Csaba Kiraly

Koustabh Dolui, Csaba Kiraly

Stringent latency requirements in advanced Internet of Things (IoT) applications as well as an increased load on cloud data centers have prompted a move towards a more decentralized approach, bringing storage and processing of IoT data closer to the end-devices through the deployment of multi-purpose IoT gateways. However, the resource constrained nature and diversity of these gateways pose a challenge in developing applications that can be deployed widely. This challenge can be overcome with containerization, a form of lightweight virtualization, bringing support for a wide range of hardware architectures and operating system agnostic deployment of applications on IoT gateways. This paper discusses the architectural aspects of containerization, and studies the suitability of available containerization tools for multi-container deployment in the context of IoT gateways. We present containerization in the context of AGILE, a multi-container and micro-service based open source framework for IoT gateways, developed as part of a Horizon 2020 project. Our study of containerized services to perform common gateway functions like device discovery, data management and cloud integration among others, reveal the advantages of having a containerized environment for IoT gateways with regard to use of base image hierarchies and image layering for in-container and cross-container performance optimizations. We illustrate these results in a set of benchmark experiments in this paper.

Arya Tschand, Arun Tejusve Raghunath Rajan, Sachin Idgunji et al.

Rapid adoption of machine learning (ML) technologies has led to a surge in power consumption across diverse systems, from tiny IoT devices to massive datacenter clusters. Benchmarking the energy efficiency of these systems is crucial for optimization, but presents novel challenges due to the variety of hardware platforms, workload characteristics, and system-level interactions. This paper introduces MLPerf Power, a comprehensive benchmarking methodology with capabilities to evaluate the energy efficiency of ML systems at power levels ranging from microwatts to megawatts. Developed by a consortium of industry professionals from more than 20 organizations, MLPerf Power establishes rules and best practices to ensure comparability across diverse architectures. We use representative workloads from the MLPerf benchmark suite to collect 1,841 reproducible measurements from 60 systems across the entire range of ML deployment scales. Our analysis reveals trade-offs between performance, complexity, and energy efficiency across this wide range of systems, providing actionable insights for designing optimized ML solutions from the smallest edge devices to the largest cloud infrastructures. This work emphasizes the importance of energy efficiency as a key metric in the evaluation and comparison of the ML system, laying the foundation for future research in this critical area. We discuss the implications for developing sustainable AI solutions and standardizing energy efficiency benchmarking for ML systems.

Colby Banbury, Vijay Janapa Reddi, Peter Torelli et al.

Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark for these systems. To meet this need, we present MLPerf Tiny, the first industry-standard benchmark suite for ultra-low-power tiny machine learning systems. The benchmark suite is the collaborative effort of more than 50 organizations from industry and academia and reflects the needs of the community. MLPerf Tiny measures the accuracy, latency, and energy of machine learning inference to properly evaluate the tradeoffs between systems. Additionally, MLPerf Tiny implements a modular design that enables benchmark submitters to show the benefits of their product, regardless of where it falls on the ML deployment stack, in a fair and reproducible manner. The suite features four benchmarks: keyword spotting, visual wake words, image classification, and anomaly detection.