LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910270539956224 |
|---|---|
| author | Vungarala, Deepak Amin, Md Hasibul Mercati, Pietro Ghosh, Arnob Roohi, Arman Pan, David Z. Zand, Ramtin Angizi, Shaahin |
| author_facet | Vungarala, Deepak Amin, Md Hasibul Mercati, Pietro Ghosh, Arnob Roohi, Arman Pan, David Z. Zand, Ramtin Angizi, Shaahin |
| contents | Resistive crossbars enabling analog In-Memory Computing (IMC) have emerged as a promising architecture for Deep Neural Network (DNN) acceleration, offering high memory bandwidth and in-situ computation. However, the manual, knowledge-intensive design process and the lack of high-quality circuit netlists have significantly constrained design space exploration and optimization to behavioral system-level tools. In this work, we introduce LIMCA, a novel fine-tune-free Large Language Model (LLM)-driven framework for automating the design and evaluation of IMC crossbar architectures. Unlike traditional approaches, LIMCA employs a No-Human-In-Loop (NHIL) automated pipeline to generate and validate circuit netlists for SPICE simulations, eliminating manual intervention. LIMCA systematically explores the IMC design space by leveraging a structured dataset and LLM-based performance evaluation. Our experimental results on MNIST classification demonstrate that LIMCA successfully generates crossbar designs achieving $\geq$96% accuracy while maintaining a power consumption $\leq$3W, making this the first work in LLM-assisted IMC design space exploration. Compared to existing frameworks, LIMCA provides an automated, scalable, and hardware-aware solution, reducing design exploration time while ensuring user-constrained performance trade-offs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13301 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration Vungarala, Deepak Amin, Md Hasibul Mercati, Pietro Ghosh, Arnob Roohi, Arman Pan, David Z. Zand, Ramtin Angizi, Shaahin Hardware Architecture Resistive crossbars enabling analog In-Memory Computing (IMC) have emerged as a promising architecture for Deep Neural Network (DNN) acceleration, offering high memory bandwidth and in-situ computation. However, the manual, knowledge-intensive design process and the lack of high-quality circuit netlists have significantly constrained design space exploration and optimization to behavioral system-level tools. In this work, we introduce LIMCA, a novel fine-tune-free Large Language Model (LLM)-driven framework for automating the design and evaluation of IMC crossbar architectures. Unlike traditional approaches, LIMCA employs a No-Human-In-Loop (NHIL) automated pipeline to generate and validate circuit netlists for SPICE simulations, eliminating manual intervention. LIMCA systematically explores the IMC design space by leveraging a structured dataset and LLM-based performance evaluation. Our experimental results on MNIST classification demonstrate that LIMCA successfully generates crossbar designs achieving $\geq$96% accuracy while maintaining a power consumption $\leq$3W, making this the first work in LLM-assisted IMC design space exploration. Compared to existing frameworks, LIMCA provides an automated, scalable, and hardware-aware solution, reducing design exploration time while ensuring user-constrained performance trade-offs. |
| title | LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2503.13301 |