skip to main content
10.1145/3526241.3530380acmconferencesArticle/Chapter ViewAbstractPublication PagesglsvlsiConference Proceedingsconference-collections
short-paper

MOCCA: A Process Variation Tolerant Systolic DNN Accelerator using CNFETs in Monolithic 3D

Published: 06 June 2022 Publication History

Abstract

Hardware accelerators based on systolic arrays have become the dominant method for efficient processing of deep neural networks (DNNs). Although such designs provide significant performance improvement compared to its contemporary CPUs or GPUs, their power efficiency and area efficiency are greatly limited by the large computing array and on-chip memory. In this work, we demonstrate that we can further improve the efficiency of systolic accelerators using emerging carbon nanotube field-effect transistors (CNFETs) by stacking the computing logic and on-chip memory on multiple layers and utilizing monolithic 3D (M3D) vias for low-latency communication. We comprehensively explore the design space and present MOCCA, the first process variation tolerable CNFET-based systolic DNN accelerator. We validate MOCCA against previous 2D accelerators on state-of-the-arts DNN models. On average, MOCCA achieves the same throughput with 6.12× and 2.12× improvement respectively on performance and power efficiency in a 2× reduced chip footprint.

Supplementary Material

MP4 File (GLSVLSI22-117.mp4)
MOCCA is the first process variation tolerable CNFET-based systolic DNN accelerator. It can further improve the efficiency of systolic accelerators using emerging carbon nanotube field-effect transistors (CNFETs) by stacking the computing logic and on-chip memory on multiple layers and utilizing monolithic 3D (M3D) vias for low-latency communication.

References

[1]
N. P. Jouppi et al., "In-Datacenter Performance Analysis of a Tensor Processing Unit," in ISCA, 2017.
[2]
D. Woods, "Photonic Neural Networks," in Nature Physics, 2012.
[3]
J. Deng et al., "A compact SPICE Model for Carbon-Nanotube Field-Effect Transistors Including Nonidealities and Its Application-Part II: Full Device Model and Circuit Performance Benchmarking," IEEE T-ED, 2007.
[4]
A. D. Franklin et al., "Sub-10 nm Carbon Nanotube Transistor," Nano letters, 2012.
[5]
C. Yu et al., "Thermal Conductance and Thermopower of an Individual Single- Wall Carbon Nanotube," Nano Letters, 2005.
[6]
M. M. Shulaker et al., "Monolithic 3D Integration of Logic and Memory: Carbon Nanotube FETs, Resistive RAM, and Silicon FETs," in IEDM, 2014.
[7]
S. Banerjee et al., "Analysis of the Impact of Process Variations and Manufacturing Defects on the Performance of Carbon-Nanotube FETs," IEEE TVLSIS, 2020.
[8]
J. Zhang et al., "Carbon Nanotube Circuits in the Presence of Carbon Nanotube Density Variations," in DAC, 2009.
[9]
J. Zhang et al., "Probabilistic Analysis and Design of Metallic-Carbon-Nanotube- Tolerant Digital Logic Circuits," TCAD, 2009.
[10]
G. Zhang et al., "Selective Etching of Metallic Carbon Nanotubes by Gas-Phase Reaction," Science, 2006.
[11]
M. M. S. Aly et al., "The N3XT Approach to Energy-Efficient Abundant-Data Computing," in Proceedings of the IEEE, 2018.
[12]
F. Chen et al., "Marvel: A Vertical Resistive Accelerator for Low-Power Deep Learning Inference in Monolithic 3D," in DATE, 2021.
[13]
S. Sarangi et al., "VARIUS: A Model of Process Variation and Resulting Timing Errors for Microarchitects," in IEEE Trans. Semicond. Manuf., 2008.
[14]
J. Zhang et al., "Design Guidelines for Metallic-Carbon-Nanotube-Tolerant Digital Logic Circuits," in DAC, 2008.
[15]
G. Hills, "Variation-Aware Nanosystem Design Kit (NDK)," 2015.
[16]
C. . Lee et al., "A Compact Virtual-Source Model for Carbon Nanotube FETs in the Sub-10-nm Regime-Part I: Intrinsic Elements," T-ED, 2015.
[17]
T. Li et al., "CNFET-based High Throughput Register File Architecture," in ICCD, 2016.
[18]
G. Hills et al., "TRIG: Hardware Accelerator for Inference-based Applications and Experimental Demonstration using Carbon Nanotube FETs," in DAC, 2018.
[19]
A. Samajdar et al., "SCALE-Sim: Systolic CNN Accelerator Simulator," arXiv e-prints, 2018.
[20]
S. Han et al., "Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding," in ICLR, 2016.
[21]
J. Shi et al., "A 14nm FinFET Transistor-Level 3D Partitioning Design to Enable High-Performance and Low-Cost Monolithic 3D IC," in IEDM, 2016.

Index Terms

  1. MOCCA: A Process Variation Tolerant Systolic DNN Accelerator using CNFETs in Monolithic 3D

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    GLSVLSI '22: Proceedings of the Great Lakes Symposium on VLSI 2022
    June 2022
    560 pages
    ISBN:9781450393225
    DOI:10.1145/3526241
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 06 June 2022

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. cnfet
    2. dnn
    3. process variation
    4. systolic array

    Qualifiers

    • Short-paper

    Conference

    GLSVLSI '22
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 312 of 1,156 submissions, 27%

    Upcoming Conference

    GLSVLSI '25
    Great Lakes Symposium on VLSI 2025
    June 30 - July 2, 2025
    New Orleans , LA , USA

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 101
      Total Downloads
    • Downloads (Last 12 months)13
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 15 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media