# CMAKE generated file: DO NOT EDIT!
# Generated by "Unix Makefiles" Generator, CMake Version 3.26

CMakeFiles/tiny-cuda-nn.dir/src/common_host.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/common_host.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h
 /usr/include/c++/9/stack
 /usr/include/c++/9/bits/stl_stack.h
 /usr/include/c++/9/iostream

CMakeFiles/tiny-cuda-nn.dir/src/cpp_api.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/cpp_api.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encoding.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h
 /usr/include/c++/9/stack
 /usr/include/c++/9/bits/stl_stack.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/network_with_input_encoding.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/network.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h

CMakeFiles/tiny-cuda-nn.dir/src/cutlass_mlp.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/cutlass_mlp.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/networks/cutlass_mlp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/network.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cutlass_matmul.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/cutlass.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/numeric_types.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/integer_subbyte.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/platform/platform.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/half.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/bfloat16.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tfloat32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array_subbyte.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/functional.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/complex.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuComplex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/real.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/fast_math.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/uint128.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/quaternion.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/pitch_linear_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/vector.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/arch.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/device_kernel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/threadblock_swizzle.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/conv2d_problem_size.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/convolution.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/conv3d_problem_size.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/semaphore.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/aligned_buffer.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix_shape.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/default_gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/mma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/mma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_bf16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_bf16.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/mma.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm50.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm60.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm61.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/wmma_array.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sparse_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm72.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/epilogue.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/pitch_linear_thread_map.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/predicate_vector.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_ref.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/subbyte_reference.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_view.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/epilogue_base.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/output_tile_thread_map.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/cache_operation.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_params.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/numeric_conversion.h
 /usr/include/c++/9/cfenv
 /usr/include/c++/9/fenv.h
 /usr/include/fenv.h
 /usr/include/x86_64-linux-gnu/bits/fenv.h
 /usr/include/x86_64-linux-gnu/bits/fenvinline.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/thread/unaryOp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/scale_type.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm_pipelined.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_fast_f32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_tensor_op_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_pipelined.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_base.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_singlestage.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_tensor_op_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm50.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm60.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/thread/reduce.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm61.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_multistage_mma_complex_core.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_multistage_mma_complex_core_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op_fast_f32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_gaussian_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_gaussian_complex_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_multistage.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator_params.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_iterator_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/thread/transpose.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_clamp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_relu.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/activation.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/constants.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_relu0.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_gelu.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_generic.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_sigmoid.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_hardswish.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_planar_complex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array_planar_complex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/conversion_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/reduction_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_tensor_op_mixed.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_strided_dgrad.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_affine.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/shared_load_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/shared_load_iterator_mixed.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/interleaved_epilogue.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/volta_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/simt_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/wmma_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/default_gemm_configuration.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/default_gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/kernel/reduce_split_k.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/thread/reduction_operators.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h
 /usr/include/c++/9/stack
 /usr/include/c++/9/bits/stl_stack.h

CMakeFiles/tiny-cuda-nn.dir/src/encoding.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/encoding.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encoding.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/composite.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h
 /usr/include/c++/9/stack
 /usr/include/c++/9/bits/stl_stack.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/empty.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/frequency.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/grid.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/grid_interface.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/random.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/identity.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/oneblob.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/spherical_harmonics.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/encodings/triangle_wave.h

CMakeFiles/tiny-cuda-nn.dir/src/fully_fused_mlp.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/fully_fused_mlp.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/networks/fully_fused_mlp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/network.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cutlass_matmul.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/cutlass.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/numeric_types.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/integer_subbyte.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/platform/platform.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/half.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/bfloat16.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tfloat32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array_subbyte.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/functional.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/complex.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuComplex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/real.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/fast_math.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/uint128.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/quaternion.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/pitch_linear_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/vector.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/arch.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/device_kernel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/threadblock_swizzle.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/conv2d_problem_size.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_coord.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/convolution.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/conv/conv3d_problem_size.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/semaphore.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/aligned_buffer.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/matrix_shape.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/default_gemm.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/mma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/mma.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_bf16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_bf16.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/mma.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm50.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm60.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm61.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/wmma_array.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/mma_sparse_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm72.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/wmma_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/epilogue.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/pitch_linear_thread_map.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/predicate_vector.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_ref.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/subbyte_reference.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/tensor_view.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/epilogue_base.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/output_tile_thread_map.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/memory_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/arch/cache_operation.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_params.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/numeric_conversion.h
 /usr/include/c++/9/cfenv
 /usr/include/c++/9/fenv.h
 /usr/include/fenv.h
 /usr/include/x86_64-linux-gnu/bits/fenv.h
 /usr/include/x86_64-linux-gnu/bits/fenvinline.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/thread/unaryOp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/scale_type.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm_pipelined.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm75.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_fast_f32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_tensor_op_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_pipelined.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_base.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_singlestage.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/layout/tensor_op_multiplicand_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_tensor_op_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_sm70.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm50.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm60.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/thread/reduce.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/thread/mma_sm61.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_simt_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_multistage_mma_complex_core.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_access_iterator_tensor_op_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_multistage_mma_complex_core_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/default_mma_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_complex_tensor_op_fast_f32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_gaussian_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_gaussian_complex_tensor_op_tile_iterator_sm80.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/mma_multistage.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator_params.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_iterator_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/predicated_tile_access_iterator_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/thread/transpose.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear_2dthreadtile.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/threadblock/default_mma_core_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/warp/mma_tensor_op_tile_iterator_wmma.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_clamp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_relu.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/activation.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/constants.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_relu0.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_gelu.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_generic.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_sigmoid.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_hardswish.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/linear_combination_planar_complex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/array_planar_complex.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/conversion_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/thread/reduction_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_complex_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_tensor_op_mixed.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_strided_dgrad.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/predicated_tile_iterator_affine.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/shared_load_iterator.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/shared_load_iterator_mixed.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/interleaved_epilogue.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/volta_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_volta_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/simt_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_simt.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_epilogue_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/fragment_iterator_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/wmma_tensor_op_policy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/warp/tile_iterator_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/epilogue/threadblock/default_thread_map_wmma_tensor_op.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/default_gemm_configuration.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/device/gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/default_gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/gemm/kernel/gemm_splitk_parallel.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/kernel/reduce_split_k.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/cutlass/include/cutlass/reduction/thread/reduction_operators.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h
 /usr/include/c++/9/stack
 /usr/include/c++/9/bits/stl_stack.h

CMakeFiles/tiny-cuda-nn.dir/src/loss.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/loss.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/loss.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/mape.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/smape.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/l1.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/l2.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/relative_l1.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/relative_l2.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/relative_l2_luminance.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/cross_entropy.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/losses/variance_is.h

CMakeFiles/tiny-cuda-nn.dir/src/network.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/network.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/network.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/networks/cutlass_mlp.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/networks/fully_fused_mlp.h

CMakeFiles/tiny-cuda-nn.dir/src/object.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/object.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic

CMakeFiles/tiny-cuda-nn.dir/src/optimizer.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/optimizer.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizer.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/object.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_matrix.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/pcg32/pcg32.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/adam.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_device.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory_json.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/average.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/batched.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/composite.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/ema.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/exponential_decay.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/lookahead.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/novograd.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/reduce_sum.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/optimizers/sgd.h

CMakeFiles/tiny-cuda-nn.dir/src/reduce_sum.cu.o
 /home/worker/yt/CVPR24/tiny-cuda-nn/src/reduce_sum.cu
 /usr/include/stdc-predef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_config.h
 /usr/include/features.h
 /usr/include/x86_64-linux-gnu/sys/cdefs.h
 /usr/include/x86_64-linux-gnu/bits/wordsize.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/local/cuda-11.6/targets/x86_64-linux/include/builtin_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/host_defines.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_types.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/limits.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/syslimits.h
 /usr/include/limits.h
 /usr/include/x86_64-linux-gnu/bits/libc-header-start.h
 /usr/include/x86_64-linux-gnu/bits/posix1_lim.h
 /usr/include/x86_64-linux-gnu/bits/local_lim.h
 /usr/include/linux/limits.h
 /usr/include/x86_64-linux-gnu/bits/posix2_lim.h
 /usr/include/x86_64-linux-gnu/bits/xopen_lim.h
 /usr/include/x86_64-linux-gnu/bits/uio_lim.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stddef.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/library_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/channel_descriptor.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_device_runtime_api.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/driver_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/vector_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/common_functions.h
 /usr/include/string.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/strings.h
 /usr/include/x86_64-linux-gnu/bits/strings_fortified.h
 /usr/include/x86_64-linux-gnu/bits/string_fortified.h
 /usr/include/time.h
 /usr/include/x86_64-linux-gnu/bits/time.h
 /usr/include/x86_64-linux-gnu/bits/types.h
 /usr/include/x86_64-linux-gnu/bits/timesize.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/timex.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h
 /usr/include/x86_64-linux-gnu/bits/types/clock_t.h
 /usr/include/x86_64-linux-gnu/bits/types/time_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.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/types/clockid_t.h
 /usr/include/x86_64-linux-gnu/bits/types/timer_t.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h
 /usr/include/c++/9/new
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++config.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/os_defines.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/cpu_defines.h
 /usr/include/c++/9/exception
 /usr/include/c++/9/bits/exception.h
 /usr/include/c++/9/bits/exception_ptr.h
 /usr/include/c++/9/bits/exception_defines.h
 /usr/include/c++/9/bits/cxxabi_init_exception.h
 /usr/include/c++/9/typeinfo
 /usr/include/c++/9/bits/hash_bytes.h
 /usr/include/c++/9/bits/nested_exception.h
 /usr/include/c++/9/bits/move.h
 /usr/include/c++/9/bits/concept_check.h
 /usr/include/c++/9/type_traits
 /usr/include/stdio.h
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdarg.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/sys_errlist.h
 /usr/include/x86_64-linux-gnu/bits/stdio.h
 /usr/include/x86_64-linux-gnu/bits/stdio2.h
 /usr/include/c++/9/stdlib.h
 /usr/include/c++/9/cstdlib
 /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/floatn.h
 /usr/include/x86_64-linux-gnu/bits/floatn-common.h
 /usr/include/x86_64-linux-gnu/sys/types.h
 /usr/include/x86_64-linux-gnu/bits/stdint-intn.h
 /usr/include/endian.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/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/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++/9/bits/std_abs.h
 /usr/include/assert.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.h
 /usr/include/c++/9/math.h
 /usr/include/c++/9/cmath
 /usr/include/c++/9/bits/cpp_type_traits.h
 /usr/include/c++/9/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/x86_64-linux-gnu/bits/mathinline.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/math_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_surface_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_texture_types.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/device_double_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_60_atomic_functions.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_20_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_30_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_32_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_35_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/sm_61_intrinsics.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_70_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/crt/sm_80_rt.hpp
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_fetch_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/texture_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/surface_indirect_functions.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/device_launch_parameters.h
 /usr/include/c++/9/functional
 /usr/include/c++/9/bits/stl_function.h
 /usr/include/c++/9/backward/binders.h
 /usr/include/c++/9/tuple
 /usr/include/c++/9/utility
 /usr/include/c++/9/bits/stl_relops.h
 /usr/include/c++/9/bits/stl_pair.h
 /usr/include/c++/9/initializer_list
 /usr/include/c++/9/array
 /usr/include/c++/9/stdexcept
 /usr/include/c++/9/string
 /usr/include/c++/9/bits/stringfwd.h
 /usr/include/c++/9/bits/memoryfwd.h
 /usr/include/c++/9/bits/char_traits.h
 /usr/include/c++/9/bits/stl_algobase.h
 /usr/include/c++/9/bits/functexcept.h
 /usr/include/c++/9/ext/numeric_traits.h
 /usr/include/c++/9/bits/stl_iterator_base_types.h
 /usr/include/c++/9/bits/stl_iterator_base_funcs.h
 /usr/include/c++/9/debug/assertions.h
 /usr/include/c++/9/bits/stl_iterator.h
 /usr/include/c++/9/bits/ptr_traits.h
 /usr/include/c++/9/debug/debug.h
 /usr/include/c++/9/bits/predefined_ops.h
 /usr/include/c++/9/bits/postypes.h
 /usr/include/c++/9/cwchar
 /usr/include/wchar.h
 /usr/include/x86_64-linux-gnu/bits/wchar.h
 /usr/include/x86_64-linux-gnu/bits/types/wint_t.h
 /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h
 /usr/include/x86_64-linux-gnu/bits/wchar2.h
 /usr/include/c++/9/cstdint
 /usr/lib/gcc/x86_64-linux-gnu/9/include/stdint.h
 /usr/include/stdint.h
 /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h
 /usr/include/c++/9/bits/allocator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++allocator.h
 /usr/include/c++/9/ext/new_allocator.h
 /usr/include/c++/9/bits/localefwd.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/c++locale.h
 /usr/include/c++/9/clocale
 /usr/include/locale.h
 /usr/include/x86_64-linux-gnu/bits/locale.h
 /usr/include/c++/9/iosfwd
 /usr/include/c++/9/cctype
 /usr/include/ctype.h
 /usr/include/c++/9/bits/ostream_insert.h
 /usr/include/c++/9/bits/cxxabi_forced.h
 /usr/include/c++/9/bits/range_access.h
 /usr/include/c++/9/bits/basic_string.h
 /usr/include/c++/9/ext/atomicity.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/gthr-default.h
 /usr/include/pthread.h
 /usr/include/sched.h
 /usr/include/x86_64-linux-gnu/bits/sched.h
 /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h
 /usr/include/x86_64-linux-gnu/bits/cpu-set.h
 /usr/include/x86_64-linux-gnu/bits/setjmp.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/atomic_word.h
 /usr/include/c++/9/ext/alloc_traits.h
 /usr/include/c++/9/bits/alloc_traits.h
 /usr/include/c++/9/ext/string_conversions.h
 /usr/include/c++/9/cstdio
 /usr/include/c++/9/cerrno
 /usr/include/errno.h
 /usr/include/x86_64-linux-gnu/bits/errno.h
 /usr/include/linux/errno.h
 /usr/include/x86_64-linux-gnu/asm/errno.h
 /usr/include/asm-generic/errno.h
 /usr/include/asm-generic/errno-base.h
 /usr/include/x86_64-linux-gnu/bits/types/error_t.h
 /usr/include/c++/9/bits/functional_hash.h
 /usr/include/c++/9/bits/basic_string.tcc
 /usr/include/c++/9/bits/uses_allocator.h
 /usr/include/c++/9/bits/invoke.h
 /usr/include/c++/9/bits/refwrap.h
 /usr/include/c++/9/bits/std_function.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/reduce_sum.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common.h
 /usr/include/c++/9/algorithm
 /usr/include/c++/9/bits/stl_algo.h
 /usr/include/c++/9/bits/algorithmfwd.h
 /usr/include/c++/9/bits/stl_heap.h
 /usr/include/c++/9/bits/stl_tempbuf.h
 /usr/include/c++/9/bits/stl_construct.h
 /usr/include/c++/9/bits/uniform_int_dist.h
 /usr/include/c++/9/limits
 /usr/include/c++/9/cstddef
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda_fp16.hpp
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/vec.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/gpu_memory.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/common_host.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cpp_api.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/json/json.hpp
 /usr/include/c++/9/iterator
 /usr/include/c++/9/ostream
 /usr/include/c++/9/ios
 /usr/include/c++/9/bits/ios_base.h
 /usr/include/c++/9/bits/locale_classes.h
 /usr/include/c++/9/bits/locale_classes.tcc
 /usr/include/c++/9/system_error
 /usr/include/x86_64-linux-gnu/c++/9/bits/error_constants.h
 /usr/include/c++/9/streambuf
 /usr/include/c++/9/bits/streambuf.tcc
 /usr/include/c++/9/bits/basic_ios.h
 /usr/include/c++/9/bits/locale_facets.h
 /usr/include/c++/9/cwctype
 /usr/include/wctype.h
 /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_base.h
 /usr/include/c++/9/bits/streambuf_iterator.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/ctype_inline.h
 /usr/include/c++/9/bits/locale_facets.tcc
 /usr/include/c++/9/bits/basic_ios.tcc
 /usr/include/c++/9/bits/ostream.tcc
 /usr/include/c++/9/istream
 /usr/include/c++/9/bits/istream.tcc
 /usr/include/c++/9/bits/stream_iterator.h
 /usr/include/c++/9/memory
 /usr/include/c++/9/bits/stl_uninitialized.h
 /usr/include/c++/9/bits/stl_raw_storage_iter.h
 /usr/include/c++/9/ext/concurrence.h
 /usr/include/c++/9/bits/unique_ptr.h
 /usr/include/c++/9/bits/shared_ptr.h
 /usr/include/c++/9/bits/shared_ptr_base.h
 /usr/include/c++/9/bits/allocated_ptr.h
 /usr/include/c++/9/ext/aligned_buffer.h
 /usr/include/c++/9/bits/shared_ptr_atomic.h
 /usr/include/c++/9/bits/atomic_base.h
 /usr/include/c++/9/bits/atomic_lockfree_defines.h
 /usr/include/c++/9/backward/auto_ptr.h
 /usr/include/c++/9/numeric
 /usr/include/c++/9/bits/stl_numeric.h
 /usr/include/c++/9/vector
 /usr/include/c++/9/bits/stl_vector.h
 /usr/include/c++/9/bits/stl_bvector.h
 /usr/include/c++/9/bits/vector.tcc
 /usr/include/c++/9/forward_list
 /usr/include/c++/9/bits/forward_list.h
 /usr/include/c++/9/bits/forward_list.tcc
 /usr/include/c++/9/map
 /usr/include/c++/9/bits/stl_tree.h
 /usr/include/c++/9/bits/stl_map.h
 /usr/include/c++/9/bits/stl_multimap.h
 /usr/include/c++/9/bits/erase_if.h
 /usr/include/c++/9/unordered_map
 /usr/include/c++/9/bits/hashtable.h
 /usr/include/c++/9/bits/hashtable_policy.h
 /usr/include/c++/9/bits/unordered_map.h
 /usr/include/c++/9/valarray
 /usr/include/c++/9/bits/valarray_array.h
 /usr/include/c++/9/bits/valarray_array.tcc
 /usr/include/c++/9/bits/valarray_before.h
 /usr/include/c++/9/bits/slice_array.h
 /usr/include/c++/9/bits/valarray_after.h
 /usr/include/c++/9/bits/gslice.h
 /usr/include/c++/9/bits/gslice_array.h
 /usr/include/c++/9/bits/mask_array.h
 /usr/include/c++/9/bits/indirect_array.h
 /usr/include/c++/9/cassert
 /usr/include/c++/9/cstring
 /usr/include/c++/9/iomanip
 /usr/include/c++/9/locale
 /usr/include/c++/9/bits/locale_facets_nonio.h
 /usr/include/c++/9/ctime
 /usr/include/x86_64-linux-gnu/c++/9/bits/time_members.h
 /usr/include/x86_64-linux-gnu/c++/9/bits/messages_members.h
 /usr/include/libintl.h
 /usr/include/c++/9/bits/codecvt.h
 /usr/include/c++/9/bits/locale_facets_nonio.tcc
 /usr/include/c++/9/bits/locale_conv.h
 /usr/include/c++/9/bits/quoted_string.h
 /usr/include/c++/9/sstream
 /usr/include/c++/9/bits/sstream.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/format.h
 /home/worker/yt/CVPR24/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h
 /usr/include/c++/9/experimental/string_view
 /usr/include/c++/9/experimental/bits/lfts_config.h
 /usr/include/c++/9/experimental/bits/string_view.tcc
 /home/worker/yt/CVPR24/tiny-cuda-nn/include/tiny-cuda-nn/cuda_graph.h
 /usr/local/cuda-11.6/targets/x86_64-linux/include/cuda.h
 /usr/include/c++/9/deque
 /usr/include/c++/9/bits/stl_deque.h
 /usr/include/c++/9/bits/deque.tcc
 /usr/include/c++/9/atomic

