Zhenjiang Li

Jiesong Chen, Jun You, Zhidan Liu et al.

Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins against deadlines and trade them for enhanced model performance or resource savings. However, the ubiquity of Dynamic Voltage and Frequency Scaling (DVFS) renders traditional static profiling invalid in real-world deployments, as inference latency fluctuates with varying processor (CPU and GPU) frequencies. While extensive profiling across frequency combinations is theoretically possible, it is prohibitively expensive, particularly for emerging Small Language Models (SLMs), where variable context lengths explode the profiling up to days. We observe that simple analytic scaling fails to predict these fluctuations due to the complex asynchronous coupling between CPU (kernel launching) and GPU (execution). In this paper, we introduce FLAME to accurately estimate inference latency across frequency combinations. It features a novel layer-wise modeling that quantifies the overlapping parallelism and then aggregates dynamic pipeline bubbles caused by asynchronous processor interactions when extending to the full model. This bottom-up approach ensures generalizability across diverse models from DNNs to SLMs, and its precise modeling allows for profiling a sparse subset of samples, cutting DNN profiling from hours to minutes and SLM profiling from days to mere minutes, while maintaining small estimation errors across frequencies. We further showcase FLAME's utility in a deadline-aware DVFS, outperforming the state-of-the-art approach in both power efficiency and latency guarantees.

Kun Wang, Jiani Cao, Zimu Zhou et al.

Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed in such applications. Existing solutions, such as model compression or cloud offloading, reduce the memory footprint of DNN inference at the cost of decreased model accuracy or autonomy. To avoid these drawbacks, we divide DNN into blocks and swap them in and out in order, such that large DNNs can execute within a small memory budget. Nevertheless, naive swapping on edge AI devices induces significant delays due to the redundant memory operations in the DNN development ecosystem for edge AI devices. To this end, we develop SwapNet, an efficient DNN block swapping middleware for edge AI devices. We systematically eliminate the unnecessary memory operations during block swapping while retaining compatible with the deep learning frameworks, GPU backends, and hardware architectures of edge AI devices. We further showcase the utility of SwapNet via a multi-DNN scheduling scheme. Evaluations on eleven DNN inference tasks in three applications demonstrate that SwapNet achieves almost the same latency as the case with sufficient memory even when DNNs demand 2.32x to 5.81x memory beyond the available budget. The design of SwapNet also provides novel and feasible insights for deploying large language models (LLMs) on edge AI devices in the future.

Lixiang Han, Zhen Xiao, Zhenjiang Li

DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs). The motivation for designing DTMM comes from the emerging field of tiny machine learning (TinyML), which explores extending the reach of machine learning to many low-end IoT devices to achieve ubiquitous intelligence. Due to the weak capability of embedded devices, it is necessary to compress models by pruning enough weights before deploying. Although pruning has been studied extensively on many computing platforms, two key issues with pruning methods are exacerbated on MCUs: models need to be deeply compressed without significantly compromising accuracy, and they should perform efficiently after pruning. Current solutions only achieve one of these objectives, but not both. In this paper, we find that pruned models have great potential for efficient deployment and execution on MCUs. Therefore, we propose DTMM with pruning unit selection, pre-execution pruning optimizations, runtime acceleration, and post-execution low-cost storage to fill the gap for efficient deployment and execution of pruned models. It can be integrated into commercial ML frameworks for practical deployment, and a prototype system has been developed. Extensive experiments on various models show promising gains compared to state-of-the-art methods.

Huanqi Yang, Mingzhe Li, Mingda Han et al.

Embedded IoT system development is crucial for enabling seamless connectivity and functionality across a wide range of applications. However, such a complex process requires cross-domain knowledge of hardware and software and hence often necessitates direct developer involvement, making it labor-intensive, time-consuming, and error-prone. To address this challenge, this paper introduces EmbedGenius, the first fully automated software development platform for general-purpose embedded IoT systems. The key idea is to leverage the reasoning ability of Large Language Models (LLMs) and embedded system expertise to automate the hardware-in-the-loop development process. The main methods include a component-aware library resolution method for addressing hardware dependencies, a library knowledge generation method that injects utility domain knowledge into LLMs, and an auto-programming method that ensures successful deployment. We evaluate EmbedGenius's performance across 71 modules and four mainstream embedded development platforms with over 350 IoT tasks. Experimental results show that EmbedGenius can generate codes with an accuracy of 95.7% and complete tasks with a success rate of 86.5%, surpassing human-in-the-loop baselines by 15.6%--37.7% and 25.5%--53.4%, respectively. We also show EmbedGenius's potential through case studies in environmental monitoring and remote control systems development.

Fei Wang, Zhenjiang Li, Jinsong Han

This paper presents BodyPIN, which is a continuous user authentication system by contactless wireless sensing using commodity Wi-Fi. BodyPIN can track the current user's legal identity throughout a computer system's execution. In case the authentication fails, the consequent accesses will be denied to protect the system. The recent rich wireless-based user identification designs cannot be applied to BodyPIN directly, because they identify a user's various activities, rather than the user herself. The enforced to be performed activities can thus interrupt the user's operations on the system, highly inconvenient and not user-friendly. In this paper, we leverage the bio-electromagnetics domain human model for quantifying the impact of human body on the bypassing Wi-Fi signals and deriving the component that indicates a user's identity. Then we extract suitable Wi-Fi signal features to fully represent such an identity component, based on which we fulfill the continuous user authentication design. We implement a BodyPIN prototype by commodity Wi-Fi NICs without any extra or dedicated wireless hardware. We show that BodyPIN achieves promising authentication performances, which is also lightweight and robust under various practical settings.