# RED: A ReRAM-based Deconvolution Accelerator

## TL;DR

RED is a ReRAM-based deconvolution accelerator that improves efficiency by reducing redundancy and increasing parallelism, achieving significant speedup and energy savings over existing designs.

## Contribution

The paper introduces RED, a novel ReRAM-based accelerator that combines pixel-wise mapping and zero-skipping techniques for efficient deconvolution processing.

## Key findings

- RED speeds up deconvolution operations by up to 3.69 times.
- RED reduces energy consumption by up to 88.36%.
- Experimental results outperform state-of-the-art ReRAM accelerators.

## Abstract

Deconvolution has been widespread in neural networks. For example, it is essential for performing unsupervised learning in generative adversarial networks or constructing fully convolutional networks for semantic segmentation. Resistive RAM (ReRAM)-based processing-in-memory architecture has been widely explored in accelerating convolutional computation and demonstrates good performance. Performing deconvolution on existing ReRAM-based accelerator designs, however, suffers from long latency and high energy consumption because deconvolutional computation includes not only convolution but also extra add-on operations. To realize the more efficient execution for deconvolution, we analyze its computation requirement and propose a ReRAM-based accelerator design, namely, RED. More specific, RED integrates two orthogonal methods, the pixel-wise mapping scheme for reducing redundancy caused by zero-inserting operations and the zero-skipping data flow for increasing the computation parallelism and therefore improving performance. Experimental evaluations show that compared to the state-of-the-art ReRAM-based accelerator, RED can speed up operation 3.69x~1.15x and reduce 8%~88.36% energy consumption.