A comprehensive hardware-aware design framework for systematically mapping algorithmic workloads onto IMC architectures, using the discrete Fourier transform (DFT) as a case study and a novel mapping scheme that reduces energy consumption per computation by 53% compared with conventional mapping techniques is introduced.
Abstract
Although memristor-based in-memory computing (IMC) has been widely investigated for brain-inspired neuromorphic workloads, systematic evaluations of its energy, latency, and signal-to-noise ratio (SNR) trade-offs across diverse system parameters remain scarce for classical digital signal processing (DSP). To address this gap, this paper introduces a comprehensive hardware-aware design framework for systematically mapping algorithmic workloads onto IMC architectures, using the discrete Fourier transform (DFT) as a case study. Tailored to the stringent performance requirements of a DFT accelerator for 5G orthogonal frequency-division multiplexing (OFDM) systems, we propose a novel mapping scheme that reduces energy consumption per computation by 53% compared with conventional mapping techniques. Additionally, we present a comparative study of resistive random-access memory (RRAM) and ferroelectric tunnel junction (FTJ) technologies with identical numbers of programmable states but distinct conductance ranges, demonstrating the importance of device-informed architectural co-design. By bridging the gap between emerging IMC architectures and rigid DSP constraints, this work provides a pathway toward energy-efficient edge accelerators for future wireless communication systems.
The escalating computational demand of modern AI is increasingly constrained by the data-movement overhead of von Neumann architectures, motivating memristor-based compute-in-memory (CIM) as an energy-efficient alternative. Yet extending CIM to reliable analog computation remains difficult because practical memristor a...
Yi-Fei Yu, Ji-Chang Yang, Zi-Jian Ye et al.· npj Unconventional Computing· 0 citations
This review examines how that physical operation of memristive crossbars is translated into numerical formats, peripheral circuits, neural-network mappings, heterogeneous accelerators, local learning, compilation, and calibration in representative heterogeneous systems.
Chao-Yang Dong, Xuan Xie, Jian-Jun Chen et al.· Electronics· 0 citations
Modern edge devices increasingly require real-time adaptation to their environment without relying on cloud-based updates, which can introduce latency and security risks. To meet these demands, memory-augmented neural networks (MANNs) have gained traction for enabling adaptive on-device learning. Hardware implementatio...
Changhoon Joe, K. Byun, Min-Seung Kang et al.· npj Unconventional Computing· 0 citations
This work demonstrates the parallel and cascading execution of logic functions in an RRAM-based CIM array and provides new insights into the reliability and logic correctness of resistive CIM and outlines a potential path towards scalable and energy-efficient computing architectures.
L. Brackmann, Tobias Ziegler, N. Kopperberg et al.· npj Unconventional Computing· 0 citations
The rapid advancement of artificial intelligence (AI) necessitates high-performance computing architecture. While compute express link (CXL) technologies facilitate memory expansion, conventional dynamic random-access memory (DRAM) encounters fundamental limitations in power consumption and scalability. Consequently, 1...
Je-Yeon Jung, Munhyeon Kim, Sihyun Kim· Micromachines· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.