hs_tohidi
/
cimp-impl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Compare commits

merge into: hs_tohidi:master
hs_tohidi:detached
hs_tohidi:master
...
pull from: hs_tohidi:detached
hs_tohidi:detached
hs_tohidi:master

2 Commits
master ... detached

Author SHA1 Message Date
mht ba35c5b500 a stable stage
1 week ago
mht c4156feccc Refactor: Remove double precision in BBRegressor LinearBlock
1 week ago
42 changed files with 1384 additions and 20149 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats
  1. 1
      .idea/vcs.xml
  2. 32
      CMakeLists.txt
  3. 52
      bb_regressor_stats.txt
  4. BIN
      bin/tracking_demo
  5. 29
      build.sh
  6. 16
      build/CMakeCache.txt
  7. BIN
      build/CMakeFiles/3.22.1/CMakeDetermineCompilerABI_CUDA.bin
  8. 418
      build/CMakeFiles/CMakeOutput.log
  9. 2
      build/CMakeFiles/Makefile.cmake
  10. 67
      build/CMakeFiles/Makefile2
  11. 2
      build/CMakeFiles/TargetDirectories.txt
  12. 1
      build/CMakeFiles/bb_regressor.dir/DependInfo.cmake
  13. 20
      build/CMakeFiles/bb_regressor.dir/build.make
  14. BIN
      build/CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o
  15. 2
      build/CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o.d
  16. 2
      build/CMakeFiles/bb_regressor.dir/cmake_clean.cmake
  17. 163
      build/CMakeFiles/bb_regressor.dir/compiler_depend.internal
  18. 246
      build/CMakeFiles/bb_regressor.dir/compiler_depend.make
  19. 2
      build/CMakeFiles/bb_regressor.dir/link.txt
  20. 1
      build/CMakeFiles/bb_regressor.dir/progress.make
  21. BIN
      build/CMakeFiles/classifier.dir/cimp/classifier/classifier.cpp.o
  22. 4
      build/CMakeFiles/classifier.dir/progress.make
  23. 2
      build/CMakeFiles/progress.marks
  24. BIN
      build/CMakeFiles/tracking_demo.dir/cimp/demo.cpp.o
  25. 4830
      build/CMakeFiles/tracking_demo.dir/compiler_depend.internal
  26. 14481
      build/CMakeFiles/tracking_demo.dir/compiler_depend.make
  27. 4
      build/CMakeFiles/tracking_demo.dir/progress.make
  28. 109
      build/Makefile
  29. 40
      build/cmake_install.cmake
  30. 4
      build/install_manifest.txt
  31. BIN
      build/libbb_regressor.a
  32. BIN
      build/libclassifier.a
  33. BIN
      build/tracking_demo
  34. 439
      cimp/bb_regressor/bb_regressor.cpp
  35. 10
      cimp/bb_regressor/bb_regressor.h
  36. 135
      cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.c
  37. 33
      cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cu
  38. 20
      cimp/demo.cpp
  39. 12
      classifier_stats.txt
  40. 9
      cmake-build-debug/CMakeCache.txt
  41. 4
      run_demo.sh
  42. 341
      test/compare_models.py

1
.idea/vcs.xml
View File

@ -1,6 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
<mapping directory="$PROJECT_DIR$/vcpkg" vcs="Git" />
</component>
</project>

32
CMakeLists.txt
View File

@ -12,19 +12,13 @@ find_package(Torch REQUIRED)
message(STATUS "Found LibTorch: ${TORCH_LIBRARIES}")
# Determine whether to use CPU-only or CUDA implementation
option(CPU_ONLY "Build without CUDA support" TRUE)
if(CPU_ONLY)
message(STATUS "Building in CPU-only mode")
add_definitions(-DCPU_ONLY)
else()
message(STATUS "Building with CUDA support")
endif()
# Always use CUDA implementation (no CPU fallback)
message(STATUS "Building with CUDA support")
# Define source files for the libraries
set(BB_REGRESSOR_SOURCES
cimp/bb_regressor/bb_regressor.cpp
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp
)
set(CLASSIFIER_SOURCES
@ -53,13 +47,23 @@ add_executable(tracking_demo cimp/demo.cpp)
# Link the demo with the libraries
target_link_libraries(tracking_demo PRIVATE bb_regressor classifier ${TORCH_LIBRARIES})
# Create the test models executable
add_executable(test_models test/test_models.cpp)
# Link the test with the libraries
target_link_libraries(test_models PRIVATE bb_regressor classifier ${TORCH_LIBRARIES})
# Create the test sample generator executable (without dependencies on our libraries)
add_executable(generate_test_samples test/generate_test_samples.cpp)
# Link the test sample generator only with LibTorch
target_link_libraries(generate_test_samples PRIVATE ${TORCH_LIBRARIES})
# Copy the executable to the binary directory
install(TARGETS tracking_demo DESTINATION bin)
install(TARGETS test_models DESTINATION bin)
install(TARGETS generate_test_samples DESTINATION bin)
# Print some info during the build
message(STATUS "LibTorch found at: ${TORCH_INCLUDE_DIRS}")
if(CPU_ONLY)
message(STATUS "Using CPU-only build")
else()
message(STATUS "Using CUDA-enabled build")
endif()
message(STATUS "Using CUDA-enabled build")

52
bb_regressor_stats.txt
View File

@ -1,45 +1,45 @@
Output 0:
Shape: [1, 256, 18, 18]
Mean: 0.261343
Std: 0.373308
Mean: 0.260712
Std: 0.375281
Min: 0
Max: 2.83079
Sum: 21676.9
Sample values: [0.273305, 0.153942, 0.0177385]
Max: 2.83518
Sum: 21624.5
Sample values: [0.270668, 0.159451, 0]
Output 1:
Shape: [1, 256, 9, 9]
Mean: 0.334883
Std: 0.854804
Mean: 0.338533
Std: 0.864997
Min: 0
Max: 7.18794
Sum: 6944.14
Sample values: [6.22439, 0, 0]
Max: 7.52249
Sum: 7019.83
Sample values: [6.37661, 0, 0]
Output 2:
Shape: [1, 256, 1, 1]
Mean: 0.412101
Std: 0.568328
Shape: [1, 256]
Mean: 0.0984123
Std: 0.273788
Min: 0
Max: 2.80441
Sum: 105.498
Max: 1.96461
Sum: 25.1935
Sample values: [0]
Output 3:
Shape: [1, 256, 1, 1]
Mean: 0.413812
Std: 0.62911
Shape: [1, 256]
Mean: 0.651337
Std: 1.65163
Min: 0
Max: 3.27012
Sum: 105.936
Max: 10.0534
Sum: 166.742
Sample values: [0]
Output 4:
Shape: [1, 5]
Mean: 0.441597
Std: 0.430799
Min: 0.0278997
Max: 0.899234
Sum: 2.20798
Sample values: [0.0278997]
Mean: -2.65813
Std: 8.42937e-08
Min: -2.65813
Max: -2.65813
Sum: -13.2907
Sample values: [-2.65813]

BIN
bin/tracking_demo
View File

29
build.sh
View File

@ -28,7 +28,9 @@ if [ $CUDA_AVAILABLE -eq 1 ]; then
CUDA_VERSION=$(nvcc --version | grep "release" | awk '{print $6}' | cut -c2- | cut -d'.' -f1-2)
echo "Detected CUDA version: $CUDA_VERSION"
else
echo "CUDA not found, building in CPU-only mode"
echo "CUDA not found. The project requires CUDA to build."
echo "Please install CUDA and try again."
exit 1
fi
# Download and extract LibTorch with appropriate CUDA support if not already present
@ -36,18 +38,13 @@ LIBTORCH_DIR="$HOME/libtorch"
if [ ! -d "$LIBTORCH_DIR" ]; then
echo "Downloading LibTorch..."
# Use a compatible version based on detected CUDA
if [ $CUDA_AVAILABLE -eq 1 ]; then
echo "Downloading CUDA-enabled LibTorch"
if [[ "$CUDA_VERSION" == "11.5" || "$CUDA_VERSION" == "11.6" || "$CUDA_VERSION" == "11.7" ]]; then
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu116/libtorch-cxx11-abi-shared-with-deps-1.13.0%2Bcu116.zip"
elif [[ "$CUDA_VERSION" == "11.3" || "$CUDA_VERSION" == "11.4" ]]; then
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu113/libtorch-cxx11-abi-shared-with-deps-1.12.1%2Bcu113.zip"
else
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu118/libtorch-cxx11-abi-shared-with-deps-2.0.0%2Bcu118.zip"
fi
echo "Downloading CUDA-enabled LibTorch"
if [[ "$CUDA_VERSION" == "11.5" || "$CUDA_VERSION" == "11.6" || "$CUDA_VERSION" == "11.7" ]]; then
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu116/libtorch-cxx11-abi-shared-with-deps-1.13.0%2Bcu116.zip"
elif [[ "$CUDA_VERSION" == "11.3" || "$CUDA_VERSION" == "11.4" ]]; then
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu113/libtorch-cxx11-abi-shared-with-deps-1.12.1%2Bcu113.zip"
else
echo "Downloading CPU-only LibTorch"
LIBTORCH_URL="https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.0.0%2Bcpu.zip"
LIBTORCH_URL="https://download.pytorch.org/libtorch/cu118/libtorch-cxx11-abi-shared-with-deps-2.0.0%2Bcu118.zip"
fi
wget $LIBTORCH_URL -O libtorch.zip
@ -67,13 +64,9 @@ cd build
# Create local bin directory
mkdir -p ../bin
# Configure with CMake
# Configure with CMake - always use CUDA, never use CPU_ONLY
echo "Configuring with CMake..."
if [ $CUDA_AVAILABLE -eq 1 ]; then
cmake .. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=.. -DCPU_ONLY=OFF
else
cmake .. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=.. -DCPU_ONLY=ON
fi
cmake .. -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=.. -DCPU_ONLY=OFF
# Build the project
echo "Building the project..."

16
build/CMakeCache.txt
View File

@ -207,8 +207,8 @@ CMAKE_STRIP:FILEPATH=/usr/bin/strip
// Studio IDE projects all commands are done without /nologo.
CMAKE_VERBOSE_MAKEFILE:BOOL=FALSE
//Build without CUDA support
CPU_ONLY:BOOL=OFF
//No help, variable specified on the command line.
CPU_ONLY:UNINITIALIZED=OFF
//Compile device code in 64 bit mode
CUDA_64_BIT_DEVICE_CODE:BOOL=ON
@ -373,9 +373,6 @@ TORCH_LIBRARY:FILEPATH=/home/mht/libtorch/lib/libtorch.so
//The directory containing a CMake configuration file for Torch.
Torch_DIR:PATH=/home/mht/libtorch/share/cmake/Torch
//Use ROI Align from torchvision
USE_ROI_ALIGN:BOOL=OFF
//Path to a library.
c10_LIBRARY:FILEPATH=/home/mht/libtorch/lib/libc10.so
@ -388,15 +385,6 @@ cpp_tracker_IS_TOP_LEVEL:STATIC=ON
//Value Computed by CMake
cpp_tracker_SOURCE_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker
//Value Computed by CMake
cpp_tracker_tests_BINARY_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker/build/test
//Value Computed by CMake
cpp_tracker_tests_IS_TOP_LEVEL:STATIC=OFF
//Value Computed by CMake
cpp_tracker_tests_SOURCE_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker/test
//Path to a library.
kineto_LIBRARY:FILEPATH=/home/mht/libtorch/lib/libkineto.a

BIN
build/CMakeFiles/3.22.1/CMakeDetermineCompilerABI_CUDA.bin
View File

418
build/CMakeFiles/CMakeOutput.log
View File

@ -12,13 +12,150 @@ Compilation of the CXX compiler identification source "CMakeCXXCompilerId.cpp" p
The CXX compiler identification is GNU, found in "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCXX/a.out"
Checking whether the CUDA compiler is NVIDIA using "" matched "nvcc: NVIDIA \(R\) Cuda compiler driver":
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0
Compiling the CUDA compiler identification source file "CMakeCUDACompilerId.cu" succeeded.
Compiler: /usr/bin/nvcc
Build flags:
Id flags: --keep;--keep-dir;tmp -v
The output was:
0
#$ _NVVM_BRANCH_=nvvm
#$ _SPACE_=
#$ _CUDART_=cudart
#$ _HERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _THERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _TARGET_SIZE_=
#$ _TARGET_DIR_=
#$ _TARGET_SIZE_=64
#$ NVVMIR_LIBRARY_DIR=/usr/lib/nvidia-cuda-toolkit/libdevice
#$ PATH=/usr/lib/nvidia-cuda-toolkit/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorF6bS95/usr/bin:/tmp/.mount_cursorF6bS95/usr/sbin:/tmp/.mount_cursorF6bS95/usr/games:/tmp/.mount_cursorF6bS95/bin:/tmp/.mount_cursorF6bS95/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts
#$ LIBRARIES= -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu
#$ rm tmp/a_dlink.reg.c
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii"
#$ cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"
#$ ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin"
#$ fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o"
#$ nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"
#$ fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o"
#$ g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out"
Compilation of the CUDA compiler identification source "CMakeCUDACompilerId.cu" produced "a.out"
The CUDA compiler identification is NVIDIA, found in "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/a.out"
Parsed CUDA nvcc implicit link information from above output:
found 'PATH=' string: [/usr/lib/nvidia-cuda-toolkit/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorF6bS95/usr/bin:/tmp/.mount_cursorF6bS95/usr/sbin:/tmp/.mount_cursorF6bS95/usr/games:/tmp/.mount_cursorF6bS95/bin:/tmp/.mount_cursorF6bS95/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts]
found 'LIBRARIES=' string: [-L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu]
considering line: [#$ rm tmp/a_dlink.reg.c]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii" ]
considering line: [cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"]
considering line: [ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin" ]
considering line: [fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o" ]
considering line: [nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"]
ignoring nvlink line
considering line: [fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o" ]
considering line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
extracted link line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
considering line: []
extracted link launcher name: [g++]
found link launcher absolute path: [/usr/lib/nvidia-cuda-toolkit/bin/g++]
link line regex: [^( *|.*[/\])(ld|CMAKE_LINK_STARTFILE-NOTFOUND|([^/\]+-)?ld|collect2)[^/\]*( |$)]
link line: [cuda-fake-ld g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
arg [cuda-fake-ld] ==> ignore
arg [g++] ==> ignore
arg [-D__CUDA_ARCH_LIST__=520] ==> ignore
arg [-m64] ==> ignore
arg [-Wl,--start-group] ==> ignore
arg [tmp/a_dlink.o] ==> ignore
arg [tmp/CMakeCUDACompilerId.o] ==> ignore
arg [-L/usr/lib/x86_64-linux-gnu/stubs] ==> dir [/usr/lib/x86_64-linux-gnu/stubs]
arg [-L/usr/lib/x86_64-linux-gnu] ==> dir [/usr/lib/x86_64-linux-gnu]
arg [-lcudadevrt] ==> lib [cudadevrt]
arg [-lcudart_static] ==> lib [cudart_static]
arg [-lrt] ==> lib [rt]
arg [-lpthread] ==> lib [pthread]
arg [-ldl] ==> lib [dl]
arg [-Wl,--end-group] ==> ignore
arg [-o] ==> ignore
arg [a.out] ==> ignore
collapse library dir [/usr/lib/x86_64-linux-gnu/stubs] ==> [/usr/lib/x86_64-linux-gnu/stubs]
collapse library dir [/usr/lib/x86_64-linux-gnu] ==> [/usr/lib/x86_64-linux-gnu]
implicit libs: [cudadevrt;cudart_static;rt;pthread;dl]
implicit objs: []
implicit dirs: [/usr/lib/x86_64-linux-gnu/stubs;/usr/lib/x86_64-linux-gnu]
implicit fwks: []
Failed to detect CUDA nvcc include information:
found 'PATH=' string: [/usr/lib/nvidia-cuda-toolkit/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorF6bS95/usr/bin:/tmp/.mount_cursorF6bS95/usr/sbin:/tmp/.mount_cursorF6bS95/usr/games:/tmp/.mount_cursorF6bS95/bin:/tmp/.mount_cursorF6bS95/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts]
found 'LIBRARIES=' string: [-L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu]
considering line: [#$ rm tmp/a_dlink.reg.c]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii" ]
considering line: [cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"]
considering line: [ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin" ]
considering line: [fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o" ]
considering line: [nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"]
ignoring nvlink line
considering line: [fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o" ]
considering line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
extracted link line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
considering line: []
extracted link launcher name: [g++]
found link launcher absolute path: [/usr/lib/nvidia-cuda-toolkit/bin/g++]
no 'INCLUDES=' string found in nvcc output:
#$ _NVVM_BRANCH_=nvvm
#$ _SPACE_=
#$ _CUDART_=cudart
#$ _HERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _THERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _TARGET_SIZE_=
#$ _TARGET_DIR_=
#$ _TARGET_SIZE_=64
#$ NVVMIR_LIBRARY_DIR=/usr/lib/nvidia-cuda-toolkit/libdevice
#$ PATH=/usr/lib/nvidia-cuda-toolkit/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorF6bS95/usr/bin:/tmp/.mount_cursorF6bS95/usr/sbin:/tmp/.mount_cursorF6bS95/usr/games:/tmp/.mount_cursorF6bS95/bin:/tmp/.mount_cursorF6bS95/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts
#$ LIBRARIES= -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu
#$ rm tmp/a_dlink.reg.c
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii"
#$ cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"
#$ ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin"
#$ fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o"
#$ nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"
#$ fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o"
#$ g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out"
Detecting CXX compiler ABI info compiled with the following output:
Change Dir: /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp
Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_51a9f/fast && /usr/bin/gmake -f CMakeFiles/cmTC_51a9f.dir/build.make CMakeFiles/cmTC_51a9f.dir/build
Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_50e53/fast && /usr/bin/gmake -f CMakeFiles/cmTC_50e53.dir/build.make CMakeFiles/cmTC_50e53.dir/build
gmake[1]: Entering directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp'
Building CXX object CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o
/usr/bin/c++ -v -o CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -c /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp
Building CXX object CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o
/usr/bin/c++ -v -o CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -c /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp
Using built-in specs.
COLLECT_GCC=/usr/bin/c++
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
@ -28,8 +165,8 @@ Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp -quiet -dumpdir CMakeFiles/cmTC_51a9f.dir/ -dumpbase CMakeCXXCompilerABI.cpp.cpp -dumpbase-ext .cpp -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccZejfDs.s
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp -quiet -dumpdir CMakeFiles/cmTC_50e53.dir/ -dumpbase CMakeCXXCompilerABI.cpp.cpp -dumpbase-ext .cpp -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/cc8sAEZe.s
GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)
compiled by GNU C version 11.4.0, GMP version 6.2.1, MPFR version 4.1.0, MPC version 1.2.1, isl version isl-0.24-GMP
@ -53,15 +190,15 @@ GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)
GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
Compiler executable checksum: d591828bb4d392ae8b7b160e5bb0b95f
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/'
as -v --64 -o CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o /tmp/ccZejfDs.s
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/'
as -v --64 -o CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o /tmp/cc8sAEZe.s
GNU assembler version 2.38 (x86_64-linux-gnu) using BFD version (GNU Binutils for Ubuntu) 2.38
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.'
Linking CXX executable cmTC_51a9f
/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_51a9f.dir/link.txt --verbose=1
/usr/bin/c++ -v CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -o cmTC_51a9f
COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.'
Linking CXX executable cmTC_50e53
/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_50e53.dir/link.txt --verbose=1
/usr/bin/c++ -v CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -o cmTC_50e53
Using built-in specs.
COLLECT_GCC=/usr/bin/c++
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper
@ -74,9 +211,9 @@ Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_51a9f' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_51a9f.'
/usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccJLlbFI.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_51a9f /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_51a9f' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_51a9f.'
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_50e53' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_50e53.'
/usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/cctwOU9y.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_50e53 /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_50e53' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_50e53.'
gmake[1]: Leaving directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp'
@ -106,10 +243,10 @@ Parsed CXX implicit link information from above output:
link line regex: [^( *|.*[/\])(ld|CMAKE_LINK_STARTFILE-NOTFOUND|([^/\]+-)?ld|collect2)[^/\]*( |$)]
ignore line: [Change Dir: /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp]
ignore line: []
ignore line: [Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_51a9f/fast && /usr/bin/gmake -f CMakeFiles/cmTC_51a9f.dir/build.make CMakeFiles/cmTC_51a9f.dir/build]
ignore line: [Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_50e53/fast && /usr/bin/gmake -f CMakeFiles/cmTC_50e53.dir/build.make CMakeFiles/cmTC_50e53.dir/build]
ignore line: [gmake[1]: Entering directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp']
ignore line: [Building CXX object CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o]
ignore line: [/usr/bin/c++ -v -o CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -c /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp]
ignore line: [Building CXX object CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o]
ignore line: [/usr/bin/c++ -v -o CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -c /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp]
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=/usr/bin/c++]
ignore line: [OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa]
@ -119,8 +256,8 @@ Parsed CXX implicit link information from above output:
ignore line: [Thread model: posix]
ignore line: [Supported LTO compression algorithms: zlib zstd]
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp -quiet -dumpdir CMakeFiles/cmTC_51a9f.dir/ -dumpbase CMakeCXXCompilerABI.cpp.cpp -dumpbase-ext .cpp -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccZejfDs.s]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE /usr/share/cmake-3.22/Modules/CMakeCXXCompilerABI.cpp -quiet -dumpdir CMakeFiles/cmTC_50e53.dir/ -dumpbase CMakeCXXCompilerABI.cpp.cpp -dumpbase-ext .cpp -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/cc8sAEZe.s]
ignore line: [GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)]
ignore line: [ compiled by GNU C version 11.4.0 GMP version 6.2.1 MPFR version 4.1.0 MPC version 1.2.1 isl version isl-0.24-GMP]
ignore line: []
@ -144,15 +281,15 @@ Parsed CXX implicit link information from above output:
ignore line: []
ignore line: [GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072]
ignore line: [Compiler executable checksum: d591828bb4d392ae8b7b160e5bb0b95f]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/']
ignore line: [ as -v --64 -o CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o /tmp/ccZejfDs.s]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/']
ignore line: [ as -v --64 -o CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o /tmp/cc8sAEZe.s]
ignore line: [GNU assembler version 2.38 (x86_64-linux-gnu) using BFD version (GNU Binutils for Ubuntu) 2.38]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.']
ignore line: [Linking CXX executable cmTC_51a9f]
ignore line: [/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_51a9f.dir/link.txt --verbose=1]
ignore line: [/usr/bin/c++ -v CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -o cmTC_51a9f ]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o' '-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.']
ignore line: [Linking CXX executable cmTC_50e53]
ignore line: [/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_50e53.dir/link.txt --verbose=1]
ignore line: [/usr/bin/c++ -v CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -o cmTC_50e53 ]
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=/usr/bin/c++]
ignore line: [COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper]
@ -165,13 +302,13 @@ Parsed CXX implicit link information from above output:
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_51a9f' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_51a9f.']
link line: [ /usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccJLlbFI.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_51a9f /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_50e53' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_50e53.']
link line: [ /usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/cctwOU9y.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_50e53 /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/collect2] ==> ignore
arg [-plugin] ==> ignore
arg [/usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so] ==> ignore
arg [-plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper] ==> ignore
arg [-plugin-opt=-fresolution=/tmp/ccJLlbFI.res] ==> ignore
arg [-plugin-opt=-fresolution=/tmp/cctwOU9y.res] ==> ignore
arg [-plugin-opt=-pass-through=-lgcc_s] ==> ignore
arg [-plugin-opt=-pass-through=-lgcc] ==> ignore
arg [-plugin-opt=-pass-through=-lc] ==> ignore
@ -189,7 +326,7 @@ Parsed CXX implicit link information from above output:
arg [-znow] ==> ignore
arg [-zrelro] ==> ignore
arg [-o] ==> ignore
arg [cmTC_51a9f] ==> ignore
arg [cmTC_50e53] ==> ignore
arg [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o]
@ -201,7 +338,7 @@ Parsed CXX implicit link information from above output:
arg [-L/usr/lib/x86_64-linux-gnu] ==> dir [/usr/lib/x86_64-linux-gnu]
arg [-L/usr/lib/../lib] ==> dir [/usr/lib/../lib]
arg [-L/usr/lib/gcc/x86_64-linux-gnu/11/../../..] ==> dir [/usr/lib/gcc/x86_64-linux-gnu/11/../../..]
arg [CMakeFiles/cmTC_51a9f.dir/CMakeCXXCompilerABI.cpp.o] ==> ignore
arg [CMakeFiles/cmTC_50e53.dir/CMakeCXXCompilerABI.cpp.o] ==> ignore
arg [-lstdc++] ==> lib [stdc++]
arg [-lm] ==> lib [m]
arg [-lgcc_s] ==> lib [gcc_s]
@ -228,150 +365,13 @@ Parsed CXX implicit link information from above output:
implicit fwks: []
Checking whether the CUDA compiler is NVIDIA using "" matched "nvcc: NVIDIA \(R\) Cuda compiler driver":
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0
Compiling the CUDA compiler identification source file "CMakeCUDACompilerId.cu" succeeded.
Compiler: /usr/bin/nvcc
Build flags:
Id flags: --keep;--keep-dir;tmp -v
The output was:
0
#$ _NVVM_BRANCH_=nvvm
#$ _SPACE_=
#$ _CUDART_=cudart
#$ _HERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _THERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _TARGET_SIZE_=
#$ _TARGET_DIR_=
#$ _TARGET_SIZE_=64
#$ NVVMIR_LIBRARY_DIR=/usr/lib/nvidia-cuda-toolkit/libdevice
#$ PATH=/usr/lib/nvidia-cuda-toolkit/bin:/usr/lib/cuda/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorUdwtnC/usr/bin:/tmp/.mount_cursorUdwtnC/usr/sbin:/tmp/.mount_cursorUdwtnC/usr/games:/tmp/.mount_cursorUdwtnC/bin:/tmp/.mount_cursorUdwtnC/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts
#$ LIBRARIES= -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu
#$ rm tmp/a_dlink.reg.c
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii"
#$ cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"
#$ ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin"
#$ fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o"
#$ nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"
#$ fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o"
#$ g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out"
Compilation of the CUDA compiler identification source "CMakeCUDACompilerId.cu" produced "a.out"
The CUDA compiler identification is NVIDIA, found in "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/a.out"
Parsed CUDA nvcc implicit link information from above output:
found 'PATH=' string: [/usr/lib/nvidia-cuda-toolkit/bin:/usr/lib/cuda/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorUdwtnC/usr/bin:/tmp/.mount_cursorUdwtnC/usr/sbin:/tmp/.mount_cursorUdwtnC/usr/games:/tmp/.mount_cursorUdwtnC/bin:/tmp/.mount_cursorUdwtnC/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts]
found 'LIBRARIES=' string: [-L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu]
considering line: [#$ rm tmp/a_dlink.reg.c]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii" ]
considering line: [cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"]
considering line: [ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin" ]
considering line: [fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o" ]
considering line: [nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"]
ignoring nvlink line
considering line: [fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o" ]
considering line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
extracted link line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
considering line: []
extracted link launcher name: [g++]
found link launcher absolute path: [/usr/lib/nvidia-cuda-toolkit/bin/g++]
link line regex: [^( *|.*[/\])(ld|CMAKE_LINK_STARTFILE-NOTFOUND|([^/\]+-)?ld|collect2)[^/\]*( |$)]
link line: [cuda-fake-ld g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
arg [cuda-fake-ld] ==> ignore
arg [g++] ==> ignore
arg [-D__CUDA_ARCH_LIST__=520] ==> ignore
arg [-m64] ==> ignore
arg [-Wl,--start-group] ==> ignore
arg [tmp/a_dlink.o] ==> ignore
arg [tmp/CMakeCUDACompilerId.o] ==> ignore
arg [-L/usr/lib/x86_64-linux-gnu/stubs] ==> dir [/usr/lib/x86_64-linux-gnu/stubs]
arg [-L/usr/lib/x86_64-linux-gnu] ==> dir [/usr/lib/x86_64-linux-gnu]
arg [-lcudadevrt] ==> lib [cudadevrt]
arg [-lcudart_static] ==> lib [cudart_static]
arg [-lrt] ==> lib [rt]
arg [-lpthread] ==> lib [pthread]
arg [-ldl] ==> lib [dl]
arg [-Wl,--end-group] ==> ignore
arg [-o] ==> ignore
arg [a.out] ==> ignore
collapse library dir [/usr/lib/x86_64-linux-gnu/stubs] ==> [/usr/lib/x86_64-linux-gnu/stubs]
collapse library dir [/usr/lib/x86_64-linux-gnu] ==> [/usr/lib/x86_64-linux-gnu]
implicit libs: [cudadevrt;cudart_static;rt;pthread;dl]
implicit objs: []
implicit dirs: [/usr/lib/x86_64-linux-gnu/stubs;/usr/lib/x86_64-linux-gnu]
implicit fwks: []
Failed to detect CUDA nvcc include information:
found 'PATH=' string: [/usr/lib/nvidia-cuda-toolkit/bin:/usr/lib/cuda/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorUdwtnC/usr/bin:/tmp/.mount_cursorUdwtnC/usr/sbin:/tmp/.mount_cursorUdwtnC/usr/games:/tmp/.mount_cursorUdwtnC/bin:/tmp/.mount_cursorUdwtnC/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts]
found 'LIBRARIES=' string: [-L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu]
considering line: [#$ rm tmp/a_dlink.reg.c]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii" ]
considering line: [cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"]
considering line: [ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin" ]
considering line: [fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii" ]
considering line: [gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o" ]
considering line: [nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"]
ignoring nvlink line
considering line: [fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c" ]
considering line: [gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o" ]
considering line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
extracted link line: [g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out" ]
considering line: []
extracted link launcher name: [g++]
found link launcher absolute path: [/usr/lib/nvidia-cuda-toolkit/bin/g++]
no 'INCLUDES=' string found in nvcc output:
#$ _NVVM_BRANCH_=nvvm
#$ _SPACE_=
#$ _CUDART_=cudart
#$ _HERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _THERE_=/usr/lib/nvidia-cuda-toolkit/bin
#$ _TARGET_SIZE_=
#$ _TARGET_DIR_=
#$ _TARGET_SIZE_=64
#$ NVVMIR_LIBRARY_DIR=/usr/lib/nvidia-cuda-toolkit/libdevice
#$ PATH=/usr/lib/nvidia-cuda-toolkit/bin:/usr/lib/cuda/bin:/home/mht/anaconda3/bin:/home/mht/anaconda3/condabin:/tmp/.mount_cursorUdwtnC/usr/bin:/tmp/.mount_cursorUdwtnC/usr/sbin:/tmp/.mount_cursorUdwtnC/usr/games:/tmp/.mount_cursorUdwtnC/bin:/tmp/.mount_cursorUdwtnC/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts:/home/mht/.local/share/JetBrains/Toolbox/scripts
#$ LIBRARIES= -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu
#$ rm tmp/a_dlink.reg.c
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -E -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp1.ii"
#$ cicc --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed -arch compute_52 -m64 --no-version-ident -ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"
#$ ptxas -arch=sm_52 -m64 "tmp/CMakeCUDACompilerId.ptx" -o "tmp/CMakeCUDACompilerId.sm_52.cubin"
#$ fatbinary --create="tmp/CMakeCUDACompilerId.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " "--image3=kind=elf,sm=52,file=tmp/CMakeCUDACompilerId.sm_52.cubin" "--image3=kind=ptx,sm=52,file=tmp/CMakeCUDACompilerId.ptx" --embedded-fatbin="tmp/CMakeCUDACompilerId.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -E -x c++ -D__CUDACC__ -D__NVCC__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" -o "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ cudafe++ --c++17 --gnu_version=110400 --display_error_number --orig_src_file_name "CMakeCUDACompilerId.cu" --orig_src_path_name "/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/3.22.1/CompilerIdCUDA/CMakeCUDACompilerId.cu" --allow_managed --m64 --parse_templates --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.cpp" --stub_file_name "CMakeCUDACompilerId.cudafe1.stub.c" --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" "tmp/CMakeCUDACompilerId.cpp4.ii"
#$ gcc -D__CUDA_ARCH__=520 -D__CUDA_ARCH_LIST__=520 -c -x c++ -DCUDA_DOUBLE_MATH_FUNCTIONS -m64 "tmp/CMakeCUDACompilerId.cudafe1.cpp" -o "tmp/CMakeCUDACompilerId.o"
#$ nvlink -m64 --arch=sm_52 --register-link-binaries="tmp/a_dlink.reg.c" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -cpu-arch=X86_64 "tmp/CMakeCUDACompilerId.o" -lcudadevrt -o "tmp/a_dlink.sm_52.cubin"
#$ fatbinary --create="tmp/a_dlink.fatbin" -64 --cicc-cmdline="-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 " -link "--image3=kind=elf,sm=52,file=tmp/a_dlink.sm_52.cubin" --embedded-fatbin="tmp/a_dlink.fatbin.c"
#$ gcc -D__CUDA_ARCH_LIST__=520 -c -x c++ -DFATBINFILE="\"tmp/a_dlink.fatbin.c\"" -DREGISTERLINKBINARYFILE="\"tmp/a_dlink.reg.c\"" -I. -D__NV_EXTRA_INITIALIZATION= -D__NV_EXTRA_FINALIZATION= -D__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__ -D__CUDACC_VER_MAJOR__=11 -D__CUDACC_VER_MINOR__=5 -D__CUDACC_VER_BUILD__=119 -D__CUDA_API_VER_MAJOR__=11 -D__CUDA_API_VER_MINOR__=5 -D__NVCC_DIAG_PRAGMA_SUPPORT__=1 -m64 "/usr/lib/nvidia-cuda-toolkit/bin/crt/link.stub" -o "tmp/a_dlink.o"
#$ g++ -D__CUDA_ARCH_LIST__=520 -m64 -Wl,--start-group "tmp/a_dlink.o" "tmp/CMakeCUDACompilerId.o" -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -lcudadevrt -lcudart_static -lrt -lpthread -ldl -Wl,--end-group -o "a.out"
Detecting CUDA compiler ABI info compiled with the following output:
Change Dir: /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp
Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_c6bab/fast && /usr/bin/gmake -f CMakeFiles/cmTC_c6bab.dir/build.make CMakeFiles/cmTC_c6bab.dir/build
Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_4b2ab/fast && /usr/bin/gmake -f CMakeFiles/cmTC_4b2ab.dir/build.make CMakeFiles/cmTC_4b2ab.dir/build
gmake[1]: Entering directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp'
Building CUDA object CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o
/usr/bin/nvcc -forward-unknown-to-host-compiler --generate-code=arch=compute_52,code=[compute_52,sm_52] -Xcompiler=-v -MD -MT CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -MF CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o.d -x cu -c /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o
Building CUDA object CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o
/usr/bin/nvcc -forward-unknown-to-host-compiler --generate-code=arch=compute_52,code=[compute_52,sm_52] -Xcompiler=-v -MD -MT CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -MF CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o.d -x cu -c /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o
Using built-in specs.
COLLECT_GCC=gcc-11
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
@ -381,8 +381,8 @@ Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.cu -dumpbase-ext .cu
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.cu -dumpbase-ext .cu
ignoring duplicate directory "/usr/include/x86_64-linux-gnu/c++/11"
ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"
ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/include-fixed"
@ -399,7 +399,7 @@ ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/../../../../x86
End of search list.
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.'
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.'
Using built-in specs.
COLLECT_GCC=gcc-11
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
@ -409,8 +409,8 @@ Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH_LIST__=520 -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.cu -dumpbase-ext .cu
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH_LIST__=520 -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.cu -dumpbase-ext .cu
ignoring duplicate directory "/usr/include/x86_64-linux-gnu/c++/11"
ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"
ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/include-fixed"
@ -427,7 +427,7 @@ ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/../../../../x86
End of search list.
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.'
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.'
Using built-in specs.
COLLECT_GCC=gcc-11
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
@ -437,8 +437,8 @@ Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS /tmp/tmpxft_0000dbca_00000000-6_CMakeCUDACompilerABI.cudafe1.cpp -quiet -dumpdir CMakeFiles/cmTC_c6bab.dir/ -dumpbase CMakeCUDACompilerABI.cu.cpp -dumpbase-ext .cpp -m64 -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccnCGoqW.s
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/'
/usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS /tmp/tmpxft_000229d3_00000000-6_CMakeCUDACompilerABI.cudafe1.cpp -quiet -dumpdir CMakeFiles/cmTC_4b2ab.dir/ -dumpbase CMakeCUDACompilerABI.cu.cpp -dumpbase-ext .cpp -m64 -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccueYgmA.s
GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)
compiled by GNU C version 11.4.0, GMP version 6.2.1, MPFR version 4.1.0, MPC version 1.2.1, isl version isl-0.24-GMP
@ -462,15 +462,15 @@ GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)
GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
Compiler executable checksum: d591828bb4d392ae8b7b160e5bb0b95f
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/'
as -v --64 -o CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o /tmp/ccnCGoqW.s
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/'
as -v --64 -o CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o /tmp/ccueYgmA.s
GNU assembler version 2.38 (x86_64-linux-gnu) using BFD version (GNU Binutils for Ubuntu) 2.38
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.'
Linking CUDA executable cmTC_c6bab
/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_c6bab.dir/link.txt --verbose=1
/usr/lib/nvidia-cuda-toolkit/bin/g++ -v CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -o cmTC_c6bab -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L"/usr/lib/x86_64-linux-gnu/stubs" -L"/usr/lib/x86_64-linux-gnu"
COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.'
Linking CUDA executable cmTC_4b2ab
/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_4b2ab.dir/link.txt --verbose=1
/usr/lib/nvidia-cuda-toolkit/bin/g++ -v CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -o cmTC_4b2ab -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L"/usr/lib/x86_64-linux-gnu/stubs" -L"/usr/lib/x86_64-linux-gnu"
Using built-in specs.
COLLECT_GCC=g++-11
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper
@ -483,9 +483,9 @@ Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_c6bab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_c6bab.'
/usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccfVs73h.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_c6bab /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_c6bab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_c6bab.'
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_4b2ab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_4b2ab.'
/usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccak7FDB.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_4b2ab /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o
COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_4b2ab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_4b2ab.'
gmake[1]: Leaving directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp'
@ -515,10 +515,10 @@ Parsed CUDA implicit link information from above output:
link line regex: [^( *|.*[/\])(ld|CMAKE_LINK_STARTFILE-NOTFOUND|([^/\]+-)?ld|collect2)[^/\]*( |$)]
ignore line: [Change Dir: /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp]
ignore line: []
ignore line: [Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_c6bab/fast && /usr/bin/gmake -f CMakeFiles/cmTC_c6bab.dir/build.make CMakeFiles/cmTC_c6bab.dir/build]
ignore line: [Run Build Command(s):/usr/bin/gmake -f Makefile cmTC_4b2ab/fast && /usr/bin/gmake -f CMakeFiles/cmTC_4b2ab.dir/build.make CMakeFiles/cmTC_4b2ab.dir/build]
ignore line: [gmake[1]: Entering directory '/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/CMakeTmp']
ignore line: [Building CUDA object CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o]
ignore line: [/usr/bin/nvcc -forward-unknown-to-host-compiler --generate-code=arch=compute_52 code=[compute_52 sm_52] -Xcompiler=-v -MD -MT CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -MF CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o.d -x cu -c /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o]
ignore line: [Building CUDA object CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o]
ignore line: [/usr/bin/nvcc -forward-unknown-to-host-compiler --generate-code=arch=compute_52 code=[compute_52 sm_52] -Xcompiler=-v -MD -MT CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -MF CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o.d -x cu -c /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o]
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=gcc-11]
ignore line: [OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa]
@ -528,8 +528,8 @@ Parsed CUDA implicit link information from above output:
ignore line: [Thread model: posix]
ignore line: [Supported LTO compression algorithms: zlib zstd]
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.cu -dumpbase-ext .cu]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.cu -dumpbase-ext .cu]
ignore line: [ignoring duplicate directory "/usr/include/x86_64-linux-gnu/c++/11"]
ignore line: [ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"]
ignore line: [ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/include-fixed"]
@ -546,7 +546,7 @@ Parsed CUDA implicit link information from above output:
ignore line: [End of search list.]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_0000dbca_00000000-7_CMakeCUDACompilerABI.cpp1.']
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_000229d3_00000000-7_CMakeCUDACompilerABI.cpp1.']
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=gcc-11]
ignore line: [OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa]
@ -556,8 +556,8 @@ Parsed CUDA implicit link information from above output:
ignore line: [Thread model: posix]
ignore line: [Supported LTO compression algorithms: zlib zstd]
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH_LIST__=520 -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.cu -dumpbase-ext .cu]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -E -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH_LIST__=520 -D __CUDACC__ -D __NVCC__ -D __CUDACC_VER_MAJOR__=11 -D __CUDACC_VER_MINOR__=5 -D __CUDACC_VER_BUILD__=119 -D __CUDA_API_VER_MAJOR__=11 -D __CUDA_API_VER_MINOR__=5 -D __NVCC_DIAG_PRAGMA_SUPPORT__=1 -include cuda_runtime.h /usr/share/cmake-3.22/Modules/CMakeCUDACompilerABI.cu -o /tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii -m64 -mtune=generic -march=x86-64 -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -dumpdir /tmp/ -dumpbase tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.cu -dumpbase-ext .cu]
ignore line: [ignoring duplicate directory "/usr/include/x86_64-linux-gnu/c++/11"]
ignore line: [ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"]
ignore line: [ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/11/include-fixed"]
@ -574,7 +574,7 @@ Parsed CUDA implicit link information from above output:
ignore line: [End of search list.]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_0000dbca_00000000-5_CMakeCUDACompilerABI.cpp4.']
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH_LIST__=520' '-E' '-D' '__CUDACC__' '-D' '__NVCC__' '-v' '-D' '__CUDACC_VER_MAJOR__=11' '-D' '__CUDACC_VER_MINOR__=5' '-D' '__CUDACC_VER_BUILD__=119' '-D' '__CUDA_API_VER_MAJOR__=11' '-D' '__CUDA_API_VER_MINOR__=5' '-D' '__NVCC_DIAG_PRAGMA_SUPPORT__=1' '-include' 'cuda_runtime.h' '-m64' '-o' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.ii' '-mtune=generic' '-march=x86-64' '-dumpdir' '/tmp/tmpxft_000229d3_00000000-5_CMakeCUDACompilerABI.cpp4.']
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=gcc-11]
ignore line: [OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa]
@ -584,8 +584,8 @@ Parsed CUDA implicit link information from above output:
ignore line: [Thread model: posix]
ignore line: [Supported LTO compression algorithms: zlib zstd]
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS /tmp/tmpxft_0000dbca_00000000-6_CMakeCUDACompilerABI.cudafe1.cpp -quiet -dumpdir CMakeFiles/cmTC_c6bab.dir/ -dumpbase CMakeCUDACompilerABI.cu.cpp -dumpbase-ext .cpp -m64 -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccnCGoqW.s]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/']
ignore line: [ /usr/lib/gcc/x86_64-linux-gnu/11/cc1plus -quiet -v -imultiarch x86_64-linux-gnu -D_GNU_SOURCE -D __CUDA_ARCH__=520 -D __CUDA_ARCH_LIST__=520 -D CUDA_DOUBLE_MATH_FUNCTIONS /tmp/tmpxft_000229d3_00000000-6_CMakeCUDACompilerABI.cudafe1.cpp -quiet -dumpdir CMakeFiles/cmTC_4b2ab.dir/ -dumpbase CMakeCUDACompilerABI.cu.cpp -dumpbase-ext .cpp -m64 -mtune=generic -march=x86-64 -version -fasynchronous-unwind-tables -fstack-protector-strong -Wformat -Wformat-security -fstack-clash-protection -fcf-protection -o /tmp/ccueYgmA.s]
ignore line: [GNU C++17 (Ubuntu 11.4.0-1ubuntu1~22.04) version 11.4.0 (x86_64-linux-gnu)]
ignore line: [ compiled by GNU C version 11.4.0 GMP version 6.2.1 MPFR version 4.1.0 MPC version 1.2.1 isl version isl-0.24-GMP]
ignore line: []
@ -609,15 +609,15 @@ Parsed CUDA implicit link information from above output:
ignore line: []
ignore line: [GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072]
ignore line: [Compiler executable checksum: d591828bb4d392ae8b7b160e5bb0b95f]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/']
ignore line: [ as -v --64 -o CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o /tmp/ccnCGoqW.s]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/']
ignore line: [ as -v --64 -o CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o /tmp/ccueYgmA.s]
ignore line: [GNU assembler version 2.38 (x86_64-linux-gnu) using BFD version (GNU Binutils for Ubuntu) 2.38]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.']
ignore line: [Linking CUDA executable cmTC_c6bab]
ignore line: [/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_c6bab.dir/link.txt --verbose=1]
ignore line: [/usr/lib/nvidia-cuda-toolkit/bin/g++ -v CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -o cmTC_c6bab -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L"/usr/lib/x86_64-linux-gnu/stubs" -L"/usr/lib/x86_64-linux-gnu"]
ignore line: [COLLECT_GCC_OPTIONS='-D' '__CUDA_ARCH__=520' '-D' '__CUDA_ARCH_LIST__=520' '-c' '-D' 'CUDA_DOUBLE_MATH_FUNCTIONS' '-v' '-m64' '-o' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o' '-mtune=generic' '-march=x86-64' '-dumpdir' 'CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.']
ignore line: [Linking CUDA executable cmTC_4b2ab]
ignore line: [/usr/bin/cmake -E cmake_link_script CMakeFiles/cmTC_4b2ab.dir/link.txt --verbose=1]
ignore line: [/usr/lib/nvidia-cuda-toolkit/bin/g++ -v CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -o cmTC_4b2ab -lcudadevrt -lcudart_static -lrt -lpthread -ldl -L"/usr/lib/x86_64-linux-gnu/stubs" -L"/usr/lib/x86_64-linux-gnu"]
ignore line: [Using built-in specs.]
ignore line: [COLLECT_GCC=g++-11]
ignore line: [COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper]
@ -630,13 +630,13 @@ Parsed CUDA implicit link information from above output:
ignore line: [gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04) ]
ignore line: [COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/]
ignore line: [LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/11/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/11/../../../:/lib/:/usr/lib/]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_c6bab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_c6bab.']
link line: [ /usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccfVs73h.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_c6bab /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o]
ignore line: [COLLECT_GCC_OPTIONS='-v' '-o' 'cmTC_4b2ab' '-L/usr/lib/x86_64-linux-gnu/stubs' '-L/usr/lib/x86_64-linux-gnu' '-shared-libgcc' '-mtune=generic' '-march=x86-64' '-dumpdir' 'cmTC_4b2ab.']
link line: [ /usr/lib/gcc/x86_64-linux-gnu/11/collect2 -plugin /usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so -plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper -plugin-opt=-fresolution=/tmp/ccak7FDB.res -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc -plugin-opt=-pass-through=-lc -plugin-opt=-pass-through=-lgcc_s -plugin-opt=-pass-through=-lgcc --build-id --eh-frame-hdr -m elf_x86_64 --hash-style=gnu --as-needed -dynamic-linker /lib64/ld-linux-x86-64.so.2 -pie -z now -z relro -o cmTC_4b2ab /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o /usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o -L/usr/lib/x86_64-linux-gnu/stubs -L/usr/lib/x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11 -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/11/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/11/../../.. CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-linux-gnu/11/crtendS.o /usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crtn.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/collect2] ==> ignore
arg [-plugin] ==> ignore
arg [/usr/lib/gcc/x86_64-linux-gnu/11/liblto_plugin.so] ==> ignore
arg [-plugin-opt=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper] ==> ignore
arg [-plugin-opt=-fresolution=/tmp/ccfVs73h.res] ==> ignore
arg [-plugin-opt=-fresolution=/tmp/ccak7FDB.res] ==> ignore
arg [-plugin-opt=-pass-through=-lgcc_s] ==> ignore
arg [-plugin-opt=-pass-through=-lgcc] ==> ignore
arg [-plugin-opt=-pass-through=-lc] ==> ignore
@ -654,7 +654,7 @@ Parsed CUDA implicit link information from above output:
arg [-znow] ==> ignore
arg [-zrelro] ==> ignore
arg [-o] ==> ignore
arg [cmTC_c6bab] ==> ignore
arg [cmTC_4b2ab] ==> ignore
arg [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/Scrt1.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/../../../x86_64-linux-gnu/crti.o]
arg [/usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o] ==> obj [/usr/lib/gcc/x86_64-linux-gnu/11/crtbeginS.o]
@ -668,7 +668,7 @@ Parsed CUDA implicit link information from above output:
arg [-L/usr/lib/x86_64-linux-gnu] ==> dir [/usr/lib/x86_64-linux-gnu]
arg [-L/usr/lib/../lib] ==> dir [/usr/lib/../lib]
arg [-L/usr/lib/gcc/x86_64-linux-gnu/11/../../..] ==> dir [/usr/lib/gcc/x86_64-linux-gnu/11/../../..]
arg [CMakeFiles/cmTC_c6bab.dir/CMakeCUDACompilerABI.cu.o] ==> ignore
arg [CMakeFiles/cmTC_4b2ab.dir/CMakeCUDACompilerABI.cu.o] ==> ignore
arg [-lcudadevrt] ==> lib [cudadevrt]
arg [-lcudart_static] ==> lib [cudart_static]
arg [-lrt] ==> lib [rt]

2
build/CMakeFiles/Makefile.cmake
View File

@ -65,4 +65,6 @@ set(CMAKE_DEPEND_INFO_FILES
"CMakeFiles/bb_regressor.dir/DependInfo.cmake"
"CMakeFiles/classifier.dir/DependInfo.cmake"
"CMakeFiles/tracking_demo.dir/DependInfo.cmake"
"CMakeFiles/test_models.dir/DependInfo.cmake"
"CMakeFiles/generate_test_samples.dir/DependInfo.cmake"
)

67
build/CMakeFiles/Makefile2
View File

@ -66,6 +66,8 @@ CMAKE_BINARY_DIR = /media/mht/ADATA/repos/cpp_tracker/build
all: CMakeFiles/bb_regressor.dir/all
all: CMakeFiles/classifier.dir/all
all: CMakeFiles/tracking_demo.dir/all
all: CMakeFiles/test_models.dir/all
all: CMakeFiles/generate_test_samples.dir/all
.PHONY : all
# The main recursive "preinstall" target.
@ -76,6 +78,8 @@ preinstall:
clean: CMakeFiles/bb_regressor.dir/clean
clean: CMakeFiles/classifier.dir/clean
clean: CMakeFiles/tracking_demo.dir/clean
clean: CMakeFiles/test_models.dir/clean
clean: CMakeFiles/generate_test_samples.dir/clean
.PHONY : clean
#=============================================================================
@ -85,12 +89,12 @@ clean: CMakeFiles/tracking_demo.dir/clean
CMakeFiles/bb_regressor.dir/all:
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/depend
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/build
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=1,2 "Built target bb_regressor"
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=1,2,3 "Built target bb_regressor"
.PHONY : CMakeFiles/bb_regressor.dir/all
# Build rule for subdir invocation for target.
CMakeFiles/bb_regressor.dir/rule: cmake_check_build_system
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 2
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 3
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 CMakeFiles/bb_regressor.dir/all
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 0
.PHONY : CMakeFiles/bb_regressor.dir/rule
@ -111,7 +115,7 @@ CMakeFiles/bb_regressor.dir/clean:
CMakeFiles/classifier.dir/all:
$(MAKE) $(MAKESILENT) -f CMakeFiles/classifier.dir/build.make CMakeFiles/classifier.dir/depend
$(MAKE) $(MAKESILENT) -f CMakeFiles/classifier.dir/build.make CMakeFiles/classifier.dir/build
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=3,4 "Built target classifier"
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=4,5 "Built target classifier"
.PHONY : CMakeFiles/classifier.dir/all
# Build rule for subdir invocation for target.
@ -138,12 +142,12 @@ CMakeFiles/tracking_demo.dir/all: CMakeFiles/bb_regressor.dir/all
CMakeFiles/tracking_demo.dir/all: CMakeFiles/classifier.dir/all
$(MAKE) $(MAKESILENT) -f CMakeFiles/tracking_demo.dir/build.make CMakeFiles/tracking_demo.dir/depend
$(MAKE) $(MAKESILENT) -f CMakeFiles/tracking_demo.dir/build.make CMakeFiles/tracking_demo.dir/build
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=5,6 "Built target tracking_demo"
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=10,11 "Built target tracking_demo"
.PHONY : CMakeFiles/tracking_demo.dir/all
# Build rule for subdir invocation for target.
CMakeFiles/tracking_demo.dir/rule: cmake_check_build_system
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 6
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 7
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 CMakeFiles/tracking_demo.dir/all
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 0
.PHONY : CMakeFiles/tracking_demo.dir/rule
@ -157,6 +161,59 @@ CMakeFiles/tracking_demo.dir/clean:
$(MAKE) $(MAKESILENT) -f CMakeFiles/tracking_demo.dir/build.make CMakeFiles/tracking_demo.dir/clean
.PHONY : CMakeFiles/tracking_demo.dir/clean
#=============================================================================
# Target rules for target CMakeFiles/test_models.dir
# All Build rule for target.
CMakeFiles/test_models.dir/all: CMakeFiles/bb_regressor.dir/all
CMakeFiles/test_models.dir/all: CMakeFiles/classifier.dir/all
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/depend
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/build
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=8,9 "Built target test_models"
.PHONY : CMakeFiles/test_models.dir/all
# Build rule for subdir invocation for target.
CMakeFiles/test_models.dir/rule: cmake_check_build_system
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 7
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 CMakeFiles/test_models.dir/all
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 0
.PHONY : CMakeFiles/test_models.dir/rule
# Convenience name for target.
test_models: CMakeFiles/test_models.dir/rule
.PHONY : test_models
# clean rule for target.
CMakeFiles/test_models.dir/clean:
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/clean
.PHONY : CMakeFiles/test_models.dir/clean
#=============================================================================
# Target rules for target CMakeFiles/generate_test_samples.dir
# All Build rule for target.
CMakeFiles/generate_test_samples.dir/all:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/depend
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/build
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=6,7 "Built target generate_test_samples"
.PHONY : CMakeFiles/generate_test_samples.dir/all
# Build rule for subdir invocation for target.
CMakeFiles/generate_test_samples.dir/rule: cmake_check_build_system
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 2
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 CMakeFiles/generate_test_samples.dir/all
$(CMAKE_COMMAND) -E cmake_progress_start /media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles 0
.PHONY : CMakeFiles/generate_test_samples.dir/rule
# Convenience name for target.
generate_test_samples: CMakeFiles/generate_test_samples.dir/rule
.PHONY : generate_test_samples
# clean rule for target.
CMakeFiles/generate_test_samples.dir/clean:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/clean
.PHONY : CMakeFiles/generate_test_samples.dir/clean
#=============================================================================
# Special targets to cleanup operation of make.

2
build/CMakeFiles/TargetDirectories.txt
View File

@ -1,6 +1,8 @@
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/bb_regressor.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/classifier.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/tracking_demo.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/test_models.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/generate_test_samples.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/edit_cache.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/rebuild_cache.dir
/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles/list_install_components.dir

1
build/CMakeFiles/bb_regressor.dir/DependInfo.cmake
View File

@ -9,6 +9,7 @@ set(CMAKE_DEPENDS_LANGUAGES
# The set of dependency files which are needed:
set(CMAKE_DEPENDS_DEPENDENCY_FILES
"/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/bb_regressor.cpp" "CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o" "gcc" "CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o.d"
"/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp" "CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o" "gcc" "CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o.d"
)
# Targets to which this target links.

20
build/CMakeFiles/bb_regressor.dir/build.make
View File

@ -83,17 +83,33 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.s: cmake_force
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green "Compiling CXX source to assembly CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.s"
/usr/bin/c++ $(CXX_DEFINES) $(CXX_INCLUDES) $(CXX_FLAGS) -S /media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/bb_regressor.cpp -o CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.s
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o: CMakeFiles/bb_regressor.dir/flags.make
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o: ../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o: CMakeFiles/bb_regressor.dir/compiler_depend.ts
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=$(CMAKE_PROGRESS_2) "Building CXX object CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o"
/usr/bin/c++ $(CXX_DEFINES) $(CXX_INCLUDES) $(CXX_FLAGS) -MD -MT CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o -MF CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o.d -o CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o -c /media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i: cmake_force
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green "Preprocessing CXX source to CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i"
/usr/bin/c++ $(CXX_DEFINES) $(CXX_INCLUDES) $(CXX_FLAGS) -E /media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp > CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s: cmake_force
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green "Compiling CXX source to assembly CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s"
/usr/bin/c++ $(CXX_DEFINES) $(CXX_INCLUDES) $(CXX_FLAGS) -S /media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp -o CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s
# Object files for target bb_regressor
bb_regressor_OBJECTS = \
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o"
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o" \
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o"
# External object files for target bb_regressor
bb_regressor_EXTERNAL_OBJECTS =
libbb_regressor.a: CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o
libbb_regressor.a: CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
libbb_regressor.a: CMakeFiles/bb_regressor.dir/build.make
libbb_regressor.a: CMakeFiles/bb_regressor.dir/link.txt
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green --bold --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=$(CMAKE_PROGRESS_2) "Linking CXX static library libbb_regressor.a"
@$(CMAKE_COMMAND) -E cmake_echo_color --switch=$(COLOR) --green --bold --progress-dir=/media/mht/ADATA/repos/cpp_tracker/build/CMakeFiles --progress-num=$(CMAKE_PROGRESS_3) "Linking CXX static library libbb_regressor.a"
$(CMAKE_COMMAND) -P CMakeFiles/bb_regressor.dir/cmake_clean_target.cmake
$(CMAKE_COMMAND) -E cmake_link_script CMakeFiles/bb_regressor.dir/link.txt --verbose=$(VERBOSE)

BIN
build/CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o
View File

2
build/CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o.d
View File

@ -4795,4 +4795,4 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: \
/usr/include/cuda.h /home/mht/libtorch/include/ATen/cuda/Exceptions.h \
/usr/include/cusolver_common.h \
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h \
/media/mht/ADATA/repos/cpp_tracker/ltr/external/PreciseRoIPooling/pytorch/prroi_pool/src/prroi_pooling_gpu_impl.cuh
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cuh

2
build/CMakeFiles/bb_regressor.dir/cmake_clean.cmake
View File

@ -1,6 +1,8 @@
file(REMOVE_RECURSE
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o"
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o.d"
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o"
"CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o.d"
"libbb_regressor.a"
"libbb_regressor.pdb"
)

163
build/CMakeFiles/bb_regressor.dir/compiler_depend.internal
View File

@ -4844,4 +4844,167 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o
/home/mht/libtorch/include/torch/csrc/jit/frontend/tree_views.h
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickler.h
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickle.h
/usr/include/cuda_runtime.h
/usr/include/crt/host_config.h
/usr/include/builtin_types.h
/usr/include/device_types.h
/usr/include/crt/host_defines.h
/usr/include/driver_types.h
/usr/include/vector_types.h
/usr/include/surface_types.h
/usr/include/texture_types.h
/usr/include/library_types.h
/usr/include/channel_descriptor.h
/usr/include/cuda_runtime_api.h
/usr/include/cuda_device_runtime_api.h
/usr/include/driver_functions.h
/usr/include/vector_functions.h
/usr/include/vector_functions.hpp
/home/mht/libtorch/include/ATen/cuda/CUDAContext.h
/usr/include/cuda_runtime_api.h
/usr/include/cusparse.h
/usr/include/cuComplex.h
/usr/include/c++/11/math.h
/usr/include/cuda_fp16.h
/usr/include/cuda_fp16.hpp
/usr/include/driver_types.h
/usr/include/library_types.h
/usr/include/cublas_v2.h
/usr/include/cublas_api.h
/usr/include/cuComplex.h
/usr/include/cuda_bf16.h
/usr/include/cuda_bf16.hpp
/usr/include/cusolverDn.h
/usr/include/cublas_v2.h
/usr/include/cusolver_common.h
/home/mht/libtorch/include/c10/cuda/CUDAStream.h
/home/mht/libtorch/include/c10/cuda/CUDAFunctions.h
/home/mht/libtorch/include/c10/core/impl/GPUTrace.h
/home/mht/libtorch/include/c10/cuda/CUDAException.h
/home/mht/libtorch/include/c10/cuda/CUDADeviceAssertionHost.h
/home/mht/libtorch/include/c10/cuda/CUDAMacros.h
/home/mht/libtorch/include/c10/cuda/impl/cuda_cmake_macros.h
/home/mht/libtorch/include/c10/cuda/CUDAMiscFunctions.h
/usr/include/cuda.h
/home/mht/libtorch/include/ATen/cuda/Exceptions.h
/usr/include/cusolver_common.h
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cuh
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp
/usr/include/stdc-predef.h
/media/mht/ADATA/repos/cpp_tracker/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h
/usr/include/stdio.h
/usr/include/x86_64-linux-gnu/bits/libc-header-start.h
/usr/include/features.h
/usr/include/features-time64.h
/usr/include/x86_64-linux-gnu/bits/wordsize.h
/usr/include/x86_64-linux-gnu/bits/timesize.h
/usr/include/x86_64-linux-gnu/sys/cdefs.h
/usr/include/x86_64-linux-gnu/bits/long-double.h
/usr/include/x86_64-linux-gnu/gnu/stubs.h
/usr/include/x86_64-linux-gnu/gnu/stubs-64.h
/usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h
/usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h
/usr/include/x86_64-linux-gnu/bits/types.h
/usr/include/x86_64-linux-gnu/bits/typesizes.h
/usr/include/x86_64-linux-gnu/bits/time64.h
/usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h
/usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h
/usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h
/usr/include/x86_64-linux-gnu/bits/types/__FILE.h
/usr/include/x86_64-linux-gnu/bits/types/FILE.h
/usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h
/usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h
/usr/include/x86_64-linux-gnu/bits/stdio_lim.h
/usr/include/x86_64-linux-gnu/bits/floatn.h
/usr/include/x86_64-linux-gnu/bits/floatn-common.h
/usr/include/x86_64-linux-gnu/bits/stdio.h
/usr/include/x86_64-linux-gnu/bits/stdio2.h
/usr/include/c++/11/math.h
/usr/include/c++/11/cmath
/usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h
/usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h
/usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h
/usr/include/c++/11/pstl/pstl_config.h
/usr/include/c++/11/bits/cpp_type_traits.h
/usr/include/c++/11/ext/type_traits.h
/usr/include/math.h
/usr/include/x86_64-linux-gnu/bits/math-vector.h
/usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h
/usr/include/x86_64-linux-gnu/bits/flt-eval-method.h
/usr/include/x86_64-linux-gnu/bits/fp-logb.h
/usr/include/x86_64-linux-gnu/bits/fp-fast.h
/usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h
/usr/include/x86_64-linux-gnu/bits/mathcalls.h
/usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h
/usr/include/x86_64-linux-gnu/bits/iscanonical.h
/usr/include/c++/11/bits/std_abs.h
/usr/include/stdlib.h
/usr/include/x86_64-linux-gnu/bits/waitflags.h
/usr/include/x86_64-linux-gnu/bits/waitstatus.h
/usr/include/x86_64-linux-gnu/bits/types/locale_t.h
/usr/include/x86_64-linux-gnu/bits/types/__locale_t.h
/usr/include/x86_64-linux-gnu/sys/types.h
/usr/include/x86_64-linux-gnu/bits/types/clock_t.h
/usr/include/x86_64-linux-gnu/bits/types/clockid_t.h
/usr/include/x86_64-linux-gnu/bits/types/time_t.h
/usr/include/x86_64-linux-gnu/bits/types/timer_t.h
/usr/include/x86_64-linux-gnu/bits/stdint-intn.h
/usr/include/endian.h
/usr/include/x86_64-linux-gnu/bits/endian.h
/usr/include/x86_64-linux-gnu/bits/endianness.h
/usr/include/x86_64-linux-gnu/bits/byteswap.h
/usr/include/x86_64-linux-gnu/bits/uintn-identity.h
/usr/include/x86_64-linux-gnu/sys/select.h
/usr/include/x86_64-linux-gnu/bits/select.h
/usr/include/x86_64-linux-gnu/bits/types/sigset_t.h
/usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h
/usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
/usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h
/usr/include/x86_64-linux-gnu/bits/select2.h
/usr/include/x86_64-linux-gnu/bits/pthreadtypes.h
/usr/include/x86_64-linux-gnu/bits/thread-shared-types.h
/usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h
/usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h
/usr/include/x86_64-linux-gnu/bits/struct_mutex.h
/usr/include/x86_64-linux-gnu/bits/struct_rwlock.h
/usr/include/alloca.h
/usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h
/usr/include/x86_64-linux-gnu/bits/stdlib-float.h
/usr/include/x86_64-linux-gnu/bits/stdlib.h
/usr/include/c++/11/bits/specfun.h
/usr/include/c++/11/bits/stl_algobase.h
/usr/include/c++/11/bits/functexcept.h
/usr/include/c++/11/bits/exception_defines.h
/usr/include/c++/11/ext/numeric_traits.h
/usr/include/c++/11/bits/stl_pair.h
/usr/include/c++/11/bits/move.h
/usr/include/c++/11/type_traits
/usr/include/c++/11/bits/stl_iterator_base_types.h
/usr/include/c++/11/bits/stl_iterator_base_funcs.h
/usr/include/c++/11/bits/concept_check.h
/usr/include/c++/11/debug/assertions.h
/usr/include/c++/11/bits/stl_iterator.h
/usr/include/c++/11/bits/ptr_traits.h
/usr/include/c++/11/debug/debug.h
/usr/include/c++/11/bits/predefined_ops.h
/usr/include/c++/11/limits
/usr/include/c++/11/tr1/gamma.tcc
/usr/include/c++/11/tr1/special_function_util.h
/usr/include/c++/11/tr1/bessel_function.tcc
/usr/include/c++/11/tr1/beta_function.tcc
/usr/include/c++/11/tr1/ell_integral.tcc
/usr/include/c++/11/tr1/exp_integral.tcc
/usr/include/c++/11/tr1/hypergeometric.tcc
/usr/include/c++/11/tr1/legendre_function.tcc
/usr/include/c++/11/tr1/modified_bessel_func.tcc
/usr/include/c++/11/tr1/poly_hermite.tcc
/usr/include/c++/11/tr1/poly_laguerre.tcc
/usr/include/c++/11/tr1/riemann_zeta.tcc
/usr/include/string.h
/usr/include/strings.h
/usr/include/x86_64-linux-gnu/bits/strings_fortified.h
/usr/include/x86_64-linux-gnu/bits/string_fortified.h

246
build/CMakeFiles/bb_regressor.dir/compiler_depend.make
View File

@ -4842,8 +4842,202 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/torch/csrc/jit/frontend/versioned_symbols.h \
/home/mht/libtorch/include/torch/csrc/jit/frontend/tree_views.h \
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickler.h \
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickle.h
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickle.h \
/usr/include/cuda_runtime.h \
/usr/include/crt/host_config.h \
/usr/include/builtin_types.h \
/usr/include/device_types.h \
/usr/include/crt/host_defines.h \
/usr/include/driver_types.h \
/usr/include/vector_types.h \
/usr/include/surface_types.h \
/usr/include/texture_types.h \
/usr/include/library_types.h \
/usr/include/channel_descriptor.h \
/usr/include/cuda_runtime_api.h \
/usr/include/cuda_device_runtime_api.h \
/usr/include/driver_functions.h \
/usr/include/vector_functions.h \
/usr/include/vector_functions.hpp \
/home/mht/libtorch/include/ATen/cuda/CUDAContext.h \
/usr/include/cuda_runtime_api.h \
/usr/include/cusparse.h \
/usr/include/cuComplex.h \
/usr/include/c++/11/math.h \
/usr/include/cuda_fp16.h \
/usr/include/cuda_fp16.hpp \
/usr/include/driver_types.h \
/usr/include/library_types.h \
/usr/include/cublas_v2.h \
/usr/include/cublas_api.h \
/usr/include/cuComplex.h \
/usr/include/cuda_bf16.h \
/usr/include/cuda_bf16.hpp \
/usr/include/cusolverDn.h \
/usr/include/cublas_v2.h \
/usr/include/cusolver_common.h \
/home/mht/libtorch/include/c10/cuda/CUDAStream.h \
/home/mht/libtorch/include/c10/cuda/CUDAFunctions.h \
/home/mht/libtorch/include/c10/core/impl/GPUTrace.h \
/home/mht/libtorch/include/c10/cuda/CUDAException.h \
/home/mht/libtorch/include/c10/cuda/CUDADeviceAssertionHost.h \
/home/mht/libtorch/include/c10/cuda/CUDAMacros.h \
/home/mht/libtorch/include/c10/cuda/impl/cuda_cmake_macros.h \
/home/mht/libtorch/include/c10/cuda/CUDAMiscFunctions.h \
/usr/include/cuda.h \
/home/mht/libtorch/include/ATen/cuda/Exceptions.h \
/usr/include/cusolver_common.h \
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h \
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cuh
CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o: ../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp \
/usr/include/stdc-predef.h \
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h \
/usr/include/stdio.h \
/usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
/usr/include/features.h \
/usr/include/features-time64.h \
/usr/include/x86_64-linux-gnu/bits/wordsize.h \
/usr/include/x86_64-linux-gnu/bits/timesize.h \
/usr/include/x86_64-linux-gnu/sys/cdefs.h \
/usr/include/x86_64-linux-gnu/bits/long-double.h \
/usr/include/x86_64-linux-gnu/gnu/stubs.h \
/usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
/usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
/usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
/usr/include/x86_64-linux-gnu/bits/types.h \
/usr/include/x86_64-linux-gnu/bits/typesizes.h \
/usr/include/x86_64-linux-gnu/bits/time64.h \
/usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
/usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
/usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
/usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
/usr/include/x86_64-linux-gnu/bits/types/FILE.h \
/usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
/usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
/usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
/usr/include/x86_64-linux-gnu/bits/floatn.h \
/usr/include/x86_64-linux-gnu/bits/floatn-common.h \
/usr/include/x86_64-linux-gnu/bits/stdio.h \
/usr/include/x86_64-linux-gnu/bits/stdio2.h \
/usr/include/c++/11/math.h \
/usr/include/c++/11/cmath \
/usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
/usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
/usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
/usr/include/c++/11/pstl/pstl_config.h \
/usr/include/c++/11/bits/cpp_type_traits.h \
/usr/include/c++/11/ext/type_traits.h \
/usr/include/math.h \
/usr/include/x86_64-linux-gnu/bits/math-vector.h \
/usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
/usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
/usr/include/x86_64-linux-gnu/bits/fp-logb.h \
/usr/include/x86_64-linux-gnu/bits/fp-fast.h \
/usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
/usr/include/x86_64-linux-gnu/bits/mathcalls.h \
/usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
/usr/include/x86_64-linux-gnu/bits/iscanonical.h \
/usr/include/c++/11/bits/std_abs.h \
/usr/include/stdlib.h \
/usr/include/x86_64-linux-gnu/bits/waitflags.h \
/usr/include/x86_64-linux-gnu/bits/waitstatus.h \
/usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
/usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
/usr/include/x86_64-linux-gnu/sys/types.h \
/usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
/usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
/usr/include/x86_64-linux-gnu/bits/types/time_t.h \
/usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
/usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
/usr/include/endian.h \
/usr/include/x86_64-linux-gnu/bits/endian.h \
/usr/include/x86_64-linux-gnu/bits/endianness.h \
/usr/include/x86_64-linux-gnu/bits/byteswap.h \
/usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
/usr/include/x86_64-linux-gnu/sys/select.h \
/usr/include/x86_64-linux-gnu/bits/select.h \
/usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
/usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
/usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
/usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
/usr/include/x86_64-linux-gnu/bits/select2.h \
/usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
/usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
/usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
/usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
/usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
/usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
/usr/include/alloca.h \
/usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
/usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
/usr/include/x86_64-linux-gnu/bits/stdlib.h \
/usr/include/c++/11/bits/specfun.h \
/usr/include/c++/11/bits/stl_algobase.h \
/usr/include/c++/11/bits/functexcept.h \
/usr/include/c++/11/bits/exception_defines.h \
/usr/include/c++/11/ext/numeric_traits.h \
/usr/include/c++/11/bits/stl_pair.h \
/usr/include/c++/11/bits/move.h \
/usr/include/c++/11/type_traits \
/usr/include/c++/11/bits/stl_iterator_base_types.h \
/usr/include/c++/11/bits/stl_iterator_base_funcs.h \
/usr/include/c++/11/bits/concept_check.h \
/usr/include/c++/11/debug/assertions.h \
/usr/include/c++/11/bits/stl_iterator.h \
/usr/include/c++/11/bits/ptr_traits.h \
/usr/include/c++/11/debug/debug.h \
/usr/include/c++/11/bits/predefined_ops.h \
/usr/include/c++/11/limits \
/usr/include/c++/11/tr1/gamma.tcc \
/usr/include/c++/11/tr1/special_function_util.h \
/usr/include/c++/11/tr1/bessel_function.tcc \
/usr/include/c++/11/tr1/beta_function.tcc \
/usr/include/c++/11/tr1/ell_integral.tcc \
/usr/include/c++/11/tr1/exp_integral.tcc \
/usr/include/c++/11/tr1/hypergeometric.tcc \
/usr/include/c++/11/tr1/legendre_function.tcc \
/usr/include/c++/11/tr1/modified_bessel_func.tcc \
/usr/include/c++/11/tr1/poly_hermite.tcc \
/usr/include/c++/11/tr1/poly_laguerre.tcc \
/usr/include/c++/11/tr1/riemann_zeta.tcc \
/usr/include/string.h \
/usr/include/strings.h \
/usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
/usr/include/x86_64-linux-gnu/bits/string_fortified.h
/home/mht/libtorch/include/c10/cuda/impl/cuda_cmake_macros.h:
/home/mht/libtorch/include/c10/core/impl/GPUTrace.h:
/usr/include/cusolver_common.h:
/usr/include/cuda_bf16.hpp:
/usr/include/cuda_fp16.h:
/usr/include/c++/11/math.h:
/home/mht/libtorch/include/ATen/cuda/CUDAContext.h:
/usr/include/vector_functions.h:
/usr/include/driver_functions.h:
/usr/include/cuda_runtime_api.h:
/usr/include/channel_descriptor.h:
/usr/include/library_types.h:
/usr/include/driver_types.h:
/usr/include/crt/host_defines.h:
/usr/include/device_types.h:
/usr/include/builtin_types.h:
/home/mht/libtorch/include/torch/csrc/jit/serialization/pickle.h:
@ -5025,6 +5219,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/torch/csrc/api/include/torch/data/datasets/map.h:
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.h:
/home/mht/libtorch/include/torch/csrc/jit/api/compilation_unit.h:
/home/mht/libtorch/include/torch/csrc/jit/runtime/variable_tensor_list.h:
@ -6147,6 +6343,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/ccol_indices_copy_native.h:
/home/mht/libtorch/include/c10/cuda/CUDAFunctions.h:
/home/mht/libtorch/include/ATen/ops/ccol_indices_native.h:
/home/mht/libtorch/include/torch/csrc/jit/runtime/interpreter.h:
@ -6161,6 +6359,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/bmm_meta.h:
/home/mht/libtorch/include/c10/cuda/CUDAStream.h:
/home/mht/libtorch/include/ATen/ops/block_diag_native.h:
/usr/include/c++/11/bits/forward_list.tcc:
@ -6519,6 +6719,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/_pad_circular_native.h:
/usr/include/cuda_bf16.h:
/home/mht/libtorch/include/ATen/ops/_pack_padded_sequence_native.h:
/home/mht/libtorch/include/ATen/ops/_nnpack_spatial_convolution_native.h:
@ -6959,6 +7161,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/unbind.h:
/usr/include/texture_types.h:
/home/mht/libtorch/include/ATen/ops/type_as.h:
/home/mht/libtorch/include/ATen/ops/special_scaled_modified_bessel_k1_native.h:
@ -6977,6 +7181,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/tril.h:
/usr/include/cuComplex.h:
/home/mht/libtorch/include/ATen/ops/resize_as_native.h:
/home/mht/libtorch/include/ATen/ops/triangular_solve.h:
@ -7093,6 +7299,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/split_with_sizes_copy.h:
/usr/include/vector_types.h:
/home/mht/libtorch/include/ATen/ops/split.h:
/home/mht/libtorch/include/ATen/ops/special_xlogy_ops.h:
@ -7189,6 +7397,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/special_i1.h:
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp:
/home/mht/libtorch/include/ATen/ops/special_i0e_ops.h:
/home/mht/libtorch/include/ATen/ops/special_i0e.h:
@ -7741,6 +7951,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/nuclear_norm.h:
/usr/include/cuda.h:
/home/mht/libtorch/include/ATen/ops/not_equal.h:
/home/mht/libtorch/include/ATen/ops/embedding_renorm_native.h:
@ -8147,6 +8359,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/_aminmax.h:
/usr/include/cuda_fp16.hpp:
/usr/lib/gcc/x86_64-linux-gnu/11/include/avx512bf16intrin.h:
/home/mht/libtorch/include/ATen/ops/_addmm_activation.h:
@ -8579,6 +8793,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/resize_ops.h:
/home/mht/libtorch/include/c10/cuda/CUDAException.h:
/home/mht/libtorch/include/ATen/ops/logcumsumexp.h:
/home/mht/libtorch/include/ATen/ops/zeros_native.h:
@ -9619,6 +9835,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/masked_select_backward.h:
/home/mht/libtorch/include/c10/cuda/CUDAMiscFunctions.h:
/home/mht/libtorch/include/ATen/ops/_convolution_native.h:
/usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h:
@ -9711,6 +9929,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/clamp_min_ops.h:
/usr/include/cusolverDn.h:
/home/mht/libtorch/include/ATen/ops/index_copy_ops.h:
/home/mht/libtorch/include/ATen/ops/_foreach_log1p.h:
@ -10323,6 +10543,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/le_ops.h:
/usr/include/cublas_v2.h:
/home/mht/libtorch/include/ATen/ops/bitwise_and.h:
/home/mht/libtorch/include/ATen/ops/from_file.h:
@ -10793,6 +11015,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/c10/util/Exception.h:
/usr/include/cusparse.h:
/usr/include/x86_64-linux-gnu/bits/waitflags.h:
/home/mht/libtorch/include/ATen/ops/_slow_conv2d_forward_native.h:
@ -10927,6 +11151,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/usr/include/x86_64-linux-gnu/bits/endian.h:
/usr/include/cuda_runtime.h:
/home/mht/libtorch/include/ATen/ops/argwhere_ops.h:
/home/mht/libtorch/include/ATen/ops/real.h:
@ -12325,6 +12551,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/_mps_convolution_transpose_ops.h:
/home/mht/libtorch/include/ATen/cuda/Exceptions.h:
/home/mht/libtorch/include/ATen/ops/lstm_cell.h:
/home/mht/libtorch/include/ATen/ops/log_sigmoid_forward_ops.h:
@ -12953,6 +13181,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/_upsample_nearest_exact1d.h:
/usr/include/cuda_device_runtime_api.h:
/home/mht/libtorch/include/ATen/ops/smm_ops.h:
/usr/include/c++/11/bits/locale_facets_nonio.tcc:
@ -13113,6 +13343,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/conv_tbc_backward.h:
../cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cuh:
/home/mht/libtorch/include/ATen/ops/cudnn_batch_norm_backward.h:
/home/mht/libtorch/include/ATen/ops/_grid_sampler_2d_cpu_fallback_backward_native.h:
@ -13179,6 +13411,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/index_copy.h:
/usr/include/vector_functions.hpp:
/home/mht/libtorch/include/ATen/ops/amin_ops.h:
/usr/include/x86_64-linux-gnu/sys/cdefs.h:
@ -13191,6 +13425,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/atan2.h:
/usr/include/crt/host_config.h:
/home/mht/libtorch/include/ATen/ops/upsample_bicubic2d_backward_native.h:
/home/mht/libtorch/include/ATen/ops/quantized_max_pool2d_native.h:
@ -13431,6 +13667,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/is_leaf.h:
/usr/include/surface_types.h:
/home/mht/libtorch/include/ATen/ops/acosh_native.h:
/home/mht/libtorch/include/ATen/ops/constant_pad_nd.h:
@ -13489,6 +13727,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/copy_sparse_to_sparse_ops.h:
/usr/include/cublas_api.h:
/home/mht/libtorch/include/ATen/ops/_fused_adamw_ops.h:
/home/mht/libtorch/include/ATen/ops/layer_norm_ops.h:
@ -14347,6 +14587,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/linalg_svd_ops.h:
/home/mht/libtorch/include/c10/cuda/CUDADeviceAssertionHost.h:
/home/mht/libtorch/include/torch/csrc/api/include/torch/nn/modules/normalization.h:
/home/mht/libtorch/include/ATen/ops/index_copy_native.h:
@ -14517,6 +14759,8 @@ CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o: ../cimp/bb_reg
/home/mht/libtorch/include/ATen/ops/miopen_batch_norm.h:
/home/mht/libtorch/include/c10/cuda/CUDAMacros.h:
/home/mht/libtorch/include/ATen/ops/fake_quantize_per_tensor_affine_cachemask_backward_ops.h:
/home/mht/libtorch/include/ATen/ops/miopen_batch_norm_backward.h:

2
build/CMakeFiles/bb_regressor.dir/link.txt
View File

@ -1,2 +1,2 @@
/usr/bin/ar qc libbb_regressor.a CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o
/usr/bin/ar qc libbb_regressor.a CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.o CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
/usr/bin/ranlib libbb_regressor.a

1
build/CMakeFiles/bb_regressor.dir/progress.make
View File

@ -1,3 +1,4 @@
CMAKE_PROGRESS_1 = 1
CMAKE_PROGRESS_2 = 2
CMAKE_PROGRESS_3 = 3

BIN
build/CMakeFiles/classifier.dir/cimp/classifier/classifier.cpp.o
View File

4
build/CMakeFiles/classifier.dir/progress.make
View File

@ -1,3 +1,3 @@
CMAKE_PROGRESS_1 = 3
CMAKE_PROGRESS_2 = 4
CMAKE_PROGRESS_1 = 4
CMAKE_PROGRESS_2 = 5

2
build/CMakeFiles/progress.marks
View File

@ -1 +1 @@
6
11

BIN
build/CMakeFiles/tracking_demo.dir/cimp/demo.cpp.o
View File

4830
build/CMakeFiles/tracking_demo.dir/compiler_depend.internal
File diff suppressed because it is too large
View File

14481
build/CMakeFiles/tracking_demo.dir/compiler_depend.make
File diff suppressed because it is too large
View File

4
build/CMakeFiles/tracking_demo.dir/progress.make
View File

@ -1,3 +1,3 @@
CMAKE_PROGRESS_1 = 5
CMAKE_PROGRESS_2 = 6
CMAKE_PROGRESS_1 = 10
CMAKE_PROGRESS_2 = 11

109
build/Makefile
View File

@ -200,6 +200,32 @@ tracking_demo/fast:
$(MAKE) $(MAKESILENT) -f CMakeFiles/tracking_demo.dir/build.make CMakeFiles/tracking_demo.dir/build
.PHONY : tracking_demo/fast
#=============================================================================
# Target rules for targets named test_models
# Build rule for target.
test_models: cmake_check_build_system
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 test_models
.PHONY : test_models
# fast build rule for target.
test_models/fast:
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/build
.PHONY : test_models/fast
#=============================================================================
# Target rules for targets named generate_test_samples
# Build rule for target.
generate_test_samples: cmake_check_build_system
$(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 generate_test_samples
.PHONY : generate_test_samples
# fast build rule for target.
generate_test_samples/fast:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/build
.PHONY : generate_test_samples/fast
cimp/bb_regressor/bb_regressor.o: cimp/bb_regressor/bb_regressor.cpp.o
.PHONY : cimp/bb_regressor/bb_regressor.o
@ -224,6 +250,30 @@ cimp/bb_regressor/bb_regressor.cpp.s:
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/cimp/bb_regressor/bb_regressor.cpp.s
.PHONY : cimp/bb_regressor/bb_regressor.cpp.s
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.o: cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.o
# target to build an object file
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o:
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.o
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.i: cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.i
# target to preprocess a source file
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i:
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.i
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.s: cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.s
# target to generate assembly for a file
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s:
$(MAKE) $(MAKESILENT) -f CMakeFiles/bb_regressor.dir/build.make CMakeFiles/bb_regressor.dir/cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s
.PHONY : cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.cpp.s
cimp/classifier/classifier.o: cimp/classifier/classifier.cpp.o
.PHONY : cimp/classifier/classifier.o
@ -272,6 +322,54 @@ cimp/demo.cpp.s:
$(MAKE) $(MAKESILENT) -f CMakeFiles/tracking_demo.dir/build.make CMakeFiles/tracking_demo.dir/cimp/demo.cpp.s
.PHONY : cimp/demo.cpp.s
test/generate_test_samples.o: test/generate_test_samples.cpp.o
.PHONY : test/generate_test_samples.o
# target to build an object file
test/generate_test_samples.cpp.o:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/test/generate_test_samples.cpp.o
.PHONY : test/generate_test_samples.cpp.o
test/generate_test_samples.i: test/generate_test_samples.cpp.i
.PHONY : test/generate_test_samples.i
# target to preprocess a source file
test/generate_test_samples.cpp.i:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/test/generate_test_samples.cpp.i
.PHONY : test/generate_test_samples.cpp.i
test/generate_test_samples.s: test/generate_test_samples.cpp.s
.PHONY : test/generate_test_samples.s
# target to generate assembly for a file
test/generate_test_samples.cpp.s:
$(MAKE) $(MAKESILENT) -f CMakeFiles/generate_test_samples.dir/build.make CMakeFiles/generate_test_samples.dir/test/generate_test_samples.cpp.s
.PHONY : test/generate_test_samples.cpp.s
test/test_models.o: test/test_models.cpp.o
.PHONY : test/test_models.o
# target to build an object file
test/test_models.cpp.o:
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/test/test_models.cpp.o
.PHONY : test/test_models.cpp.o
test/test_models.i: test/test_models.cpp.i
.PHONY : test/test_models.i
# target to preprocess a source file
test/test_models.cpp.i:
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/test/test_models.cpp.i
.PHONY : test/test_models.cpp.i
test/test_models.s: test/test_models.cpp.s
.PHONY : test/test_models.s
# target to generate assembly for a file
test/test_models.cpp.s:
$(MAKE) $(MAKESILENT) -f CMakeFiles/test_models.dir/build.make CMakeFiles/test_models.dir/test/test_models.cpp.s
.PHONY : test/test_models.cpp.s
# Help Target
help:
@echo "The following are some of the valid targets for this Makefile:"
@ -286,16 +384,27 @@ help:
@echo "... rebuild_cache"
@echo "... bb_regressor"
@echo "... classifier"
@echo "... generate_test_samples"
@echo "... test_models"
@echo "... tracking_demo"
@echo "... cimp/bb_regressor/bb_regressor.o"
@echo "... cimp/bb_regressor/bb_regressor.i"
@echo "... cimp/bb_regressor/bb_regressor.s"
@echo "... cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.o"
@echo "... cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.i"
@echo "... cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.s"
@echo "... cimp/classifier/classifier.o"
@echo "... cimp/classifier/classifier.i"
@echo "... cimp/classifier/classifier.s"
@echo "... cimp/demo.o"
@echo "... cimp/demo.i"
@echo "... cimp/demo.s"
@echo "... test/generate_test_samples.o"
@echo "... test/generate_test_samples.i"
@echo "... test/generate_test_samples.s"
@echo "... test/test_models.o"
@echo "... test/test_models.i"
@echo "... test/test_models.s"
.PHONY : help

40
build/cmake_install.cmake
View File

@ -62,6 +62,46 @@ if("x${CMAKE_INSTALL_COMPONENT}x" STREQUAL "xUnspecifiedx" OR NOT CMAKE_INSTALL_
endif()
endif()
if("x${CMAKE_INSTALL_COMPONENT}x" STREQUAL "xUnspecifiedx" OR NOT CMAKE_INSTALL_COMPONENT)
if(EXISTS "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models" AND
NOT IS_SYMLINK "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models")
file(RPATH_CHECK
FILE "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models"
RPATH "")
endif()
file(INSTALL DESTINATION "${CMAKE_INSTALL_PREFIX}/bin" TYPE EXECUTABLE FILES "/media/mht/ADATA/repos/cpp_tracker/build/test_models")
if(EXISTS "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models" AND
NOT IS_SYMLINK "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models")
file(RPATH_CHANGE
FILE "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models"
OLD_RPATH "/home/mht/libtorch/lib:"
NEW_RPATH "")
if(CMAKE_INSTALL_DO_STRIP)
execute_process(COMMAND "/usr/bin/strip" "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/test_models")
endif()
endif()
endif()
if("x${CMAKE_INSTALL_COMPONENT}x" STREQUAL "xUnspecifiedx" OR NOT CMAKE_INSTALL_COMPONENT)
if(EXISTS "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples" AND
NOT IS_SYMLINK "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples")
file(RPATH_CHECK
FILE "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples"
RPATH "")
endif()
file(INSTALL DESTINATION "${CMAKE_INSTALL_PREFIX}/bin" TYPE EXECUTABLE FILES "/media/mht/ADATA/repos/cpp_tracker/build/generate_test_samples")
if(EXISTS "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples" AND
NOT IS_SYMLINK "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples")
file(RPATH_CHANGE
FILE "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples"
OLD_RPATH "/home/mht/libtorch/lib:"
NEW_RPATH "")
if(CMAKE_INSTALL_DO_STRIP)
execute_process(COMMAND "/usr/bin/strip" "$ENV{DESTDIR}${CMAKE_INSTALL_PREFIX}/bin/generate_test_samples")
endif()
endif()
endif()
if(CMAKE_INSTALL_COMPONENT)
set(CMAKE_INSTALL_MANIFEST "install_manifest_${CMAKE_INSTALL_COMPONENT}.txt")
else()

4
build/install_manifest.txt
View File

@ -1 +1,3 @@
/media/mht/ADATA/repos/cpp_tracker/bin/tracking_demo
/media/mht/ADATA/repos/cpp_tracker/bin/tracking_demo
/media/mht/ADATA/repos/cpp_tracker/bin/test_models
/media/mht/ADATA/repos/cpp_tracker/bin/generate_test_samples

BIN
build/libbb_regressor.a
View File

BIN
build/libclassifier.a
View File

BIN
build/tracking_demo
View File

439
cimp/bb_regressor/bb_regressor.cpp
View File

@ -221,16 +221,11 @@ torch::Tensor BBRegressor::load_tensor(const std::string& file_path) {
}
// Constructor
BBRegressor::BBRegressor(const std::string& base_dir, torch::Device dev)
: device(dev), model_dir(base_dir + "/exported_weights/bb_regressor"),
BBRegressor::BBRegressor(const std::string& model_weights_dir, torch::Device dev)
: device(dev), model_dir(model_weights_dir),
fc3_rt(256, 256, 5, true, true, true),
fc4_rt(256, 256, 3, true, true, true) {
// Check if base directory exists
if (!fs::exists(base_dir)) {
throw std::runtime_error("Base directory does not exist: " + base_dir);
}
// Check if model directory exists
if (!fs::exists(model_dir)) {
throw std::runtime_error("Model directory does not exist: " + model_dir);
@ -586,307 +581,213 @@ std::vector<torch::Tensor> BBRegressor::get_iou_feat(std::vector<torch::Tensor>
// Get modulation vectors for the target
std::vector<torch::Tensor> BBRegressor::get_modulation(std::vector<torch::Tensor> feat, torch::Tensor bb) {
// Apply target branch to get modulation vectors
std::cout << " get_modulation input bb: " << bb.sizes() << std::endl;
// Convert bounding box from [x, y, w, h] to [batch_idx, x1, y1, x2, y2] format for ROI pooling
auto roi = torch::zeros({bb.size(0), 5}, bb.options());
// Set batch index to 0 (first element)
roi.index_put_({torch::indexing::Slice(), 0}, 0);
// Copy x, y coordinates
roi.index_put_({torch::indexing::Slice(), 1}, bb.index({torch::indexing::Slice(), 0}));
roi.index_put_({torch::indexing::Slice(), 2}, bb.index({torch::indexing::Slice(), 1}));
// Calculate x2, y2 from width and height
auto x2 = bb.index({torch::indexing::Slice(), 0}) + bb.index({torch::indexing::Slice(), 2});
auto y2 = bb.index({torch::indexing::Slice(), 1}) + bb.index({torch::indexing::Slice(), 3});
roi.index_put_({torch::indexing::Slice(), 3}, x2);
roi.index_put_({torch::indexing::Slice(), 4}, y2);
std::cout << " Converted ROI: [";
for (int i = 0; i < roi.size(1); i++) {
std::cout << roi[0][i].item<float>();
if (i < roi.size(1) - 1) std::cout << ", ";
// feat should contain two tensors: feat3_r and feat4_r (backbone features)
// bb is the initial bounding box [batch_size, 1, 4] (x,y,w,h) or [batch_size, 4]
// Ensure inputs are on the correct device
torch::NoGradGuard no_grad; // Ensure no gradients are computed
auto feat3_r = feat[0].to(device);
auto feat4_r = feat[1].to(device);
auto current_bb = bb.to(device);
// Reshape bb if it's [batch, 1, 4] to [batch, 4]
if (current_bb.dim() == 3 && current_bb.size(1) == 1) {
current_bb = current_bb.squeeze(1);
}
if (current_bb.dim() != 2 || current_bb.size(1) != 4) {
throw std::runtime_error("BBRegressor::get_modulation: bb must be [batch, 4] or [batch, 1, 4]");
}
// Pass through early conv layers (reference branch)
// Python: c3_r = self.conv3_1r(feat3_r)
auto c3_r = conv3_1r->forward(feat3_r);
// Prepare ROIs: convert bb from [x,y,w,h] to [batch_idx, x1,y1,x2,y2]
int batch_size = current_bb.size(0);
auto batch_idx = torch::arange(0, batch_size, current_bb.options().dtype(torch::kFloat)).unsqueeze(1);
auto rois = torch::zeros({batch_size, 5}, current_bb.options());
rois.index_put_({torch::indexing::Slice(), 0}, batch_idx.squeeze(1)); // batch index
rois.index_put_({torch::indexing::Slice(), 1}, current_bb.index({torch::indexing::Slice(), 0})); // x1
rois.index_put_({torch::indexing::Slice(), 2}, current_bb.index({torch::indexing::Slice(), 1})); // y1
rois.index_put_({torch::indexing::Slice(), 3}, current_bb.index({torch::indexing::Slice(), 0}) + current_bb.index({torch::indexing::Slice(), 2})); // x2 = x1 + w
rois.index_put_({torch::indexing::Slice(), 4}, current_bb.index({torch::indexing::Slice(), 1}) + current_bb.index({torch::indexing::Slice(), 3})); // y2 = y1 + h
rois = rois.to(device); // Ensure ROIs are on the correct device
std::cout << " BBRegressor::get_modulation: Converted ROIs (first item): [";
if (batch_size > 0) {
for (int j = 0; j < rois.size(1); j++) {
std::cout << rois[0][j].item<float>();
if (j < rois.size(1) - 1) std::cout << ", ";
}
}
std::cout << "]" << std::endl;
std::cout << " BBRegressor::get_modulation: c3_r shape: " << c3_r.sizes() << ", device: " << c3_r.device() << std::endl;
// Python: roi3r = self.prroi_pool3r(c3_r, roi1)
auto roi3r = prroi_pool3r->forward(c3_r, rois);
std::cout << " BBRegressor::get_modulation: roi3r shape: " << roi3r.sizes() << std::endl;
// Python: c4_r = self.conv4_1r(feat4_r)
auto c4_r = conv4_1r->forward(feat4_r);
std::cout << " BBRegressor::get_modulation: c4_r shape: " << c4_r.sizes() << ", device: " << c4_r.device() << std::endl;
// Python: roi4r = self.prroi_pool4r(c4_r, roi1)
auto roi4r = prroi_pool4r->forward(c4_r, rois);
std::cout << " BBRegressor::get_modulation: roi4r shape: " << roi4r.sizes() << std::endl;
// Python: fc3_r = self.fc3_1r(roi3r)
// fc3_1r is a conv block: conv(128, 256, kernel_size=3, stride=1, padding=0)
// Input roi3r is (batch, 128, 3, 3) -> Output fc3_r is (batch, 256, 1, 1)
auto fc3_r = fc3_1r->forward(roi3r);
std::cout << " BBRegressor::get_modulation: fc3_r shape: " << fc3_r.sizes() << std::endl;
// Python: fc34_r = torch.cat((fc3_r, roi4r), dim=1)
// fc3_r is (batch, 256, 1, 1), roi4r is (batch, 256, 1, 1)
// Result fc34_r is (batch, 512, 1, 1)
auto fc34_r = torch::cat({fc3_r, roi4r}, 1);
std::cout << " BBRegressor::get_modulation: fc34_r shape: " << fc34_r.sizes() << std::endl;
// Python: fc34_3_r = self.fc34_3r(fc34_r)
// fc34_3r is conv(512, 256, kernel_size=1, stride=1, padding=0)
// Output fc34_3_r is (batch, 256, 1, 1)
auto mod_vec1 = fc34_3r->forward(fc34_r);
std::cout << " BBRegressor::get_modulation: mod_vec1 (fc34_3_r) shape: " << mod_vec1.sizes() << std::endl;
// Python: fc34_4_r = self.fc34_4r(fc34_r)
// fc34_4r is conv(512, 256, kernel_size=1, stride=1, padding=0)
// Output fc34_4_r is (batch, 256, 1, 1)
auto mod_vec2 = fc34_4r->forward(fc34_r);
std::cout << " BBRegressor::get_modulation: mod_vec2 (fc34_4_r) shape: " << mod_vec2.sizes() << std::endl;
// Apply target branch to get modulation vectors
auto feat1 = conv3_1t->forward(feat[0]);
auto feat2 = conv3_2t->forward(feat1);
// Apply target branch to get modulation vectors for second feature map
auto feat3 = conv4_1t->forward(feat[1]);
auto feat4 = conv4_2t->forward(feat3);
// ROI pool the features - use the same ROI for both feature maps
std::cout << " Applying ROI pooling to layer 3..." << std::endl;
auto pooled_feat1 = prroi_pool3t->forward(feat2, roi);
std::cout << " Applying ROI pooling to layer 4..." << std::endl;
auto pooled_feat2 = prroi_pool4t->forward(feat4, roi);
// Flatten and concatenate the pooled features
auto vec1 = pooled_feat1.reshape({pooled_feat1.size(0), -1});
auto vec2 = pooled_feat2.reshape({pooled_feat2.size(0), -1});
// Apply fully connected layer to get modulation vectors
auto modulation1 = fc3_rt.forward(vec1);
auto modulation2 = fc4_rt.forward(vec2);
// Return modulation vectors
return {modulation1, modulation2};
return {mod_vec1, mod_vec2};
}
// Predict IoU for proposals
torch::Tensor BBRegressor::predict_iou(std::vector<torch::Tensor> modulation,
std::vector<torch::Tensor> feat,
torch::Tensor proposals) {
// Debug dimensions
std::cout << "Input dimensions:" << std::endl;
std::cout << " modulation[0]: [" << modulation[0].size(0) << ", " << modulation[0].size(1) << "]" << std::endl;
std::cout << " modulation[1]: [" << modulation[1].size(0) << ", " << modulation[1].size(1) << "]" << std::endl;
std::cout << " feat[0]: [" << feat[0].size(0) << ", " << feat[0].size(1) << ", "
<< feat[0].size(2) << ", " << feat[0].size(3) << "]" << std::endl;
std::cout << " feat[1]: [" << feat[1].size(0) << ", " << feat[1].size(1) << ", "
<< feat[1].size(2) << ", " << feat[1].size(3) << "]" << std::endl;
std::cout << " proposals: [" << proposals.size(0) << ", " << proposals.size(1) << ", " << proposals.size(2) << "]" << std::endl;
// Convert proposals from [batch, num_proposals, 4] to [num_proposals, 5] format
// with batch index as the first element
auto batch_size = proposals.size(0);
auto num_proposals = proposals.size(1);
// Reshape proposals to [num_proposals, 4]
auto proposals_view = proposals.reshape({-1, 4});
// Create batch indices tensor [0, 0, 0, ...] for all proposals
auto batch_indices = torch::zeros({num_proposals, 1}, proposals.options());
// Convert proposals from [x, y, w, h] to [batch_idx, x1, y1, x2, y2] format
auto roi = torch::zeros({num_proposals, 5}, proposals.options());
roi.index_put_({torch::indexing::Slice(), 0}, batch_indices.squeeze());
roi.index_put_({torch::indexing::Slice(), 1}, proposals_view.index({torch::indexing::Slice(), 0}));
roi.index_put_({torch::indexing::Slice(), 2}, proposals_view.index({torch::indexing::Slice(), 1}));
// Calculate x2, y2 from width and height
auto x2 = proposals_view.index({torch::indexing::Slice(), 0}) + proposals_view.index({torch::indexing::Slice(), 2});
auto y2 = proposals_view.index({torch::indexing::Slice(), 1}) + proposals_view.index({torch::indexing::Slice(), 3});
roi.index_put_({torch::indexing::Slice(), 3}, x2);
roi.index_put_({torch::indexing::Slice(), 4}, y2);
// Make sure ROI is on the same device as features
torch::Device feat_device = feat[0].device();
// Ensure all inputs are on the correct device
auto target_device = device; // Assuming 'device' is a member of BBRegressor
for (auto& t : feat) { t = t.to(target_device); }
for (auto& m : modulation) { m = m.to(target_device); }
proposals = proposals.to(target_device);
// Get batch size and number of proposals
int batch_size = proposals.size(0);
int num_proposals = proposals.size(1);
// Reshape proposals to [batch_size * num_proposals, 4]
// and add batch index for PrRoIPooling
auto proposals_view = proposals.reshape({batch_size * num_proposals, 4});
auto roi_batch_index = torch::arange(0, batch_size, proposals.options().dtype(torch::kInt)).unsqueeze(1);
roi_batch_index = roi_batch_index.repeat_interleave(num_proposals, 0);
auto roi = torch::cat(std::vector<torch::Tensor>{roi_batch_index.to(proposals_view.options()), proposals_view}, 1);
// Ensure ROI is on the correct device, matching features
auto feat_device = feat[0].device();
roi = roi.to(feat_device);
// Apply ROI pooling to get features for each proposal
auto pooled_feat1 = prroi_pool3r->forward(feat[0], roi);
auto pooled_feat2 = prroi_pool4r->forward(feat[1], roi);
// Make sure all tensors are on the same device (GPU)
torch::Device target_device = modulation[0].device();
pooled_feat1 = pooled_feat1.to(target_device);
pooled_feat2 = pooled_feat2.to(target_device);
auto pooled_feat1 = prroi_pool3t->forward(feat[0], roi); // Output: [batch_size * num_proposals, C, 5, 5]
auto pooled_feat2 = prroi_pool4t->forward(feat[1], roi); // Output: [batch_size * num_proposals, C, 3, 3]
// Print intermediate tensor shapes
std::cout << " Pooled shapes:" << std::endl;
std::cout << " pooled_feat1: [" << pooled_feat1.size(0) << ", " << pooled_feat1.size(1) << ", "
<< pooled_feat1.size(2) << ", " << pooled_feat1.size(3) << "]" << std::endl;
std::cout << " pooled_feat2: [" << pooled_feat2.size(0) << ", " << pooled_feat2.size(1) << ", "
<< pooled_feat2.size(2) << ", " << pooled_feat2.size(3) << "]" << std::endl;
std::cout << " pooled_feat1 (from prroi_pool3t on feat[0]): [" << pooled_feat1.sizes() << "] dev: " << pooled_feat1.device() << std::endl;
std::cout << " pooled_feat2 (from prroi_pool4t on feat[1]): [" << pooled_feat2.sizes() << "] dev: " << pooled_feat2.device() << std::endl;
// Inspect the IoU predictor dimensions
std::cout << " IoU predictor dimensions:" << std::endl;
std::cout << " weight: [" << iou_predictor->weight.size(0) << ", " << iou_predictor->weight.size(1) << "]" << std::endl;
std::cout << " bias: [" << iou_predictor->bias.size(0) << "]" << std::endl;
std::cout << " weight: [" << iou_predictor->weight.sizes() << "]" << std::endl;
std::cout << " bias: [" << iou_predictor->bias.sizes() << "]" << std::endl;
try {
// Flatten pooled features
auto vec1 = pooled_feat1.reshape({pooled_feat1.size(0), -1});
auto vec2 = pooled_feat2.reshape({pooled_feat2.size(0), -1});
// Print flattened shapes
std::cout << " Flattened shapes:" << std::endl;
std::cout << " vec1: [" << vec1.size(0) << ", " << vec1.size(1) << "]" << std::endl;
std::cout << " vec2: [" << vec2.size(0) << ", " << vec2.size(1) << "]" << std::endl;
// We need to adapt the input to match what the IoU predictor expects
// The IoU predictor has a weight matrix of size 512x1, so input should have 512 features
// Instead of concatenating the full features, we need to first reduce them to match expected size
// This is based on the original Python implementation
// Get modulation shapes
std::cout << " Modulation vector shapes:" << std::endl;
std::cout << " mod1: [" << modulation[0].size(0) << ", " << modulation[0].size(1) << "]" << std::endl;
std::cout << " mod2: [" << modulation[1].size(0) << ", " << modulation[1].size(1) << "]" << std::endl;
// Calculate expected dimensions
int mod1_dim = modulation[0].size(1); // Should be 256
int mod2_dim = modulation[1].size(1); // Should be 256
int total_mod_dim = mod1_dim + mod2_dim; // Should be 512, matching iou_predictor weight row count
std::cout << " Using correct input dimensions for IoU predictor (total_dim=" << total_mod_dim << ")" << std::endl;
// Create processed features with correct dimensions
auto processed_feat1 = torch::zeros({num_proposals, mod1_dim}, vec1.options());
auto processed_feat2 = torch::zeros({num_proposals, mod2_dim}, vec2.options());
// We need to reduce the dimensionality of vec1 and vec2 to match mod1_dim and mod2_dim
// We'll use average pooling across spatial dimensions
if (vec1.size(1) > mod1_dim) {
// Average every N values to reduce dimension
int pool_size = vec1.size(1) / mod1_dim;
std::cout << " Reducing vec1 features with pool_size=" << pool_size << std::endl;
for (int i = 0; i < num_proposals; i++) {
for (int j = 0; j < mod1_dim; j++) {
float sum = 0.0f;
for (int k = 0; k < pool_size; k++) {
int idx = j * pool_size + k;
if (idx < vec1.size(1)) {
sum += vec1[i][idx].item<float>();
}
}
processed_feat1[i][j] = sum / pool_size;
}
}
} else {
// Just copy directly if dimensions already match
processed_feat1 = vec1;
auto mod0_4d = modulation[0].to(target_device);
auto mod1_4d = modulation[1].to(target_device);
if (mod0_4d.dim() == 2) {
mod0_4d = mod0_4d.reshape({mod0_4d.size(0), mod0_4d.size(1), 1, 1});
}
if (vec2.size(1) > mod2_dim) {
// Similar reduction for vec2
int pool_size = vec2.size(1) / mod2_dim;
std::cout << " Reducing vec2 features with pool_size=" << pool_size << std::endl;
for (int i = 0; i < num_proposals; i++) {
for (int j = 0; j < mod2_dim; j++) {
float sum = 0.0f;
for (int k = 0; k < pool_size; k++) {
int idx = j * pool_size + k;
if (idx < vec2.size(1)) {
sum += vec2[i][idx].item<float>();
}
}
processed_feat2[i][j] = sum / pool_size;
}
}
} else {
// Just copy directly if dimensions already match
processed_feat2 = vec2;
if (mod1_4d.dim() == 2) {
mod1_4d = mod1_4d.reshape({mod1_4d.size(0), mod1_4d.size(1), 1, 1});
}
// Prepare modulation vectors for each proposal
auto mod1 = modulation[0].repeat({num_proposals, 1});
auto mod2 = modulation[1].repeat({num_proposals, 1});
std::cout << " Final feature shapes:" << std::endl;
std::cout << " processed_feat1: [" << processed_feat1.size(0) << ", " << processed_feat1.size(1) << "]" << std::endl;
std::cout << " processed_feat2: [" << processed_feat2.size(0) << ", " << processed_feat2.size(1) << "]" << std::endl;
std::cout << " mod1: [" << mod1.size(0) << ", " << mod1.size(1) << "]" << std::endl;
std::cout << " mod2: [" << mod2.size(0) << ", " << mod2.size(1) << "]" << std::endl;
// Element-wise multiply features with modulation vectors
auto mod_feat1 = processed_feat1 * mod1;
auto mod_feat2 = processed_feat2 * mod2;
// Concatenate to get final features for IoU prediction
auto ioufeat = torch::cat({mod_feat1, mod_feat2}, /*dim=*/1);
std::cout << " ioufeat shape: [" << ioufeat.size(0) << ", " << ioufeat.size(1) << "]" << std::endl;
// Try GPU implementation first
if (mod0_4d.size(0) == 1 && pooled_feat1.size(0) > 1) {
mod0_4d = mod0_4d.repeat({pooled_feat1.size(0), 1, 1, 1});
}
if (mod1_4d.size(0) == 1 && pooled_feat2.size(0) > 1) {
mod1_4d = mod1_4d.repeat({pooled_feat2.size(0), 1, 1, 1});
}
std::cout << " Modulation vector shapes (reshaped 4D):" << std::endl;
std::cout << " mod0_4d: [" << mod0_4d.sizes() << "] dev: " << mod0_4d.device() << std::endl;
std::cout << " mod1_4d: [" << mod1_4d.sizes() << "] dev: " << mod1_4d.device() << std::endl;
auto feat_prod_0 = pooled_feat1 * mod0_4d;
auto feat_prod_1 = pooled_feat2 * mod1_4d;
std::cout << " After element-wise product with modulation:\n feat_prod_0 (pooled_feat1 * mod0_4d): [" << feat_prod_0.sizes() << "] dev: " << feat_prod_0.device() << "\n feat_prod_1 (pooled_feat2 * mod1_4d): [" << feat_prod_1.sizes() << "] dev: " << feat_prod_1.device() << std::endl;
std::cout << " Applying fc3_rt to feat_prod_0..." << std::endl;
auto x0 = fc3_rt.forward(feat_prod_0); // Corrected: . instead of ->
std::cout << " Applying fc4_rt to feat_prod_1..." << std::endl;
auto x1 = fc4_rt.forward(feat_prod_1); // Corrected: . instead of ->
std::cout << " After fc_rt blocks:\n x0 (fc3_rt output): [" << x0.sizes() << "] dev: " << x0.device() << "\n x1 (fc4_rt output): [" << x1.sizes() << "] dev: " << x1.device() << std::endl;
auto ioufeat_final = torch::cat(std::vector<torch::Tensor>{x0, x1}, 1).contiguous(); // Corrected: std::vector wrapper
std::cout << " Concatenated ioufeat_final: [" << ioufeat_final.sizes() << "] dev: " << ioufeat_final.device() << std::endl;
torch::Tensor iou_scores;
try {
// Apply IoU predictor using GPU
std::cout << " Applying IoU predictor on GPU" << std::endl;
iou_scores = iou_predictor->forward(ioufeat);
std::cout << " Applying final iou_predictor on GPU" << std::endl;
iou_predictor->to(target_device);
iou_scores = iou_predictor->forward(ioufeat_final.to(target_device));
std::cout << " Final iou_predictor on GPU successful. Output scores shape: [" << iou_scores.sizes() << "]" << std::endl;
} catch (const std::exception& cuda_error) {
// If GPU implementation fails, use CPU implementation
std::cout << " GPU implementation failed: " << cuda_error.what() << std::endl;
std::cout << " Falling back to CPU implementation" << std::endl;
// Move tensors to CPU
auto ioufeat_cpu = ioufeat.to(torch::kCPU);
auto weight_cpu = iou_predictor->weight.to(torch::kCPU);
auto bias_cpu = iou_predictor->bias.to(torch::kCPU);
std::cout << " GPU iou_predictor->forward() failed: " << cuda_error.what() << std::endl;
std::cout << " Falling back to CPU for final iou_predictor" << std::endl;
// Implement the linear layer manually
// For each proposal, compute: score = bias + ioufeat * weight
auto scores_cpu = torch::zeros({num_proposals, 1}, torch::kCPU);
auto ioufeat_final_cpu = ioufeat_final.to(torch::kCPU).contiguous();
auto weight_cpu = iou_predictor->weight.to(torch::kCPU).contiguous();
auto bias_cpu = torch::Tensor();
if (iou_predictor->bias.defined()) {
bias_cpu = iou_predictor->bias.to(torch::kCPU).contiguous();
}
std::cout << " DEBUG CPU Fallback: ioufeat_final_cpu device: " << ioufeat_final_cpu.device() << std::endl;
std::cout << " DEBUG CPU Fallback: weight_cpu device: " << weight_cpu.device() << std::endl;
if (bias_cpu.defined()) {
std::cout << " DEBUG CPU Fallback: bias_cpu device: " << bias_cpu.device() << std::endl;
} else {
std::cout << " DEBUG CPU Fallback: bias_cpu is undefined." << std::endl;
}
for (int i = 0; i < num_proposals; i++) {
// Start with bias
float score = bias_cpu[0].item<float>();
// Add weighted sum of features
for (int j = 0; j < ioufeat_cpu.size(1); j++) {
score += ioufeat_cpu[i][j].item<float>() * weight_cpu[0][j].item<float>();
}
scores_cpu[i][0] = score;
try {
iou_scores = torch::nn::functional::linear(ioufeat_final_cpu, weight_cpu, bias_cpu);
std::cout << " CPU fallback torch::nn::functional::linear() successful. Output device: " << iou_scores.device() << std::endl;
} catch (const std::exception& cpu_fwd_error) {
std::cerr << "ERROR during CPU torch::nn::functional::linear(): " << cpu_fwd_error.what() << std::endl;
iou_predictor->to(target_device);
throw;
}
// Move results back to original device
iou_scores = scores_cpu.to(target_device);
iou_predictor->to(target_device);
iou_scores = iou_scores.to(target_device);
}
std::cout << " iou_scores raw shape: [" << iou_scores.size(0) << ", " << iou_scores.size(1) << "]" << std::endl;
// Reshape back to [batch_size, num_proposals]
iou_scores = iou_scores.reshape({batch_size, num_proposals});
std::cout << " Final iou_scores shape: [" << iou_scores.size(0) << ", " << iou_scores.size(1) << "]" << std::endl;
return iou_scores;
} catch (const std::exception& e) {
// This should never happen with our robust implementation
std::cerr << "CRITICAL: Unexpected error in predict_iou: " << e.what() << std::endl;
// We'll implement direct box overlaps as a true fallback that doesn't use "magic numbers"
std::cout << " Implementing direct IoU calculation using box overlaps" << std::endl;
// Move tensors to CPU for direct calculation
auto proposals_cpu = proposals.to(torch::kCPU);
auto bb_cpu = modulation[0].to(torch::kCPU); // Using modulation[0] to get the original target box
// Create output tensor on CPU
auto iou_scores = torch::zeros({batch_size, num_proposals}, torch::kCPU);
// Calculate IoU geometrically for each proposal
// This is a direct, mathematical implementation that doesn't rely on neural networks
for (int i = 0; i < num_proposals; i++) {
float target_x1 = proposals_view[i][0].item<float>();
float target_y1 = proposals_view[i][1].item<float>();
float target_x2 = target_x1 + proposals_view[i][2].item<float>();
float target_y2 = target_y1 + proposals_view[i][3].item<float>();
float box_x1 = bb_cpu[0][0].item<float>();
float box_y1 = bb_cpu[0][1].item<float>();
float box_x2 = box_x1 + bb_cpu[0][2].item<float>();
float box_y2 = box_y1 + bb_cpu[0][3].item<float>();
// Calculate intersection area
float x_left = std::max(target_x1, box_x1);
float y_top = std::max(target_y1, box_y1);
float x_right = std::min(target_x2, box_x2);
float y_bottom = std::min(target_y2, box_y2);
float intersection_area = std::max(0.0f, x_right - x_left) * std::max(0.0f, y_bottom - y_top);
// Calculate union area
float target_area = (target_x2 - target_x1) * (target_y2 - target_y1);
float box_area = (box_x2 - box_x1) * (box_y2 - box_y1);
float union_area = target_area + box_area - intersection_area;
// IoU = intersection / union
float iou = union_area > 0 ? intersection_area / union_area : 0;
iou_scores[0][i] = iou;
}
// Move back to original device
return iou_scores.to(target_device);
std::cout << " Propagating critical error. No fallback available for this stage." << std::endl;
throw;
}
}

10
cimp/bb_regressor/bb_regressor.h
View File

@ -44,19 +44,11 @@ public:
bool use_relu;
};
// PrRoIPool2D implementation
// PrRoIPool2D implementation (requires CUDA)
class PrRoIPool2D {
public:
PrRoIPool2D(int pooled_height, int pooled_width, float spatial_scale);
torch::Tensor forward(torch::Tensor feat, torch::Tensor rois);
// CPU-based fallback implementation
torch::Tensor forward_cpu(torch::Tensor feat, torch::Tensor rois) {
// Simple implementation that returns zeros (for fallback only)
int channels = feat.size(1);
int num_rois = rois.size(0);
return torch::zeros({num_rois, channels, pooled_height_, pooled_width_}, feat.options());
}
private:
int pooled_height_;

135
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu.c
View File

@ -1,135 +0,0 @@
/*
* File : prroi_pooling_gpu.c
* Simplified version for C++ compatibility
*/
#include "prroi_pooling_gpu.h"
#include "prroi_pooling_gpu_impl.cuh"
#include <cuda_runtime.h>
// C wrapper function for the CUDA forward implementation
int prroi_pooling_forward_cuda(
const float *features_data,
const float *rois_data,
float *output_data,
int channels,
int height,
int width,
int num_rois,
int pooled_height,
int pooled_width,
float spatial_scale
) {
int top_count = num_rois * channels * pooled_height * pooled_width;
// Get current CUDA stream
cudaStream_t stream = 0; // Use default stream if no stream is available
cudaError_t err = cudaStreamSynchronize(stream);
if (err != cudaSuccess) {
fprintf(stderr, "CUDA stream error: %s\n", cudaGetErrorString(err));
return -1;
}
// Call the implementation
PrRoIPoolingForwardGpu(
stream,
features_data,
rois_data,
output_data,
channels,
height,
width,
pooled_height,
pooled_width,
spatial_scale,
top_count
);
return 0;
}
// Simplified wrapper for backward pass
int prroi_pooling_backward_cuda(
const float *features_data,
const float *rois_data,
const float *output_data,
const float *output_diff_data,
float *features_diff_data,
int channels,
int height,
int width,
int num_rois,
int pooled_height,
int pooled_width,
float spatial_scale
) {
// Calculate counts for features and output
int top_count = num_rois * channels * pooled_height * pooled_width;
int bottom_count = 1 * channels * height * width; // Assume batch_size = 1
// Get current CUDA stream
cudaStream_t stream = 0; // Use default stream
// Call the implementation
PrRoIPoolingBackwardGpu(
stream,
features_data,
rois_data,
output_data,
output_diff_data,
features_diff_data,
channels,
height,
width,
pooled_height,
pooled_width,
spatial_scale,
top_count,
bottom_count
);
return 0;
}
// Simplified wrapper for coordinate backward pass
int prroi_pooling_coor_backward_cuda(
const float *features_data,
const float *rois_data,
const float *output_data,
const float *output_diff_data,
float *rois_diff_data,
int channels,
int height,
int width,
int num_rois,
int pooled_height,
int pooled_width,
float spatial_scale
) {
// Calculate counts
int top_count = num_rois * channels * pooled_height * pooled_width;
int bottom_count = num_rois * 5; // ROIs are 5D (batch_idx, x1, y1, x2, y2)
// Get current CUDA stream
cudaStream_t stream = 0; // Use default stream
// Call the implementation
PrRoIPoolingCoorBackwardGpu(
stream,
features_data,
rois_data,
output_data,
output_diff_data,
rois_diff_data,
channels,
height,
width,
pooled_height,
pooled_width,
spatial_scale,
top_count,
bottom_count
);
return 0;
}

33
cimp/bb_regressor/prroi_pooling/prroi_pooling_gpu_impl.cu
View File

@ -3,19 +3,28 @@
* Simplified version for C++ compatibility
*/
#include "prroi_pooling_gpu_impl.cuh"
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
#include <cstdio>
#include <cfloat>
#include <cmath>
#define CUDA_NUM_THREADS 512
// Forward declaration of CUDA kernel functions
__global__ void PRROIPoolingForwardKernel(
const int nthreads,
const float *bottom_data,
const float *bottom_rois,
float *top_data,
const int channels,
const int height,
const int width,
const int pooled_height,
const int pooled_width,
const float spatial_scale
);
// Helper macros for CUDA kernel execution
#define CUDA_KERNEL_LOOP(i, n) \
for (int i = blockIdx.x * blockDim.x + threadIdx.x; \
i < (n); \
i += blockDim.x * gridDim.x)
#define CUDA_NUM_THREADS 512
// Helper function to check CUDA errors
inline void checkCudaErrors(cudaError_t err) {
@ -55,7 +64,9 @@ __global__ void PRROIPoolingForwardKernel(
const int pooled_width,
const float spatial_scale
) {
CUDA_KERNEL_LOOP(index, nthreads) {
for (int index = blockIdx.x * blockDim.x + threadIdx.x;
index < nthreads;
index += blockDim.x * gridDim.x) {
// (n, c, ph, pw) is the index in output
int pw = index % pooled_width;
int ph = (index / pooled_width) % pooled_height;
@ -137,7 +148,7 @@ __global__ void PRROIPoolingForwardKernel(
}
// C API wrapper for Forward pass
void PrRoIPoolingForwardGpu(
extern "C" void PrRoIPoolingForwardGpu(
cudaStream_t stream,
const float *bottom_data,
const float *bottom_rois,
@ -170,7 +181,7 @@ void PrRoIPoolingForwardGpu(
}
// Simplified dummy implementations of backward passes
void PrRoIPoolingBackwardGpu(
extern "C" void PrRoIPoolingBackwardGpu(
cudaStream_t stream,
const float *bottom_data,
const float *bottom_rois,
@ -190,7 +201,7 @@ void PrRoIPoolingBackwardGpu(
cudaMemsetAsync(bottom_diff, 0, bottom_count * sizeof(float), stream);
}
void PrRoIPoolingCoorBackwardGpu(
extern "C" void PrRoIPoolingCoorBackwardGpu(
cudaStream_t stream,
const float *bottom_data,
const float *bottom_rois,

20
cimp/demo.cpp
View File

@ -135,20 +135,20 @@ int main(int argc, char* argv[]) {
try {
std::cout << "=== Object Tracking Demo with BBRegressor and Classifier ===" << std::endl;
// Determine which device to use
torch::Device device(torch::kCPU);
// Add more detailed CUDA debugging
// Check CUDA availability - required for this application
std::cout << "Checking CUDA availability..." << std::endl;
std::cout << "torch::cuda::is_available(): " << (torch::cuda::is_available() ? "true" : "false") << std::endl;
if (torch::cuda::is_available()) {
device = torch::Device(torch::kCUDA, 0);
std::cout << "Using CUDA device: " << device << std::endl;
std::cout << "CUDA Device Count: " << torch::cuda::device_count() << std::endl;
} else {
std::cout << "CUDA is not available, using CPU" << std::endl;
if (!torch::cuda::is_available()) {
std::cerr << "ERROR: CUDA is not available. This application requires CUDA." << std::endl;
std::cerr << "Please ensure you have a CUDA-capable GPU and the proper drivers installed." << std::endl;
return 1;
}
// Always use CUDA device
torch::Device device(torch::kCUDA, 0);
std::cout << "Using CUDA device: " << device << std::endl;
std::cout << "CUDA Device Count: " << torch::cuda::device_count() << std::endl;
std::cout << std::endl;
// Find the base directory containing exported weights

12
classifier_stats.txt
View File

@ -1,9 +1,9 @@
Output 0:
Shape: [1, 512, 9, 9]
Mean: -0.000479055
Std: 0.0110019
Min: -0.0458832
Max: 0.0493125
Sum: -19.8674
Sample values: [-0.0125058, 0.00186453, 0.0141787]
Mean: 0.000174798
Std: 0.0110712
Min: -0.0531409
Max: 0.0471968
Sum: 7.24922
Sample values: [-0.00536738, 0.00499956, 0.00910664]

9
cmake-build-debug/CMakeCache.txt
View File

@ -100,6 +100,15 @@ Z_VCPKG_CL:FILEPATH=Z_VCPKG_CL-NOTFOUND
// triplet
_VCPKG_INSTALLED_DIR:PATH=/media/mht/ADATA/repos/cpp_tracker/cmake-build-debug/vcpkg_installed
//Value Computed by CMake
cimp_BINARY_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker/cmake-build-debug
//Value Computed by CMake
cimp_IS_TOP_LEVEL:STATIC=ON
//Value Computed by CMake
cimp_SOURCE_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker
//Value Computed by CMake
cpp_tracker_BINARY_DIR:STATIC=/media/mht/ADATA/repos/cpp_tracker/cmake-build-debug

4
run_demo.sh
View File

@ -8,7 +8,9 @@ elif [ -d "/usr/lib/cuda" ]; then
export CUDA_HOME=/usr/lib/cuda
echo "CUDA environment set to $CUDA_HOME"
else
echo "CUDA not found. Running in CPU-only mode."
echo "CUDA not found. The project requires CUDA to run."
echo "Please install CUDA and try again."
exit 1
fi
# Set LibTorch library path

341
test/compare_models.py
View File

@ -15,33 +15,59 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
# Import model wrappers
from pytracking.features.net_wrappers import DiMPTorchScriptWrapper
# For loading AtomIoUNet from source
from ltr.models.bbreg.atom_iou_net import AtomIoUNet
class ModelComparison:
def __init__(self, model_dir='exported_weights', num_samples=1000):
self.model_dir = model_dir
self.model_dir_name = model_dir # Store the string name for paths
self.num_samples = num_samples
self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
# Base path for models, inputs, and outputs
self.project_root = Path(__file__).resolve().parent.parent
self.model_base_dir = self.project_root / self.model_dir_name
self.input_dir_base = self.project_root / 'test' / 'input_samples'
self.cpp_output_dir_base = self.project_root / 'test' / 'output'
# Initialize comparison results
self.comparison_dir = Path('test') / 'comparison'
self.comparison_dir = self.project_root / 'test' / 'comparison'
self.comparison_dir.mkdir(parents=True, exist_ok=True)
self.plots_dir = self.comparison_dir / 'plots' # plots_dir initialized here
self.plots_dir = self.comparison_dir / 'plots'
self.plots_dir.mkdir(parents=True, exist_ok=True)
self.all_errors_stats = {}
# Initialize models
# Initialize models (TorchScript and from-source)
self._init_models()
def _init_models(self):
"""Initialize Python models"""
print("Loading Python models...")
# Load DiMP components
# Load TorchScript models using _sd arguments for directories of tensors
self.models = DiMPTorchScriptWrapper(
model_dir=self.model_dir,
model_dir=str(self.model_base_dir), # Expects string path
device=self.device,
backbone_sd='backbone', # Directory with backbone weights
classifier_sd='classifier', # Directory with classifier weights
bbregressor_sd='bb_regressor' # Directory with bbox regressor weights
backbone_sd='backbone', # Directory name for backbone weights
classifier_sd='classifier', # Directory name for classifier weights
bbregressor_sd='bb_regressor' # Directory name for bb_regressor weights
)
# Initialize BBRegressor from source for get_modulation fallback
self.bb_regressor_from_source = AtomIoUNet(
input_dim=(512, 1024),
pred_input_dim=(256, 256),
pred_inter_dim=(256, 256)
)
ModelComparison.load_weights_for_custom_model(
self.bb_regressor_from_source,
'bb_regressor', # model_name for path and doc file
self.model_base_dir,
self.device
)
self.bb_regressor_from_source.eval().to(self.device)
print("Python models loaded.")
def compare_classifier(self):
"""Compare classifier model outputs between Python and C++"""
@ -143,115 +169,159 @@ class ModelComparison:
def compare_bb_regressor(self):
"""Compare bb_regressor model outputs between Python and C++"""
print("\nComparing bb_regressor outputs...")
input_dir = Path('test') / 'input_samples' / 'bb_regressor'
cpp_output_dir = Path('test') / 'output' / 'bb_regressor'
input_dir_path = self.input_dir_base / 'bb_regressor'
cpp_output_dir_path = self.cpp_output_dir_base / 'bb_regressor'
if not input_dir.exists() or not cpp_output_dir.exists():
print(f"BB Regressor input or C++ output directory not found ({input_dir}, {cpp_output_dir}). Skipping.")
if not input_dir_path.exists() or not cpp_output_dir_path.exists():
print(f"BB Regressor input or C++ output directory not found ({input_dir_path}, {cpp_output_dir_path}). Skipping BB Regressor comparison.")
# Populate NaN for all expected BB Regressor comparisons if dirs are missing
for i in range(self.num_samples):
sample_key_base = f"BBReg_Sample_{i}"
current_errors = {}
self._compare_tensor_data(None, None, "BBReg PyIoUFeat0 vs CppIoUFeat0", i, current_errors)
self._compare_tensor_data(None, None, "BBReg PyIoUFeat1 vs CppIoUFeat1", i, current_errors)
self._compare_tensor_data(None, None, "BBReg PyMod0 vs CppMod0", i, current_errors)
self._compare_tensor_data(None, None, "BBReg PyMod1 vs CppMod1", i, current_errors)
self._compare_tensor_data(None, None, "BBReg IoUPred", i, current_errors)
self.all_errors_stats[sample_key_base] = current_errors
return
for i in tqdm(range(self.num_samples), desc="BB Regressor samples"):
sample_dir = input_dir / f'sample_{i}'
cpp_output_sample_dir = cpp_output_dir / f'sample_{i}'
sample_dir = input_dir_path / f'sample_{i}'
cpp_out_sample_dir = cpp_output_dir_path / f'sample_{i}'
# Load input tensors for BB Regressor for this sample
feat_layer2_path = sample_dir / 'feat_layer2.pt'
feat_layer3_path = sample_dir / 'feat_layer3.pt'
init_bbox_path = sample_dir / 'init_bbox.pt'
proposals_path = sample_dir / 'proposals.pt'
feat_layer2 = self.load_cpp_tensor(feat_layer2_path, self.device)
feat_layer3 = self.load_cpp_tensor(feat_layer3_path, self.device)
init_bbox = self.load_cpp_tensor(init_bbox_path, self.device)
proposals = self.load_cpp_tensor(proposals_path, self.device)
if any(t is None for t in [feat_layer2, feat_layer3, init_bbox, proposals]):
print(f"Critical: Failed to load one or more BB Regressor input tensors for sample {i}. Skipping.")
continue
py_feat_layer2, py_feat_layer3, py_init_bbox, py_proposals = None, None, None, None
backbone_feat_tuple = (feat_layer2, feat_layer3) # Define the tuple for clarity
# Get IoU features from Python model
# self.models.get_backbone_bbreg_feat calls self.bb_regressor.get_iou_feat
with torch.no_grad():
py_iou_feat = self.models.get_backbone_bbreg_feat({"layer2": feat_layer2, "layer3": feat_layer3})
# Get modulation vectors
squeezed_init_bbox = init_bbox
if init_bbox is not None and init_bbox.dim() == 3 and init_bbox.shape[1] == 1:
squeezed_init_bbox = init_bbox.squeeze(1)
with torch.no_grad():
# Pass original backbone features to get_modulation
py_modulation = self.models.bb_regressor.get_modulation(backbone_feat_tuple, squeezed_init_bbox)
if not sample_dir.exists() or not cpp_out_sample_dir.exists():
print(f"Warning: Skipping BB Regressor sample {i}, files not found at {sample_dir} or {cpp_out_sample_dir}.")
else:
py_feat_layer2 = self.load_cpp_tensor(sample_dir / 'feat_layer2.pt', self.device)
py_feat_layer3 = self.load_cpp_tensor(sample_dir / 'feat_layer3.pt', self.device)
py_init_bbox = self.load_cpp_tensor(sample_dir / 'init_bbox.pt', self.device)
py_proposals = self.load_cpp_tensor(sample_dir / 'proposals.pt', self.device)
# Get Python IoU features (these come directly from backbone, so should be reliable)
py_iou_feat = None
if py_feat_layer2 is not None and py_feat_layer3 is not None:
# Use from-source get_iou_feat for consistent 256-channel features
try:
py_iou_feat = self.bb_regressor_from_source.get_iou_feat([py_feat_layer2, py_feat_layer3])
if isinstance(py_iou_feat, tuple): py_iou_feat = list(py_iou_feat)
print(f"Sample {i}: Successfully used from-source get_iou_feat.")
# py_iou_feat will be a list of two tensors, e.g., [B, 256, H1, W1], [B, 256, H2, W2]
except Exception as e_iou_source:
print(f"Sample {i}: From-source get_iou_feat failed: {e_iou_source}")
py_iou_feat = None # Ensure it's None if failed
# DEBUG: Print shapes
print(f"Sample {i}: py_iou_feat[0] shape: {py_iou_feat[0].shape}, py_modulation[0] shape: {py_modulation[0].shape}")
print(f"Sample {i}: py_iou_feat[1] shape: {py_iou_feat[1].shape}, py_modulation[1] shape: {py_modulation[1].shape}")
# Get Python modulation vectors
py_modulation = None
if py_feat_layer2 is not None and py_feat_layer3 is not None and py_init_bbox is not None:
py_features_list = [py_feat_layer2, py_feat_layer3] # Pass as a list
# Squeeze py_init_bbox if it's [B, 1, 4] to [B, 4]
squeezed_init_bbox = py_init_bbox
if py_init_bbox.ndim == 3 and py_init_bbox.shape[0] > 0 and py_init_bbox.shape[1] == 1:
squeezed_init_bbox = py_init_bbox.squeeze(1)
elif py_init_bbox.ndim == 2:
pass # Already [B,4] or similar, assume correct
else:
print(f"Sample {i}: Warning - py_init_bbox has unexpected shape {py_init_bbox.shape}. Expecting 2D or 3D [B,1,4].")
# Predict IoU (Python model)
try:
# Try TorchScript model first
py_modulation = self.models.bb_regressor.get_modulation(py_features_list, squeezed_init_bbox)
if isinstance(py_modulation, tuple): py_modulation = list(py_modulation)
print(f"Sample {i}: Successfully used TorchScript get_modulation.")
except Exception as e_ts:
print(f"Sample {i}: TorchScript get_modulation failed: {e_ts}. Trying from-source model.")
try:
py_modulation = self.bb_regressor_from_source.get_modulation(py_features_list, squeezed_init_bbox)
if isinstance(py_modulation, tuple): py_modulation = list(py_modulation)
print(f"Sample {i}: Successfully used from-source get_modulation.")
except Exception as e_source:
print(f"Sample {i}: From-source get_modulation also failed: {e_source}")
py_modulation = None
if py_modulation:
print(f"Sample {i}: py_iou_feat[0] shape: {py_iou_feat[0].shape if py_iou_feat and len(py_iou_feat) > 0 else 'N/A'}, py_modulation[0] shape: {py_modulation[0].shape if py_modulation and len(py_modulation) > 0 else 'N/A'}")
print(f"Sample {i}: py_iou_feat[1] shape: {py_iou_feat[1].shape if py_iou_feat and len(py_iou_feat) > 1 else 'N/A'}, py_modulation[1] shape: {py_modulation[1].shape if py_modulation and len(py_modulation) > 1 else 'N/A'}")
# Run Python bb_regressor's predict_iou (from TorchScript model)
py_iou_pred = None
try:
with torch.no_grad():
py_iou_pred = self.models.bb_regressor.predict_iou(py_modulation, py_iou_feat, proposals)
except RuntimeError as e:
print(f"WARNING: Python model self.models.bb_regressor.predict_iou failed for sample {i}: {e}")
if py_modulation is not None and py_iou_feat is not None and py_proposals is not None:
# Ensure modulation vectors are 2D [B, C] for predict_iou
py_mod_0_squeezed = py_modulation[0].squeeze(-1).squeeze(-1) if py_modulation[0].ndim == 4 else py_modulation[0]
py_mod_1_squeezed = py_modulation[1].squeeze(-1).squeeze(-1) if py_modulation[1].ndim == 4 else py_modulation[1]
py_modulation_squeezed_for_pred = [py_mod_0_squeezed, py_mod_1_squeezed]
try:
# Try TorchScript predict_iou first
print(f"Sample {i}: Attempting TorchScript predict_iou with mod_0: {py_modulation[0].shape}, iou_feat_0: {py_iou_feat[0].shape}")
# Ensure inputs for predict_iou are 2D for modulation and 4D for iou_feat
mod_0_squeezed = py_modulation[0].squeeze(-1).squeeze(-1) if py_modulation[0].dim() == 4 else py_modulation[0]
mod_1_squeezed = py_modulation[1].squeeze(-1).squeeze(-1) if py_modulation[1].dim() == 4 else py_modulation[1]
# --- BEGIN PYTHON DETAILED LOGGING ---
print(f" DEBUG PYTHON: py_iou_feat[0] (first 5 rows of first batch) sample values:\n{py_iou_feat[0][0, :, :5, :5] if py_iou_feat[0].numel() > 0 else 'N/A'}") # Print a slice of the feature map
print(f" DEBUG PYTHON: py_iou_feat[1] (first 5 rows of first batch) sample values:\n{py_iou_feat[1][0, :, :5, :5] if py_iou_feat[1].numel() > 0 else 'N/A'}")
print(f" DEBUG PYTHON: mod_0_squeezed sample values:\n{mod_0_squeezed[0, :5] if mod_0_squeezed.numel() > 0 else 'N/A'}")
print(f" DEBUG PYTHON: mod_1_squeezed sample values:\n{mod_1_squeezed[0, :5] if mod_1_squeezed.numel() > 0 else 'N/A'}")
# Construct ioufeat equivalent for Python to log before predict_iou
# This mimics the C++: mod_feat1 = mod_target_0 * mod1_repeated_for_proposals; mod_feat2 = mod_target_1 * mod2_repeated_for_proposals; ioufeat = torch.cat({mod_feat1, mod_feat2}, 1);
# We need py_pooled_feat1, py_pooled_feat2 from PrRoIPool like in C++ before fc3_rt and fc4_rt
# This part is tricky as Python model does it internally in predict_iou.
# For now, let's log the direct inputs to predict_iou and its weights.
# Log weights of the iou_predictor in the TorchScript model
ts_iou_predictor_weight = self.models.bb_regressor.iou_predictor.weight.data
ts_iou_predictor_bias = self.models.bb_regressor.iou_predictor.bias.data
print(f" DEBUG PYTHON: TorchScript iou_predictor.weight:\n{ts_iou_predictor_weight}")
print(f" DEBUG PYTHON: TorchScript iou_predictor.bias:\n{ts_iou_predictor_bias}")
# --- END PYTHON DETAILED LOGGING ---
py_iou_pred = self.models.bb_regressor.predict_iou(
py_modulation_squeezed_for_pred,
py_iou_feat, # These are now from source model (256ch)
py_proposals
)
print(f"Sample {i}: Successfully used TorchScript predict_iou.")
except Exception as e_ts_pred:
print(f"WARNING: Python model self.models.bb_regressor.predict_iou failed for sample {i}: {e_ts_pred}")
print(f"Sample {i}: Falling back to from-source predict_iou.")
try:
py_iou_pred = self.bb_regressor_from_source.predict_iou(
py_modulation_squeezed_for_pred,
py_iou_feat,
py_proposals
)
print(f"Sample {i}: Successfully used from-source predict_iou.")
except Exception as e_source_pred:
print(f"ERROR: Python model self.bb_regressor_from_source.predict_iou also failed for sample {i}: {e_source_pred}")
py_iou_pred = None # Ensure it's None if fallback also failed
# Load C++ outputs
cpp_iou_pred_path = cpp_output_sample_dir / 'iou_pred.pt'
cpp_modulation_0_path = cpp_output_sample_dir / 'modulation_0.pt'
cpp_modulation_1_path = cpp_output_sample_dir / 'modulation_1.pt'
cpp_feat_0_path = cpp_output_sample_dir / 'iou_feat_0.pt'
cpp_feat_1_path = cpp_output_sample_dir / 'iou_feat_1.pt'
cpp_iou_pred = self.load_cpp_tensor(cpp_iou_pred_path, self.device)
cpp_modulation_0 = self.load_cpp_tensor(cpp_modulation_0_path, self.device)
cpp_modulation_1 = self.load_cpp_tensor(cpp_modulation_1_path, self.device)
cpp_feat_0 = self.load_cpp_tensor(cpp_feat_0_path, self.device)
cpp_feat_1 = self.load_cpp_tensor(cpp_feat_1_path, self.device)
current_errors = {} # Store errors for this sample for the HTML report
# Compare IoU features (py_iou_feat vs cpp_feat_0/1)
# _compare_tensor_data will handle None inputs appropriately
cpp_iou_pred, cpp_mod_0, cpp_mod_1, cpp_iou_feat_0, cpp_iou_feat_1 = None, None, None, None, None
if cpp_out_sample_dir.exists():
cpp_iou_pred = self.load_cpp_tensor(cpp_output_dir_path / f"sample_{i}" / 'iou_pred.pt', self.device)
cpp_mod_0 = self.load_cpp_tensor(cpp_output_dir_path / f"sample_{i}" / 'modulation_0.pt', self.device)
cpp_mod_1 = self.load_cpp_tensor(cpp_output_dir_path / f"sample_{i}" / 'modulation_1.pt', self.device)
cpp_iou_feat_0 = self.load_cpp_tensor(cpp_output_dir_path / f"sample_{i}" / 'iou_feat_0.pt', self.device)
cpp_iou_feat_1 = self.load_cpp_tensor(cpp_output_dir_path / f"sample_{i}" / 'iou_feat_1.pt', self.device)
current_errors = {}
py_iou_f0 = py_iou_feat[0] if py_iou_feat and len(py_iou_feat) > 0 else None
py_iou_f1 = py_iou_feat[1] if py_iou_feat and len(py_iou_feat) > 1 else None
self._compare_tensor_data(py_iou_f0, cpp_feat_0, "BBReg PyIoUFeat0 vs CppIoUFeat0", i, current_errors)
self._compare_tensor_data(py_iou_f1, cpp_feat_1, "BBReg PyIoUFeat1 vs CppIoUFeat1", i, current_errors)
# Compare modulation vectors (py_modulation vs cpp_modulation_0/1)
self._compare_tensor_data(py_iou_f0, cpp_iou_feat_0, "BBReg PyIoUFeat0 vs CppIoUFeat0", i, current_errors)
self._compare_tensor_data(py_iou_f1, cpp_iou_feat_1, "BBReg PyIoUFeat1 vs CppIoUFeat1", i, current_errors)
py_mod_0 = py_modulation[0] if py_modulation and len(py_modulation) > 0 else None
py_mod_1 = py_modulation[1] if py_modulation and len(py_modulation) > 1 else None
self._compare_tensor_data(py_mod_0, cpp_modulation_0, "BBReg PyMod0 vs CppMod0", i, current_errors)
self._compare_tensor_data(py_mod_1, cpp_modulation_1, "BBReg PyMod1 vs CppMod1", i, current_errors)
# Compare final IoU prediction
# _compare_tensor_data will handle None for py_iou_pred or cpp_iou_pred
self._compare_tensor_data(py_mod_0, cpp_mod_0, "BBReg PyMod0 vs CppMod0", i, current_errors)
self._compare_tensor_data(py_mod_1, cpp_mod_1, "BBReg PyMod1 vs CppMod1", i, current_errors)
self._compare_tensor_data(py_iou_pred, cpp_iou_pred, "BBReg IoUPred", i, current_errors)
if current_errors: # Add to overall statistics if any comparisons were made/attempted
self.all_errors_stats[f"BBReg_Sample_{i}"] = current_errors
# Note: MAE accumulation for overall average needs to be selective based on valid comparisons
# For simplicity, we'll let the HTML report show NaNs for failed/skipped comparisons.
if not self.all_errors_stats: # Check if any BB regressor comparisons were made
print("No BB Regressor comparisons were performed for this model type.") # Clarified message
# No plots or stats if nothing was compared for BB regressor
return
# The following old averaging and plotting is now handled by generate_html_report using all_errors_stats
# print("\nBB Regressor Comparison Statistics:")
# if iou_pred_errors:
# print(f" IoU Prediction MAE: Mean={np.mean(iou_pred_errors):.4e}, Std={np.std(iou_pred_errors):.4e}")
# if modulation_errors:
# print(f" Modulation MAE: Mean={np.mean(modulation_errors):.4e}, Std={np.std(modulation_errors):.4e}")
# if feat_errors:
# print(f" IoU Feature MAE: Mean={np.mean(feat_errors):.4e}, Std={np.std(feat_errors):.4e}")
# # Plots - these would need to be rethought with the new error structure
# self._generate_stats_and_plots(iou_pred_errors, "BB Regressor IoU Prediction Error", self.plots_dir / "bbreg_iou_pred_error_hist.png")
# self._generate_stats_and_plots(modulation_errors, "BB Regressor Modulation Error", self.plots_dir / "bbreg_modulation_error_hist.png")
# self._generate_stats_and_plots(feat_errors, "BB Regressor IoU Feature Error", self.plots_dir / "bbreg_feature_error_hist.png")
self.all_errors_stats[f"BBReg_Sample_{i}"] = current_errors
def generate_html_report(self):
print("\nGenerating HTML report...")
@ -747,6 +817,73 @@ class ModelComparison:
# For direct use, if needed, it could return the tuple:
# return (mae, max_err, diff_arr_for_hist, mean_py_val, std_abs_err, l2_norm_py, l2_norm_cpp, l2_norm_diff, cosine_sim, pearson_corr, mean_rel_err)
@staticmethod
def load_weights_for_custom_model(model, model_name, base_model_dir, device):
"""
Helper to load weights from individual .pt files into a model instance.
model: the PyTorch nn.Module instance.
model_name: e.g., 'classifier' or 'bb_regressor'.
base_model_dir: Path object to the base directory like 'exported_weights'.
device: torch device.
"""
tensor_dir = base_model_dir / model_name
doc_file = tensor_dir / f"{model_name}_weights_doc.txt"
if not doc_file.exists():
print(f"Warning: Documentation file not found: {doc_file} for {model_name}. Skipping weight loading for source model.")
return
with open(doc_file, 'r') as f:
lines = f.readlines()
i = 0
while i < len(lines):
line = lines[i]
if line.startswith('## '):
key = line.strip()[3:]
j = i + 1
while j < len(lines) and 'File:' not in lines[j]:
j += 1
if j < len(lines) and 'File:' in lines[j]:
file_name = lines[j].split('File:')[1].strip()
tensor_path = tensor_dir / file_name
if tensor_path.exists():
try:
tensor_data = torch.load(str(tensor_path), map_location=device)
# For .pt files that might be RecursiveScriptModule, try to extract tensor
if isinstance(tensor_data, torch.jit.RecursiveScriptModule):
if hasattr(tensor_data, 'weight'): tensor = tensor_data.weight
elif hasattr(tensor_data, 'bias'): tensor = tensor_data.bias
elif len(list(tensor_data.parameters())) > 0: tensor = list(tensor_data.parameters())[0]
else: tensor = tensor_data() # Try calling it
else:
tensor = tensor_data
parts = key.split('.')
module_to_set = model
for part in parts[:-1]:
module_to_set = getattr(module_to_set, part)
param_name = parts[-1]
if hasattr(module_to_set, param_name):
if param_name in module_to_set._parameters:
module_to_set._parameters[param_name] = torch.nn.Parameter(tensor.to(device))
elif param_name in module_to_set._buffers:
module_to_set._buffers[param_name] = tensor.to(device)
else: # Direct attribute assignment
setattr(module_to_set, param_name, tensor.to(device))
# print(f"Loaded {key} from {file_name} into source {model_name}")
else:
print(f"Warning: Attribute {key} not found in source model {model_name}.")
except Exception as e:
print(f"Error loading tensor for {key} from {tensor_path} for source {model_name}: {e}")
else:
print(f"Warning: Tensor file not found: {tensor_path} for source {model_name}")
i = j
i += 1
model.eval().to(device)
if __name__ == "__main__":
# Parse command line arguments

Write Preview
Loading…
Cancel
Save