.png){kind=icon}
返回
A high-performance dataflow-centric optimization framework for deep learning inference on the edge
.png){kind=icon}
PRE
AI
DOI：10.1016/j.sysarc.2024.103180.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Edge computing has been emerging as a popular scenario for model inference. However, the inference performance on edge devices (e.g., Multi-Core DSP, FGPA, etc.) suffers from inefficiency due to the lack of highly optimized inference frameworks. Previous model inference frameworks are mainly developed in an operator-centric way, which provides insufficient acceleration to edge-based inference. Besides, the operator-centric framework incurs significant costs for continuous development and maintenance. Targeting the existing drawbacks of operator-centric frameworks, we design Xenos, which can automatically conduct dataflow-centric optimization of the computation graph and accelerate inference in two dimensions. Vertically, Xenos develops operator linking technique to improve data locality by restructuring the inter-operator dataflow. Horizontally, Xenos develops DSP-aware operator split technique to enable higher parallelism across multiple DSP units. Our evaluation demonstrates the effectiveness of vertical and horizontal dataflow optimization, which reduce the inference time by 15.0%-84.9% and 17.9%-89.9% , respectively. Besides, Xenos also outperforms the widely-used TVM by 1.1x-1.9x. Moreover, we extend Xenos to a distributed solution, which we call d-Xenos. d-Xenos employs multiple edge devices to jointly conduct the inference task and achieves a speedup of 3.68x-3.78x compared with the single device.
Keyword:
Edge computing
Model inference
Dataflow-centric
Computation graph
Data locality
期刊
IF:
4.1
论文数:
3.0K
被引数:
4.2K
机构
引用论文
分享收藏The value of the biopsy of the contralateral testis in patients with testicular germ cell cancer: The recent German experience.png)
APMIS
APMISIF0
PREAI
分享收藏
查看更多内容