Abstract
As program workloads (e.g., AI) increase in size and algorithmic complexity, the primary challenge lies in their high dimensionality, encompassing computing cores, array sizes, and memory hierarchies. To overcome these obstacles, innovative approaches are required. Agile chip design has already benefited from machine learning integration at various stages, including logic synthesis, placement, and routing. With Large Language Models (LLMs) recently demonstrating impressive proficiency in Hardware Description Language (HDL) generation, it is promising to extend their abilities to 2.5D integration, an advanced technique that saves area overhead and development costs. However, LLM-driven chiplet design faces challenges such as flatten design, high validation cost and imprecise parameter optimization, which limit its chiplet design capability. To address this, we propose MAHL, a hierarchical LLM-based chiplet design generation framework that features six agents which collaboratively enable AI algorithm-hardware mapping, including hierarchical description generation, retrieval-augmented code generation, diverseflow-based validation, and multi-granularity design space exploration. These components together enhance the efficient generation of chiplet design with optimized Power, Performance and Area (PPA). Experiments show that MAHL not only significantly improves the generation accuracy of simple RTL design, but also increases the generation accuracy of real-world chiplet design, evaluated by Pass@5, from 0 to 0.72 compared to conventional LLMs under the best-case scenario. Compared to state-of-the-art CLARIE (expert-based), MAHL achieves comparable or even superior PPA results under certain optimization objectives.
| Original language | English (US) |
|---|---|
| Title of host publication | 2025 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2025 - Conference Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798331515607 |
| DOIs | |
| State | Published - 2025 |
| Event | 44th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2025 - Munich, Germany Duration: Oct 26 2025 → Oct 30 2025 |
Publication series
| Name | IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD |
|---|---|
| ISSN (Print) | 1092-3152 |
Conference
| Conference | 44th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2025 |
|---|---|
| Country/Territory | Germany |
| City | Munich |
| Period | 10/26/25 → 10/30/25 |
Bibliographical note
Publisher Copyright:© 2025 IEEE.
Keywords
- AI workloads
- Chiplet
- Compiler
- Design Space Exploration
- Hierarchy
- LLM
- Multi-agent
Fingerprint
Dive into the research topics of 'MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS