Summary of Agentic-hls: An Agentic Reasoning Based High-level Synthesis System Using Large Language Models (ai For Eda Workshop 2024), by Ali Emre Oztas et al.
Agentic-HLS: An agentic reasoning based high-level synthesis system using large language models (AI for EDA workshop 2024)
by Ali Emre Oztas, Mahdi Jelodari
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Hardware Architecture (cs.AR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents an approach to predicting various metrics related to chip design using Chain-of-thought techniques and large language models (LLMs). Specifically, the authors aim to predict validity, running latency, BRAM utilization, LUT utilization, FF utilization, and DSP utilization. To achieve this, they employ LLMs for classification and regression tasks. The results suggest that larger models improve reasoning capabilities. The authors release their prompts and propose a benchmarking task for LLMs in the context of high-level synthesis (HLS). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about using special computer programs to predict how well certain chip designs will work. It’s like trying to guess how fast or efficient a particular design will be. They use big language models, which are like super smart computers that can understand and generate human-like text. These models help them make predictions and improve their performance by getting better at “reasoning” – in other words, making smarter decisions. |
Keywords
» Artificial intelligence » Classification » Regression
