API tools faq
paste
mahmoodn

mxnet-build2

mahmoodn
Feb 22nd, 2019
758
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 391.15 KB | None | 0 0
raw download clone embed print report
  1. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/broadcast_reduce_op_index_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/broadcast_reduce_op_index.cu
  2. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o src/operator/tensor/elemwise_binary_broadcast_op_logic.cu >build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.d
  3. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/elemwise_scatter_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/elemwise_scatter_op.cu
  4. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/indexing_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/indexing_op.cu
  5. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/elemwise_binary_broadcast_op_logic.cu
  6. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/tensor/la_op_gpu.o src/operator/tensor/la_op.cu >build/src/operator/tensor/la_op_gpu.d
  7. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/la_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/la_op.cu
  8. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/tensor/elemwise_binary_op_logic_gpu.o src/operator/tensor/elemwise_binary_op_logic.cu >build/src/operator/tensor/elemwise_binary_op_logic_gpu.d
  9. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/tensor/elemwise_unary_op_basic_gpu.o src/operator/tensor/elemwise_unary_op_basic.cu >build/src/operator/tensor/elemwise_unary_op_basic_gpu.d
  10. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/elemwise_binary_op_logic_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/elemwise_binary_op_logic.cu
  11. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/tensor/sparse_retain_gpu.o src/operator/tensor/sparse_retain.cu >build/src/operator/tensor/sparse_retain_gpu.d
  12. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/elemwise_unary_op_basic_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/elemwise_unary_op_basic.cu
  13. /usr/local/cuda/bin/nvcc -c -o build/src/operator/tensor/sparse_retain_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/tensor/sparse_retain.cu
  14. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  15. detected during:
  16. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  17. src/operator/tensor/./../mxnet_op.h(701): here
  18. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  19. src/operator/tensor/./../mxnet_op.h(721): here
  20. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  21. src/operator/tensor/./elemwise_unary_op.h(243): here
  22. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  23. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  24.  
  25. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  26. detected during:
  27. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  28. src/operator/tensor/./../mxnet_op.h(701): here
  29. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  30. src/operator/tensor/./../mxnet_op.h(721): here
  31. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  32. src/operator/tensor/./elemwise_unary_op.h(243): here
  33. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  34. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  35.  
  36. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  37. detected during:
  38. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  39. src/operator/tensor/./../mxnet_op.h(479): here
  40. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  41. src/operator/tensor/./../mxnet_op.h(701): here
  42. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  43. src/operator/tensor/./../mxnet_op.h(721): here
  44. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  45. src/operator/tensor/./elemwise_unary_op.h(243): here
  46. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  47. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  48.  
  49. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  50. detected during:
  51. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  52. src/operator/tensor/./../mxnet_op.h(479): here
  53. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  54. src/operator/tensor/./../mxnet_op.h(701): here
  55. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  56. src/operator/tensor/./../mxnet_op.h(721): here
  57. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  58. src/operator/tensor/./elemwise_unary_op.h(243): here
  59. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  60. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  61.  
  62. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  63. detected during:
  64. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  65. src/operator/tensor/./../mxnet_op.h(479): here
  66. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  67. src/operator/tensor/./../mxnet_op.h(701): here
  68. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  69. src/operator/tensor/./../mxnet_op.h(721): here
  70. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  71. src/operator/tensor/./elemwise_unary_op.h(243): here
  72. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  73. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  74.  
  75. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  76. detected during:
  77. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  78. src/operator/tensor/./../mxnet_op.h(701): here
  79. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  80. src/operator/tensor/./../mxnet_op.h(721): here
  81. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  82. src/operator/tensor/./elemwise_unary_op.h(243): here
  83. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  84. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  85.  
  86. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  87. detected during:
  88. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  89. src/operator/tensor/./../mxnet_op.h(701): here
  90. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  91. src/operator/tensor/./../mxnet_op.h(721): here
  92. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  93. src/operator/tensor/./elemwise_unary_op.h(243): here
  94. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  95. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  96.  
  97. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  98. detected during:
  99. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  100. src/operator/tensor/./../mxnet_op.h(479): here
  101. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  102. src/operator/tensor/./../mxnet_op.h(701): here
  103. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  104. src/operator/tensor/./../mxnet_op.h(721): here
  105. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  106. src/operator/tensor/./elemwise_unary_op.h(243): here
  107. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  108. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  109.  
  110. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  111. detected during:
  112. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  113. src/operator/tensor/./../mxnet_op.h(479): here
  114. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  115. src/operator/tensor/./../mxnet_op.h(701): here
  116. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  117. src/operator/tensor/./../mxnet_op.h(721): here
  118. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  119. src/operator/tensor/./elemwise_unary_op.h(243): here
  120. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  121. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  122.  
  123. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  124. detected during:
  125. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  126. src/operator/tensor/./../mxnet_op.h(479): here
  127. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  128. src/operator/tensor/./../mxnet_op.h(701): here
  129. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  130. src/operator/tensor/./../mxnet_op.h(721): here
  131. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  132. src/operator/tensor/./elemwise_unary_op.h(243): here
  133. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  134. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  135.  
  136. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/optimizer_op_gpu.o src/operator/contrib/optimizer_op.cu >build/src/operator/contrib/optimizer_op_gpu.d
  137. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/optimizer_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/optimizer_op.cu
  138. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  139. detected during:
  140. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  141. src/operator/tensor/./../mxnet_op.h(701): here
  142. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  143. src/operator/tensor/./../mxnet_op.h(721): here
  144. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  145. src/operator/tensor/./elemwise_unary_op.h(243): here
  146. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  147. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  148.  
  149. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  150. detected during:
  151. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  152. src/operator/tensor/./../mxnet_op.h(701): here
  153. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  154. src/operator/tensor/./../mxnet_op.h(721): here
  155. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  156. src/operator/tensor/./elemwise_unary_op.h(243): here
  157. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  158. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  159.  
  160. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  161. detected during:
  162. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  163. src/operator/tensor/./../mxnet_op.h(479): here
  164. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  165. src/operator/tensor/./../mxnet_op.h(701): here
  166. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  167. src/operator/tensor/./../mxnet_op.h(721): here
  168. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  169. src/operator/tensor/./elemwise_unary_op.h(243): here
  170. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  171. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  172.  
  173. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  174. detected during:
  175. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  176. src/operator/tensor/./../mxnet_op.h(479): here
  177. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  178. src/operator/tensor/./../mxnet_op.h(701): here
  179. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  180. src/operator/tensor/./../mxnet_op.h(721): here
  181. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  182. src/operator/tensor/./elemwise_unary_op.h(243): here
  183. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  184. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  185.  
  186. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  187. detected during:
  188. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  189. src/operator/tensor/./../mxnet_op.h(479): here
  190. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  191. src/operator/tensor/./../mxnet_op.h(701): here
  192. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  193. src/operator/tensor/./../mxnet_op.h(721): here
  194. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  195. src/operator/tensor/./elemwise_unary_op.h(243): here
  196. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  197. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  198.  
  199. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/boolean_mask_gpu.o src/operator/contrib/boolean_mask.cu >build/src/operator/contrib/boolean_mask_gpu.d
  200. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/boolean_mask_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/boolean_mask.cu
  201. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/adaptive_avg_pooling_gpu.o src/operator/contrib/adaptive_avg_pooling.cu >build/src/operator/contrib/adaptive_avg_pooling_gpu.d
  202. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  203. detected during:
  204. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  205. src/operator/tensor/./../mxnet_op.h(701): here
  206. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  207. src/operator/tensor/./../mxnet_op.h(721): here
  208. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  209. src/operator/tensor/./elemwise_unary_op.h(243): here
  210. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  211. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  212.  
  213. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  214. detected during:
  215. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  216. src/operator/tensor/./../mxnet_op.h(701): here
  217. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  218. src/operator/tensor/./../mxnet_op.h(721): here
  219. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  220. src/operator/tensor/./elemwise_unary_op.h(243): here
  221. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  222. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  223.  
  224. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  225. detected during:
  226. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  227. src/operator/tensor/./../mxnet_op.h(479): here
  228. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  229. src/operator/tensor/./../mxnet_op.h(701): here
  230. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  231. src/operator/tensor/./../mxnet_op.h(721): here
  232. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  233. src/operator/tensor/./elemwise_unary_op.h(243): here
  234. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  235. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  236.  
  237. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  238. detected during:
  239. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  240. src/operator/tensor/./../mxnet_op.h(479): here
  241. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  242. src/operator/tensor/./../mxnet_op.h(701): here
  243. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  244. src/operator/tensor/./../mxnet_op.h(721): here
  245. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  246. src/operator/tensor/./elemwise_unary_op.h(243): here
  247. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  248. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  249.  
  250. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  251. detected during:
  252. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  253. src/operator/tensor/./../mxnet_op.h(479): here
  254. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  255. src/operator/tensor/./../mxnet_op.h(701): here
  256. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  257. src/operator/tensor/./../mxnet_op.h(721): here
  258. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  259. src/operator/tensor/./elemwise_unary_op.h(243): here
  260. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  261. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  262.  
  263. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/adaptive_avg_pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/adaptive_avg_pooling.cu
  264. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/ifft_gpu.o src/operator/contrib/ifft.cu >build/src/operator/contrib/ifft_gpu.d
  265. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/multibox_detection_gpu.o src/operator/contrib/multibox_detection.cu >build/src/operator/contrib/multibox_detection_gpu.d
  266. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/ifft_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/ifft.cu
  267. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  268. detected during:
  269. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  270. src/operator/tensor/./../mxnet_op.h(701): here
  271. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  272. src/operator/tensor/./../mxnet_op.h(721): here
  273. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  274. src/operator/tensor/./elemwise_unary_op.h(243): here
  275. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  276. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  277.  
  278. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  279. detected during:
  280. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  281. src/operator/tensor/./../mxnet_op.h(701): here
  282. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  283. src/operator/tensor/./../mxnet_op.h(721): here
  284. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  285. src/operator/tensor/./elemwise_unary_op.h(243): here
  286. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  287. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  288.  
  289. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  290. detected during:
  291. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  292. src/operator/tensor/./../mxnet_op.h(479): here
  293. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  294. src/operator/tensor/./../mxnet_op.h(701): here
  295. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  296. src/operator/tensor/./../mxnet_op.h(721): here
  297. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  298. src/operator/tensor/./elemwise_unary_op.h(243): here
  299. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  300. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  301.  
  302. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  303. detected during:
  304. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  305. src/operator/tensor/./../mxnet_op.h(479): here
  306. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  307. src/operator/tensor/./../mxnet_op.h(701): here
  308. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  309. src/operator/tensor/./../mxnet_op.h(721): here
  310. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  311. src/operator/tensor/./elemwise_unary_op.h(243): here
  312. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  313. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  314.  
  315. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  316. detected during:
  317. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  318. src/operator/tensor/./../mxnet_op.h(479): here
  319. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  320. src/operator/tensor/./../mxnet_op.h(701): here
  321. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  322. src/operator/tensor/./../mxnet_op.h(721): here
  323. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  324. src/operator/tensor/./elemwise_unary_op.h(243): here
  325. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  326. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  327.  
  328. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/multibox_detection_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/multibox_detection.cu
  329. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/index_copy_gpu.o src/operator/contrib/index_copy.cu >build/src/operator/contrib/index_copy_gpu.d
  330. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/tensorrt_gpu.o src/operator/contrib/tensorrt.cu >build/src/operator/contrib/tensorrt_gpu.d
  331. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/tensorrt_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/tensorrt.cu
  332. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  333. detected during:
  334. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  335. src/operator/tensor/./../mxnet_op.h(701): here
  336. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  337. src/operator/tensor/./../mxnet_op.h(721): here
  338. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  339. src/operator/tensor/./elemwise_unary_op.h(243): here
  340. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  341. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  342.  
  343. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  344. detected during:
  345. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  346. src/operator/tensor/./../mxnet_op.h(701): here
  347. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  348. src/operator/tensor/./../mxnet_op.h(721): here
  349. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  350. src/operator/tensor/./elemwise_unary_op.h(243): here
  351. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  352. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  353.  
  354. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  355. detected during:
  356. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  357. src/operator/tensor/./../mxnet_op.h(479): here
  358. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  359. src/operator/tensor/./../mxnet_op.h(701): here
  360. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  361. src/operator/tensor/./../mxnet_op.h(721): here
  362. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  363. src/operator/tensor/./elemwise_unary_op.h(243): here
  364. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  365. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  366.  
  367. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  368. detected during:
  369. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  370. src/operator/tensor/./../mxnet_op.h(479): here
  371. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  372. src/operator/tensor/./../mxnet_op.h(701): here
  373. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  374. src/operator/tensor/./../mxnet_op.h(721): here
  375. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  376. src/operator/tensor/./elemwise_unary_op.h(243): here
  377. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  378. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  379.  
  380. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  381. detected during:
  382. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  383. src/operator/tensor/./../mxnet_op.h(479): here
  384. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  385. src/operator/tensor/./../mxnet_op.h(701): here
  386. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  387. src/operator/tensor/./../mxnet_op.h(721): here
  388. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  389. src/operator/tensor/./elemwise_unary_op.h(243): here
  390. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  391. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  392.  
  393. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/multibox_target_gpu.o src/operator/contrib/multibox_target.cu >build/src/operator/contrib/multibox_target_gpu.d
  394. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/index_copy_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/index_copy.cu
  395. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/multibox_target_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/multibox_target.cu
  396. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/proposal_gpu.o src/operator/contrib/proposal.cu >build/src/operator/contrib/proposal_gpu.d
  397. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/bilinear_resize_gpu.o src/operator/contrib/bilinear_resize.cu >build/src/operator/contrib/bilinear_resize_gpu.d
  398. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/proposal_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/proposal.cu
  399. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/bilinear_resize_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/bilinear_resize.cu
  400. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/count_sketch_gpu.o src/operator/contrib/count_sketch.cu >build/src/operator/contrib/count_sketch_gpu.d
  401. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/count_sketch_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/count_sketch.cu
  402. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  403. detected during:
  404. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  405. src/operator/tensor/./../mxnet_op.h(701): here
  406. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  407. src/operator/tensor/./../mxnet_op.h(721): here
  408. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  409. src/operator/tensor/./elemwise_unary_op.h(243): here
  410. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  411. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  412.  
  413. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  414. detected during:
  415. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  416. src/operator/tensor/./../mxnet_op.h(701): here
  417. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  418. src/operator/tensor/./../mxnet_op.h(721): here
  419. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  420. src/operator/tensor/./elemwise_unary_op.h(243): here
  421. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  422. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  423.  
  424. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  425. detected during:
  426. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  427. src/operator/tensor/./../mxnet_op.h(479): here
  428. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  429. src/operator/tensor/./../mxnet_op.h(701): here
  430. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  431. src/operator/tensor/./../mxnet_op.h(721): here
  432. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  433. src/operator/tensor/./elemwise_unary_op.h(243): here
  434. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  435. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  436.  
  437. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  438. detected during:
  439. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  440. src/operator/tensor/./../mxnet_op.h(479): here
  441. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  442. src/operator/tensor/./../mxnet_op.h(701): here
  443. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  444. src/operator/tensor/./../mxnet_op.h(721): here
  445. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  446. src/operator/tensor/./elemwise_unary_op.h(243): here
  447. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  448. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  449.  
  450. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  451. detected during:
  452. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  453. src/operator/tensor/./../mxnet_op.h(479): here
  454. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  455. src/operator/tensor/./../mxnet_op.h(701): here
  456. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  457. src/operator/tensor/./../mxnet_op.h(721): here
  458. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  459. src/operator/tensor/./elemwise_unary_op.h(243): here
  460. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  461. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  462.  
  463. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/dgl_graph_gpu.o src/operator/contrib/dgl_graph.cu >build/src/operator/contrib/dgl_graph_gpu.d
  464. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/gradient_multiplier_op_gpu.o src/operator/contrib/gradient_multiplier_op.cu >build/src/operator/contrib/gradient_multiplier_op_gpu.d
  465. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/dgl_graph_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/dgl_graph.cu
  466. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/gradient_multiplier_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/gradient_multiplier_op.cu
  467. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/bounding_box_gpu.o src/operator/contrib/bounding_box.cu >build/src/operator/contrib/bounding_box_gpu.d
  468. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: calling a constexpr __host__ function("quiet_NaN") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  469. detected during:
  470. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  471. src/operator/tensor/./../mxnet_op.h(701): here
  472. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  473. src/operator/tensor/./../mxnet_op.h(721): here
  474. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  475. src/operator/tensor/./elemwise_unary_op.h(243): here
  476. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  477. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  478.  
  479. src/operator/tensor/./.././contrib/erfinv-inl.h(81): warning: calling a constexpr __host__ function("infinity") from a __host__ __device__ function("Map") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.
  480. detected during:
  481. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=float]"
  482. src/operator/tensor/./../mxnet_op.h(701): here
  483. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  484. src/operator/tensor/./../mxnet_op.h(721): here
  485. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<float *, float *>]"
  486. src/operator/tensor/./elemwise_unary_op.h(243): here
  487. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  488. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  489.  
  490. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  491. detected during:
  492. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int8_t]"
  493. src/operator/tensor/./../mxnet_op.h(479): here
  494. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int8_t]"
  495. src/operator/tensor/./../mxnet_op.h(701): here
  496. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  497. src/operator/tensor/./../mxnet_op.h(721): here
  498. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int8_t *, int8_t *>]"
  499. src/operator/tensor/./elemwise_unary_op.h(243): here
  500. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  501. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  502.  
  503. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  504. detected during:
  505. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int32_t]"
  506. src/operator/tensor/./../mxnet_op.h(479): here
  507. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int32_t]"
  508. src/operator/tensor/./../mxnet_op.h(701): here
  509. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  510. src/operator/tensor/./../mxnet_op.h(721): here
  511. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int32_t *, int32_t *>]"
  512. src/operator/tensor/./elemwise_unary_op.h(243): here
  513. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  514. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  515.  
  516. src/operator/tensor/./.././contrib/erfinv-inl.h(79): warning: floating-point value does not fit in required integral type
  517. detected during:
  518. instantiation of "DType mxnet::op::mshadow_op::erfinv::Map(DType) [with DType=int64_t]"
  519. src/operator/tensor/./../mxnet_op.h(479): here
  520. instantiation of "void mxnet::op::mxnet_op::op_with_req<OP, req>::Map(mxnet::index_t, DType *, const DType *) [with OP=mxnet::op::mshadow_op::erfinv, req=1, DType=int64_t]"
  521. src/operator/tensor/./../mxnet_op.h(701): here
  522. instantiation of "void mxnet::op::mxnet_op::mxnet_generic_kernel<OP,Args...>(int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  523. src/operator/tensor/./../mxnet_op.h(721): here
  524. instantiation of "void mxnet::op::mxnet_op::Kernel<OP, mxnet::gpu>::Launch(mshadow::Stream<mshadow::gpu> *, int, Args...) [with OP=mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::erfinv, 1>, Args=<int64_t *, int64_t *>]"
  525. src/operator/tensor/./elemwise_unary_op.h(243): here
  526. instantiation of "void mxnet::op::UnaryOp::Compute<xpu,OP>(const nnvm::NodeAttrs &, const mxnet::OpContext &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &, const std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType>> &, const std::vector<mxnet::TBlob, std::allocator<mxnet::TBlob>> &) [with xpu=mxnet::gpu, OP=mxnet::op::mshadow_op::erfinv]"
  527. src/operator/tensor/elemwise_unary_op_basic.cu(67): here
  528.  
  529. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/bounding_box_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/bounding_box.cu
  530. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/fft_gpu.o src/operator/contrib/fft.cu >build/src/operator/contrib/fft_gpu.d
  531. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/multibox_prior_gpu.o src/operator/contrib/multibox_prior.cu >build/src/operator/contrib/multibox_prior_gpu.d
  532. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/fft_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/fft.cu
  533. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/multibox_prior_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/multibox_prior.cu
  534. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/deformable_psroi_pooling_gpu.o src/operator/contrib/deformable_psroi_pooling.cu >build/src/operator/contrib/deformable_psroi_pooling_gpu.d
  535. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/deformable_psroi_pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/deformable_psroi_pooling.cu
  536. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/quadratic_op_gpu.o src/operator/contrib/quadratic_op.cu >build/src/operator/contrib/quadratic_op_gpu.d
  537. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/transformer_gpu.o src/operator/contrib/transformer.cu >build/src/operator/contrib/transformer_gpu.d
  538. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/transformer_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/transformer.cu
  539. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/quadratic_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/quadratic_op.cu
  540. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/multi_proposal_gpu.o src/operator/contrib/multi_proposal.cu >build/src/operator/contrib/multi_proposal_gpu.d
  541. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/multi_proposal_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/multi_proposal.cu
  542. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/adamw_gpu.o src/operator/contrib/adamw.cu >build/src/operator/contrib/adamw_gpu.d
  543. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/sync_batch_norm_gpu.o src/operator/contrib/sync_batch_norm.cu >build/src/operator/contrib/sync_batch_norm_gpu.d
  544. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/adamw_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/adamw.cu
  545. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/sync_batch_norm_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/sync_batch_norm.cu
  546. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h: In function ‘void mxnet::op::SliceLikeInferRanges(const TShape&, const TShape&, const TShape&, nnvm::Tuple<dmlc::optional<int> >*, nnvm::Tuple<dmlc::optional<int> >*, nnvm::Tuple<dmlc::optional<int> >*)’:
  547. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +20)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  548. new (&val) T(other.value());
  549. ^
  550. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +28)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  551. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +36)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  552. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +20)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  553. new (&val) T(other.value());
  554. ^
  555. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +28)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  556. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +36)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  557. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +20)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  558. new (&val) T(other.value());
  559. ^
  560. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +28)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  561. /home/mahmood/mx/mxnet/3rdparty/dmlc-core/include/dmlc/././optional.h:56:1: warning: ‘*((void*)&<anonymous> +36)’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  562. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/psroi_pooling_gpu.o src/operator/contrib/psroi_pooling.cu >build/src/operator/contrib/psroi_pooling_gpu.d
  563. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/deformable_convolution_gpu.o src/operator/contrib/deformable_convolution.cu >build/src/operator/contrib/deformable_convolution_gpu.d
  564. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/psroi_pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/psroi_pooling.cu
  565. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/contrib/roi_align_gpu.o src/operator/contrib/roi_align.cu >build/src/operator/contrib/roi_align_gpu.d
  566. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/deformable_convolution_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/deformable_convolution.cu
  567. /usr/local/cuda/bin/nvcc -c -o build/src/operator/contrib/roi_align_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/contrib/roi_align.cu
  568. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/random/shuffle_op_gpu.o src/operator/random/shuffle_op.cu >build/src/operator/random/shuffle_op_gpu.d
  569. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/random/sample_multinomial_op_gpu.o src/operator/random/sample_multinomial_op.cu >build/src/operator/random/sample_multinomial_op_gpu.d
  570. /usr/local/cuda/bin/nvcc -c -o build/src/operator/random/shuffle_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/random/shuffle_op.cu
  571. /usr/local/cuda/bin/nvcc -c -o build/src/operator/random/sample_multinomial_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/random/sample_multinomial_op.cu
  572. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/random/multisample_op_gpu.o src/operator/random/multisample_op.cu >build/src/operator/random/multisample_op_gpu.d
  573. /usr/local/cuda/bin/nvcc -c -o build/src/operator/random/multisample_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/random/multisample_op.cu
  574. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/random/sample_op_gpu.o src/operator/random/sample_op.cu >build/src/operator/random/sample_op_gpu.d
  575. /usr/local/cuda/bin/nvcc -c -o build/src/operator/random/sample_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/random/sample_op.cu
  576. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/requantize_gpu.o src/operator/quantization/requantize.cu >build/src/operator/quantization/requantize_gpu.d
  577. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantize_gpu.o src/operator/quantization/quantize.cu >build/src/operator/quantization/quantize_gpu.d
  578. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantize_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantize.cu
  579. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/requantize_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/requantize.cu
  580. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/dequantize_gpu.o src/operator/quantization/dequantize.cu >build/src/operator/quantization/dequantize_gpu.d
  581. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantized_conv_gpu.o src/operator/quantization/quantized_conv.cu >build/src/operator/quantization/quantized_conv_gpu.d
  582. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/dequantize_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/dequantize.cu
  583. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantized_conv_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantized_conv.cu
  584. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantized_flatten_gpu.o src/operator/quantization/quantized_flatten.cu >build/src/operator/quantization/quantized_flatten_gpu.d
  585. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantized_fully_connected_gpu.o src/operator/quantization/quantized_fully_connected.cu >build/src/operator/quantization/quantized_fully_connected_gpu.d
  586. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantized_flatten_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantized_flatten.cu
  587. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantized_fully_connected_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantized_fully_connected.cu
  588. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantized_pooling_gpu.o src/operator/quantization/quantized_pooling.cu >build/src/operator/quantization/quantized_pooling_gpu.d
  589. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantized_pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantized_pooling.cu
  590. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/quantization/quantize_v2_gpu.o src/operator/quantization/quantize_v2.cu >build/src/operator/quantization/quantize_v2_gpu.d
  591. /usr/local/cuda/bin/nvcc -c -o build/src/operator/quantization/quantize_v2_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/quantization/quantize_v2.cu
  592. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/custom/native_op_gpu.o src/operator/custom/native_op.cu >build/src/operator/custom/native_op_gpu.d
  593. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/image/resize_gpu.o src/operator/image/resize.cu >build/src/operator/image/resize_gpu.d
  594. /usr/local/cuda/bin/nvcc -c -o build/src/operator/custom/native_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/custom/native_op.cu
  595. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/image/image_random_gpu.o src/operator/image/image_random.cu >build/src/operator/image/image_random_gpu.d
  596. /usr/local/cuda/bin/nvcc -c -o build/src/operator/image/resize_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/image/resize.cu
  597. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/lrn_gpu.o src/operator/nn/lrn.cu >build/src/operator/nn/lrn_gpu.d
  598. /usr/local/cuda/bin/nvcc -c -o build/src/operator/image/image_random_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/image/image_random.cu
  599. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/lrn_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/lrn.cu
  600. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/dropout_gpu.o src/operator/nn/dropout.cu >build/src/operator/nn/dropout_gpu.d
  601. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/softmax_activation_gpu.o src/operator/nn/softmax_activation.cu >build/src/operator/nn/softmax_activation_gpu.d
  602. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/dropout_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/dropout.cu
  603. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/softmax_activation_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/softmax_activation.cu
  604. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  605.  
  606. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  607.  
  608. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  609.  
  610. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  611.  
  612. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  613.  
  614. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  615.  
  616. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  617.  
  618. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  619.  
  620. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  621.  
  622. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  623.  
  624. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  625.  
  626. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  627.  
  628. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/fully_connected_gpu.o src/operator/nn/fully_connected.cu >build/src/operator/nn/fully_connected_gpu.d
  629. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/fully_connected_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/fully_connected.cu
  630. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  631.  
  632. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  633.  
  634. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  635.  
  636. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/deconvolution_gpu.o src/operator/nn/deconvolution.cu >build/src/operator/nn/deconvolution_gpu.d
  637. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/pooling_gpu.o src/operator/nn/pooling.cu >build/src/operator/nn/pooling_gpu.d
  638. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/deconvolution_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/deconvolution.cu
  639. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/softmax_gpu.o src/operator/nn/softmax.cu >build/src/operator/nn/softmax_gpu.d
  640. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  641.  
  642. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  643.  
  644. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  645.  
  646. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/pooling.cu
  647. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/activation_gpu.o src/operator/nn/activation.cu >build/src/operator/nn/activation_gpu.d
  648. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/softmax_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/softmax.cu
  649. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  650.  
  651. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  652.  
  653. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  654.  
  655. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/ctc_loss_gpu.o src/operator/nn/ctc_loss.cu >build/src/operator/nn/ctc_loss_gpu.d
  656. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/activation_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/activation.cu
  657. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/ctc_loss_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/ctc_loss.cu
  658. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  659.  
  660. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  661.  
  662. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  663.  
  664. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/convolution_gpu.o src/operator/nn/convolution.cu >build/src/operator/nn/convolution_gpu.d
  665. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/upsampling_gpu.o src/operator/nn/upsampling.cu >build/src/operator/nn/upsampling_gpu.d
  666. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/convolution_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/convolution.cu
  667. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  668.  
  669. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  670.  
  671. src/operator/nn/./dropout-inl.h(498): warning: statement is unreachable
  672.  
  673. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/upsampling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/upsampling.cu
  674. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/batch_norm_gpu.o src/operator/nn/batch_norm.cu >build/src/operator/nn/batch_norm_gpu.d
  675. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/batch_norm_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/batch_norm.cu
  676. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/layer_norm_gpu.o src/operator/nn/layer_norm.cu >build/src/operator/nn/layer_norm_gpu.d
  677. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/layer_norm_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/layer_norm.cu
  678. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/nn/concat_gpu.o src/operator/nn/concat.cu >build/src/operator/nn/concat_gpu.d
  679. /usr/local/cuda/bin/nvcc -c -o build/src/operator/nn/concat_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/nn/concat.cu
  680. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/common/utils_gpu.o src/common/utils.cu >build/src/common/utils_gpu.d
  681. /usr/local/cuda/bin/nvcc -c -o build/src/common/utils_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/common/utils.cu
  682. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/common/random_generator_gpu.o src/common/random_generator.cu >build/src/common/random_generator_gpu.d
  683. /usr/local/cuda/bin/nvcc -c -o build/src/common/random_generator_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/common/random_generator.cu
  684. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/ndarray/ndarray_function_gpu.o src/ndarray/ndarray_function.cu >build/src/ndarray/ndarray_function_gpu.d
  685. /usr/local/cuda/bin/nvcc -c -o build/src/ndarray/ndarray_function_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/ndarray/ndarray_function.cu
  686. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/svm_output_gpu.o src/operator/svm_output.cu >build/src/operator/svm_output_gpu.d
  687. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/optimizer_op_gpu.o src/operator/optimizer_op.cu >build/src/operator/optimizer_op_gpu.d
  688. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/spatial_transformer_gpu.o src/operator/spatial_transformer.cu >build/src/operator/spatial_transformer_gpu.d
  689. /usr/local/cuda/bin/nvcc -c -o build/src/operator/svm_output_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/svm_output.cu
  690. /usr/local/cuda/bin/nvcc -c -o build/src/operator/optimizer_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/optimizer_op.cu
  691. /usr/local/cuda/bin/nvcc -c -o build/src/operator/spatial_transformer_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/spatial_transformer.cu
  692. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/make_loss_gpu.o src/operator/make_loss.cu >build/src/operator/make_loss_gpu.d
  693. /usr/local/cuda/bin/nvcc -c -o build/src/operator/make_loss_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/make_loss.cu
  694. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/pooling_v1_gpu.o src/operator/pooling_v1.cu >build/src/operator/pooling_v1_gpu.d
  695. /usr/local/cuda/bin/nvcc -c -o build/src/operator/pooling_v1_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/pooling_v1.cu
  696. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/instance_norm_gpu.o src/operator/instance_norm.cu >build/src/operator/instance_norm_gpu.d
  697. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/sequence_mask_gpu.o src/operator/sequence_mask.cu >build/src/operator/sequence_mask_gpu.d
  698. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/correlation_gpu.o src/operator/correlation.cu >build/src/operator/correlation_gpu.d
  699. /usr/local/cuda/bin/nvcc -c -o build/src/operator/instance_norm_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/instance_norm.cu
  700. /usr/local/cuda/bin/nvcc -c -o build/src/operator/sequence_mask_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/sequence_mask.cu
  701. /usr/local/cuda/bin/nvcc -c -o build/src/operator/correlation_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/correlation.cu
  702. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/slice_channel_gpu.o src/operator/slice_channel.cu >build/src/operator/slice_channel_gpu.d
  703. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/rnn_gpu.o src/operator/rnn.cu >build/src/operator/rnn_gpu.d
  704. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/crop_gpu.o src/operator/crop.cu >build/src/operator/crop_gpu.d
  705. /usr/local/cuda/bin/nvcc -c -o build/src/operator/slice_channel_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/slice_channel.cu
  706. /usr/local/cuda/bin/nvcc -c -o build/src/operator/rnn_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/rnn.cu
  707. /usr/local/cuda/bin/nvcc -c -o build/src/operator/crop_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/crop.cu
  708. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/convolution_v1_gpu.o src/operator/convolution_v1.cu >build/src/operator/convolution_v1_gpu.d
  709. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/sequence_reverse_gpu.o src/operator/sequence_reverse.cu >build/src/operator/sequence_reverse_gpu.d
  710. /usr/local/cuda/bin/nvcc -c -o build/src/operator/convolution_v1_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/convolution_v1.cu
  711. /usr/local/cuda/bin/nvcc -c -o build/src/operator/sequence_reverse_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/sequence_reverse.cu
  712. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/identity_attach_KL_sparse_reg_gpu.o src/operator/identity_attach_KL_sparse_reg.cu >build/src/operator/identity_attach_KL_sparse_reg_gpu.d
  713. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/leaky_relu_gpu.o src/operator/leaky_relu.cu >build/src/operator/leaky_relu_gpu.d
  714. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/swapaxis_gpu.o src/operator/swapaxis.cu >build/src/operator/swapaxis_gpu.d
  715. /usr/local/cuda/bin/nvcc -c -o build/src/operator/identity_attach_KL_sparse_reg_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/identity_attach_KL_sparse_reg.cu
  716. /usr/local/cuda/bin/nvcc -c -o build/src/operator/leaky_relu_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/leaky_relu.cu
  717. /usr/local/cuda/bin/nvcc -c -o build/src/operator/swapaxis_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/swapaxis.cu
  718. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/grid_generator_gpu.o src/operator/grid_generator.cu >build/src/operator/grid_generator_gpu.d
  719. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/pad_gpu.o src/operator/pad.cu >build/src/operator/pad_gpu.d
  720. /usr/local/cuda/bin/nvcc -c -o build/src/operator/grid_generator_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/grid_generator.cu
  721. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/bilinear_sampler_gpu.o src/operator/bilinear_sampler.cu >build/src/operator/bilinear_sampler_gpu.d
  722. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/roi_pooling_gpu.o src/operator/roi_pooling.cu >build/src/operator/roi_pooling_gpu.d
  723. /usr/local/cuda/bin/nvcc -c -o build/src/operator/pad_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/pad.cu
  724. /usr/local/cuda/bin/nvcc -c -o build/src/operator/bilinear_sampler_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/bilinear_sampler.cu
  725. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/batch_norm_v1_gpu.o src/operator/batch_norm_v1.cu >build/src/operator/batch_norm_v1_gpu.d
  726. /usr/local/cuda/bin/nvcc -c -o build/src/operator/roi_pooling_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/roi_pooling.cu
  727. /usr/local/cuda/bin/nvcc -c -o build/src/operator/batch_norm_v1_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/batch_norm_v1.cu
  728. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/loss_binary_op_gpu.o src/operator/loss_binary_op.cu >build/src/operator/loss_binary_op_gpu.d
  729. /usr/local/cuda/bin/nvcc -c -o build/src/operator/loss_binary_op_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/loss_binary_op.cu
  730. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/regression_output_gpu.o src/operator/regression_output.cu >build/src/operator/regression_output_gpu.d
  731. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/l2_normalization_gpu.o src/operator/l2_normalization.cu >build/src/operator/l2_normalization_gpu.d
  732. /usr/local/cuda/bin/nvcc -c -o build/src/operator/regression_output_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/regression_output.cu
  733. /usr/local/cuda/bin/nvcc -c -o build/src/operator/l2_normalization_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/l2_normalization.cu
  734. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/sequence_last_gpu.o src/operator/sequence_last.cu >build/src/operator/sequence_last_gpu.d
  735. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/operator/softmax_output_gpu.o src/operator/softmax_output.cu >build/src/operator/softmax_output_gpu.d
  736. /usr/local/cuda/bin/nvcc -c -o build/src/operator/sequence_last_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/sequence_last.cu
  737. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/kvstore/gradient_compression_gpu.o src/kvstore/gradient_compression.cu >build/src/kvstore/gradient_compression_gpu.d
  738. /usr/local/cuda/bin/nvcc -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" --generate-dependencies -MT build/src/kvstore/kvstore_utils_gpu.o src/kvstore/kvstore_utils.cu >build/src/kvstore/kvstore_utils_gpu.d
  739. /usr/local/cuda/bin/nvcc -c -o build/src/operator/softmax_output_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/operator/softmax_output.cu
  740. /usr/local/cuda/bin/nvcc -c -o build/src/kvstore/gradient_compression_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/kvstore/gradient_compression.cu
  741. /usr/local/cuda/bin/nvcc -c -o build/src/kvstore/kvstore_utils_gpu.o -std=c++11 -Xcompiler -D_FORCE_INLINES -O3 -ccbin g++ -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=[sm_75,compute_75] --fatbin-options -compress-all -Xcompiler "-DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0" src/kvstore/kvstore_utils.cu
  742. ar crv lib/libmxnet.a build/src/operator/quantization/mkldnn/mkldnn_quantized_conv.o build/src/operator/quantization/mkldnn/mkldnn_quantized_pooling.o build/src/operator/quantization/mkldnn/mkldnn_quantized_concat.o build/src/operator/subgraph/mkldnn/mkldnn_conv_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv_post_quantize_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv.o build/src/operator/nn/mkldnn/mkldnn_convolution.o build/src/operator/nn/mkldnn/mkldnn_concat.o build/src/operator/nn/mkldnn/mkldnn_base.o build/src/operator/nn/mkldnn/mkldnn_slice.o build/src/operator/nn/mkldnn/mkldnn_act.o build/src/operator/nn/mkldnn/mkldnn_softmax.o build/src/operator/nn/mkldnn/mkldnn_deconvolution.o build/src/operator/nn/mkldnn/mkldnn_copy.o build/src/operator/nn/mkldnn/mkldnn_softmax_output.o build/src/operator/nn/mkldnn/mkldnn_fully_connected.o build/src/operator/nn/mkldnn/mkldnn_pooling.o build/src/operator/nn/mkldnn/mkldnn_sum.o build/src/operator/nn/cudnn/cudnn_algoreg.o build/src/operator/nn/cudnn/cudnn_batch_norm.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic.o build/src/operator/tensor/elemwise_binary_op_logic.o build/src/operator/tensor/square_sum.o build/src/operator/tensor/matrix_op.o build/src/operator/tensor/init_op.o build/src/operator/tensor/elemwise_sum.o build/src/operator/tensor/la_op.o build/src/operator/tensor/histogram.o build/src/operator/tensor/broadcast_reduce_op_index.o build/src/operator/tensor/dot.o build/src/operator/tensor/elemwise_scatter_op.o build/src/operator/tensor/elemwise_unary_op_basic.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended.o build/src/operator/tensor/ravel.o build/src/operator/tensor/broadcast_reduce_op_value.o build/src/operator/tensor/control_flow_op.o build/src/operator/tensor/elemwise_binary_op_basic.o build/src/operator/tensor/elemwise_binary_op_extended.o build/src/operator/tensor/indexing_op.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic.o build/src/operator/tensor/diag_op.o build/src/operator/tensor/ordering_op.o build/src/operator/tensor/sparse_retain.o build/src/operator/tensor/elemwise_binary_scalar_op_extended.o build/src/operator/tensor/elemwise_binary_scalar_op_basic.o build/src/operator/tensor/elemwise_binary_scalar_op_logic.o build/src/operator/tensor/cast_storage.o build/src/operator/tensor/elemwise_binary_op.o build/src/operator/tensor/elemwise_unary_op_trig.o build/src/operator/contrib/tensorrt.o build/src/operator/contrib/multibox_target.o build/src/operator/contrib/sync_batch_norm.o build/src/operator/contrib/count_sketch.o build/src/operator/contrib/roi_align.o build/src/operator/contrib/bilinear_resize.o build/src/operator/contrib/nnz.o build/src/operator/contrib/multibox_detection.o build/src/operator/contrib/nnvm_to_onnx.o build/src/operator/contrib/deformable_psroi_pooling.o build/src/operator/contrib/dgl_graph.o build/src/operator/contrib/fft.o build/src/operator/contrib/multibox_prior.o build/src/operator/contrib/gradient_multiplier_op.o build/src/operator/contrib/adamw.o build/src/operator/contrib/transformer.o build/src/operator/contrib/krprod.o build/src/operator/contrib/multi_proposal.o build/src/operator/contrib/index_copy.o build/src/operator/contrib/optimizer_op.o build/src/operator/contrib/bounding_box.o build/src/operator/contrib/proposal.o build/src/operator/contrib/boolean_mask.o build/src/operator/contrib/psroi_pooling.o build/src/operator/contrib/quadratic_op.o build/src/operator/contrib/deformable_convolution.o build/src/operator/contrib/ifft.o build/src/operator/contrib/adaptive_avg_pooling.o build/src/operator/random/sample_multinomial_op.o build/src/operator/random/multisample_op.o build/src/operator/random/unique_sample_op.o build/src/operator/random/sample_op.o build/src/operator/random/shuffle_op.o build/src/operator/quantization/requantize.o build/src/operator/quantization/dequantize.o build/src/operator/quantization/quantize_graph_pass.o build/src/operator/quantization/quantized_flatten.o build/src/operator/quantization/quantized_conv.o build/src/operator/quantization/quantized_fully_connected.o build/src/operator/quantization/quantized_pooling.o build/src/operator/quantization/quantize_v2.o build/src/operator/quantization/quantized_concat.o build/src/operator/quantization/quantize.o build/src/operator/custom/native_op.o build/src/operator/custom/ndarray_op.o build/src/operator/custom/custom.o build/src/operator/subgraph/partition_graph.o build/src/operator/subgraph/default_subgraph_property.o build/src/operator/nnpack/nnpack_util.o build/src/operator/image/image_random.o build/src/operator/image/resize.o build/src/operator/nn/softmax.o build/src/operator/nn/pooling.o build/src/operator/nn/deconvolution.o build/src/operator/nn/activation.o build/src/operator/nn/upsampling.o build/src/operator/nn/batch_norm.o build/src/operator/nn/ctc_loss.o build/src/operator/nn/fully_connected.o build/src/operator/nn/convolution.o build/src/operator/nn/layer_norm.o build/src/operator/nn/concat.o build/src/operator/nn/softmax_activation.o build/src/operator/nn/lrn.o build/src/operator/nn/dropout.o build/src/io/io.o build/src/io/image_aug_default.o build/src/io/iter_image_det_recordio.o build/src/io/image_io.o build/src/io/image_det_aug_default.o build/src/io/iter_csv.o build/src/io/iter_image_recordio.o build/src/io/iter_mnist.o build/src/io/iter_image_recordio_2.o build/src/io/iter_libsvm.o build/src/common/utils.o build/src/common/rtc.o build/src/nnvm/legacy_op_util.o build/src/nnvm/tvm_bridge.o build/src/nnvm/graph_editor.o build/src/nnvm/legacy_json_util.o build/src/profiler/profiler.o build/src/profiler/aggregate_stats.o build/src/profiler/vtune.o build/src/imperative/cached_op.o build/src/imperative/imperative_utils.o build/src/imperative/imperative.o build/src/ndarray/ndarray_function.o build/src/ndarray/ndarray.o build/src/operator/instance_norm.o build/src/operator/subgraph_op_common.o build/src/operator/grid_generator.o build/src/operator/pooling_v1.o build/src/operator/l2_normalization.o build/src/operator/rnn.o build/src/operator/make_loss.o build/src/operator/crop.o build/src/operator/spatial_transformer.o build/src/operator/operator.o build/src/operator/control_flow.o build/src/operator/swapaxis.o build/src/operator/convolution_v1.o build/src/operator/softmax_output.o build/src/operator/operator_util.o build/src/operator/roi_pooling.o build/src/operator/slice_channel.o build/src/operator/batch_norm_v1.o build/src/operator/loss_binary_op.o build/src/operator/regression_output.o build/src/operator/sequence_reverse.o build/src/operator/c_lapack_api.o build/src/operator/identity_attach_KL_sparse_reg.o build/src/operator/bilinear_sampler.o build/src/operator/svm_output.o build/src/operator/optimizer_op.o build/src/operator/sequence_last.o build/src/operator/cross_device_copy.o build/src/operator/correlation.o build/src/operator/pad.o build/src/operator/leaky_relu.o build/src/operator/operator_tune.o build/src/operator/sequence_mask.o build/src/engine/naive_engine.o build/src/engine/openmp.o build/src/engine/threaded_engine_pooled.o build/src/engine/threaded_engine.o build/src/engine/engine.o build/src/engine/threaded_engine_perdevice.o build/src/storage/storage.o build/src/c_api/c_api_executor.o build/src/c_api/c_api_symbolic.o build/src/c_api/c_api_profile.o build/src/c_api/c_api_ndarray.o build/src/c_api/c_api_test.o build/src/c_api/c_predict_api.o build/src/c_api/c_api_function.o build/src/c_api/c_api.o build/src/c_api/c_api_error.o build/src/executor/onnx_to_tensorrt.o build/src/executor/inplace_addto_detect_pass.o build/src/executor/graph_executor.o build/src/executor/trt_graph_executor.o build/src/executor/infer_graph_attr_pass.o build/src/executor/tensorrt_pass.o build/src/executor/attach_op_execs_pass.o build/src/executor/attach_op_resource_pass.o build/src/kvstore/gradient_compression.o build/src/kvstore/kvstore_utils.o build/src/kvstore/kvstore.o build/src/resource.o build/src/libinfo.o build/src/initialize.o build/src/operator/nn/cudnn/cudnn_batch_norm_gpu.o build/src/operator/tensor/elemwise_binary_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_extended_gpu.o build/src/operator/tensor/matrix_op_gpu.o build/src/operator/tensor/ordering_op_gpu.o build/src/operator/tensor/elemwise_unary_op_trig_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended_gpu.o build/src/operator/tensor/diag_op_gpu.o build/src/operator/tensor/square_sum_gpu.o build/src/operator/tensor/elemwise_binary_op_extended_gpu.o build/src/operator/tensor/elemwise_sum_gpu.o build/src/operator/tensor/init_op_gpu.o build/src/operator/tensor/cast_storage_gpu.o build/src/operator/tensor/histogram_gpu.o build/src/operator/tensor/dot_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_logic_gpu.o build/src/operator/tensor/ravel_gpu.o build/src/operator/tensor/control_flow_op_gpu.o build/src/operator/tensor/broadcast_reduce_op_value_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic_gpu.o build/src/operator/tensor/broadcast_reduce_op_index_gpu.o build/src/operator/tensor/elemwise_scatter_op_gpu.o build/src/operator/tensor/indexing_op_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o build/src/operator/tensor/la_op_gpu.o build/src/operator/tensor/elemwise_binary_op_logic_gpu.o build/src/operator/tensor/elemwise_unary_op_basic_gpu.o build/src/operator/tensor/sparse_retain_gpu.o build/src/operator/contrib/optimizer_op_gpu.o build/src/operator/contrib/boolean_mask_gpu.o build/src/operator/contrib/adaptive_avg_pooling_gpu.o build/src/operator/contrib/ifft_gpu.o build/src/operator/contrib/multibox_detection_gpu.o build/src/operator/contrib/index_copy_gpu.o build/src/operator/contrib/tensorrt_gpu.o build/src/operator/contrib/multibox_target_gpu.o build/src/operator/contrib/proposal_gpu.o build/src/operator/contrib/bilinear_resize_gpu.o build/src/operator/contrib/count_sketch_gpu.o build/src/operator/contrib/dgl_graph_gpu.o build/src/operator/contrib/gradient_multiplier_op_gpu.o build/src/operator/contrib/bounding_box_gpu.o build/src/operator/contrib/fft_gpu.o build/src/operator/contrib/multibox_prior_gpu.o build/src/operator/contrib/deformable_psroi_pooling_gpu.o build/src/operator/contrib/quadratic_op_gpu.o build/src/operator/contrib/transformer_gpu.o build/src/operator/contrib/multi_proposal_gpu.o build/src/operator/contrib/adamw_gpu.o build/src/operator/contrib/sync_batch_norm_gpu.o build/src/operator/contrib/psroi_pooling_gpu.o build/src/operator/contrib/deformable_convolution_gpu.o build/src/operator/contrib/roi_align_gpu.o build/src/operator/random/shuffle_op_gpu.o build/src/operator/random/sample_multinomial_op_gpu.o build/src/operator/random/multisample_op_gpu.o build/src/operator/random/sample_op_gpu.o build/src/operator/quantization/requantize_gpu.o build/src/operator/quantization/quantize_gpu.o build/src/operator/quantization/dequantize_gpu.o build/src/operator/quantization/quantized_conv_gpu.o build/src/operator/quantization/quantized_flatten_gpu.o build/src/operator/quantization/quantized_fully_connected_gpu.o build/src/operator/quantization/quantized_pooling_gpu.o build/src/operator/quantization/quantize_v2_gpu.o build/src/operator/custom/native_op_gpu.o build/src/operator/image/resize_gpu.o build/src/operator/image/image_random_gpu.o build/src/operator/nn/lrn_gpu.o build/src/operator/nn/dropout_gpu.o build/src/operator/nn/softmax_activation_gpu.o build/src/operator/nn/fully_connected_gpu.o build/src/operator/nn/deconvolution_gpu.o build/src/operator/nn/pooling_gpu.o build/src/operator/nn/softmax_gpu.o build/src/operator/nn/activation_gpu.o build/src/operator/nn/ctc_loss_gpu.o build/src/operator/nn/convolution_gpu.o build/src/operator/nn/upsampling_gpu.o build/src/operator/nn/batch_norm_gpu.o build/src/operator/nn/layer_norm_gpu.o build/src/operator/nn/concat_gpu.o build/src/common/utils_gpu.o build/src/common/random_generator_gpu.o build/src/ndarray/ndarray_function_gpu.o build/src/operator/svm_output_gpu.o build/src/operator/optimizer_op_gpu.o build/src/operator/spatial_transformer_gpu.o build/src/operator/make_loss_gpu.o build/src/operator/pooling_v1_gpu.o build/src/operator/instance_norm_gpu.o build/src/operator/sequence_mask_gpu.o build/src/operator/correlation_gpu.o build/src/operator/slice_channel_gpu.o build/src/operator/rnn_gpu.o build/src/operator/crop_gpu.o build/src/operator/convolution_v1_gpu.o build/src/operator/sequence_reverse_gpu.o build/src/operator/identity_attach_KL_sparse_reg_gpu.o build/src/operator/leaky_relu_gpu.o build/src/operator/swapaxis_gpu.o build/src/operator/grid_generator_gpu.o build/src/operator/pad_gpu.o build/src/operator/bilinear_sampler_gpu.o build/src/operator/roi_pooling_gpu.o build/src/operator/batch_norm_v1_gpu.o build/src/operator/loss_binary_op_gpu.o build/src/operator/regression_output_gpu.o build/src/operator/l2_normalization_gpu.o build/src/operator/sequence_last_gpu.o build/src/operator/softmax_output_gpu.o build/src/kvstore/gradient_compression_gpu.o build/src/kvstore/kvstore_utils_gpu.o
  743. g++ -DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0 -shared -o lib/libmxnet.so build/src/operator/quantization/mkldnn/mkldnn_quantized_conv.o build/src/operator/quantization/mkldnn/mkldnn_quantized_pooling.o build/src/operator/quantization/mkldnn/mkldnn_quantized_concat.o build/src/operator/subgraph/mkldnn/mkldnn_conv_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv_post_quantize_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv.o build/src/operator/nn/mkldnn/mkldnn_convolution.o build/src/operator/nn/mkldnn/mkldnn_concat.o build/src/operator/nn/mkldnn/mkldnn_base.o build/src/operator/nn/mkldnn/mkldnn_slice.o build/src/operator/nn/mkldnn/mkldnn_act.o build/src/operator/nn/mkldnn/mkldnn_softmax.o build/src/operator/nn/mkldnn/mkldnn_deconvolution.o build/src/operator/nn/mkldnn/mkldnn_copy.o build/src/operator/nn/mkldnn/mkldnn_softmax_output.o build/src/operator/nn/mkldnn/mkldnn_fully_connected.o build/src/operator/nn/mkldnn/mkldnn_pooling.o build/src/operator/nn/mkldnn/mkldnn_sum.o build/src/operator/nn/cudnn/cudnn_algoreg.o build/src/operator/nn/cudnn/cudnn_batch_norm.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic.o build/src/operator/tensor/elemwise_binary_op_logic.o build/src/operator/tensor/square_sum.o build/src/operator/tensor/matrix_op.o build/src/operator/tensor/init_op.o build/src/operator/tensor/elemwise_sum.o build/src/operator/tensor/la_op.o build/src/operator/tensor/histogram.o build/src/operator/tensor/broadcast_reduce_op_index.o build/src/operator/tensor/dot.o build/src/operator/tensor/elemwise_scatter_op.o build/src/operator/tensor/elemwise_unary_op_basic.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended.o build/src/operator/tensor/ravel.o build/src/operator/tensor/broadcast_reduce_op_value.o build/src/operator/tensor/control_flow_op.o build/src/operator/tensor/elemwise_binary_op_basic.o build/src/operator/tensor/elemwise_binary_op_extended.o build/src/operator/tensor/indexing_op.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic.o build/src/operator/tensor/diag_op.o build/src/operator/tensor/ordering_op.o build/src/operator/tensor/sparse_retain.o build/src/operator/tensor/elemwise_binary_scalar_op_extended.o build/src/operator/tensor/elemwise_binary_scalar_op_basic.o build/src/operator/tensor/elemwise_binary_scalar_op_logic.o build/src/operator/tensor/cast_storage.o build/src/operator/tensor/elemwise_binary_op.o build/src/operator/tensor/elemwise_unary_op_trig.o build/src/operator/contrib/tensorrt.o build/src/operator/contrib/multibox_target.o build/src/operator/contrib/sync_batch_norm.o build/src/operator/contrib/count_sketch.o build/src/operator/contrib/roi_align.o build/src/operator/contrib/bilinear_resize.o build/src/operator/contrib/nnz.o build/src/operator/contrib/multibox_detection.o build/src/operator/contrib/nnvm_to_onnx.o build/src/operator/contrib/deformable_psroi_pooling.o build/src/operator/contrib/dgl_graph.o build/src/operator/contrib/fft.o build/src/operator/contrib/multibox_prior.o build/src/operator/contrib/gradient_multiplier_op.o build/src/operator/contrib/adamw.o build/src/operator/contrib/transformer.o build/src/operator/contrib/krprod.o build/src/operator/contrib/multi_proposal.o build/src/operator/contrib/index_copy.o build/src/operator/contrib/optimizer_op.o build/src/operator/contrib/bounding_box.o build/src/operator/contrib/proposal.o build/src/operator/contrib/boolean_mask.o build/src/operator/contrib/psroi_pooling.o build/src/operator/contrib/quadratic_op.o build/src/operator/contrib/deformable_convolution.o build/src/operator/contrib/ifft.o build/src/operator/contrib/adaptive_avg_pooling.o build/src/operator/random/sample_multinomial_op.o build/src/operator/random/multisample_op.o build/src/operator/random/unique_sample_op.o build/src/operator/random/sample_op.o build/src/operator/random/shuffle_op.o build/src/operator/quantization/requantize.o build/src/operator/quantization/dequantize.o build/src/operator/quantization/quantize_graph_pass.o build/src/operator/quantization/quantized_flatten.o build/src/operator/quantization/quantized_conv.o build/src/operator/quantization/quantized_fully_connected.o build/src/operator/quantization/quantized_pooling.o build/src/operator/quantization/quantize_v2.o build/src/operator/quantization/quantized_concat.o build/src/operator/quantization/quantize.o build/src/operator/custom/native_op.o build/src/operator/custom/ndarray_op.o build/src/operator/custom/custom.o build/src/operator/subgraph/partition_graph.o build/src/operator/subgraph/default_subgraph_property.o build/src/operator/nnpack/nnpack_util.o build/src/operator/image/image_random.o build/src/operator/image/resize.o build/src/operator/nn/softmax.o build/src/operator/nn/pooling.o build/src/operator/nn/deconvolution.o build/src/operator/nn/activation.o build/src/operator/nn/upsampling.o build/src/operator/nn/batch_norm.o build/src/operator/nn/ctc_loss.o build/src/operator/nn/fully_connected.o build/src/operator/nn/convolution.o build/src/operator/nn/layer_norm.o build/src/operator/nn/concat.o build/src/operator/nn/softmax_activation.o build/src/operator/nn/lrn.o build/src/operator/nn/dropout.o build/src/io/io.o build/src/io/image_aug_default.o build/src/io/iter_image_det_recordio.o build/src/io/image_io.o build/src/io/image_det_aug_default.o build/src/io/iter_csv.o build/src/io/iter_image_recordio.o build/src/io/iter_mnist.o build/src/io/iter_image_recordio_2.o build/src/io/iter_libsvm.o build/src/common/utils.o build/src/common/rtc.o build/src/nnvm/legacy_op_util.o build/src/nnvm/tvm_bridge.o build/src/nnvm/graph_editor.o build/src/nnvm/legacy_json_util.o build/src/profiler/profiler.o build/src/profiler/aggregate_stats.o build/src/profiler/vtune.o build/src/imperative/cached_op.o build/src/imperative/imperative_utils.o build/src/imperative/imperative.o build/src/ndarray/ndarray_function.o build/src/ndarray/ndarray.o build/src/operator/instance_norm.o build/src/operator/subgraph_op_common.o build/src/operator/grid_generator.o build/src/operator/pooling_v1.o build/src/operator/l2_normalization.o build/src/operator/rnn.o build/src/operator/make_loss.o build/src/operator/crop.o build/src/operator/spatial_transformer.o build/src/operator/operator.o build/src/operator/control_flow.o build/src/operator/swapaxis.o build/src/operator/convolution_v1.o build/src/operator/softmax_output.o build/src/operator/operator_util.o build/src/operator/roi_pooling.o build/src/operator/slice_channel.o build/src/operator/batch_norm_v1.o build/src/operator/loss_binary_op.o build/src/operator/regression_output.o build/src/operator/sequence_reverse.o build/src/operator/c_lapack_api.o build/src/operator/identity_attach_KL_sparse_reg.o build/src/operator/bilinear_sampler.o build/src/operator/svm_output.o build/src/operator/optimizer_op.o build/src/operator/sequence_last.o build/src/operator/cross_device_copy.o build/src/operator/correlation.o build/src/operator/pad.o build/src/operator/leaky_relu.o build/src/operator/operator_tune.o build/src/operator/sequence_mask.o build/src/engine/naive_engine.o build/src/engine/openmp.o build/src/engine/threaded_engine_pooled.o build/src/engine/threaded_engine.o build/src/engine/engine.o build/src/engine/threaded_engine_perdevice.o build/src/storage/storage.o build/src/c_api/c_api_executor.o build/src/c_api/c_api_symbolic.o build/src/c_api/c_api_profile.o build/src/c_api/c_api_ndarray.o build/src/c_api/c_api_test.o build/src/c_api/c_predict_api.o build/src/c_api/c_api_function.o build/src/c_api/c_api.o build/src/c_api/c_api_error.o build/src/executor/onnx_to_tensorrt.o build/src/executor/inplace_addto_detect_pass.o build/src/executor/graph_executor.o build/src/executor/trt_graph_executor.o build/src/executor/infer_graph_attr_pass.o build/src/executor/tensorrt_pass.o build/src/executor/attach_op_execs_pass.o build/src/executor/attach_op_resource_pass.o build/src/kvstore/gradient_compression.o build/src/kvstore/kvstore_utils.o build/src/kvstore/kvstore.o build/src/resource.o build/src/libinfo.o build/src/initialize.o /home/mahmood/mx/mxnet/3rdparty/dmlc-core/libdmlc.a build/src/operator/nn/cudnn/cudnn_batch_norm_gpu.o build/src/operator/tensor/elemwise_binary_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_extended_gpu.o build/src/operator/tensor/matrix_op_gpu.o build/src/operator/tensor/ordering_op_gpu.o build/src/operator/tensor/elemwise_unary_op_trig_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended_gpu.o build/src/operator/tensor/diag_op_gpu.o build/src/operator/tensor/square_sum_gpu.o build/src/operator/tensor/elemwise_binary_op_extended_gpu.o build/src/operator/tensor/elemwise_sum_gpu.o build/src/operator/tensor/init_op_gpu.o build/src/operator/tensor/cast_storage_gpu.o build/src/operator/tensor/histogram_gpu.o build/src/operator/tensor/dot_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_logic_gpu.o build/src/operator/tensor/ravel_gpu.o build/src/operator/tensor/control_flow_op_gpu.o build/src/operator/tensor/broadcast_reduce_op_value_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic_gpu.o build/src/operator/tensor/broadcast_reduce_op_index_gpu.o build/src/operator/tensor/elemwise_scatter_op_gpu.o build/src/operator/tensor/indexing_op_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o build/src/operator/tensor/la_op_gpu.o build/src/operator/tensor/elemwise_binary_op_logic_gpu.o build/src/operator/tensor/elemwise_unary_op_basic_gpu.o build/src/operator/tensor/sparse_retain_gpu.o build/src/operator/contrib/optimizer_op_gpu.o build/src/operator/contrib/boolean_mask_gpu.o build/src/operator/contrib/adaptive_avg_pooling_gpu.o build/src/operator/contrib/ifft_gpu.o build/src/operator/contrib/multibox_detection_gpu.o build/src/operator/contrib/index_copy_gpu.o build/src/operator/contrib/tensorrt_gpu.o build/src/operator/contrib/multibox_target_gpu.o build/src/operator/contrib/proposal_gpu.o build/src/operator/contrib/bilinear_resize_gpu.o build/src/operator/contrib/count_sketch_gpu.o build/src/operator/contrib/dgl_graph_gpu.o build/src/operator/contrib/gradient_multiplier_op_gpu.o build/src/operator/contrib/bounding_box_gpu.o build/src/operator/contrib/fft_gpu.o build/src/operator/contrib/multibox_prior_gpu.o build/src/operator/contrib/deformable_psroi_pooling_gpu.o build/src/operator/contrib/quadratic_op_gpu.o build/src/operator/contrib/transformer_gpu.o build/src/operator/contrib/multi_proposal_gpu.o build/src/operator/contrib/adamw_gpu.o build/src/operator/contrib/sync_batch_norm_gpu.o build/src/operator/contrib/psroi_pooling_gpu.o build/src/operator/contrib/deformable_convolution_gpu.o build/src/operator/contrib/roi_align_gpu.o build/src/operator/random/shuffle_op_gpu.o build/src/operator/random/sample_multinomial_op_gpu.o build/src/operator/random/multisample_op_gpu.o build/src/operator/random/sample_op_gpu.o build/src/operator/quantization/requantize_gpu.o build/src/operator/quantization/quantize_gpu.o build/src/operator/quantization/dequantize_gpu.o build/src/operator/quantization/quantized_conv_gpu.o build/src/operator/quantization/quantized_flatten_gpu.o build/src/operator/quantization/quantized_fully_connected_gpu.o build/src/operator/quantization/quantized_pooling_gpu.o build/src/operator/quantization/quantize_v2_gpu.o build/src/operator/custom/native_op_gpu.o build/src/operator/image/resize_gpu.o build/src/operator/image/image_random_gpu.o build/src/operator/nn/lrn_gpu.o build/src/operator/nn/dropout_gpu.o build/src/operator/nn/softmax_activation_gpu.o build/src/operator/nn/fully_connected_gpu.o build/src/operator/nn/deconvolution_gpu.o build/src/operator/nn/pooling_gpu.o build/src/operator/nn/softmax_gpu.o build/src/operator/nn/activation_gpu.o build/src/operator/nn/ctc_loss_gpu.o build/src/operator/nn/convolution_gpu.o build/src/operator/nn/upsampling_gpu.o build/src/operator/nn/batch_norm_gpu.o build/src/operator/nn/layer_norm_gpu.o build/src/operator/nn/concat_gpu.o build/src/common/utils_gpu.o build/src/common/random_generator_gpu.o build/src/ndarray/ndarray_function_gpu.o build/src/operator/svm_output_gpu.o build/src/operator/optimizer_op_gpu.o build/src/operator/spatial_transformer_gpu.o build/src/operator/make_loss_gpu.o build/src/operator/pooling_v1_gpu.o build/src/operator/instance_norm_gpu.o build/src/operator/sequence_mask_gpu.o build/src/operator/correlation_gpu.o build/src/operator/slice_channel_gpu.o build/src/operator/rnn_gpu.o build/src/operator/crop_gpu.o build/src/operator/convolution_v1_gpu.o build/src/operator/sequence_reverse_gpu.o build/src/operator/identity_attach_KL_sparse_reg_gpu.o build/src/operator/leaky_relu_gpu.o build/src/operator/swapaxis_gpu.o build/src/operator/grid_generator_gpu.o build/src/operator/pad_gpu.o build/src/operator/bilinear_sampler_gpu.o build/src/operator/roi_pooling_gpu.o build/src/operator/batch_norm_v1_gpu.o build/src/operator/loss_binary_op_gpu.o build/src/operator/regression_output_gpu.o build/src/operator/l2_normalization_gpu.o build/src/operator/sequence_last_gpu.o build/src/operator/softmax_output_gpu.o build/src/kvstore/gradient_compression_gpu.o build/src/kvstore/kvstore_utils_gpu.o -pthread -lm -lcudart -lcublas -lcurand -lcusolver -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib -Wl,--as-needed -lmklml_intel -lmklml_gnu -liomp5 -L/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/lib/ -lopenblas -fopenmp -lrt -L/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/lib -lmkldnn -Wl,-rpath,'${ORIGIN}' -lopencv_shape -lopencv_stitching -lopencv_superres -lopencv_videostab -lopencv_aruco -lopencv_bgsegm -lopencv_bioinspired -lopencv_ccalib -lopencv_datasets -lopencv_dpm -lopencv_face -lopencv_freetype -lopencv_fuzzy -lopencv_hdf -lopencv_line_descriptor -lopencv_optflow -lopencv_video -lopencv_plot -lopencv_reg -lopencv_saliency -lopencv_stereo -lopencv_structured_light -lopencv_phase_unwrapping -lopencv_rgbd -lopencv_viz -lopencv_surface_matching -lopencv_text -lopencv_ximgproc -lopencv_calib3d -lopencv_features2d -lopencv_flann -lopencv_xobjdetect -lopencv_objdetect -lopencv_ml -lopencv_xphoto -lopencv_highgui -lopencv_videoio -lopencv_imgcodecs -lopencv_photo -lopencv_imgproc -lopencv_core -lcudnn -lcufft -lcuda -lnvrtc -L/usr/local/cuda/lib64/stubs \
  744. -Wl,--whole-archive /home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/lib/libnnvm.a -Wl,--no-whole-archive
  745. a - build/src/operator/quantization/mkldnn/mkldnn_quantized_conv.o
  746. a - build/src/operator/quantization/mkldnn/mkldnn_quantized_pooling.o
  747. a - build/src/operator/quantization/mkldnn/mkldnn_quantized_concat.o
  748. a - build/src/operator/subgraph/mkldnn/mkldnn_conv_property.o
  749. a - build/src/operator/subgraph/mkldnn/mkldnn_conv_post_quantize_property.o
  750. a - build/src/operator/subgraph/mkldnn/mkldnn_conv.o
  751. a - build/src/operator/nn/mkldnn/mkldnn_convolution.o
  752. a - build/src/operator/nn/mkldnn/mkldnn_concat.o
  753. a - build/src/operator/nn/mkldnn/mkldnn_base.o
  754. a - build/src/operator/nn/mkldnn/mkldnn_slice.o
  755. a - build/src/operator/nn/mkldnn/mkldnn_act.o
  756. a - build/src/operator/nn/mkldnn/mkldnn_softmax.o
  757. a - build/src/operator/nn/mkldnn/mkldnn_deconvolution.o
  758. a - build/src/operator/nn/mkldnn/mkldnn_copy.o
  759. a - build/src/operator/nn/mkldnn/mkldnn_softmax_output.o
  760. a - build/src/operator/nn/mkldnn/mkldnn_fully_connected.o
  761. a - build/src/operator/nn/mkldnn/mkldnn_pooling.o
  762. a - build/src/operator/nn/mkldnn/mkldnn_sum.o
  763. a - build/src/operator/nn/cudnn/cudnn_algoreg.o
  764. a - build/src/operator/nn/cudnn/cudnn_batch_norm.o
  765. a - build/src/operator/tensor/elemwise_binary_broadcast_op_basic.o
  766. a - build/src/operator/tensor/elemwise_binary_op_logic.o
  767. a - build/src/operator/tensor/square_sum.o
  768. a - build/src/operator/tensor/matrix_op.o
  769. a - build/src/operator/tensor/init_op.o
  770. a - build/src/operator/tensor/elemwise_sum.o
  771. a - build/src/operator/tensor/la_op.o
  772. a - build/src/operator/tensor/histogram.o
  773. a - build/src/operator/tensor/broadcast_reduce_op_index.o
  774. a - build/src/operator/tensor/dot.o
  775. a - build/src/operator/tensor/elemwise_scatter_op.o
  776. a - build/src/operator/tensor/elemwise_unary_op_basic.o
  777. a - build/src/operator/tensor/elemwise_binary_broadcast_op_extended.o
  778. a - build/src/operator/tensor/ravel.o
  779. a - build/src/operator/tensor/broadcast_reduce_op_value.o
  780. a - build/src/operator/tensor/control_flow_op.o
  781. a - build/src/operator/tensor/elemwise_binary_op_basic.o
  782. a - build/src/operator/tensor/elemwise_binary_op_extended.o
  783. a - build/src/operator/tensor/indexing_op.o
  784. a - build/src/operator/tensor/elemwise_binary_broadcast_op_logic.o
  785. a - build/src/operator/tensor/diag_op.o
  786. a - build/src/operator/tensor/ordering_op.o
  787. a - build/src/operator/tensor/sparse_retain.o
  788. a - build/src/operator/tensor/elemwise_binary_scalar_op_extended.o
  789. a - build/src/operator/tensor/elemwise_binary_scalar_op_basic.o
  790. a - build/src/operator/tensor/elemwise_binary_scalar_op_logic.o
  791. a - build/src/operator/tensor/cast_storage.o
  792. a - build/src/operator/tensor/elemwise_binary_op.o
  793. a - build/src/operator/tensor/elemwise_unary_op_trig.o
  794. a - build/src/operator/contrib/tensorrt.o
  795. a - build/src/operator/contrib/multibox_target.o
  796. a - build/src/operator/contrib/sync_batch_norm.o
  797. a - build/src/operator/contrib/count_sketch.o
  798. a - build/src/operator/contrib/roi_align.o
  799. a - build/src/operator/contrib/bilinear_resize.o
  800. a - build/src/operator/contrib/nnz.o
  801. a - build/src/operator/contrib/multibox_detection.o
  802. g++ -DMSHADOW_FORCE_STREAM -Wall -Wsign-compare -O3 -DNDEBUG=1 -I/home/mahmood/mx/mxnet/3rdparty/mshadow/ -I/home/mahmood/mx/mxnet/3rdparty/dmlc-core/include -fPIC -I/home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/include -I/home/mahmood/mx/mxnet/3rdparty/dlpack/include -I/home/mahmood/mx/mxnet/3rdparty/tvm/include -Iinclude -funroll-loops -Wno-unused-parameter -Wno-unknown-pragmas -Wno-unused-local-typedefs -msse3 -mf16c -I/usr/local/cuda/include -DMSHADOW_USE_CBLAS=1 -DMSHADOW_USE_MKL=0 -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMSHADOW_RABIT_PS=0 -DMSHADOW_DIST_PS=0 -DMSHADOW_USE_PASCAL=0 -DMXNET_USE_MKLDNN=1 -DUSE_MKL=1 -I/home/mahmood/mx/mxnet/src/operator/nn/mkldnn/ -I/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/include -DMXNET_USE_OPENCV=1 -I/usr/include/opencv -fopenmp -DMXNET_USE_OPERATOR_TUNING=1 -DMSHADOW_USE_CUDNN=1 -I/home/mahmood/mx/mxnet/3rdparty/cub -DMXNET_ENABLE_CUDA_RTC=1 -DMXNET_USE_NCCL=0 -DMXNET_USE_LIBJPEG_TURBO=0 -std=c++11 -o bin/im2rec tools/im2rec.cc build/src/operator/quantization/mkldnn/mkldnn_quantized_conv.o build/src/operator/quantization/mkldnn/mkldnn_quantized_pooling.o build/src/operator/quantization/mkldnn/mkldnn_quantized_concat.o build/src/operator/subgraph/mkldnn/mkldnn_conv_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv_post_quantize_property.o build/src/operator/subgraph/mkldnn/mkldnn_conv.o build/src/operator/nn/mkldnn/mkldnn_convolution.o build/src/operator/nn/mkldnn/mkldnn_concat.o build/src/operator/nn/mkldnn/mkldnn_base.o build/src/operator/nn/mkldnn/mkldnn_slice.o build/src/operator/nn/mkldnn/mkldnn_act.o build/src/operator/nn/mkldnn/mkldnn_softmax.o build/src/operator/nn/mkldnn/mkldnn_deconvolution.o build/src/operator/nn/mkldnn/mkldnn_copy.o build/src/operator/nn/mkldnn/mkldnn_softmax_output.o build/src/operator/nn/mkldnn/mkldnn_fully_connected.o build/src/operator/nn/mkldnn/mkldnn_pooling.o build/src/operator/nn/mkldnn/mkldnn_sum.o build/src/operator/nn/cudnn/cudnn_algoreg.o build/src/operator/nn/cudnn/cudnn_batch_norm.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic.o build/src/operator/tensor/elemwise_binary_op_logic.o build/src/operator/tensor/square_sum.o build/src/operator/tensor/matrix_op.o build/src/operator/tensor/init_op.o build/src/operator/tensor/elemwise_sum.o build/src/operator/tensor/la_op.o build/src/operator/tensor/histogram.o build/src/operator/tensor/broadcast_reduce_op_index.o build/src/operator/tensor/dot.o build/src/operator/tensor/elemwise_scatter_op.o build/src/operator/tensor/elemwise_unary_op_basic.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended.o build/src/operator/tensor/ravel.o build/src/operator/tensor/broadcast_reduce_op_value.o build/src/operator/tensor/control_flow_op.o build/src/operator/tensor/elemwise_binary_op_basic.o build/src/operator/tensor/elemwise_binary_op_extended.o build/src/operator/tensor/indexing_op.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic.o build/src/operator/tensor/diag_op.o build/src/operator/tensor/ordering_op.o build/src/operator/tensor/sparse_retain.o build/src/operator/tensor/elemwise_binary_scalar_op_extended.o build/src/operator/tensor/elemwise_binary_scalar_op_basic.o build/src/operator/tensor/elemwise_binary_scalar_op_logic.o build/src/operator/tensor/cast_storage.o build/src/operator/tensor/elemwise_binary_op.o build/src/operator/tensor/elemwise_unary_op_trig.o build/src/operator/contrib/tensorrt.o build/src/operator/contrib/multibox_target.o build/src/operator/contrib/sync_batch_norm.o build/src/operator/contrib/count_sketch.o build/src/operator/contrib/roi_align.o build/src/operator/contrib/bilinear_resize.o build/src/operator/contrib/nnz.o build/src/operator/contrib/multibox_detection.o build/src/operator/contrib/nnvm_to_onnx.o build/src/operator/contrib/deformable_psroi_pooling.o build/src/operator/contrib/dgl_graph.o build/src/operator/contrib/fft.o build/src/operator/contrib/multibox_prior.o build/src/operator/contrib/gradient_multiplier_op.o build/src/operator/contrib/adamw.o build/src/operator/contrib/transformer.o build/src/operator/contrib/krprod.o build/src/operator/contrib/multi_proposal.o build/src/operator/contrib/index_copy.o build/src/operator/contrib/optimizer_op.o build/src/operator/contrib/bounding_box.o build/src/operator/contrib/proposal.o build/src/operator/contrib/boolean_mask.o build/src/operator/contrib/psroi_pooling.o build/src/operator/contrib/quadratic_op.o build/src/operator/contrib/deformable_convolution.o build/src/operator/contrib/ifft.o build/src/operator/contrib/adaptive_avg_pooling.o build/src/operator/random/sample_multinomial_op.o build/src/operator/random/multisample_op.o build/src/operator/random/unique_sample_op.o build/src/operator/random/sample_op.o build/src/operator/random/shuffle_op.o build/src/operator/quantization/requantize.o build/src/operator/quantization/dequantize.o build/src/operator/quantization/quantize_graph_pass.o build/src/operator/quantization/quantized_flatten.o build/src/operator/quantization/quantized_conv.o build/src/operator/quantization/quantized_fully_connected.o build/src/operator/quantization/quantized_pooling.o build/src/operator/quantization/quantize_v2.o build/src/operator/quantization/quantized_concat.o build/src/operator/quantization/quantize.o build/src/operator/custom/native_op.o build/src/operator/custom/ndarray_op.o build/src/operator/custom/custom.o build/src/operator/subgraph/partition_graph.o build/src/operator/subgraph/default_subgraph_property.o build/src/operator/nnpack/nnpack_util.o build/src/operator/image/image_random.o build/src/operator/image/resize.o build/src/operator/nn/softmax.o build/src/operator/nn/pooling.o build/src/operator/nn/deconvolution.o build/src/operator/nn/activation.o build/src/operator/nn/upsampling.o build/src/operator/nn/batch_norm.o build/src/operator/nn/ctc_loss.o build/src/operator/nn/fully_connected.o build/src/operator/nn/convolution.o build/src/operator/nn/layer_norm.o build/src/operator/nn/concat.o build/src/operator/nn/softmax_activation.o build/src/operator/nn/lrn.o build/src/operator/nn/dropout.o build/src/io/io.o build/src/io/image_aug_default.o build/src/io/iter_image_det_recordio.o build/src/io/image_io.o build/src/io/image_det_aug_default.o build/src/io/iter_csv.o build/src/io/iter_image_recordio.o build/src/io/iter_mnist.o build/src/io/iter_image_recordio_2.o build/src/io/iter_libsvm.o build/src/common/utils.o build/src/common/rtc.o build/src/nnvm/legacy_op_util.o build/src/nnvm/tvm_bridge.o build/src/nnvm/graph_editor.o build/src/nnvm/legacy_json_util.o build/src/profiler/profiler.o build/src/profiler/aggregate_stats.o build/src/profiler/vtune.o build/src/imperative/cached_op.o build/src/imperative/imperative_utils.o build/src/imperative/imperative.o build/src/ndarray/ndarray_function.o build/src/ndarray/ndarray.o build/src/operator/instance_norm.o build/src/operator/subgraph_op_common.o build/src/operator/grid_generator.o build/src/operator/pooling_v1.o build/src/operator/l2_normalization.o build/src/operator/rnn.o build/src/operator/make_loss.o build/src/operator/crop.o build/src/operator/spatial_transformer.o build/src/operator/operator.o build/src/operator/control_flow.o build/src/operator/swapaxis.o build/src/operator/convolution_v1.o build/src/operator/softmax_output.o build/src/operator/operator_util.o build/src/operator/roi_pooling.o build/src/operator/slice_channel.o build/src/operator/batch_norm_v1.o build/src/operator/loss_binary_op.o build/src/operator/regression_output.o build/src/operator/sequence_reverse.o build/src/operator/c_lapack_api.o build/src/operator/identity_attach_KL_sparse_reg.o build/src/operator/bilinear_sampler.o build/src/operator/svm_output.o build/src/operator/optimizer_op.o build/src/operator/sequence_last.o build/src/operator/cross_device_copy.o build/src/operator/correlation.o build/src/operator/pad.o build/src/operator/leaky_relu.o build/src/operator/operator_tune.o build/src/operator/sequence_mask.o build/src/engine/naive_engine.o build/src/engine/openmp.o build/src/engine/threaded_engine_pooled.o build/src/engine/threaded_engine.o build/src/engine/engine.o build/src/engine/threaded_engine_perdevice.o build/src/storage/storage.o build/src/c_api/c_api_executor.o build/src/c_api/c_api_symbolic.o build/src/c_api/c_api_profile.o build/src/c_api/c_api_ndarray.o build/src/c_api/c_api_test.o build/src/c_api/c_predict_api.o build/src/c_api/c_api_function.o build/src/c_api/c_api.o build/src/c_api/c_api_error.o build/src/executor/onnx_to_tensorrt.o build/src/executor/inplace_addto_detect_pass.o build/src/executor/graph_executor.o build/src/executor/trt_graph_executor.o build/src/executor/infer_graph_attr_pass.o build/src/executor/tensorrt_pass.o build/src/executor/attach_op_execs_pass.o build/src/executor/attach_op_resource_pass.o build/src/kvstore/gradient_compression.o build/src/kvstore/kvstore_utils.o build/src/kvstore/kvstore.o build/src/resource.o build/src/libinfo.o build/src/initialize.o /home/mahmood/mx/mxnet/3rdparty/dmlc-core/libdmlc.a /home/mahmood/mx/mxnet/3rdparty/tvm/nnvm/lib/libnnvm.a build/src/operator/nn/cudnn/cudnn_batch_norm_gpu.o build/src/operator/tensor/elemwise_binary_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_basic_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_extended_gpu.o build/src/operator/tensor/matrix_op_gpu.o build/src/operator/tensor/ordering_op_gpu.o build/src/operator/tensor/elemwise_unary_op_trig_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_extended_gpu.o build/src/operator/tensor/diag_op_gpu.o build/src/operator/tensor/square_sum_gpu.o build/src/operator/tensor/elemwise_binary_op_extended_gpu.o build/src/operator/tensor/elemwise_sum_gpu.o build/src/operator/tensor/init_op_gpu.o build/src/operator/tensor/cast_storage_gpu.o build/src/operator/tensor/histogram_gpu.o build/src/operator/tensor/dot_gpu.o build/src/operator/tensor/elemwise_binary_scalar_op_logic_gpu.o build/src/operator/tensor/ravel_gpu.o build/src/operator/tensor/control_flow_op_gpu.o build/src/operator/tensor/broadcast_reduce_op_value_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_basic_gpu.o build/src/operator/tensor/broadcast_reduce_op_index_gpu.o build/src/operator/tensor/elemwise_scatter_op_gpu.o build/src/operator/tensor/indexing_op_gpu.o build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o build/src/operator/tensor/la_op_gpu.o build/src/operator/tensor/elemwise_binary_op_logic_gpu.o build/src/operator/tensor/elemwise_unary_op_basic_gpu.o build/src/operator/tensor/sparse_retain_gpu.o build/src/operator/contrib/optimizer_op_gpu.o build/src/operator/contrib/boolean_mask_gpu.o build/src/operator/contrib/adaptive_avg_pooling_gpu.o build/src/operator/contrib/ifft_gpu.o build/src/operator/contrib/multibox_detection_gpu.o build/src/operator/contrib/index_copy_gpu.o build/src/operator/contrib/tensorrt_gpu.o build/src/operator/contrib/multibox_target_gpu.o build/src/operator/contrib/proposal_gpu.o build/src/operator/contrib/bilinear_resize_gpu.o build/src/operator/contrib/count_sketch_gpu.o build/src/operator/contrib/dgl_graph_gpu.o build/src/operator/contrib/gradient_multiplier_op_gpu.o build/src/operator/contrib/bounding_box_gpu.o build/src/operator/contrib/fft_gpu.o build/src/operator/contrib/multibox_prior_gpu.o build/src/operator/contrib/deformable_psroi_pooling_gpu.o build/src/operator/contrib/quadratic_op_gpu.o build/src/operator/contrib/transformer_gpu.o build/src/operator/contrib/multi_proposal_gpu.o build/src/operator/contrib/adamw_gpu.o build/src/operator/contrib/sync_batch_norm_gpu.o build/src/operator/contrib/psroi_pooling_gpu.o build/src/operator/contrib/deformable_convolution_gpu.o build/src/operator/contrib/roi_align_gpu.o build/src/operator/random/shuffle_op_gpu.o build/src/operator/random/sample_multinomial_op_gpu.o build/src/operator/random/multisample_op_gpu.o build/src/operator/random/sample_op_gpu.o build/src/operator/quantization/requantize_gpu.o build/src/operator/quantization/quantize_gpu.o build/src/operator/quantization/dequantize_gpu.o build/src/operator/quantization/quantized_conv_gpu.o build/src/operator/quantization/quantized_flatten_gpu.o build/src/operator/quantization/quantized_fully_connected_gpu.o build/src/operator/quantization/quantized_pooling_gpu.o build/src/operator/quantization/quantize_v2_gpu.o build/src/operator/custom/native_op_gpu.o build/src/operator/image/resize_gpu.o build/src/operator/image/image_random_gpu.o build/src/operator/nn/lrn_gpu.o build/src/operator/nn/dropout_gpu.o build/src/operator/nn/softmax_activation_gpu.o build/src/operator/nn/fully_connected_gpu.o build/src/operator/nn/deconvolution_gpu.o build/src/operator/nn/pooling_gpu.o build/src/operator/nn/softmax_gpu.o build/src/operator/nn/activation_gpu.o build/src/operator/nn/ctc_loss_gpu.o build/src/operator/nn/convolution_gpu.o build/src/operator/nn/upsampling_gpu.o build/src/operator/nn/batch_norm_gpu.o build/src/operator/nn/layer_norm_gpu.o build/src/operator/nn/concat_gpu.o build/src/common/utils_gpu.o build/src/common/random_generator_gpu.o build/src/ndarray/ndarray_function_gpu.o build/src/operator/svm_output_gpu.o build/src/operator/optimizer_op_gpu.o build/src/operator/spatial_transformer_gpu.o build/src/operator/make_loss_gpu.o build/src/operator/pooling_v1_gpu.o build/src/operator/instance_norm_gpu.o build/src/operator/sequence_mask_gpu.o build/src/operator/correlation_gpu.o build/src/operator/slice_channel_gpu.o build/src/operator/rnn_gpu.o build/src/operator/crop_gpu.o build/src/operator/convolution_v1_gpu.o build/src/operator/sequence_reverse_gpu.o build/src/operator/identity_attach_KL_sparse_reg_gpu.o build/src/operator/leaky_relu_gpu.o build/src/operator/swapaxis_gpu.o build/src/operator/grid_generator_gpu.o build/src/operator/pad_gpu.o build/src/operator/bilinear_sampler_gpu.o build/src/operator/roi_pooling_gpu.o build/src/operator/batch_norm_v1_gpu.o build/src/operator/loss_binary_op_gpu.o build/src/operator/regression_output_gpu.o build/src/operator/l2_normalization_gpu.o build/src/operator/sequence_last_gpu.o build/src/operator/softmax_output_gpu.o build/src/kvstore/gradient_compression_gpu.o build/src/kvstore/kvstore_utils_gpu.o -pthread -lm -lcudart -lcublas -lcurand -lcusolver -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib -Wl,--as-needed -lmklml_intel -lmklml_gnu -liomp5 -L/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/lib/ -lopenblas -fopenmp -lrt -L/home/mahmood/mx/mxnet/3rdparty/mkldnn/build/install/lib -lmkldnn -Wl,-rpath,'${ORIGIN}' -lopencv_shape -lopencv_stitching -lopencv_superres -lopencv_videostab -lopencv_aruco -lopencv_bgsegm -lopencv_bioinspired -lopencv_ccalib -lopencv_datasets -lopencv_dpm -lopencv_face -lopencv_freetype -lopencv_fuzzy -lopencv_hdf -lopencv_line_descriptor -lopencv_optflow -lopencv_video -lopencv_plot -lopencv_reg -lopencv_saliency -lopencv_stereo -lopencv_structured_light -lopencv_phase_unwrapping -lopencv_rgbd -lopencv_viz -lopencv_surface_matching -lopencv_text -lopencv_ximgproc -lopencv_calib3d -lopencv_features2d -lopencv_flann -lopencv_xobjdetect -lopencv_objdetect -lopencv_ml -lopencv_xphoto -lopencv_highgui -lopencv_videoio -lopencv_imgcodecs -lopencv_photo -lopencv_imgproc -lopencv_core -lcudnn -lcufft -lcuda -lnvrtc -L/usr/local/cuda/lib64/stubs
  803. a - build/src/operator/contrib/nnvm_to_onnx.o
  804. a - build/src/operator/contrib/deformable_psroi_pooling.o
  805. a - build/src/operator/contrib/dgl_graph.o
  806. a - build/src/operator/contrib/fft.o
  807. a - build/src/operator/contrib/multibox_prior.o
  808. a - build/src/operator/contrib/gradient_multiplier_op.o
  809. a - build/src/operator/contrib/adamw.o
  810. a - build/src/operator/contrib/transformer.o
  811. a - build/src/operator/contrib/krprod.o
  812. a - build/src/operator/contrib/multi_proposal.o
  813. a - build/src/operator/contrib/index_copy.o
  814. a - build/src/operator/contrib/optimizer_op.o
  815. a - build/src/operator/contrib/bounding_box.o
  816. a - build/src/operator/contrib/proposal.o
  817. a - build/src/operator/contrib/boolean_mask.o
  818. a - build/src/operator/contrib/psroi_pooling.o
  819. a - build/src/operator/contrib/quadratic_op.o
  820. a - build/src/operator/contrib/deformable_convolution.o
  821. a - build/src/operator/contrib/ifft.o
  822. a - build/src/operator/contrib/adaptive_avg_pooling.o
  823. a - build/src/operator/random/sample_multinomial_op.o
  824. a - build/src/operator/random/multisample_op.o
  825. a - build/src/operator/random/unique_sample_op.o
  826. a - build/src/operator/random/sample_op.o
  827. a - build/src/operator/random/shuffle_op.o
  828. a - build/src/operator/quantization/requantize.o
  829. a - build/src/operator/quantization/dequantize.o
  830. a - build/src/operator/quantization/quantize_graph_pass.o
  831. a - build/src/operator/quantization/quantized_flatten.o
  832. a - build/src/operator/quantization/quantized_conv.o
  833. a - build/src/operator/quantization/quantized_fully_connected.o
  834. a - build/src/operator/quantization/quantized_pooling.o
  835. a - build/src/operator/quantization/quantize_v2.o
  836. a - build/src/operator/quantization/quantized_concat.o
  837. a - build/src/operator/quantization/quantize.o
  838. a - build/src/operator/custom/native_op.o
  839. a - build/src/operator/custom/ndarray_op.o
  840. a - build/src/operator/custom/custom.o
  841. a - build/src/operator/subgraph/partition_graph.o
  842. a - build/src/operator/subgraph/default_subgraph_property.o
  843. a - build/src/operator/nnpack/nnpack_util.o
  844. a - build/src/operator/image/image_random.o
  845. a - build/src/operator/image/resize.o
  846. a - build/src/operator/nn/softmax.o
  847. a - build/src/operator/nn/pooling.o
  848. a - build/src/operator/nn/deconvolution.o
  849. a - build/src/operator/nn/activation.o
  850. a - build/src/operator/nn/upsampling.o
  851. a - build/src/operator/nn/batch_norm.o
  852. a - build/src/operator/nn/ctc_loss.o
  853. a - build/src/operator/nn/fully_connected.o
  854. a - build/src/operator/nn/convolution.o
  855. a - build/src/operator/nn/layer_norm.o
  856. a - build/src/operator/nn/concat.o
  857. a - build/src/operator/nn/softmax_activation.o
  858. a - build/src/operator/nn/lrn.o
  859. a - build/src/operator/nn/dropout.o
  860. a - build/src/io/io.o
  861. a - build/src/io/image_aug_default.o
  862. a - build/src/io/iter_image_det_recordio.o
  863. a - build/src/io/image_io.o
  864. a - build/src/io/image_det_aug_default.o
  865. a - build/src/io/iter_csv.o
  866. a - build/src/io/iter_image_recordio.o
  867. a - build/src/io/iter_mnist.o
  868. a - build/src/io/iter_image_recordio_2.o
  869. a - build/src/io/iter_libsvm.o
  870. a - build/src/common/utils.o
  871. a - build/src/common/rtc.o
  872. a - build/src/nnvm/legacy_op_util.o
  873. a - build/src/nnvm/tvm_bridge.o
  874. a - build/src/nnvm/graph_editor.o
  875. a - build/src/nnvm/legacy_json_util.o
  876. a - build/src/profiler/profiler.o
  877. a - build/src/profiler/aggregate_stats.o
  878. a - build/src/profiler/vtune.o
  879. a - build/src/imperative/cached_op.o
  880. a - build/src/imperative/imperative_utils.o
  881. a - build/src/imperative/imperative.o
  882. a - build/src/ndarray/ndarray_function.o
  883. a - build/src/ndarray/ndarray.o
  884. a - build/src/operator/instance_norm.o
  885. a - build/src/operator/subgraph_op_common.o
  886. a - build/src/operator/grid_generator.o
  887. a - build/src/operator/pooling_v1.o
  888. a - build/src/operator/l2_normalization.o
  889. a - build/src/operator/rnn.o
  890. a - build/src/operator/make_loss.o
  891. a - build/src/operator/crop.o
  892. a - build/src/operator/spatial_transformer.o
  893. a - build/src/operator/operator.o
  894. a - build/src/operator/control_flow.o
  895. a - build/src/operator/swapaxis.o
  896. a - build/src/operator/convolution_v1.o
  897. a - build/src/operator/softmax_output.o
  898. a - build/src/operator/operator_util.o
  899. a - build/src/operator/roi_pooling.o
  900. a - build/src/operator/slice_channel.o
  901. a - build/src/operator/batch_norm_v1.o
  902. a - build/src/operator/loss_binary_op.o
  903. a - build/src/operator/regression_output.o
  904. a - build/src/operator/sequence_reverse.o
  905. a - build/src/operator/c_lapack_api.o
  906. a - build/src/operator/identity_attach_KL_sparse_reg.o
  907. a - build/src/operator/bilinear_sampler.o
  908. a - build/src/operator/svm_output.o
  909. a - build/src/operator/optimizer_op.o
  910. a - build/src/operator/sequence_last.o
  911. a - build/src/operator/cross_device_copy.o
  912. a - build/src/operator/correlation.o
  913. a - build/src/operator/pad.o
  914. a - build/src/operator/leaky_relu.o
  915. a - build/src/operator/operator_tune.o
  916. a - build/src/operator/sequence_mask.o
  917. a - build/src/engine/naive_engine.o
  918. a - build/src/engine/openmp.o
  919. a - build/src/engine/threaded_engine_pooled.o
  920. a - build/src/engine/threaded_engine.o
  921. a - build/src/engine/engine.o
  922. a - build/src/engine/threaded_engine_perdevice.o
  923. a - build/src/storage/storage.o
  924. a - build/src/c_api/c_api_executor.o
  925. a - build/src/c_api/c_api_symbolic.o
  926. a - build/src/c_api/c_api_profile.o
  927. a - build/src/c_api/c_api_ndarray.o
  928. a - build/src/c_api/c_api_test.o
  929. a - build/src/c_api/c_predict_api.o
  930. a - build/src/c_api/c_api_function.o
  931. a - build/src/c_api/c_api.o
  932. a - build/src/c_api/c_api_error.o
  933. a - build/src/executor/onnx_to_tensorrt.o
  934. a - build/src/executor/inplace_addto_detect_pass.o
  935. a - build/src/executor/graph_executor.o
  936. a - build/src/executor/trt_graph_executor.o
  937. a - build/src/executor/infer_graph_attr_pass.o
  938. a - build/src/executor/tensorrt_pass.o
  939. a - build/src/executor/attach_op_execs_pass.o
  940. a - build/src/executor/attach_op_resource_pass.o
  941. a - build/src/kvstore/gradient_compression.o
  942. a - build/src/kvstore/kvstore_utils.o
  943. a - build/src/kvstore/kvstore.o
  944. a - build/src/resource.o
  945. a - build/src/libinfo.o
  946. a - build/src/initialize.o
  947. a - build/src/operator/nn/cudnn/cudnn_batch_norm_gpu.o
  948. a - build/src/operator/tensor/elemwise_binary_op_basic_gpu.o
  949. a - build/src/operator/tensor/elemwise_binary_scalar_op_basic_gpu.o
  950. a - build/src/operator/tensor/elemwise_binary_scalar_op_extended_gpu.o
  951. a - build/src/operator/tensor/matrix_op_gpu.o
  952. a - build/src/operator/tensor/ordering_op_gpu.o
  953. a - build/src/operator/tensor/elemwise_unary_op_trig_gpu.o
  954. a - build/src/operator/tensor/elemwise_binary_broadcast_op_extended_gpu.o
  955. a - build/src/operator/tensor/diag_op_gpu.o
  956. a - build/src/operator/tensor/square_sum_gpu.o
  957. a - build/src/operator/tensor/elemwise_binary_op_extended_gpu.o
  958. a - build/src/operator/tensor/elemwise_sum_gpu.o
  959. a - build/src/operator/tensor/init_op_gpu.o
  960. a - build/src/operator/tensor/cast_storage_gpu.o
  961. a - build/src/operator/tensor/histogram_gpu.o
  962. a - build/src/operator/tensor/dot_gpu.o
  963. a - build/src/operator/tensor/elemwise_binary_scalar_op_logic_gpu.o
  964. a - build/src/operator/tensor/ravel_gpu.o
  965. a - build/src/operator/tensor/control_flow_op_gpu.o
  966. a - build/src/operator/tensor/broadcast_reduce_op_value_gpu.o
  967. a - build/src/operator/tensor/elemwise_binary_broadcast_op_basic_gpu.o
  968. a - build/src/operator/tensor/broadcast_reduce_op_index_gpu.o
  969. a - build/src/operator/tensor/elemwise_scatter_op_gpu.o
  970. a - build/src/operator/tensor/indexing_op_gpu.o
  971. a - build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o
  972. a - build/src/operator/tensor/la_op_gpu.o
  973. a - build/src/operator/tensor/elemwise_binary_op_logic_gpu.o
  974. a - build/src/operator/tensor/elemwise_unary_op_basic_gpu.o
  975. a - build/src/operator/tensor/sparse_retain_gpu.o
  976. a - build/src/operator/contrib/optimizer_op_gpu.o
  977. a - build/src/operator/contrib/boolean_mask_gpu.o
  978. a - build/src/operator/contrib/adaptive_avg_pooling_gpu.o
  979. a - build/src/operator/contrib/ifft_gpu.o
  980. a - build/src/operator/contrib/multibox_detection_gpu.o
  981. a - build/src/operator/contrib/index_copy_gpu.o
  982. a - build/src/operator/contrib/tensorrt_gpu.o
  983. a - build/src/operator/contrib/multibox_target_gpu.o
  984. a - build/src/operator/contrib/proposal_gpu.o
  985. a - build/src/operator/contrib/bilinear_resize_gpu.o
  986. a - build/src/operator/contrib/count_sketch_gpu.o
  987. a - build/src/operator/contrib/dgl_graph_gpu.o
  988. a - build/src/operator/contrib/gradient_multiplier_op_gpu.o
  989. a - build/src/operator/contrib/bounding_box_gpu.o
  990. a - build/src/operator/contrib/fft_gpu.o
  991. a - build/src/operator/contrib/multibox_prior_gpu.o
  992. a - build/src/operator/contrib/deformable_psroi_pooling_gpu.o
  993. a - build/src/operator/contrib/quadratic_op_gpu.o
  994. a - build/src/operator/contrib/transformer_gpu.o
  995. a - build/src/operator/contrib/multi_proposal_gpu.o
  996. a - build/src/operator/contrib/adamw_gpu.o
  997. a - build/src/operator/contrib/sync_batch_norm_gpu.o
  998. a - build/src/operator/contrib/psroi_pooling_gpu.o
  999. a - build/src/operator/contrib/deformable_convolution_gpu.o
  1000. a - build/src/operator/contrib/roi_align_gpu.o
  1001. a - build/src/operator/random/shuffle_op_gpu.o
  1002. a - build/src/operator/random/sample_multinomial_op_gpu.o
  1003. a - build/src/operator/random/multisample_op_gpu.o
  1004. a - build/src/operator/random/sample_op_gpu.o
  1005. a - build/src/operator/quantization/requantize_gpu.o
  1006. a - build/src/operator/quantization/quantize_gpu.o
  1007. a - build/src/operator/quantization/dequantize_gpu.o
  1008. a - build/src/operator/quantization/quantized_conv_gpu.o
  1009. a - build/src/operator/quantization/quantized_flatten_gpu.o
  1010. a - build/src/operator/quantization/quantized_fully_connected_gpu.o
  1011. a - build/src/operator/quantization/quantized_pooling_gpu.o
  1012. a - build/src/operator/quantization/quantize_v2_gpu.o
  1013. a - build/src/operator/custom/native_op_gpu.o
  1014. a - build/src/operator/image/resize_gpu.o
  1015. a - build/src/operator/image/image_random_gpu.o
  1016. a - build/src/operator/nn/lrn_gpu.o
  1017. a - build/src/operator/nn/dropout_gpu.o
  1018. a - build/src/operator/nn/softmax_activation_gpu.o
  1019. a - build/src/operator/nn/fully_connected_gpu.o
  1020. a - build/src/operator/nn/deconvolution_gpu.o
  1021. a - build/src/operator/nn/pooling_gpu.o
  1022. a - build/src/operator/nn/softmax_gpu.o
  1023. a - build/src/operator/nn/activation_gpu.o
  1024. a - build/src/operator/nn/ctc_loss_gpu.o
  1025. a - build/src/operator/nn/convolution_gpu.o
  1026. a - build/src/operator/nn/upsampling_gpu.o
  1027. a - build/src/operator/nn/batch_norm_gpu.o
  1028. a - build/src/operator/nn/layer_norm_gpu.o
  1029. a - build/src/operator/nn/concat_gpu.o
  1030. a - build/src/common/utils_gpu.o
  1031. a - build/src/common/random_generator_gpu.o
  1032. a - build/src/ndarray/ndarray_function_gpu.o
  1033. a - build/src/operator/svm_output_gpu.o
  1034. a - build/src/operator/optimizer_op_gpu.o
  1035. a - build/src/operator/spatial_transformer_gpu.o
  1036. a - build/src/operator/make_loss_gpu.o
  1037. a - build/src/operator/pooling_v1_gpu.o
  1038. a - build/src/operator/instance_norm_gpu.o
  1039. a - build/src/operator/sequence_mask_gpu.o
  1040. a - build/src/operator/correlation_gpu.o
  1041. a - build/src/operator/slice_channel_gpu.o
  1042. a - build/src/operator/rnn_gpu.o
  1043. a - build/src/operator/crop_gpu.o
  1044. a - build/src/operator/convolution_v1_gpu.o
  1045. a - build/src/operator/sequence_reverse_gpu.o
  1046. a - build/src/operator/identity_attach_KL_sparse_reg_gpu.o
  1047. a - build/src/operator/leaky_relu_gpu.o
  1048. a - build/src/operator/swapaxis_gpu.o
  1049. a - build/src/operator/grid_generator_gpu.o
  1050. a - build/src/operator/pad_gpu.o
  1051. a - build/src/operator/bilinear_sampler_gpu.o
  1052. a - build/src/operator/roi_pooling_gpu.o
  1053. a - build/src/operator/batch_norm_v1_gpu.o
  1054. a - build/src/operator/loss_binary_op_gpu.o
  1055. a - build/src/operator/regression_output_gpu.o
  1056. a - build/src/operator/l2_normalization_gpu.o
  1057. a - build/src/operator/sequence_last_gpu.o
  1058. a - build/src/operator/softmax_output_gpu.o
  1059. a - build/src/kvstore/gradient_compression_gpu.o
  1060. a - build/src/kvstore/kvstore_utils_gpu.o
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!