Recryptor: A Reconfigurable Cryptographic Cortex-M0 Processor With In-Memory and Near-Memory Computing for IoT Security

Providing security for the Internet of Things (IoT) is increasingly important, but supporting many different cryptographic algorithms and standards within the physical constraints of IoT devices is highly challenging. Software implementations are inefficient due to the high bitwidth cryptographic op...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of solid-state circuits 2018-04, Vol.53 (4), p.995-1005
Hauptverfasser: Zhang, Yiqun, Xu, Li, Dong, Qing, Wang, Jingcheng, Blaauw, David, Sylvester, Dennis
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Providing security for the Internet of Things (IoT) is increasingly important, but supporting many different cryptographic algorithms and standards within the physical constraints of IoT devices is highly challenging. Software implementations are inefficient due to the high bitwidth cryptographic operations; domain-specific accelerators are often inflexible; and reconfigurable crypto processors generally have large area and power overhead. This paper proposes Recryptor, a reconfigurable cryptographic processor that augments the existing memory of a commercial general-purpose processor with compute capabilities. It supports in-memory bitline computing using a 10-transistor bitcell to support different bitwise operations up to 512-bits wide. Custom-designed shifter, rotator, and S-box modules sit near the memory, providing high-throughput near-memory computing capabilities. We demonstrate Recryptor's programmability by implementing the cryptographic primitives of various public/ secret key cryptographies and hash functions. Recryptor runs at 28.8 MHz in 0.7 V, achieving 6.8\times average speedup and 12.8\times average energy improvements over the state-of-the-art software- and hardware-accelerated implementations with only 0.128 mm 2 area overhead in 40-nm CMOS.
ISSN:0018-9200
1558-173X
DOI:10.1109/JSSC.2017.2776302