.png){kind=icon}
返回
Autotuning LSTM for accelerated execution on Edge
.png){kind=icon}
PRE
AI
DOI：10.1109/ISCAS51556.2021.9401783.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deployment of Deep Neural Networks (DNNs) on edge devices is highly desirable to address user privacy concerns and minimize the turnaround time of AI applications. However, the execution of DNN models on a battery-operated device requires a highly optimized implementation specific to the target hardware. Moreover, as different layers of a DNN exhibit distinct computation and memory characteristics, it is imperative to optimize each layer separately. This is in contrast to the widely deployed library-based approach where all the configurations of DNN operations share the same implementation. In this paper, we address this issue by auto-tuning the implementation of Long Short Term Memory (LSTM) operations which are widely used in sequence based AI applications. To exhaustively search through the space of optimizations and its parameters, we develop a high-level auto-tuning framework based on Halide. We use grid search to find the parameters that lead to minimum runtime and further present TPE based search method to find the near-optimal runtime in a limited number of trials. We observe 2.2 x -3.1x speedup in execution time for LSTM layers used in widely deployed GNMT and DeepSpeech2 models.
Keyword:
Deep Learning
Edge computing
ASR
NLP
Halide
Compiler
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
0
论文数:
87
被引数:
0
机构
引用论文
.png){kind=icon}
分享收藏Nonlinear model predictive energy management of hydrostatic drive transmissions静液压传动系统的非线性模型预测能量管理
PREAI
分享收藏
没有更多内容
没有更多内容