Summary of Cross-modality Program Representation Learning For Electronic Design Automation with High-level Synthesis, by Zongyue Qin et al.
Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis
by Zongyue Qin, Yunsheng Bai, Atefeh Sohrabizadeh, Zijian Ding, Ziniu Hu, Yizhou Sun, Jason Cong
First submitted to arxiv on: 13 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 Machine learning educators can generate a medium-difficulty summary as follows: Recent advancements in domain-specific accelerators (DSAs) have sparked interest in high-level synthesis (HLS) for efficient compilation of C/C++ code into hardware description languages. However, HLS design quality relies heavily on microarchitecture decisions expressed through pragmas, requiring domain expertise. To alleviate this issue, researchers propose a machine learning-based approach that leverages both sequence and graph modalities to predict HLS design quality. Specifically, ProgSG is a model that interacts between source code sequences and control data flow graphs (CDFGs) in a deep and fine-grained manner. Experimental results demonstrate the effectiveness of ProgSG, reducing RMSE by up to 22% and identifying designs with performance improvements ranging from 1.10x to 13.31x compared to HARP and AutoDSE. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning for high school students or non-technical adults: This research paper is about finding a way to make computers better at understanding and using special computer chips called domain-specific accelerators (DSAs). Right now, it’s hard for programmers to design these chips because they need a lot of expertise. The researchers want to use machine learning to help with this problem by looking at two types of data: the code that makes up the chip and the way the chip is put together. They call this model ProgSG. When they tested ProgSG, it did really well, making predictions that were more accurate than other methods. |
Keywords
* Artificial intelligence * Machine learning
