TRIG: Hardware Accelerator for Inference-Based Applications and Experimental Demonstration Using Carbon Nanotube FETs

The energy efficiency demands of future abundant-data applications, e.g., those which use inference-based techniques to classify large amounts of data, exceed the capabilities of digital systems today. Field-effect transistors (FETs) built using nanotechnologies, such as carbon nanotubes (CNTs), can improve energy efficiency significantly. However, carbon nanotube FETs (CNFETs) are subject to process variations inherent to CNTs: variations in CNT type (semiconductor or metallic), CNT density, or CNT diameter, to name a few. These CNT variations can degrade CNFET benefits at advanced technology nodes. One path to overcome CNT variations is to co-optimize CNT processing and CNFET circuit design; however, the required CNT process advancements have not been achieved experimentally. We present a new design approach (TRIG, Technique for Reducing errors using Iterative Gray code) to overcome process variations in hardware accelerators targeting inference-based applications that use serial matrix operations (serial: accumulated over at least 2 clock cycles). We demonstrate that TRIG can retain the major energy efficiency benefits (quantified using Energy Delay Product or EDP) of CNFETs despite CNT variations that exist in today's CNFET fabrication - without requiring further CNT processing improvements to overcome CNT variations. As a case study, we analyze the effectiveness of TRIG for a binary neural network hardware accelerator that classifies images. Despite CNT variations that exist today, TRIG can maintain 99% (90%) of projected EDP benefits of CNFET digital circuits for 90% (99%) image classification accuracy target. We also demonstrate experimentally fabricated CNFET circuits to compute scalar product (a common matrix operation, also called dot product), with and without TRIG: TRIG reduces the mean difference between the expected result (no errors) and the experimentally computed result by 30 × in the presence of CNT variations, shown experimentally.

[1]  Zhenan Bao,et al.  Efficient metallic carbon nanotube removal for highly-scaled technologies , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[2]  Marian Verhelst,et al.  Bit Error Tolerance of a CIFAR-10 Binarized Convolutional Neural Network Processor , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[3]  Lianmao Peng,et al.  Scaling carbon nanotube complementary transistors to 5-nm gate lengths , 2017, Science.

[4]  Marian Verhelst,et al.  An always-on 3.8μJ/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28nm CMOS , 2018, 2018 IEEE International Solid - State Circuits Conference - (ISSCC).

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jan M. Rabaey,et al.  Brain-inspired computing exploiting carbon nanotube FETs and resistive RAM: Hyperdimensional computing case study , 2018, 2018 IEEE International Solid - State Circuits Conference - (ISSCC).

[7]  Subhasish Mitra,et al.  Three-dimensional integration of nanotechnologies for computing and data storage on a single chip , 2017, Nature.

[8]  Subhasish Mitra,et al.  High-performance carbon nanotube field-effect transistors , 2014, 2014 IEEE International Electron Devices Meeting.

[9]  Marian Verhelst,et al.  A 0.3–2.6 TOPS/W precision-scalable processor for real-time large-scale ConvNets , 2016, 2016 IEEE Symposium on VLSI Circuits (VLSI-Circuits).

[10]  J. Ryckaert,et al.  Extreme scaling enabled by 5 tracks cells: Holistic design-device co-optimization for FinFETs and lateral nanowires , 2016, 2016 IEEE International Electron Devices Meeting (IEDM).

[11]  W. Haensch,et al.  Arrays of single-walled carbon nanotubes with full surface coverage for high-performance electronics. , 2013, Nature nanotechnology.

[12]  Naresh R. Shanbhag,et al.  Energy-efficient soft error-tolerant digital signal processing , 2006, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[13]  Saurabh Sinha,et al.  32-bit Processor core at 5-nm technology: Analysis of transistor and interconnect impact on VLSI system performance , 2016, 2016 IEEE International Electron Devices Meeting (IEDM).

[14]  H.-S. Philip Wong,et al.  Special session paper 3D nanosystems enable embedded abundant-data computing , 2017, 2017 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS).

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  H.-S. Philip Wong,et al.  Characterization and Design of Logic Circuits in the Presence of Carbon Nanotube Density Variations , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[17]  Hai Wei,et al.  Carbon Nanotube Robust Digital VLSI , 2012, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[18]  Boris Murmann,et al.  BinarEye: An always-on energy-accuracy-scalable binary CNN processor with all memory on chip in 28nm CMOS , 2018, 2018 IEEE Custom Integrated Circuits Conference (CICC).

[19]  Boris Murmann,et al.  A Pixel Pitch-Matched Ultrasound Receiver for 3-D Photoacoustic Imaging With Integrated Delta-Sigma Beamformer in 28-nm UTBB FD-SOI , 2017, IEEE Journal of Solid-State Circuits.

[20]  H. Wong,et al.  A Compact Virtual-Source Model for Carbon Nanotube FETs in the Sub-10-nm Regime—Part I: Intrinsic Elements , 2015, IEEE Transactions on Electron Devices.

[21]  Christoforos E. Kozyrakis,et al.  3D nanosystems enable embedded abundant-data computing: special session paper , 2017, CODES+ISSS.

[22]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, NIPS.

[23]  Kunle Olukotun,et al.  Energy-Efficient Abundant-Data Computing: The N3XT 1,000x , 2015, Computer.

[24]  Mark Horowitz,et al.  Energy dissipation in general purpose microprocessors , 1996, IEEE J. Solid State Circuits.

[25]  Naresh R. Shanbhag,et al.  Energy-efficient signal processing via algorithmic noise-tolerance , 1999, Proceedings. 1999 International Symposium on Low Power Electronics and Design (Cat. No.99TH8477).

[26]  Saurabh Sinha,et al.  ASAP7: A 7-nm finFET predictive process design kit , 2016, Microelectron. J..

[27]  Carla Savage,et al.  A Survey of Combinatorial Gray Codes , 1997, SIAM Rev..

[28]  Hai Wei,et al.  Rapid Co-Optimization of Processing and Circuit Design to Overcome Carbon Nanotube Variations , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.