Need step-by-step guide for installation of nvCOMP and running of the accompanying examples

AI & Data Science Data Processing
1

I don’t understand the instructions given at “nvcomp/blob/main/README.md”

Could someone please provide a step-by-step guide for the installation of nvCOMP using the following assumption and format:

System info:
• Ubuntu 20.04
• RTX-3060
• NVIDIA driver 470.82.01
• CUDA 11.4
• GCC 9.4.0

The Steps

  1. Download “exact_installation_package_name(s)_here”

• Observation: The package “nvcomp_install_CUDA_11.x.tgz” from “nvcomp-download” has the exact structure as described here at nvcomp/blob/main/README.md. However, this package seems to be different from the “nvcomp” folder obtained from “git clone Loading...

  1. If needed, where to place the decompressed installation package

  2. If needed, how to run cmake to install nvCOMP (your exact code on your computer)

• Eg, “cmake -DNVCOMP_EXTS_ROOT=/path/to/nvcomp_exts/${CUDA_VERSION} … make -j” (from some web site - sorry, NVIDIA only allows me to post one link here)

• But, is “CUDA_VERSION” a literal string or a placeholder for, say, “CUDA_11.4”?

• Is this “CUDA_VERSION” already a bash variable defined or set up by the installation package, or is it a variable supposed to be recognisable by the operating system because of some prior CUDA installation?

• What exactly is “nvcomp_exts” in the path?

  1. If needed, how to specify the path(s)

  2. If needed, how to cmake the sample codes, ie, in which directory to run the terminal and what exact code to run.

  3. The exact folder+code sequence to build and run “high_level_quickstart_example.cpp”

• Eg, in “folder_foo” run terminal with “this line of code”.

• Please skip highlevel_cpp_quickstart.md

Many thanks.