菜单
This skill should be used when profiling AMD GPU kernels with rocprof-compute to collect metrics, roofline data, and analyze bottlenecks for HIP kernels.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | rocprof-compute |
| description | This skill should be used when profiling AMD GPU kernels with rocprof-compute to collect metrics, roofline data, and analyze bottlenecks for HIP kernels. |
source .venv/bin/activatepython -m pip install -r /opt/rocm-7.0.0/libexec/rocprofiler-compute/requirements.txtsource .venv/bin/activate && rocprof-compute profile -n <name> --path <out_dir> --join-type kernel -b SQ -b TCP -b TCC -- <cmd> <args>rocprof-compute profile -n kernelgen --path rocprof_compute_profile --no-roof --join-type kernel -b SQ -b TCP -b TCC -- .venv/bin/python -O op_tests/test_pa_ragged.py -p Shomy -q none -c 128--join-type kernel for comparing same kernel across grids; switch to grid if grid-sensitive.-b blocks to target specific hardware units; use --list-metrics <arch> if unsure.--no-roof to skip roofline if only counters are needed; remove it to gather roofline data.rocprof-compute analyze --path <out_dir> -b <metric_ids> or --list-stats / --list-metrics <arch> to discover ids.rocprof-compute analyze --path rocprof_compute_profile -b 2--gui (default port 8050 or --random-port) or --tui.--name + --path per experiment.--kernel or --dispatch if needed.references/rocprof_compute_profile_help.txt for full rocprof-compute profile --help.references/rocprof_compute_analyze_help.txt for full rocprof-compute analyze --help.This skill should be used when optimizing AMD GPU kernels on MI300 using the aiter project, including running op tests, benchmarking, iterating on kernel changes, and recording results in the kernel experiment database.
This skill should be used when reasoning about GPU architecture fundamentals to guide kernel optimization choices such as memory hierarchy usage, execution model mapping, block sizing, and latency-aware tuning across HIP, Triton, and PyTorch.
This skill should be used when writing or tuning HIP kernels on AMD/NVIDIA GPUs, covering memory coalescing, shared-memory tiling, bank conflict avoidance, warp primitives, occupancy, vectorization, async ops, loop unrolling, and profiling.
This skill should be used when optimizing kernels in this repo and needing to consult past optimization experiments, or when recording the current optimization iteration back into the kernel experiment database.
MI300/CDNA3 architecture guide for HIP/Triton optimization—MFMA variants, dual register files, data formats, sparsity, LDS/GWS, and best practices.
CDNA3/MI300 HIP programming insights—chiplet/cache model, Infinity Cache, memory coherency, matrix cores, sparsity, and best practices.