PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning

• Published in: Proceedings - International Symposium on High-Performance Computer Architecture pp. 541 - 552
• Main Authors: Linghao Song, Xuehai Qian, Hai Li, Yiran Chen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.02.2017
• Subjects: Computer architecture; Kernel; Machine learning; Neural networks; Pipelines; Testing; Training

Convolutional neural networks (CNNs) are the heart of deep learning applications. Recent works PRIME [1] and ISAAC [2] demonstrated the promise of using resistive random access memory (ReRAM) to perform neural computations in memory. We found that training cannot be efficiently supported with the cu...