rocm-ds-smi-science-tools

Files (37)

• SKILL.md
• SKILL.md · benchmark-validate/
• TOOLING.yaml · benchmark-validate/
• benchmark_report.md · benchmark-validate/examples/
• run_rocm_benchmark.sh · benchmark-validate/scripts/
• SKILL.md · compatibility-triage/
• TOOLING.yaml · compatibility-triage/
• official-support-notes.md · compatibility-triage/references/
• detect_rocm_env.sh · compatibility-triage/scripts/
• routing_example.md · examples/
• SKILL.md · hipdf-pandas-port/
• TOOLING.yaml · hipdf-pandas-port/
• pandas-to-hipdf-port.md · hipdf-pandas-port/examples/
• hipdf-notes.md · hipdf-pandas-port/references/
• scan-pandas.sh · hipdf-pandas-port/scripts/
• SKILL.md · hipgraph-analytics/
• TOOLING.yaml · hipgraph-analytics/
• pagerank.md · hipgraph-analytics/examples/
• SKILL.md · hipmm-memory-ops/
• TOOLING.yaml · hipmm-memory-ops/
• basic.md · hipmm-memory-ops/examples/
• SKILL.md · hipraft-primitives/
• TOOLING.yaml · hipraft-primitives/
• clustering.md · hipraft-primitives/examples/
• SKILL.md · hipvs-ann/
• TOOLING.yaml · hipvs-ann/
• ann-index-selection.md · hipvs-ann/examples/
• SKILL.md · install-build/
• TOOLING.yaml · install-build/
• create_conda_env.sh · install-build/scripts/
• SKILL.md · pipeline-integration/
• TOOLING.yaml · pipeline-integration/
• end_to_end_pipeline.py · pipeline-integration/examples/
• SKILL.md · tool-router/
• TOOLING.yaml · tool-router/
• rocm-ds-components.md · tool-router/references/
• route_task.py · tool-router/scripts/

SKILL.md (first lines)

# ROCm-DS SMI Science Tools Overview

This is the parent skill for managing tasks related to ROCm Data Science (ROCm-DS) and AMD GPU-accelerated scientific computing tools.

## When to use this skill
Use this skill to determine the appropriate nested skill to invoke when working with ROCm-DS components, porting data science workflows to ROCm, or handling installation and compatibility.

## Nested Skills Directory

- **`compatibility-triage`**: Verifies whether a requested ROCm-DS workflow is officially supported, source-build feasible, or experimental on the target system.
- **`hipdf-pandas-port`**: Migrates pandas-like workflows to hipDF and cudf.pandas style acceleration, auditing for unsupported features.
- **`hipgraph-analytics`**: Leverages GPU acceleration to process and analyze complex graph structures using hipGRAPH.
- **`hipmm-memory-ops`**: Utilizes the HIP Memory Manager (hipMM) for advanced GPU memory pooling, efficient allocation, and data movement.
- **`hipraft-primitives`**: Utilizes hipRAFT for foundational, reusable GPU-accelerated primitives like clustering, dimensionality reduction, and statistical operations.
- **`hipvs-ann`**: Selects, builds, benchmarks, and validates hipVS ANN indexes and query paths for ROCm-DS workloads.
- **`install-build`**: Handles installation and source compilation of ROCm-DS components via conda, PyPI, or source builds.
- **`pipeline-integration`**: Integrates ROCm-DS components into broader data science pipelines.
- **`benchmark-validate`**: Validates and benchmarks ROCm-DS component ports against their CPU baselines (e.g., pandas vs hipDF).
- **`tool-router`**: Classifies and routes tasks to the appropriate ROCm-DS component (hipDF, hipVS, hipGRAPH, hipRAFT, hipMM) based on workload requirements.

From carlosfundora/gfxGRAPH, MIT.

More from carlosfundora/gfxGRAPH