• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

一种具有可变微架构的超低功耗嵌入式处理器。

An Ultra-Low-Power Embedded Processor with Variable Micro-Architecture.

作者信息

Ma Wenheng, Cheng Qiao, Gao Yudi, Xu Lan, Yu Ningmei

机构信息

Faculty of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710048, China.

出版信息

Micromachines (Basel). 2021 Mar 10;12(3):292. doi: 10.3390/mi12030292.

DOI:10.3390/mi12030292
PMID:33802187
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8000853/
Abstract

Embedded processors are widely used in various systems working on different tasks with different workloads. A more complex micro-architecture leads to better peak performance and worse power consumption. Shutting down the units designed for performance enhancement could improve energy efficiency in low-workload scenarios. In this paper, we evaluated the energy distribution in various embedded processors. According to the analysis, pipeline registers and the dynamic branch predictor, which are employed for better peak performance, have great impacts on energy efficiency. Thus, we proposed an ultra-low-power processor with variable micro-architecture. The processor is based on a 4-stage pipeline core with a Gshare branch predictor, and all units work in high-performance mode. In normal mode, the Gshare predictor is shut down and Always-Not-Taken prediction is used. In low-power mode, some of the pipeline registers are bypassed to avoid unnecessary energy dissipation and improve executing efficiency. A mode register (MR) is designed to indicate current working mode. Switching between different modes is controlled by the software. The proposed core is implemented in 40 nm technology and simulated with the traces of 17 benchmarks in Embench. The average amounts of power consumed by the respective modes are 41.7 μW, 59.7 μW and 71.1 μW. The results show that normal mode (N-mode) and low-power mode (L-mode) consume 16.08% and 41.37% less power than high-performance mode (H-mode) on average. In best case scenarios, they could save 25.36% and 49.30% more power than H-mode. Considering the execution efficiency evaluated by instructions per cycle (IPC), the proposed processor consumes 7.78% or 51.57% less energy for each instruction than the baseline core. The area of the proposed processor is only 7.19% larger than the baseline core, and only 3.08% more power is consumed in H-mode.

摘要

嵌入式处理器广泛应用于各种执行不同任务、具有不同工作负载的系统中。更复杂的微架构会带来更好的峰值性能,但功耗会更差。关闭为提高性能而设计的单元可以在低工作负载场景下提高能源效率。在本文中,我们评估了各种嵌入式处理器中的能量分布。根据分析,为实现更好的峰值性能而采用的流水线寄存器和动态分支预测器对能源效率有很大影响。因此,我们提出了一种具有可变微架构的超低功耗处理器。该处理器基于一个带有Gshare分支预测器的4级流水线核心,所有单元都工作在高性能模式。在正常模式下,Gshare预测器被关闭,并使用总是不采取预测。在低功耗模式下,一些流水线寄存器被旁路,以避免不必要的能量消耗并提高执行效率。设计了一个模式寄存器(MR)来指示当前的工作模式。不同模式之间的切换由软件控制。所提出的核心采用40纳米技术实现,并使用Embench中17个基准测试的跟踪进行模拟。各个模式下的平均功耗分别为41.7微瓦、59.7微瓦和71.1微瓦。结果表明,正常模式(N模式)和低功耗模式(L模式)平均比高性能模式(H模式)分别少消耗16.08%和41.37%的功率。在最佳情况下,它们比H模式可多节省25.36%和49.30%的功率。考虑到通过每周期指令数(IPC)评估的执行效率,所提出的处理器每条指令消耗的能量比基线核心少7.78%或51.57%。所提出处理器的面积仅比基线核心大7.19%,在H模式下仅多消耗3.08%的功率。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/f1aa1d46869f/micromachines-12-00292-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/e68092718e78/micromachines-12-00292-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/a1bcdae95197/micromachines-12-00292-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/76f2d74e5bcf/micromachines-12-00292-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/2bbb8f8d6095/micromachines-12-00292-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/2cfaf18cc69e/micromachines-12-00292-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/1f307b80f441/micromachines-12-00292-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/d7139c7447e3/micromachines-12-00292-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/df88b66183ab/micromachines-12-00292-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/04b080810d83/micromachines-12-00292-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/c6e4ffaf5bcc/micromachines-12-00292-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/30604fd0109f/micromachines-12-00292-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/42386323596f/micromachines-12-00292-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/65f08e501cd3/micromachines-12-00292-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/f1aa1d46869f/micromachines-12-00292-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/e68092718e78/micromachines-12-00292-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/a1bcdae95197/micromachines-12-00292-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/76f2d74e5bcf/micromachines-12-00292-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/2bbb8f8d6095/micromachines-12-00292-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/2cfaf18cc69e/micromachines-12-00292-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/1f307b80f441/micromachines-12-00292-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/d7139c7447e3/micromachines-12-00292-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/df88b66183ab/micromachines-12-00292-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/04b080810d83/micromachines-12-00292-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/c6e4ffaf5bcc/micromachines-12-00292-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/30604fd0109f/micromachines-12-00292-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/42386323596f/micromachines-12-00292-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/65f08e501cd3/micromachines-12-00292-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b69d/8000853/f1aa1d46869f/micromachines-12-00292-g014.jpg

相似文献

1
An Ultra-Low-Power Embedded Processor with Variable Micro-Architecture.一种具有可变微架构的超低功耗嵌入式处理器。
Micromachines (Basel). 2021 Mar 10;12(3):292. doi: 10.3390/mi12030292.
2
An efficient control flow validation method using redundant computing capacity of dual-processor architecture.利用双处理器架构的冗余计算能力的高效控制流验证方法。
PLoS One. 2018 Aug 1;13(8):e0201127. doi: 10.1371/journal.pone.0201127. eCollection 2018.
3
A 2.2 nW Analog Electrocardiogram Processor Based on Stochastic Resonance Achieving a 99.94% QRS Complex Detection Sensitivity.一款基于随机共振的2.2纳瓦模拟心电图处理器,实现了99.94%的QRS波群检测灵敏度。
IEEE Trans Biomed Circuits Syst. 2023 Feb;17(1):33-44. doi: 10.1109/TBCAS.2023.3235786. Epub 2023 Mar 30.
4
UArch: A Super-Resolution Processor With Heterogeneous Triple-Core Architecture for Workloads of U-Net Networks.UArch:一种具有异构三核架构的超分辨率处理器,适用于 U-Net 网络的工作负载。
IEEE Trans Biomed Circuits Syst. 2023 Jun;17(3):633-647. doi: 10.1109/TBCAS.2023.3261060. Epub 2023 Jul 12.
5
RisCO2: Implementation and Performance Evaluation of RISC-V Processors for Low-Power CO Concentration Sensing.RisCO2:用于低功耗一氧化碳浓度传感的RISC-V处理器的实现与性能评估
Micromachines (Basel). 2023 Jul 4;14(7):1371. doi: 10.3390/mi14071371.
6
A Heterogeneous RISC-V Processor for Efficient DNN Application in Smart Sensing System.一种用于智能传感系统中高效 DNN 应用的异构 RISC-V 处理器。
Sensors (Basel). 2021 Sep 28;21(19):6491. doi: 10.3390/s21196491.
7
Ultra-low-power wireless transmitter for neural prostheses with modified pulse position modulation.用于神经假体的具有改进脉冲位置调制的超低功耗无线发射器。
Healthc Technol Lett. 2014 Mar 21;1(1):37-9. doi: 10.1049/htl.2013.0012. eCollection 2014 Jan.
8
SENECA: building a fully digital neuromorphic processor, design trade-offs and challenges.塞内卡:构建全数字神经形态处理器、设计权衡与挑战。
Front Neurosci. 2023 Jun 23;17:1187252. doi: 10.3389/fnins.2023.1187252. eCollection 2023.
9
A Low-Latency Divider Design for Embedded Processors.一种用于嵌入式处理器的低延迟除法器设计。
Sensors (Basel). 2022 Mar 23;22(7):2471. doi: 10.3390/s22072471.
10
Micro Multiobjective Evolutionary Algorithm With Piecewise Strategy for Embedded-Processor-Based Industrial Optimization.
IEEE Trans Cybern. 2024 Aug;54(8):4763-4774. doi: 10.1109/TCYB.2023.3336369. Epub 2024 Jul 18.