In-Memory Computing (IMC) is one of the most promising candidates for data-intensive computing accelerators of machine learning (ML). A key ML algorithm for dimensionality reduction and classification is principal component analysis (PCA), which heavily relies on matrix-vector multiplications (MVM) for which classic von Neumann architectures are not optimized. Here, we provide the experimental demonstration of a new IMC-based PCA algorithm based on power iteration and deflation executed in a 4-kbit array of resistive switching random-access memory (RRAM). The classification accuracy of the Wisconsin Breast Cancer data set reaches 95.43%, close to floating-point implementation. Our simulations indicate a 250× improvement in energy efficiency compared to commercial GPUs, thus supporting IMC for energy-efficient ML in modern data-intensive computing.

In-Memory Principal Component Analysis by Crosspoint Array of Resistive Switching Memory: A new hardware approach for energy-efficient data analysis in edge computing

Zambelli C.;Olivo P.;
2022

Abstract

In-Memory Computing (IMC) is one of the most promising candidates for data-intensive computing accelerators of machine learning (ML). A key ML algorithm for dimensionality reduction and classification is principal component analysis (PCA), which heavily relies on matrix-vector multiplications (MVM) for which classic von Neumann architectures are not optimized. Here, we provide the experimental demonstration of a new IMC-based PCA algorithm based on power iteration and deflation executed in a 4-kbit array of resistive switching random-access memory (RRAM). The classification accuracy of the Wisconsin Breast Cancer data set reaches 95.43%, close to floating-point implementation. Our simulations indicate a 250× improvement in energy efficiency compared to commercial GPUs, thus supporting IMC for energy-efficient ML in modern data-intensive computing.
2022
Mannocci, P.; Baroni, A.; Melacarne, E.; Zambelli, C.; Olivo, P.; Perez, E.; Wenger, C.; Ielmini, D.
File in questo prodotto:
File Dimensione Formato  
1570771936 paper_IRIS.pdf

solo gestori archivio

Descrizione: Pre-print
Tipologia: Pre-print
Licenza: Copyright dell'editore
Dimensione 4.5 MB
Formato Adobe PDF
4.5 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
In-Memory_Principal_Component_Analysis_by_Crosspoint_Array_of_Resistive_Switching_Memory_A_new_hardware_approach_for_energy-efficient_data_analysis_in_edge_computing.pdf

solo gestori archivio

Descrizione: Full text editoriale
Tipologia: Full text (versione editoriale)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 2.83 MB
Formato Adobe PDF
2.83 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11392/2501094
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 7
social impact