Machine learning (ML) techniques such as principal component analysis (PCA) have become pivotal in enabling efficient processing of big data in an increasing number of applications. However, the data-intensive computation in PCA causes large energy consumption in conventional von Neumann computers. In-memory computing (IMC) significantly improves throughput and energy efficiency by eliminating the physical separation between memory and processing units. Here, we present a novel closed-loop IMC circuit to compute real eigenvalues and eigenvectors of a target matrix allowing IMC-based acceleration of PCA. We benchmark its performance against a commercial GPU, achieving comparable accuracy and throughput while simultaneously securing ×10000 energy and ×100÷10000 area efficiency improvements. These results support IMC as a leading candidate architecture for energy-efficient ML accelerators.
In-Memory Principal Component Analysis by Analogue Closed-Loop Eigendecomposition
Mannocci, Piergiulio;Giannone, Elisabetta;Ielmini, Daniele
2023-01-01
Abstract
Machine learning (ML) techniques such as principal component analysis (PCA) have become pivotal in enabling efficient processing of big data in an increasing number of applications. However, the data-intensive computation in PCA causes large energy consumption in conventional von Neumann computers. In-memory computing (IMC) significantly improves throughput and energy efficiency by eliminating the physical separation between memory and processing units. Here, we present a novel closed-loop IMC circuit to compute real eigenvalues and eigenvectors of a target matrix allowing IMC-based acceleration of PCA. We benchmark its performance against a commercial GPU, achieving comparable accuracy and throughput while simultaneously securing ×10000 energy and ×100÷10000 area efficiency improvements. These results support IMC as a leading candidate architecture for energy-efficient ML accelerators.File | Dimensione | Formato | |
---|---|---|---|
tcas2-2023-publisher.pdf
accesso aperto
Descrizione: Publisher's version
:
Publisher’s version
Dimensione
2.13 MB
Formato
Adobe PDF
|
2.13 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.