Source: cccl Section: libdevel Priority: optional Maintainer: Debian NVIDIA Maintainers Uploaders: Andreas Beckmann , Build-Depends: debhelper-compat (= 13), cmake, llvm-19-tools, python3, Rules-Requires-Root: no Standards-Version: 4.7.0 Homepage: https://github.com/NVIDIA/cccl Vcs-Browser: https://salsa.debian.org/nvidia-team/cccl Vcs-Git: https://salsa.debian.org/nvidia-team/cccl.git Package: libcu++-dev Architecture: all Multi-Arch: foreign Depends: ${misc:Depends}, Breaks: nvidia-cuda-dev (<< 11.6.2-5~), nvidia-cuda-dev (= 11.7.0-1), nvidia-cuda-dev (= 11.7.1-1), Replaces: nvidia-cuda-dev (<< 11.6.2-5~), nvidia-cuda-dev (= 11.7.0-1), nvidia-cuda-dev (= 11.7.1-1), Description: NVIDIA C++ Standard Library libcu++ provides a heterogeneous implementation of the C++ Standard Library that can be used in and between CPU and GPU code. . Using libcu++ is as simple as using the C++ Standard Library. All that is needed is adding 'cuda/std/' to the start of the Standard Library includes and 'cuda::' before any uses of 'std::': . * #include * cuda::std::atomic x; Package: libcub-dev Architecture: all Multi-Arch: foreign Depends: libcu++-dev (= ${binary:Version}), ${misc:Depends} Breaks: libthrust-dev (<< 1.15.0), Description: reusable software components for the CUDA programming model CUB provides state-of-the-art, reusable software components for every layer of the CUDA programming model: * Parallel primitives * Warp-wide "collective" primitives * Block-wide "collective" primitives * Device-wide primitives * Utilities * Fancy iterators * Thread and thread block I/O * PTX intrinsics * Device, kernel, and storage management Package: libthrust-dev Architecture: all Multi-Arch: foreign Depends: libcu++-dev (= ${binary:Version}), libcub-dev (= ${binary:Version}), ${misc:Depends} Recommends: libtbb-dev, Suggests: nvidia-cuda-toolkit Provides: libcccl-dev (= ${binary:Version}), Description: Thrust - Parallel Algorithms Library Thrust is a parallel algorithms library which resembles the C++ Standard Template Library (STL). Thrust's high-level interface greatly enhances programmer productivity while enabling performance portability between GPUs and multicore CPUs. Interoperability with established technologies (such as CUDA, TBB, and OpenMP) facilitates integration with existing software.