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
An Energy-Efficient In-Memory Accelerator for Graph Construction and Updating

文献类型：期刊论文

作者Chen, Mingkai; Liu, Cheng; Liang, Shengwen; He, Lei; Wang, Ying; Zhang, Lei; Li, Huawei; Li, Xiaowei
刊名IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
出版日期2024-06-01
卷号43期号:6页码:1781-1793
关键词Memory management Buildings Bandwidth Hardware Social networking (online) Energy efficiency Parallel processing Graph construction graph updating near-data processing nearest neighbors power gating stacked memory
ISSN号0278-0070
DOI10.1109/TCAD.2024.3355038
英文摘要Graph is widely utilized as a key data structure in many applications, such as social network and recommendation systems. However, many real-world graphs are constructed with large-scale correlated data, which typically involves massive random memory accesses and distance calculation resulting in considerable processing time and energy consumption on CPUs and GPUs. In this work, we present GCiM, a specialized processing-in-memory architecture for efficient graph construction and updating. By directly deploying the computing units on the logic layer of the 3-D stacked memory, GCiM benefits from memory-level parallelism and further improves the memory access efficiency with both optimized processing ordering and data layout. In addition, we notice that the computing engines for graph updating suffer from dramatic utilization imbalance and integrate a power gating module to cut down the power supply of the idle computing engines at runtime and further enhance the energy efficiency. According to our experiments, GCiM shows 634.64x and 56.27x speedup while consuming 1194.14x and 505.07x less energy compared to CPU and GPU, respectively.
资助项目National Natural Science Foundation of China (NSFC)
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001230178400021
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/40030]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Liu, Cheng
作者单位Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Mingkai,Liu, Cheng,Liang, Shengwen,et al. An Energy-Efficient In-Memory Accelerator for Graph Construction and Updating[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2024,43(6):1781-1793.
APA Chen, Mingkai.,Liu, Cheng.,Liang, Shengwen.,He, Lei.,Wang, Ying.,...&Li, Xiaowei.(2024).An Energy-Efficient In-Memory Accelerator for Graph Construction and Updating.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,43(6),1781-1793.
MLA Chen, Mingkai,et al."An Energy-Efficient In-Memory Accelerator for Graph Construction and Updating".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 43.6(2024):1781-1793.

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。