arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.16640cs.AR
收藏

HURRY:高利用率、可重构的基于ReRAM的原位加速器,具备多功能性

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

Hery Shin, Jae-Young Kim, Donghyuk Kim, Joo-Young Kim

AI总结:

针对传统ReRAM加速器时空利用率不足的问题,提出可重构多功能原位加速器HURRY,通过块激活方案与集成多种功能块提升时空利用率,实现最高3.35倍加速及显著的能效与面积效率提升。

摘要:

阻变随机存取存储器(ReRAM)交叉阵列因其模拟通用矩阵乘法(GEMM)能力,适用于神经网络的高效推理计算。然而,传统的基于ReRAM的加速器在空间和时间利用率上存在不足。我们提出了HURRY,一种可重构且多功能的基于ReRAM的原位加速器。HURRY采用块激活方案,并发激活动态调整大小的ReRAM部分,从而提升空间利用率。此外,它集成了用于卷积、ReLU、最大池化和softmax计算的功能块,以改善时间利用率。系统级调度和数据映射策略进一步优化了性能。因此,与现有的基于ReRAM的加速器相比,HURRY实现了高达3.35倍的加速、5.72倍的能效提升和7.91倍的面积效率提升。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑