This repository has been archived by the owner on Mar 21, 2024. It is now read-only.
Notify users that CUB_NS_QUALIFIER must be set when using other NS macros #350
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
DVS CL: 30228013 |
alliepiper
force-pushed
the
missing_qualifier_macro_notice
branch
from
cafb0ec
to
6c7b8be
Compare
alliepiper
added a commit
to alliepiper/thrust
that referenced
this pull request
Jul 27, 2021
alliepiper
added
testing: gpuCI passed
gevtushenko
approved these changes
Jul 28, 2021
facebook-github-bot
pushed a commit
to pytorch/FBGEMM
that referenced
this pull request
May 6, 2022
Summary: Since CUB1.14.0, there is a breaking change: NVIDIA/cub#350: When the CUB_NS_[PRE|POST]FIX macros are set, CUB_NS_QUALIFIER must also be defined to the fully qualified CUB namespace (e.g. #define CUB_NS_QUALIFIER ::foo::cub). Without the fix, on CUDA11.6, the fbgemm_gpu fail to build with following errors: > from /usr/local/cuda/include/cub/device/device_radix_sort.cuh:40, > from ../../../src/split_embeddings_cache_cuda.cu:10: > /usr/local/cuda-11.6/targets/x86_64-linux/include/cub/util_namespace.cuh:46:2: error: #error CUB requires a definition of CUB_NS_QUALIFIER when CUB_NS_PREFIX/POSTFIX are defined. > 46 | #error CUB requires a definition of CUB_NS_QUALIFIER when CUB_NS_PREFIX/POSTFIX are defined. > | ^~~~~ > [3/169] Building CUDA object CMakeFiles/fbgemm_gpu_py.dir/src/layout_transform_ops.cu.o > FAILED: CMakeFiles/fbgemm_gpu_py.dir/src/layout_transform_ops.cu.o > /usr/local/cuda/bin/nvcc -DFBGEMM_CUB_USE_NAMESPACE -DUSE_C10D_GLOO -DUSE_C10D_MPI -DUSE_C10D_NCCL -DUSE_DISTRIBUTED -DUSE_RPC -DUSE_TENSORPIPE -Dfbgemm_gpu_py_EXPORTS -I/code/FBGEMM/fbgemm_gpu -I/code/FBGEMM/fbgemm_gpu/include -I/code/FBGEMM/include -I/code/FBGEMM/third_party/asmjit/src -I/code/FBGEMM/third_party/cpuinfo/include -isystem=/usr/local/lib/python3.8/dist-packages/torch/include -isystem=/usr/local/lib/python3.8/dist-packages/torch/include/torch/csrc/api/include -isystem=/usr/local/cuda/include -DONNX_NAMESPACE=onnx_c2 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=sm_80 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=integer_sign_change,--diag_suppress=useless_using_declaration,--diag_suppress=set_but_not_used,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=implicit_return_from_non_void_function,--diag_suppress=unsigned_compare_with_zero,--diag_suppress=declared_but_not_referenced,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda -O3 -DNDEBUG -Xcompiler=-fPIC -D_GLIBCXX_USE_CXX11_ABI=1 --expt-relaxed-constexpr -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -x cu -c ../../../src/layout_transform_ops.cu -o CMakeFiles/fbgemm_gpu_py.dir/src/layout_transform_ops.cu.o && /usr/local/cuda/bin/nvcc -DFBGEMM_CUB_USE_NAMESPACE -DUSE_C10D_GLOO -DUSE_C10D_MPI -DUSE_C10D_NCCL -DUSE_DISTRIBUTED -DUSE_RPC -DUSE_TENSORPIPE -Dfbgemm_gpu_py_EXPORTS -I/code/FBGEMM/fbgemm_gpu -I/code/FBGEMM/fbgemm_gpu/include -I/code/FBGEMM/include -I/code/FBGEMM/third_party/asmjit/src -I/code/FBGEMM/third_party/cpuinfo/include -isystem=/usr/local/lib/python3.8/dist-packages/torch/include -isystem=/usr/local/lib/python3.8/dist-packages/torch/include/torch/csrc/api/include -isystem=/usr/local/cuda/include -DONNX_NAMESPACE=onnx_c2 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=sm_80 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=integer_sign_change,--diag_suppress=useless_using_declaration,--diag_suppress=set_but_not_used,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=implicit_return_from_non_void_function,--diag_suppress=unsigned_compare_with_zero,--diag_suppress=declared_but_not_referenced,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda -O3 -DNDEBUG -Xcompiler=-fPIC -D_GLIBCXX_USE_CXX11_ABI=1 --expt-relaxed-constexpr -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -x cu -M ../../../src/layout_transform_ops.cu -MT CMakeFiles/fbgemm_gpu_py.dir/src/layout_transform_ops.cu.o -o CMakeFiles/fbgemm_gpu_py.dir/src/layout_transform_ops.cu.o.d > In file included from /usr/local/cuda/include/cub/device/../util_arch.cuh:37, > from /usr/local/cuda/include/cub/device/../config.cuh:35, > from /usr/local/cuda/include/cub/device/device_scan.cuh:40, > from ../../../src/layout_transform_ops.cu:10: > /usr/local/cuda/include/cub/device/../util_namespace.cuh:46:2: error: #error CUB requires a definition of CUB_NS_QUALIFIER when CUB_NS_PREFIX/POSTFIX are defined. > 46 | #error CUB requires a definition of CUB_NS_QUALIFIER when CUB_NS_PREFIX/POSTFIX are defined. > | ^~~~~ > [4/169] Building CXX object CMakeFiles/fbgemm_gpu_py.dir/src/cpu_utils.cpp.o https://github.com/NVIDIA/cub/releases/tag/1.14.0 Pull Request resolved: #1101 Reviewed By: brad-mengchi Differential Revision: D36189683 Pulled By: jianyuh fbshipit-source-id: 11286fe3923972fd5f5f332649716e7f2d6e206a
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.