DAVE: Deriving Automatically Verilog from English

Pearce, Hammond; Tan, Benjamin; Karri, Ramesh

doi:10.1145/3380446.3430634

Cited by 25 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[27][28][29] To the best of our knowledge, only two previous works have used ML to generate HDL code. Pearce et al 30 started from the GPT-2 transformer model 31 that was pre-trained on natural language (NL) data and fine-tuned on a synthetic dataset of pairs of English descriptions with Verilog code snippets. Thakur et al 32 benchmarked recent transformer models pre-trained on general PL code for solving Verilog programming challenges.…”

Section: Related Workmentioning

confidence: 99%

A machine learning approach towards SKILL code autocompletion

Dehaerne,

Dey,

Meert

et al. 2024

DTCO and Computational Patterning III

View full text Add to dashboard Cite

As Moore's Law continues to increase the complexity of electronic systems, Electronic Design Automation (EDA) must advance to meet global demand. An important example of an EDA technology is SKILL, a scripting language used to customize and extend EDA software. Recently, code generation models using the transformer architecture have achieved impressive results in academic settings and have even been used in commercial developer tools to improve developer productivity. To the best of our knowledge, this study is the first to apply transformers to SKILL code autocompletion towards improving the productivity of hardware design engineers. In this study, a novel, data-efficient methodology for generating SKILL code is proposed and experimentally validated. More specifically, we propose a novel methodology for (i) creating a high-quality SKILL dataset with both unlabeled and labeled data, (ii) a training strategy where T5 models pre-trained on general programming language code are fine-tuned on our custom SKILL dataset using self-supervised and supervised learning, and (iii) evaluating synthesized SKILL code. We show that models trained using the proposed methodology outperform baselines in terms of human-judgment score and BLEU score. A major challenge faced was the extremely small amount of available SKILL code data that can be used to train a transformer model to generate SKILL code. Despite our validated improvements, the extremely small dataset available to us was still not enough to train a model that can reliably autocomplete SKILL code. We discuss this and other limitations as well as future work that could address these limitations.

show abstract

Section: Related Workmentioning

confidence: 99%

A machine learning approach towards SKILL code autocompletion

Dehaerne,

Dey,

Meert

et al. 2024

DTCO and Computational Patterning III

View full text Add to dashboard Cite

show abstract

“…The automated generation of hardware circuits using an LLM began by Pearce et al [13]. They utilized a GPT-2 model and demonstrated that LLMs can generate syntactically correct Verilog code, although there was still room for improvement.…”

Section: A Llms On Hardware Description Language (Hdl)mentioning

confidence: 99%

LADAC: Large Language Model-driven Auto-Designer for Analog Circuits

Liu,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The assignments include intermediate guided exercises, figures, examples, tables, online quizzes, problem sets, and basic hands-on tasks to learn Verilog inside the cloud platform provided by Colab. We also include a Colab proposed by [13] that uses machine learning to translate English to Verilog code, to highlight the possibilities for encouraging the students that go beyond by using several powerful Colab features. We also recommend the open-source CloudV framework [14], DigitalJS [15], and RiscVerilog [16] which provide browserbased interfaces for teaching Verilog and EDA software tools.…”

Section: Logic Design and Verilogmentioning

confidence: 99%

Google Colab CAD4U: Hands-On Cloud Laboratories for Digital Design

Canesche

Bragança

Neto

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Google Colab is a cloud Jupyter notebook widespread used to teach machine learning by writing text explanations and Python codes through the browser. This work introduces new Colab extensions to teach logic circuit design, Verilog language, processor, and GPU architectures. Colab allows us to share reproducible experiments on the Web. The students become motivated to do laboratory assignments without download/configure software packages and dependencies on their computers. Furthermore, almost all universities had to shut down due to the COVID-19 pandemic, forcing us to adapt to virtual learning scenarios. Colab provides portability and accessibility since it can even run on smartphones. The lab assignments include intermediate guided exercises, text explanations, figures, online quizzes, problem sets, and basic hands-on tasks. We develop a simple setup for Icarus Verilog, PyEDA, CUDA, Valgrind, and Gem5 frameworks. This work presents Verilog teaching and computer architecture simulation insights by using Valgrind and Gem5, and GPU computer architecture profiling at the thread and instruction assembly level.

show abstract

DAVE: Deriving Automatically Verilog from English

Cited by 25 publications

References 18 publications

A machine learning approach towards SKILL code autocompletion

A machine learning approach towards SKILL code autocompletion

LADAC: Large Language Model-driven Auto-Designer for Analog Circuits

Google Colab CAD4U: Hands-On Cloud Laboratories for Digital Design

Contact Info

Product

Resources

About