Saved in:
Bibliographic Details
Main Authors: Kalantzis, Vassilis, Squillante, Mark S., Ubaru, Shashanka, Gokmen, Tayfun, Wu, Chai Wah, Gupta, Anshul, Avron, Haim, Nowicki, Tomasz, Rasch, Malte, Onen, Murat, Marrero, Vanessa Lopez, Leobandung, Effendi, Kohda, Yasuteru, Haensch, Wilfried, Horesh, Lior
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13754
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911764416823296
author Kalantzis, Vassilis
Squillante, Mark S.
Ubaru, Shashanka
Gokmen, Tayfun
Wu, Chai Wah
Gupta, Anshul
Avron, Haim
Nowicki, Tomasz
Rasch, Malte
Onen, Murat
Marrero, Vanessa Lopez
Leobandung, Effendi
Kohda, Yasuteru
Haensch, Wilfried
Horesh, Lior
author_facet Kalantzis, Vassilis
Squillante, Mark S.
Ubaru, Shashanka
Gokmen, Tayfun
Wu, Chai Wah
Gupta, Anshul
Avron, Haim
Nowicki, Tomasz
Rasch, Malte
Onen, Murat
Marrero, Vanessa Lopez
Leobandung, Effendi
Kohda, Yasuteru
Haensch, Wilfried
Horesh, Lior
contents Numerical computation is essential to many areas of artificial intelligence (AI), whose computing demands continue to grow dramatically, yet their continued scaling is jeopardized by the slowdown in Moore's law. Multi-function multi-way analog (MFMWA) technology, a computing architecture comprising arrays of memristors supporting in-memory computation of matrix operations, can offer tremendous improvements in computation and energy, but at the expense of inherent unpredictability and noise. We devise novel randomized algorithms tailored to MFMWA architectures that mitigate the detrimental impact of imperfect analog computations while realizing their potential benefits across various areas of AI, such as applications in computer vision. Through analysis, measurements from analog devices, and simulations of larger systems, we demonstrate orders of magnitude reduction in both computation and energy with accuracy similar to digital computers.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13754
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Function Multi-Way Analog Technology for Sustainable Machine Intelligence Computation
Kalantzis, Vassilis
Squillante, Mark S.
Ubaru, Shashanka
Gokmen, Tayfun
Wu, Chai Wah
Gupta, Anshul
Avron, Haim
Nowicki, Tomasz
Rasch, Malte
Onen, Murat
Marrero, Vanessa Lopez
Leobandung, Effendi
Kohda, Yasuteru
Haensch, Wilfried
Horesh, Lior
Numerical Analysis
Emerging Technologies
65F10, C3, G1
G.1.3
Numerical computation is essential to many areas of artificial intelligence (AI), whose computing demands continue to grow dramatically, yet their continued scaling is jeopardized by the slowdown in Moore's law. Multi-function multi-way analog (MFMWA) technology, a computing architecture comprising arrays of memristors supporting in-memory computation of matrix operations, can offer tremendous improvements in computation and energy, but at the expense of inherent unpredictability and noise. We devise novel randomized algorithms tailored to MFMWA architectures that mitigate the detrimental impact of imperfect analog computations while realizing their potential benefits across various areas of AI, such as applications in computer vision. Through analysis, measurements from analog devices, and simulations of larger systems, we demonstrate orders of magnitude reduction in both computation and energy with accuracy similar to digital computers.
title Multi-Function Multi-Way Analog Technology for Sustainable Machine Intelligence Computation
topic Numerical Analysis
Emerging Technologies
65F10, C3, G1
G.1.3
url https://arxiv.org/abs/2401.13754