A survey on processing-in-memory techniques: Advances and challenges

Asifuzzaman, Kazi; Miniskar, Narasinga Rao; Young, Aaron; Liu, Frank; Vetter, Jeffrey S.

doi:10.1016/j.memori.2022.100022

Cited by 33 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, a tremendous surge of CIM researches [1,2,3] have been presented in different levels, including the circuit-level memory cells based on various volatile or nonvolatile memory devices, the micro-architecture-level macros for multi-bit precision computation, the processor-level chips targeting end-to-end accelerating of neural networks, and the EDA tool chains for CIM simulation and algorithm mapping. This paper gives a comprehensive review of CIMbased processors in different levels, as shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Computing-in-Memory Processor: From Circuit to Application

Sun,

Yue,

et al. 2024

IEEE Open J. Solid-State Circuits Soc.

View full text Add to dashboard Cite

The computing-in-memory (CIM) technique is emerging with the evolvement of big data and artificial intelligence (AI) application. The manuscript presents a systematic review of existing CIM works in a bottom-up view from circuit to application. Various types of CIM circuits based on different volatile/non-volatile devices are introduced. The micro CIM architectures are illustrated to support multibit precision computation. After that, several types of processor-level CIM chips are analyzed to reveal the system architecture design considerations. The corresponding CIM tool chains and applications beyond AI applications are also introduced. From circuit to application levels, this manuscript analyzes the design trade-offs, remained challenges and possible future design trends at different design hierarchies of CIM processors.INDEX TERMS Computing-in-memory (CIM), CIM processor, Circuit-level CIM cells, CIM micro architecture, CIM tool chains, CIM applications

show abstract

Section: Introductionmentioning

confidence: 99%

A Survey of Computing-in-Memory Processor: From Circuit to Application

Sun,

Yue,

et al. 2024

IEEE Open J. Solid-State Circuits Soc.

View full text Add to dashboard Cite

show abstract

“…Resources are much bigger a measurement, it can be divided into space or memory resources, capacity or CPU resources. Memory is a place where computer store data required for processing while CPU is the strength of computing processor to execute given instructions [2].…”

Section: Introductionmentioning

confidence: 99%

Challenges in data representation for efficient execution of encryption operation

Afendee Mohamed,

Garba Shawai,

Almaiah

et al. 2024

Bulletin EEI

View full text Add to dashboard Cite

Big number operation has always been a bottleneck to computer system as it imposes high demand on computing power. With a limited power available, operations such as exponentiation and multiplication involving large integer belonging to encryption process requires grave scrutiny. One way to address this issue is by replacing an original complex computation into a sequence of small computations that in the end produces the same results. This paper takes an evolutionary approach to survey numerous articles that have contributed to the advancement of integer representation. Numerous representations were proposed, those that come into play concentrated on reducing non-zero digits and limiting non-zero spacing other than allowing subtraction operation. A comparison was made to distinguish the properties of each method from the others. This detailed outlook can be a guide for identifying the correct representation to be chosen for implementation within specific application.

show abstract

“…These findings suggest that the proposed approach is effective for unidirectional transport of skyrmion and offers notable advantages, including minimal joule heating and enhanced energy efficiency by employing a non-charge-based driving force. The utilization and regulation of a magnetic skyrmion-based device through the manipulation of microwave fields hold immense promise for the advancement of future skyrmioniumbased spintronic devices and circuits 8,9 .…”

Section: Introductionmentioning

confidence: 99%

Anisotropy barrier-induced unidirectional motion of spin wave driven skyrmion

Saini,

Shukla,

Bindal

et al. 2023

Spintronics XVI

View full text Add to dashboard Cite

The propagation of spin waves and their interaction with the spin solitons like skyrmions, domain walls and vortex are one of the promising ways for designing nanoscale spintronic devices. Magnetic skyrmion, a particle-like nanoscale object has potential applications in next-generation spintronic devices. In this paper, the unidirectional motion of the skyrmion under the influence of spin wave is studied using micromagnetic simulations. Here, two different magnetic anisotropies are considered on a nanotrack that creates an energy gradient. As a result, the repulsive forces act on the skyrmion and is responsible for the motion of the skyrmion in one direction. The spin wave driving force leads the skyrmion to move in forward direction and the anisotropy gradient is responsible to prevent the skyrmion motion in reverse direction. The skyrmion moves from higher perpendicular magnetic anisotropy region to lower energy region, leading to a unidirectional transport of the skyrmion. This proposed device has less Joule heating and is more energy efficient as compared to other spin transfer torque (STT) and spin orbit torque (SOT) driven techniques. This is due to the fact that spin wave can generate a flow of magnetic momentum without generating an electron flow. This spin wave driven skyrmionics device is a promising pathway towards the development of a complete non-charge based magnetic devices.

show abstract

A survey on processing-in-memory techniques: Advances and challenges

Cited by 33 publications

References 30 publications

A Survey of Computing-in-Memory Processor: From Circuit to Application

A Survey of Computing-in-Memory Processor: From Circuit to Application

Challenges in data representation for efficient execution of encryption operation

Anisotropy barrier-induced unidirectional motion of spin wave driven skyrmion

Contact Info

Product

Resources

About