skills/amd-rocm/
  SKILL.md
  references/
    rocm-stack/
      README.md
      what-is-rocm.md
      core-sdk-overview.md
      math-compute-libraries.md
      communication-libraries.md
      runtime-and-compilers.md
      profiling-debugging-tools.md
      control-monitoring-tools.md
      media-storage-libraries.md
      install-linux.md
      install-deep-learning-frameworks.md
      install-docker-spack.md
      install-windows.md
      compatibility-and-release-history.md
      ai-ecosystem.md
      gpu-systems-infra.md
      toolkits.md
    hip/
      README.md
      programming-model.md
      hardware-implementation.md
      compilers-clr.md
      performance-guidelines.md
      cpp-language-extensions.md
      kernel-language-cpp-support.md
      hiprtc.md
      debugging-logging.md
      runtime-api-overview.md
      initialization-version.md
      device-management.md
      error-handling.md
      stream-management.md
      event-management.md
      asynchronous-execution.md
      execution-control-launch.md
      occupancy.md
      module-context-management.md
      memory-management.md
      host-memory.md
      device-memory.md
      unified-memory.md
      virtual-memory.md
      stream-ordered-allocator.md
      texture-surface.md
      graph-management.md
      cooperative-groups.md
      multi-device-peer-to-peer.md
      interop.md
      porting-cuda-to-hip.md
      cuda-to-hip-api-comparison.md
      hipify.md
      math-api.md
      env-variables.md
      deprecated-apis.md
      hardware-features.md
    gpu-arch/
      README.md
      gpu-architecture-overview.md
      gpu-arch-specs.md
      cdna-architecture.md
      rdna-architecture.md
      performance-optimization-guides.md
      mi100-microarchitecture.md
      mi250-microarchitecture.md
      mi300-microarchitecture.md
      precision-support.md
      mi300-mi200-performance-counters.md
      mi350-performance-counters.md
      isa-documentation.md
      machine-readable-isa.md
  samples/
    README.md
    vector-add-kernel.md
    explicit-memory-transfer.md
    shared-memory-tiled-matmul.md
    dynamic-shared-memory.md
    unified-memory.md
    stream-ordered-allocation.md
    stream-overlap.md
    hip-graph-stream-capture.md
    hip-graph-explicit-nodes.md
    cooperative-groups-reduction.md
    warp-shuffle-reduction.md
    multi-gpu-peer-to-peer.md
    occupancy-tuning.md
    hipify-cuda-to-hip.md
    event-timing.md
    device-query.md
    hiprtc-runtime-compilation.md
    rocblas-gemm.md
  scripts/
    README.md
    install.md
    hipcc-build.md
    hipify.md
    gpu-query.md
    profiling.md
    debug.md
    sanitize.md
    frameworks.md
    validation.md