arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.08792cs.ETcs.LGeess.SP
收藏

PCNNA:光子卷积神经网络加速器

PCNNA: A Photonic Convolutional Neural Network Accelerator

The George Washington University(乔治华盛顿大学)

Armin Mehrabian, Yousra Al-Kabani, Volker J Sorger, Tarek El-Ghazawi

摘要:

卷积神经网络(CNN)已经成为许多应用的核心,包括但不限于计算机视觉、语音处理和自然语言处理(NLP)。然而,计算上昂贵的卷积运算对CNN的性能和可扩展性提出了许多挑战。并行地,传统上用于数据通信的光子系统由于其高带宽、低功耗和可重构性而近来在数据处理方面受到欢迎。在这里,我们提出了一个光子卷积神经网络加速器(PCNNA)作为概念设计的证明,以加速卷积神经网络的卷积运算。我们的设计是基于最近推出的硅光子微权重银行,它使用广播和重量协议来执行乘法和累加(MAC)操作和移动数据通过层的神经网络。在这里,我们的目标是利用波分复用(WDM)形式的光子学固有并行性与CNN中输入特征映射和内核之间连接的稀疏性之间的协同作用。虽然我们的完整系统设计在执行时间上提供了超过3个数量级的加速,但与最先进的电子同行相比,其光学核心可能提供超过5个数量级的加速。

英文摘要:

Convolutional Neural Networks (CNN) have been the centerpiece of many applications including but not limited to computer vision, speech processing, and Natural Language Processing (NLP). However, the computationally expensive convolution operations impose many challenges to the performance and scalability of CNNs. In parallel, photonic systems, which are traditionally employed for data communication, have enjoyed recent popularity for data processing due to their high bandwidth, low power consumption, and reconfigurability. Here we propose a Photonic Convolutional Neural Network Accelerator (PCNNA) as a proof of concept design to speedup the convolution operation for CNNs. Our design is based on the recently introduced silicon photonic microring weight banks, which use broadcast-and-weight protocol to perform Multiply And Accumulate (MAC) operation and move data through layers of a neural network. Here, we aim to exploit the synergy between the inherent parallelism of photonics in the form of Wavelength Division Multiplexing (WDM) and sparsity of connections between input feature maps and kernels in CNNs. While our full system design offers up to more than 3 orders of magnitude speedup in execution time, its optical core potentially offers more than 5 order of magnitude speedup compared to state-of-the-art electronic counterparts.

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。

↑