Multi-DNN Inference of Sparse Models on Edge SoCs
AI 摘要
SparseLoom通过模型缝合技术优化边缘设备上多DNN推理系统,提升效率。
主要贡献
- 提出模型缝合技术,创建模型变体
- 设计并实现SparseLoom系统
- 实验证明能降低SLO违规率、提升吞吐量、降低内存开销
方法论
通过重组稀疏模型的子图创建模型变体,无需重新训练,并部署到SoC进行验证。
原文摘要
Modern edge applications increasingly require multi-DNN inference systems to execute tasks on heterogeneous processors, gaining performance from both concurrent execution and from matching each model to the most suited accelerator. However, existing systems support only a single model (or a few sparse variants) per task, which impedes the efficiency of this matching and results in high Service Level Objective violation rates. We introduce model stitching for multi-DNN inference systems, which creates model variants by recombining subgraphs from sparse models without re-training. We present a demonstrator system, SparseLoom, that shows model stitching can be deployed to SoCs. We show experimentally that SparseLoom reduces SLO violation rates by up to 74%, improves throughput by up to 2.31x, and lowers memory overhead by an average of 28% compared to state-of-the-art multi-DNN inference systems.