Skip to content

ywang103-amd/omniperf

This branch is 12 commits ahead of, 3 commits behind ROCm/rocprofiler-compute:amd-staging.

Folders and files

NameName
Last commit message
Last commit date
Nov 5, 2024
Jan 2, 2025
Nov 7, 2024
Nov 7, 2024
Dec 23, 2024
Nov 26, 2024
Nov 7, 2024
Jan 8, 2025
Jan 8, 2025
Jan 5, 2025
Nov 4, 2022
Nov 7, 2024
Nov 7, 2024
Aug 9, 2024
Nov 7, 2024
Nov 1, 2024
Nov 7, 2024
Nov 26, 2024
Dec 23, 2024
Jan 24, 2024
Nov 7, 2024
Jan 5, 2025
Nov 1, 2024
Nov 7, 2024
Feb 27, 2024
Nov 14, 2024

Repository files navigation

Ubuntu 22.04 RHEL 8 Instinct Docs DOI

ROCm Compute Profiler

General

ROCm Compute Profiler is a system performance profiling tool for machine learning/HPC workloads running on AMD MI GPUs. The tool presently targets usage on MI100, MI200, and MI300 accelerators.

  • For more information on available features, installation steps, and workload profiling and analysis, please refer to the online documentation.

  • ROCm Compute Profiler is an AMD open source research project and is not supported as part of the ROCm software stack. We welcome contributions and feedback from the community. Please see the CONTRIBUTING.md file for additional details on our contribution process.

  • Licensing information can be found in the LICENSE file.

Development

ROCm Compute Profiler follows a main-dev branching model. As a result, our latest stable release is shipped from the amd-mainline branch, while new features are developed in our amd-staging branch.

Users may checkout amd-staging to preview upcoming features.

Testing

To quickly get the environment (bash shell) for building and testing, run the following commands:

  • cd utils/docker_env
  • docker compose run app

Inside the docker container, clean, build and install the project with tests enabled:

rm -rf build install && cmake -B build -D CMAKE_INSTALL_PREFIX=install -D ENABLE_TESTS=ON -D INSTALL_TESTS=ON -DENABLE_COVERAGE=ON -S . && cmake --build build --target install --parallel 8

Note that per the above command, build assets will be stored under build directory and installed assets will be stored under install directory.

Then, to run the automated test suite, run the following command:

ctest

For manual testing, you can find the executable at install/bin/rocprof-compute

NOTE: This Dockerfile uses rocm/dev-ubuntu-22.04 as the base image

How to Cite

This software can be cited using a Zenodo DOI reference. A BibTex style reference is provided below for convenience:

@software{xiaomin_lu_2022_7314631
  author       = {Xiaomin Lu and
                  Cole Ramos and
                  Fei Zheng and
                  Karl W. Schulz and
                  Jose Santos and
                  Keith Lowery and
                  Nicholas Curtis and
                  Cristian Di Pietrantonio},
  title        = {ROCm/rocprofiler-compute: v3.0.0 (01 November 2024)},
  month        = November,
  year         = 2024,
  publisher    = {Zenodo},
  version      = {v3.0.0},
  doi          = {10.5281/zenodo.7314631},
  url          = {https://doi.org/10.5281/zenodo.7314631}
}

About

Advanced Profiling and Analytics for AMD Hardware

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 82.7%
  • CSS 8.3%
  • JavaScript 3.1%
  • Shell 2.4%
  • CMake 2.0%
  • HTML 0.8%
  • Other 0.7%