Hyperscale HW Optimized Neural Architecture Search (Google)

Hyperscale HW Optimized Neural Architecture Search (Google)

Source Node: 2600411

A new technical paper titled “Hyperscale Hardware Optimized Neural Architecture Search” was published by researchers at Google, Apple, and Waymo.

“This paper introduces the first Hyperscale Hardware Optimized Neural Architecture Search (H2O-NAS) to automatically design accurate and performant machine learning models tailored to the underlying hardware architecture. H2O-NAS consists of three key components: a new massively parallel “one-shot” search algorithm with intelligent weight sharing, which can scale to search spaces of O(10280) and handle large volumes of production traffic; hardware-optimized search spaces for diverse ML models on heterogeneous hardware; and a novel two-phase hybrid performance model and a multi-objective reward function optimized for large scale deployments,” states the paper.

Find the technical paper here. Published March 2023.

Sheng Li, Garrett Andersen, Tao Chen, Liqun Cheng, Julian Grady, Da Huang, Quoc V. Le, Andrew Li, Xin Li, Yang Li, Chen Liang, Yifeng Lu, Yun Ni, Ruoming Pang, Mingxing Tan, Martin Wicke, Gang Wu, Shengqi Zhu, Parthasarathy Ranganathan, and Norman P. Jouppi. 2023. Hyperscale Hardware Optimized Neural Architecture Search. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 (ASPLOS 2023). Association for Computing Machinery, New York, NY, USA, 343–358. https://doi.org/10.1145/3582016.3582049


Time Stamp:

More from Semi Engineering