HURRY: Highly Utilized, Reconfigurable ReRAM-based In-situ Accelerator with Multifunctionality

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shin, Hery, Kim, Jae-Young, Kim, Donghyuk, Kim, Joo-Young
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910619293188096
author Shin, Hery
Kim, Jae-Young
Kim, Donghyuk
Kim, Joo-Young
author_facet Shin, Hery
Kim, Jae-Young
Kim, Donghyuk
Kim, Joo-Young
contents Resistive random-access memory (ReRAM) crossbar arrays are suitable for efficient inference computations in neural networks due to their analog general matrix-matrix multiplication (GEMM) capabilities. However, traditional ReRAM-based accelerators suffer from spatial and temporal underutilization. We present HURRY, a reconfigurable and multifunctional ReRAM-based in-situ accelerator. HURRY uses a block activation scheme for concurrent activation of dynamically sized ReRAM portions, enhancing spatial utilization. Additionally, it incorporates functional blocks for convolution, ReLU, max pooling, and softmax computations to improve temporal utilization. System-level scheduling and data mapping strategies further optimize performance. Consequently, HURRY achieves up to 3.35x speedup, 5.72x higher energy efficiency, and 7.91x greater area efficiency compared to current ReRAM-based accelerators.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HURRY: Highly Utilized, Reconfigurable ReRAM-based In-situ Accelerator with Multifunctionality
Shin, Hery
Kim, Jae-Young
Kim, Donghyuk
Kim, Joo-Young
Hardware Architecture
Resistive random-access memory (ReRAM) crossbar arrays are suitable for efficient inference computations in neural networks due to their analog general matrix-matrix multiplication (GEMM) capabilities. However, traditional ReRAM-based accelerators suffer from spatial and temporal underutilization. We present HURRY, a reconfigurable and multifunctional ReRAM-based in-situ accelerator. HURRY uses a block activation scheme for concurrent activation of dynamically sized ReRAM portions, enhancing spatial utilization. Additionally, it incorporates functional blocks for convolution, ReLU, max pooling, and softmax computations to improve temporal utilization. System-level scheduling and data mapping strategies further optimize performance. Consequently, HURRY achieves up to 3.35x speedup, 5.72x higher energy efficiency, and 7.91x greater area efficiency compared to current ReRAM-based accelerators.
title HURRY: Highly Utilized, Reconfigurable ReRAM-based In-situ Accelerator with Multifunctionality
topic Hardware Architecture
url https://arxiv.org/abs/2409.16640