loader.dir/onnx/onnxifi_loader.c.o
 [  0%] Building C object confu-deps/pthreadpool/CMakeFiles/pthreadpool.dir/src/threadpool-pthreads.c.o
 Scanning dependencies of target benchmark
 Scanning dependencies of target c10
 [  0%] Generating ../aten/src/ATen/CPUByteType.cpp, ../aten/src/ATen/CPUByteType.h, ../aten/src/ATen/CPUCharType.cpp, ../aten/src/ATen/CPUCharType.h, ../aten/src/ATen/CPUCopy.cpp, ../aten/src/ATen/CPUDoubleType.cpp, ../aten/src/ATen/CPUDoubleType.h, ../aten/src/ATen/CPUFloatType.cpp, ../aten/src/ATen/CPUFloatType.h, ../aten/src/ATen/CPUGenerator.h, ../aten/src/ATen/CPUHalfType.cpp, ../aten/src/ATen/CPUHalfType.h, ../aten/src/ATen/CPUIntType.cpp, ../aten/src/ATen/CPUIntType.h, ../aten/src/ATen/CPULongType.cpp, ../aten/src/ATen/CPULongType.h, ../aten/src/ATen/CPUShortType.cpp, ../aten/src/ATen/CPUShortType.h, ../aten/src/ATen/Declarations.yaml, ../aten/src/ATen/Functions.h, ../aten/src/ATen/NativeFunctions.h, ../aten/src/ATen/RegisterCPU.cpp, ../aten/src/ATen/RegisterCPU.h, ../aten/src/ATen/SparseCPUByteType.cpp, ../aten/src/ATen/SparseCPUByteType.h, ../aten/src/ATen/SparseCPUCharType.cpp, ../aten/src/ATen/SparseCPUCharType.h, ../aten/src/ATen/SparseCPUDoubleType.cpp, ../aten/src/ATen/SparseCPUDoubleType.h, ../aten/src/ATen/SparseCPUFloatType.cpp, ../aten/src/ATen/SparseCPUFloatType.h, ../aten/src/ATen/SparseCPUIntType.cpp, ../aten/src/ATen/SparseCPUIntType.h, ../aten/src/ATen/SparseCPULongType.cpp, ../aten/src/ATen/SparseCPULongType.h, ../aten/src/ATen/SparseCPUShortType.cpp, ../aten/src/ATen/SparseCPUShortType.h, ../aten/src/ATen/TypeDefault.cpp, ../aten/src/ATen/TypeDefault.h, ../aten/src/ATen/TypeExtendedInterface.h, ../aten/src/ATen/CUDAByteType.cpp, ../aten/src/ATen/CUDAByteType.h, ../aten/src/ATen/CUDACharType.cpp, ../aten/src/ATen/CUDACharType.h, ../aten/src/ATen/CUDACopy.cpp, ../aten/src/ATen/CUDADoubleType.cpp, ../aten/src/ATen/CUDADoubleType.h, ../aten/src/ATen/CUDAFloatType.cpp, ../aten/src/ATen/CUDAFloatType.h, ../aten/src/ATen/CUDAGenerator.h, ../aten/src/ATen/CUDAHalfType.cpp, ../aten/src/ATen/CUDAHalfType.h, ../aten/src/ATen/CUDAIntType.cpp, ../aten/src/ATen/CUDAIntType.h, ../aten/src/ATen/CUDALongType.cpp, ../aten/src/ATen/CUDALongType.h, ../aten/src/ATen/CUDAShortType.cpp, ../aten/src/ATen/CUDAShortType.h, ../aten/src/ATen/RegisterCUDA.cpp, ../aten/src/ATen/RegisterCUDA.h, ../aten/src/ATen/SparseCUDAByteType.cpp, ../aten/src/ATen/SparseCUDAByteType.h, ../aten/src/ATen/SparseCUDACharType.cpp, ../aten/src/ATen/SparseCUDACharType.h, ../aten/src/ATen/SparseCUDADoubleType.cpp, ../aten/src/ATen/SparseCUDADoubleType.h, ../aten/src/ATen/SparseCUDAFloatType.cpp, ../aten/src/ATen/SparseCUDAFloatType.h, ../aten/src/ATen/SparseCUDAIntType.cpp, ../aten/src/ATen/SparseCUDAIntType.h, ../aten/src/ATen/SparseCUDALongType.cpp, ../aten/src/ATen/SparseCUDALongType.h, ../aten/src/ATen/SparseCUDAShortType.cpp, ../aten/src/ATen/SparseCUDAShortType.h
 Scanning dependencies of target libprotobuf-lite
 [  1%] Building CXX object third_party/googletest/googletest/CMakeFiles/gtest.dir/src/gtest-all.cc.o
 [  1%] Building CXX object c10/CMakeFiles/c10.dir/util/C++17.cpp.o
 Scanning dependencies of target gloo
 [  1%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/sleep.cc.o
 [  1%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/algorithm.cc.o
 [  1%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/arena.cc.o
 [  1%] Linking C static library ../../lib/libonnxifi_loader.a
 Scanning dependencies of target libprotobuf
 [  1%] Built target common
 [  1%] Linking C shared library ../../lib/libonnxifi_dummy.so
 [  1%] Linking C static library ../../../../lib/libclog.a
 [  1%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/benchmark_register.cc.o
 [  1%] Built target onnxifi_loader
 [  1%] Linking C executable ../../bin/mkdisp
 Scanning dependencies of target mkalias
 [  1%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/arena.cc.o
 [  1%] Building C object sleef/src/libm/CMakeFiles/mkalias.dir/mkalias.c.o
 [  1%] Built target clog
 [  1%] Linking C executable ../../bin/mkrename
 [  1%] Built target onnxifi_dummy
 [  1%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/context.cc.o
 [  1%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/allreduce_local.cc.o
 [  1%] Built target mkdisp
 [  1%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/arenastring.cc.o
 [  1%] Built target mkrename
 [  1%] Linking C static library ../../lib/libpthreadpool.a
 Scanning dependencies of target mkrename_gnuabi
 [  1%] Building C object sleef/src/libm/CMakeFiles/mkrename_gnuabi.dir/mkrename_gnuabi.c.o
 [  1%] Linking C executable ../../bin/mkalias
 [  1%] Built target pthreadpool
 Scanning dependencies of target mkmasked_gnuabi
 [  1%] Building C object sleef/src/libm/CMakeFiles/mkmasked_gnuabi.dir/mkmasked_gnuabi.c.o
 [  1%] Built target mkalias
 Scanning dependencies of target arraymap
 [  1%] Linking C executable ../../bin/mkrename_gnuabi
 [  1%] Building C object sleef/src/common/CMakeFiles/arraymap.dir/arraymap.c.o
 [  1%] Linking C executable ../../bin/mkmasked_gnuabi
 [  1%] Building CXX object c10/CMakeFiles/c10.dir/util/Logging.cpp.o
 [  1%] Built target mkrename_gnuabi
 [  2%] Linking CXX executable ../../../bin/js_embed
 [  2%] Building CXX object c10/CMakeFiles/c10.dir/util/Array.cpp.o
 [  2%] Built target mkmasked_gnuabi
 Scanning dependencies of target c10_utils_gpu
 [  2%] Building CXX object caffe2/utils/CMakeFiles/c10_utils_gpu.dir/dummy.cpp.o
 [  2%] Built target c10_utils_gpu
 Scanning dependencies of target c10_utils_hip
 [  2%] Built target js_embed
 [  2%] Building CXX object caffe2/utils/CMakeFiles/c10_utils_hip.dir/dummy.cpp.o
 Scanning dependencies of target c10_utils_cpu
 [  2%] Building CXX object caffe2/utils/CMakeFiles/c10_utils_cpu.dir/dummy.cpp.o
 [  2%] Built target arraymap
 [  2%] Built target c10_utils_hip
 Scanning dependencies of target cpuinfo
 [  2%] Building CXX object c10/CMakeFiles/c10.dir/util/Exception.cpp.o
 [  2%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/init.c.o
 [  2%] Built target c10_utils_cpu
 [  2%] Building CXX object c10/CMakeFiles/c10.dir/util/Type.cpp.o
 [  2%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/extension_set.cc.o
 [  2%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/api.c.o
 [  2%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/init.c.o
 [  3%] Building CXX object c10/CMakeFiles/c10.dir/util/TypeTraits.cpp.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/info.c.o
 [  3%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/common/linux.cc.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/vendor.c.o
 [  3%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/complexity.cc.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/uarch.c.o
 [  3%] Building CXX object c10/CMakeFiles/c10.dir/util/TypeList.cpp.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/name.c.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/topology.c.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/isa.c.o
 [  3%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/arenastring.cc.o
 [  3%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/extension_set.cc.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/init.c.o
 [  3%] Building CXX object c10/CMakeFiles/c10.dir/util/flags_use_gflags.cpp.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/descriptor.c.o
 [  3%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/generated_message_table_driven_lite.cc.o
 [  3%] Building CXX object c10/CMakeFiles/c10.dir/util/Optional.cpp.o
 [  3%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/cache/deterministic.c.o
 [  3%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/generated_message_util.cc.o
 [  3%] Building CXX object c10/CMakeFiles/c10.dir/util/StringUtil.cpp.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/init.c.o
 [  4%] Building CXX object c10/CMakeFiles/c10.dir/util/Metaprogramming.cpp.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/x86/linux/cpuinfo.c.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/smallfile.c.o
 [  4%] Building CXX object c10/CMakeFiles/c10.dir/util/flags_use_no_gflags.cpp.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/multiline.c.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/current.c.o
 [  4%] Building CXX object c10/CMakeFiles/c10.dir/util/Backtrace.cpp.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/cpulist.c.o
 [  4%] Building C object confu-deps/cpuinfo/CMakeFiles/cpuinfo.dir/src/linux/processors.c.o
 Scanning dependencies of target nnpack_reference_layers
 [  4%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/coded_stream.cc.o
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/convolution-output.c.o
 [  4%] Linking C static library ../../lib/libcpuinfo.a
 [  4%] Built target cpuinfo
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/convolution-input-gradient.c.o
 Scanning dependencies of target onnxifi_wrapper
 [  4%] Building C object third_party/onnx/CMakeFiles/onnxifi_wrapper.dir/onnx/onnxifi_wrapper.c.o
 Scanning dependencies of target headers
 [  4%] Generating ../../../include/sleef.h
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/convolution-kernel.c.o
 Generating sleef.h: mkrename 2 4 __m128d __m128 __m128i __m128i __SSE2__
 Generating sleef.h: mkrename 2 4 __m128d __m128 __m128i __m128i __SSE2__ sse2
 Generating sleef.h: mkrename 2 4 __m128d __m128 __m128i __m128i __SSE2__ sse4
 Generating sleef.h: mkrename 4 8 __m256d __m256 __m128i struct\ {\ __m128i\ x,\ y;\ } __AVX__
 Generating sleef.h: mkrename 4 8 __m256d __m256 __m128i struct\ {\ __m128i\ x,\ y;\ } __AVX__ avx
 Generating sleef.h: mkrename 4 8 __m256d __m256 __m128i struct\ {\ __m128i\ x,\ y;\ } __AVX__ fma4
 Generating sleef.h: mkrename 4 8 __m256d __m256 __m128i __m256i __AVX__ avx2
 Generating sleef.h: mkrename 2 4 __m128d __m128 __m128i __m128i __SSE2__ avx2128
 Generating sleef.h: mkrename 8 16 __m512d __m512 __m256i __m512i __AVX512F__
 Generating sleef.h: mkrename 8 16 __m512d __m512 __m256i __m512i __AVX512F__ avx512f
 [  4%] Generating include/renameavx512f.h
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/fully-connected-output.c.o
 Generating renameavx512f.h: mkrename 8 16 avx512f
 [  4%] Generating include/renameavx2.h
 [  4%] Linking C shared module ../../lib/libonnxifi.so
 Generating renameavx2.h: mkrename 4 8 avx2
 [  4%] Generating include/renameavx2128.h
 Generating renameavx2128.h: mkrename 2 4 avx2128
 [  4%] Generating include/renamefma4.h
 Generating renamefma4.h: mkrename 4 8 fma4
 [  4%] Generating include/renameavx.h
 Generating renameavx.h: mkrename 4 8 avx
 [  4%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/statistics.cc.o
 [  4%] Built target onnxifi_wrapper
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/max-pooling-output.c.o
 [  4%] Generating include/renamesse4.h
 [  4%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/console_reporter.cc.o
 Generating renamesse4.h: mkrename 2 4 sse4
 [  4%] Generating include/renamesse2.h
 Generating renamesse2.h: mkrename 2 4 sse2
 [  4%] Built target headers
 Scanning dependencies of target renamedsp128.h_generated
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/softmax-output.c.o
 [  4%] Generating renamedsp128.h
 [  4%] Built target renamedsp128.h_generated
 Scanning dependencies of target dispsse.c_generated
 [  4%] Generating dispsse.c
 [  4%] Built target dispsse.c_generated
 Scanning dependencies of target renameAVX.h_generated
 [  4%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/relu-output.c.o
 [  5%] Built target renameAVX.h_generated
 Scanning dependencies of target alias_avx512f.h_generated
 [  5%] Generating alias_avx512f.h
 [  5%] Built target alias_avx512f.h_generated
 Scanning dependencies of target renameAVX512F.h_generated
 [  5%] Built target renameAVX512F.h_generated
 [  5%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack_reference_layers.dir/src/ref/relu-input-gradient.c.o
 Scanning dependencies of target renamedsp256.h_generated
 [  5%] Generating renamedsp256.h
 [  5%] Built target renamedsp256.h_generated
 Scanning dependencies of target dispavx.c_generated
 [  5%] Generating dispavx.c
 [  5%] Linking C static library ../../lib/libnnpack_reference_layers.a
 [  5%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/common/logging.cc.o
 [  5%] Built target dispavx.c_generated
 [  5%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/rendezvous/context.cc.o
 [  5%] Built target nnpack_reference_layers
 Scanning dependencies of target renameSSE2.h_generated
 [  5%] Built target renameSSE2.h_generated
 Scanning dependencies of target renameAVX2.h_generated
 Scanning dependencies of target renameFMA4.h_generated
 [  5%] Built target renameFMA4.h_generated
 [  5%] Built target renameAVX2.h_generated
 [  5%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/generated_message_table_driven_lite.cc.o
 Scanning dependencies of target renameAVX2128.h_generated
 [  5%] Built target renameAVX2128.h_generated
 Scanning dependencies of target renameSSE4.h_generated
 [  5%] Built target renameSSE4.h_generated
 [  5%] Generating src/x86_64-fma/2d-fourier-8x8.py.o
 [  5%] Linking CXX shared library ../lib/libc10.so
 [  5%] Built target c10
 Scanning dependencies of target dispsse_obj
 [  5%] Building C object sleef/src/libm/CMakeFiles/dispsse_obj.dir/dispsse.c.o
 [  5%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/zero_copy_stream.cc.o
 [  5%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/zero_copy_stream_impl_lite.cc.o
 [  5%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/rendezvous/file_store.cc.o
 [  5%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/message_lite.cc.o
 [  5%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/rendezvous/hash_store.cc.o
 [  5%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/repeated_field.cc.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/generated_message_util.cc.o
 [  6%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/benchmark.cc.o
 [  6%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/sysinfo.cc.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/atomicops_internals_x86_gcc.cc.o
 [  6%] Built target dispsse_obj
 Scanning dependencies of target sleefavx
 [  6%] Building C object sleef/src/libm/CMakeFiles/sleefavx.dir/sleefsimdsp.c.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/atomicops_internals_x86_msvc.cc.o
 [  6%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/rendezvous/prefix_store.cc.o
 [  6%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/rendezvous/store.cc.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/bytestream.cc.o
 [  6%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/address.cc.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/common.cc.o
 [  6%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/int128.cc.o
 [  7%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/buffer.cc.o
 [  7%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/context.cc.o
 [  7%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/device.cc.o
 [  7%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/io/coded_stream.cc.o
 [  7%] Built target python_copy_files
 Scanning dependencies of target sleefavx512f
 [  7%] Building C object sleef/src/libm/CMakeFiles/sleefavx512f.dir/sleefsimdsp.c.o
 [  7%] Building C object sleef/src/libm/CMakeFiles/sleefavx.dir/sleefsimddp.c.o
 [  7%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/io_win32.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/once.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/pair.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/unbound_buffer.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/address.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/status.cc.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/csv_reporter.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/buffer.cc.o
 [  8%] Generating src/x86_64-fma/2d-fourier-16x16.py.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/statusor.cc.o
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefavx512f.dir/sleefsimddp.c.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/timers.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/stringpiece.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/context.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/stringprintf.cc.o
 [  8%] Built target sleefavx
 Scanning dependencies of target dispavx_obj
 [  8%] Building C object sleef/src/libm/CMakeFiles/dispavx_obj.dir/dispavx.c.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/io/zero_copy_stream.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/device.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/structurally_valid.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/io/zero_copy_stream_impl_lite.cc.o
 [  8%] Built target ATEN_CPU_FILES_GEN_TARGET
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/commandlineflags.cc.o
 Scanning dependencies of target sleefsse2
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefsse2.dir/sleefsimdsp.c.o
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefsse2.dir/sleefsimddp.c.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/strutil.cc.o
 [  8%] Built target sleefavx512f
 Scanning dependencies of target sleeffma4
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleeffma4.dir/sleefsimdsp.c.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/colorprint.cc.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/counter.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/time.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/wire_format_lite.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/message_lite.cc.o
 [  8%] Built target dispavx_obj
 Scanning dependencies of target sleefavx2
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefavx2.dir/sleefsimdsp.c.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/any.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/any.pb.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/repeated_field.cc.o
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleeffma4.dir/sleefsimddp.c.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/pair.cc.o
 [  8%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo.dir/transport/tcp/unbound_buffer.cc.o
 [  8%] Built target sleefsse2
 Scanning dependencies of target sleefavx2128
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefavx2128.dir/sleefsimdsp.c.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/string_util.cc.o
 [  8%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/reporter.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/api.pb.cc.o
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefavx2.dir/sleefsimddp.c.o
 [  8%] Linking CXX static library ../../../lib/libgtest.a
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/atomicops_internals_x86_gcc.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/compiler/importer.cc.o
 [  8%] Built target gtest
 Scanning dependencies of target sleefsse4
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefsse4.dir/sleefsimdsp.c.o
 [  8%] Building C object sleef/src/libm/CMakeFiles/sleefsse4.dir/sleefsimddp.c.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/atomicops_internals_x86_msvc.cc.o
 [  8%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/compiler/parser.cc.o
 [  9%] Built target sleeffma4
 Scanning dependencies of target gtest_main
 [  9%] Building CXX object third_party/googletest/googletest/CMakeFiles/gtest_main.dir/src/gtest_main.cc.o
 [  9%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/descriptor.cc.o
 [  9%] Building C object sleef/src/libm/CMakeFiles/sleefavx2128.dir/sleefsimddp.c.o
 [  9%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/descriptor.pb.cc.o
 [ 10%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark.dir/json_reporter.cc.o
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/bytestream.cc.o
 [ 10%] Built target sleefavx2
 Scanning dependencies of target __aten_op_header_gen
 [ 10%] Generating contrib/aten/aten_op.h
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/common.cc.o
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/int128.cc.o
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/io_win32.cc.o
 [ 10%] Built target sleefsse4
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/once.cc.o
 [ 10%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/status.cc.o
 [ 10%] Built target sleefavx2128
 Scanning dependencies of target sleef
 [ 11%] Building C object sleef/src/libm/CMakeFiles/sleef.dir/sleefdp.c.o
 [ 11%] Linking CXX static library ../../../lib/libgtest_main.a
 [ 11%] Built target gtest_main
 Scanning dependencies of target c10_TypeTraits_test
 [ 11%] Building CXX object c10/test/CMakeFiles/c10_TypeTraits_test.dir/util/TypeTraits_test.cpp.o
 [ 11%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/statusor.cc.o
 [ 11%] Linking CXX static library ../../../lib/libbenchmark.a
 [ 11%] Built target benchmark
 [ 11%] Building C object sleef/src/libm/CMakeFiles/sleef.dir/sleefsp.c.o
 Scanning dependencies of target c10_logging_test
 [ 11%] Building CXX object c10/test/CMakeFiles/c10_logging_test.dir/logging_test.cpp.o
 [ 11%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/descriptor_database.cc.o
 [ 11%] Building C object sleef/src/libm/CMakeFiles/sleef.dir/sleefld.c.o
 [ 11%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/stringpiece.cc.o
 [ 11%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/stringprintf.cc.o
 [ 11%] Building C object sleef/src/libm/CMakeFiles/sleef.dir/sleefqp.c.o
 [ 11%] Linking CXX static library ../../../lib/libgloo.a
 [ 12%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/structurally_valid.cc.o
 [ 12%] Built target gloo
 [ 12%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/duration.pb.cc.o
 Scanning dependencies of target c10_Array_test
 [ 12%] Building CXX object c10/test/CMakeFiles/c10_Array_test.dir/util/Array_test.cpp.o
 [ 12%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/strutil.cc.o
 [ 12%] Linking C static library ../../lib/libsleef.a
 [ 12%] Built target sleef
 Scanning dependencies of target c10_registry_test
 Scanning dependencies of target c10_Metaprogramming_test
 [ 12%] Building CXX object c10/test/CMakeFiles/c10_registry_test.dir/registry_test.cpp.o
 [ 12%] Building CXX object c10/test/CMakeFiles/c10_Metaprogramming_test.dir/util/Metaprogramming_test.cpp.o
 [ 12%] Linking CXX executable ../../bin/c10_TypeTraits_test
 [ 12%] Built target c10_TypeTraits_test
 Scanning dependencies of target c10_TypeList_test
 [ 12%] Building CXX object c10/test/CMakeFiles/c10_TypeList_test.dir/util/TypeList_test.cpp.o
 [ 12%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/stubs/time.cc.o
 [ 12%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf-lite.dir/__/src/google/protobuf/wire_format_lite.cc.o
 Scanning dependencies of target c10_flags_test
 [ 13%] Building CXX object c10/test/CMakeFiles/c10_flags_test.dir/flags_test.cpp.o
 [ 13%] Linking CXX executable ../../bin/c10_Array_test
 [ 13%] Built target c10_Array_test
 Scanning dependencies of target c10_utils_gpu_test
 [ 13%] Linking CXX executable ../../bin/c10_utils_gpu_test
 [ 13%] Built target c10_utils_gpu_test
 Scanning dependencies of target c10_utils_hip_test
 [ 13%] Building CXX object caffe2/utils/CMakeFiles/c10_utils_hip_test.dir/dummy.cpp.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/dynamic_message.cc.o
 [ 14%] Linking CXX executable ../../bin/c10_utils_hip_test
 [ 14%] Linking CXX executable ../../bin/c10_logging_test
 [ 14%] Built target c10_utils_hip_test
 Scanning dependencies of target c10_utils_cpu_test
 [ 14%] Linking CXX executable ../../bin/c10_utils_cpu_test
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/empty.pb.cc.o
 [ 14%] Built target c10_logging_test
 Scanning dependencies of target benchmark_main
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/extension_set_heavy.cc.o
 [ 14%] Building CXX object third_party/benchmark/src/CMakeFiles/benchmark_main.dir/benchmark_main.cc.o
 [ 14%] Built target c10_utils_cpu_test
 Scanning dependencies of target gloo_builder
 [ 14%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo_builder.dir/allreduce_builder.cc.o
 [ 14%] Linking CXX executable ../../bin/c10_TypeList_test
 [ 14%] Built target c10_TypeList_test
 [ 14%] Building CXX object third_party/gloo/gloo/CMakeFiles/gloo_builder.dir/broadcast_builder.cc.o
 [ 14%] Linking CXX static library ../../../lib/libprotobuf-lite.a
 [ 14%] Built target libprotobuf-lite
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/field_mask.pb.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/generated_message_reflection.cc.o
 [ 14%] Linking CXX executable ../../bin/c10_Metaprogramming_test
 [ 14%] Linking CXX executable ../../bin/c10_registry_test
 [ 14%] Built target c10_Metaprogramming_test
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/generated_message_table_driven.cc.o
 [ 14%] Built target c10_registry_test
 [ 14%] Linking CXX static library ../../../lib/libbenchmark_main.a
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/gzip_stream.cc.o
 [ 14%] Built target benchmark_main
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/printer.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/strtod.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/tokenizer.cc.o
 [ 14%] Linking CXX executable ../../bin/c10_flags_test
 [ 14%] Built target c10_flags_test
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/io/zero_copy_stream_impl.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/map_field.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/message.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/reflection_ops.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/service.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/source_context.pb.cc.o
 [ 14%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/struct.pb.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/mathlimits.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/stubs/substitute.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/text_format.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/timestamp.pb.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/type.pb.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/unknown_field_set.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/delimited_message_util.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/field_comparator.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/field_mask_util.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/datapiece.cc.o
 Skipping data_ptr Because of Ret: void* (void*)
 Skipping multinomial Because of Arg: Generator * (Generator*) 
 Skipping normal Because of Arg: Generator * (Generator*) 
 Skipping normal Because of Arg: Generator * (Generator*) 
 Skipping normal Because of Arg: Generator * (Generator*) 
 Skipping tensor Because of Arg: Storage (Storage) 
 Skipping tensor Because of Arg: Storage (Storage) 
 Skipping rrelu_with_noise Because of Arg: Generator * (Generator*) 
 Skipping rrelu_with_noise_forward Because of Arg: Generator * (Generator*) 
 Skipping thnn_batch_norm_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv_transpose2d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv_transpose3d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv2d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv_depthwise2d_backward Because of Arg: std::array<bool,2> (std::array<bool,2>) 
 Skipping thnn_conv3d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv_dilated2d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping thnn_conv_dilated3d_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping _cudnn_rnn_backward Because of Arg: std::array<bool,4> (std::array<bool,4>) 
 Skipping _cudnn_init_dropout_state because it is a factory method
 Skipping _fused_dropout Because of Arg: Generator * (Generator *) 
 Skipping arange because it is a factory method
 Skipping bartlett_window because it is a factory method
 Skipping bernoulli Because of Arg: Generator * (Generator *) 
 Skipping bernoulli Because of Arg: Generator * (Generator *) 
 Skipping blackman_window because it is a factory method
 Skipping _convolution_double_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping cudnn_convolution_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping cudnn_convolution_transpose_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping cumsum Because of Arg: ScalarType (ScalarType) 
 Skipping cumprod Because of Arg: ScalarType (ScalarType) 
 Skipping einsum Because of Arg: std::string (std::string) 
 Skipping empty because it is a factory method
 Skipping empty_like because it is a factory method
 Skipping empty_strided because it is a factory method
 Skipping eye because it is a factory method
 Skipping full because it is a factory method
 Skipping full_like because it is a factory method
 Skipping hann_window because it is a factory method
 Skipping hamming_window because it is a factory method
 Skipping _cufft_set_plan_cache_max_size Because of Ret: void (void)
 Skipping _cufft_clear_plan_cache Because of Ret: void (void)
 Skipping linspace because it is a factory method
 Skipping logspace because it is a factory method
 Skipping log_softmax Because of Arg: ScalarType (ScalarType) 
 Skipping mean Because of Arg: ScalarType (ScalarType) 
 Skipping mean Because of Arg: ScalarType (ScalarType) 
 Skipping mean Because of Arg: ScalarType (ScalarType) 
 Skipping mkldnn_convolution_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping miopen_convolution_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping miopen_convolution_transpose_backward Because of Arg: std::array<bool,3> (std::array<bool,3>) 
 Skipping ones because it is a factory method
 Skipping ones_like because it is a factory method
 Skipping rand because it is a factory method
 Skipping rand_like because it is a factory method
 Skipping randint because it is a factory method
 Skipping randint_like because it is a factory method
 Skipping randn because it is a factory method
 Skipping randn_like because it is a factory method
 Skipping randperm because it is a factory method
 Skipping range because it is a factory method
 Skipping rrelu Because of Arg: Generator * (Generator *) 
 Skipping softmax Because of Arg: ScalarType (ScalarType) 
 Skipping sum Because of Arg: ScalarType (ScalarType) 
 Skipping sum Because of Arg: ScalarType (ScalarType) 
 Skipping sum Because of Arg: ScalarType (ScalarType) 
 Skipping prod Because of Arg: ScalarType (ScalarType) 
 Skipping prod Because of Arg: ScalarType (ScalarType) 
 Skipping prod Because of Arg: ScalarType (ScalarType) 
 Skipping zeros because it is a factory method
 Skipping zeros_like because it is a factory method
 Skipping _standard_gamma Because of Arg: Generator * (Generator *) 
 Skipping poisson Because of Arg: Generator * (Generator *) 
 Skipping native_sparse_coo_tensor because it is a factory method
 Skipping sparse_coo_tensor because it is a factory method
 Skipping sparse_mask Because of Arg: SparseTensorRef (SparseTensorRef) 
 Skipping to Because of Arg: Device (Device) 
 Skipping to Because of Arg: Device (Device) 
 Skipping to Because of Arg: Device (Device) 
 Skipping to Because of Arg: ScalarType (ScalarType) 
 Skipping to Because of Arg: ScalarType (ScalarType) 
 Skipping to Because of Arg: ScalarType (ScalarType) 
 Skipping to Because of Arg: Device (Device) 
 Skipping to Because of Arg: Device (Device) 
 Skipping to Because of Arg: Device (Device) 
 [ 15%] Built target __aten_op_header_gen
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/default_value_objectwriter.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/error_listener.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/field_mask_utility.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/json_escaping.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/json_objectwriter.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/json_stream_parser.cc.o
 [ 15%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/object_writer.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/proto_writer.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/protostream_objectsource.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/protostream_objectwriter.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/type_info.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/type_info_test_helper.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/internal/utility.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/json_util.cc.o
 [ 16%] Generating src/x86_64-fma/2d-winograd-8x8-3x3.py.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/message_differencer.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/time_util.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/util/type_resolver_util.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/wire_format.cc.o
 [ 16%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotobuf.dir/__/src/google/protobuf/wrappers.pb.cc.o
 [ 16%] Generating src/x86_64-fma/blas/s8gemm.py.o
 [ 16%] Generating src/x86_64-fma/blas/c8gemm.py.o
 [ 16%] Linking CXX static library ../../../lib/libgloo_builder.a
 [ 16%] Built target gloo_builder
 [ 16%] Generating src/x86_64-fma/blas/s4c6gemm.py.o
 [ 16%] Linking CXX static library ../../../lib/libprotobuf.a
 [ 16%] Built target libprotobuf
 [ 16%] Generating ../../../../third_party/protobuf/src/google/protobuf/compiler/js/well_known_types_embed.cc
 [ 17%] Generating src/x86_64-fma/blas/conv1x1.py.o
 Scanning dependencies of target libprotoc
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_extension.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_file.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_enum_field.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_enum.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_message.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_field.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/code_generator.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/command_line_interface.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_helpers.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_padding_optimizer.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_generator.cc.o
 [ 17%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_map_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_message_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_service.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_primitive_field.cc.o
 [ 18%] Generating src/x86_64-fma/blas/sgemm.py.o
 [ 18%] Generating src/x86_64-fma/max-pooling.py.o
 [ 18%] Generating src/x86_64-fma/relu.py.o
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:125:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_STRING:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:123:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_BOOL:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:122:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_DOUBLE:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:121:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_FLOAT:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:120:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_UINT64:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:119:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_UINT32:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:118:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_INT64:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:117:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_INT32:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 /root/pytorch/third_party/protobuf/src/google/protobuf/compiler/cpp/cpp_message.cc:116:10: warning: comparison of two values with different enumeration types in switch statement ('FieldDescriptor::CppType' and 'google::protobuf::internal::WireFormatLite::CppType') [-Wenum-compare-switch]
    case internal::WireFormatLite::CPPTYPE_ENUM:
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 [ 18%] Generating src/x86_64-fma/softmax.py.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/cpp/cpp_string_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_doc_comment.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_enum.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_enum_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_field_base.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_generator.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_helpers.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_map_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_message.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_message_field.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_primitive_field.cc.o
 [ 18%] Generating src/x86_64-fma/blas/sdotxf.py.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_reflection_class.cc.o
 [ 18%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_repeated_enum_field.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_repeated_message_field.cc.o
 [ 19%] Generating src/x86_64-fma/blas/shdotxf.py.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_repeated_primitive_field.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_source_generator_base.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/csharp/csharp_wrapper_field.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_context.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_doc_comment.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_enum.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_enum_field.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_enum_field_lite.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_enum_lite.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_extension.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_extension_lite.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_field.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_file.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_generator.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_generator_factory.cc.o
 [ 19%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_helpers.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_lazy_message_field.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_lazy_message_field_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_map_field.cc.o
 9 warnings generated.
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_map_field_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message_builder.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message_builder_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message_field.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message_field_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_message_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_name_resolver.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_primitive_field.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_primitive_field_lite.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_service.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_shared_code_generator.cc.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_string_field.cc.o
 Scanning dependencies of target nnpack
 [ 20%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/init.c.o
 [ 20%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/java/java_string_field_lite.cc.o
 [ 20%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/convolution-inference.c.o
 [ 20%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/fully-connected-inference.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_enum.cc.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_enum_field.cc.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/pooling-output.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_extension.cc.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_field.cc.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/relu-output.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_file.cc.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_generator.cc.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/softmax-output.c.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/fully-connected-output.c.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/relu-input-gradient.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_helpers.cc.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/convolution-input-gradient.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_map_field.cc.o
 [ 21%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/convolution-kernel-gradient.c.o
 [ 21%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_message.cc.o
 [ 22%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/convolution-output.c.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_message_field.cc.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/javanano/javanano_primitive_field.cc.o
 [ 22%] Building C object confu-deps/NNPACK/CMakeFiles/nnpack.dir/src/x86_64-fma/softmax.c.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/js/js_generator.cc.o
 [ 22%] Linking C static library ../../lib/libnnpack.a
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/js/well_known_types_embed.cc.o
 [ 22%] Built target nnpack
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_enum.cc.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_enum_field.cc.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_extension.cc.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_field.cc.o
 [ 22%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_file.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_generator.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_helpers.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_map_field.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_message.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_message_field.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_oneof.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/objectivec/objectivec_primitive_field.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/php/php_generator.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/plugin.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/plugin.pb.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/python/python_generator.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/ruby/ruby_generator.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/subprocess.cc.o
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/libprotoc.dir/__/src/google/protobuf/compiler/zip_writer.cc.o
 [ 23%] Linking CXX static library ../../../lib/libprotoc.a
 [ 23%] Built target libprotoc
 Scanning dependencies of target protoc
 [ 23%] Building CXX object third_party/protobuf/cmake/CMakeFiles/protoc.dir/__/src/google/protobuf/compiler/main.cc.o
 [ 23%] Linking CXX executable ../../../bin/protoc
 [ 23%] Built target protoc
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/prof_dag.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/torch.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/caffe2.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/metanet.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/hsm.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/caffe2_legacy.proto
 [ 23%] Running C++/Python protocol buffer compiler on /root/pytorch/caffe2/proto/predictor_consts.proto
 Scanning dependencies of target gen_onnx_proto
 [ 23%] Running gen_proto.py on onnx/onnx.in.proto
 Processing /root/pytorch/third_party/onnx/onnx/onnx.in.proto
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx_onnx_torch.proto
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx_onnx_torch.proto3
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx.pb.h
 generating /root/pytorch/build/third_party/onnx/onnx/onnx_pb.py
 [ 23%] Running C++ protocol buffer compiler on /root/pytorch/build/third_party/onnx/onnx/onnx_onnx_torch.proto
 Scanning dependencies of target Caffe2_PROTO
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/caffe2_legacy.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/prof_dag.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/torch.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/hsm.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/caffe2.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/metanet.pb.cc.o
 [ 24%] Building CXX object caffe2/proto/CMakeFiles/Caffe2_PROTO.dir/predictor_consts.pb.cc.o
 [ 24%] Built target gen_onnx_proto
 [ 24%] Running gen_proto.py on onnx/onnx-operators.in.proto
 Processing /root/pytorch/third_party/onnx/onnx/onnx-operators.in.proto
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx-operators_onnx_torch.proto
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx-operators_onnx_torch.proto3
 Writing /root/pytorch/build/third_party/onnx/onnx/onnx-operators.pb.h
 generating /root/pytorch/build/third_party/onnx/onnx/onnx_operators_pb.py
 [ 24%] Running C++ protocol buffer compiler on /root/pytorch/build/third_party/onnx/onnx/onnx-operators_onnx_torch.proto
 Scanning dependencies of target onnx_proto
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx_proto.dir/onnx/onnx_onnx_torch.pb.cc.o
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx_proto.dir/onnx/onnx-operators_onnx_torch.pb.cc.o
 [ 24%] Linking CXX static library ../../lib/libonnx_proto.a
 [ 24%] Built target onnx_proto
 Scanning dependencies of target onnx
 [ 24%] Built target Caffe2_PROTO
 Scanning dependencies of target caffe2_protos
 [ 24%] Linking CXX static library ../lib/libcaffe2_protos.a
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/__/__/caffe2/onnx/torch_ops/defs.cc.o
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/optimizer/optimize.cc.o
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/common/ir_pb_converter.cc.o
 [ 24%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/common/assertions.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/__/__/caffe2/onnx/torch_ops/schema.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/optimizer/pass_manager.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/optimizer/pass.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/optimizer/pass_registry.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/common/status.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/onnxifi_utils.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/common/interned_strings.cc.o
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/common/model_helpers.cc.o
 Scanning dependencies of target Caffe2_perfkernels_avx
 [ 25%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx.dir/typed_axpy_avx.cc.o
 [ 25%] Built target caffe2_protos
 Scanning dependencies of target dispatch
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/shape_inference/implementation.cc.o
 [ 25%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/DeviceId.cpp.o
 Scanning dependencies of target Caffe2_perfkernels_avx2
 [ 25%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx2.dir/math_cpu_avx2.cc.o
 [ 25%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx2.dir/embedding_lookup_avx2.cc.o
 [ 25%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/Dispatcher.cpp.o
 [ 25%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/DispatchKey.cpp.o
 In file included from /root/pytorch/third_party/onnx/onnx/optimizer/pass_registry.cc:4:
 In file included from /root/pytorch/third_party/onnx/onnx/optimizer/pass_registry.h:22:
 /root/pytorch/third_party/onnx/onnx/optimizer/passes/nop.h:21:37: warning: 'runPass' overrides a member function but is not marked 'override' [-Winconsistent-missing-override]
  std::shared_ptr<PostPassAnalysis> runPass(Graph& graph) {
                                    ^
 /root/pytorch/third_party/onnx/onnx/optimizer/pass.h:110:45: note: overridden virtual function is here
  virtual std::shared_ptr<PostPassAnalysis> runPass(Graph& graph) = 0;
                                            ^
 In file included from /root/pytorch/third_party/onnx/onnx/optimizer/optimize.cc:4:
 In file included from /root/pytorch/third_party/onnx/onnx/optimizer/optimize.h:10:
 In file included from /root/pytorch/third_party/onnx/onnx/optimizer/pass_registry.h:22:
 /root/pytorch/third_party/onnx/onnx/optimizer/passes/nop.h:21:37: warning: 'runPass' overrides a member function but is not marked 'override' [-Winconsistent-missing-override]
  std::shared_ptr<PostPassAnalysis> runPass(Graph& graph) {
                                    ^
 /root/pytorch/third_party/onnx/onnx/optimizer/pass.h:110:45: note: overridden virtual function is here
  virtual std::shared_ptr<PostPassAnalysis> runPass(Graph& graph) = 0;
                                            ^
 [ 25%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/version_converter/convert.cc.o
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/DispatchTable.cpp.o
 [ 26%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx.dir/common_avx.cc.o
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/KernelRegistration.cpp.o
 1 warning generated.
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/LayoutId.cpp.o
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/LeftRight.cpp.o
 [ 26%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/version_converter/helper.cc.o
 [ 26%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/checker.cc.o
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/OpSchema.cpp.o
 [ 26%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/tensor/defs.cc.o
 [ 26%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch.dir/OpSchemaRegistration.cpp.o
 [ 26%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx2.dir/embedding_lookup_fused_8bit_rowwise_avx2.cc.o
 [ 26%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/tensor/old.cc.o
 [ 26%] Built target Caffe2_perfkernels_avx
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/logical/defs.cc.o
 [ 27%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx2.dir/typed_axpy_avx2.cc.o
 [ 27%] Building CXX object caffe2/perfkernels/CMakeFiles/Caffe2_perfkernels_avx2.dir/common_avx2.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/logical/old.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/experiments/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/experiments/experiments_functions.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/reduction/defs.cc.o
 [ 27%] Built target dispatch
 Scanning dependencies of target dispatch_test
 [ 27%] Building CXX object caffe2/core/dispatch/CMakeFiles/dispatch_test.dir/OpSchema_test.cpp.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/function.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/generator/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/generator/old.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/traditionalml/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/math/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/math/old.cc.o
 [ 27%] Linking CXX executable ../../../bin/dispatch_test
 [ 27%] Built target dispatch_test
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/data_type_utils.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/rnn/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/rnn/old.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/schema.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/controlflow/defs.cc.o
 [ 27%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/nn/defs.cc.o
 [ 28%] Building CXX object third_party/onnx/CMakeFiles/onnx.dir/onnx/defs/nn/old.cc.o
 [ 28%] Built target Caffe2_perfkernels_avx2
 1 warning generated.
 [ 28%] Linking CXX static library ../../lib/libonnx.a
 [ 28%] Built target onnx
 Scanning dependencies of target caffe2
 [ 28%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUGeneral.cpp.o
 [ 28%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/Utils.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/Context.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUGenerator.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseTensorImpl.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/TensorGeometry.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUTypeDefault.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/cpu/FlushDenormal.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/TensorUtils.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/UndefinedType.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/ExpandUtils.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/DLConvertor.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CUDAStream.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/detail/ComplexHooksInterface.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/UndefinedTensorImpl.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/detail/CUDAHooksInterface.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/VariableHooksInterface.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/ivalue.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/intrusive_ptr.cpp.o
 [ 29%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/OptionsGuard.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Storage.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Half.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/LegacyTypeDispatch.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/ATenCoreTest.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/blob.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/SmallVector.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Allocator.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/context_base.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/typeid.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/DeviceType.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/TensorOptions.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/interned_strings.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/StorageImpl.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/AlignOf.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/ArrayRef.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/TensorTypeIdRegistration.cpp.o
 [ 30%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/UniqueVoidPtr.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/register_symbols.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Tensor.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/TensorImpl.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Formatting.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Device.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/TensorTypeId.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/ATenGeneral.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/core/Scalar.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Dropout.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Loss.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Activation.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Memory.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/SoftMax.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Linear.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/ReduceOps.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/DispatchStub.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Distributions.cpp.o
 [ 31%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/RNN.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/SummaryOps.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Pooling.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TypeProperties.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/LossCTC.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/PackedSequence.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Gesv.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorProperties.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/SpectralOps.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/UnaryOps.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/BinaryOps.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorConversions.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/ConvolutionTBC.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Distance.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/LinearAlgebra.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorIterator.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Embedding.cpp.o
 [ 32%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorCompare.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/RoiPooling.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Convolution.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/EmbeddingBag.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorShape.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/LegacyBridge.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/WeightNorm.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorFactories.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/TensorTransformations.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Indexing.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/GridSampler.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Scalar.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/PixelShuffle.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Unique.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/Normalization.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/sparse/SparseTensor.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/sparse/SparseTensorMath.cpp.o
 [ 33%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/mkl/SpectralOps.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/mkl/LinearAlgebra.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/mkldnn/Conv.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUByteType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUCharType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUCopy.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUDoubleType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUFloatType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUHalfType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUIntType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPULongType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/CPUShortType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/RegisterCPU.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUByteType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUCharType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUDoubleType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUFloatType.cpp.o
 [ 34%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUIntType.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPULongType.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/SparseCPUShortType.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/TypeDefault.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THGeneral.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THAllocator.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THSize.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THStorageFunctions.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensor.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorCopy.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorRandom.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorMath.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorMoreMath.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorEvenMoreMath.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorConv.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THTensorLapack.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THBlas.cpp.o
 [ 35%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THLapack.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THLogAdd.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THRandom.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THFile.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THDiskFile.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THMemoryFile.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/THVector.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/vector/AVX.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/TH/vector/AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/THNN/init.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/DistanceOpsKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/TensorCompareKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/SoftMaxKernel.cpp.AVX2.cpp.o
 [ 36%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/DistanceOpsKernel.cpp.AVX.cpp.o
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX2.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/TensorCompareKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/SoftMaxKernel.cpp.AVX.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/DistanceOpsKernel.cpp.DEFAULT.cpp.o
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.AVX.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.DEFAULT.cpp.o
 28 warnings generated.
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp.DEFAULT.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp.DEFAULT.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/TensorCompareKernel.cpp.DEFAULT.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/__/aten/src/ATen/native/cpu/SoftMaxKernel.cpp.DEFAULT.cpp.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/aten/aten_op.cc.o
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:182:40: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::plus, 0>::apply' requested here
    Reduction<scalar_t, std::plus, 0>::apply(result, self, dim);
                                       ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<unsigned char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<signed char, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<double, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<float, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<int, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<long, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:42: warning: lambda capture 'cols' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                         ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:191:46: note: in instantiation of member function 'at::native::(anonymous namespace)::Reduction<short, std::multiplies, 1>::apply' requested here
    Reduction<scalar_t, std::multiplies, 1>::apply(result, self, dim);
                                             ^
 /root/pytorch/build/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp.DEFAULT.cpp:101:48: warning: lambda capture 'cols_rounded' is not used [-Wunused-lambda-capture]
          [out_, data_, n, stride, rows, cols, cols_rounded, size](
                                               ^
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/allgather_ops.cc.o
 28 warnings generated.
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/allreduce_ops.cc.o
 [ 37%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/barrier_ops.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/broadcast_ops.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/common.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/common_world_ops.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/context.cc.o
 28 warnings generated.
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/reduce_scatter_ops.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/gloo/store_handler.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/script/compiler.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/contrib/script/lexer.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/blob_stats.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_async_base.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_async_scheduling.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/qtensor_serialization.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/blob_serialization.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/stats.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_simple_async.cc.o
 [ 38%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/graph.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/event.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/init.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/operator_schema.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/allocator.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/common.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/tensor_impl.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/module.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/types.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/int8_serialization.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/transform.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/init_omp.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_async_tracing.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_async_polling.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/plan_executor.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/workspace.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/init_intrinsics_check.cc.o
 [ 39%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/memonger.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/context_base.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/numa.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/context.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_simple.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/db.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/tensor.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/operator_c10wrapper.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/tensor_int8.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/prof_dag_counters.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/operator.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/qtensor.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_dag_utils.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/net_dag.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/proto_convert.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/proto_wrap.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/proto_utils.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/murmur_hash3.cc.o
 [ 40%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/smart_tensor_printer.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/signal_handler.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/string_utils.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/threadpool/ThreadPool.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/cpuid.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/bench_utils.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/math_cpu.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/math_utils.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/thread_name.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/threadpool/pthreadpool.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/utils/threadpool/pthreadpool_impl.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/predictor/predictor.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/predictor/predictor_utils.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/predictor/predictor_config.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/nomnigraph/Representations/NeuralNet.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/core/nomnigraph/tests/test_util.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/db/create_db_op.cc.o
 [ 41%] Building CXX object caffe2/CMakeFiles/caffe2.dir/db/protodb.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/distributed/file_store_handler.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/distributed/file_store_handler_op.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/distributed/store_handler.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/distributed/store_ops.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/observers/time_observer.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/observers/runcnt_observer.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/onnx_exporter.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/backend_rep.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/onnxifi_init.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/device.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/helper.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/onnx/backend.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/square_root_divide_op.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cbrt_op.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/roi_align_op.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sigmoid_op.cc.o
 [ 42%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_reducer_fused_8bit_rowwise_ops.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/percentile_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/key_split_ops.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/locally_connected_op_util.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/crf_viterbi_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_sum_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/order_switch_ops.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conditional_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/relu_n_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/create_scope_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pad_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/hard_sigmoid_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/spatial_batch_norm_gradient_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/gru_unit_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/listwise_l2r_op.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ngram_ops.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reduce_ops.cc.o
 [ 43%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/h_softmax_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/floor_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cosh_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/layer_norm_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_bucketize_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/exp_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/instance_norm_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/one_hot_ops.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/partition_ops.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/given_tensor_byte_string_to_uint8_fill_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/distance_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/is_empty_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/unique_ops.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ensure_clipped_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/byte_weight_dequant_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/stump_func_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sparse_to_dense_mask_op.cc.o
 [ 44%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/replace_nan_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_sparse_to_dense_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/index_hash_ops.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reverse_packed_segs_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/matmul_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/communicator_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_ops_schema.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/text_file_reader.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cross_entropy_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elu_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/asin_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/log_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/deform_conv_gradient_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tanh_gradient_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/weighted_sample_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/stats_put_ops.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_op.cc.o
 [ 45%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/workspace_ops.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/minmax_gradient_ops.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pack_rnn_sequence_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/given_tensor_fill_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/expand_squeeze_dims_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cosine_embedding_criterion_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/feed_blob_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/text_file_reader_utils.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ceil_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/apmeter_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sigmoid_gradient_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/channel_shuffle_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/flatten_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lp_pool_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/copy_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/clip_op.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/dataset_ops.cc.o
 [ 46%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rowmul_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/group_norm_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tt_linear_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/piecewise_linear_transform_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/roi_align_rotated_gradient_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/norm_planar_yuv_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/moments_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/gather_ranges_to_dense_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/multi_class_accuracy_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_transpose_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/accuracy_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_linear_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/bisect_percentile_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_reducer_ops.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/mod_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reduce_front_back_sum_ops.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/normalize_l1_op.cc.o
 [ 47%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_tile_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/roi_align_gradient_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_add_gradient_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/string_ops.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/onnxifi_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/slice_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/local_response_normalization_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/concat_split_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reduce_front_back_mean_ops.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/length_split_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/integral_image_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reshape_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/filler_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ctc_beam_search_decoder_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sqrt_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_mul_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/spatial_batch_norm_op.cc.o
 [ 48%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/prepend_dim_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pool_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/logit_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/spatial_softmax_with_loss_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/accumulate_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/box_with_nms_limit_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/summarize_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/boolean_unmask_ops.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/relu_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tan_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/find_duplicate_elements_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/collect_and_distribute_fpn_rpn_proposals_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rmac_regions_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_sub_gradient_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/margin_ranking_criterion_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/free_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/counter_ops.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/roi_align_rotated_op.cc.o
 [ 49%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_transpose_op_mobile.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/numpy_tile_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_div_gradient_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/while_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sqr_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/utility_ops.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/remove_data_blocks_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/onnx_while_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lstm_unit_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_logical_ops.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/loss_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/heatmap_max_keypoint_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/softmax_with_loss_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/fc_inference.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/negate_gradient_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cube_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reciprocal_gradient_op.cc.o
 [ 50%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/quant_decode_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lpnorm_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/weighted_multi_sampling_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/variable_length_sequence_padding.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/index_ops.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tile_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/channel_stats_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sinh_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_sub_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_op_shared.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/stylizer_ops.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/map_ops.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/boolean_mask_ops.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/stop_gradient.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pool_gradient_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/merge_id_lists_op.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_ops_utils.cc.o
 [ 51%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_add_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/negative_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/softplus_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/deform_conv_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/upsample_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_top_k_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/resize_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/if_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/gather_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_box_cox_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_matmul_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/swish_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/channel_backprop_stats_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/top_k.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/abs_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/jsd_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sparse_to_dense_op.cc.o
 [ 52%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/locally_connected_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/minmax_ops.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/scale_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/perplexity_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reduction_ops.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/acos_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/feature_maps_ops.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/stats_ops.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/normalize_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rsqrt_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/instance_norm_gradient_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reciprocal_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/do_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/data_couple.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_reducer_rowwise_8bit_ops.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_gradient_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/transpose_op.cc.o
 [ 53%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/atomic_ops.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tanh_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cast_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/atan_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/prelu_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/mean_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rank_loss_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/generate_proposals_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/thresholded_relu_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/softmax_shared.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_div_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sequence_ops.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/softsign_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_mul_gradient_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/fused_rowwise_random_quantization_ops.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/fully_connected_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/find_op.cc.o
 [ 54%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/softmax_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/load_save_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/segment_reduction_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sin_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/dropout_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/selu_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/shape_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/bbox_transform_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_moments_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ctc_greedy_decoder_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reduce_front_back_max_ops.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/cos_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/expand_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/tensor_protos_db_input.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sinusoid_position_encoding_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/leaky_relu_op.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_op_eigen.cc.o
 [ 55%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/reservoir_sampling.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/conv_transpose_gradient_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/zero_gradient_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/last_n_window_collector.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/enforce_finite_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/elementwise_ops.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/half_float_ops.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/assert_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/fused_rowwise_8bit_conversion_ops.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/glu_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/roi_pool_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/sparse_normalize_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/arg_ops.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/flexible_top_k.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pow_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/space_batch_op.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/batch_gather_ops.cc.o
 [ 56%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/gather_fused_8bit_rowwise_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/ensure_cpu_output_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/pack_segments.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/affine_channel_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/lengths_pad_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/im2col_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rnn/recurrent_network_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rnn/recurrent_network_blob_fetcher_op.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/operators/rnn/recurrent_network_executor.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/passes.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/annotations.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/backend_cutting.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/distributed.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/fusion.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/onnxifi_transformer.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/sink.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/distributed_converter.cc.o
 [ 57%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/mobile.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/device.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/dead_code_elim.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/optimizer.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/optimize_ideep.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/opt/converter.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/perfkernels/embedding_lookup.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/perfkernels/typed_axpy.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/perfkernels/math_cpu_base.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/perfkernels/fused_8bit_rowwise_embedding_lookup.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/queue/rebatching_queue.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/queue/rebatching_queue_ops.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/queue/blobs_queue.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/queue/queue_ops.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/queue/blobs_queue_db.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/adam_op.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/adagrad_op.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/yellowfin_op.cc.o
 [ 58%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/wngrad_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/gftrl_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/iter_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/momentum_sgd_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/rmsprop_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/adadelta_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/learning_rate_adaption_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/ftrl_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/learning_rate_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/lars_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/sgd/clip_tensor_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/share/contrib/nnpack/conv_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/share/contrib/depthwise/depthwise3x3_conv_op.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/transforms/common_subexpression_elimination.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/transforms/pattern_net_transform.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/transforms/single_op_transform.cc.o
 [ 59%] Building CXX object caffe2/CMakeFiles/caffe2.dir/transforms/conv_to_nnpack_transform.cc.o
 [ 59%] Linking CXX shared library ../lib/libcaffe2.so
 [ 59%] Built target caffe2
 [ 59%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_BatchNorm.cpp.o
 [ 59%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_LossCTC.cpp.o
 [ 59%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/miopen/caffe2_hip_generated_Conv_miopen.cpp.o
 [ 59%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/miopen/caffe2_hip_generated_Handle.cpp.o
 [ 59%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_RNN.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_AffineGridGenerator.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_Conv.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/miopen/caffe2_hip_generated_BatchNorm_miopen.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/miopen/caffe2_hip_generated_Descriptors.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cudnn/caffe2_hip_generated_GridSampler.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/miopen/caffe2_hip_generated_Types.cpp.o
 [ 60%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/sparse/cuda/caffe2_hip_generated_SparseCUDATensor.cpp.o
 Scanning dependencies of target caffe2_module_test_dynamic
 [ 60%] Building CXX object modules/module_test/CMakeFiles/caffe2_module_test_dynamic.dir/module_test_dynamic.cc.o
 Scanning dependencies of target caffe2_observers
 [ 60%] Building CXX object modules/observers/CMakeFiles/caffe2_observers.dir/net_observer_reporter_print.cc.o
 Scanning dependencies of target caffe2_pybind11_state
 Scanning dependencies of target caffe2_detectron_ops
 [ 60%] Building CXX object caffe2/CMakeFiles/caffe2_pybind11_state.dir/python/pybind_state.cc.o
 [ 61%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/select_smooth_l1_loss_op.cc.o
 [ 61%] Building CXX object modules/observers/CMakeFiles/caffe2_observers.dir/observer_config.cc.o
 [ 61%] Linking CXX shared library ../../lib/libcaffe2_module_test_dynamic.so
 [ 61%] Built target caffe2_module_test_dynamic
 [ 61%] Building CXX object caffe2/CMakeFiles/caffe2_pybind11_state.dir/python/pybind_state_dlpack.cc.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/caffe2_hip_generated_PinnedMemoryAllocator.cpp.o
 [ 61%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/sample_as_op.cc.o
 [ 61%] Building CXX object modules/observers/CMakeFiles/caffe2_observers.dir/perf_observer.cc.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/caffe2_hip_generated_CUDAContext.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/caffe2_hip_generated_CUDAGenerator.cpp.o
 [ 61%] Building CXX object caffe2/CMakeFiles/caffe2_pybind11_state.dir/python/pybind_state_nomni.cc.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/caffe2_hip_generated_CUDAStream.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/caffe2_hip_generated_CUDATypeDefault.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/detail/caffe2_hip_generated_CUDAHooks.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_CUDAReduceOps.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_CUDAUnaryOps.cpp.o
 [ 61%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDAByteType.cpp.o
 [ 61%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/roi_pool_f_op.cc.o
 [ 61%] Linking CXX shared library ../../lib/libcaffe2_observers.so
 [ 61%] Built target caffe2_observers
 [ 61%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/smooth_l1_loss_op.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDACharType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDACopy.cpp.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/upsample_nearest_op.cc.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/softmax_focal_loss_op.cc.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/sigmoid_focal_loss_op.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDADoubleType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDAFloatType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDAHalfType.cpp.o
 [ 62%] Building CXX object caffe2/CMakeFiles/caffe2_pybind11_state.dir/python/pybind_state_registry.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDAIntType.cpp.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/ps_roi_pool_op.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDALongType.cpp.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/batch_permutation_op.cc.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/sigmoid_cross_entropy_loss_op.cc.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/group_spatial_softmax_op.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_CUDAShortType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_RegisterCUDA.cpp.o
 [ 62%] Building CXX object modules/detectron/CMakeFiles/caffe2_detectron_ops.dir/spatial_narrow_as_op.cc.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDAByteType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDACharType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDADoubleType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDAFloatType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDAIntType.cpp.o
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDALongType.cpp.o
 [ 62%] Linking CXX shared library ../../lib/libcaffe2_detectron_ops.so
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/build/aten/src/ATen/caffe2_hip_generated_SparseCUDAShortType.cpp.o
 [ 62%] Built target caffe2_detectron_ops
 [ 62%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCCachingAllocator.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCCachingHostAllocator.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCGeneral.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCStorageCopy.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCStream.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensor.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorCopy.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorRandom.cpp.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCReduceApplyUtils.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCBlas.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCSleep.cu.o
 [ 63%] Linking CXX shared module python/caffe2_pybind11_state.cpython-36m-x86_64-linux-gnu.so
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCStorage.cu.o
 [ 63%] Built target caffe2_pybind11_state
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCStorageCopy.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensor.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorCopy.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMath.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMathBlas.cu.o
 [ 63%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMathMagma.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMathPairwise.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMathReduce.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMathScan.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorIndex.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorRandom.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorScatterGather.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorTopK.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorSort.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCSortUtils.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/caffe2_hip_generated_THCTensorMode.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedByte.cu.o
 [ 64%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedChar.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedShort.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortInt.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTInt.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseInt.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareInt.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceInt.cu.o
 [ 65%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedInt.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedLong.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedHalf.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortFloat.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTFloat.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseFloat.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareFloat.cu.o
 [ 66%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceFloat.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedFloat.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorSortDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareTDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathPointwiseDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathCompareDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMathReduceDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THC/generated/caffe2_hip_generated_THCTensorMaskedDouble.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_AbsCriterion.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Abs.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_BatchNormalization.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_BCECriterion.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_ClassNLLCriterion.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Col2Im.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_DistKLDivCriterion.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_ELU.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_FeatureLPPooling.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_GatedLinearUnit.cu.o
 [ 67%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_HardTanh.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Im2Col.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_IndexLinear.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_L1Cost.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_LeakyReLU.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_LogSigmoid.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_LookupTableBag.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_LookupTable.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_MarginCriterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_MSECriterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_MultiLabelMarginCriterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_MultiMarginCriterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_RReLU.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Sigmoid.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SmoothL1Criterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SoftMarginCriterion.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SoftPlus.cu.o
 [ 68%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SoftShrink.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SparseLinear.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialAdaptiveAveragePooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialAdaptiveMaxPooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialAveragePooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialClassNLLCriterion.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialConvolutionLocal.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialConvolutionMM.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialCrossMapLRN.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialDepthwiseConvolution.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialDilatedConvolution.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialDilatedMaxPooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialFractionalMaxPooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialFullConvolution.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialFullDilatedConvolution.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialMaxPooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialMaxUnpooling.cu.o
 [ 69%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialReflectionPadding.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialReplicationPadding.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialSubSampling.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialUpSamplingBilinear.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_SpatialUpSamplingNearest.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Sqrt.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Square.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Tanh.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalConvolution.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalMaxPooling.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalReflectionPadding.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalReplicationPadding.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalRowConvolution.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalUpSamplingLinear.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_TemporalUpSamplingNearest.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_Threshold.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricAdaptiveAveragePooling.cu.o
 [ 70%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricAdaptiveMaxPooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricAveragePooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricConvolution.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricDilatedConvolution.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricDilatedMaxPooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricFractionalMaxPooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricFullConvolution.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricFullDilatedConvolution.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricMaxPooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricMaxUnpooling.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricReplicationPadding.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricUpSamplingNearest.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/THCUNN/caffe2_hip_generated_VolumetricUpSamplingTrilinear.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/cuda/detail/caffe2_hip_generated_IndexUtils.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_SoftMax.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Distributions.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_TensorTransformations.cu.o
 [ 71%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_SpectralOps.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Loss.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_RoiPooling.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_TensorFactories.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_LossCTC.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_BinaryOpsKernel.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_RNN.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_WeightNorm.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_SparseMM.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_SummaryOps.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_DistanceKernel.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Gesv.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_GridSampler.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_CUDAScalar.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_EmbeddingBag.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Embedding.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_TensorCompare.cu.o
 [ 72%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_LinearAlgebra.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Activation.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Dropout.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/cuda/caffe2_hip_generated_Unique.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/sparse/cuda/caffe2_hip_generated_SparseCUDABlas.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/sparse/cuda/caffe2_hip_generated_SparseCUDATensorMath.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/__/aten/src/ATen/native/sparse/cuda/caffe2_hip_generated_SparseCUDATensor.cu.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_net_async_hip_thread_pool_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_context_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_net_async_dag_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_event_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_blob_serialization_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_THCCachingAllocator_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_common_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/core/hip/caffe2_hip_generated_common_miopen.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/utils/hip/caffe2_hip_generated_math_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/db/hip/caffe2_hip_generated_create_db_op_hip.cc.o
 [ 73%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_instance_norm_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_lp_pool_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_stop_gradient_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_pow_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_shape_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_fully_connected_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_lengths_pad_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_glu_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_lengths_tile_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reduce_front_back_sum_mean_ops_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_segment_reduction_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_group_norm_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cosine_embedding_criterion_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_perplexity_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elu_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_matmul_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_stump_func_op_hip.cc.o
 [ 74%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sqr_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_integral_image_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cbrt_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_layer_norm_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_scale_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_distance_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_accumulate_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_mean_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_ops_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cosh_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_dropout_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_tensor_protos_db_input_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_tanh_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cross_entropy_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_moments_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_selu_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cos_op_hip.cc.o
 [ 75%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_im2col_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_conv_op_shared_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_negative_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_div_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_conv_transpose_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_data_couple_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_sub_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_softsign_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_utility_ops_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reshape_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_piecewise_linear_transform_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cast_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_roi_align_rotated_gradient_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_prepend_dim_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_zero_gradient_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_add_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_local_response_normalization_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_expand_op_hip.cc.o
 [ 76%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_channel_backprop_stats_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_find_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_swish_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_copy_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_cube_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_asin_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_rsqrt_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_prelu_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_order_switch_ops_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_lstm_unit_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_affine_channel_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reduce_ops_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_atan_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_acos_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_leaky_relu_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_log_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_mul_op_hip.cc.o
 [ 77%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sparse_normalize_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sin_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reverse_packed_segs_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sparse_to_dense_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_summarize_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_gather_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_conv_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_do_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_gru_unit_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_rmac_regions_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_pad_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_arg_ops_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sigmoid_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_assert_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_deform_conv_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_abs_op_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_softmax_ops_hip.cc.o
 [ 78%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_half_float_ops_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_loss_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_boolean_mask_ops_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_given_tensor_byte_string_to_uint8_fill_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_accuracy_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_transpose_op_hip.cc.o
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:398:35: warning: using integer absolute value function 'abs' when argument is of floating point type [-Wabsolute-value]
            cur_w + dx < width && abs(cur_inv_h_data - (cur_h + dy)) < 1 &&
                                  ^
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:449:22: note: in instantiation of function template specialization 'caffe2::deformable_col2im_gpu_kernel<float>' requested here
 hipLaunchKernelGGL( deformable_col2im_gpu_kernel<DType>
                     ^
 /root/pytorch/caffe2/operators/deform_conv_op_impl.h:350:7: note: in instantiation of member function 'caffe2::DeformConvOpBase<float, caffe2::HIPContext>::DeformableCol2im' requested here
      DeformableCol2im(
      ^
 /root/pytorch/caffe2/operators/deform_conv_op.h:87:3: note: in instantiation of member function 'caffe2::DeformConvGradientOp<float, caffe2::HIPContext>::RunOnDeviceWithOrderNCHW' requested here
  DeformConvGradientOp(const OperatorDef& operator_def, Workspace* ws)
  ^
 /root/pytorch/c10/util/Registry.h:182:30: note: in instantiation of member function 'caffe2::DeformConvGradientOp<float, caffe2::HIPContext>::DeformConvGradientOp' requested here
    return ObjectPtrType(new DerivedType(args...));
                             ^
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:623:1: note: in instantiation of function template specialization 'c10::Registerer<std::__cxx11::basic_string<char>, std::unique_ptr<caffe2::OperatorBase, std::default_delete<caffe2::OperatorBase> >, const caffe2::OperatorDef &, caffe2::Workspace *>::DefaultCreator<caffe2::DeformConvGradientOp<float, caffe2::HIPContext> >' requested here
 REGISTER_HIP_OPERATOR(
 ^
 /root/pytorch/caffe2/core/operator.h:907:3: note: expanded from macro 'REGISTER_HIP_OPERATOR'
  C10_REGISTER_CLASS(HIPOperatorRegistry, name, __VA_ARGS__)
  ^
 /root/pytorch/c10/util/Registry.h:289:3: note: expanded from macro 'C10_REGISTER_CLASS'
  C10_REGISTER_TYPED_CLASS(RegistryName, #key, __VA_ARGS__)
  ^
 /root/pytorch/c10/util/Registry.h:248:33: note: expanded from macro 'C10_REGISTER_TYPED_CLASS'
      Registerer##RegistryName::DefaultCreator<__VA_ARGS__>,                \
                                ^
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:398:35: note: use function 'std::abs' instead
            cur_w + dx < width && abs(cur_inv_h_data - (cur_h + dy)) < 1 &&
                                  ^~~
                                  std::abs
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:399:13: warning: using integer absolute value function 'abs' when argument is of floating point type [-Wabsolute-value]
            abs(cur_inv_w_data - (cur_w + dx)) < 1) {
            ^
 /root/pytorch/caffe2/operators/hip/deform_conv_op_hip.cc:399:13: note: use function 'std::abs' instead
            abs(cur_inv_w_data - (cur_w + dx)) < 1) {
            ^~~
            std::abs
 2 warnings generated.
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_margin_ranking_criterion_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_elementwise_linear_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_max_pool_with_index_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_concat_split_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_spatial_batch_norm_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_free_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_ensure_cpu_output_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_replace_nan_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_exp_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_mem_query_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_ceil_op_hip.cc.o
 [ 79%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_softplus_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_expand_squeeze_dims_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reduce_front_back_max_ops_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_roi_align_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_multi_class_accuracy_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_load_save_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_while_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sinh_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_boolean_unmask_ops_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_floor_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sequence_ops_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_space_batch_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_pack_segments_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_given_tensor_fill_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_normalize_ops_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_tan_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_pool_op_hip.cc.o
 [ 80%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_relu_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_roi_align_gradient_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_relu_n_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_resize_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_thresholded_relu_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reduction_ops_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_negate_gradient_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_sqrt_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_batch_moments_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_unique_ops_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_roi_align_rotated_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_slice_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_batch_matmul_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_communicator_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_batch_gather_ops_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_logit_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_reciprocal_op_hip.cc.o
 [ 81%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_filler_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_enforce_finite_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_locally_connected_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_roi_pool_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_channel_stats_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_tile_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_clip_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_channel_shuffle_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_counter_ops_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_weighted_sample_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_hard_sigmoid_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_one_hot_ops_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_if_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/rnn/hip/caffe2_hip_generated_recurrent_network_blob_fetcher_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/rnn/hip/caffe2_hip_generated_recurrent_network_executor_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/rnn/hip/caffe2_hip_generated_recurrent_network_op_hip.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_conv_op_miopen.cc.o
 [ 82%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_local_response_normalization_op_miopen.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_relu_op_miopen.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_spatial_batch_norm_op_miopen.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/caffe2_hip_generated_pool_op_miopen.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/operators/rnn/hip/caffe2_hip_generated_recurrent_op_miopen.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/queue/hip/caffe2_hip_generated_queue_ops_hip.cc.o
 Stack dump:
 0.	Program arguments: /opt/rocm/hcc/bin/clang-7 -cc1 -D__KALMAR_HC__=1 -D__HCC_HC__=1 -famp-is-device -fno-builtin -fno-common -O2 -triple amdgcn--amdhsa-hcc -aux-triple x86_64-unknown-linux-gnu -S -disable-free -disable-llvm-verifier -main-file-name unique_ops_hip.cc -mrelocation-model pic -pic-level 2 -mthread-model posix -mdisable-fp-elim -fmath-errno -no-integrated-as -mconstructor-aliases -fuse-init-array -coverage-notes-file /root/pytorch/build/caffe2/CMakeFiles/caffe2_hip.dir/operators/hip/./caffe2_hip_generated_unique_ops_hip.cc.gcno -resource-dir /opt/rocm/hcc/lib/clang/7.0.0 -I/opt/rocm/hcc/bin/../include -I/opt/rocm/hcc/bin/../hcc/include -D __HIPCC__ -I /opt/rocm/hcc/include -I /opt/rocm/include/hip/hcc_detail/cuda -I /opt/rocm/hsa/include -I /opt/rocm/profiler/CXLActivityLogger/include -I /opt/rocm/include -D HIP_VERSION_MAJOR=1 -D HIP_VERSION_MINOR=5 -D HIP_VERSION_PATCH=18382 -D __HIP_ARCH_GFX900__=1 -I /usr/include/x86_64-linux-gnu -I /usr/include/x86_64-linux-gnu/c++/4.2.1 -I /usr/include/c++/4.2.1 -D __HIP_PLATFORM_HCC__=1 -D CUDA_HAS_FP16=1 -D __HIP_NO_HALF_OPERATORS__=1 -D __HIP_NO_HALF_CONVERSIONS__=1 -D NDEBUG -D ONNX_NAMESPACE=onnx_torch -D USE_GCC_ATOMICS=1 -D HAVE_MMAP=1 -D _FILE_OFFSET_BITS=64 -D HAVE_SHM_OPEN=1 -D HAVE_SHM_UNLINK=1 -D HAVE_MALLOC_USABLE_SIZE=1 -I /opt/rocm/hcc/include -I /opt/rocm/hsa/include -I /opt/rocm/rocrand/include -I /opt/rocm/hiprand/include -I /opt/rocm/rocblas/include -I /opt/rocm/miopen/include -I /opt/rocm/include -I /opt/rocm/include/thrust/system/cuda/detail/cub-hip -I /opt/rocm/hcc/include -I /opt/rocm/hsa/include -I /opt/rocm/rocrand/include -I /opt/rocm/hiprand/include -I /opt/rocm/rocblas/include -I /opt/rocm/miopen/include -I /opt/rocm/include -I /opt/rocm/include/thrust/system/cuda/detail/cub-hip -I /root/pytorch/build/caffe2/aten/src/TH -I /root/pytorch/aten/src/TH -I /root/pytorch/aten/src/THC -I /root/pytorch/build/caffe2/aten/src/THC -I /root/pytorch/build/caffe2/aten/src/THC -I /root/pytorch/aten/src/THC -I /root/pytorch/aten/src/THCUNN -I /root/pytorch/aten/src/ATen/cuda -I /root/pytorch/build/caffe2/aten/src/TH -I /root/pytorch/aten/src/TH -I /root/pytorch/aten/src/TH -I /root/pytorch/build/caffe2/aten/src/TH -I /root/pytorch/aten/src -I /root/pytorch/build/caffe2/aten/src -I /root/pytorch/build/aten/src -I /root/pytorch/aten/src/THNN -I /root/pytorch/aten/src/THCUNN -I /root/pytorch/aten/src -I /root/pytorch/aten/../third_party/catch/single_include -I /root/pytorch/build/caffe2/aten/src/ATen -I /root/pytorch/aten/src/ATen/.. -I /root/pytorch/build/caffe2/aten/src/ATen -I /root/pytorch/aten/src -I /root/pytorch/build -I /root/pytorch -I /opt/rocm/miopen/include -I /root/pytorch/build/third_party/gloo -I /root/pytorch/cmake/../third_party/gloo -I /root/pytorch/third_party/protobuf/src -I /root/pytorch/cmake/../third_party/googletest/googletest/include -I /root/pytorch/cmake/../third_party/benchmark/include -I /usr/include -I /root/pytorch/cmake/../third_party/eigen -I /usr/include/python3.6m -I /usr/local/lib/python3.6/dist-packages/numpy/core/include -I /root/pytorch/cmake/../third_party/pybind11/include -I /opt/rocm/hip/include -I /opt/rocm/rocblas/include -I /opt/rocm/rocfft/include -I /opt/rocm/hipsparse/include -I /opt/rocm/hiprand/include -I /opt/rocm/rocrand/include -I /opt/rocm/include -I /root/pytorch/build/caffe2/contrib/aten -I /root/pytorch/third_party/onnx -I /root/pytorch/build/third_party/onnx -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/x86_64-linux-gnu/c++/5.4.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/x86_64-linux-gnu/c++/5.4.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0/backward -internal-isystem /usr/local/include -internal-isystem /opt/rocm/hcc/lib/clang/7.0.0/include -internal-externc-isystem /usr/include/x86_64-linux-gnu -internal-externc-isystem /include -internal-externc-isystem /usr/include -Wno-deprecated-register -Wno-macro-redefined -Wno-inconsistent-missing-override -Wno-exceptions -Wno-shift-count-negative -Wno-shift-count-overflow -Wno-unused-command-line-argument -Wno-duplicate-decl-specifier -std=c++amp -fdeprecated-macro -fno-dwarf-directory-asm -fdebug-compilation-dir /root/pytorch/build/caffe2/CMakeFiles/caffe2_hip.dir/operators/hip -ferror-limit 19 -fmessage-length 0 -fobjc-runtime=gcc -fcxx-exceptions -fexceptions -fdiagnostics-show-option -famp -fhsa-ext -o /tmp/unique_ops_hip-ba853c.s -x hc-kernel /root/pytorch/caffe2/operators/hip/unique_ops_hip.cc -emit-llvm-bc 
 1.	<eof> parser at end of file
 2.	Per-module optimization passes
 3.	Running pass 'Function Pass Manager' on module '/root/pytorch/caffe2/operators/hip/unique_ops_hip.cc'.
 4.	Running pass 'Combine redundant instructions' on function '@_ZN6thrust6system4cuda6detail4cub_28DeviceRadixSortUpsweepKernelINS3_21DeviceRadixSortPolicyIliiE9Policy700ELb0ELb0EliEEvPKT2_PT3_SB_iiNS3_13GridEvenShareISB_EE'
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm3sys15PrintStackTraceERNS_11raw_ostreamE+0x2a)[0x17678fa]
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm3sys17RunSignalHandlersEv+0x4c)[0x1765c2c]
 /opt/rocm/hcc/bin/clang-7[0x1765d97]
 /lib/x86_64-linux-gnu/libpthread.so.0(+0x11390)[0x7f2c56230390]
 /opt/rocm/hcc/bin/clang-7[0x1378daa]
 /opt/rocm/hcc/bin/clang-7[0x1379a08]
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm24InstructionCombiningPass13runOnFunctionERNS_8FunctionE+0x232)[0x137a042]
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm13FPPassManager13runOnFunctionERNS_8FunctionE+0x2ca)[0x125d39a]
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm13FPPassManager11runOnModuleERNS_6ModuleE+0x33)[0x125d463]
 /opt/rocm/hcc/bin/clang-7(_ZN4llvm6legacy15PassManagerImpl3runERNS_6ModuleE+0x32c)[0x125cf0c]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang17EmitBackendOutputERNS_17DiagnosticsEngineERKNS_19HeaderSearchOptionsERKNS_14CodeGenOptionsERKNS_13TargetOptionsERKNS_11LangOptionsERKN4llvm10DataLayoutEPNSE_6ModuleENS_13BackendActionESt10unique_ptrINSE_17raw_pwrite_streamESt14default_deleteISM_EEb+0xc47)[0x195cbb7]
 /opt/rocm/hcc/bin/clang-7[0x2088602]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang8ParseASTERNS_4SemaEbb+0x370)[0x2814310]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang13CodeGenAction13ExecuteActionEv+0x37)[0x2087ba7]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang14FrontendAction7ExecuteEv+0x126)[0x1d5e7c6]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang16CompilerInstance13ExecuteActionERNS_14FrontendActionE+0x146)[0x1d281c6]
 /opt/rocm/hcc/bin/clang-7(_ZN5clang25ExecuteCompilerInvocationEPNS_16CompilerInstanceE+0x96c)[0x1df9c0c]
 /opt/rocm/hcc/bin/clang-7(_Z8cc1_mainN4llvm8ArrayRefIPKcEES2_Pv+0xa18)[0x8f9248]
 /opt/rocm/hcc/bin/clang-7(main+0x17e3)[0x8974c3]
 /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0)[0x7f2c54f8d830]
 /opt/rocm/hcc/bin/clang-7(_start+0x29)[0x8f6a19]
 clang-7: error: unable to execute command: Segmentation fault (core dumped)
 clang-7: error: clang frontend command failed due to signal (use -v to see invocation)
 HCC clang version 7.0.0 (ssh://gerritgit/compute/ec/hcc-tot/clang 37396a09268c7b90c63b91dbd66fe6c3b765bfee) (ssh://gerritgit/compute/ec/hcc-tot/llvm 4144ab076c5720d34d0f36c158ef3b094fe0d339) (based on HCC 1.2.18383-7685003-37396a0-4144ab0 )
 Target: x86_64-unknown-linux-gnu
 Thread model: posix
 InstalledDir: /opt/rocm/hcc/bin
 clang-7: note: diagnostic msg: PLEASE submit a bug report to https://bugs.llvm.org/ and include the crash backtrace, preprocessed source, and associated run script.
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_fp16_momentum_sgd_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_momentum_sgd_op_hip.cc.o
 clang-7: note: diagnostic msg: 
 ********************

 PLEASE ATTACH THE FOLLOWING FILES TO THE BUG REPORT:
 Preprocessed source(s) and associated run script(s) are located at:
 clang-7: note: diagnostic msg: /tmp/unique_ops_hip-b16c04.cpp
 clang-7: note: diagnostic msg: /tmp/unique_ops_hip-efcfe7.cpp
 clang-7: note: diagnostic msg: /tmp/unique_ops_hip-b16c04.sh
 clang-7: note: diagnostic msg: 

 ********************
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_learning_rate_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_adam_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_iter_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_adagrad_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_rmsprop_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_fp32_momentum_sgd_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_yellowfin_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_adadelta_op_hip.cc.o
 [ 83%] Building HIPCC object caffe2/CMakeFiles/caffe2_hip.dir/sgd/hip/caffe2_hip_generated_lars_op_hip.cc.o
 Scanning dependencies of target caffe2_hip
 [ 84%] Linking HIP shared library ../lib/libcaffe2_hip.so
diff --git a/ROCmSoftwarePlatform\PyTorch test output Python3 b/ROCmSoftwarePlatform\PyTorch test output Python3
 Excluding c10d on ROCm
 Excluding cpp_extensions on ROCm
 Excluding distributed on ROCm
 Excluding multiprocessing on ROCm
 Excluding nccl on ROCm
 Excluding thd_distributed on ROCm
 Selected tests: autograd, cuda, cuda_primary_ctx, dataloader, distributions, expecttest, indexing, jit, nn, numba_integration, optim, sparse, torch, type_info, utils
 Running test_autograd ...
 test___getitem__ (__main__.TestAutograd) ... ok
 test___getitem___adv_index (__main__.TestAutograd) ... ok
 test___getitem___adv_index_beg (__main__.TestAutograd) ... ok
 test___getitem___adv_index_comb (__main__.TestAutograd) ... ok
 test___getitem___adv_index_dup (__main__.TestAutograd) ... ok
 test___getitem___adv_index_end (__main__.TestAutograd) ... ok
 test___getitem___adv_index_mid (__main__.TestAutograd) ... ok
 test___getitem___adv_index_sub (__main__.TestAutograd) ... ok
 test___getitem___adv_index_sub_2 (__main__.TestAutograd) ... ok
 test___getitem___adv_index_sub_3 (__main__.TestAutograd) ... ok
 test___getitem___adv_index_var (__main__.TestAutograd) ... ok
 test___getitem___slice (__main__.TestAutograd) ... ok
 test___getitem___slice_index (__main__.TestAutograd) ... ok
 test___radd___constant (__main__.TestAutograd) ... ok
 test___radd___scalar_constant (__main__.TestAutograd) ... ok
 test___rdiv___constant (__main__.TestAutograd) ... ok
 test___rdiv___scalar_constant (__main__.TestAutograd) ... ok
 test___rmul___constant (__main__.TestAutograd) ... ok
 test___rmul___scalar_constant (__main__.TestAutograd) ... ok
 test___rpow___constant (__main__.TestAutograd) ... ok
 test___rpow___scalar_constant (__main__.TestAutograd) ... ok
 test___rsub___constant (__main__.TestAutograd) ... ok
 test___rsub___scalar_constant (__main__.TestAutograd) ... ok
 test_abs (__main__.TestAutograd) ... ok
 test_abs_scalar (__main__.TestAutograd) ... ok
 test_accumulate_grad (__main__.TestAutograd) ... ok
 test_acos (__main__.TestAutograd) ... ok
 test_add (__main__.TestAutograd) ... ok
 test_add_broadcast_all (__main__.TestAutograd) ... ok
 test_add_broadcast_lhs (__main__.TestAutograd) ... ok
 test_add_broadcast_rhs (__main__.TestAutograd) ... ok
 test_add_constant (__main__.TestAutograd) ... ok
 test_add_scalar (__main__.TestAutograd) ... ok
 test_add_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_add_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_add_scalar_constant (__main__.TestAutograd) ... ok
 test_addbmm (__main__.TestAutograd) ... ok
 test_addbmm_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addbmm_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addbmm_coef (__main__.TestAutograd) ... ok
 test_addbmm_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addbmm_scalar_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addcdiv (__main__.TestAutograd) ... ok
 test_addcdiv_broadcast_all (__main__.TestAutograd) ... ok
 test_addcdiv_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcdiv_scalar (__main__.TestAutograd) ... ok
 test_addcdiv_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addcdiv_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcdiv_scalar_scale (__main__.TestAutograd) ... ok
 test_addcdiv_scalar_scale_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addcdiv_scalar_scale_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcdiv_scale (__main__.TestAutograd) ... ok
 test_addcdiv_scale_broadcast_all (__main__.TestAutograd) ... ok
 test_addcdiv_scale_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcmul (__main__.TestAutograd) ... ok
 test_addcmul_broadcast_all (__main__.TestAutograd) ... ok
 test_addcmul_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcmul_scalar (__main__.TestAutograd) ... ok
 test_addcmul_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addcmul_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcmul_scalar_scale (__main__.TestAutograd) ... ok
 test_addcmul_scalar_scale_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addcmul_scalar_scale_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addcmul_scale (__main__.TestAutograd) ... ok
 test_addcmul_scale_broadcast_all (__main__.TestAutograd) ... ok
 test_addcmul_scale_broadcast_rhs (__main__.TestAutograd) ... ok
 test_addmm (__main__.TestAutograd) ... ok
 test_addmm_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addmm_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addmm_coef (__main__.TestAutograd) ... ok
 test_addmm_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addmm_scalar_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addmv (__main__.TestAutograd) ... ok
 test_addmv_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addmv_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addmv_coef (__main__.TestAutograd) ... ok
 test_addmv_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addmv_scalar_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addr (__main__.TestAutograd) ... ok
 test_addr_broadcast_lhs (__main__.TestAutograd) ... ok
 test_addr_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_addr_coef (__main__.TestAutograd) ... ok
 test_anomaly_detect_nan (__main__.TestAutograd) ... ok
 test_as_strided (__main__.TestAutograd) ... ok
 test_asin (__main__.TestAutograd) ... ok
 test_atan (__main__.TestAutograd) ... ok
 test_atan2 (__main__.TestAutograd) ... ok
 test_atan2_scalar (__main__.TestAutograd) ... ok
 test_atan_scalar (__main__.TestAutograd) ... ok
 test_backward (__main__.TestAutograd) ... ok
 test_backward_badcalls (__main__.TestAutograd) ... ok
 test_backward_copy (__main__.TestAutograd) ... ok
 test_backward_device (__main__.TestAutograd) ... skipped 'no multi-GPU'
 test_backward_no_grad (__main__.TestAutograd) ... ok
 test_baddbmm (__main__.TestAutograd) ... ok
 test_baddbmm_broadcast_lhs (__main__.TestAutograd) ... ok
 test_baddbmm_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_baddbmm_coef (__main__.TestAutograd) ... ok
 test_baddbmm_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_baddbmm_scalar_broadcast_lhs_coef (__main__.TestAutograd) ... ok
 test_bmm (__main__.TestAutograd) ... ok
 test_broadcast_tensors (__main__.TestAutograd) ... ok
 test_cat (__main__.TestAutograd) ... ok
 test_cat_empty (__main__.TestAutograd) ... ok
 test_cat_empty_legacy (__main__.TestAutograd) ... ok
 test_cat_negdim_1 (__main__.TestAutograd) ... ok
 test_cat_negdim_2 (__main__.TestAutograd) ... ok
 test_ceil (__main__.TestAutograd) ... ok
 test_ceil_scalar (__main__.TestAutograd) ... ok
 test_chain_matmul (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_chunk (__main__.TestAutograd) ... ok
 test_chunk_dim (__main__.TestAutograd) ... ok
 test_chunk_dim_neg0 (__main__.TestAutograd) ... ok
 test_clamp (__main__.TestAutograd) ... ok
 test_clamp_max (__main__.TestAutograd) ... ok
 test_clamp_max_scalar (__main__.TestAutograd) ... ok
 test_clamp_min (__main__.TestAutograd) ... ok
 test_clamp_min_scalar (__main__.TestAutograd) ... ok
 test_clamp_scalar (__main__.TestAutograd) ... ok
 test_clone (__main__.TestAutograd) ... ok
 test_clone_scalar (__main__.TestAutograd) ... ok
 test_cos (__main__.TestAutograd) ... ok
 test_cos_scalar (__main__.TestAutograd) ... ok
 test_cosh (__main__.TestAutograd) ... ok
 test_cosh_scalar (__main__.TestAutograd) ... ok
 test_cross (__main__.TestAutograd) ... ok
 test_cross_dim (__main__.TestAutograd) ... ok
 test_ctc_loss (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_cumprod (__main__.TestAutograd) ... ok
 test_cumprod_dim1 (__main__.TestAutograd) ... ok
 test_cumprod_dim1_neg0 (__main__.TestAutograd) ... ok
 test_cumprod_scalar (__main__.TestAutograd) ... ok
 test_cumprod_scalar_zeros (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim0 (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim0_neg0 (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim1 (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim1_neg0 (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim2 (__main__.TestAutograd) ... ok
 test_cumprod_zeros_dim2_neg0 (__main__.TestAutograd) ... ok
 test_cumsum_dim0 (__main__.TestAutograd) ... ok
 test_cumsum_dim0_neg0 (__main__.TestAutograd) ... ok
 test_cumsum_dim0_scalar (__main__.TestAutograd) ... ok
 test_cumsum_dim0_scalar_neg0 (__main__.TestAutograd) ... ok
 test_cumsum_dim1 (__main__.TestAutograd) ... ok
 test_cumsum_dim1_neg0 (__main__.TestAutograd) ... ok
 test_dep_nograd (__main__.TestAutograd) ... ok
 test_dependent_backward (__main__.TestAutograd) ... ok
 test_det (__main__.TestAutograd) ... ok
 test_det_1x1 (__main__.TestAutograd) ... ok
 test_det_dim2_null (__main__.TestAutograd) ... ok
 test_det_distinct_singular_values (__main__.TestAutograd) ... ok
 test_det_rank1 (__main__.TestAutograd) ... ok
 test_det_rank2 (__main__.TestAutograd) ... ok
 test_det_symmetric (__main__.TestAutograd) ... ok
 test_det_symmetric_pd (__main__.TestAutograd) ... ok
 test_det_symmetric_psd (__main__.TestAutograd) ... ok
 test_detach (__main__.TestAutograd) ... ok
 test_detach_base (__main__.TestAutograd)
 detaching base does not detach view ... ok
 test_diag_1d (__main__.TestAutograd) ... ok
 test_diag_2d (__main__.TestAutograd) ... ok
 test_diag_2d_1 (__main__.TestAutograd) ... ok
 test_diag_2d_2 (__main__.TestAutograd) ... ok
 test_diag_2d_tall (__main__.TestAutograd) ... ok
 test_diag_2d_tall_neg (__main__.TestAutograd) ... ok
 test_diag_2d_tall_pos (__main__.TestAutograd) ... ok
 test_diag_2d_wide (__main__.TestAutograd) ... ok
 test_diag_2d_wide_neg (__main__.TestAutograd) ... ok
 test_diag_2d_wide_pos (__main__.TestAutograd) ... ok
 test_diagonal_2d (__main__.TestAutograd) ... ok
 test_diagonal_2d_1 (__main__.TestAutograd) ... ok
 test_diagonal_2d_2 (__main__.TestAutograd) ... ok
 test_diagonal_2d_tall (__main__.TestAutograd) ... ok
 test_diagonal_2d_tall_neg (__main__.TestAutograd) ... ok
 test_diagonal_2d_tall_pos (__main__.TestAutograd) ... ok
 test_diagonal_2d_wide (__main__.TestAutograd) ... ok
 test_diagonal_2d_wide_neg (__main__.TestAutograd) ... ok
 test_diagonal_2d_wide_pos (__main__.TestAutograd) ... ok
 test_diagonal_3d_1 (__main__.TestAutograd) ... ok
 test_diagonal_3d_2 (__main__.TestAutograd) ... ok
 test_diagonal_3d_3 (__main__.TestAutograd) ... ok
 test_diagonal_derivative_requires_grad (__main__.TestAutograd) ... ok
 test_dir (__main__.TestAutograd) ... ok
 test_dist (__main__.TestAutograd) ... ok
 test_dist_4 (__main__.TestAutograd) ... ok
 test_dist_4_broadcast_all (__main__.TestAutograd) ... ok
 test_dist_4_broadcast_lhs (__main__.TestAutograd) ... ok
 test_dist_4_broadcast_rhs (__main__.TestAutograd) ... ok
 test_dist_broadcast_all (__main__.TestAutograd) ... ok
 test_dist_broadcast_lhs (__main__.TestAutograd) ... ok
 test_dist_broadcast_rhs (__main__.TestAutograd) ... ok
 test_dist_scalar (__main__.TestAutograd) ... ok
 test_dist_scalar_4 (__main__.TestAutograd) ... ok
 test_dist_scalar_4_broadcast_lhs (__main__.TestAutograd) ... ok
 test_dist_scalar_4_broadcast_rhs (__main__.TestAutograd) ... ok
 test_dist_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_dist_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_div (__main__.TestAutograd) ... ok
 test_div_broadcast_all (__main__.TestAutograd) ... ok
 test_div_broadcast_lhs (__main__.TestAutograd) ... ok
 test_div_broadcast_rhs (__main__.TestAutograd) ... ok
 test_div_constant (__main__.TestAutograd) ... ok
 test_div_scalar (__main__.TestAutograd) ... ok
 test_div_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_div_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_div_scalar_constant (__main__.TestAutograd) ... ok
 test_dot (__main__.TestAutograd) ... ok
 test_duplicate_backward_root (__main__.TestAutograd) ... ok
 test_eq_ (__main__.TestAutograd) ... ok
 test_eq__broadcast_rhs (__main__.TestAutograd) ... ok
 test_eq__pyscalar (__main__.TestAutograd) ... ok
 test_eq__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_eq__scalar (__main__.TestAutograd) ... ok
 test_eq__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_erf (__main__.TestAutograd) ... ok
 test_erf_scalar (__main__.TestAutograd) ... ok
 test_erfc (__main__.TestAutograd) ... ok
 test_erfc_scalar (__main__.TestAutograd) ... ok
 test_erfinv (__main__.TestAutograd) ... ok
 test_erfinv_scalar (__main__.TestAutograd) ... ok
 test_exp (__main__.TestAutograd) ... ok
 test_exp_scalar (__main__.TestAutograd) ... ok
 test_expand (__main__.TestAutograd) ... ok
 test_expand_1_element (__main__.TestAutograd) ... ok
 test_expand_new_dim (__main__.TestAutograd) ... ok
 test_expand_new_dim_front_old_front_1 (__main__.TestAutograd) ... ok
 test_expand_scalar_to_dims (__main__.TestAutograd) ... ok
 test_expand_scalar_to_scalar (__main__.TestAutograd) ... ok
 test_expand_size (__main__.TestAutograd) ... ok
 test_expm1 (__main__.TestAutograd) ... ok
 test_expm1_scalar (__main__.TestAutograd) ... ok
 test_fft_ifft_rfft_irfft (__main__.TestAutograd) ... skipped 'PyTorch is built without MKL support'
 test_fill (__main__.TestAutograd) ... ok
 test_fill__number (__main__.TestAutograd) ... ok
 test_fill__number_scalar (__main__.TestAutograd) ... ok
 test_fill__variable (__main__.TestAutograd) ... ok
 test_flip_d0 (__main__.TestAutograd) ... ok
 test_flip_d012 (__main__.TestAutograd) ... ok
 test_flip_d02 (__main__.TestAutograd) ... ok
 test_flip_d20 (__main__.TestAutograd) ... ok
 test_flip_neg_d (__main__.TestAutograd) ... ok
 test_floor (__main__.TestAutograd) ... ok
 test_floor_scalar (__main__.TestAutograd) ... ok
 test_fmod (__main__.TestAutograd) ... ok
 test_fmod_scalar (__main__.TestAutograd) ... ok
 test_fmod_scalar_tensor (__main__.TestAutograd) ... ok
 test_fmod_scalar_tensor_broadcast_lhs (__main__.TestAutograd) ... ok
 test_fmod_scalar_tensor_broadcast_rhs (__main__.TestAutograd) ... ok
 test_fmod_tensor (__main__.TestAutograd) ... ok
 test_fmod_tensor_broadcast_all (__main__.TestAutograd) ... ok
 test_fmod_tensor_broadcast_lhs (__main__.TestAutograd) ... ok
 test_fmod_tensor_broadcast_rhs (__main__.TestAutograd) ... ok
 test_frac (__main__.TestAutograd) ... ok
 test_frac_scalar (__main__.TestAutograd) ... ok
 test_free_deep_graph (__main__.TestAutograd) ... ok
 test_free_deep_graph_complicated (__main__.TestAutograd) ... ok
 test_free_deep_graph_pyfunction (__main__.TestAutograd) ... ok
 test_function (__main__.TestAutograd) ... ok
 test_function_returns_input (__main__.TestAutograd) ... ok
 test_gather_dim0 (__main__.TestAutograd) ... ok
 test_gather_dim0_neg0 (__main__.TestAutograd) ... ok
 test_gather_dim1 (__main__.TestAutograd) ... ok
 test_gather_dim1_neg0 (__main__.TestAutograd) ... ok
 test_gather_scalar_both (__main__.TestAutograd) ... ok
 test_gather_scalar_both_neg0 (__main__.TestAutograd) ... ok
 test_gather_scalar_index (__main__.TestAutograd) ... ok
 test_gather_scalar_index_neg0 (__main__.TestAutograd) ... ok
 test_gather_scalar_input (__main__.TestAutograd) ... ok
 test_gather_scalar_input_neg0 (__main__.TestAutograd) ... ok
 test_gc_in_destructor (__main__.TestAutograd) ... ok
 test_ge_ (__main__.TestAutograd) ... ok
 test_ge__broadcast_rhs (__main__.TestAutograd) ... ok
 test_ge__pyscalar (__main__.TestAutograd) ... ok
 test_ge__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_ge__scalar (__main__.TestAutograd) ... ok
 test_ge__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_ger (__main__.TestAutograd) ... ok
 test_gesv (__main__.TestAutograd) ... ok
 test_gesv_batched (__main__.TestAutograd) ... ok
 test_gesv_batched_broadcast_A (__main__.TestAutograd) ... ok
 test_gesv_batched_broadcast_b (__main__.TestAutograd) ... ok
 test_gesv_batched_dims (__main__.TestAutograd) ... ok
 test_grad (__main__.TestAutograd) ... ok
 test_grad_assignment (__main__.TestAutograd) ... skipped 'At least 2 CUDA devices needed'
 test_grad_badcalls (__main__.TestAutograd) ... ok
 test_grad_fn_badcalls (__main__.TestAutograd) ... ok
 test_grad_nonleaf (__main__.TestAutograd) ... ok
 test_grad_nonleaf_many_outputs (__main__.TestAutograd) ... ok
 test_grad_nonleaf_register_hook (__main__.TestAutograd) ... ok
 test_grad_unreachable (__main__.TestAutograd) ... ok
 test_gt_ (__main__.TestAutograd) ... ok
 test_gt__broadcast_rhs (__main__.TestAutograd) ... ok
 test_gt__pyscalar (__main__.TestAutograd) ... ok
 test_gt__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_gt__scalar (__main__.TestAutograd) ... ok
 test_gt__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_hessian_vector (__main__.TestAutograd) ... ok
 test_hook_none (__main__.TestAutograd) ... ok
 test_hooks (__main__.TestAutograd) ... ok
 test_hooks_cpp (__main__.TestAutograd) ... ok
 test_index_add_dim (__main__.TestAutograd) ... ok
 test_index_add_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_add_scalar_all_dim (__main__.TestAutograd) ... ok
 test_index_add_scalar_all_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_add_scalar_input_dim (__main__.TestAutograd) ... ok
 test_index_add_scalar_input_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_copy_dim (__main__.TestAutograd) ... ok
 test_index_copy_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_copy_scalar_all_dim (__main__.TestAutograd) ... ok
 test_index_copy_scalar_all_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_copy_scalar_input_dim (__main__.TestAutograd) ... ok
 test_index_copy_scalar_input_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_fill_dim (__main__.TestAutograd) ... ok
 test_index_fill_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_fill_scalar_both_dim (__main__.TestAutograd) ... ok
 test_index_fill_scalar_both_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_fill_scalar_index_dim (__main__.TestAutograd) ... ok
 test_index_fill_scalar_index_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_fill_scalar_input_dim (__main__.TestAutograd) ... ok
 test_index_fill_scalar_input_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_fill_variable_dim (__main__.TestAutograd) ... ok
 test_index_fill_variable_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_select_dim (__main__.TestAutograd) ... ok
 test_index_select_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_select_scalar_dim (__main__.TestAutograd) ... ok
 test_index_select_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_index_select_scalar_mixed_dim (__main__.TestAutograd) ... ok
 test_index_select_scalar_mixed_dim_neg0 (__main__.TestAutograd) ... ok
 test_indexing (__main__.TestAutograd) ... ok
 test_indexing_duplicates (__main__.TestAutograd) ... ok
 test_inplace (__main__.TestAutograd) ... ok
 test_inplace_view_backprop_base (__main__.TestAutograd) ... ok
 test_inplace_view_backprop_view (__main__.TestAutograd) ... ok
 test_inplace_view_backprop_view_of_view (__main__.TestAutograd) ... ok
 test_inplace_view_gradcheck (__main__.TestAutograd) ... ok
 test_inplace_view_makes_base_require_grad (__main__.TestAutograd) ... ok
 test_inplace_view_modify_base (__main__.TestAutograd) ... ok
 test_inplace_view_non_contig (__main__.TestAutograd) ... ok
 test_inplace_view_of_view (__main__.TestAutograd) ... ok
 test_inplace_view_python (__main__.TestAutograd) ... ok
 test_inplace_view_saved_output (__main__.TestAutograd) ... ok
 test_inputbuffer_add_multigpu (__main__.TestAutograd) ... skipped 'no multi-GPU'
 test_invalid_gradients (__main__.TestAutograd) ... ok
 test_inverse (__main__.TestAutograd) ... ok
 test_isolated_node (__main__.TestAutograd) ... ok
 test_kthvalue (__main__.TestAutograd) ... ok
 test_kthvalue_dim (__main__.TestAutograd) ... ok
 test_kthvalue_dim_1d (__main__.TestAutograd) ... ok
 test_kthvalue_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_kthvalue_dim_neg0 (__main__.TestAutograd) ... ok
 test_kthvalue_keepdim_dim (__main__.TestAutograd) ... ok
 test_kthvalue_keepdim_dim_1d (__main__.TestAutograd) ... ok
 test_kthvalue_keepdim_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_kthvalue_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_kthvalue_scalar (__main__.TestAutograd) ... ok
 test_kthvalue_scalar_dim (__main__.TestAutograd) ... ok
 test_kthvalue_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_kthvalue_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_kthvalue_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_le_ (__main__.TestAutograd) ... ok
 test_le__broadcast_rhs (__main__.TestAutograd) ... ok
 test_le__pyscalar (__main__.TestAutograd) ... ok
 test_le__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_le__scalar (__main__.TestAutograd) ... ok
 test_le__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_leaf_assignment (__main__.TestAutograd) ... ok
 test_legacy_function_none_grad (__main__.TestAutograd) ... ok
 test_lerp (__main__.TestAutograd) ... ok
 test_lerp_broadcast_all (__main__.TestAutograd) ... ok
 test_lerp_broadcast_lhs (__main__.TestAutograd) ... ok
 test_lerp_broadcast_rhs (__main__.TestAutograd) ... ok
 test_lerp_scalar (__main__.TestAutograd) ... ok
 test_lerp_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_lerp_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_log (__main__.TestAutograd) ... ok
 test_log10 (__main__.TestAutograd) ... ok
 test_log10_scalar (__main__.TestAutograd) ... ok
 test_log1p (__main__.TestAutograd) ... ok
 test_log1p_scalar (__main__.TestAutograd) ... ok
 test_log2 (__main__.TestAutograd) ... ok
 test_log2_scalar (__main__.TestAutograd) ... ok
 test_log_scalar (__main__.TestAutograd) ... ok
 test_logdet (__main__.TestAutograd) ... ok
 test_logdet_1x1 (__main__.TestAutograd) ... ok
 test_logdet_distinct_singular_values (__main__.TestAutograd) ... ok
 test_logdet_symmetric (__main__.TestAutograd) ... ok
 test_logdet_symmetric_pd (__main__.TestAutograd) ... ok
 test_logsumexp (__main__.TestAutograd) ... ok
 test_logsumexp_scalar (__main__.TestAutograd) ... ok
 test_lstmcell_backward_only_one_output_grad (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_lt_ (__main__.TestAutograd) ... ok
 test_lt__broadcast_rhs (__main__.TestAutograd) ... ok
 test_lt__pyscalar (__main__.TestAutograd) ... ok
 test_lt__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_lt__scalar (__main__.TestAutograd) ... ok
 test_lt__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_mark_non_differentiable (__main__.TestAutograd) ... ok
 test_mark_non_differentiable_mixed (__main__.TestAutograd) ... ok
 test_mark_non_differentiable_none (__main__.TestAutograd) ... ok
 test_masked_fill (__main__.TestAutograd) ... ok
 test_masked_fill_broadcast_rhs (__main__.TestAutograd) ... ok
 test_masked_fill_scalar (__main__.TestAutograd) ... ok
 test_masked_fill_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_masked_fill_scalar_variable (__main__.TestAutograd) ... ok
 test_masked_fill_tensor (__main__.TestAutograd) ... ok
 test_masked_scatter (__main__.TestAutograd) ... ok
 test_masked_scatter_broadcast_rhs (__main__.TestAutograd) ... ok
 test_masked_scatter_scalar (__main__.TestAutograd) ... ok
 test_masked_scatter_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_masked_select (__main__.TestAutograd) ... ok
 test_masked_select_broadcast_all (__main__.TestAutograd) ... ok
 test_masked_select_broadcast_lhs (__main__.TestAutograd) ... ok
 test_masked_select_broadcast_rhs (__main__.TestAutograd) ... ok
 test_masked_select_scalar (__main__.TestAutograd) ... ok
 test_masked_select_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_masked_select_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_matmul (__main__.TestAutograd) ... ok
 test_matmul_1d_2d (__main__.TestAutograd) ... ok
 test_matmul_1d_4d (__main__.TestAutograd) ... ok
 test_matmul_2d_1d (__main__.TestAutograd) ... ok
 test_matmul_2d_2d (__main__.TestAutograd) ... ok
 test_matmul_4d_1d (__main__.TestAutograd) ... ok
 test_matmul_4d_4d (__main__.TestAutograd) ... ok
 test_matrix_power_n=-1 (__main__.TestAutograd) ... ok
 test_matrix_power_n=-3 (__main__.TestAutograd) ... ok
 test_matrix_power_n=0 (__main__.TestAutograd) ... ok
 test_matrix_power_n=1 (__main__.TestAutograd) ... ok
 test_matrix_power_n=2 (__main__.TestAutograd) ... ok
 test_matrix_power_n=3 (__main__.TestAutograd) ... ok
 test_max (__main__.TestAutograd) ... ok
 test_max_dim (__main__.TestAutograd) ... ok
 test_max_dim_neg0 (__main__.TestAutograd) ... ok
 test_max_elementwise (__main__.TestAutograd) ... ok
 test_max_elementwise_broadcast_all (__main__.TestAutograd) ... ok
 test_max_elementwise_broadcast_lhs (__main__.TestAutograd) ... ok
 test_max_elementwise_broadcast_rhs (__main__.TestAutograd) ... ok
 test_max_keepdim_dim (__main__.TestAutograd) ... ok
 test_max_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_max_scalar (__main__.TestAutograd) ... ok
 test_max_scalar_dim (__main__.TestAutograd) ... ok
 test_max_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_max_scalar_elementwise (__main__.TestAutograd) ... ok
 test_max_scalar_elementwise_broadcast_lhs (__main__.TestAutograd) ... ok
 test_max_scalar_elementwise_broadcast_rhs (__main__.TestAutograd) ... ok
 test_max_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_max_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_mean (__main__.TestAutograd) ... ok
 test_mean_dim (__main__.TestAutograd) ... ok
 test_mean_dim_neg0 (__main__.TestAutograd) ... ok
 test_mean_keepdim_dim (__main__.TestAutograd) ... ok
 test_mean_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_mean_scalar (__main__.TestAutograd) ... ok
 test_mean_scalar_dim (__main__.TestAutograd) ... ok
 test_mean_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_mean_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_mean_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_median (__main__.TestAutograd) ... ok
 test_median_dim (__main__.TestAutograd) ... ok
 test_median_dim_neg0 (__main__.TestAutograd) ... ok
 test_median_keepdim_dim (__main__.TestAutograd) ... ok
 test_median_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_median_scalar (__main__.TestAutograd) ... ok
 test_median_scalar_dim (__main__.TestAutograd) ... ok
 test_median_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_median_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_median_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_min (__main__.TestAutograd) ... ok
 test_min_dim (__main__.TestAutograd) ... ok
 test_min_dim_neg0 (__main__.TestAutograd) ... ok
 test_min_elementwise (__main__.TestAutograd) ... ok
 test_min_elementwise_broadcast_all (__main__.TestAutograd) ... ok
 test_min_elementwise_broadcast_lhs (__main__.TestAutograd) ... ok
 test_min_elementwise_broadcast_rhs (__main__.TestAutograd) ... ok
 test_min_keepdim_dim (__main__.TestAutograd) ... ok
 test_min_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_min_scalar (__main__.TestAutograd) ... ok
 test_min_scalar_dim (__main__.TestAutograd) ... ok
 test_min_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_min_scalar_elementwise (__main__.TestAutograd) ... ok
 test_min_scalar_elementwise_broadcast_lhs (__main__.TestAutograd) ... ok
 test_min_scalar_elementwise_broadcast_rhs (__main__.TestAutograd) ... ok
 test_min_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_min_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_mm (__main__.TestAutograd) ... ok
 test_mode (__main__.TestAutograd) ... ok
 test_mode_dim (__main__.TestAutograd) ... ok
 test_mode_dim_neg0 (__main__.TestAutograd) ... ok
 test_mode_keepdim_dim (__main__.TestAutograd) ... ok
 test_mode_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_mode_scalar (__main__.TestAutograd) ... ok
 test_mode_scalar_dim (__main__.TestAutograd) ... ok
 test_mode_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_mode_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_mode_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_mul (__main__.TestAutograd) ... ok
 test_mul_broadcast_all (__main__.TestAutograd) ... ok
 test_mul_broadcast_lhs (__main__.TestAutograd) ... ok
 test_mul_broadcast_rhs (__main__.TestAutograd) ... ok
 test_mul_constant (__main__.TestAutograd) ... ok
 test_mul_out (__main__.TestAutograd) ... ok
 test_mul_out_result_requires_grad (__main__.TestAutograd) ... ok
 test_mul_scalar (__main__.TestAutograd) ... ok
 test_mul_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_mul_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_mul_scalar_constant (__main__.TestAutograd) ... ok
 test_multi_backward (__main__.TestAutograd) ... ok
 test_multi_backward_no_grad (__main__.TestAutograd) ... ok
 test_mv (__main__.TestAutograd) ... ok
 test_narrow_dim (__main__.TestAutograd) ... ok
 test_narrow_dim_neg0 (__main__.TestAutograd) ... ok
 test_narrow_empty_dim (__main__.TestAutograd) ... ok
 test_narrow_empty_dim_neg0 (__main__.TestAutograd) ... ok
 test_ne_ (__main__.TestAutograd) ... ok
 test_ne__broadcast_rhs (__main__.TestAutograd) ... ok
 test_ne__pyscalar (__main__.TestAutograd) ... ok
 test_ne__pyscalar_scalar (__main__.TestAutograd) ... ok
 test_ne__scalar (__main__.TestAutograd) ... ok
 test_ne__scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_next_functions (__main__.TestAutograd) ... ok
 test_no_grad (__main__.TestAutograd) ... ok
 test_no_grad_assignment (__main__.TestAutograd) ... ok
 test_no_grad_copy (__main__.TestAutograd) ... ok
 test_no_grad_input (__main__.TestAutograd) ... ok
 test_no_grad_modifies_version (__main__.TestAutograd) ... ok
 test_no_grad_python_function (__main__.TestAutograd)
 Python Functions should respect grad mode. ... ok
 test_no_requires_grad_inplace (__main__.TestAutograd) ... ok
 test_norm_-inf (__main__.TestAutograd) ... ok
 test_norm_0 (__main__.TestAutograd) ... ok
 test_norm_0_2_dim (__main__.TestAutograd) ... ok
 test_norm_0_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_0_5 (__main__.TestAutograd) ... ok
 test_norm_1 (__main__.TestAutograd) ... ok
 test_norm_1_2_dim (__main__.TestAutograd) ... ok
 test_norm_1_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_1_5_default (__main__.TestAutograd) ... ok
 test_norm_1_5_dim (__main__.TestAutograd) ... ok
 test_norm_1_5_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_2 (__main__.TestAutograd) ... ok
 test_norm_2_2_dim (__main__.TestAutograd) ... ok
 test_norm_2_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_2_dim (__main__.TestAutograd) ... ok
 test_norm_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_2_dim_scalar (__main__.TestAutograd) ... ok
 test_norm_2_dim_scalar_neg0 (__main__.TestAutograd) ... ok
 test_norm_3 (__main__.TestAutograd) ... ok
 test_norm_3_2_dim (__main__.TestAutograd) ... ok
 test_norm_3_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_3_dim (__main__.TestAutograd) ... ok
 test_norm_3_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_3_dim_scalar (__main__.TestAutograd) ... ok
 test_norm_3_dim_scalar_neg0 (__main__.TestAutograd) ... ok
 test_norm_default (__main__.TestAutograd) ... ok
 test_norm_fro (__main__.TestAutograd) ... ok
 test_norm_fro_default (__main__.TestAutograd) ... ok
 test_norm_inf (__main__.TestAutograd) ... ok
 test_norm_inf_2_dim (__main__.TestAutograd) ... ok
 test_norm_keepdim_1_5_dim (__main__.TestAutograd) ... ok
 test_norm_keepdim_1_5_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_keepdim_2_dim (__main__.TestAutograd) ... ok
 test_norm_keepdim_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_keepdim_2_dim_scalar (__main__.TestAutograd) ... ok
 test_norm_keepdim_2_dim_scalar_neg0 (__main__.TestAutograd) ... ok
 test_norm_keepdim_3_dim (__main__.TestAutograd) ... ok
 test_norm_keepdim_3_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_keepdim_3_dim_scalar (__main__.TestAutograd) ... ok
 test_norm_keepdim_3_dim_scalar_neg0 (__main__.TestAutograd) ... ok
 test_norm_neg_0_5 (__main__.TestAutograd) ... ok
 test_norm_neg_1 (__main__.TestAutograd) ... ok
 test_norm_neg_1_2_dim (__main__.TestAutograd) ... ok
 test_norm_neg_1_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_neg_1_5 (__main__.TestAutograd) ... ok
 test_norm_neg_2 (__main__.TestAutograd) ... ok
 test_norm_neg_2_2_dim (__main__.TestAutograd) ... ok
 test_norm_neg_2_2_dim_neg0 (__main__.TestAutograd) ... ok
 test_norm_nuc (__main__.TestAutograd) ... ok
 test_norm_subgradient (__main__.TestAutograd) ... ok
 test_numpy_requires_grad (__main__.TestAutograd) ... ok
 test_once_differentiable (__main__.TestAutograd) ... ok
 test_permute (__main__.TestAutograd) ... ok
 test_permute_neg_dim (__main__.TestAutograd) ... ok
 test_permute_scalar (__main__.TestAutograd) ... ok
 test_pickle (__main__.TestAutograd) ... ok
 test_pin_memory (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_pinverse (__main__.TestAutograd) ... ok
 test_potrf (__main__.TestAutograd) ... ok
 test_pow (__main__.TestAutograd) ... ok
 test_pow_broadcast_all (__main__.TestAutograd) ... ok
 test_pow_broadcast_lhs (__main__.TestAutograd) ... ok
 test_pow_broadcast_rhs (__main__.TestAutograd) ... ok
 test_pow_constant (__main__.TestAutograd) ... ok
 test_pow_scalar (__main__.TestAutograd) ... ok
 test_pow_scalar_base (__main__.TestAutograd) ... ok
 test_pow_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_pow_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_pow_scalar_constant (__main__.TestAutograd) ... ok
 test_pow_zero_tensor_gradient (__main__.TestAutograd) ... ok
 test_prod (__main__.TestAutograd) ... ok
 test_prod_dim (__main__.TestAutograd) ... ok
 test_prod_dim_neg0 (__main__.TestAutograd) ... ok
 test_prod_keepdim_dim (__main__.TestAutograd) ... ok
 test_prod_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims0 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims0_neg0 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims1 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims1_neg0 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims2 (__main__.TestAutograd) ... ok
 test_prod_keepdim_zeros_dims2_neg0 (__main__.TestAutograd) ... ok
 test_prod_scalar (__main__.TestAutograd) ... ok
 test_prod_scalar_dim (__main__.TestAutograd) ... ok
 test_prod_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_prod_scalar_dim_zero (__main__.TestAutograd) ... ok
 test_prod_scalar_dim_zero_neg0 (__main__.TestAutograd) ... ok
 test_prod_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_prod_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_prod_scalar_keepdim_dim_zero (__main__.TestAutograd) ... ok
 test_prod_scalar_keepdim_dim_zero_neg0 (__main__.TestAutograd) ... ok
 test_prod_scalar_zero (__main__.TestAutograd) ... ok
 test_prod_single_zero (__main__.TestAutograd) ... ok
 test_prod_zerodims0 (__main__.TestAutograd) ... ok
 test_prod_zerodims1 (__main__.TestAutograd) ... ok
 test_prod_zerodims2 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims0 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims0_neg0 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims1 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims1_neg0 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims2 (__main__.TestAutograd) ... ok
 test_prod_zeros_dims2_neg0 (__main__.TestAutograd) ... ok
 test_profiler (__main__.TestAutograd) ... ok
 test_put (__main__.TestAutograd) ... ok
 test_put_accumulate (__main__.TestAutograd) ... ok
 test_pyscalar_conversions (__main__.TestAutograd) ... ok
 test_reciprocal (__main__.TestAutograd) ... ok
 test_reciprocal_scalar (__main__.TestAutograd) ... ok
 test_reentrant (__main__.TestAutograd) ... ok
 test_remainder (__main__.TestAutograd) ... ok
 test_remainder_scalar (__main__.TestAutograd) ... ok
 test_remainder_scalar_tensor (__main__.TestAutograd) ... ok
 test_remainder_scalar_tensor_broadcast_lhs (__main__.TestAutograd) ... ok
 test_remainder_tensor (__main__.TestAutograd) ... ok
 test_remainder_tensor_broadcast_all (__main__.TestAutograd) ... ok
 test_remainder_tensor_broadcast_lhs (__main__.TestAutograd) ... ok
 test_renorm_dim (__main__.TestAutograd) ... ok
 test_renorm_dim_neg0 (__main__.TestAutograd) ... ok
 test_renorm_norm_1 (__main__.TestAutograd) ... ok
 test_renorm_norm_inf (__main__.TestAutograd) ... ok
 test_repeat (__main__.TestAutograd) ... ok
 test_repeat_scalar (__main__.TestAutograd) ... ok
 test_repeat_single_number (__main__.TestAutograd) ... ok
 test_repeat_unsqueeze (__main__.TestAutograd) ... ok
 test_requires_grad (__main__.TestAutograd) ... ok
 test_requires_grad_ (__main__.TestAutograd) ... ok
 test_requires_grad_factory (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_requires_grad_inplace (__main__.TestAutograd) ... ok
 test_reshape (__main__.TestAutograd) ... ok
 test_reshape_1d (__main__.TestAutograd) ... ok
 test_reshape_as (__main__.TestAutograd) ... ok
 test_reshape_as_scalar (__main__.TestAutograd) ... ok
 test_reshape_as_scalar_to_dims (__main__.TestAutograd) ... ok
 test_reshape_scalar_to_1d (__main__.TestAutograd) ... ok
 test_reshape_scalar_to_scalar (__main__.TestAutograd) ... ok
 test_reshape_size (__main__.TestAutograd) ... ok
 test_resize (__main__.TestAutograd) ... ok
 test_resize__fewer_dims (__main__.TestAutograd) ... ok
 test_resize__scalar (__main__.TestAutograd) ... ok
 test_resize__scalar_to_dims (__main__.TestAutograd) ... ok
 test_resize_as_ (__main__.TestAutograd) ... ok
 test_resize_as__scalar (__main__.TestAutograd) ... ok
 test_resize_as__scalar_to_dims (__main__.TestAutograd) ... ok
 test_retain_grad (__main__.TestAutograd) ... ok
 test_retain_grad_cycle (__main__.TestAutograd) ... ok
 test_return_duplicate (__main__.TestAutograd) ... ok
 test_return_duplicate_inplace (__main__.TestAutograd) ... ok
 test_return_leaf (__main__.TestAutograd) ... ok
 test_return_leaf_inplace (__main__.TestAutograd) ... ok
 test_rnn_backward_to_input_but_not_parameters_cuda (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_rot90_default (__main__.TestAutograd) ... ok
 test_rot90_k1_d01 (__main__.TestAutograd) ... ok
 test_rot90_k1_d12 (__main__.TestAutograd) ... ok
 test_rot90_k1_neg_d (__main__.TestAutograd) ... ok
 test_round (__main__.TestAutograd) ... ok
 test_round_scalar (__main__.TestAutograd) ... ok
 test_rsqrt (__main__.TestAutograd) ... ok
 test_rsqrt_scalar (__main__.TestAutograd) ... ok
 test_save_none_for_backward (__main__.TestAutograd) ... ok
 test_save_output_nr (__main__.TestAutograd) ... ok
 test_saved_variables_deprecated (__main__.TestAutograd) ... ok
 test_scatter_add_dim0 (__main__.TestAutograd) ... ok
 test_scatter_add_dim0_neg0 (__main__.TestAutograd) ... ok
 test_scatter_add_dim1 (__main__.TestAutograd) ... ok
 test_scatter_add_dim1_neg0 (__main__.TestAutograd) ... ok
 test_scatter_add_scalar_all_dim0 (__main__.TestAutograd) ... ok
 test_scatter_add_scalar_all_dim0_neg0 (__main__.TestAutograd) ... ok
 test_scatter_dim0 (__main__.TestAutograd) ... ok
 test_scatter_dim0_neg0 (__main__.TestAutograd) ... ok
 test_scatter_dim1 (__main__.TestAutograd) ... ok
 test_scatter_dim1_neg0 (__main__.TestAutograd) ... ok
 test_scatter_scalar_all_dim0 (__main__.TestAutograd) ... ok
 test_scatter_scalar_all_dim0_neg0 (__main__.TestAutograd) ... ok
 test_select_1d (__main__.TestAutograd) ... ok
 test_select_dim (__main__.TestAutograd) ... ok
 test_select_dim_neg0 (__main__.TestAutograd) ... ok
 test_select_sum (__main__.TestAutograd) ... ok
 test_select_wrap_dim (__main__.TestAutograd) ... ok
 test_select_wrap_dim_neg0 (__main__.TestAutograd) ... ok
 test_set_grad_enabled (__main__.TestAutograd) ... ok
 test_set_requires_grad_only_for_floats (__main__.TestAutograd) ... ok
 test_set_requires_grad_only_for_floats_cuda (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_setitem (__main__.TestAutograd) ... ok
 test_setitem_mask (__main__.TestAutograd) ... ok
 test_shape (__main__.TestAutograd) ... ok
 test_sharded_grad (__main__.TestAutograd) ... ok
 test_sigmoid (__main__.TestAutograd) ... ok
 test_sigmoid_scalar (__main__.TestAutograd) ... ok
 test_sign (__main__.TestAutograd) ... ok
 test_sign_scalar (__main__.TestAutograd) ... ok
 test_sin (__main__.TestAutograd) ... ok
 test_sin_scalar (__main__.TestAutograd) ... ok
 test_sinh (__main__.TestAutograd) ... ok
 test_sinh_scalar (__main__.TestAutograd) ... ok
 test_slogdet_1x1_neg_det (__main__.TestAutograd) ... ok
 test_slogdet_1x1_pos_det (__main__.TestAutograd) ... ok
 test_slogdet_distinct_singular_values (__main__.TestAutograd) ... ok
 test_slogdet_neg_det (__main__.TestAutograd) ... ok
 test_slogdet_pos_det (__main__.TestAutograd) ... ok
 test_slogdet_symmetric (__main__.TestAutograd) ... ok
 test_slogdet_symmetric_pd (__main__.TestAutograd) ... ok
 test_sort (__main__.TestAutograd) ... ok
 test_sort_dim (__main__.TestAutograd) ... ok
 test_sort_dim_desc (__main__.TestAutograd) ... ok
 test_sort_dim_desc_scalar (__main__.TestAutograd) ... ok
 test_sort_dim_scalar (__main__.TestAutograd) ... ok
 test_sort_scalar (__main__.TestAutograd) ... ok
 test_sparse_backward (__main__.TestAutograd) ... ok
 test_split (__main__.TestAutograd) ... ok
 test_split_dim (__main__.TestAutograd) ... ok
 test_split_dim_neg0 (__main__.TestAutograd) ... ok
 test_split_size_list (__main__.TestAutograd) ... ok
 test_split_size_list_dim (__main__.TestAutograd) ... ok
 test_split_size_list_dim_neg0 (__main__.TestAutograd) ... ok
 test_sqrt (__main__.TestAutograd) ... ok
 test_sqrt_scalar (__main__.TestAutograd) ... ok
 test_squeeze (__main__.TestAutograd) ... ok
 test_squeeze_1_dim (__main__.TestAutograd) ... ok
 test_squeeze_1_dim_neg0 (__main__.TestAutograd) ... ok
 test_squeeze_input_sizes_are_ones (__main__.TestAutograd) ... ok
 test_squeeze_not_1_dim (__main__.TestAutograd) ... ok
 test_squeeze_not_1_dim_neg0 (__main__.TestAutograd) ... ok
 test_squeeze_scalar (__main__.TestAutograd) ... ok
 test_squeeze_scalar_neg0 (__main__.TestAutograd) ... ok
 test_stack (__main__.TestAutograd) ... ok
 test_std (__main__.TestAutograd) ... ok
 test_std_dim (__main__.TestAutograd) ... ok
 test_std_dim_1d (__main__.TestAutograd) ... ok
 test_std_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_std_dim_neg0 (__main__.TestAutograd) ... ok
 test_std_keepdim_dim (__main__.TestAutograd) ... ok
 test_std_keepdim_dim_1d (__main__.TestAutograd) ... ok
 test_std_keepdim_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_std_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_sub (__main__.TestAutograd) ... ok
 test_sub_broadcast_all (__main__.TestAutograd) ... ok
 test_sub_broadcast_lhs (__main__.TestAutograd) ... ok
 test_sub_broadcast_rhs (__main__.TestAutograd) ... ok
 test_sub_constant (__main__.TestAutograd) ... ok
 test_sub_scalar_broadcast_lhs (__main__.TestAutograd) ... ok
 test_sub_scalar_broadcast_rhs (__main__.TestAutograd) ... ok
 test_sub_scalar_constant (__main__.TestAutograd) ... ok
 test_sum (__main__.TestAutograd) ... ok
 test_sum_dim (__main__.TestAutograd) ... ok
 test_sum_dim_neg0 (__main__.TestAutograd) ... ok
 test_sum_keepdim_dim (__main__.TestAutograd) ... ok
 test_sum_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_sum_multi_dim (__main__.TestAutograd) ... ok
 test_sum_multi_dim_keepdim (__main__.TestAutograd) ... ok
 test_sum_scalar (__main__.TestAutograd) ... ok
 test_sum_scalar_dim (__main__.TestAutograd) ... ok
 test_sum_scalar_dim_neg0 (__main__.TestAutograd) ... ok
 test_sum_scalar_keepdim_dim (__main__.TestAutograd) ... ok
 test_sum_scalar_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_svd (__main__.TestAutograd) ... ok
 test_svd_large (__main__.TestAutograd) ... ok
 test_svd_no_singularvectors (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_svd_tall (__main__.TestAutograd) ... ok
 test_svd_tall_all (__main__.TestAutograd) ... ok
 test_svd_wide (__main__.TestAutograd) ... ok
 test_svd_wide_all (__main__.TestAutograd) ... ok
 test_symeig_large (__main__.TestAutograd) ... ok
 test_symeig_lower (__main__.TestAutograd) ... ok
 test_symeig_no_eigenvectors (__main__.TestAutograd) ... ok
 test_symeig_upper (__main__.TestAutograd) ... ok
 test_t (__main__.TestAutograd) ... ok
 test_take (__main__.TestAutograd) ... ok
 test_take_scalar_both (__main__.TestAutograd) ... ok
 test_take_scalar_data (__main__.TestAutograd) ... ok
 test_take_scalar_index (__main__.TestAutograd) ... ok
 test_tan (__main__.TestAutograd) ... ok
 test_tanh (__main__.TestAutograd) ... ok
 test_tanh_scalar (__main__.TestAutograd) ... ok
 test_too_many_grads (__main__.TestAutograd) ... ok
 test_topk (__main__.TestAutograd) ... ok
 test_topk_dim (__main__.TestAutograd) ... ok
 test_topk_dim_desc (__main__.TestAutograd) ... ok
 test_topk_dim_desc_neg0 (__main__.TestAutograd) ... ok
 test_topk_dim_desc_scalar (__main__.TestAutograd) ... ok
 test_topk_dim_desc_scalar_neg0 (__main__.TestAutograd) ... ok
 test_topk_dim_desc_sort (__main__.TestAutograd) ... ok
 test_topk_dim_desc_sort_neg0 (__main__.TestAutograd) ... ok
 test_topk_dim_desc_sort_scalar (__main__.TestAutograd) ... ok
 test_topk_dim_desc_sort_scalar_neg0 (__main__.TestAutograd) ... ok
 test_topk_dim_neg0 (__main__.TestAutograd) ... ok
 test_topk_dim_scalar (__main__.TestAutograd) ... ok
 test_topk_dim_scalar_neg0 (__main__.TestAutograd) ... ok
 test_topk_scalar (__main__.TestAutograd) ... ok
 test_trace (__main__.TestAutograd) ... ok
 test_transpose_1d (__main__.TestAutograd) ... ok
 test_transpose_2d (__main__.TestAutograd) ... ok
 test_transpose_3d (__main__.TestAutograd) ... ok
 test_transpose_dim (__main__.TestAutograd) ... ok
 test_transpose_dim_neg0 (__main__.TestAutograd) ... ok
 test_transpose_dim_neg0_neg1 (__main__.TestAutograd) ... ok
 test_transpose_dim_neg1 (__main__.TestAutograd) ... ok
 test_transpose_scalar (__main__.TestAutograd) ... ok
 test_tril (__main__.TestAutograd) ... ok
 test_tril_idx (__main__.TestAutograd) ... ok
 test_triu (__main__.TestAutograd) ... ok
 test_triu_idx (__main__.TestAutograd) ... ok
 test_trtrs (__main__.TestAutograd) ... ok
 test_trunc (__main__.TestAutograd) ... ok
 test_trunc_scalar (__main__.TestAutograd) ... ok
 test_type_conversions (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_unbind (__main__.TestAutograd) ... ok
 test_unfold (__main__.TestAutograd) ... ok
 test_unfold_lastdim (__main__.TestAutograd) ... ok
 test_unfold_lastdim_neg0 (__main__.TestAutograd) ... ok
 test_unfold_neg0 (__main__.TestAutograd) ... ok
 test_unfold_scalar (__main__.TestAutograd) ... ok
 test_unfold_scalar_neg0 (__main__.TestAutograd) ... ok
 test_unsqueeze_first (__main__.TestAutograd) ... ok
 test_unsqueeze_first_neg0 (__main__.TestAutograd) ... ok
 test_unsqueeze_last (__main__.TestAutograd) ... ok
 test_unsqueeze_last_neg0 (__main__.TestAutograd) ... ok
 test_unsqueeze_middle (__main__.TestAutograd) ... ok
 test_unsqueeze_middle_neg0 (__main__.TestAutograd) ... ok
 test_unsqueeze_scalar (__main__.TestAutograd) ... ok
 test_unsqueeze_scalar_neg0 (__main__.TestAutograd) ... ok
 test_unused_output (__main__.TestAutograd) ... ok
 test_unused_output_gpu (__main__.TestAutograd) ... skipped 'no multi-GPU'
 test_var (__main__.TestAutograd) ... ok
 test_var_dim (__main__.TestAutograd) ... ok
 test_var_dim_1d (__main__.TestAutograd) ... ok
 test_var_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_var_dim_neg0 (__main__.TestAutograd) ... ok
 test_var_keepdim_dim (__main__.TestAutograd) ... ok
 test_var_keepdim_dim_1d (__main__.TestAutograd) ... ok
 test_var_keepdim_dim_1d_neg0 (__main__.TestAutograd) ... ok
 test_var_keepdim_dim_neg0 (__main__.TestAutograd) ... ok
 test_variable_traverse (__main__.TestAutograd) ... ok
 test_view (__main__.TestAutograd) ... ok
 test_view_1d (__main__.TestAutograd) ... ok
 test_view_as (__main__.TestAutograd) ... ok
 test_view_as_scalar (__main__.TestAutograd) ... ok
 test_view_as_scalar_to_dims (__main__.TestAutograd) ... ok
 test_view_scalar_to_1d (__main__.TestAutograd) ... ok
 test_view_scalar_to_scalar (__main__.TestAutograd) ... ok
 test_view_size (__main__.TestAutograd) ... ok
 test_volatile_deprecated (__main__.TestAutograd) ... ok
 test_where (__main__.TestAutograd) ... ok
 test_where_broadcast_all (__main__.TestAutograd) ... ok
 test_where_functional (__main__.TestAutograd) ... ok
 test_where_functional_cuda (__main__.TestAutograd) ... skipped "test doesn't currently work on the ROCm stack"
 test_where_scalar (__main__.TestAutograd) ... ok
 test_where_scalar_broadcast_mask (__main__.TestAutograd) ... ok
 test_where_scalar_broadcast_non_mask (__main__.TestAutograd) ... ok
 test_zero_ (__main__.TestAutograd) ... ok
 test_zero__scalar (__main__.TestAutograd) ... ok

 ----------------------------------------------------------------------
 Ran 874 tests in 140.328s

 OK (skipped=15)
 Running test_cuda ...
 test_ByteTensor_add (__main__.TestCuda) ... ok
 test_ByteTensor_add_ (__main__.TestCuda) ... ok
 test_ByteTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_add__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_add_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_addbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addcdiv (__main__.TestCuda) ... ok
 test_ByteTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_ByteTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_ByteTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_ByteTensor_addcmul (__main__.TestCuda) ... ok
 test_ByteTensor_addcmul_ (__main__.TestCuda) ... ok
 test_ByteTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_ByteTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_ByteTensor_addmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addmv_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_addr_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_baddbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ByteTensor_chunk (__main__.TestCuda) ... ok
 test_ByteTensor_chunk_dim (__main__.TestCuda) ... ok
 test_ByteTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_clamp (__main__.TestCuda) ... ok
 test_ByteTensor_clamp_ (__main__.TestCuda) ... ok
 test_ByteTensor_clone (__main__.TestCuda) ... ok
 test_ByteTensor_contiguous (__main__.TestCuda) ... ok
 test_ByteTensor_cross (__main__.TestCuda) ... ok
 test_ByteTensor_cumprod (__main__.TestCuda) ... ok
 test_ByteTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_cumsum (__main__.TestCuda) ... ok
 test_ByteTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_dim (__main__.TestCuda) ... ok
 test_ByteTensor_div (__main__.TestCuda) ... ok
 test_ByteTensor_div_ (__main__.TestCuda) ... ok
 test_ByteTensor_div__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_div_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_element_size (__main__.TestCuda) ... ok
 test_ByteTensor_eq (__main__.TestCuda) ... ok
 test_ByteTensor_eq_ (__main__.TestCuda) ... ok
 test_ByteTensor_eq__equal (__main__.TestCuda) ... ok
 test_ByteTensor_eq_equal (__main__.TestCuda) ... ok
 test_ByteTensor_equal (__main__.TestCuda) ... ok
 test_ByteTensor_equal_equal (__main__.TestCuda) ... ok
 test_ByteTensor_expand (__main__.TestCuda) ... ok
 test_ByteTensor_expand_as (__main__.TestCuda) ... ok
 test_ByteTensor_fill_ (__main__.TestCuda) ... ok
 test_ByteTensor_flip_d0 (__main__.TestCuda) ... ok
 test_ByteTensor_flip_d012 (__main__.TestCuda) ... ok
 test_ByteTensor_flip_d02 (__main__.TestCuda) ... ok
 test_ByteTensor_flip_d20 (__main__.TestCuda) ... ok
 test_ByteTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_ByteTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_fmod__value (__main__.TestCuda) ... ok
 test_ByteTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_fmod_value (__main__.TestCuda) ... ok
 test_ByteTensor_ge (__main__.TestCuda) ... ok
 test_ByteTensor_ge_ (__main__.TestCuda) ... ok
 test_ByteTensor_gt (__main__.TestCuda) ... ok
 test_ByteTensor_gt_ (__main__.TestCuda) ... ok
 test_ByteTensor_is_contiguous (__main__.TestCuda) ... ok
 test_ByteTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_ByteTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_ByteTensor_is_set_to (__main__.TestCuda) ... ok
 test_ByteTensor_le (__main__.TestCuda) ... ok
 test_ByteTensor_le_ (__main__.TestCuda) ... ok
 test_ByteTensor_lt (__main__.TestCuda) ... ok
 test_ByteTensor_lt_ (__main__.TestCuda) ... ok
 test_ByteTensor_max (__main__.TestCuda) ... ok
 test_ByteTensor_max_dim (__main__.TestCuda) ... ok
 test_ByteTensor_max_elementwise (__main__.TestCuda) ... ok
 test_ByteTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_min (__main__.TestCuda) ... ok
 test_ByteTensor_min_dim (__main__.TestCuda) ... ok
 test_ByteTensor_min_elementwise (__main__.TestCuda) ... ok
 test_ByteTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_mode (__main__.TestCuda) ... ok
 test_ByteTensor_mode_dim (__main__.TestCuda) ... ok
 test_ByteTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_mul (__main__.TestCuda) ... ok
 test_ByteTensor_mul_ (__main__.TestCuda) ... ok
 test_ByteTensor_mul__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_mul_scalar (__main__.TestCuda) ... ok
 test_ByteTensor_mul_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_narrow (__main__.TestCuda) ... ok
 test_ByteTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_ndimension (__main__.TestCuda) ... ok
 test_ByteTensor_ne (__main__.TestCuda) ... ok
 test_ByteTensor_ne_ (__main__.TestCuda) ... ok
 test_ByteTensor_ne__equal (__main__.TestCuda) ... ok
 test_ByteTensor_ne_equal (__main__.TestCuda) ... ok
 test_ByteTensor_nelement (__main__.TestCuda) ... ok
 test_ByteTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ByteTensor_numel (__main__.TestCuda) ... ok
 test_ByteTensor_permute (__main__.TestCuda) ... ok
 test_ByteTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_ByteTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_ByteTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_ByteTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_ByteTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_ByteTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_ByteTensor_prod (__main__.TestCuda) ... ok
 test_ByteTensor_prod_dim (__main__.TestCuda) ... ok
 test_ByteTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ByteTensor_put__accumulate (__main__.TestCuda) ... ok
 test_ByteTensor_put__empty (__main__.TestCuda) ... ok
 test_ByteTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_remainder__value (__main__.TestCuda) ... ok
 test_ByteTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_remainder_value (__main__.TestCuda) ... ok
 test_ByteTensor_repeat (__main__.TestCuda) ... ok
 test_ByteTensor_rot90_default (__main__.TestCuda) ... ok
 test_ByteTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_ByteTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_ByteTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_ByteTensor_sign (__main__.TestCuda) ... ok
 test_ByteTensor_sign_ (__main__.TestCuda) ... ok
 test_ByteTensor_size (__main__.TestCuda) ... ok
 test_ByteTensor_size_dim (__main__.TestCuda) ... ok
 test_ByteTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_sort (__main__.TestCuda) ... ok
 test_ByteTensor_sort_dim (__main__.TestCuda) ... ok
 test_ByteTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_ByteTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_ByteTensor_split (__main__.TestCuda) ... ok
 test_ByteTensor_split_dim (__main__.TestCuda) ... ok
 test_ByteTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze_ (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_ByteTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_sub (__main__.TestCuda) ... ok
 test_ByteTensor_sub_ (__main__.TestCuda) ... ok
 test_ByteTensor_sub__tensor (__main__.TestCuda) ... ok
 test_ByteTensor_sub_tensor (__main__.TestCuda) ... ok
 test_ByteTensor_sum (__main__.TestCuda) ... ok
 test_ByteTensor_sum_dim (__main__.TestCuda) ... ok
 test_ByteTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_t (__main__.TestCuda) ... ok
 test_ByteTensor_t_ (__main__.TestCuda) ... ok
 test_ByteTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ByteTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_ByteTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_ByteTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_ByteTensor_trace (__main__.TestCuda) ... ok
 test_ByteTensor_transpose (__main__.TestCuda) ... ok
 test_ByteTensor_transpose_ (__main__.TestCuda) ... ok
 test_ByteTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_tril (__main__.TestCuda) ... ok
 test_ByteTensor_tril_ (__main__.TestCuda) ... ok
 test_ByteTensor_tril__negative (__main__.TestCuda) ... ok
 test_ByteTensor_tril__positive (__main__.TestCuda) ... ok
 test_ByteTensor_tril_negative (__main__.TestCuda) ... ok
 test_ByteTensor_tril_positive (__main__.TestCuda) ... ok
 test_ByteTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_ByteTensor_triu (__main__.TestCuda) ... ok
 test_ByteTensor_triu_ (__main__.TestCuda) ... ok
 test_ByteTensor_triu__negative (__main__.TestCuda) ... ok
 test_ByteTensor_triu__positive (__main__.TestCuda) ... ok
 test_ByteTensor_triu_negative (__main__.TestCuda) ... ok
 test_ByteTensor_triu_positive (__main__.TestCuda) ... ok
 test_ByteTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_ByteTensor_unsqueeze (__main__.TestCuda) ... ok
 test_ByteTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_ByteTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_ByteTensor_view_as (__main__.TestCuda) ... ok
 test_ByteTensor_view_contiguous (__main__.TestCuda) ... ok
 test_ByteTensor_zero_ (__main__.TestCuda) ... ok
 test_CharTensor___lshift__ (__main__.TestCuda) ... ok
 test_CharTensor___rshift__ (__main__.TestCuda) ... ok
 test_CharTensor_add (__main__.TestCuda) ... ok
 test_CharTensor_add_ (__main__.TestCuda) ... ok
 test_CharTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_CharTensor_add__tensor (__main__.TestCuda) ... ok
 test_CharTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_CharTensor_add_tensor (__main__.TestCuda) ... ok
 test_CharTensor_addbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addcdiv (__main__.TestCuda) ... ok
 test_CharTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_CharTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_CharTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_CharTensor_addcmul (__main__.TestCuda) ... ok
 test_CharTensor_addcmul_ (__main__.TestCuda) ... ok
 test_CharTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_CharTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_CharTensor_addmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addmv_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_addr_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_baddbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_CharTensor_chunk (__main__.TestCuda) ... ok
 test_CharTensor_chunk_dim (__main__.TestCuda) ... ok
 test_CharTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_clamp (__main__.TestCuda) ... ok
 test_CharTensor_clamp_ (__main__.TestCuda) ... ok
 test_CharTensor_clone (__main__.TestCuda) ... ok
 test_CharTensor_contiguous (__main__.TestCuda) ... ok
 test_CharTensor_cross (__main__.TestCuda) ... ok
 test_CharTensor_cumprod (__main__.TestCuda) ... ok
 test_CharTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_cumsum (__main__.TestCuda) ... ok
 test_CharTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_dim (__main__.TestCuda) ... ok
 test_CharTensor_div (__main__.TestCuda) ... ok
 test_CharTensor_div_ (__main__.TestCuda) ... ok
 test_CharTensor_div__tensor (__main__.TestCuda) ... ok
 test_CharTensor_div_tensor (__main__.TestCuda) ... ok
 test_CharTensor_element_size (__main__.TestCuda) ... ok
 test_CharTensor_eq (__main__.TestCuda) ... ok
 test_CharTensor_eq_ (__main__.TestCuda) ... ok
 test_CharTensor_eq__equal (__main__.TestCuda) ... ok
 test_CharTensor_eq_equal (__main__.TestCuda) ... ok
 test_CharTensor_equal (__main__.TestCuda) ... ok
 test_CharTensor_equal_equal (__main__.TestCuda) ... ok
 test_CharTensor_expand (__main__.TestCuda) ... ok
 test_CharTensor_expand_as (__main__.TestCuda) ... ok
 test_CharTensor_fill_ (__main__.TestCuda) ... ok
 test_CharTensor_flip_d0 (__main__.TestCuda) ... ok
 test_CharTensor_flip_d012 (__main__.TestCuda) ... ok
 test_CharTensor_flip_d02 (__main__.TestCuda) ... ok
 test_CharTensor_flip_d20 (__main__.TestCuda) ... ok
 test_CharTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_CharTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_CharTensor_fmod__value (__main__.TestCuda) ... ok
 test_CharTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_CharTensor_fmod_value (__main__.TestCuda) ... ok
 test_CharTensor_ge (__main__.TestCuda) ... ok
 test_CharTensor_ge_ (__main__.TestCuda) ... ok
 test_CharTensor_gt (__main__.TestCuda) ... ok
 test_CharTensor_gt_ (__main__.TestCuda) ... ok
 test_CharTensor_is_contiguous (__main__.TestCuda) ... ok
 test_CharTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_CharTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_CharTensor_is_set_to (__main__.TestCuda) ... ok
 test_CharTensor_le (__main__.TestCuda) ... ok
 test_CharTensor_le_ (__main__.TestCuda) ... ok
 test_CharTensor_lt (__main__.TestCuda) ... ok
 test_CharTensor_lt_ (__main__.TestCuda) ... ok
 test_CharTensor_max (__main__.TestCuda) ... ok
 test_CharTensor_max_dim (__main__.TestCuda) ... ok
 test_CharTensor_max_elementwise (__main__.TestCuda) ... ok
 test_CharTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_min (__main__.TestCuda) ... ok
 test_CharTensor_min_dim (__main__.TestCuda) ... ok
 test_CharTensor_min_elementwise (__main__.TestCuda) ... ok
 test_CharTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_mode (__main__.TestCuda) ... ok
 test_CharTensor_mode_dim (__main__.TestCuda) ... ok
 test_CharTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_mul (__main__.TestCuda) ... ok
 test_CharTensor_mul_ (__main__.TestCuda) ... ok
 test_CharTensor_mul__tensor (__main__.TestCuda) ... ok
 test_CharTensor_mul_scalar (__main__.TestCuda) ... ok
 test_CharTensor_mul_tensor (__main__.TestCuda) ... ok
 test_CharTensor_narrow (__main__.TestCuda) ... ok
 test_CharTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_ndimension (__main__.TestCuda) ... ok
 test_CharTensor_ne (__main__.TestCuda) ... ok
 test_CharTensor_ne_ (__main__.TestCuda) ... ok
 test_CharTensor_ne__equal (__main__.TestCuda) ... ok
 test_CharTensor_ne_equal (__main__.TestCuda) ... ok
 test_CharTensor_nelement (__main__.TestCuda) ... ok
 test_CharTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_CharTensor_numel (__main__.TestCuda) ... ok
 test_CharTensor_permute (__main__.TestCuda) ... ok
 test_CharTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_CharTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_CharTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_CharTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_CharTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_CharTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_CharTensor_prod (__main__.TestCuda) ... ok
 test_CharTensor_prod_dim (__main__.TestCuda) ... ok
 test_CharTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_CharTensor_put__accumulate (__main__.TestCuda) ... ok
 test_CharTensor_put__empty (__main__.TestCuda) ... ok
 test_CharTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_CharTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_CharTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_CharTensor_remainder__value (__main__.TestCuda) ... ok
 test_CharTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_CharTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_CharTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_CharTensor_remainder_value (__main__.TestCuda) ... ok
 test_CharTensor_repeat (__main__.TestCuda) ... ok
 test_CharTensor_rot90_default (__main__.TestCuda) ... ok
 test_CharTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_CharTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_CharTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_CharTensor_sign (__main__.TestCuda) ... ok
 test_CharTensor_sign_ (__main__.TestCuda) ... ok
 test_CharTensor_size (__main__.TestCuda) ... ok
 test_CharTensor_size_dim (__main__.TestCuda) ... ok
 test_CharTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_sort (__main__.TestCuda) ... ok
 test_CharTensor_sort_dim (__main__.TestCuda) ... ok
 test_CharTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_CharTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_CharTensor_split (__main__.TestCuda) ... ok
 test_CharTensor_split_dim (__main__.TestCuda) ... ok
 test_CharTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_squeeze (__main__.TestCuda) ... ok
 test_CharTensor_squeeze_ (__main__.TestCuda) ... ok
 test_CharTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_CharTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_CharTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_sub (__main__.TestCuda) ... ok
 test_CharTensor_sub_ (__main__.TestCuda) ... ok
 test_CharTensor_sub__tensor (__main__.TestCuda) ... ok
 test_CharTensor_sub_tensor (__main__.TestCuda) ... ok
 test_CharTensor_sum (__main__.TestCuda) ... ok
 test_CharTensor_sum_dim (__main__.TestCuda) ... ok
 test_CharTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_t (__main__.TestCuda) ... ok
 test_CharTensor_t_ (__main__.TestCuda) ... ok
 test_CharTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_CharTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_CharTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_CharTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_CharTensor_trace (__main__.TestCuda) ... ok
 test_CharTensor_transpose (__main__.TestCuda) ... ok
 test_CharTensor_transpose_ (__main__.TestCuda) ... ok
 test_CharTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_tril (__main__.TestCuda) ... ok
 test_CharTensor_tril_ (__main__.TestCuda) ... ok
 test_CharTensor_tril__negative (__main__.TestCuda) ... ok
 test_CharTensor_tril__positive (__main__.TestCuda) ... ok
 test_CharTensor_tril_negative (__main__.TestCuda) ... ok
 test_CharTensor_tril_positive (__main__.TestCuda) ... ok
 test_CharTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_CharTensor_triu (__main__.TestCuda) ... ok
 test_CharTensor_triu_ (__main__.TestCuda) ... ok
 test_CharTensor_triu__negative (__main__.TestCuda) ... ok
 test_CharTensor_triu__positive (__main__.TestCuda) ... ok
 test_CharTensor_triu_negative (__main__.TestCuda) ... ok
 test_CharTensor_triu_positive (__main__.TestCuda) ... ok
 test_CharTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_CharTensor_unsqueeze (__main__.TestCuda) ... ok
 test_CharTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_CharTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_CharTensor_view_as (__main__.TestCuda) ... ok
 test_CharTensor_view_contiguous (__main__.TestCuda) ... ok
 test_CharTensor_zero_ (__main__.TestCuda) ... ok
 test_DoubleTensor___lshift__ (__main__.TestCuda) ... ok
 test_DoubleTensor___rshift__ (__main__.TestCuda) ... ok
 test_DoubleTensor_abs (__main__.TestCuda) ... ok
 test_DoubleTensor_abs_ (__main__.TestCuda) ... ok
 test_DoubleTensor_acos (__main__.TestCuda) ... ok
 test_DoubleTensor_acos_ (__main__.TestCuda) ... ok
 test_DoubleTensor_add (__main__.TestCuda) ... ok
 test_DoubleTensor_add_ (__main__.TestCuda) ... ok
 test_DoubleTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_add__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_add_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm__two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addbmm_two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addcdiv (__main__.TestCuda) ... ok
 test_DoubleTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addcmul (__main__.TestCuda) ... ok
 test_DoubleTensor_addcmul_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm__two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addmm_two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv__two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addmv_two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addr (__main__.TestCuda) ... ok
 test_DoubleTensor_addr_ (__main__.TestCuda) ... ok
 test_DoubleTensor_addr__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addr__two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_addr_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_addr_two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_asin (__main__.TestCuda) ... ok
 test_DoubleTensor_asin_ (__main__.TestCuda) ... ok
 test_DoubleTensor_atan (__main__.TestCuda) ... ok
 test_DoubleTensor_atan2 (__main__.TestCuda) ... ok
 test_DoubleTensor_atan2_ (__main__.TestCuda) ... ok
 test_DoubleTensor_atan_ (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm_ (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm__scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm__two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_baddbmm_two_scalars (__main__.TestCuda) ... ok
 test_DoubleTensor_ceil (__main__.TestCuda) ... ok
 test_DoubleTensor_ceil_ (__main__.TestCuda) ... ok
 test_DoubleTensor_chunk (__main__.TestCuda) ... ok
 test_DoubleTensor_chunk_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_clamp (__main__.TestCuda) ... ok
 test_DoubleTensor_clamp_ (__main__.TestCuda) ... ok
 test_DoubleTensor_clone (__main__.TestCuda) ... ok
 test_DoubleTensor_contiguous (__main__.TestCuda) ... ok
 test_DoubleTensor_cos (__main__.TestCuda) ... ok
 test_DoubleTensor_cos_ (__main__.TestCuda) ... ok
 test_DoubleTensor_cosh (__main__.TestCuda) ... ok
 test_DoubleTensor_cosh_ (__main__.TestCuda) ... ok
 test_DoubleTensor_cross (__main__.TestCuda) ... ok
 test_DoubleTensor_cumprod (__main__.TestCuda) ... ok
 test_DoubleTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_cumsum (__main__.TestCuda) ... ok
 test_DoubleTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_digamma (__main__.TestCuda) ... ok
 test_DoubleTensor_digamma_ (__main__.TestCuda) ... ok
 test_DoubleTensor_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_dist (__main__.TestCuda) ... ok
 test_DoubleTensor_dist_2_5_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_dist_3_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_div (__main__.TestCuda) ... ok
 test_DoubleTensor_div_ (__main__.TestCuda) ... ok
 test_DoubleTensor_div__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_div_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_dot (__main__.TestCuda) ... ok
 test_DoubleTensor_eig_with_eigvec (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_element_size (__main__.TestCuda) ... ok
 test_DoubleTensor_eq (__main__.TestCuda) ... ok
 test_DoubleTensor_eq_ (__main__.TestCuda) ... ok
 test_DoubleTensor_eq__equal (__main__.TestCuda) ... ok
 test_DoubleTensor_eq_equal (__main__.TestCuda) ... ok
 test_DoubleTensor_equal (__main__.TestCuda) ... ok
 test_DoubleTensor_equal_equal (__main__.TestCuda) ... ok
 test_DoubleTensor_erf (__main__.TestCuda) ... ok
 test_DoubleTensor_erf_ (__main__.TestCuda) ... ok
 test_DoubleTensor_erfc (__main__.TestCuda) ... ok
 test_DoubleTensor_erfc_ (__main__.TestCuda) ... ok
 test_DoubleTensor_erfinv (__main__.TestCuda) ... ok
 test_DoubleTensor_erfinv_ (__main__.TestCuda) ... ok
 test_DoubleTensor_exp (__main__.TestCuda) ... ok
 test_DoubleTensor_exp_ (__main__.TestCuda) ... ok
 test_DoubleTensor_expand (__main__.TestCuda) ... ok
 test_DoubleTensor_expand_as (__main__.TestCuda) ... ok
 test_DoubleTensor_expm1 (__main__.TestCuda) ... ok
 test_DoubleTensor_expm1_ (__main__.TestCuda) ... ok
 test_DoubleTensor_fill_ (__main__.TestCuda) ... ok
 test_DoubleTensor_flip_d0 (__main__.TestCuda) ... ok
 test_DoubleTensor_flip_d012 (__main__.TestCuda) ... ok
 test_DoubleTensor_flip_d02 (__main__.TestCuda) ... ok
 test_DoubleTensor_flip_d20 (__main__.TestCuda) ... ok
 test_DoubleTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_DoubleTensor_floor (__main__.TestCuda) ... ok
 test_DoubleTensor_floor_ (__main__.TestCuda) ... ok
 test_DoubleTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_fmod__value (__main__.TestCuda) ... ok
 test_DoubleTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_fmod_value (__main__.TestCuda) ... ok
 test_DoubleTensor_frac (__main__.TestCuda) ... ok
 test_DoubleTensor_frac_ (__main__.TestCuda) ... ok
 test_DoubleTensor_ge (__main__.TestCuda) ... ok
 test_DoubleTensor_ge_ (__main__.TestCuda) ... ok
 test_DoubleTensor_geqrf (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_gt (__main__.TestCuda) ... ok
 test_DoubleTensor_gt_ (__main__.TestCuda) ... ok
 test_DoubleTensor_inverse (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_DoubleTensor_is_contiguous (__main__.TestCuda) ... ok
 test_DoubleTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_DoubleTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_DoubleTensor_is_set_to (__main__.TestCuda) ... ok
 test_DoubleTensor_le (__main__.TestCuda) ... ok
 test_DoubleTensor_le_ (__main__.TestCuda) ... ok
 test_DoubleTensor_lerp (__main__.TestCuda) ... ok
 test_DoubleTensor_lerp_ (__main__.TestCuda) ... ok
 test_DoubleTensor_lgamma (__main__.TestCuda) ... ok
 test_DoubleTensor_lgamma_ (__main__.TestCuda) ... ok
 test_DoubleTensor_log (__main__.TestCuda) ... ok
 test_DoubleTensor_log10 (__main__.TestCuda) ... ok
 test_DoubleTensor_log10_ (__main__.TestCuda) ... ok
 test_DoubleTensor_log1p (__main__.TestCuda) ... ok
 test_DoubleTensor_log1p_ (__main__.TestCuda) ... ok
 test_DoubleTensor_log2 (__main__.TestCuda) ... ok
 test_DoubleTensor_log2_ (__main__.TestCuda) ... ok
 test_DoubleTensor_log_ (__main__.TestCuda) ... ok
 test_DoubleTensor_lt (__main__.TestCuda) ... ok
 test_DoubleTensor_lt_ (__main__.TestCuda) ... ok
 test_DoubleTensor_max (__main__.TestCuda) ... ok
 test_DoubleTensor_max_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_max_elementwise (__main__.TestCuda) ... ok
 test_DoubleTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_mean (__main__.TestCuda) ... ok
 test_DoubleTensor_mean_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_mean_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_min (__main__.TestCuda) ... ok
 test_DoubleTensor_min_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_min_elementwise (__main__.TestCuda) ... ok
 test_DoubleTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_mode (__main__.TestCuda) ... ok
 test_DoubleTensor_mode_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_mul (__main__.TestCuda) ... ok
 test_DoubleTensor_mul_ (__main__.TestCuda) ... ok
 test_DoubleTensor_mul__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_mul_scalar (__main__.TestCuda) ... ok
 test_DoubleTensor_mul_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_mvlgamma_2d_p=1 (__main__.TestCuda) ... ok
 test_DoubleTensor_mvlgamma_2d_p=2 (__main__.TestCuda) ... ok
 test_DoubleTensor_mvlgamma__2d_p=1 (__main__.TestCuda) ... ok
 test_DoubleTensor_mvlgamma__2d_p=2 (__main__.TestCuda) ... ok
 test_DoubleTensor_narrow (__main__.TestCuda) ... ok
 test_DoubleTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_ndimension (__main__.TestCuda) ... ok
 test_DoubleTensor_ne (__main__.TestCuda) ... ok
 test_DoubleTensor_ne_ (__main__.TestCuda) ... ok
 test_DoubleTensor_ne__equal (__main__.TestCuda) ... ok
 test_DoubleTensor_ne_equal (__main__.TestCuda) ... ok
 test_DoubleTensor_neg (__main__.TestCuda) ... ok
 test_DoubleTensor_neg_ (__main__.TestCuda) ... ok
 test_DoubleTensor_nelement (__main__.TestCuda) ... ok
 test_DoubleTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_DoubleTensor_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_norm_3_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_norm_3_norm_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_norm_3_norm_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_numel (__main__.TestCuda) ... ok
 test_DoubleTensor_permute (__main__.TestCuda) ... ok
 test_DoubleTensor_pow (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_ (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__pow-1 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__pow-2 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_pow-1 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_pow-2 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_DoubleTensor_pow_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_prod (__main__.TestCuda) ... ok
 test_DoubleTensor_prod_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_DoubleTensor_put__accumulate (__main__.TestCuda) ... ok
 test_DoubleTensor_put__empty (__main__.TestCuda) ... ok
 test_DoubleTensor_qr_big (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_qr_fat (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_qr_skinny (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_qr_square (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_reciprocal (__main__.TestCuda) ... ok
 test_DoubleTensor_reciprocal_ (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder__value (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_remainder_value (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm_1_5_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm_2_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm_2_norm_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm__1_5_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm__2_norm (__main__.TestCuda) ... ok
 test_DoubleTensor_renorm__2_norm_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_repeat (__main__.TestCuda) ... ok
 test_DoubleTensor_rot90_default (__main__.TestCuda) ... ok
 test_DoubleTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_DoubleTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_DoubleTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_DoubleTensor_round (__main__.TestCuda) ... ok
 test_DoubleTensor_round_ (__main__.TestCuda) ... ok
 test_DoubleTensor_rsqrt (__main__.TestCuda) ... ok
 test_DoubleTensor_rsqrt_ (__main__.TestCuda) ... ok
 test_DoubleTensor_sigmoid (__main__.TestCuda) ... ok
 test_DoubleTensor_sigmoid_ (__main__.TestCuda) ... ok
 test_DoubleTensor_sign (__main__.TestCuda) ... ok
 test_DoubleTensor_sign_ (__main__.TestCuda) ... ok
 test_DoubleTensor_sin (__main__.TestCuda) ... ok
 test_DoubleTensor_sin_ (__main__.TestCuda) ... ok
 test_DoubleTensor_sinh (__main__.TestCuda) ... ok
 test_DoubleTensor_sinh_ (__main__.TestCuda) ... ok
 test_DoubleTensor_size (__main__.TestCuda) ... ok
 test_DoubleTensor_size_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sort (__main__.TestCuda) ... ok
 test_DoubleTensor_sort_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_DoubleTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_DoubleTensor_split (__main__.TestCuda) ... ok
 test_DoubleTensor_split_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sqrt (__main__.TestCuda) ... ok
 test_DoubleTensor_sqrt_ (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze_ (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_std (__main__.TestCuda) ... ok
 test_DoubleTensor_std_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_std_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sub (__main__.TestCuda) ... ok
 test_DoubleTensor_sub_ (__main__.TestCuda) ... ok
 test_DoubleTensor_sub__tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_sub_tensor (__main__.TestCuda) ... ok
 test_DoubleTensor_sum (__main__.TestCuda) ... ok
 test_DoubleTensor_sum_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_svd_square (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_svd_square_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_svd_tall_all (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_svd_tall_all_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_svd_tall_some (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_svd_tall_some_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_DoubleTensor_t (__main__.TestCuda) ... ok
 test_DoubleTensor_t_ (__main__.TestCuda) ... ok
 test_DoubleTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_DoubleTensor_tan (__main__.TestCuda) ... ok
 test_DoubleTensor_tan_ (__main__.TestCuda) ... ok
 test_DoubleTensor_tanh (__main__.TestCuda) ... ok
 test_DoubleTensor_tanh_ (__main__.TestCuda) ... ok
 test_DoubleTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_DoubleTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_DoubleTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_DoubleTensor_trace (__main__.TestCuda) ... ok
 test_DoubleTensor_transpose (__main__.TestCuda) ... ok
 test_DoubleTensor_transpose_ (__main__.TestCuda) ... ok
 test_DoubleTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_tril (__main__.TestCuda) ... ok
 test_DoubleTensor_tril_ (__main__.TestCuda) ... ok
 test_DoubleTensor_tril__negative (__main__.TestCuda) ... ok
 test_DoubleTensor_tril__positive (__main__.TestCuda) ... ok
 test_DoubleTensor_tril_negative (__main__.TestCuda) ... ok
 test_DoubleTensor_tril_positive (__main__.TestCuda) ... ok
 test_DoubleTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_DoubleTensor_triu (__main__.TestCuda) ... ok
 test_DoubleTensor_triu_ (__main__.TestCuda) ... ok
 test_DoubleTensor_triu__negative (__main__.TestCuda) ... ok
 test_DoubleTensor_triu__positive (__main__.TestCuda) ... ok
 test_DoubleTensor_triu_negative (__main__.TestCuda) ... ok
 test_DoubleTensor_triu_positive (__main__.TestCuda) ... ok
 test_DoubleTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_DoubleTensor_trunc (__main__.TestCuda) ... ok
 test_DoubleTensor_trunc_ (__main__.TestCuda) ... ok
 test_DoubleTensor_unsqueeze (__main__.TestCuda) ... ok
 test_DoubleTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_DoubleTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_var (__main__.TestCuda) ... ok
 test_DoubleTensor_var_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_var_neg_dim (__main__.TestCuda) ... ok
 test_DoubleTensor_view_as (__main__.TestCuda) ... ok
 test_DoubleTensor_view_contiguous (__main__.TestCuda) ... ok
 test_DoubleTensor_zero_ (__main__.TestCuda) ... ok
 test_FloatTensor___lshift__ (__main__.TestCuda) ... ok
 test_FloatTensor___rshift__ (__main__.TestCuda) ... ok
 test_FloatTensor_abs (__main__.TestCuda) ... ok
 test_FloatTensor_abs_ (__main__.TestCuda) ... ok
 test_FloatTensor_acos (__main__.TestCuda) ... ok
 test_FloatTensor_acos_ (__main__.TestCuda) ... ok
 test_FloatTensor_add (__main__.TestCuda) ... ok
 test_FloatTensor_add_ (__main__.TestCuda) ... ok
 test_FloatTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_add__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_add_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm_ (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm__two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addbmm_two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addcdiv (__main__.TestCuda) ... ok
 test_FloatTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_FloatTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addcmul (__main__.TestCuda) ... ok
 test_FloatTensor_addcmul_ (__main__.TestCuda) ... ok
 test_FloatTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addmm (__main__.TestCuda) ... ok
 test_FloatTensor_addmm_ (__main__.TestCuda) ... ok
 test_FloatTensor_addmm__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addmm__two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addmm_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addmm_two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addmv (__main__.TestCuda) ... ok
 test_FloatTensor_addmv_ (__main__.TestCuda) ... ok
 test_FloatTensor_addmv__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addmv__two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addmv_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addmv_two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addr (__main__.TestCuda) ... ok
 test_FloatTensor_addr_ (__main__.TestCuda) ... ok
 test_FloatTensor_addr__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addr__two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_addr_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_addr_two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_asin (__main__.TestCuda) ... ok
 test_FloatTensor_asin_ (__main__.TestCuda) ... ok
 test_FloatTensor_atan (__main__.TestCuda) ... ok
 test_FloatTensor_atan2 (__main__.TestCuda) ... ok
 test_FloatTensor_atan2_ (__main__.TestCuda) ... ok
 test_FloatTensor_atan_ (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm_ (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm__scalar (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm__two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_baddbmm_two_scalars (__main__.TestCuda) ... ok
 test_FloatTensor_ceil (__main__.TestCuda) ... ok
 test_FloatTensor_ceil_ (__main__.TestCuda) ... ok
 test_FloatTensor_chunk (__main__.TestCuda) ... ok
 test_FloatTensor_chunk_dim (__main__.TestCuda) ... ok
 test_FloatTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_clamp (__main__.TestCuda) ... ok
 test_FloatTensor_clamp_ (__main__.TestCuda) ... ok
 test_FloatTensor_clone (__main__.TestCuda) ... ok
 test_FloatTensor_contiguous (__main__.TestCuda) ... ok
 test_FloatTensor_cos (__main__.TestCuda) ... ok
 test_FloatTensor_cos_ (__main__.TestCuda) ... ok
 test_FloatTensor_cosh (__main__.TestCuda) ... ok
 test_FloatTensor_cosh_ (__main__.TestCuda) ... ok
 test_FloatTensor_cross (__main__.TestCuda) ... ok
 test_FloatTensor_cumprod (__main__.TestCuda) ... ok
 test_FloatTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_cumsum (__main__.TestCuda) ... ok
 test_FloatTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_digamma (__main__.TestCuda) ... ok
 test_FloatTensor_digamma_ (__main__.TestCuda) ... ok
 test_FloatTensor_dim (__main__.TestCuda) ... ok
 test_FloatTensor_dist (__main__.TestCuda) ... ok
 test_FloatTensor_dist_2_5_norm (__main__.TestCuda) ... ok
 test_FloatTensor_dist_3_norm (__main__.TestCuda) ... ok
 test_FloatTensor_div (__main__.TestCuda) ... ok
 test_FloatTensor_div_ (__main__.TestCuda) ... ok
 test_FloatTensor_div__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_div_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_dot (__main__.TestCuda) ... ok
 test_FloatTensor_eig_with_eigvec (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_element_size (__main__.TestCuda) ... ok
 test_FloatTensor_eq (__main__.TestCuda) ... ok
 test_FloatTensor_eq_ (__main__.TestCuda) ... ok
 test_FloatTensor_eq__equal (__main__.TestCuda) ... ok
 test_FloatTensor_eq_equal (__main__.TestCuda) ... ok
 test_FloatTensor_equal (__main__.TestCuda) ... ok
 test_FloatTensor_equal_equal (__main__.TestCuda) ... ok
 test_FloatTensor_erf (__main__.TestCuda) ... ok
 test_FloatTensor_erf_ (__main__.TestCuda) ... ok
 test_FloatTensor_erfc (__main__.TestCuda) ... ok
 test_FloatTensor_erfc_ (__main__.TestCuda) ... ok
 test_FloatTensor_erfinv (__main__.TestCuda) ... ok
 test_FloatTensor_erfinv_ (__main__.TestCuda) ... ok
 test_FloatTensor_exp (__main__.TestCuda) ... ok
 test_FloatTensor_exp_ (__main__.TestCuda) ... ok
 test_FloatTensor_expand (__main__.TestCuda) ... ok
 test_FloatTensor_expand_as (__main__.TestCuda) ... ok
 test_FloatTensor_expm1 (__main__.TestCuda) ... ok
 test_FloatTensor_expm1_ (__main__.TestCuda) ... ok
 test_FloatTensor_fill_ (__main__.TestCuda) ... ok
 test_FloatTensor_flip_d0 (__main__.TestCuda) ... ok
 test_FloatTensor_flip_d012 (__main__.TestCuda) ... ok
 test_FloatTensor_flip_d02 (__main__.TestCuda) ... ok
 test_FloatTensor_flip_d20 (__main__.TestCuda) ... ok
 test_FloatTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_FloatTensor_floor (__main__.TestCuda) ... ok
 test_FloatTensor_floor_ (__main__.TestCuda) ... ok
 test_FloatTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_fmod__value (__main__.TestCuda) ... ok
 test_FloatTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_fmod_value (__main__.TestCuda) ... ok
 test_FloatTensor_frac (__main__.TestCuda) ... ok
 test_FloatTensor_frac_ (__main__.TestCuda) ... ok
 test_FloatTensor_ge (__main__.TestCuda) ... ok
 test_FloatTensor_ge_ (__main__.TestCuda) ... ok
 test_FloatTensor_geqrf (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_gt (__main__.TestCuda) ... ok
 test_FloatTensor_gt_ (__main__.TestCuda) ... ok
 test_FloatTensor_inverse (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_is_contiguous (__main__.TestCuda) ... ok
 test_FloatTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_FloatTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_FloatTensor_is_set_to (__main__.TestCuda) ... ok
 test_FloatTensor_le (__main__.TestCuda) ... ok
 test_FloatTensor_le_ (__main__.TestCuda) ... ok
 test_FloatTensor_lerp (__main__.TestCuda) ... ok
 test_FloatTensor_lerp_ (__main__.TestCuda) ... ok
 test_FloatTensor_lgamma (__main__.TestCuda) ... ok
 test_FloatTensor_lgamma_ (__main__.TestCuda) ... ok
 test_FloatTensor_log (__main__.TestCuda) ... ok
 test_FloatTensor_log10 (__main__.TestCuda) ... ok
 test_FloatTensor_log10_ (__main__.TestCuda) ... ok
 test_FloatTensor_log1p (__main__.TestCuda) ... ok
 test_FloatTensor_log1p_ (__main__.TestCuda) ... ok
 test_FloatTensor_log2 (__main__.TestCuda) ... ok
 test_FloatTensor_log2_ (__main__.TestCuda) ... ok
 test_FloatTensor_log_ (__main__.TestCuda) ... ok
 test_FloatTensor_lt (__main__.TestCuda) ... ok
 test_FloatTensor_lt_ (__main__.TestCuda) ... ok
 test_FloatTensor_max (__main__.TestCuda) ... ok
 test_FloatTensor_max_dim (__main__.TestCuda) ... ok
 test_FloatTensor_max_elementwise (__main__.TestCuda) ... ok
 test_FloatTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_mean (__main__.TestCuda) ... ok
 test_FloatTensor_mean_dim (__main__.TestCuda) ... ok
 test_FloatTensor_mean_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_min (__main__.TestCuda) ... ok
 test_FloatTensor_min_dim (__main__.TestCuda) ... ok
 test_FloatTensor_min_elementwise (__main__.TestCuda) ... ok
 test_FloatTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_mode (__main__.TestCuda) ... ok
 test_FloatTensor_mode_dim (__main__.TestCuda) ... ok
 test_FloatTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_mul (__main__.TestCuda) ... ok
 test_FloatTensor_mul_ (__main__.TestCuda) ... ok
 test_FloatTensor_mul__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_mul_scalar (__main__.TestCuda) ... ok
 test_FloatTensor_mul_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_mvlgamma_2d_p=1 (__main__.TestCuda) ... ok
 test_FloatTensor_mvlgamma_2d_p=2 (__main__.TestCuda) ... ok
 test_FloatTensor_mvlgamma__2d_p=1 (__main__.TestCuda) ... ok
 test_FloatTensor_mvlgamma__2d_p=2 (__main__.TestCuda) ... ok
 test_FloatTensor_narrow (__main__.TestCuda) ... ok
 test_FloatTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_ndimension (__main__.TestCuda) ... ok
 test_FloatTensor_ne (__main__.TestCuda) ... ok
 test_FloatTensor_ne_ (__main__.TestCuda) ... ok
 test_FloatTensor_ne__equal (__main__.TestCuda) ... ok
 test_FloatTensor_ne_equal (__main__.TestCuda) ... ok
 test_FloatTensor_neg (__main__.TestCuda) ... ok
 test_FloatTensor_neg_ (__main__.TestCuda) ... ok
 test_FloatTensor_nelement (__main__.TestCuda) ... ok
 test_FloatTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_norm (__main__.TestCuda) ... ok
 test_FloatTensor_norm_3_norm (__main__.TestCuda) ... ok
 test_FloatTensor_norm_3_norm_dim (__main__.TestCuda) ... ok
 test_FloatTensor_norm_3_norm_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_numel (__main__.TestCuda) ... ok
 test_FloatTensor_permute (__main__.TestCuda) ... ok
 test_FloatTensor_pow (__main__.TestCuda) ... ok
 test_FloatTensor_pow_ (__main__.TestCuda) ... ok
 test_FloatTensor_pow__pow-1 (__main__.TestCuda) ... ok
 test_FloatTensor_pow__pow-2 (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_FloatTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_FloatTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_FloatTensor_pow__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_pow_pow-1 (__main__.TestCuda) ... ok
 test_FloatTensor_pow_pow-2 (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_FloatTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_FloatTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_FloatTensor_pow_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_prod (__main__.TestCuda) ... ok
 test_FloatTensor_prod_dim (__main__.TestCuda) ... ok
 test_FloatTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_put__accumulate (__main__.TestCuda) ... ok
 test_FloatTensor_put__empty (__main__.TestCuda) ... ok
 test_FloatTensor_qr_big (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_qr_fat (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_qr_skinny (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_qr_square (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_reciprocal (__main__.TestCuda) ... ok
 test_FloatTensor_reciprocal_ (__main__.TestCuda) ... ok
 test_FloatTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_FloatTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_remainder__value (__main__.TestCuda) ... ok
 test_FloatTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_FloatTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_remainder_value (__main__.TestCuda) ... ok
 test_FloatTensor_renorm_1_5_norm (__main__.TestCuda) ... ok
 test_FloatTensor_renorm_2_norm (__main__.TestCuda) ... ok
 test_FloatTensor_renorm_2_norm_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_renorm__1_5_norm (__main__.TestCuda) ... ok
 test_FloatTensor_renorm__2_norm (__main__.TestCuda) ... ok
 test_FloatTensor_renorm__2_norm_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_repeat (__main__.TestCuda) ... ok
 test_FloatTensor_rot90_default (__main__.TestCuda) ... ok
 test_FloatTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_FloatTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_FloatTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_FloatTensor_round (__main__.TestCuda) ... ok
 test_FloatTensor_round_ (__main__.TestCuda) ... ok
 test_FloatTensor_rsqrt (__main__.TestCuda) ... ok
 test_FloatTensor_rsqrt_ (__main__.TestCuda) ... ok
 test_FloatTensor_sigmoid (__main__.TestCuda) ... ok
 test_FloatTensor_sigmoid_ (__main__.TestCuda) ... ok
 test_FloatTensor_sign (__main__.TestCuda) ... ok
 test_FloatTensor_sign_ (__main__.TestCuda) ... ok
 test_FloatTensor_sin (__main__.TestCuda) ... ok
 test_FloatTensor_sin_ (__main__.TestCuda) ... ok
 test_FloatTensor_sinh (__main__.TestCuda) ... ok
 test_FloatTensor_sinh_ (__main__.TestCuda) ... ok
 test_FloatTensor_size (__main__.TestCuda) ... ok
 test_FloatTensor_size_dim (__main__.TestCuda) ... ok
 test_FloatTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sort (__main__.TestCuda) ... ok
 test_FloatTensor_sort_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_FloatTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_FloatTensor_split (__main__.TestCuda) ... ok
 test_FloatTensor_split_dim (__main__.TestCuda) ... ok
 test_FloatTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sqrt (__main__.TestCuda) ... ok
 test_FloatTensor_sqrt_ (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze_ (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_FloatTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_std (__main__.TestCuda) ... ok
 test_FloatTensor_std_dim (__main__.TestCuda) ... ok
 test_FloatTensor_std_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sub (__main__.TestCuda) ... ok
 test_FloatTensor_sub_ (__main__.TestCuda) ... ok
 test_FloatTensor_sub__tensor (__main__.TestCuda) ... ok
 test_FloatTensor_sub_tensor (__main__.TestCuda) ... ok
 test_FloatTensor_sum (__main__.TestCuda) ... ok
 test_FloatTensor_sum_dim (__main__.TestCuda) ... ok
 test_FloatTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_svd_square (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_svd_square_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_svd_tall_all (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_svd_tall_all_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_svd_tall_some (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_svd_tall_some_col_maj (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_FloatTensor_t (__main__.TestCuda) ... ok
 test_FloatTensor_t_ (__main__.TestCuda) ... ok
 test_FloatTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_FloatTensor_tan (__main__.TestCuda) ... ok
 test_FloatTensor_tan_ (__main__.TestCuda) ... ok
 test_FloatTensor_tanh (__main__.TestCuda) ... ok
 test_FloatTensor_tanh_ (__main__.TestCuda) ... ok
 test_FloatTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_FloatTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_FloatTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_FloatTensor_trace (__main__.TestCuda) ... ok
 test_FloatTensor_transpose (__main__.TestCuda) ... ok
 test_FloatTensor_transpose_ (__main__.TestCuda) ... ok
 test_FloatTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_tril (__main__.TestCuda) ... ok
 test_FloatTensor_tril_ (__main__.TestCuda) ... ok
 test_FloatTensor_tril__negative (__main__.TestCuda) ... ok
 test_FloatTensor_tril__positive (__main__.TestCuda) ... ok
 test_FloatTensor_tril_negative (__main__.TestCuda) ... ok
 test_FloatTensor_tril_positive (__main__.TestCuda) ... ok
 test_FloatTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_FloatTensor_triu (__main__.TestCuda) ... ok
 test_FloatTensor_triu_ (__main__.TestCuda) ... ok
 test_FloatTensor_triu__negative (__main__.TestCuda) ... ok
 test_FloatTensor_triu__positive (__main__.TestCuda) ... ok
 test_FloatTensor_triu_negative (__main__.TestCuda) ... ok
 test_FloatTensor_triu_positive (__main__.TestCuda) ... ok
 test_FloatTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_FloatTensor_trunc (__main__.TestCuda) ... ok
 test_FloatTensor_trunc_ (__main__.TestCuda) ... ok
 test_FloatTensor_unsqueeze (__main__.TestCuda) ... ok
 test_FloatTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_FloatTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_var (__main__.TestCuda) ... ok
 test_FloatTensor_var_dim (__main__.TestCuda) ... ok
 test_FloatTensor_var_neg_dim (__main__.TestCuda) ... ok
 test_FloatTensor_view_as (__main__.TestCuda) ... ok
 test_FloatTensor_view_contiguous (__main__.TestCuda) ... ok
 test_FloatTensor_zero_ (__main__.TestCuda) ... ok
 test_HalfTensor_abs (__main__.TestCuda) ... ok
 test_HalfTensor_abs_ (__main__.TestCuda) ... ok
 test_HalfTensor_acos (__main__.TestCuda) ... ok
 test_HalfTensor_acos_ (__main__.TestCuda) ... ok
 test_HalfTensor_add (__main__.TestCuda) ... ok
 test_HalfTensor_add_ (__main__.TestCuda) ... ok
 test_HalfTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_add__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_add_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm_ (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm__two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addbmm_two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_addcdiv (__main__.TestCuda) ... ok
 test_HalfTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_HalfTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addcmul (__main__.TestCuda) ... ok
 test_HalfTensor_addcmul_ (__main__.TestCuda) ... ok
 test_HalfTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addmm (__main__.TestCuda) ... ok
 test_HalfTensor_addmm_ (__main__.TestCuda) ... ok
 test_HalfTensor_addmm__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addmm__two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_addmm_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addmm_two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_addmv (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addmv_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addmv__scalar (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addmv__two_scalars (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addmv_scalar (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addmv_two_scalars (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_addr (__main__.TestCuda) ... ok
 test_HalfTensor_addr_ (__main__.TestCuda) ... ok
 test_HalfTensor_addr__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addr__two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_addr_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_addr_two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_asin (__main__.TestCuda) ... ok
 test_HalfTensor_asin_ (__main__.TestCuda) ... ok
 test_HalfTensor_atan (__main__.TestCuda) ... ok
 test_HalfTensor_atan2 (__main__.TestCuda) ... ok
 test_HalfTensor_atan2_ (__main__.TestCuda) ... ok
 test_HalfTensor_atan_ (__main__.TestCuda) ... ok
 test_HalfTensor_baddbmm (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_baddbmm_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_baddbmm__scalar (__main__.TestCuda) ... ok
 test_HalfTensor_baddbmm__two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_baddbmm_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_baddbmm_two_scalars (__main__.TestCuda) ... ok
 test_HalfTensor_ceil (__main__.TestCuda) ... ok
 test_HalfTensor_ceil_ (__main__.TestCuda) ... ok
 test_HalfTensor_chunk (__main__.TestCuda) ... ok
 test_HalfTensor_chunk_dim (__main__.TestCuda) ... ok
 test_HalfTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_clone (__main__.TestCuda) ... ok
 test_HalfTensor_contiguous (__main__.TestCuda) ... ok
 test_HalfTensor_cos (__main__.TestCuda) ... ok
 test_HalfTensor_cos_ (__main__.TestCuda) ... ok
 test_HalfTensor_cosh (__main__.TestCuda) ... ok
 test_HalfTensor_cosh_ (__main__.TestCuda) ... ok
 test_HalfTensor_cross (__main__.TestCuda) ... ok
 test_HalfTensor_cumprod (__main__.TestCuda) ... ok
 test_HalfTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_cumsum (__main__.TestCuda) ... ok
 test_HalfTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_digamma (__main__.TestCuda) ... ok
 test_HalfTensor_digamma_ (__main__.TestCuda) ... ok
 test_HalfTensor_dim (__main__.TestCuda) ... ok
 test_HalfTensor_dist (__main__.TestCuda) ... ok
 test_HalfTensor_dist_2_5_norm (__main__.TestCuda) ... ok
 test_HalfTensor_dist_3_norm (__main__.TestCuda) ... ok
 test_HalfTensor_div (__main__.TestCuda) ... ok
 test_HalfTensor_div_ (__main__.TestCuda) ... ok
 test_HalfTensor_div__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_div_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_dot (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_element_size (__main__.TestCuda) ... ok
 test_HalfTensor_eq (__main__.TestCuda) ... ok
 test_HalfTensor_eq_ (__main__.TestCuda) ... ok
 test_HalfTensor_eq__equal (__main__.TestCuda) ... ok
 test_HalfTensor_eq_equal (__main__.TestCuda) ... ok
 test_HalfTensor_equal (__main__.TestCuda) ... ok
 test_HalfTensor_equal_equal (__main__.TestCuda) ... ok
 test_HalfTensor_erf (__main__.TestCuda) ... ok
 test_HalfTensor_erf_ (__main__.TestCuda) ... ok
 test_HalfTensor_erfc (__main__.TestCuda) ... ok
 test_HalfTensor_erfc_ (__main__.TestCuda) ... ok
 test_HalfTensor_erfinv (__main__.TestCuda) ... ok
 test_HalfTensor_erfinv_ (__main__.TestCuda) ... ok
 test_HalfTensor_exp (__main__.TestCuda) ... ok
 test_HalfTensor_exp_ (__main__.TestCuda) ... ok
 test_HalfTensor_expand (__main__.TestCuda) ... ok
 test_HalfTensor_expand_as (__main__.TestCuda) ... ok
 test_HalfTensor_expm1 (__main__.TestCuda) ... ok
 test_HalfTensor_expm1_ (__main__.TestCuda) ... ok
 test_HalfTensor_fill_ (__main__.TestCuda) ... ok
 test_HalfTensor_flip_d0 (__main__.TestCuda) ... ok
 test_HalfTensor_flip_d012 (__main__.TestCuda) ... ok
 test_HalfTensor_flip_d02 (__main__.TestCuda) ... ok
 test_HalfTensor_flip_d20 (__main__.TestCuda) ... ok
 test_HalfTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_HalfTensor_floor (__main__.TestCuda) ... ok
 test_HalfTensor_floor_ (__main__.TestCuda) ... ok
 test_HalfTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_fmod__value (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_fmod_value (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_frac (__main__.TestCuda) ... ok
 test_HalfTensor_frac_ (__main__.TestCuda) ... ok
 test_HalfTensor_ge (__main__.TestCuda) ... ok
 test_HalfTensor_ge_ (__main__.TestCuda) ... ok
 test_HalfTensor_gt (__main__.TestCuda) ... ok
 test_HalfTensor_gt_ (__main__.TestCuda) ... ok
 test_HalfTensor_is_contiguous (__main__.TestCuda) ... ok
 test_HalfTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_HalfTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_HalfTensor_is_set_to (__main__.TestCuda) ... ok
 test_HalfTensor_le (__main__.TestCuda) ... ok
 test_HalfTensor_le_ (__main__.TestCuda) ... ok
 test_HalfTensor_lerp (__main__.TestCuda) ... ok
 test_HalfTensor_lerp_ (__main__.TestCuda) ... ok
 test_HalfTensor_lgamma (__main__.TestCuda) ... ok
 test_HalfTensor_lgamma_ (__main__.TestCuda) ... ok
 test_HalfTensor_log (__main__.TestCuda) ... ok
 test_HalfTensor_log10 (__main__.TestCuda) ... ok
 test_HalfTensor_log10_ (__main__.TestCuda) ... ok
 test_HalfTensor_log1p (__main__.TestCuda) ... ok
 test_HalfTensor_log1p_ (__main__.TestCuda) ... ok
 test_HalfTensor_log2 (__main__.TestCuda) ... ok
 test_HalfTensor_log2_ (__main__.TestCuda) ... ok
 test_HalfTensor_log_ (__main__.TestCuda) ... ok
 test_HalfTensor_lt (__main__.TestCuda) ... ok
 test_HalfTensor_lt_ (__main__.TestCuda) ... ok
 test_HalfTensor_max (__main__.TestCuda) ... ok
 test_HalfTensor_max_dim (__main__.TestCuda) ... ok
 test_HalfTensor_max_elementwise (__main__.TestCuda) ... ok
 test_HalfTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_mean (__main__.TestCuda) ... ok
 test_HalfTensor_mean_dim (__main__.TestCuda) ... ok
 test_HalfTensor_mean_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_min (__main__.TestCuda) ... ok
 test_HalfTensor_min_dim (__main__.TestCuda) ... ok
 test_HalfTensor_min_elementwise (__main__.TestCuda) ... ok
 test_HalfTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_mode (__main__.TestCuda) ... ok
 test_HalfTensor_mode_dim (__main__.TestCuda) ... ok
 test_HalfTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_mul (__main__.TestCuda) ... ok
 test_HalfTensor_mul_ (__main__.TestCuda) ... ok
 test_HalfTensor_mul__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_mul_scalar (__main__.TestCuda) ... ok
 test_HalfTensor_mul_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_narrow (__main__.TestCuda) ... ok
 test_HalfTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_ndimension (__main__.TestCuda) ... ok
 test_HalfTensor_ne (__main__.TestCuda) ... ok
 test_HalfTensor_ne_ (__main__.TestCuda) ... ok
 test_HalfTensor_ne__equal (__main__.TestCuda) ... ok
 test_HalfTensor_ne_equal (__main__.TestCuda) ... ok
 test_HalfTensor_neg (__main__.TestCuda) ... ok
 test_HalfTensor_neg_ (__main__.TestCuda) ... ok
 test_HalfTensor_nelement (__main__.TestCuda) ... ok
 test_HalfTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_norm (__main__.TestCuda) ... ok
 test_HalfTensor_norm_3_norm (__main__.TestCuda) ... ok
 test_HalfTensor_norm_3_norm_dim (__main__.TestCuda) ... ok
 test_HalfTensor_norm_3_norm_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_numel (__main__.TestCuda) ... ok
 test_HalfTensor_permute (__main__.TestCuda) ... ok
 test_HalfTensor_pow (__main__.TestCuda) ... ok
 test_HalfTensor_pow_ (__main__.TestCuda) ... ok
 test_HalfTensor_pow__pow-1 (__main__.TestCuda) ... ok
 test_HalfTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_HalfTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_HalfTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_HalfTensor_pow__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_pow_pow-1 (__main__.TestCuda) ... ok
 test_HalfTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_HalfTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_HalfTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_HalfTensor_pow_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_prod (__main__.TestCuda) ... ok
 test_HalfTensor_prod_dim (__main__.TestCuda) ... ok
 test_HalfTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_put__accumulate (__main__.TestCuda) ... ok
 test_HalfTensor_put__empty (__main__.TestCuda) ... ok
 test_HalfTensor_reciprocal (__main__.TestCuda) ... ok
 test_HalfTensor_reciprocal_ (__main__.TestCuda) ... ok
 test_HalfTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_remainder__value (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_remainder_value (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_renorm_1_5_norm (__main__.TestCuda) ... ok
 test_HalfTensor_renorm_2_norm (__main__.TestCuda) ... ok
 test_HalfTensor_renorm_2_norm_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_renorm__1_5_norm (__main__.TestCuda) ... ok
 test_HalfTensor_renorm__2_norm (__main__.TestCuda) ... ok
 test_HalfTensor_renorm__2_norm_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_repeat (__main__.TestCuda) ... ok
 test_HalfTensor_rot90_default (__main__.TestCuda) ... ok
 test_HalfTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_HalfTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_HalfTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_HalfTensor_round (__main__.TestCuda) ... ok
 test_HalfTensor_round_ (__main__.TestCuda) ... ok
 test_HalfTensor_rsqrt (__main__.TestCuda) ... ok
 test_HalfTensor_rsqrt_ (__main__.TestCuda) ... ok
 test_HalfTensor_sigmoid (__main__.TestCuda) ... ok
 test_HalfTensor_sigmoid_ (__main__.TestCuda) ... ok
 test_HalfTensor_sign (__main__.TestCuda) ... ok
 test_HalfTensor_sign_ (__main__.TestCuda) ... ok
 test_HalfTensor_sin (__main__.TestCuda) ... ok
 test_HalfTensor_sin_ (__main__.TestCuda) ... ok
 test_HalfTensor_sinh (__main__.TestCuda) ... ok
 test_HalfTensor_sinh_ (__main__.TestCuda) ... ok
 test_HalfTensor_size (__main__.TestCuda) ... ok
 test_HalfTensor_size_dim (__main__.TestCuda) ... ok
 test_HalfTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sort (__main__.TestCuda) ... ok
 test_HalfTensor_sort_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_HalfTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_HalfTensor_split (__main__.TestCuda) ... ok
 test_HalfTensor_split_dim (__main__.TestCuda) ... ok
 test_HalfTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sqrt (__main__.TestCuda) ... ok
 test_HalfTensor_sqrt_ (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze_ (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_HalfTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_std (__main__.TestCuda) ... ok
 test_HalfTensor_std_dim (__main__.TestCuda) ... ok
 test_HalfTensor_std_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sub (__main__.TestCuda) ... ok
 test_HalfTensor_sub_ (__main__.TestCuda) ... ok
 test_HalfTensor_sub__tensor (__main__.TestCuda) ... ok
 test_HalfTensor_sub_tensor (__main__.TestCuda) ... ok
 test_HalfTensor_sum (__main__.TestCuda) ... ok
 test_HalfTensor_sum_dim (__main__.TestCuda) ... ok
 test_HalfTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_t (__main__.TestCuda) ... ok
 test_HalfTensor_t_ (__main__.TestCuda) ... ok
 test_HalfTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_tan (__main__.TestCuda) ... ok
 test_HalfTensor_tan_ (__main__.TestCuda) ... ok
 test_HalfTensor_tanh (__main__.TestCuda) ... ok
 test_HalfTensor_tanh_ (__main__.TestCuda) ... ok
 test_HalfTensor_topk_dim_desc_sort (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_topk_dim_sort (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_topk_neg_dim_sort (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_HalfTensor_trace (__main__.TestCuda) ... ok
 test_HalfTensor_transpose (__main__.TestCuda) ... ok
 test_HalfTensor_transpose_ (__main__.TestCuda) ... ok
 test_HalfTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_tril (__main__.TestCuda) ... ok
 test_HalfTensor_tril_ (__main__.TestCuda) ... ok
 test_HalfTensor_tril__negative (__main__.TestCuda) ... ok
 test_HalfTensor_tril__positive (__main__.TestCuda) ... ok
 test_HalfTensor_tril_negative (__main__.TestCuda) ... ok
 test_HalfTensor_tril_positive (__main__.TestCuda) ... ok
 test_HalfTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_HalfTensor_triu (__main__.TestCuda) ... ok
 test_HalfTensor_triu_ (__main__.TestCuda) ... ok
 test_HalfTensor_triu__negative (__main__.TestCuda) ... ok
 test_HalfTensor_triu__positive (__main__.TestCuda) ... ok
 test_HalfTensor_triu_negative (__main__.TestCuda) ... ok
 test_HalfTensor_triu_positive (__main__.TestCuda) ... ok
 test_HalfTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_HalfTensor_trunc (__main__.TestCuda) ... ok
 test_HalfTensor_trunc_ (__main__.TestCuda) ... ok
 test_HalfTensor_unsqueeze (__main__.TestCuda) ... ok
 test_HalfTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_HalfTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_var (__main__.TestCuda) ... ok
 test_HalfTensor_var_dim (__main__.TestCuda) ... ok
 test_HalfTensor_var_neg_dim (__main__.TestCuda) ... ok
 test_HalfTensor_view_as (__main__.TestCuda) ... ok
 test_HalfTensor_view_contiguous (__main__.TestCuda) ... ok
 test_HalfTensor_zero_ (__main__.TestCuda) ... ok
 test_IntTensor___lshift__ (__main__.TestCuda) ... ok
 test_IntTensor___rshift__ (__main__.TestCuda) ... ok
 test_IntTensor_abs (__main__.TestCuda) ... ok
 test_IntTensor_abs_ (__main__.TestCuda) ... ok
 test_IntTensor_add (__main__.TestCuda) ... ok
 test_IntTensor_add_ (__main__.TestCuda) ... ok
 test_IntTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_IntTensor_add__tensor (__main__.TestCuda) ... ok
 test_IntTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_IntTensor_add_tensor (__main__.TestCuda) ... ok
 test_IntTensor_addbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addcdiv (__main__.TestCuda) ... ok
 test_IntTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_IntTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_IntTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_IntTensor_addcmul (__main__.TestCuda) ... ok
 test_IntTensor_addcmul_ (__main__.TestCuda) ... ok
 test_IntTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_IntTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_IntTensor_addmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addmv_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_addr_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_baddbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_IntTensor_chunk (__main__.TestCuda) ... ok
 test_IntTensor_chunk_dim (__main__.TestCuda) ... ok
 test_IntTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_clamp (__main__.TestCuda) ... ok
 test_IntTensor_clamp_ (__main__.TestCuda) ... ok
 test_IntTensor_clone (__main__.TestCuda) ... ok
 test_IntTensor_contiguous (__main__.TestCuda) ... ok
 test_IntTensor_cross (__main__.TestCuda) ... ok
 test_IntTensor_cumprod (__main__.TestCuda) ... ok
 test_IntTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_cumsum (__main__.TestCuda) ... ok
 test_IntTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_dim (__main__.TestCuda) ... ok
 test_IntTensor_div (__main__.TestCuda) ... ok
 test_IntTensor_div_ (__main__.TestCuda) ... ok
 test_IntTensor_div__tensor (__main__.TestCuda) ... ok
 test_IntTensor_div_tensor (__main__.TestCuda) ... ok
 test_IntTensor_element_size (__main__.TestCuda) ... ok
 test_IntTensor_eq (__main__.TestCuda) ... ok
 test_IntTensor_eq_ (__main__.TestCuda) ... ok
 test_IntTensor_eq__equal (__main__.TestCuda) ... ok
 test_IntTensor_eq_equal (__main__.TestCuda) ... ok
 test_IntTensor_equal (__main__.TestCuda) ... ok
 test_IntTensor_equal_equal (__main__.TestCuda) ... ok
 test_IntTensor_expand (__main__.TestCuda) ... ok
 test_IntTensor_expand_as (__main__.TestCuda) ... ok
 test_IntTensor_fill_ (__main__.TestCuda) ... ok
 test_IntTensor_flip_d0 (__main__.TestCuda) ... ok
 test_IntTensor_flip_d012 (__main__.TestCuda) ... ok
 test_IntTensor_flip_d02 (__main__.TestCuda) ... ok
 test_IntTensor_flip_d20 (__main__.TestCuda) ... ok
 test_IntTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_IntTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_IntTensor_fmod__value (__main__.TestCuda) ... ok
 test_IntTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_IntTensor_fmod_value (__main__.TestCuda) ... ok
 test_IntTensor_ge (__main__.TestCuda) ... ok
 test_IntTensor_ge_ (__main__.TestCuda) ... ok
 test_IntTensor_gt (__main__.TestCuda) ... ok
 test_IntTensor_gt_ (__main__.TestCuda) ... ok
 test_IntTensor_is_contiguous (__main__.TestCuda) ... ok
 test_IntTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_IntTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_IntTensor_is_set_to (__main__.TestCuda) ... ok
 test_IntTensor_le (__main__.TestCuda) ... ok
 test_IntTensor_le_ (__main__.TestCuda) ... ok
 test_IntTensor_lt (__main__.TestCuda) ... ok
 test_IntTensor_lt_ (__main__.TestCuda) ... ok
 test_IntTensor_max (__main__.TestCuda) ... ok
 test_IntTensor_max_dim (__main__.TestCuda) ... ok
 test_IntTensor_max_elementwise (__main__.TestCuda) ... ok
 test_IntTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_min (__main__.TestCuda) ... ok
 test_IntTensor_min_dim (__main__.TestCuda) ... ok
 test_IntTensor_min_elementwise (__main__.TestCuda) ... ok
 test_IntTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_mode (__main__.TestCuda) ... ok
 test_IntTensor_mode_dim (__main__.TestCuda) ... ok
 test_IntTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_mul (__main__.TestCuda) ... ok
 test_IntTensor_mul_ (__main__.TestCuda) ... ok
 test_IntTensor_mul__tensor (__main__.TestCuda) ... ok
 test_IntTensor_mul_scalar (__main__.TestCuda) ... ok
 test_IntTensor_mul_tensor (__main__.TestCuda) ... ok
 test_IntTensor_narrow (__main__.TestCuda) ... ok
 test_IntTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_ndimension (__main__.TestCuda) ... ok
 test_IntTensor_ne (__main__.TestCuda) ... ok
 test_IntTensor_ne_ (__main__.TestCuda) ... ok
 test_IntTensor_ne__equal (__main__.TestCuda) ... ok
 test_IntTensor_ne_equal (__main__.TestCuda) ... ok
 test_IntTensor_nelement (__main__.TestCuda) ... ok
 test_IntTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_IntTensor_numel (__main__.TestCuda) ... ok
 test_IntTensor_permute (__main__.TestCuda) ... ok
 test_IntTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_IntTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_IntTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_IntTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_IntTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_IntTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_IntTensor_prod (__main__.TestCuda) ... ok
 test_IntTensor_prod_dim (__main__.TestCuda) ... ok
 test_IntTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_IntTensor_put__accumulate (__main__.TestCuda) ... ok
 test_IntTensor_put__empty (__main__.TestCuda) ... ok
 test_IntTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_IntTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_IntTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_IntTensor_remainder__value (__main__.TestCuda) ... ok
 test_IntTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_IntTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_IntTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_IntTensor_remainder_value (__main__.TestCuda) ... ok
 test_IntTensor_repeat (__main__.TestCuda) ... ok
 test_IntTensor_rot90_default (__main__.TestCuda) ... ok
 test_IntTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_IntTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_IntTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_IntTensor_sign (__main__.TestCuda) ... ok
 test_IntTensor_sign_ (__main__.TestCuda) ... ok
 test_IntTensor_size (__main__.TestCuda) ... ok
 test_IntTensor_size_dim (__main__.TestCuda) ... ok
 test_IntTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_sort (__main__.TestCuda) ... ok
 test_IntTensor_sort_dim (__main__.TestCuda) ... ok
 test_IntTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_IntTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_IntTensor_split (__main__.TestCuda) ... ok
 test_IntTensor_split_dim (__main__.TestCuda) ... ok
 test_IntTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_squeeze (__main__.TestCuda) ... ok
 test_IntTensor_squeeze_ (__main__.TestCuda) ... ok
 test_IntTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_IntTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_IntTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_sub (__main__.TestCuda) ... ok
 test_IntTensor_sub_ (__main__.TestCuda) ... ok
 test_IntTensor_sub__tensor (__main__.TestCuda) ... ok
 test_IntTensor_sub_tensor (__main__.TestCuda) ... ok
 test_IntTensor_sum (__main__.TestCuda) ... ok
 test_IntTensor_sum_dim (__main__.TestCuda) ... ok
 test_IntTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_t (__main__.TestCuda) ... ok
 test_IntTensor_t_ (__main__.TestCuda) ... ok
 test_IntTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_IntTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_IntTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_IntTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_IntTensor_trace (__main__.TestCuda) ... ok
 test_IntTensor_transpose (__main__.TestCuda) ... ok
 test_IntTensor_transpose_ (__main__.TestCuda) ... ok
 test_IntTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_tril (__main__.TestCuda) ... ok
 test_IntTensor_tril_ (__main__.TestCuda) ... ok
 test_IntTensor_tril__negative (__main__.TestCuda) ... ok
 test_IntTensor_tril__positive (__main__.TestCuda) ... ok
 test_IntTensor_tril_negative (__main__.TestCuda) ... ok
 test_IntTensor_tril_positive (__main__.TestCuda) ... ok
 test_IntTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_IntTensor_triu (__main__.TestCuda) ... ok
 test_IntTensor_triu_ (__main__.TestCuda) ... ok
 test_IntTensor_triu__negative (__main__.TestCuda) ... ok
 test_IntTensor_triu__positive (__main__.TestCuda) ... ok
 test_IntTensor_triu_negative (__main__.TestCuda) ... ok
 test_IntTensor_triu_positive (__main__.TestCuda) ... ok
 test_IntTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_IntTensor_unsqueeze (__main__.TestCuda) ... ok
 test_IntTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_IntTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_IntTensor_view_as (__main__.TestCuda) ... ok
 test_IntTensor_view_contiguous (__main__.TestCuda) ... ok
 test_IntTensor_zero_ (__main__.TestCuda) ... ok
 test_LongTensor___lshift__ (__main__.TestCuda) ... ok
 test_LongTensor___rshift__ (__main__.TestCuda) ... ok
 test_LongTensor_abs (__main__.TestCuda) ... ok
 test_LongTensor_abs_ (__main__.TestCuda) ... ok
 test_LongTensor_add (__main__.TestCuda) ... ok
 test_LongTensor_add_ (__main__.TestCuda) ... ok
 test_LongTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_LongTensor_add__tensor (__main__.TestCuda) ... ok
 test_LongTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_LongTensor_add_tensor (__main__.TestCuda) ... ok
 test_LongTensor_addbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addcdiv (__main__.TestCuda) ... ok
 test_LongTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_LongTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_LongTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_LongTensor_addcmul (__main__.TestCuda) ... ok
 test_LongTensor_addcmul_ (__main__.TestCuda) ... ok
 test_LongTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_LongTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_LongTensor_addmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addmv_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_addr_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_baddbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_LongTensor_chunk (__main__.TestCuda) ... ok
 test_LongTensor_chunk_dim (__main__.TestCuda) ... ok
 test_LongTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_clamp (__main__.TestCuda) ... ok
 test_LongTensor_clamp_ (__main__.TestCuda) ... ok
 test_LongTensor_clone (__main__.TestCuda) ... ok
 test_LongTensor_contiguous (__main__.TestCuda) ... ok
 test_LongTensor_cross (__main__.TestCuda) ... ok
 test_LongTensor_cumprod (__main__.TestCuda) ... ok
 test_LongTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_cumsum (__main__.TestCuda) ... ok
 test_LongTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_dim (__main__.TestCuda) ... ok
 test_LongTensor_div (__main__.TestCuda) ... ok
 test_LongTensor_div_ (__main__.TestCuda) ... ok
 test_LongTensor_div__tensor (__main__.TestCuda) ... ok
 test_LongTensor_div_tensor (__main__.TestCuda) ... ok
 test_LongTensor_element_size (__main__.TestCuda) ... ok
 test_LongTensor_eq (__main__.TestCuda) ... ok
 test_LongTensor_eq_ (__main__.TestCuda) ... ok
 test_LongTensor_eq__equal (__main__.TestCuda) ... ok
 test_LongTensor_eq_equal (__main__.TestCuda) ... ok
 test_LongTensor_equal (__main__.TestCuda) ... ok
 test_LongTensor_equal_equal (__main__.TestCuda) ... ok
 test_LongTensor_expand (__main__.TestCuda) ... ok
 test_LongTensor_expand_as (__main__.TestCuda) ... ok
 test_LongTensor_fill_ (__main__.TestCuda) ... ok
 test_LongTensor_flip_d0 (__main__.TestCuda) ... ok
 test_LongTensor_flip_d012 (__main__.TestCuda) ... ok
 test_LongTensor_flip_d02 (__main__.TestCuda) ... ok
 test_LongTensor_flip_d20 (__main__.TestCuda) ... ok
 test_LongTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_LongTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_LongTensor_fmod__value (__main__.TestCuda) ... ok
 test_LongTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_LongTensor_fmod_value (__main__.TestCuda) ... ok
 test_LongTensor_ge (__main__.TestCuda) ... ok
 test_LongTensor_ge_ (__main__.TestCuda) ... ok
 test_LongTensor_gt (__main__.TestCuda) ... ok
 test_LongTensor_gt_ (__main__.TestCuda) ... ok
 test_LongTensor_is_contiguous (__main__.TestCuda) ... ok
 test_LongTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_LongTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_LongTensor_is_set_to (__main__.TestCuda) ... ok
 test_LongTensor_le (__main__.TestCuda) ... ok
 test_LongTensor_le_ (__main__.TestCuda) ... ok
 test_LongTensor_lt (__main__.TestCuda) ... ok
 test_LongTensor_lt_ (__main__.TestCuda) ... ok
 test_LongTensor_max (__main__.TestCuda) ... ok
 test_LongTensor_max_dim (__main__.TestCuda) ... ok
 test_LongTensor_max_elementwise (__main__.TestCuda) ... ok
 test_LongTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_min (__main__.TestCuda) ... ok
 test_LongTensor_min_dim (__main__.TestCuda) ... ok
 test_LongTensor_min_elementwise (__main__.TestCuda) ... ok
 test_LongTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_mode (__main__.TestCuda) ... ok
 test_LongTensor_mode_dim (__main__.TestCuda) ... ok
 test_LongTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_mul (__main__.TestCuda) ... ok
 test_LongTensor_mul_ (__main__.TestCuda) ... ok
 test_LongTensor_mul__tensor (__main__.TestCuda) ... ok
 test_LongTensor_mul_scalar (__main__.TestCuda) ... ok
 test_LongTensor_mul_tensor (__main__.TestCuda) ... ok
 test_LongTensor_narrow (__main__.TestCuda) ... ok
 test_LongTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_ndimension (__main__.TestCuda) ... ok
 test_LongTensor_ne (__main__.TestCuda) ... ok
 test_LongTensor_ne_ (__main__.TestCuda) ... ok
 test_LongTensor_ne__equal (__main__.TestCuda) ... ok
 test_LongTensor_ne_equal (__main__.TestCuda) ... ok
 test_LongTensor_nelement (__main__.TestCuda) ... ok
 test_LongTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_LongTensor_numel (__main__.TestCuda) ... ok
 test_LongTensor_permute (__main__.TestCuda) ... ok
 test_LongTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_LongTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_LongTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_LongTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_LongTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_LongTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_LongTensor_prod (__main__.TestCuda) ... ok
 test_LongTensor_prod_dim (__main__.TestCuda) ... ok
 test_LongTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_LongTensor_put__accumulate (__main__.TestCuda) ... ok
 test_LongTensor_put__empty (__main__.TestCuda) ... ok
 test_LongTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_LongTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_LongTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_LongTensor_remainder__value (__main__.TestCuda) ... ok
 test_LongTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_LongTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_LongTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_LongTensor_remainder_value (__main__.TestCuda) ... ok
 test_LongTensor_repeat (__main__.TestCuda) ... ok
 test_LongTensor_rot90_default (__main__.TestCuda) ... ok
 test_LongTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_LongTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_LongTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_LongTensor_sign (__main__.TestCuda) ... ok
 test_LongTensor_sign_ (__main__.TestCuda) ... ok
 test_LongTensor_size (__main__.TestCuda) ... ok
 test_LongTensor_size_dim (__main__.TestCuda) ... ok
 test_LongTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_sort (__main__.TestCuda) ... ok
 test_LongTensor_sort_dim (__main__.TestCuda) ... ok
 test_LongTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_LongTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_LongTensor_split (__main__.TestCuda) ... ok
 test_LongTensor_split_dim (__main__.TestCuda) ... ok
 test_LongTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_squeeze (__main__.TestCuda) ... ok
 test_LongTensor_squeeze_ (__main__.TestCuda) ... ok
 test_LongTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_LongTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_LongTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_sub (__main__.TestCuda) ... ok
 test_LongTensor_sub_ (__main__.TestCuda) ... ok
 test_LongTensor_sub__tensor (__main__.TestCuda) ... ok
 test_LongTensor_sub_tensor (__main__.TestCuda) ... ok
 test_LongTensor_sum (__main__.TestCuda) ... ok
 test_LongTensor_sum_dim (__main__.TestCuda) ... ok
 test_LongTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_t (__main__.TestCuda) ... ok
 test_LongTensor_t_ (__main__.TestCuda) ... ok
 test_LongTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_LongTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_LongTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_LongTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_LongTensor_trace (__main__.TestCuda) ... ok
 test_LongTensor_transpose (__main__.TestCuda) ... ok
 test_LongTensor_transpose_ (__main__.TestCuda) ... ok
 test_LongTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_tril (__main__.TestCuda) ... ok
 test_LongTensor_tril_ (__main__.TestCuda) ... ok
 test_LongTensor_tril__negative (__main__.TestCuda) ... ok
 test_LongTensor_tril__positive (__main__.TestCuda) ... ok
 test_LongTensor_tril_negative (__main__.TestCuda) ... ok
 test_LongTensor_tril_positive (__main__.TestCuda) ... ok
 test_LongTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_LongTensor_triu (__main__.TestCuda) ... ok
 test_LongTensor_triu_ (__main__.TestCuda) ... ok
 test_LongTensor_triu__negative (__main__.TestCuda) ... ok
 test_LongTensor_triu__positive (__main__.TestCuda) ... ok
 test_LongTensor_triu_negative (__main__.TestCuda) ... ok
 test_LongTensor_triu_positive (__main__.TestCuda) ... ok
 test_LongTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_LongTensor_unsqueeze (__main__.TestCuda) ... ok
 test_LongTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_LongTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_LongTensor_view_as (__main__.TestCuda) ... ok
 test_LongTensor_view_contiguous (__main__.TestCuda) ... ok
 test_LongTensor_zero_ (__main__.TestCuda) ... ok
 test_ShortTensor___lshift__ (__main__.TestCuda) ... ok
 test_ShortTensor___rshift__ (__main__.TestCuda) ... ok
 test_ShortTensor_abs (__main__.TestCuda) ... ok
 test_ShortTensor_abs_ (__main__.TestCuda) ... ok
 test_ShortTensor_add (__main__.TestCuda) ... ok
 test_ShortTensor_add_ (__main__.TestCuda) ... ok
 test_ShortTensor_add__scalar_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_add__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_add_scalar_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_add_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_addbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addcdiv (__main__.TestCuda) ... ok
 test_ShortTensor_addcdiv_ (__main__.TestCuda) ... ok
 test_ShortTensor_addcdiv__scalar (__main__.TestCuda) ... ok
 test_ShortTensor_addcdiv_scalar (__main__.TestCuda) ... ok
 test_ShortTensor_addcmul (__main__.TestCuda) ... ok
 test_ShortTensor_addcmul_ (__main__.TestCuda) ... ok
 test_ShortTensor_addcmul__scalar (__main__.TestCuda) ... ok
 test_ShortTensor_addcmul_scalar (__main__.TestCuda) ... ok
 test_ShortTensor_addmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addmv_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_addr_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm_ (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm__scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm__two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm_scalar (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_baddbmm_two_scalars (__main__.TestCuda) ... skipped 'unimplemented data type'
 test_ShortTensor_chunk (__main__.TestCuda) ... ok
 test_ShortTensor_chunk_dim (__main__.TestCuda) ... ok
 test_ShortTensor_chunk_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_clamp (__main__.TestCuda) ... ok
 test_ShortTensor_clamp_ (__main__.TestCuda) ... ok
 test_ShortTensor_clone (__main__.TestCuda) ... ok
 test_ShortTensor_contiguous (__main__.TestCuda) ... ok
 test_ShortTensor_cross (__main__.TestCuda) ... ok
 test_ShortTensor_cumprod (__main__.TestCuda) ... ok
 test_ShortTensor_cumprod_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_cumsum (__main__.TestCuda) ... ok
 test_ShortTensor_cumsum_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_dim (__main__.TestCuda) ... ok
 test_ShortTensor_div (__main__.TestCuda) ... ok
 test_ShortTensor_div_ (__main__.TestCuda) ... ok
 test_ShortTensor_div__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_div_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_element_size (__main__.TestCuda) ... ok
 test_ShortTensor_eq (__main__.TestCuda) ... ok
 test_ShortTensor_eq_ (__main__.TestCuda) ... ok
 test_ShortTensor_eq__equal (__main__.TestCuda) ... ok
 test_ShortTensor_eq_equal (__main__.TestCuda) ... ok
 test_ShortTensor_equal (__main__.TestCuda) ... ok
 test_ShortTensor_equal_equal (__main__.TestCuda) ... ok
 test_ShortTensor_expand (__main__.TestCuda) ... ok
 test_ShortTensor_expand_as (__main__.TestCuda) ... ok
 test_ShortTensor_fill_ (__main__.TestCuda) ... ok
 test_ShortTensor_flip_d0 (__main__.TestCuda) ... ok
 test_ShortTensor_flip_d012 (__main__.TestCuda) ... ok
 test_ShortTensor_flip_d02 (__main__.TestCuda) ... ok
 test_ShortTensor_flip_d20 (__main__.TestCuda) ... ok
 test_ShortTensor_flip_neg_d (__main__.TestCuda) ... ok
 test_ShortTensor_fmod__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_fmod__value (__main__.TestCuda) ... ok
 test_ShortTensor_fmod_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_fmod_value (__main__.TestCuda) ... ok
 test_ShortTensor_ge (__main__.TestCuda) ... ok
 test_ShortTensor_ge_ (__main__.TestCuda) ... ok
 test_ShortTensor_gt (__main__.TestCuda) ... ok
 test_ShortTensor_gt_ (__main__.TestCuda) ... ok
 test_ShortTensor_is_contiguous (__main__.TestCuda) ... ok
 test_ShortTensor_is_same_size_negative (__main__.TestCuda) ... ok
 test_ShortTensor_is_same_size_positive (__main__.TestCuda) ... ok
 test_ShortTensor_is_set_to (__main__.TestCuda) ... ok
 test_ShortTensor_le (__main__.TestCuda) ... ok
 test_ShortTensor_le_ (__main__.TestCuda) ... ok
 test_ShortTensor_lt (__main__.TestCuda) ... ok
 test_ShortTensor_lt_ (__main__.TestCuda) ... ok
 test_ShortTensor_max (__main__.TestCuda) ... ok
 test_ShortTensor_max_dim (__main__.TestCuda) ... ok
 test_ShortTensor_max_elementwise (__main__.TestCuda) ... ok
 test_ShortTensor_max_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_min (__main__.TestCuda) ... ok
 test_ShortTensor_min_dim (__main__.TestCuda) ... ok
 test_ShortTensor_min_elementwise (__main__.TestCuda) ... ok
 test_ShortTensor_min_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_mode (__main__.TestCuda) ... ok
 test_ShortTensor_mode_dim (__main__.TestCuda) ... ok
 test_ShortTensor_mode_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_mul (__main__.TestCuda) ... ok
 test_ShortTensor_mul_ (__main__.TestCuda) ... ok
 test_ShortTensor_mul__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_mul_scalar (__main__.TestCuda) ... ok
 test_ShortTensor_mul_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_narrow (__main__.TestCuda) ... ok
 test_ShortTensor_narrow_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_ndimension (__main__.TestCuda) ... ok
 test_ShortTensor_ne (__main__.TestCuda) ... ok
 test_ShortTensor_ne_ (__main__.TestCuda) ... ok
 test_ShortTensor_ne__equal (__main__.TestCuda) ... ok
 test_ShortTensor_ne_equal (__main__.TestCuda) ... ok
 test_ShortTensor_nelement (__main__.TestCuda) ... ok
 test_ShortTensor_nonzero (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ShortTensor_numel (__main__.TestCuda) ... ok
 test_ShortTensor_permute (__main__.TestCuda) ... ok
 test_ShortTensor_pow__pow1 (__main__.TestCuda) ... ok
 test_ShortTensor_pow__pow2 (__main__.TestCuda) ... ok
 test_ShortTensor_pow__pow3 (__main__.TestCuda) ... ok
 test_ShortTensor_pow_pow1 (__main__.TestCuda) ... ok
 test_ShortTensor_pow_pow2 (__main__.TestCuda) ... ok
 test_ShortTensor_pow_pow3 (__main__.TestCuda) ... ok
 test_ShortTensor_prod (__main__.TestCuda) ... ok
 test_ShortTensor_prod_dim (__main__.TestCuda) ... ok
 test_ShortTensor_prod_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_put_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ShortTensor_put__accumulate (__main__.TestCuda) ... ok
 test_ShortTensor_put__empty (__main__.TestCuda) ... ok
 test_ShortTensor_remainder__negative_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_remainder__negative_value (__main__.TestCuda) ... ok
 test_ShortTensor_remainder__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_remainder__value (__main__.TestCuda) ... ok
 test_ShortTensor_remainder_negative_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_remainder_negative_value (__main__.TestCuda) ... ok
 test_ShortTensor_remainder_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_remainder_value (__main__.TestCuda) ... ok
 test_ShortTensor_repeat (__main__.TestCuda) ... ok
 test_ShortTensor_rot90_default (__main__.TestCuda) ... ok
 test_ShortTensor_rot90_k1_d01 (__main__.TestCuda) ... ok
 test_ShortTensor_rot90_k1_d12 (__main__.TestCuda) ... ok
 test_ShortTensor_rot90_k1_neg_d (__main__.TestCuda) ... ok
 test_ShortTensor_sign (__main__.TestCuda) ... ok
 test_ShortTensor_sign_ (__main__.TestCuda) ... ok
 test_ShortTensor_size (__main__.TestCuda) ... ok
 test_ShortTensor_size_dim (__main__.TestCuda) ... ok
 test_ShortTensor_size_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_sort (__main__.TestCuda) ... ok
 test_ShortTensor_sort_dim (__main__.TestCuda) ... ok
 test_ShortTensor_sort_dim_descending (__main__.TestCuda) ... ok
 test_ShortTensor_sort_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_sort_neg_dim_descending (__main__.TestCuda) ... ok
 test_ShortTensor_split (__main__.TestCuda) ... ok
 test_ShortTensor_split_dim (__main__.TestCuda) ... ok
 test_ShortTensor_split_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze_ (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze__dim (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze__neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze_dim (__main__.TestCuda) ... ok
 test_ShortTensor_squeeze_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_sub (__main__.TestCuda) ... ok
 test_ShortTensor_sub_ (__main__.TestCuda) ... ok
 test_ShortTensor_sub__tensor (__main__.TestCuda) ... ok
 test_ShortTensor_sub_tensor (__main__.TestCuda) ... ok
 test_ShortTensor_sum (__main__.TestCuda) ... ok
 test_ShortTensor_sum_dim (__main__.TestCuda) ... ok
 test_ShortTensor_sum_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_t (__main__.TestCuda) ... ok
 test_ShortTensor_t_ (__main__.TestCuda) ... ok
 test_ShortTensor_take (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_ShortTensor_topk_dim_desc_sort (__main__.TestCuda) ... ok
 test_ShortTensor_topk_dim_sort (__main__.TestCuda) ... ok
 test_ShortTensor_topk_neg_dim_sort (__main__.TestCuda) ... ok
 test_ShortTensor_trace (__main__.TestCuda) ... ok
 test_ShortTensor_transpose (__main__.TestCuda) ... ok
 test_ShortTensor_transpose_ (__main__.TestCuda) ... ok
 test_ShortTensor_transpose__neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_transpose_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_tril (__main__.TestCuda) ... ok
 test_ShortTensor_tril_ (__main__.TestCuda) ... ok
 test_ShortTensor_tril__negative (__main__.TestCuda) ... ok
 test_ShortTensor_tril__positive (__main__.TestCuda) ... ok
 test_ShortTensor_tril_negative (__main__.TestCuda) ... ok
 test_ShortTensor_tril_positive (__main__.TestCuda) ... ok
 test_ShortTensor_tril_zero_stride (__main__.TestCuda) ... ok
 test_ShortTensor_triu (__main__.TestCuda) ... ok
 test_ShortTensor_triu_ (__main__.TestCuda) ... ok
 test_ShortTensor_triu__negative (__main__.TestCuda) ... ok
 test_ShortTensor_triu__positive (__main__.TestCuda) ... ok
 test_ShortTensor_triu_negative (__main__.TestCuda) ... ok
 test_ShortTensor_triu_positive (__main__.TestCuda) ... ok
 test_ShortTensor_triu_zero_stride (__main__.TestCuda) ... ok
 test_ShortTensor_unsqueeze (__main__.TestCuda) ... ok
 test_ShortTensor_unsqueeze_ (__main__.TestCuda) ... ok
 test_ShortTensor_unsqueeze__neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_unsqueeze_neg_dim (__main__.TestCuda) ... ok
 test_ShortTensor_view_as (__main__.TestCuda) ... ok
 test_ShortTensor_view_contiguous (__main__.TestCuda) ... ok
 test_ShortTensor_zero_ (__main__.TestCuda) ... ok
 test_advancedindex (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_advancedindex_big (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_advancedindex_mixed_cpu_cuda (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_arange (__main__.TestCuda) ... ok
 test_arithmetic_large_tensor (__main__.TestCuda) ... ok
 test_autogpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_bernoulli (__main__.TestCuda) ... ok
 test_bincount_cuda (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_broadcast (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_broadcast_batched_matmul (__main__.TestCuda) ... ok
 test_broadcast_coalesced (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_broadcast_coalesced_dense_only (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_broadcast_cpu (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_broadcast_fused_matmul (__main__.TestCuda) ... ok
 test_broadcast_gpu (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_btrifact (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_btrisolve (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_caching_pinned_memory (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_caching_pinned_memory_multi_gpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_cat (__main__.TestCuda) ... ok
 test_cat_autogpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_cat_bad_input_sizes (__main__.TestCuda) ... ok
 test_cat_empty (__main__.TestCuda) ... ok
 test_cat_empty_legacy (__main__.TestCuda) ... ok
 test_chain_matmul (__main__.TestCuda) ... ok
 test_contiguous (__main__.TestCuda) ... ok
 test_copy_device (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_cuda_memory_leak_detection (__main__.TestCuda) ... ok
 test_cuda_memory_leak_detection_propagates_errors (__main__.TestCuda) ... ok
 test_cuda_set_device (__main__.TestCuda) ... skipped 'detected only one GPU'
 test_cuda_synchronize (__main__.TestCuda) ... ok
 test_det_logdet_slogdet (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_diagflat (__main__.TestCuda) ... ok
 test_diagonal (__main__.TestCuda) ... ok
 test_digamma (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_dim_reduction (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_events (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_fft_ifft_rfft_irfft (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_flip (__main__.TestCuda) ... ok
 test_from_sequence (__main__.TestCuda) ... ok
 test_gather (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_gather_dim (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_gesv_batched (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_gesv_batched_dims (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_get_set_rng_state_all (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_index (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_int_pow (__main__.TestCuda) ... ok
 test_is_tensor (__main__.TestCuda) ... ok
 test_linspace (__main__.TestCuda) ... ok
 test_load_nonexistent_device (__main__.TestCuda) ... ok
 test_logspace (__main__.TestCuda) ... ok
 test_manual_seed (__main__.TestCuda) ... ok
 test_matrix_power (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_matrix_rank (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_max_with_inf (__main__.TestCuda) ... ok
 test_memory_stats (__main__.TestCuda) ... ok
 test_memory_stats_multigpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_min_max_inits (__main__.TestCuda) ... ok
 test_min_max_nan (__main__.TestCuda) ... ok
 test_min_with_inf (__main__.TestCuda) ... ok
 test_mul_intertype_scalar (__main__.TestCuda) ... ok
 test_multigpu_serialization (__main__.TestCuda) ... skipped 'detected only one GPU'
 test_multigpu_serialization_remap (__main__.TestCuda) ... skipped 'detected only one GPU'
 test_multigpu_serialization_remap_dict (__main__.TestCuda) ... skipped 'detected only one GPU'
 test_multinomial (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_multinomial_invalid_probs_cuda (__main__.TestCuda) ... FAIL
 test_neg (__main__.TestCuda) ... ok
 test_new (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_noncontiguous_pinned_memory (__main__.TestCuda) ... ok
 test_nvtx (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_pinverse (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_polygamma (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_random_neg_values (__main__.TestCuda) ... ok
 test_randperm_cuda (__main__.TestCuda) ... ok
 test_record_stream (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_reduce_add (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_reduce_add_coalesced (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_reduce_add_coalesced_dense_only (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_remainder_overflow (__main__.TestCuda) ... ok
 test_rot90 (__main__.TestCuda) ... ok
 test_scatter_cpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_cpu_dim (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_cpu_neg_dim (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_cpu_sizes (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_gpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_gpu_dim (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_scatter_gpu_neg_dim (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_scatter_gpu_sizes (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_serialization (__main__.TestCuda) ... ok
 test_serialization_array_with_empty (__main__.TestCuda) ... ok
 test_serialization_array_with_storage (__main__.TestCuda) ... ok
 test_signal_window_functions (__main__.TestCuda) ... ok
 test_stft (__main__.TestCuda) ... skipped 'librosa not found'
 test_streams (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_streams_multi_gpu (__main__.TestCuda) ... skipped 'detected only one GPU'
 test_svd_no_singularvectors (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_symeig (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_tensor_device (__main__.TestCuda) ... skipped 'multi-GPU not supported'
 test_tensor_gather (__main__.TestCuda) ... ok
 test_tensor_scatter (__main__.TestCuda) ... ok
 test_tensor_scatterAdd (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_tensor_scatterFill (__main__.TestCuda) ... ok
 test_tiny_half_norm_ (__main__.TestCuda) ... skipped "test doesn't currently work on the ROCm stack"
 test_torch_manual_seed_seeds_cuda_devices (__main__.TestCuda) ... ok
 test_trtrs (__main__.TestCuda) ... skipped 'no MAGMA library detected'
 test_type_conversions (__main__.TestCuda) ... ok
 test_type_conversions_same_gpu (__main__.TestCuda) ... skipped 'only one GPU detected'
 test_var (__main__.TestCuda) ... ok
 test_var_large_input (__main__.TestCuda) ... ok
 test_var_stability (__main__.TestCuda) ... ok
 test_var_unbiased (__main__.TestCuda) ... ok
 test_view (__main__.TestCuda) ... ok

 ======================================================================
 FAIL: test_multinomial_invalid_probs_cuda (__main__.TestCuda)
 ----------------------------------------------------------------------
 Traceback (most recent call last):
  File "/root/pytorch/test/common_utils.py", line 280, in wrapper
    method(*args, **kwargs)
  File "test_cuda.py", line 1598, in test_multinomial_invalid_probs_cuda
    self._spawn_method(test_method, torch.Tensor([1, -1, 1]))
  File "test_cuda.py", line 1578, in _spawn_method
    self.fail(e)
 AssertionError: False

 ----------------------------------------------------------------------
 Ran 2049 tests in 76.103s

 FAILED (failures=1, skipped=269)
 Traceback (most recent call last):
  File "test/run_test.py", line 392, in <module>
    main()
  File "test/run_test.py", line 384, in main
    raise RuntimeError(message)
 RuntimeError: test_cuda failed!