Zichen Fan, Hyochan An, Qirui Zhang, Boxun Xu, Li Xu, Chien-Wei Tseng, Yimai Peng, Ang Cao, Bowen Liu, Changwook Lee, Zhehong Wang, Fanghao Liu, Guanru Wang, S. Jiang, Hun-Seok Kim, D. Blaauw, D. Sylvester
{"title":"Audio and Image Cross-Modal Intelligence via a 10TOPS/W 22nm SoC with Back-Propagation and Dynamic Power Gating","authors":"Zichen Fan, Hyochan An, Qirui Zhang, Boxun Xu, Li Xu, Chien-Wei Tseng, Yimai Peng, Ang Cao, Bowen Liu, Changwook Lee, Zhehong Wang, Fanghao Liu, Guanru Wang, S. Jiang, Hun-Seok Kim, D. Blaauw, D. Sylvester","doi":"10.1109/vlsitechnologyandcir46769.2022.9830226","DOIUrl":null,"url":null,"abstract":"We present an ultra-low-power multimedia signal processor (MMSP) SoC that integrates a versatile deep neural network (DNN) engine with audio and image signal processing accelerators for cross-modal IoT intelligence. The proposed MMSP features 2MB MRAM to store all DNN weights on-chip with an energy-efficient dataflow using an MRAM-cache and dynamic power gating. The SoC achieves up to 3-10 TOPS/W peak energy efficiency and consumes only 0.25-3.84 mW. Being the first to demonstrate CNN, GAN, and back-propagation (BP) on a single accelerator SoC for cross-modal fusion, it outperforms state-of-the-art DNN processors by 1.4 - 4.5× in energy efficiency.","PeriodicalId":332454,"journal":{"name":"2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/vlsitechnologyandcir46769.2022.9830226","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
We present an ultra-low-power multimedia signal processor (MMSP) SoC that integrates a versatile deep neural network (DNN) engine with audio and image signal processing accelerators for cross-modal IoT intelligence. The proposed MMSP features 2MB MRAM to store all DNN weights on-chip with an energy-efficient dataflow using an MRAM-cache and dynamic power gating. The SoC achieves up to 3-10 TOPS/W peak energy efficiency and consumes only 0.25-3.84 mW. Being the first to demonstrate CNN, GAN, and back-propagation (BP) on a single accelerator SoC for cross-modal fusion, it outperforms state-of-the-art DNN processors by 1.4 - 4.5× in energy efficiency.