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.
Redundancy and Analog Slicing for Precise in-Memory Machine Learning--Part I: Programming Techniques
Pedretti G.;Mannocci P.;Sun Z.;Ielmini D.
2021-01-01
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.File | Dimensione | Formato | |
---|---|---|---|
IEEE_TED_redundancy_and_slicing_part_1-3 copia.pdf
accesso aperto
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
914.34 kB
Formato
Adobe PDF
|
914.34 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.