Ref Model

Prerequisites

• docs/phase-1-research/iron-requirements.json present with REQ-F-* items.
• JM 19.0 (H.264) or HM 16.20 (H.265) installed and on PATH.

If missing: WARNING — proceed with available artifacts; feature coverage step will note absent requirements file.

Apply steps 1-9 to every algorithm unit requested — do not stop after the first.

Task(subagent_type="rtl-agent-team:ref-model-dev", prompt="Implement C functional reference model at refc/. Must be bitexact vs JM. " "No clock/reset — pure functional. I/O as function args. Internal memory as arrays/struct. " "External memory via ext_mem_read/write. PARALLEL_LANES parameterizable. " "C11, DPI-C compatible (no C++ features). Use templates/ scaffolding.")

Task(subagent_type="rtl-agent-team:ref-model-reviewer", prompt="Review refc/ model quality. Check algorithm fidelity, fixed-point/bit-width correctness, " "build warnings, UB risks, and I/O format compatibility. " "Save report to reviews/phase-2-architecture/ref-model-review.md with PASS/FAIL verdict.")

</Tool_Usage>

<Examples>
<example index="1">
<scenario>New CABAC entropy coder; Phase 1 complete; JM 19.0 available.</scenario>
<expected_output>refc/cabac_encoder.c compiled clean; 500 ITU-T vectors pass bitexact vs JM 19.0; bandwidth_report.json shows 2.3 MB/frame reads; all REQ-F-* mapped; ref-model-reviewer issues PASS.</expected_output>
</example>

<example index="2">
<scenario>Spec change adds intra 8×8 prediction; existing ref model misses REQ-F-042.</scenario>
<expected_output>ref-model-dev adds intra_predict_8x8(); feature-coverage.md updated; re-run confirms bitexact match; conformance_report.json refreshed.</expected_output>
</example>

<example index="3">
<scenario>Datapath width exploration: choose between PARALLEL_LANES=4 and PARALLEL_LANES=8.</scenario>
<expected_output>bandwidth_report.json generated for both configs; estimated_read_cycles compared; architect selects PARALLEL_LANES=4 based on memory bandwidth budget.</expected_output>
</example>
</Examples>

<Escalation_And_Stop_Conditions>
- Bitexact mismatch persists after 3 fix iterations → report failing vectors with diff to user.
- JM/HM not available → halt; instruct user to install before proceeding.
- Feature coverage < 100% and user declines to implement missing feature → record ADR with impact estimate; proceed only with explicit approval.
- External memory bandwidth exceeds technology limits → escalate to arch-designer for block restructuring.
</Escalation_And_Stop_Conditions>

## Output

- `refc/*.c`, `refc/include/*.h` — C11 functional reference model.
- `conformance_report.json` — per-vector bitexact results with JM/HM version.
- `bandwidth_report.json` — external memory access statistics per block.
- `reviews/phase-2-architecture/ref-model-feature-coverage.md` — REQ-F-* mapping table.
- `reviews/phase-2-architecture/ref-model-review.md` — reviewer verdict.

<Final_Checklist>
- [ ] `refc/*.c` compiles with `gcc -std=c11 -Wall -Wextra -Werror`.
- [ ] No C++ features — DPI-C compatible pure C.
- [ ] No clock/reset — pure functional model.
- [ ] External memory uses `ext_mem_read`/`ext_mem_write` abstraction.
- [ ] `PARALLEL_LANES` parameterizable.
- [ ] All test vectors pass bitexact comparison vs JM/HM.
- [ ] `make sanitize` passes clean (`-fsanitize=address,undefined`).
- [ ] All `REQ-F-*` items mapped to code paths; `ref-model-feature-coverage.md` saved.
- [ ] Missing features escalated; user-approved omissions have ADR.
- [ ] `ref-model-reviewer` report saved with PASS verdict.
- [ ] `conformance_report.json` and `bandwidth_report.json` written.
</Final_Checklist>