Different in-memory computing paradigms enabled by emerging non-volatile memory technologies are promising solutions for the development of ultra-low-power hardware for edge com-puting. Among these, SIMPLY, a smart logic-in-memory architecture, provides high reconfigurability and enables the in-memory computation of both logic operations and binarized neural networks (BNNs) inference. However, operation-specific hardware accelerators can result in better performance for a particular task, such as the analog computation of the multiply and accumulate operation for BNN inference, but lack reconfigurability. Nonetheless, a solution providing the flexibility of SIMPLY while also achieving the high performance of BNN-specific analog hardware accelerators is missing. In this work, we propose a novel in-memory architecture based on 1T1R crossbar arrays, which enables the coexistence on the same crossbar array of both SIMPLY computing paradigm and the analog acceleration of the multiply and accumulate operation for BNN inference. We also highlight the main design tradeoffs and opportunities enabled by different emerging non-volatile memory technologies. Finally, by using a physics-based Resistive Random Access Memory (RRAM) compact model calibrated on data from the literature, we show that the proposed architecture improves the energy delay product by >103 times when performing a BNN inference task with respect to a SIMPLY implementation.
Energy-efficient non-von neumann computing architecture supporting multiple computing paradigms for logic and binarized neural networks / Zanotti, T.; Puglisi, F. M.; Pavan, P.. - In: JOURNAL OF LOW POWER ELECTRONICS AND APPLICATIONS. - ISSN 2079-9268. - 11:3(2021), pp. 29-47. [10.3390/jlpea11030029]
Energy-efficient non-von neumann computing architecture supporting multiple computing paradigms for logic and binarized neural networks
Zanotti T.;Puglisi F. M.;Pavan P.
2021
Abstract
Different in-memory computing paradigms enabled by emerging non-volatile memory technologies are promising solutions for the development of ultra-low-power hardware for edge com-puting. Among these, SIMPLY, a smart logic-in-memory architecture, provides high reconfigurability and enables the in-memory computation of both logic operations and binarized neural networks (BNNs) inference. However, operation-specific hardware accelerators can result in better performance for a particular task, such as the analog computation of the multiply and accumulate operation for BNN inference, but lack reconfigurability. Nonetheless, a solution providing the flexibility of SIMPLY while also achieving the high performance of BNN-specific analog hardware accelerators is missing. In this work, we propose a novel in-memory architecture based on 1T1R crossbar arrays, which enables the coexistence on the same crossbar array of both SIMPLY computing paradigm and the analog acceleration of the multiply and accumulate operation for BNN inference. We also highlight the main design tradeoffs and opportunities enabled by different emerging non-volatile memory technologies. Finally, by using a physics-based Resistive Random Access Memory (RRAM) compact model calibrated on data from the literature, we show that the proposed architecture improves the energy delay product by >103 times when performing a BNN inference task with respect to a SIMPLY implementation.File | Dimensione | Formato | |
---|---|---|---|
jlpea-11-00029-v2.pdf
Open access
Tipologia:
VOR - Versione pubblicata dall'editore
Dimensione
2.2 MB
Formato
Adobe PDF
|
2.2 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris