How to Install and Uninstall libcub-dev Package on Ubuntu 21.04 (Hirsute Hippo)

Last updated: May 10,2024

1. Install "libcub-dev" package

This guide covers the steps necessary to install libcub-dev on Ubuntu 21.04 (Hirsute Hippo)


    
        
            $
        

        
            
                sudo apt update
            
                    
    
    Copied


    
        
            $
        

        
            
                sudo apt install
            
                        
                libcub-dev
            
                    
    
    Copied

2. Uninstall "libcub-dev" package

Here is a brief guide to show you how to uninstall libcub-dev on Ubuntu 21.04 (Hirsute Hippo):


    
        
            $
        

        
            
                sudo apt remove
            
                        
                libcub-dev
            
                    
    
    Copied


    
        
            $
        

        
            
                sudo apt autoclean && sudo apt autoremove
            
                    
    
    Copied

3. Information about the libcub-dev package on Ubuntu 21.04 (Hirsute Hippo)

Package: libcub-dev
Architecture: all
Version: 1.11.0-1
Multi-Arch: foreign
Priority: optional
Section: universe/libdevel
Source: cub
Origin: Ubuntu
Maintainer: Ubuntu Developers
Original-Maintainer: Debian NVIDIA Maintainers
Bugs: https://bugs.launchpad.net/ubuntu/+filebug
Installed-Size: 2160
Filename: pool/universe/c/cub/libcub-dev_1.11.0-1_all.deb
Size: 169908
MD5sum: 533d012de2bb6bbf6767e9b5fc12cd5b
SHA1: 732775b556cc722b9108ed908cea17abd4c730b0
SHA256: 234ccb537e4fbcd6e8882b6bdb378a66bfce0075d98917a981e24281c2e86292
SHA512: 75473fed42fc8d3b4d73fee76bbcd9b106e071b50a5f943fb7dc8c4ebcc526765f49f47af70a456065e2ebaeaf82d58205200c82f92a6d8205673cd627e8e3d5
Homepage: https://github.com/NVIDIA/cub
Description-en: 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
Description-md5: c26ecbfbeaf591f27a9db7f69082e611