// Add a new operation to the OpenVINO CPU plugin — node registration, JIT/oneDNN executors (AVX2/AVX-512/AMX), and functional tests.
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.
Add a new operation to the OpenVINO GPU plugin — OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests.
Analyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report.
Investigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.
| 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 |