中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Improving Utilization of Dataflow Unit for Multi-Batch Processing

文献类型：期刊论文

作者Fan, Zhihua2; Li, Wenming; Wang, Zhen; Yang, Yu; Ye, Xiaochun; Fan, Dongrui; Sun, Ninghui; An, Xuejun
刊名ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION
出版日期2024-03-01
卷号21期号:1页码:26
关键词Utilization network-on-chip decoupled architecture batch processing
ISSN号1544-3566
DOI10.1145/3637906
英文摘要Dataflow architectures can achieve much better performance and higher efficiency than general-purpose core, approaching the performance of a specialized design while retaining programmability. However, advanced application scenarios place higher demands on the hardware in terms of cross-domain and multi-batch processing. In this article, we propose a unified scale-vector architecture that can work in multiple modes and adapt to diverse algorithms and requirements efficiently. First, a novel reconfigurable interconnection structure is proposed, which can organize execution units into different cluster typologies as a way to accommodate different data-level parallelism. Second, we decouple threads within each DFG node into consecutive pipeline stages and provide architectural support. By time-multiplexing during these stages, dataflow hardware can achieve much higher utilization and performance. In addition, the task-based program model can also exploit multi-level parallelism and deploy applications efficiently. Evaluated in a wide range of benchmarks, including digital signal processing algorithms, CNNs, and scientific computing algorithms, our design attains up to 11.95x energy efficiency (performance-per-watt) improvement over GPU (V100), and 2.01x energy efficiency improvement over state-of-the-art dataflow architectures.
资助项目National Key R&D Program of China[2022YFB4501404] ; Beijing Nova Program[20230484420] ; Beijing Nova Program[20220484054] ; CAS Project for Young Scientists in Basic Research[YSBR-029] ; CAS Project for Youth Innovation Promotion Association ; Open Research Projects of Zhejiang Lab[2022PB0AB01]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001193465400017
出版者ASSOC COMPUTING MACHINERY
源URL[http://119.78.100.204/handle/2XEOYT63/38772]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Fan, Zhihua
作者单位1.Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, 6 South Sci Acad Rd, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
4.Chinese Acad Sci, State Key Lab Processors Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Fan, Zhihua,Li, Wenming,Wang, Zhen,et al. Improving Utilization of Dataflow Unit for Multi-Batch Processing[J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,2024,21(1):26.
APA Fan, Zhihua.,Li, Wenming.,Wang, Zhen.,Yang, Yu.,Ye, Xiaochun.,...&An, Xuejun.(2024).Improving Utilization of Dataflow Unit for Multi-Batch Processing.ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,21(1),26.
MLA Fan, Zhihua,et al."Improving Utilization of Dataflow Unit for Multi-Batch Processing".ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 21.1(2024):26.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。