HURRY: Highly Utilized, Reconfigurable ReRAM-based In-situ Accelerator with Multifunctionality
Year: 2024
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Shin, Hery, Kim, Jae-Young, Kim, Donghyuk, Kim, Joo-Young
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4403784077