一种面向边缘计算的混合内存系统

doi:10.13190/j.jbupt.2019-091

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (2): 103-109.doi: 10.13190/j.jbupt.2019-091

一种面向边缘计算的混合内存系统

孙浩^1,2, 陈岚¹, 郝晓冉¹, 刘晨吉^1,2, 倪茂¹

1. 中国科学院微电子研究所, 北京 100029;
2. 中国科学院大学, 北京 100049

收稿日期:2019-05-28 发布日期:2020-04-28
通讯作者: 陈岚(1968-),女,研究员,博士生导师,E-mail:chenlan@ime.ac.cn. E-mail:chenlan@ime.ac.cn
作者简介:孙浩(1993-),男,博士生.
基金资助:
国家物联网与智慧城市重点专项对接（Z181100003518002）；北京市科技专项（Z171100001117147）

A Hybrid Memory System for Edge Computing

SUN Hao^1,2, CHEN Lan¹, HAO Xiao-ran¹, LIU Chen-ji^1,2, NI Mao¹

1. Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2019-05-28 Published:2020-04-28

摘要/Abstract

摘要： 针对物联网智能终端的低功耗需求，提出了一种基于内存控制器扩展的低功耗混合内存系统.使用动态随机存储器和相变存储器构成混合内存结构，通过在内存控制器中添加迁移控制模块对混合内存进行管理.设计了一种改进的双队列算法，筛选出相变存储器中写请求较多的内存页面，并通过地址映射模块和迁移控制模块将写请求较多的页面从相变存储器迁移到动态随机存储器中，规避相变存储器写操作的缺陷，从而实现对低功耗混合内存系统的性能优化.仿真结果表明，与动态随机存储器构成的内存系统相比，混合内存系统的功耗延时积平均降低了43.9%，在面向边缘计算的应用场景中具有一定的可行性.

关键词: 边缘计算, 混合内存, 内存控制器, 页面迁移

Abstract: In order to satisfy the low power requirements of IoT devices, a low power hybrid main memory system composed of dynamic random access memory and phase change memory is proposed. The hybrid main memory is managed by the hybrid memory control modules which are added to the memory controller. An improved dual queue algorithm is proposed to filter out memory pages with more write requests from phase change memory. Because of the poor write performance of phase change memory, the page migration module migrates the selected pages from phase change memory to dynamic random access memory. And then the updated page address is recorded in the address mapping table for subsequent memory access. Experimental results show that compared with the traditional main memory composed entirely of dynamic random access memory, the hybrid main memory reduces the power-delay product by 43.9% on average.

Key words: edge computing, hybrid memory, memory controller, page migration

中图分类号:

TP333.1

孙浩, 陈岚, 郝晓冉, 刘晨吉, 倪茂. 一种面向边缘计算的混合内存系统[J]. 北京邮电大学学报, 2020, 43(2): 103-109.

SUN Hao, CHEN Lan, HAO Xiao-ran, LIU Chen-ji, NI Mao. A Hybrid Memory System for Edge Computing[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(2): 103-109.

参考文献

[1] Shi Weisong, Cao Jie, Zhang Quan, et al. Edge computing:vision and challenges[J]. IEEE Internet of Things Journal, 2016, 3(5):637-646.
[2] 王力玉, 陈岚, 郝晓冉, 等. 利用SSD和DRAM构建的扩展内存架构[J]. 西安电子科技大学学报, 2017, 44(3):144-150. Wang Liyu, Chen Lan, Hao Xiaoran, et al. Memory-extended architecture based on the SSD and DRAM[J]. Journal of Xidian University, 2017, 44(3):144-150.
[3] 王强, 陈岚, 郝晓冉. 一种基于访存行为地址映射机制的混合内存系统[J]. 小型微型计算机系统, 2014, 35(6):1201-1206. Wang Qiang, Chen Lan, Hao Xiaoran. Hybrid memory system using memory access-aware remapping mechanism[J]. Journal of Chinese Computer Systems, 2014, 35(6):1201-1206.
[4] Bock S, Childers B R, Melhem R, et al. Concurrent migration of multiple pages in software-managed hybrid main memory[C]//IEEE International Conference on Computer Design. New York:IEEE Press, 2016:420-423.
[5] Ramos L E, Gorbatov E, Bianchini R. Page placement in hybrid memory systems[C]//Proceedings of the 25th International Conference on Supercomputing. New York:ACM Press, 2011:85-95.
[6] Jia Gangyong, Han Guangjie, Xie Hongtianchen, et al. Hybrid-LRU caching for optimizing data storage and retrieval in edge computing-based wearable sensors[J]. IEEE Internet of Things Journal, 2019, 6(2):1342-1351.
[7] Chen Di, Jin Hai, Liao Xiaofei, et al. MALRU:miss-penalty aware LRU-based cache replacement for hybrid memory systems[C]//Design, Automation & Test in Europe Conference & Exhibition (DATE). New York:IEEE Press, 2017:1086-1091.
[8] Guthaus M R, Ringenberg J S, Ernst D, et al. MiBench:a free, commercially representative embedded benchmark suite[C]//Proceedings of the IEEE Workshop on Workload Characterization. New York:IEEE Press, 2001:3-14.
[9] Fritts J E, Steiling F W, Tucek J A, et al. MediaBench Ⅱ video:expediting the next generation of video systems research[J]. Microprocessors & Microsystems, 2009, 33(4):301-318.
[10] Binkert N, Beckmann B, Black G, et al. The gem5 simulator[J]. Acm Sigarch Computer Architecture News, 2011, 39(2):1-7.
[11] Poremba M, Zhang T, Xie Y. NVMain 2.0:a user-friendly memory simulator to model (non-)volatile memory systems[J]. IEEE Computer Architecture Letters, 2015, 14(2):140-143.
[12] Ved S, Awasthi M. Exploring non-volatile main memory architectures for handheld devices[C]//Design, Automation & Test in Europe Conference & Exhibition (DATE). New York:IEEE Press, 2018:1528-1531.
[13] Samie F, Bauer L, Henkel J. IoT technologies for embedded computing:a survey[C]//International Conference on Hardware/Software Codesign and System Synthesis. New York:IEEE Press, 2016:1-10.
[14] Gautschi M, Schiavone P D, Traber A, et al. Near-threshold RISC-V core with DSP extensions for scalable IoT endpoint devices[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017, 25(10):2700-2713.

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	彭维平王戈宋成阎俊豪. 面向高移动性车联网场景的预测卸载决策算法[J]. 北京邮电大学学报, 2023, 46(2): 43-49.
[3]	魏明亮耿绥燕赵雄文胡玮范静怡. 超密集网络中移动边缘计算的资源分配和任务卸载联合优化研究[J]. 北京邮电大学学报, 2023, 46(2): 50-56.
[4]	李晓辉苏家楠吕思婷张鹏. 基于SMDP模型的车路协同任务智能卸载算法研究[J]. 北京邮电大学学报, 2023, 46(2): 15-21.
[5]	公雨魏翼飞. 一种集成学习辅助DDPG的资源优化算法[J]. 北京邮电大学学报, 2023, 46(2): 29-36.
[6]	付志远施丽琴叶迎晖卢光跃. 反向散射辅助的无线供能NOMA-MEC网络中公平性优化研究[J]. 北京邮电大学学报, 2023, 46(2): 71-77.
[7]	班嘉阳叶迎晖卢光跃徐瑞. 硬件损伤下NOMA-MEC网络性能分析和优化[J]. 北京邮电大学学报, 2023, 46(2): 64-70.
[8]	彭维平杨玉莹宋成阎俊豪. VEC中多边缘节点协作卸载与资源分配算法[J]. 北京邮电大学学报, 2023, 46(2): 78-83.
[9]	李松王新荣王博文孙彦景陈瑞瑞. 基于随机网络演算的车联网边缘计算性能分析[J]. 北京邮电大学学报, 2022, 45(5): 16-22.
[10]	郅佳琳, 王楠, 满毅, 滕颖蕾. 面向硬件感知的边缘计算卸载和资源分配[J]. 北京邮电大学学报, 2022, 45(2): 22-28.
[11]	杜梅, 周军华, 李敦桥, 陈士钊, 魏翼飞. MEC计算卸载与资源分配联合智能优化方案[J]. 北京邮电大学学报, 2022, 45(2): 65-71.
[12]	张雨晴, 李云, 黄鸿锐, 庄宏成. 异构网络中任务卸载与资源分配联合优化算法[J]. 北京邮电大学学报, 2022, 45(2): 91-97.
[13]	彭维平, 韩宁, 宋成. 边缘计算环境下无证书车联网身份认证方案[J]. 北京邮电大学学报, 2022, 45(1): 46-51.
[14]	郑远鹏, 张天魁, 朱光宇, 沈鸿. MEC系统中面向网络切片的3C联合资源分配算法[J]. 北京邮电大学学报, 2021, 44(5): 41-47.
[15]	陈伟, 霍如, 汪硕, 黄韬, 刘韵洁. 基于区块链的D2D辅助的MEC资源共享架构[J]. 北京邮电大学学报, 2021, 44(5): 1-9.

一种面向边缘计算的混合内存系统

A Hybrid Memory System for Edge Computing

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价