Post-synthesis Area Prediction on RTL Design Dataset (test)
0.3649MAEStructRTL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| StructRTLKnowledge Distillation=w/o KD, Category=Ours2025.08 | 0.3649 | 6 | 0.7463 | 0.5037 | |
| StructRTL (w/o Lmnm)Knowledge Distillation=w/o KD, Category=Ours, Ablation=without structural graph alignment loss2025.08 | 0.39 | 7 | 0.7249 | 0.5245 | |
| StructRTL (w/o Lep)Knowledge Distillation=w/o KD, Category=Ours, Ablation=without positional embedding loss2025.08 | 0.4035 | 7 | 0.7018 | 0.546 | |
| Graph-GNNKnowledge Distillation=w/o KD, Category=Graph-Based Baselines2025.08 | 0.5497 | 9 | 0.5857 | 0.6437 | |
| CodeV-QW-7BKnowledge Distillation=w/o KD, Category=LLM-Based Baselines, Backbone=CodeQwen2025.08 | 0.7229 | 13 | 0.6353 | 0.6039 | |
| CodeV-CL-7BKnowledge Distillation=w/o KD, Category=LLM-Based Baselines, Backbone=CodeLlama2025.08 | 0.7982 | 15 | 0.5755 | 0.6515 | |
| CodeV-DS-6.7BKnowledge Distillation=w/o KD, Category=LLM-Based Baselines, Backbone=DeepSeek-Coder2025.08 | 0.8967 | 17 | 0.4862 | 0.6973 | |
| Graph-XGBoostKnowledge Distillation=w/o KD, Category=Graph-Based Baselines2025.08 | 0.9267 | 19 | 0.3987 | 0.7754 |