Performance and Thermal Tradeoffs for Energy-Efficient Monolithic 3D Network-on-Chip

Author:

Lee Dongjin1,Das Sourav1,Doppa Janardhan Rao1,Pande Partha Pratim1,Chakrabarty Krishnendu2

Affiliation:

1. Washington State University, Pullman, Washington

2. Duke University, Hudson Hall, Durham, NC

Abstract

Three-dimensional (3D) integration enables the design of high-performance and energy-efficient network on chip (NoC) architectures as communication backbones for manycore chips. To exploit the benefits of the vertical dimension of 3D integration, through-silicon-via (TSV) has been predominantly used in state-of-the-art manycore chip design. However, for TSV-based systems, high power density and the resultant thermal hotspot remain major concerns from the perspectives of chip functionality and overall reliability. The power consumption and thermal profiles of 3D NoCs can be improved by incorporating a Voltage-Frequency-Island (VFI)-based power management strategy. However, due to inherent thermal constraints of a TSV-based 3D system, we are unable to fully exploit the benefits offered by the power management methodology. In this context, emergence of monolithic 3D (M3D) integration has opened up new possibility of designing ultra-low-power and high-performance circuits and systems. The smaller dimensions of the inter-layer dielectric (ILD) and monolithic inter-tier vias (MIVs) offer high-density integration, flexibility of partitioning logic blocks across multiple tiers, and significant reduction of total wire-length. In this work, we present the first-ever study of the performance-thermal tradeoffs for energy efficient monolithic 3D manycore chips. In particular, we present a comparative performance evaluation of M3D NoCs with respect to their conventional TSV-based counterparts. We demonstrate that the proposed M3D-based NoC architecture incorporating VFI-based power management achieves a maximum of 29.4% lower energy-delay-product (EDP) compared to the TSV-based designs for a large set of benchmarks. We also demonstrate that the M3D-based NoC shows up to 29.1% lower maximum temperature than the TSV-based counterpart for these benchmarks.

Funder

Army Research Office

National Science Foundation

Publisher

Association for Computing Machinery (ACM)

Subject

Electrical and Electronic Engineering,Computer Graphics and Computer-Aided Design,Computer Science Applications

Reference62 articles.

1. 3-D Sequential Integration: A Key Enabling Technology for Heterogeneous Co-Integration of New Function With CMOS

2. C. Bienia. 2011. Benchmarking Modern Multiprocessors. Ph.D. Diss. Princeton Univ. Princeton NJ. C. Bienia. 2011. Benchmarking Modern Multiprocessors. Ph.D. Diss. Princeton Univ. Princeton NJ.

3. The gem5 simulator

Cited by 22 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. NeuroTAP: Thermal and Memory Access Pattern-Aware Data Mapping on 3D DRAM for Maximizing DNN Performance;ACM Transactions on Embedded Computing Systems;2024-09-11

2. 3D-TemPo: Optimizing 3-D DRAM Performance Under Temperature and Power Constraints;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2024-08

3. A survey on mapping and scheduling techniques for 3D Network-on-chip;Journal of Systems Architecture;2024-02

4. NeuroCool: Dynamic Thermal Management of 3D DRAM for Deep Neural Networks through Customized Prefetching;ACM Transactions on Design Automation of Electronic Systems;2023-12-18

5. Dynamic Thermal Management of 3D Memory through Rotating Low Power States and Partial Channel Closure;ACM Transactions on Embedded Computing Systems;2023-11-09

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3