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
- 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...
-
If needed, where to place the decompressed installation package
-
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?
-
If needed, how to specify the path(s)
-
If needed, how to cmake the sample codes, ie, in which directory to run the terminal and what exact code to run.
-
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.