面向嵌入式FPGA的节能LSTM加速器设计
Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design
AI总结:
本文提出一种面向嵌入式FPGA的参数化LSTM加速器设计,通过优化资源受限环境下的执行速度和能耗,支持通过DSP使用和激活函数实现等参数适应不同场景。
摘要:
长短期记忆网络(LSTMs)是一种重要的深度学习技术,适用于嵌入式设备本地传感器数据流的时序分析。本文提出了一种新的LSTM硬件加速器设计,特别针对资源受限的嵌入式可编程门阵列(FPGAs)进行优化。我们的设计相比相关工作提高了执行速度并降低了能耗。此外,通过多个优化参数(如DSP的使用或激活函数的实现)可适应不同情况。我们提出了关键设计决策并评估了性能。该加速器在实时推理中以32873样本/秒的速度实现了11.89 GOP/s/W的能效。
英文摘要:
Long Short-term Memory Networks (LSTMs) are a vital Deep Learning technique suitable for performing on-device time series analysis on local sensor data streams of embedded devices. In this paper, we propose a new hardware accelerator design for LSTMs specially optimised for resource-scarce embedded Field Programmable Gate Arrays (FPGAs). Our design improves the execution speed and reduces energy consumption compared to related work. Moreover, it can be adapted to different situations using a number of optimisation parameters, such as the usage of DSPs or the implementation of activation functions. We present our key design decisions and evaluate the performance. Our accelerator achieves an energy efficiency of 11.89 GOP/s/W during a real-time inference with 32873 samples/s.
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。