> For the complete documentation index, see [llms.txt](https://zeju.gitbook.io/lcm-team/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://zeju.gitbook.io/lcm-team/deepcircuitx/rtl-code-annotations-by-gpt.md).

# RTL code annotations by GPT

To construct the RTL-language dataset, we organize the data into four distinct levels: repository, file, module, and block. The detailed example shown in the figure.

&#x20;We employ a Chain of Thought (CoT) approach for RTL code annotation, leveraging GPT-4 and Claude to generate detailed comments, descriptions, and question-answer pairs.&#x20;

<table><thead><tr><th width="172">RTL Category</th><th width="135">Module-Level Annotations</th><th width="207">Block-Level Annotations</th><th>Repository-Level Annotations</th></tr></thead><tbody><tr><td><strong>Chip</strong></td><td>5,471</td><td>36,955</td><td>84</td></tr><tr><td><strong>IP</strong></td><td>12,863</td><td>20,101</td><td>183</td></tr><tr><td><strong>Module</strong></td><td>28,901</td><td>-</td><td>1,389</td></tr><tr><td><strong>RISC-V</strong></td><td>2,116</td><td>-</td><td>560</td></tr></tbody></table>

The table illustrates the number of annotations at the module, block, and repository levels for various RTL categories.

*<mark style="color:red;">**The annotation download url:**</mark>*&#x20;

{% embed url="<https://drive.google.com/file/d/14tntC-N-kCGbYkTGD3mZe6H18Mf449PV/view?usp=sharing>" %}
All the RTL code and corresponding different level annotations&#x20;
{% endembed %}

<sup>*<mark style="color:$info;">**if you get some problems when using this link, such as 'cannot unzip' , 'cannot download' and 'the link is not valid', you can try this new link:**</mark>*</sup>  [<sup>*<mark style="color:$primary;">**https://huggingface.co/datasets/zeju-0727/DeepCirCuitX\_Dataset**</mark>*</sup>](https://huggingface.co/datasets/zeju-0727/DeepCirCuitX_Dataset)

*<mark style="color:red;">**The annotation test case download url:**</mark>*&#x20;

{% embed url="<https://drive.google.com/file/d/1eBEwESWOCGFDfqgKqDouChRGvqrrsy24/view?usp=sharing>" %}
One complete case of our annotation data （with RTL code）
{% endembed %}

*<mark style="color:red;">**One case of our data structure：**</mark>*

chip/Communications\_Processor/Design-of-reduced-latency-and-increased-throughput-Polar-Decoder

```
design_files
├── design_files/pe_1         //pe_1 in original code is a Verilog file
│   ├── design_files/pe_1/intermediate_comment
│   │   ├── design_files/pe_1/intermediate_comment/pe_1_QA.json
│   │   ├── design_files/pe_1/intermediate_comment/pe_1_module.json
│   │   └── design_files/pe_1/intermediate_comment/pe_1_spec.json
│   ├── design_files/pe_1/pe_1.txt  // Module-level comment
│   └── design_files/pe_1/spec
│       └── design_files/pe_1/spec/spec.txt   // file-level specification annotation
│   └── design_files/pe_1/pe_1.v  // file-level code
├── design_files/pe_2   ...
├── design_files/t_to_s_or_s_to_t   ...
├── design_files/sign_processing_unit   ...
├── design_files/half_adder_subtractor   ...
├── design_files/pe_1_modified_merge   ...
├── design_files/comparator_module   ...
├── design_files/full_adder_subtractor   ...
├── design_files/merged_pe_2   ...
TestBench_Files ...

Design-of-reduced-latency-and-increased-throughput-Polar-Decoder.txt  // Repo-level comment
```

**The structure for the annotated Verilog code in the 'Design-of-reduced-latency-and-increased-throughput-Polar-Decoder' project.**&#x20;

**The `design_files` folder contains individual Verilog files, with `pe_1` serving as an example. Each module's source code (e.g., `pe_1.v`) is accompanied by various annotation files, such as intermediate comments, specifications, and a textual description (`pe_1.txt`).**&#x20;

**These annotations are organized into subdirectories like `intermediate_comment` and `spec`. This structure enables detailed documentation and analysis of the Verilog code for various modules across the project.**

<figure><img src="/files/lACg22SZWR2j1aiLjDKE" alt=""><figcaption><p>Illustration of the dataset repository structure with multi-level annotations</p></figcaption></figure>
