bring-example-ptx-back

[yunwei37]

This pull request introduces enhancements and documentation updates to support PTX generation for CUDA on GPUs using the llvmbpf library. It includes changes to the main documentation, a new example program, and build configurations to demonstrate and facilitate this functionality.

Documentation Updates:

• Updated README.md to clarify the PTX generation feature, including renaming a section to "PTX generation for CUDA on GPU" and adding a new table of contents entry for this feature. [1] [2] [3]
• Added a detailed README.md in the example/ptx directory, explaining the workflow, components, and usage of the PTX example program. This includes instructions for building and running the example, as well as a comprehensive code explanation.

Code and Build Enhancements:

• Added a new example program (ptx_test) in example/ptx to demonstrate generating and running PTX code for eBPF programs on CUDA-capable GPUs. This includes a complete workflow from eBPF to PTX compilation, CUDA binary generation, and execution.
• Updated CMakeLists.txt in example/ptx to include build configurations for the new ptx_test program, with options for specifying the CUDA installation path and linking necessary libraries.

[Copilot]

Pull Request Overview

This PR adds support and documentation for generating and running PTX code on NVIDIA GPUs using the llvmbpf library.

• Refactored main README.md to clarify and rename the PTX/CUDA feature and update the table of contents.
• Introduced a new PTX example under example/ptx, complete with a detailed README and a ptx_test program.
• Added CMake configuration in example/ptx to build ptx_test with CUDA path options and necessary library links.

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.

File	Description
example/ptx/README.md	Added detailed README for the PTX example, covering setup and code explanations
example/ptx/CMakeLists.txt	New CMakeLists for ptx_test, including CUDA path option and library/link settings
README.md	Renamed PTX section to “PTX generation for CUDA on GPU” and added TOC entry

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 78.96%. Comparing base (486e7b1) to head (6148b53).
Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #32   +/-   ##
=======================================
  Coverage   78.96%   78.96%           
=======================================
  Files           5        5           
  Lines        1193     1193           
  Branches      124      124           
=======================================
  Hits          942      942           
  Misses        251      251           

Flag	Coverage Δ
bpf_conformance	66.30% <ø> (ø)
unittests	52.13% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.