Redundancy and Analog Slicing for Precise In-Memory Machine Learning—Part I: Programming Techniques

IEEE Transactions on Electron Devices, vol. 68, pp. 4373–4378

Abstract

In-memory computing (IMC) is receiving considerable interest for accelerating artificial intelligence (AI) tasks, such as neural network training and inference. However, IMC can also accelerate other machine learning (ML) and scientific computing problems, such as recommendation systems, regression, and PageRank, which are ubiquitous in datacenters. These applications typically have higher precision requirements than neural networks, which can challenge analog-based IMC and sacrifice some of the expected energy efficiency benefits. In this article, we address these challenges experimentally, presenting new techniques improving the accuracy of the solution of linear algebra problems, such as eigenvector extraction for PageRank, in a fully integrated circuit (IC) with analog resistive random access memory (RRAM) devices. Our custom redundancy algorithm can improve the programming accuracy by using multiple memory devices for representing a single matrix entry. Accuracy is further improved by error compensation with analog slicing, which allows an ever more precise value representation.

Authors 6

1. Giacomo Pedretti

   Hewlett-Packard (United States)

   Affiliation as printed

   Hewlett Packard Labs, Milpitas, CA, USA

2. Piergiulio Mannocci

   Politecnico di Milano

   Affiliation as printed

   Dipartimento di Elettronica Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy

3. Can Li

   University of Hong Kong

   Affiliation as printed

   Department of Electrical and Electronic Engineering, The University of Hong Kong (HKU), Hong Kong, SAR, China

4. Zhong Sun

   Peking University

   Affiliation as printed

   Institute for Artificial Intelligence and Microelectronics, Peking University (PKU), Beijing, China

5. John Paul Strachan Aachen

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Peter Grünberg Institute (PGI-14), Forschungszentrum Jülich, Jülich, Germany

   RWTH Aachen University, Aachen, Germany

6. Daniele Ielmini

   Politecnico di Milano

   Affiliation as printed

   Dipartimento di Elettronica Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy