Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912381887578112 |
|---|---|
| author | Dupuis, Nicolas Nair, Ravi Ramji, Shyam McClintock, Sean Chauhan, Nishant Nagpal, Priyanka Blaner, Bart Valk, Ken Stok, Leon Puri, Ruchir |
| author_facet | Dupuis, Nicolas Nair, Ravi Ramji, Shyam McClintock, Sean Chauhan, Nishant Nagpal, Priyanka Blaner, Bart Valk, Ken Stok, Leon Puri, Ruchir |
| contents | The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09610 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors Dupuis, Nicolas Nair, Ravi Ramji, Shyam McClintock, Sean Chauhan, Nishant Nagpal, Priyanka Blaner, Bart Valk, Ken Stok, Leon Puri, Ruchir Hardware Architecture Artificial Intelligence Computation and Language Software Engineering The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world. |
| title | Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors |
| topic | Hardware Architecture Artificial Intelligence Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2505.09610 |