On-chip Built-In Self-Calibration of Thermal Variations for Mixed-Signal In-Memory Computing

Gaurav Singh*, Omar Numan, Dipesh Monga, Martin Andraud, Kari Halonen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

15 Downloads (Pure)

Abstract

In-memory computing (IMC) accelerators have become a pivotal architecture for enhancing AI algorithm computations, particularly critical for embedding deep neural networks (DNNs) in edge devices. The efficiency of these systems is paramount, yet IMC cores are prone to fluctuations due to process, temperature, and voltage variations, which can detrimentally impact DNN accuracy. This research introduces an innovative Built-In Self-Calibration (BISC) methodology, specifically designed to compensate for temperature-induced variations in mixed-signal IMC cores. The methodology enables real-time, on-chip adjustment of DNN weights during computation within the IMC core without modifying the computation path. The proposed approach, implemented on a silicon prototype, not only maintained DNN computation accuracy under substantial temperature variations but also fully compensated for almost 90% of the offset caused by these variations, without introducing any non-idealities.

Original languageEnglish
Title of host publicationProceedings - 2024 29th IEEE European Test Symposium, ETS 2024
PublisherIEEE
Number of pages6
ISBN (Electronic)979-8-3503-4932-0
DOIs
Publication statusPublished - 2024
MoE publication typeA4 Conference publication
EventIEEE European Test Symposium - The Hague, Netherlands
Duration: 20 May 202424 May 2024
Conference number: 29

Publication series

NameProceedings of the European Test Workshop
ISSN (Print)1530-1877
ISSN (Electronic)1558-1780

Conference

ConferenceIEEE European Test Symposium
Abbreviated titleETS
Country/TerritoryNetherlands
CityThe Hague
Period20/05/202424/05/2024

Keywords

  • In-memory computing (IMC)
  • multiply-and-accumulate (MAC)
  • temperature sensor
  • thermal compensation

Fingerprint

Dive into the research topics of 'On-chip Built-In Self-Calibration of Thermal Variations for Mixed-Signal In-Memory Computing'. Together they form a unique fingerprint.

Cite this