arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.12565cs.AR
收藏

SigDLA:用于信号处理的深度学习加速器扩展

SigDLA: A Deep Learning Accelerator Extension for Signal Processing

Fangfa Fu, Wenyu Zhang, Zesong Jiang, Zhiyu Zhu, Guoyu Li, Bing Yang, Cheng Liu, Liyi Xiao, Jinxiang Wang, Huawei Li, Xiaowei Li

AI总结:

针对物联网中深度学习与信号处理需求并存但DSP效率低的问题,提出在深度学习加速器上通过可编程数据混洗和可重构计算阵列实现信号处理,显著提升性能并降低能耗。

摘要:

深度学习和信号处理在许多物联网场景(如异常检测)中密切相关,以赋能万物智能。许多物联网处理器利用数字信号处理器(DSP)进行信号处理,并在此基础上构建深度学习框架。由于深度学习通常比信号处理计算密集得多,且缺乏原生硬件支持,深度学习在DSP上的计算效率受到限制。针对这一情况,我们提出了一种相反的策略,即建议在经典深度学习加速器(DLA)之上实现信号处理。我们观察到,诸如FFT中的蝶形运算等不规则数据模式是阻碍信号处理在DLA上部署的主要障碍,因此我们提出了一种可编程数据混洗结构,并将其插入DLA的输入缓冲区和计算阵列之间,从而对不规则数据进行重组,使处理过程变得规则化。通过在线数据混洗,所提出的架构SigDLA能够适应各种信号处理任务,同时不影响深度学习处理。此外,我们构建了一个可重构计算阵列,以适应信号处理和深度学习的不同数据宽度要求。根据我们的实验,与带有定制DSP指令的嵌入式ARM处理器、DSP处理器以及独立的DSP-DLA架构相比,SigDLA分别实现了平均4.4倍、1.4倍和1.52倍的性能加速,以及平均4.82倍、3.27倍和2.15倍的能耗降低,而芯片面积仅比原始DLA增加17%。

英文摘要:

Deep learning and signal processing are closely correlated in many IoT scenarios such as anomaly detection to empower intelligence of things. Many IoT processors utilize digital signal processors (DSPs) for signal processing and build deep learning frameworks on this basis. While deep learning is usually much more computing-intensive than signal processing, the computing efficiency of deep learning on DSPs is limited due to the lack of native hardware support. In this case, we present a contrary strategy and propose to enable signal processing on top of a classical deep learning accelerator (DLA). With the observation that irregular data patterns such as butterfly operations in FFT are the major barrier that hinders the deployment of signal processing on DLAs, we propose a programmable data shuffling fabric and have it inserted between the input buffer and computing array of DLAs such that the irregular data is reorganized and the processing is converted to be regular. With the online data shuffling, the proposed architecture, SigDLA, can adapt to various signal processing tasks without affecting the deep learning processing. Moreover, we build a reconfigurable computing array to suit the various data width requirements of both signal processing and deep learning. According to our experiments, SigDLA achieves an average performance speedup of 4.4$\times$, 1.4$\times$, and 1.52$\times$, and average energy reduction of 4.82$\times$, 3.27$\times$, and 2.15$\times$ compared to an embedded ARM processor with customized DSP instructions, a DSP processor, and an independent DSP-DLA architecture respectively with 17% more chip area over the original DLAs.

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。

↑