A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method

In recent years, several designs that use in-memory processing to accelerate machine-learning inference problems have been proposed. Such designs are also a perfect fit for discrete, dynamic, and distributed systems that can solve large-dimensional optimization problems using iterative algorithms. F...

Full description

Bibliographic Details
Main Authors:	Insik Yoon, Muya Chang, Kai Ni, Matthew Jerry, Samantak Gangopadhyay, Gus Henry Smith, Tomer Hamam, Justin Romberg, Vijaykrishnan Narayanan, Asif Khan, Suman Datta, Arijit Raychowdhury
Format:	Article
Language:	English
Published:	IEEE 2019-01-01
Series:	IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
Subjects:	Distributed computing emerging ferroelectric field-effect transistors (FerroFETs) hardware in-memory processing least square
Online Access:	https://ieeexplore.ieee.org/document/8767985/

id	doaj-976b889045294db4b36cbdca4b063d28
record_format	Article
spelling	doaj-976b889045294db4b36cbdca4b063d282021-04-05T17:39:50ZengIEEEIEEE Journal on Exploratory Solid-State Computational Devices and Circuits2329-92312019-01-015213214110.1109/JXCDC.2019.29302228767985A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares MethodInsik Yoon0https://orcid.org/0000-0003-4545-4404Muya Chang1https://orcid.org/0000-0002-3035-1106Kai Ni2https://orcid.org/0000-0002-3628-3431Matthew Jerry3https://orcid.org/0000-0001-7220-1854Samantak Gangopadhyay4Gus Henry Smith5Tomer Hamam6Justin Romberg7https://orcid.org/0000-0002-6616-197XVijaykrishnan Narayanan8https://orcid.org/0000-0001-6266-6068Asif Khan9https://orcid.org/0000-0003-4369-106XSuman Datta10https://orcid.org/0000-0001-6044-5173Arijit Raychowdhury11https://orcid.org/0000-0001-8391-0576Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Electrical Engineering, University of Notre Dame, South Bend, IN, USADepartment of Electrical Engineering, University of Notre Dame, South Bend, IN, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Computer Science and Engineering and Electrical Engineering, Penn State University, State College, PA, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Computer Science and Engineering and Electrical Engineering, Penn State University, State College, PA, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Electrical Engineering, University of Notre Dame, South Bend, IN, USADepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USAIn recent years, several designs that use in-memory processing to accelerate machine-learning inference problems have been proposed. Such designs are also a perfect fit for discrete, dynamic, and distributed systems that can solve large-dimensional optimization problems using iterative algorithms. For in-memory computations, ferroelectric field-effect transistors (FerroFETs) owing to their compact area and distinguishable multiple states offer promising possibilities. We present a distributed architecture that uses FerroFET memory and implements in-memory processing to solve a template problem of least squares minimization. Through this architecture, we demonstrate an improvement of 21× in energy efficiency and 3× in compute time compared to a static random access memory (SRAM)-based processing-inmemory (PIM) architecture.https://ieeexplore.ieee.org/document/8767985/Distributed computingemergingferroelectric field-effect transistors (FerroFETs)hardwarein-memory processingleast square
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Insik Yoon Muya Chang Kai Ni Matthew Jerry Samantak Gangopadhyay Gus Henry Smith Tomer Hamam Justin Romberg Vijaykrishnan Narayanan Asif Khan Suman Datta Arijit Raychowdhury
spellingShingle	Insik Yoon Muya Chang Kai Ni Matthew Jerry Samantak Gangopadhyay Gus Henry Smith Tomer Hamam Justin Romberg Vijaykrishnan Narayanan Asif Khan Suman Datta Arijit Raychowdhury A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method IEEE Journal on Exploratory Solid-State Computational Devices and Circuits Distributed computing emerging ferroelectric field-effect transistors (FerroFETs) hardware in-memory processing least square
author_facet	Insik Yoon Muya Chang Kai Ni Matthew Jerry Samantak Gangopadhyay Gus Henry Smith Tomer Hamam Justin Romberg Vijaykrishnan Narayanan Asif Khan Suman Datta Arijit Raychowdhury
author_sort	Insik Yoon
title	A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method
title_short	A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method
title_full	A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method
title_fullStr	A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method
title_full_unstemmed	A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method
title_sort	ferrofet-based in-memory processor for solving distributed and iterative optimizations via least-squares method
publisher	IEEE
series	IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
issn	2329-9231
publishDate	2019-01-01
description	In recent years, several designs that use in-memory processing to accelerate machine-learning inference problems have been proposed. Such designs are also a perfect fit for discrete, dynamic, and distributed systems that can solve large-dimensional optimization problems using iterative algorithms. For in-memory computations, ferroelectric field-effect transistors (FerroFETs) owing to their compact area and distinguishable multiple states offer promising possibilities. We present a distributed architecture that uses FerroFET memory and implements in-memory processing to solve a template problem of least squares minimization. Through this architecture, we demonstrate an improvement of 21× in energy efficiency and 3× in compute time compared to a static random access memory (SRAM)-based processing-inmemory (PIM) architecture.
topic	Distributed computing emerging ferroelectric field-effect transistors (FerroFETs) hardware in-memory processing least square
url	https://ieeexplore.ieee.org/document/8767985/
work_keys_str_mv	AT insikyoon aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT muyachang aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT kaini aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT matthewjerry aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT samantakgangopadhyay aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT gushenrysmith aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT tomerhamam aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT justinromberg aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT vijaykrishnannarayanan aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT asifkhan aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT sumandatta aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT arijitraychowdhury aferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT insikyoon ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT muyachang ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT kaini ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT matthewjerry ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT samantakgangopadhyay ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT gushenrysmith ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT tomerhamam ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT justinromberg ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT vijaykrishnannarayanan ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT asifkhan ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT sumandatta ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod AT arijitraychowdhury ferrofetbasedinmemoryprocessorforsolvingdistributedanditerativeoptimizationsvialeastsquaresmethod
_version_	1721539192895307776

A FerroFET-Based In-Memory Processor for Solving Distributed and Iterative Optimizations via Least-Squares Method

Similar Items