Enabling Normally-Off in Situ Computing with a Magneto-Electric FET-Based SRAM Design

Deniz Najafi, Mehrdad Morsali, Ranyang Zhou, Arman Roohi, Andrew Marshall, Durga Misra, Shaahin Angizi

Research output: Contribution to journalArticlepeer-review

Abstract

As an emerging post-CMOS Field Effect Transistor, magneto-electric field-effect transistors (MEFETs) offer compelling design characteristics for logic and memory applications, such as high-speed switching, low power consumption, and nonvolatility. In this article, for the first time, a nonvolatile MEFET-based SRAM design named ME-SRAM is proposed for edge applications which can remarkably save the SRAM static power consumption in the idle state through a fast backup-restore process. To enable normally- OFF in situ computing, the ME-SRAM cell is integrated into a novel processing-in-SRAM architecture that exploits a hardware-optimized bitline computing approach for the execution of Boolean logic operations between operands housed in a memory sub-array within a single clock cycle. Our device-to-architecture evaluation results on Binary convolutional neural network acceleration show the robust performance of ME-SRAM while reducing energy consumption on average by a factor of compared to the best in-SRAM designs.

Original languageEnglish (US)
Article number10440020
Pages (from-to)2742-2748
Number of pages7
JournalIEEE Transactions on Electron Devices
Volume71
Issue number4
DOIs
StatePublished - Apr 1 2024

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Keywords

  • Magneto-electric field-effect transistor (MEFET)
  • normally-OFF computing
  • processing-in-SRAM

Fingerprint

Dive into the research topics of 'Enabling Normally-Off in Situ Computing with a Magneto-Electric FET-Based SRAM Design'. Together they form a unique fingerprint.

Cite this