メニュー
Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Write unit tests for OpenVINO ov::Model graph transformations (passes). Use when the user asks to write, add, or refactor tests for a transformation pass (MatcherPass, ModelPass), or to modernize legacy transformation tests.
Troubleshooting all sorts of failures, crashes, exceptions and errors using debug capabilities. Analyze accuracy, performance, model compilation, or memory issues. Dump tensors and intermediate blobs. Serialize and visualize IRs, execution graphs. Enable verbose, logging. Profile execution. Compare layer outputs. Inspect, trace or dump transformations. Identify executed operations, nodes, primitives, kernels.
Upgrade the PyTorch version used by OpenVINO tests (torch / torchvision / torchaudio) and resolve fallout — missing operator translators, new functionalized `*_copy` aten ops, decomposition changes, FX-only tests failing in TorchScript mode, and accuracy regressions caused by stricter typing. Use when the user asks to "bump torch", "update pytorch to X.Y", "upgrade torch tests", or when pytorch_tests / model_hub pytorch tests fail after a torch version change. Do not use for: enabling a single new PyTorch operator unrelated to a version bump, GenAI / Optimum upgrades, or plugin-level numerical bugs unrelated to the frontend.
Adds a core operator to the OpenVINO toolkit. Use when asked to implement a new operation into OpenVINO.
Adds a new operation to OpenVINO Frontend pipelines with translator updates, registration, and tests.
Adds a new OpenVINO fusion transformation (subgraph to one or several operations) and corresponding tests.
| name | add-cpu-op |
| description | Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests. |
When the Core OpSpec agent has produced a new op spec and you need to implement CPU plugin support: node class, executor strategy, and single-layer tests.
Execute in order — each step produces artifacts consumed by the next.
| Step | File | Purpose |
|---|---|---|
| 1 | step1-analysis.md | Read op spec, determine implementation strategy (reference / JIT / oneDNN), identify ISA targets and precision requirements |
| 2 | step2-implementation.md | Create node class (header + source), register in factory, hook up shape inference |
| 3 | step3-optimization.md | Write JIT executor (AVX2/AVX-512/AMX) or oneDNN-backed path; CpuParallel integration |
| 4 | step4-testing.md | Shared single-layer tests, custom CPU tests, dynamic shapes |
