University of Oulu

M. Safarpour, R. Inanlou and O. Silvén, "Algorithm Level Error Detection in Low Voltage Systolic Array," in IEEE Transactions on Circuits and Systems II: Express Briefs, doi: 10.1109/TCSII.2021.3094923

Algorithm level error detection in low voltage systolic array

Saved in:
Author: Safarpour, Mehdi1; Inanlou, Reza2; Silvén, Olli1
Organizations: 1Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
2School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 2.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021080341988
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-08-03
Description:

Abstract

In this brief an approach is proposed to achieve energy savings from reduced voltage operation. The solution detects timing-errors by integrating Algorithm Based Fault Tolerance (ABFT) into a digital architecture. The approach has been studied with a systolic array matrix multiplier operating at reduced voltages, detecting errors on-the-fly to avoid energy demanding memory round-trips. The analysis of the solution has been done using analog-digital co-simulation to extract the transient behavior under different voltages and clock frequencies. HSPICE simulations using 90nm CMOS transistor models, and experiments by reducing operation voltage of an FPGA device were carried out. HSPICE simulations, showed possibility of 10x increase in energy-efficiency by approaching near-threshold region.

see all

Series: IEEE transactions on circuits and systems. II, Express briefs
ISSN: 1549-7747
ISSN-E: 1558-3791
ISSN-L: 1549-7747
Volume: Early Access
Issue: Early Access
Pages: 1 - 5
DOI: 10.1109/TCSII.2021.3094923
OADOI: https://oadoi.org/10.1109/TCSII.2021.3094923
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: This work was supported by 6G Flagship research programme under Academy of Finland Grant 318927.
Academy of Finland Grant Number: 318927
Detailed Information: 318927 (Academy of Finland Funding decision)
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.