A Maximally Row-Parallel MRAM In-Memory-Computing Macro Addressing Readout Circuit Sensitivity and Area

Peter Deaville, Bonan Zhang, Lung Yen Chen, Naveen Verma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

This paper presents the first MRAM-based In-Memory-Computing (IMC) macro, implemented as a 128-kb array in an advanced-node 22nm FD-SOI technology. The design maximizes IMC row parallelism for energy efficiency and throughput, while addressing the critical challenges this raises, namely: high column currents; high output dynamic-range requirements; and large area of peripheral readout circuits. These are addressed through current-insensitive column-multiplexing and high-sensitivity readout circuits, occupying 26% of the macro area. Residual IMC non-idealities, arising from statistical circuit variations, are modeled and incorporated in a chip-generalized one-time neural-network training algorithm, with CIFAR-10 image-classification accuracy demonstrated at 90.1%, equal to ideal digital computation. The design addresses the particularly high sensitivity required for MRAM-based IMC compared to other non-volatile memory technologies, while achieving area-normalized throughput of 758 GOPS/mm2 and energy efficiency of 5.1 TOPS/W for the macro.

Original languageEnglish (US)
Title of host publicationESSCIRC 2021 - IEEE 47th European Solid State Circuits Conference, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages75-78
Number of pages4
ISBN (Electronic)9781665437479
DOIs
StatePublished - Sep 13 2021
Event47th IEEE European Solid State Circuits Conference, ESSCIRC 2021 - Virtual, Online, France
Duration: Sep 6 2021Sep 9 2021

Publication series

NameESSCIRC 2021 - IEEE 47th European Solid State Circuits Conference, Proceedings

Conference

Conference47th IEEE European Solid State Circuits Conference, ESSCIRC 2021
Country/TerritoryFrance
CityVirtual, Online
Period9/6/219/9/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Fingerprint

Dive into the research topics of 'A Maximally Row-Parallel MRAM In-Memory-Computing Macro Addressing Readout Circuit Sensitivity and Area'. Together they form a unique fingerprint.

Cite this