Processing-in-Memory Technology for Machine Learning: From Basic to ASIC
- 19 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (6) , 2598-2603
Abstract
Due to the need for computing models that can process large quantities of data efficiently and with high throughput in many state-of-the-art machine learning algorithms, the processing-in-memory (PIM) paradigm is emerging as a potential replacement for standard digital architectures on these workloads. In this tutorial, we review the progress of PIM technology in recent years, at both the circuit and architecture level. We further present an analysis of when and how PIM technology surpasses the performance of conventional architectures. Finally, we outline our vision for the future of PIM technology.Keywords
Funding Information
- Natural Science Foundation (1955246, 1910299, 1725456)
- Army Research Office (W911NF-19-2-0107)
This publication has 46 references indexed in Scilit:
- ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars2016
- PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory2016
- Repeatable, accurate, and high speed multi-level programming of memristor 1T1R arrays for power efficient analog computing applicationsNanotechnology, 2016
- A neuromorphic ASIC design using one-selector-one-memristor crossbar2016
- A spiking neuromorphic design with resistive crossbar2015
- Reduction and IR-drop compensations techniques for reliable neuromorphic computing systems2014
- MAGIC—Memristor-Aided LogicIEEE Transactions on Circuits and Systems II: Express Briefs, 2014
- Crossbar RRAM Arrays: Selector Device Requirements During Read OperationIEEE Transactions on Electron Devices, 2014
- Memristive devices for computingNature Nanotechnology, 2012
- Memristor crossbar based hardware realization of BSB recall function2012