nvidia-cuda-toolkit for Debian
------------------------------
Contents:
1. Getting NVCC Working with the Compiler
2. Installing the CUDA Code Samples
Getting NVCC Working with the Compiler
======================================
It is worth noting that not all compilers can be used together with NVCC.
Here is a list of possible combinations, partially based on [1]:
```
CUDA Toolkit Version | Supported GCC Versions | Supported Clang Versions
---------------------+------------------------+-------------------------
11.5 | 6 - 11 | 6.0 - 12
11.4.1 | 6 - 11 | 6.0 - 11
11.4 | 6 - 10 | 6.0 - 11
11.3 | (5) 6 - 10 | (3.8) 6.0 - 11
11.2 | (5) 6 - 10 | (3.8) 6.0 - 11
11.1 | (5) 6 - 10 | (3.8) 6.0 - 10
11.0 | (5) 6 - 9 | (3.8) 6.0 - 9
10.2 | 5 - 8 | 3.8 - 8
10.1 Update 1 | 5 - 8 | 3.8 - 8
10.1 | 5 - 8 | 3.8 - 7
10.0 | 5 - 7 | 3.8 - 6.0
9.2 | 5 - 7 | 3.8 - 5.0
9.1 | 5 - 6 | 3.8 - 4.0
9.0 | 5 - 6 | 3.8 - 3.9
8.0 | 5 | 3.8
7.5 | 4.9 (5) | 3.6
```
[1] https://gist.github.com/ax3l/9489132
Installing the CUDA Code Samples
=================================
The CUDA Code Samples come with non-redistributable media files (images,
videos, ...) and therefore cannot be packaged.
(See https://bugs.debian.org/702948 for details.)
To install the CUDA Code Samples, download the RUN installer for Linux from
https://developer.nvidia.com/cuda-downloads#linux
This download includes an old driver and the full toolkit, but unfortunately
there is no separate download available for the Samples.
Install the Samples to ~/NVIDIA_CUDA-11.4_Samples/ with
sh cuda_11.4.1_470.57.02_linux.run --silent --override --samples --samplespath=$HOME
(Adjust the filename if you downloaded a different version.)
The following Debian packages are needed to build the examples:
* freeglut3-dev
* libfreeimage-dev
* libglfw3-dev
* libvulkan-dev
* pkgconf
This optional package will be used if it is installed, too:
* mpi-default-dev
For using clang as host compiler, this package is needed as well:
* libomp-dev
To build the example programs, change to the directory where the Samples were
installed (by default: ~/NVIDIA_CUDA-11.4_Samples/) and run
MA_LIBDIR=/usr/lib/$(dpkg-architecture -qDEB_HOST_MULTIARCH)
make CUDA_PATH=/usr CUDA_SEARCH_PATH=$MA_LIBDIR GLPATH=$MA_LIBDIR VULKAN_SDK_PATH=$MA_LIBDIR
Optionally add HOST_COMPILER=... to select a different compiler for the host
parts of the code. Currently up to g++-11 and clang++-12 are supported.
For more information on the Samples, please see
https://developer.nvidia.com/cuda-code-samples
-- Andreas Beckmann <anbe@debian.org> Sun, 18 Jul 2021 01:02:40 +0200
Generated by dwww version 1.14 on Mon Aug 11 02:39:03 CEST 2025.