# circuitnet/circuitnet architecture

> Architecture diagram of the GitHub repository circuitnet/circuitnet, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-01-27). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/circuitnet/circuitnet
- Repository: https://github.com/circuitnet/circuitnet

## Overview

##### Main Components (Top Level)

a) Data Processing Layer
- Feature Extraction Module
- Graph Building Module
- Data Preprocessing Module

b) Machine Learning Tasks Layer
- Congestion Prediction
- DRC (Design Rule Check) Prediction
- IR Drop Prediction
- Net Delay Prediction

c) Dataset Management Layer
- CircuitNet-N28 Dataset
- CircuitNet-N14 Dataset
- Graph Features Storage

##### Component Relationships and Data Flow

**[Raw Circuit Data (LEF/DEF)]**
- ↓
**[Feature Extraction Layer]**

- ↓            ↓           ↓
**[Graph       [Circuit     [Design**
**Features]    Features]    Metrics]**

- ↓            ↓           ↓
**[ML Models Layer]**

- ↓            ↓           ↓
**[Prediction Outputs]**

##### Specific Implementation Details

a) Feature Extraction Pipeline:
- LEF/DEF processing
- Netlist analysis
- Graph feature generation

b) Model Architecture Components:
- GPDL (Congestion)
- RouteNet (DRC)
- MAVI (IR Drop)
- GNN (Net Delay)

c) Dataset Organization:
- Training/Testing splits
- N14/N28 technology nodes
- Feature types (congestion, timing, IR drop)

##### Key Technical Elements

- DGL integration for graph neural networks
- PyTorch-based model implementations
- Data augmentation pipelines
- Evaluation metrics and loss functions

##### Implementation Notes

- Use hexagons for ML models
- Version information (CircuitNet 2.0)

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph Input
        RawData[Raw Circuit Data LEF/DEF]
    end

    subgraph "Data Processing Layer"
        FE[Feature Extraction Module]:::processing
        GB[Graph Building Module]:::processing
        DP[Data Preprocessing Module]:::processing
    end

    subgraph "Dataset Management Layer"
        N14[CircuitNet-N14 Dataset]:::storage
        N28[CircuitNet-N28 Dataset]:::storage
        GF[Graph Features Storage]:::storage
    end

    subgraph "ML Models Layer"
        GPDL[GPDL Model]:::model
        RouteNet[RouteNet Model]:::model
        MAVI[MAVI Model]:::model
        GNN[Net Delay GNN]:::model
    end

    subgraph "Prediction Outputs"
        CP[Congestion Prediction]:::output
        DRC[DRC Prediction]:::output
        IR[IR Drop Prediction]:::output
        ND[Net Delay Prediction]:::output
    end

    %% Data Flow
    RawData --> FE
    RawData --> GB
    RawData --> DP

    FE --> GF
    GB --> GF
    DP --> N14
    DP --> N28

    GF --> GPDL
    GF --> RouteNet
    GF --> MAVI
    GF --> GNN

    N14 --> GPDL
    N14 --> RouteNet
    N14 --> MAVI
    N14 --> GNN

    N28 --> GPDL
    N28 --> RouteNet
    N28 --> MAVI
    N28 --> GNN

    GPDL --> CP
    RouteNet --> DRC
    MAVI --> IR
    GNN --> ND

    %% Click Events
    click FE "https://github.com/circuitnet/CircuitNet/tree/main/feature_extraction/"
    click GB "https://github.com/circuitnet/CircuitNet/tree/main/build_graph_demo/"
    click GF "https://github.com/circuitnet/CircuitNet/tree/main/build_graph_demo/graph_information/"
    click GPDL "https://github.com/circuitnet/CircuitNet/blob/main/routability_ir_drop_prediction/models/gpdl.py"
    click RouteNet "https://github.com/circuitnet/CircuitNet/blob/main/routability_ir_drop_prediction/models/routenet.py"
    click MAVI "https://github.com/circuitnet/CircuitNet/blob/main/routability_ir_drop_prediction/models/mavi.py"
    click GNN "https://github.com/circuitnet/CircuitNet/blob/main/net_delay_prediction/model.py"
    click N14 "https://github.com/circuitnet/CircuitNet/blob/main/routability_ir_drop_prediction/files/train_N14.csv"
    click N28 "https://github.com/circuitnet/CircuitNet/blob/main/routability_ir_drop_prediction/files/train_N28.csv"
    click DP "https://github.com/circuitnet/CircuitNet/tree/main/routability_ir_drop_prediction/preprocess_scripts/"

    %% Styling
    classDef processing fill:#a8d1ff,stroke:#333,stroke-width:2px
    classDef storage fill:#ffe6a8,stroke:#333,stroke-width:2px
    classDef model fill:#a8ffc9,stroke:#333,stroke-width:2px
    classDef output fill:#ffa8a8,stroke:#333,stroke-width:2px

    %% Legend
    subgraph Legend
        L1[Processing Module]:::processing
        L2[Storage Component]:::storage
        L3[ML Model]:::model
        L4[Prediction Output]:::output
    end
```
