Jun Ji, Zichen Xi, Bernadeta R. Srijanto, Ivan I. Kravchenko, Ming Jin, Wenjie Xiong, Linbo Shao
{"title":"利用单芯片非线性声波器件进行频域并行计算","authors":"Jun Ji, Zichen Xi, Bernadeta R. Srijanto, Ivan I. Kravchenko, Ming Jin, Wenjie Xiong, Linbo Shao","doi":"arxiv-2409.02689","DOIUrl":null,"url":null,"abstract":"Multiply-accumulation (MAC) is a crucial computing operation in signal\nprocessing, numerical simulations, and machine learning. This work presents a\nscalable, programmable, frequency-domain parallel computing leveraging\ngigahertz (GHz)-frequency acoustic-wave nonlinearities. By encoding data in the\nfrequency domain, a single nonlinear acoustic-wave device can perform a billion\narithmetic operations simultaneously. A single device with a footprint of 0.03\nmm$^2$ on lithium niobate (LN) achieves 0.0144 tera floating-point operations\nper second (TFLOPS), leading to a computing area density of 0.48 TFLOPS/mm$^2$\nand a core power efficiency of 0.14 TFLOPS/Watt. As applications, we\ndemonstrate multiplications of two 16-by-16 matrices and convolutional imaging\nprocessing of 128-by-128-pixel photos. Our technology could find versatile\napplications in near-sensor signal processing and edge computing.","PeriodicalId":501083,"journal":{"name":"arXiv - PHYS - Applied Physics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Frequency-domain Parallel Computing Using Single On-Chip Nonlinear Acoustic-wave Device\",\"authors\":\"Jun Ji, Zichen Xi, Bernadeta R. Srijanto, Ivan I. Kravchenko, Ming Jin, Wenjie Xiong, Linbo Shao\",\"doi\":\"arxiv-2409.02689\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multiply-accumulation (MAC) is a crucial computing operation in signal\\nprocessing, numerical simulations, and machine learning. This work presents a\\nscalable, programmable, frequency-domain parallel computing leveraging\\ngigahertz (GHz)-frequency acoustic-wave nonlinearities. By encoding data in the\\nfrequency domain, a single nonlinear acoustic-wave device can perform a billion\\narithmetic operations simultaneously. A single device with a footprint of 0.03\\nmm$^2$ on lithium niobate (LN) achieves 0.0144 tera floating-point operations\\nper second (TFLOPS), leading to a computing area density of 0.48 TFLOPS/mm$^2$\\nand a core power efficiency of 0.14 TFLOPS/Watt. As applications, we\\ndemonstrate multiplications of two 16-by-16 matrices and convolutional imaging\\nprocessing of 128-by-128-pixel photos. Our technology could find versatile\\napplications in near-sensor signal processing and edge computing.\",\"PeriodicalId\":501083,\"journal\":{\"name\":\"arXiv - PHYS - Applied Physics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Applied Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.02689\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Applied Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.02689","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Frequency-domain Parallel Computing Using Single On-Chip Nonlinear Acoustic-wave Device
Multiply-accumulation (MAC) is a crucial computing operation in signal
processing, numerical simulations, and machine learning. This work presents a
scalable, programmable, frequency-domain parallel computing leveraging
gigahertz (GHz)-frequency acoustic-wave nonlinearities. By encoding data in the
frequency domain, a single nonlinear acoustic-wave device can perform a billion
arithmetic operations simultaneously. A single device with a footprint of 0.03
mm$^2$ on lithium niobate (LN) achieves 0.0144 tera floating-point operations
per second (TFLOPS), leading to a computing area density of 0.48 TFLOPS/mm$^2$
and a core power efficiency of 0.14 TFLOPS/Watt. As applications, we
demonstrate multiplications of two 16-by-16 matrices and convolutional imaging
processing of 128-by-128-pixel photos. Our technology could find versatile
applications in near-sensor signal processing and edge computing.