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-11.2_Samples/ with

  sh cuda_11.2.2_460.32.03_linux.run --silent --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-11.2_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++-10 and clang++-11 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