A graph placement methodology for fast chip design

By Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, J. Jiang, Ebrahim M. Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Omkar Pathak, Azade Nazi and 10 more. Nature, 2021

775 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/07aa07cb6791f336cb32643d54201eab295b2757

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Hardware and Architecture

Citations in the corpus

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, background): “In particular, the chip design procedure for edge AI hardware can be signiﬁcantly accelerated by the recent proposal of deep RL assisted fast chip ﬂoorplanning [298].”
The alignment problem from a deep learning perspective (2022, methodology): “…addition to standard drivers of progress, AI developers are increasingly using ML systems for accelerating programming [OpenAI, 2023a], and developing new architectures [Elsken et al., 2019], algorithms [Fawzi et al., 2022], training data [Huang et al., 2022a], and chips [Mirhoseini et al., 2021].”
Dense reinforcement learning for safety validation of autonomous vehicles (2023, neutral): “21 ) .”
Solving math word problems with process- and outcome-based feedback (2022, neutral): “For example, outcome-based feedback based on power-consumption, chip area, and other metrics can be used to optimize computer chip layouts (Mirhoseini et al., 2021), while a process-based approach would require detailed expert knowledge on designing chip layouts.”
Open-Ended Learning Leads to Generally Capable Agents (2021, background): “Over recent years, deep reinforcement learning (deep RL) has repeatedly yielded highly performant artificial agents across a range of training domains (Mirhoseini et al., 2021; OpenAI et al., 2019; Silver et al., 2017).”
Managing extreme AI risks amid rapid progress (2023, methodology): “Progress in AI also enables faster AI progress 8 : AI assistants are increasingly used to automate programming 9 , data collection 10,11 , and chip design 12 .”
Everything is Connected: Graph Neural Networks (2023, background): “…serve estimated travel times in Google Maps (Derrow-Pinion et al., 2021), power content recommendations in Pinterest (Ying et al., 2018) and product recommendations in Amazon (Hao et al., 2020), and design the latest generation of machine learning hardware: the TPUv5 (Mirhoseini et al., 2021).”