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.

翻译：阻变随机存取存储器（ReRAM）交叉阵列因其模拟通用矩阵-矩阵乘法（GEMM）能力，非常适用于神经网络的高效推理计算。然而，传统的基于ReRAM的加速器存在空间和时间利用率不足的问题。本文提出HURRY，一种可重构且具备多功能性的基于ReRAM的原位加速器。HURRY采用块激活方案，可并发激活动态尺寸的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，以提高时间利用率。系统级调度与数据映射策略进一步优化了性能。因此，与当前基于ReRAM的加速器相比，HURRY实现了高达3.35倍的加速比、5.72倍的能效提升和7.91倍的面积效率提升。