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 1806.01087cs.DCcs.LG
收藏

稀疏神经网络训练的高度并行FPGA实现

A Highly Parallel FPGA Implementation of Sparse Neural Network Training

University of Southern California(南加州大学)

Sourya Dey, Diandian Chen, Zongyang Li, Souvik Kundu, Kuan-Wen Huang, Keith M. Chugg, Peter A. Beerel

摘要:

我们展示了一个FPGA实现的并行和可重构架构的稀疏神经网络,能够在芯片上的训练和推理。网络连接使用预先确定的结构化稀疏性,通过降低内存和计算要求来显著降低复杂性。该架构使用边缘处理的概念,从而实现高效的流水线和并行化。此外,该设备可以重新配置,以权衡资源利用与训练时间,以适应不同大小的网络和数据集。复杂性降低和易于重新配置的综合效果使芯片上的网络超参数和结构能够得到更大的探索。作为概念证明,我们展示了在Artix-7 FPGA上的实现结果。

英文摘要:

We demonstrate an FPGA implementation of a parallel and reconfigurable architecture for sparse neural networks, capable of on-chip training and inference. The network connectivity uses pre-determined, structured sparsity to significantly reduce complexity by lowering memory and computational requirements. The architecture uses a notion of edge-processing, leading to efficient pipelining and parallelization. Moreover, the device can be reconfigured to trade off resource utilization with training time to fit networks and datasets of varying sizes. The combined effects of complexity reduction and easy reconfigurability enable significantly greater exploration of network hyperparameters and structures on-chip. As proof of concept, we show implementation results on an Artix-7 FPGA.

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。

↑